Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.841
Koredianto Usman, Nor Kumalasari Caecar Pratiwi, Nur Ibrahim, Heri Syahrian, V. P. Rahadi
ABSTRAKKomoditas teh berperan strategis terhadap pertumbuhan perekonomian Indonesia, salah satunya dari teh klon Gambung (GMB). Klon GMB memiliki beberapa karakter khas, dengan tingkat kemiripan morfologi yang sangat tinggi. Hal ini berdampak pada proses pengenalan klon GMB dilakukan melalui pengamatan visual oleh tenaga ahli sangat rentan terhadap kesalahan identifikasi. Sehingga, dalam penelitian ini dirancang suatu sistem identifikasi terhadap 11 klon teh seri GMB (GMB-1 hingga GMB-11) dengan menggunakan arsitektur ResNet101. Evaluasi sistem akan dilakukan dengan membandingkan tujuh algoritma optimizer yang berbeda, yaitu; Adam, SGD, RMSProp, AdaGrad, AdaMax, AdaDelta dan Nadam. Hasil pengujian menunjukkan bahwa Adam dan SGD memberikan nilai rata-rata presisi, recall dan F1-score terbaik. Selain itu, Adam memberikan nilai akurasi yang cenderung stabil sejak iterasi pertama. Metode yang diusulkan memberikan tingkat presisi, recall, F1-score sebesar 96% dan akurasi terbaik sebesar 97%.Kata kunci: klasifikasi daun teh, seri Gambung (GMB), CNN, ResNet101 ABSTRACTGambung (GMB) tea is one of the tea commodities that plays a key role in Indonesia's economic development. GMB clones have a number of distinguishing characteristics, including a high degree of morphological similarities. This has an impact on the process of identifying GMB clones through visual observation by experts who are subject to mistakes. In this study, ResNet101 architecture was used to create an identification scheme for 11 tea clones from the GMB series (GMB-1 to GMB-11). System evaluation will be carried out by comparing seven different optimizer; Adam, SGD, RMSProp, AdaGrad, AdaMax, AdaDelta, and Nadam. The test results indicate that Adam and SGD have the highest average accuracy, recall, and f1-score values. Adam also has an accuracy value that has remained consistent since the first iteration. The proposed method provides highest precision, recall, F1-score of 96% and accuracy of 97%.Keywords: tea leaves classification, GMB series, CNN, ResNet101
{"title":"Evaluasi Optimizer pada Residual Network untuk Klasifikasi Klon Teh Seri GMB Berbasis Citra Daun","authors":"Koredianto Usman, Nor Kumalasari Caecar Pratiwi, Nur Ibrahim, Heri Syahrian, V. P. Rahadi","doi":"10.26760/elkomika.v9i4.841","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.841","url":null,"abstract":"ABSTRAKKomoditas teh berperan strategis terhadap pertumbuhan perekonomian Indonesia, salah satunya dari teh klon Gambung (GMB). Klon GMB memiliki beberapa karakter khas, dengan tingkat kemiripan morfologi yang sangat tinggi. Hal ini berdampak pada proses pengenalan klon GMB dilakukan melalui pengamatan visual oleh tenaga ahli sangat rentan terhadap kesalahan identifikasi. Sehingga, dalam penelitian ini dirancang suatu sistem identifikasi terhadap 11 klon teh seri GMB (GMB-1 hingga GMB-11) dengan menggunakan arsitektur ResNet101. Evaluasi sistem akan dilakukan dengan membandingkan tujuh algoritma optimizer yang berbeda, yaitu; Adam, SGD, RMSProp, AdaGrad, AdaMax, AdaDelta dan Nadam. Hasil pengujian menunjukkan bahwa Adam dan SGD memberikan nilai rata-rata presisi, recall dan F1-score terbaik. Selain itu, Adam memberikan nilai akurasi yang cenderung stabil sejak iterasi pertama. Metode yang diusulkan memberikan tingkat presisi, recall, F1-score sebesar 96% dan akurasi terbaik sebesar 97%.Kata kunci: klasifikasi daun teh, seri Gambung (GMB), CNN, ResNet101 ABSTRACTGambung (GMB) tea is one of the tea commodities that plays a key role in Indonesia's economic development. GMB clones have a number of distinguishing characteristics, including a high degree of morphological similarities. This has an impact on the process of identifying GMB clones through visual observation by experts who are subject to mistakes. In this study, ResNet101 architecture was used to create an identification scheme for 11 tea clones from the GMB series (GMB-1 to GMB-11). System evaluation will be carried out by comparing seven different optimizer; Adam, SGD, RMSProp, AdaGrad, AdaMax, AdaDelta, and Nadam. The test results indicate that Adam and SGD have the highest average accuracy, recall, and f1-score values. Adam also has an accuracy value that has remained consistent since the first iteration. The proposed method provides highest precision, recall, F1-score of 96% and accuracy of 97%.Keywords: tea leaves classification, GMB series, CNN, ResNet101","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131576352","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.923
M. Arrofiq, Lukman Sidiq Nugroho, Fahmizal Fahmizal, E. Apriaskar
ABSTRAKMakalah ini memberikan analisis perbandingan antara teknik kendali klasik yaitu kendali PID dengan teknik kendali modern pada sistem Eddy current brakes dinamometer. Eddy current brakes merupakan sistem pengereman modern yang membutuhkan sebuah sistem kendali untuk menunjang kinerja pengereman. Selama ini kendali PID lebih sering digunakan, namun di beberapa kondisi dinilai kurang optimal. Dengan demikian, diperlukan pengembangan kendali yang modern dan optimal yaitu full state feedback Linear Quadratic Regulator (LQR). Perbandingan respon waktu pengereman disimulasikan menggunakan Matlab/Simulink. Hasil simulasi menunjukkan respon waktu pengereman pada kendali LQR lebih baik dibandingkan dengan kendali PID, dengan Ts = 2.12 detik, Tr = 1.18 detik, dan tanpa overshoot. Adapun kendali PID, meskipun menghasilkan Ts = 0.27 detik dan Tr = 0.18 detik, namun demikian masih terdapat overshoot sebesar 0.7%.Kata kunci: Eddy brakes, PID, LQR, Matlab ABSTRACTThis paper provides a comparative analysis between PID control as a classical control technique and modern control technique in the dinamometer Eddy current brakes system. Eddy current brakes is a modern braking system that requires a control system to support the braking performance. PID control is often used to be implemented but in some conditions it is less optimal. Therefore, it is necessary to develop a modern and optimal control, such as a full state feedback Linear Quadratic Regulator (LQR). The comparison of the braking time responses were simulated using Matlab/Simulink. The simulation results show that the response of LQR control is better than the PID, with Ts = 2.12 seconds, Tr = 1.18 seconds, and without overshoot. On the other side, PID control, although having Ts = 0.27 seconds and Tr = 0.18 seconds, there is still an overshoot about 0.7%.Keywords: Eddy brakes, PID, LQR, Matlab
{"title":"Sistem Kendali Eddy Current Brakes Dinamometer menggunakan Linear Quadratic Regulator (LQR)","authors":"M. Arrofiq, Lukman Sidiq Nugroho, Fahmizal Fahmizal, E. Apriaskar","doi":"10.26760/elkomika.v9i4.923","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.923","url":null,"abstract":"ABSTRAKMakalah ini memberikan analisis perbandingan antara teknik kendali klasik yaitu kendali PID dengan teknik kendali modern pada sistem Eddy current brakes dinamometer. Eddy current brakes merupakan sistem pengereman modern yang membutuhkan sebuah sistem kendali untuk menunjang kinerja pengereman. Selama ini kendali PID lebih sering digunakan, namun di beberapa kondisi dinilai kurang optimal. Dengan demikian, diperlukan pengembangan kendali yang modern dan optimal yaitu full state feedback Linear Quadratic Regulator (LQR). Perbandingan respon waktu pengereman disimulasikan menggunakan Matlab/Simulink. Hasil simulasi menunjukkan respon waktu pengereman pada kendali LQR lebih baik dibandingkan dengan kendali PID, dengan Ts = 2.12 detik, Tr = 1.18 detik, dan tanpa overshoot. Adapun kendali PID, meskipun menghasilkan Ts = 0.27 detik dan Tr = 0.18 detik, namun demikian masih terdapat overshoot sebesar 0.7%.Kata kunci: Eddy brakes, PID, LQR, Matlab ABSTRACTThis paper provides a comparative analysis between PID control as a classical control technique and modern control technique in the dinamometer Eddy current brakes system. Eddy current brakes is a modern braking system that requires a control system to support the braking performance. PID control is often used to be implemented but in some conditions it is less optimal. Therefore, it is necessary to develop a modern and optimal control, such as a full state feedback Linear Quadratic Regulator (LQR). The comparison of the braking time responses were simulated using Matlab/Simulink. The simulation results show that the response of LQR control is better than the PID, with Ts = 2.12 seconds, Tr = 1.18 seconds, and without overshoot. On the other side, PID control, although having Ts = 0.27 seconds and Tr = 0.18 seconds, there is still an overshoot about 0.7%.Keywords: Eddy brakes, PID, LQR, Matlab","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117321297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
ABSTRAKPenyebaran Covid-19 dapat diminimalisir dengan bebeberapa cara diantaranya penyemprotan antiseptik. Tujuan penelitian ini menghasilkan robot yang berguna meminimalisir penyebaran Covid-19 dengan sistem kontrol otomatis menggunakan Arduino Uno R3 serta panel surya yang dikoneksikan dengan sistem IoT (Internet Of Things). Penelitian ini menggunakan metode penelitian yang terdiri dari empat tahapan: 1). Mendesain (merancang) alat, 2). Tahapan pembuatan alat, 3). Tahapan ujicoba alat, 4) Tahapan analisis alat. Ketika ada benda yang berada pada titik atau jarak tertentu maka sensor ultrasonik akan mendeteksinya dan akan mengirimkan sinyal ke mikrokontroler selanjutnya robot akan bekerja kembali seuai perintah dari android. Hasil pengujian saat ada obstacle dengan nilai v= 11,40 Volt di dapat nilai acuan pengukuran dan nilai hasil pengkuruan memiliki nilai rentang error tertinggi pada saat nilai acuan 55 cm dan nilai hasil pengukuran 52 cm. Pengujian RPM pada roda kiri posisi (maju) nilai tertinggi sebesar 40,0 RPM dan roda kanan 39,7 RPM.Kata kunci: Arduino, robot, android, IoT, Covid-19, panel surya ABSTRACTThe spread of Covid-19 can be minimized in several ways, including spraying antiseptics. The purpose of this research is to produce a robot that is useful for minimizing the spread of Covid-19 with an automatic control system using Arduino Uno R3 and solar panels that are connected to the IoT (Internet Of Things) system. This study uses a research method consisting of four stages: 1). Designing (designing) tools, 2). Stages of making tools, 3). Stages of testing tools, 4) Stages of tool analysis. When there is an object that is at a certain point or distance, the ultrasonic sensor will detect it and will send a signal to the microcontroller then the robot will work again according to the command from the android. The test results when there is an obstacle with a value of v = 11.40 Volts the measurement reference value is obtained and the measurement result value has the highest error range value when the reference value is 55 cm and the measurement value is 52 cm. RPM testing on the left wheel position (forward) the highest value of 40.0 RPM and the right wheel 39.7 RPM.Keywords: Arduino, robot, android, IoT, Covid-19, solar panels
ABSTRAKCovid-19防盗系统可减少防盗装置的数量。Covid-19 是一个由 Arduino Uno R3 和 IoT（物联网）系统控制的控制面板组成的机器人。该系统采用的系统模式包括：1）.............Mendesain (merancang) alat, 2).对所有类型的房屋进行评估，3）.4) 分析能力。目前，超声波传感器已被广泛应用于机器人和安卓系统中。目前的障碍物功率 v= 11,40 伏，可用于低速电动滚筒，而低速电动滚筒可在低速电动滚筒 55 厘米和低速电动滚筒 52 厘米时产生误差。在啮合杆（maju）上的转速为每分钟 40.0 转，而在啮合杆上的转速为每分钟 39.7 转。 Kata kunci: Arduino, robot, android, IoT, Covid-19, panel surya ABSTRACTThe spread of Covid-19 can be minimized in several ways, including spraying antiseptics.本研究的目的是生产出一种新的机器人。本研究的目的是利用 Arduino Uno R3 和连接到物联网（Internet Of Things）系统的太阳能电池板，通过自动控制系统制作一个机器人，用于最大限度地减少 Covid-19 的传播。本研究采用的研究方法包括四个阶段：1).设计（设计）工具；2）.制作工具阶段；3）.工具测试阶段；4）工具分析阶段。当有物体在某一点或某一距离时，超声波传感器会检测到它，并向微控制器发送信号，然后机器人会根据安卓的指令重新工作。测试结果表明，当有障碍物存在时，测量参考值为 v = 11.40 伏，当参考值为 55 厘米而测量值为 52 厘米时，测量结果值的误差范围值最大。左轮位置（前进）的转速测试最高值为 40.0 RPM，右轮为 39.7 RPM：Arduino、机器人、安卓、物联网、Covid-19、太阳能电池板
{"title":"Kendali Robot Spray Disinfektan Otomatis","authors":"Yosi Apriani, Wiwin Oktaviani Anwar, Ertati Suarni","doi":"10.26760/elkomika.v9i4.800","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.800","url":null,"abstract":"ABSTRAKPenyebaran Covid-19 dapat diminimalisir dengan bebeberapa cara diantaranya penyemprotan antiseptik. Tujuan penelitian ini menghasilkan robot yang berguna meminimalisir penyebaran Covid-19 dengan sistem kontrol otomatis menggunakan Arduino Uno R3 serta panel surya yang dikoneksikan dengan sistem IoT (Internet Of Things). Penelitian ini menggunakan metode penelitian yang terdiri dari empat tahapan: 1). Mendesain (merancang) alat, 2). Tahapan pembuatan alat, 3). Tahapan ujicoba alat, 4) Tahapan analisis alat. Ketika ada benda yang berada pada titik atau jarak tertentu maka sensor ultrasonik akan mendeteksinya dan akan mengirimkan sinyal ke mikrokontroler selanjutnya robot akan bekerja kembali seuai perintah dari android. Hasil pengujian saat ada obstacle dengan nilai v= 11,40 Volt di dapat nilai acuan pengukuran dan nilai hasil pengkuruan memiliki nilai rentang error tertinggi pada saat nilai acuan 55 cm dan nilai hasil pengukuran 52 cm. Pengujian RPM pada roda kiri posisi (maju) nilai tertinggi sebesar 40,0 RPM dan roda kanan 39,7 RPM.Kata kunci: Arduino, robot, android, IoT, Covid-19, panel surya ABSTRACTThe spread of Covid-19 can be minimized in several ways, including spraying antiseptics. The purpose of this research is to produce a robot that is useful for minimizing the spread of Covid-19 with an automatic control system using Arduino Uno R3 and solar panels that are connected to the IoT (Internet Of Things) system. This study uses a research method consisting of four stages: 1). Designing (designing) tools, 2). Stages of making tools, 3). Stages of testing tools, 4) Stages of tool analysis. When there is an object that is at a certain point or distance, the ultrasonic sensor will detect it and will send a signal to the microcontroller then the robot will work again according to the command from the android. The test results when there is an obstacle with a value of v = 11.40 Volts the measurement reference value is obtained and the measurement result value has the highest error range value when the reference value is 55 cm and the measurement value is 52 cm. RPM testing on the left wheel position (forward) the highest value of 40.0 RPM and the right wheel 39.7 RPM.Keywords: Arduino, robot, android, IoT, Covid-19, solar panels","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129174012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.867
I. Santhiarsa, Komang Alit Kumara Jaya
One of the renewable energy sources that can be used as alternative energy is solar energy. The 3rd generation solar cell technology is Dye Sensitive Solar Cell (DSSC) which can convert sunlight into electricity. Purple leaves are leaves that are scattered in Indonesia which are also economical leaves. In this study, purple leaf shoot extract was used as a sensitizer dye extracted with 96% alcohol with a mixture ratio of 20 grams of purple leaf shoots that had been ground until smooth with 50 ml alcohol, then soaking was carried out with immersion variations of 12, 24, and 36 hours. The purpose of this study was to determine the effect of immersion time on the stress generated by the DSSC. The highest current results were obtained in the 36 hours immersion variation of 0.8 μA. Immersion for 12 hours was 0.6 μA and immersion for 24 hours was 0.7 μA.
{"title":"Immersion Duration Effect of Purple Leaf Extract (Graptophllum Pictum) on DSSC","authors":"I. Santhiarsa, Komang Alit Kumara Jaya","doi":"10.26760/elkomika.v9i4.867","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.867","url":null,"abstract":"One of the renewable energy sources that can be used as alternative energy is solar energy. The 3rd generation solar cell technology is Dye Sensitive Solar Cell (DSSC) which can convert sunlight into electricity. Purple leaves are leaves that are scattered in Indonesia which are also economical leaves. In this study, purple leaf shoot extract was used as a sensitizer dye extracted with 96% alcohol with a mixture ratio of 20 grams of purple leaf shoots that had been ground until smooth with 50 ml alcohol, then soaking was carried out with immersion variations of 12, 24, and 36 hours. The purpose of this study was to determine the effect of immersion time on the stress generated by the DSSC. The highest current results were obtained in the 36 hours immersion variation of 0.8 μA. Immersion for 12 hours was 0.6 μA and immersion for 24 hours was 0.7 μA.","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114253227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.966
Istikmal Istikmal, S. Hadiyoso, I. D. Irawati, A. Irawan
In this paper, we compared the proactive routing protocols Optimized Link State Routing (OLSR) and the reactive routing protocols Ad-hoc on-demand distance vector (AODV) and Dynamic Source Routing (DSR) in shadowing propagation and mobility model on mobile adhoc network (MANET). There are two test scenarios, such as the impact of user movement velocity and variations in user pause time with Random Way Point (RWP) mobility. In user velocity testing, the greater the speed, the throughput performance will decrease, while the delay and Normalized Routing Load (NRL) will increase. The pause time test describes the dynamics of changing network topology. The longer the pause time, the longer the topology changes, as a result, the throughput parameter increases while the end-to-end delay and NRL decrease. The proactive OLSR shows the best performance compared to other protocols based on throughput parameters, while the reactive AODV outperforms for end-to-end delay and NRL parameters.
{"title":"Shadowing and Mobility Effect on Proactive and Reactive Routing Protocol in MANET","authors":"Istikmal Istikmal, S. Hadiyoso, I. D. Irawati, A. Irawan","doi":"10.26760/elkomika.v9i4.966","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.966","url":null,"abstract":"In this paper, we compared the proactive routing protocols Optimized Link State Routing (OLSR) and the reactive routing protocols Ad-hoc on-demand distance vector (AODV) and Dynamic Source Routing (DSR) in shadowing propagation and mobility model on mobile adhoc network (MANET). There are two test scenarios, such as the impact of user movement velocity and variations in user pause time with Random Way Point (RWP) mobility. In user velocity testing, the greater the speed, the throughput performance will decrease, while the delay and Normalized Routing Load (NRL) will increase. The pause time test describes the dynamics of changing network topology. The longer the pause time, the longer the topology changes, as a result, the throughput parameter increases while the end-to-end delay and NRL decrease. The proactive OLSR shows the best performance compared to other protocols based on throughput parameters, while the reactive AODV outperforms for end-to-end delay and NRL parameters.","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131381137","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.878
Reni Dyah Wahyuningrum, Khoirun Ni’amah, S. Larasati
ABSTRAKGenerasi telekomunikasi kelima (5G) diterapkan pada 2021 dengan frekuensi tinggi yang menyebabkan redaman yang besar dibandingkan pita sub-1 GHz. Penelitian ini mengkaji sistem 5G dengan frekuensi operasi 3,3 GHz dan bandwidth 99 MHz berdasarkan spesifikasi 5G dari Cyclic Prefix-Orthogonal Frequency Division Multiplexing (CP-OFDM) numerologi μ = 1 menggunakan parameter lingkungan yang diukur secara langsung di kota Bandung. Penelitian ini menemukan bahwa model kanal 5G dengan pengaruh kelembapan maksimum memiliki power delay profile (PDP) 9 path dengan nilai daya yang lebih kecil dan outage performances (𝑅>𝐶) yang lebih buruk dengan gap sebesar 0,3 dB dibandingkan dengan pengaruh kelembapan minimum. Hasil penelitian menunjukkan bahwa penggunaan convolutional codes dapat membantu menghemat Signal to Noise Ratio (SNR) dengan gap sebesar 3 dB. Hasil dari penelitian ini diharapkan dapat memberikan kontribusi bagi perkembangan komunikasi nirkabel 5G di Indonesia.Kata kunci: 5G, model kanal, convolutional codes, PDP, FER, BER. ABSTRACTThe fifth generation of telecommunications (5G) implemented in 2021, where high frequency which causes a large attenuation compared to the sub-1 GHz band. This research examines a 5G system with an operating frequency of 3.3 GHz and a bandwidth of 99 MHz based on the 5G specification of the Cyclic Prefix - Orthogonal Frequency Division Multiplexing (CP-OFDM) numerology μ = 1 using environmental parameters measured directly in Bandung, Indonesia. This research shows that the 5G channel model under maximum humidity has a 9 power delay profile (PDP) with a smaller power value and worse outage performances (𝑅>𝐶) with a gap of 0.3 dB compared to the effect of minimum humidity. The results showed that the use of convolutional codes can save the Signal to Noise Ratio (SNR) with gap of 3 dB. The results of this research are expected to contribute to the development of 5G wireless communications in Indonesia.Keywords: 5G, channel model, convolutional codes, PDP, FER, BER.
第五代电信(5G)应用于2021年，其频率高，导致比一个子GHz大减重。这项研究评估5G系统操作3.3兆赫频率和带宽99兆赫基于5G的规格Cyclic Prefix-Orthogonal频率分裂Multiplexing (CP-OFDM)命理学μ= 1使用直接在万隆市的环境参数测量。这项研究发现运河5G最大湿度的影响有动力延迟模型简介(PDP) 9 path较小的资源价值和outage performances(𝑅>𝐶)更糟的最低湿度的影响相比,差距高达0.3 dB。研究结果表明，使用联阵编码可以节省3分贝差距的噪声信号(SNR)。本研究的结果预计将有助于印尼5G无线通信的发展。关键词:5G，运河模型，联邦性密码，PDP, FER, BER。字幕翻译:这个研究examines a 5G系统的操作频率。3的兆赫和a的带宽99兆赫5G specification》改编自Cyclic这个前缀了- Orthogonal频率分裂Multiplexing (CP-OFDM) numerologyμ= 1用环境parameters measured直接在印尼万隆,。这个研究节目这5G频道下最高humidity模型有一个9动力延迟低调(PDP) a小功率价值和更糟outage performances(𝑅>𝐶)with a gap的0。3分贝compared to humidity最低之效应。建议使用旋转式密码可以将信号保存为3分贝的平衡。这项研究的结果预计将与印尼5G无线通信的发展相协调。基调:5G，模型通道，联调密码，PDP, FER, BER。
{"title":"Model Kanal 5G dengan Pengaruh Kelembapan pada Frekuensi 3,3 GHz dan Bandwidth 99 MHz Berbasis Convolutional Codes","authors":"Reni Dyah Wahyuningrum, Khoirun Ni’amah, S. Larasati","doi":"10.26760/elkomika.v9i4.878","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.878","url":null,"abstract":"ABSTRAKGenerasi telekomunikasi kelima (5G) diterapkan pada 2021 dengan frekuensi tinggi yang menyebabkan redaman yang besar dibandingkan pita sub-1 GHz. Penelitian ini mengkaji sistem 5G dengan frekuensi operasi 3,3 GHz dan bandwidth 99 MHz berdasarkan spesifikasi 5G dari Cyclic Prefix-Orthogonal Frequency Division Multiplexing (CP-OFDM) numerologi μ = 1 menggunakan parameter lingkungan yang diukur secara langsung di kota Bandung. Penelitian ini menemukan bahwa model kanal 5G dengan pengaruh kelembapan maksimum memiliki power delay profile (PDP) 9 path dengan nilai daya yang lebih kecil dan outage performances (𝑅>𝐶) yang lebih buruk dengan gap sebesar 0,3 dB dibandingkan dengan pengaruh kelembapan minimum. Hasil penelitian menunjukkan bahwa penggunaan convolutional codes dapat membantu menghemat Signal to Noise Ratio (SNR) dengan gap sebesar 3 dB. Hasil dari penelitian ini diharapkan dapat memberikan kontribusi bagi perkembangan komunikasi nirkabel 5G di Indonesia.Kata kunci: 5G, model kanal, convolutional codes, PDP, FER, BER. ABSTRACTThe fifth generation of telecommunications (5G) implemented in 2021, where high frequency which causes a large attenuation compared to the sub-1 GHz band. This research examines a 5G system with an operating frequency of 3.3 GHz and a bandwidth of 99 MHz based on the 5G specification of the Cyclic Prefix - Orthogonal Frequency Division Multiplexing (CP-OFDM) numerology μ = 1 using environmental parameters measured directly in Bandung, Indonesia. This research shows that the 5G channel model under maximum humidity has a 9 power delay profile (PDP) with a smaller power value and worse outage performances (𝑅>𝐶) with a gap of 0.3 dB compared to the effect of minimum humidity. The results showed that the use of convolutional codes can save the Signal to Noise Ratio (SNR) with gap of 3 dB. The results of this research are expected to contribute to the development of 5G wireless communications in Indonesia.Keywords: 5G, channel model, convolutional codes, PDP, FER, BER.","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116207151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.913
Anggoro Dwi Nur Rohman, M. A. Muslim, Bambang Siswojo
ABSTRAKKendali formasi adalah topik penelitian kendali multi-robot, dimana sekelompok robot dapat mencapai formasi tertentu dan mempertahankannya ketika berpindah ke arah yang diinginkan. Salah satu pengembangan kendali formasi adalah kendali formasi berdasarkan jarak dimana setiap individu robot menggunakan informasi jarak antara sesamanya untuk mencapai tujuan formasi. Banyak pengembangan yang dilakukan pada kendali formasi berdasarkan jarak menggunakan model yang sederhana dan membutuhkan pengembangan lebih lanjut untuk penerapan kendali ke model yang lebih nyata. Ketika penerapan kendali formasi berdasarkan jarak, terdapat permasalahan kondisi awal yaitu robot tidak dapat menentukan koordinat tetangganya. Penelitian ini akan mengembangkan algoritma cosinus sebagai solusi untuk kondisi awal kendali formasi berdasarkan jarak. Algoritma cosinus terinspirasi dari rumus segitiga sederhana dan mengharuskan robot melakukan dua langkah saja untuk dapat menemukan koordinat tetangganya. Hasil percobaan simulasi, kendali formasi berdasarkan jarak menggunakan tiga model robot holonomic dan penerapan algoritma cosinus membutuhkan waktu rata-rata 6.5 detik untuk menemukan koordinat tetangganya.Kata kunci: Kendali Formasi, Multi-Robot, Algoritma Cosinus, Mobile Robot. ABSTRACTFormation control is a research topic of multi-robot control, where a group of robots can reach a certain formation and defend it when moving in the desired direction. One of the developments is distance-based where formation goals achieved using the distance between each other only. Many developments are using a simple model and need further development into a realistic model. When applying distance-based, there is a problem in the initial condition, namely that the robot cannot find the coordinates of its neighbors when using only distance. In this work, the cosine algorithm was developed as a solution to the initial conditions which are inspired by a simple triangle formula and need only two steps to find the coordinates. From simulation experiment results, distance-based formation control using three holonomic robot models and the application of the cosine algorithm takes an average of 6.5 seconds to find the coordinates of its neighbors.Keywords: Formation Control, Multi-robot, Cosine Algorithm, Mobile Robot.
编队的抽象控制是一个多机器人控制研究的主题，在这个研究中，一组机器人可以达到特定的形态并保持它们在向一个特定的方向移动时的位置。一种控制阵型的方法是根据每个机器人使用彼此之间的距离来达到队形的目的的距离来控制阵型。许多是通过使用简单的模型对阵型的距离控制进行的发展，需要进一步的发展才能将控制应用到更真实的模型上。当按距离进行控制时，第一个问题是机器人无法确定邻居坐标。本研究将开发cosin算法，以解决基于距离控制形成的初始条件。cosinus算法的灵感来自一个简单的三角形公式，它要求机器人只走两步就能找到它的邻居坐标。模拟实验结果:使用三种全息机型和余弦算法的应用需要6.5秒的时间来定位它的邻居坐标。关键词:多机器人控制，多机器人，余弦算法，移动机器人。abstract控制是一项多机器人控制的研究，其中一组机器人在移动需要时可以接触到稳定的形成和防御。一号developments之用的是distance-based编队目标achieved哪里只有彼此之间的距离。许多developments用一个简单的模型和需要是离开发进入一个现实的模型。当applying distance-based,有一个问题是在《机器人初始条件,namely,以至于不能找到它的邻居当用之coordinates只有远处。在这个工作,cosine算法是美国developed a solution to这部最初条件,这是一个简单的三角公式和需要只有两个步骤找到the coordinates。从模拟结果结果来看，使用三种先进机器人模型和共性算法的应用需要6.5秒的平均时间来找到它的邻居。重点词:形成控制，多机器人，联合算法，移动机器人。
{"title":"Kendali Formasi Mobile Robot berdasarkan Jarak menggunakan Algoritma Cosinus","authors":"Anggoro Dwi Nur Rohman, M. A. Muslim, Bambang Siswojo","doi":"10.26760/elkomika.v9i4.913","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.913","url":null,"abstract":"ABSTRAKKendali formasi adalah topik penelitian kendali multi-robot, dimana sekelompok robot dapat mencapai formasi tertentu dan mempertahankannya ketika berpindah ke arah yang diinginkan. Salah satu pengembangan kendali formasi adalah kendali formasi berdasarkan jarak dimana setiap individu robot menggunakan informasi jarak antara sesamanya untuk mencapai tujuan formasi. Banyak pengembangan yang dilakukan pada kendali formasi berdasarkan jarak menggunakan model yang sederhana dan membutuhkan pengembangan lebih lanjut untuk penerapan kendali ke model yang lebih nyata. Ketika penerapan kendali formasi berdasarkan jarak, terdapat permasalahan kondisi awal yaitu robot tidak dapat menentukan koordinat tetangganya. Penelitian ini akan mengembangkan algoritma cosinus sebagai solusi untuk kondisi awal kendali formasi berdasarkan jarak. Algoritma cosinus terinspirasi dari rumus segitiga sederhana dan mengharuskan robot melakukan dua langkah saja untuk dapat menemukan koordinat tetangganya. Hasil percobaan simulasi, kendali formasi berdasarkan jarak menggunakan tiga model robot holonomic dan penerapan algoritma cosinus membutuhkan waktu rata-rata 6.5 detik untuk menemukan koordinat tetangganya.Kata kunci: Kendali Formasi, Multi-Robot, Algoritma Cosinus, Mobile Robot. ABSTRACTFormation control is a research topic of multi-robot control, where a group of robots can reach a certain formation and defend it when moving in the desired direction. One of the developments is distance-based where formation goals achieved using the distance between each other only. Many developments are using a simple model and need further development into a realistic model. When applying distance-based, there is a problem in the initial condition, namely that the robot cannot find the coordinates of its neighbors when using only distance. In this work, the cosine algorithm was developed as a solution to the initial conditions which are inspired by a simple triangle formula and need only two steps to find the coordinates. From simulation experiment results, distance-based formation control using three holonomic robot models and the application of the cosine algorithm takes an average of 6.5 seconds to find the coordinates of its neighbors.Keywords: Formation Control, Multi-robot, Cosine Algorithm, Mobile Robot.","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126761617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.856
Muhammad Hilmi Faridh, U. S. Zulpratita
In this paper, the detection of sound activity is presented on smartphones in realtime with convolutional neural networks. Reduced computing time is a problem from previous studies. Despite the use of machine learning approaches, there are still many shortcomings from previous research. A log-mel energy spectrogram narrates the sound signal image. Then the sound signal image is inputted into CNN's deep learning to classify the human voice and noise. HiVAD outperformed the percentage of other VAD methods, namely G729B, Sohn, and RF from the test results shown with an average SHR accuracy of 15.89%, 28.98%, 42.13% at 0dB, 8.67%, 16.29% ,17.63% at 5 dB, and 1.35%, 7.72%, 5.14% at 10 dB. In addition, the Multi-threading mechanism enables efficient computing for real-time. This study shows that CNN's architecture on HiVAD significantly improves the accuracy of sound activity detection.
{"title":"HiVAD : A Voice Activity Detection Application Based on Deep Learning","authors":"Muhammad Hilmi Faridh, U. S. Zulpratita","doi":"10.26760/elkomika.v9i4.856","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.856","url":null,"abstract":"In this paper, the detection of sound activity is presented on smartphones in realtime with convolutional neural networks. Reduced computing time is a problem from previous studies. Despite the use of machine learning approaches, there are still many shortcomings from previous research. A log-mel energy spectrogram narrates the sound signal image. Then the sound signal image is inputted into CNN's deep learning to classify the human voice and noise. HiVAD outperformed the percentage of other VAD methods, namely G729B, Sohn, and RF from the test results shown with an average SHR accuracy of 15.89%, 28.98%, 42.13% at 0dB, 8.67%, 16.29% ,17.63% at 5 dB, and 1.35%, 7.72%, 5.14% at 10 dB. In addition, the Multi-threading mechanism enables efficient computing for real-time. This study shows that CNN's architecture on HiVAD significantly improves the accuracy of sound activity detection.","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132765546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.813
Asep Andang, Rendi Priyatna, F. M. S. Nursuwars
ABSTRAKKebutuhan sistem otomasi untuk pekerjaan tentu sangat dituntut untuk menjadi lebih efektif dan efisien seperti halnya pemanfaatan PLC dalam bidang industri untuk menjalankan segala aktifitas menjadi otomatis, terkadang sistem ADC (analog to digital converter) pada PLC itu terbatas, dan harus diberi tambahan ekstensi eksternal yang dijual terpisah di masing-masing vendor. Tentunya harganya juga terkadang lebih mahal dari pada Unit pemrosesnya, hal ini yang sering menjadi sebuah pertimbangan. Contoh nya sistem ADC pada PLC CP1L-E memiliki 2 kanal. Oleh karena itu penelitian ini dilakukan, dengan melakukan perancangan multiplekser dan demultiplekser analog dengan memanfaatkan IC 74HC4067, hasil dari penelitian ini dalam 1 kanal input analog PLC CP1L-E dapat menjadi 16 kanal input dengan waktu pensaklaran direkomendasikan diatas 0,1detik / kanal berdasarkan hasil selisih pembacaan nilai ADC dibandingkan dengan tanpa melalui multiplekser berkisar antara 0,00% sampai 1,969%, dan multiplekser ini direkomendasikan untuk penggunaan sinyal input pada tegangan0 sampai 5 volt.Kata kunci: ADC, Multiplekser,Demultiplekser, IC CD74HC4067, PLC ABSTRACTThe need for automation systems for work is certainly highly demanded to be more effective and efficient as well as the use of PLCs in the industrial sector to carry out all activities automatically, sometimes the ADC (analog to digital converter) system on the PLC is limited, and must be given additional external extensions that are sold separately for each vendor. Of course the price is also sometimes more expensive than the processing unit, this is often a consideration. For example, the ADC system on the CP1L-E PLC has 2 channels. Therefore, this research was carried out, by designing an analog multiplexer and demultiplexer using IC 74HC4067, the results of this study in 1 analog input channel PLC CP1L-E can be 16 input channels with recommended switching times above 0.1 seconds / channel based on the results of the difference. The reading of the ADC value compared to without going through the multiplexer ranges from 0.00% to 1.969%, and this multiplexer is recommended for the use of input signals at a voltage of 0 to 5 volts.Keywords: ADC, Multiplexer, Demultiplexer, IC CD74HC4067, PLC
自动化系统ABSTRAKKebutuhan为了工作当然是一个非常需要更有效和高效利用PLC一样经营活动都为工业自动化领域,有时ADC(模拟到数字转换器)系统的PLC是有限的,必须在每个卖主得到了额外的外部扩展单独出售。当然，价格有时也比处理单元贵，这通常是一个考虑因素。他在PLC cp1 - l - e上的ADC系统有两个频道。因此这个研究,做multiplekser设计和模拟demultiplekser与利用IC 74HC4067运河,这项研究的结果1模拟PLC输入CP1L-E可以随着时间的推移,成为16输入运河pensaklaran 0,1detik -运河上根据推荐结果相比,差距为ADC值读数没有通过multiplekser 0,00%至1,969%不等,这个多视距建议在电压为0到5伏的同时使用输入信号。关键词:ADC, Multiplekser Demultiplekser IC CD74HC4067, PLC为automation ABSTRACTThe需要系统的工作是肯定强烈demanded成为更有效的和efficient as well as境之用的PLCs工业到嘉莉出去的所有活动自动,有时区ADC杂志》(模拟到数字转换器)《PLC系统是有限公司,和一定赐予external措施extensions那就是每出售了separately for供应商。当然，价格有时也比单位的消耗更贵，这是一种考虑。例如，CP1L-E PLC上的ADC系统有2个频道。例如，这项研究被设计成使用IC 74HC4067设计出一种多路复用例和dem路复用例，这项研究在一个输输式通道PLC 74HC4067中得到的结果是，这个研究在一个输输式海峡PLC CP1L-E可以是16个输入频道，以0.1秒的时间为基础，以差异的结果为基础。ADC珍惜读书》无国界compared to要穿过multiplexer ranges从0 . 00%到1.969%之用,和这multiplexer recommended for signals at a输入0到5伏特的电压。键盘:ADC，多路复用器，多路复用器，IC CD74HC4067, PLC
{"title":"Multiplikasi Input Analog pada PLC menggunakan Multiplekser IC74HC4067","authors":"Asep Andang, Rendi Priyatna, F. M. S. Nursuwars","doi":"10.26760/elkomika.v9i4.813","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.813","url":null,"abstract":"ABSTRAKKebutuhan sistem otomasi untuk pekerjaan tentu sangat dituntut untuk menjadi lebih efektif dan efisien seperti halnya pemanfaatan PLC dalam bidang industri untuk menjalankan segala aktifitas menjadi otomatis, terkadang sistem ADC (analog to digital converter) pada PLC itu terbatas, dan harus diberi tambahan ekstensi eksternal yang dijual terpisah di masing-masing vendor. Tentunya harganya juga terkadang lebih mahal dari pada Unit pemrosesnya, hal ini yang sering menjadi sebuah pertimbangan. Contoh nya sistem ADC pada PLC CP1L-E memiliki 2 kanal. Oleh karena itu penelitian ini dilakukan, dengan melakukan perancangan multiplekser dan demultiplekser analog dengan memanfaatkan IC 74HC4067, hasil dari penelitian ini dalam 1 kanal input analog PLC CP1L-E dapat menjadi 16 kanal input dengan waktu pensaklaran direkomendasikan diatas 0,1detik / kanal berdasarkan hasil selisih pembacaan nilai ADC dibandingkan dengan tanpa melalui multiplekser berkisar antara 0,00% sampai 1,969%, dan multiplekser ini direkomendasikan untuk penggunaan sinyal input pada tegangan0 sampai 5 volt.Kata kunci: ADC, Multiplekser,Demultiplekser, IC CD74HC4067, PLC ABSTRACTThe need for automation systems for work is certainly highly demanded to be more effective and efficient as well as the use of PLCs in the industrial sector to carry out all activities automatically, sometimes the ADC (analog to digital converter) system on the PLC is limited, and must be given additional external extensions that are sold separately for each vendor. Of course the price is also sometimes more expensive than the processing unit, this is often a consideration. For example, the ADC system on the CP1L-E PLC has 2 channels. Therefore, this research was carried out, by designing an analog multiplexer and demultiplexer using IC 74HC4067, the results of this study in 1 analog input channel PLC CP1L-E can be 16 input channels with recommended switching times above 0.1 seconds / channel based on the results of the difference. The reading of the ADC value compared to without going through the multiplexer ranges from 0.00% to 1.969%, and this multiplexer is recommended for the use of input signals at a voltage of 0 to 5 volts.Keywords: ADC, Multiplexer, Demultiplexer, IC CD74HC4067, PLC","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125695691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-10DOI: 10.26760/elkomika.v9i4.786
H. Fakhruddin, Handri Toar, Era Purwanto, Hary Oktavianto, Gamar Basuki, R. Apriyanto, Abdillah Aziz Muntashir
ABSTRAKKendali vektor merupakan solusi terbaik dalam kendali motor induksi untuk meningkatkan karakter dinamis dan efisiensinya. Pada penelitian ini, sebuah kendali kecepatan PID dipadukan dengan Adaptive Neuro Fuzzy Inference System (ANFIS) untuk meningkatkan keandalan pada berbagai kecepatan acuan. Metode cerdas Particle Swarm Optimization (PSO) digunakan untuk optimasi dataset ANFIS. Pengujian keandalan dilakukan dengan membandingkan PID konvensional dengan PID-ANFIS pada motor induksi 3 fase berdaya 2HP. Validasi penelitian dilakukan melalui simulasi di platform LabView. PID-ANFIS membuktikan hasil yang jauh lebih baik dari kendali PID konvensional pada berbagai kecepatan acuan. Pemilihan rise time tercepat sebagai fungsi fitness menghasilkan kendali yang memiliki dead time dan rise time 1.5x lebih cepat. PID-ANFIS berhasil menghilangkan undershoot dan osilasi steady state ketika uji kecepatan tinggi.Kata kunci: Kendali Vektor, Adaptive Neuro Fuzzy Inference System, Particle Swarm Optimization, LabView ABSTRACTVector control is the best solution in induction motor control to enhance its dynamic character and efficiency. In this research, a PID speed controller is combined with the Adaptive Neuro-Fuzzy Inference System (ANFIS) to enhance reliability at various reference speeds. The intelligent method Particle Swarm Optimization (PSO) is used to optimize the ANFIS dataset. Reliability testing is done by comparing conventional PID with PID-ANFIS on a 2HP 3-phase induction motor. The research validation was carried out through a simulation on the LabView platform. The PID-ANFIS proved significantly better results than conventional PID control at a wide range of reference speeds. Selection of the fastest rise time as a fitness function results in a control that has a dead time and a rise time of 1.5x faster. PID-ANFIS successfully negates undershoot and steadystate oscillations during high-speed tests.Keywords: Vector Control, Adaptive Neuro Fuzzy Inference System, Particle Swarm Optimization, LabView
{"title":"Strategi Implementasi Adaptive Neuro Fuzzy Inference System (ANFIS) pada Kendali Motor Induksi 3 Fase Metode Vektor-Tidak Langsung","authors":"H. Fakhruddin, Handri Toar, Era Purwanto, Hary Oktavianto, Gamar Basuki, R. Apriyanto, Abdillah Aziz Muntashir","doi":"10.26760/elkomika.v9i4.786","DOIUrl":"https://doi.org/10.26760/elkomika.v9i4.786","url":null,"abstract":"ABSTRAKKendali vektor merupakan solusi terbaik dalam kendali motor induksi untuk meningkatkan karakter dinamis dan efisiensinya. Pada penelitian ini, sebuah kendali kecepatan PID dipadukan dengan Adaptive Neuro Fuzzy Inference System (ANFIS) untuk meningkatkan keandalan pada berbagai kecepatan acuan. Metode cerdas Particle Swarm Optimization (PSO) digunakan untuk optimasi dataset ANFIS. Pengujian keandalan dilakukan dengan membandingkan PID konvensional dengan PID-ANFIS pada motor induksi 3 fase berdaya 2HP. Validasi penelitian dilakukan melalui simulasi di platform LabView. PID-ANFIS membuktikan hasil yang jauh lebih baik dari kendali PID konvensional pada berbagai kecepatan acuan. Pemilihan rise time tercepat sebagai fungsi fitness menghasilkan kendali yang memiliki dead time dan rise time 1.5x lebih cepat. PID-ANFIS berhasil menghilangkan undershoot dan osilasi steady state ketika uji kecepatan tinggi.Kata kunci: Kendali Vektor, Adaptive Neuro Fuzzy Inference System, Particle Swarm Optimization, LabView ABSTRACTVector control is the best solution in induction motor control to enhance its dynamic character and efficiency. In this research, a PID speed controller is combined with the Adaptive Neuro-Fuzzy Inference System (ANFIS) to enhance reliability at various reference speeds. The intelligent method Particle Swarm Optimization (PSO) is used to optimize the ANFIS dataset. Reliability testing is done by comparing conventional PID with PID-ANFIS on a 2HP 3-phase induction motor. The research validation was carried out through a simulation on the LabView platform. The PID-ANFIS proved significantly better results than conventional PID control at a wide range of reference speeds. Selection of the fastest rise time as a fitness function results in a control that has a dead time and a rise time of 1.5x faster. PID-ANFIS successfully negates undershoot and steadystate oscillations during high-speed tests.Keywords: Vector Control, Adaptive Neuro Fuzzy Inference System, Particle Swarm Optimization, LabView","PeriodicalId":344430,"journal":{"name":"ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127075994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：