In 21st century, mass production and industrial machines are required to operate for 24 hours. The swift response is essential in case of emergency or predicted failure happening in the manufacturing line. The complication of a system obscures the indication of problems. Thus, developing a specific program that can detect machine's status and notify problems is the first major step to decrease downtime. Furthermore, the highly efficient predicted notification can be archived by Machine learning. In this paper, a notification software to identify problem and monitor the system is developed based on Neural Network. The Neural Network data collection is obtained from sensors, which measured the linear acceleration and angular speed of the machine. 323 datasets, categorized into 11 states, are collected from one testing machine. Training and testing sets are randomly separated by 80/20 percent respectively. To evaluate the best prediction model, input datasets are ranked from the highest to lowest frequency and chosen in 3 situations, using all input datasets, using only the top 2 up to 10 points of the highest frequency, and using only the top 2 up to 10 points of the highest and lowest frequency. Moreover, the Neural Network setups are analyzed for each situation by the following configurations: 1 to 3 hidden layers with 100 to 500 nodes. In conclusion, the best evaluation result of 88.52 % is achieved by using the top 9 points of the highest and the lowest frequency, training with 3 hidden layers and 400 or 500 nodes of neural network.
{"title":"Notifying problems of a machine by using Machine Learning","authors":"Supod Kaewkorn, C. Joochim, Siraphop Prasertprasasna, Chanon Leartrussameejit, Haem Kuhataparuks, Alisa Kunapinun","doi":"10.1109/RI2C48728.2019.8999912","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999912","url":null,"abstract":"In 21st century, mass production and industrial machines are required to operate for 24 hours. The swift response is essential in case of emergency or predicted failure happening in the manufacturing line. The complication of a system obscures the indication of problems. Thus, developing a specific program that can detect machine's status and notify problems is the first major step to decrease downtime. Furthermore, the highly efficient predicted notification can be archived by Machine learning. In this paper, a notification software to identify problem and monitor the system is developed based on Neural Network. The Neural Network data collection is obtained from sensors, which measured the linear acceleration and angular speed of the machine. 323 datasets, categorized into 11 states, are collected from one testing machine. Training and testing sets are randomly separated by 80/20 percent respectively. To evaluate the best prediction model, input datasets are ranked from the highest to lowest frequency and chosen in 3 situations, using all input datasets, using only the top 2 up to 10 points of the highest frequency, and using only the top 2 up to 10 points of the highest and lowest frequency. Moreover, the Neural Network setups are analyzed for each situation by the following configurations: 1 to 3 hidden layers with 100 to 500 nodes. In conclusion, the best evaluation result of 88.52 % is achieved by using the top 9 points of the highest and the lowest frequency, training with 3 hidden layers and 400 or 500 nodes of neural network.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124043338","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 : 2019-12-01DOI: 10.1109/RI2C48728.2019.8999897
N. Meitei, R. Mehta, Kanan Wahengbam
This finding will enable precise illumination control of a focus area of any working plane or environment through a wireless sensor to ensure visual comfort. The proposed design will give user the provision to control illumination in the form of duty cycle through a keypad, which can vary from 0 to 100 percent, thereby giving the opportunity to find the exact illumination as per IES recommendation by analyzing the value of lux shown on the LCD display which is actually the illumination received on the focus area of the working plane. Based on this concept, programs were written, verified and uploaded through arduino IDE. Two arduino microcontrollers were used to guide all the integrated hardwires.
{"title":"Meticulous Illumination Controller for Visual Comfort Using Wireless Sensor","authors":"N. Meitei, R. Mehta, Kanan Wahengbam","doi":"10.1109/RI2C48728.2019.8999897","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999897","url":null,"abstract":"This finding will enable precise illumination control of a focus area of any working plane or environment through a wireless sensor to ensure visual comfort. The proposed design will give user the provision to control illumination in the form of duty cycle through a keypad, which can vary from 0 to 100 percent, thereby giving the opportunity to find the exact illumination as per IES recommendation by analyzing the value of lux shown on the LCD display which is actually the illumination received on the focus area of the working plane. Based on this concept, programs were written, verified and uploaded through arduino IDE. Two arduino microcontrollers were used to guide all the integrated hardwires.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123408708","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}
The shift to cloud computing has affected the future of software engineering in several ways i.e., multilateral software development, scalability, and new technology stack such as an open-source software, plus infrastructure as code such as container, serverless architecture and software defined network (SDN). In order to support the cloud project delivery for government organizations, requirements engineering (RE) is a crucial step in software engineering that determines whether a project will be successful or result in a failure. RE steps include requirement elicitation, requirement analysis, requirement specification and requirement validation. Data is collected by semi-structured interview from the providers and the users of cloud services in 11 Thai government organizations, and from cloud service provider for meeting enterprise requirements and user requirements. The results reveal nine key issues that affect cloud project delivery: (1) lack of trust with external cloud service provider by generation X and baby boomer (2) lack of transparency as regards the legal agreement about the cloud user's personal data protection responsibility by cloud service provider, (3) the issues of reliability, security and service level agreements (4) lack of knowledge and lack of understanding of cloud technology (5) required training and a learning by doing (6) the policy to use government cloud services instead of developing their own cloud, (7) older people at top-level tend to resist cloud technology, (8) people in general lack of knowledge and understanding of cloud technology (9) problems about pricing model, it's impact on 23 cloud requirements (functional and non-functional) as well as factors that involved in RE phases. Based on these results this paper presents a Conceptual Model of Requirement Engineering for Cloud Project Delivery in Thai Government Organizations.
{"title":"A Conceptual Model of Requirement Engineering in Cloud Project Delivery for Thai Government Organizations","authors":"Ajchareeya Chaipunyathat, Nalinpat Porrawatpreyakorn, Siranee Nuchitprasitchai, Kanchana Viriyapant","doi":"10.1109/RI2C48728.2019.8999923","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999923","url":null,"abstract":"The shift to cloud computing has affected the future of software engineering in several ways i.e., multilateral software development, scalability, and new technology stack such as an open-source software, plus infrastructure as code such as container, serverless architecture and software defined network (SDN). In order to support the cloud project delivery for government organizations, requirements engineering (RE) is a crucial step in software engineering that determines whether a project will be successful or result in a failure. RE steps include requirement elicitation, requirement analysis, requirement specification and requirement validation. Data is collected by semi-structured interview from the providers and the users of cloud services in 11 Thai government organizations, and from cloud service provider for meeting enterprise requirements and user requirements. The results reveal nine key issues that affect cloud project delivery: (1) lack of trust with external cloud service provider by generation X and baby boomer (2) lack of transparency as regards the legal agreement about the cloud user's personal data protection responsibility by cloud service provider, (3) the issues of reliability, security and service level agreements (4) lack of knowledge and lack of understanding of cloud technology (5) required training and a learning by doing (6) the policy to use government cloud services instead of developing their own cloud, (7) older people at top-level tend to resist cloud technology, (8) people in general lack of knowledge and understanding of cloud technology (9) problems about pricing model, it's impact on 23 cloud requirements (functional and non-functional) as well as factors that involved in RE phases. Based on these results this paper presents a Conceptual Model of Requirement Engineering for Cloud Project Delivery in Thai Government Organizations.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128641085","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 : 2019-12-01DOI: 10.1109/RI2C48728.2019.8999886
Pongsathorn Chomdee, A. Boonpoonga, P. Akkaraekthalin
This paper presents a method of rail defect detection. The method is based on a radar target identification system by transmitting a short pulse to the rail and receiving the reflected one to characterize the rail property. A matrix pencil method is employed to extract poles used as a signature of individual railway. Simulations are conducted to investigate the performance of the proposed method used to identify the rail detect. Results in term of time-domain response and extracted poles are shown to verify that the radar target identification can distinguish the normal rail out of the defected rail.
{"title":"Rail Defect Detection using Matrix Pencil Method-Based Radar Target Identification","authors":"Pongsathorn Chomdee, A. Boonpoonga, P. Akkaraekthalin","doi":"10.1109/RI2C48728.2019.8999886","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999886","url":null,"abstract":"This paper presents a method of rail defect detection. The method is based on a radar target identification system by transmitting a short pulse to the rail and receiving the reflected one to characterize the rail property. A matrix pencil method is employed to extract poles used as a signature of individual railway. Simulations are conducted to investigate the performance of the proposed method used to identify the rail detect. Results in term of time-domain response and extracted poles are shown to verify that the radar target identification can distinguish the normal rail out of the defected rail.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121058448","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 : 2019-12-01DOI: 10.1109/RI2C48728.2019.8999937
Chutiwan Boonarchatong, M. Ketcham
The overall bedridden patients increased by 40 million in this year, however there aren't enough care workers to service them. This research aims to design the prototype workspace of anthropomorphic robot arm for self-service patient, the elderly, and those that have disability. The robotic arm workspace is designed based on kinematics theory. The structure of the robot arm compounds with 6 servo motors, 6 DOF, with 4 links. The peripheral is commanded by computer program, Arduino, via GUI. The robot arm performance was measured by time series and users' satisfaction. The result shows that testers gained the skill to command the robot arm when they repeated the test many times. They were satisfied with the prototype because the prototype would help them to service themselves.
{"title":"The Prototype of Anthropomorphic Robot Arm Work Space Design for Self-reliant Patients","authors":"Chutiwan Boonarchatong, M. Ketcham","doi":"10.1109/RI2C48728.2019.8999937","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999937","url":null,"abstract":"The overall bedridden patients increased by 40 million in this year, however there aren't enough care workers to service them. This research aims to design the prototype workspace of anthropomorphic robot arm for self-service patient, the elderly, and those that have disability. The robotic arm workspace is designed based on kinematics theory. The structure of the robot arm compounds with 6 servo motors, 6 DOF, with 4 links. The peripheral is commanded by computer program, Arduino, via GUI. The robot arm performance was measured by time series and users' satisfaction. The result shows that testers gained the skill to command the robot arm when they repeated the test many times. They were satisfied with the prototype because the prototype would help them to service themselves.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116281428","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 : 2019-12-01DOI: 10.1109/ri2c48728.2019.8999925
{"title":"Call for Papers: RI2C 2019","authors":"","doi":"10.1109/ri2c48728.2019.8999925","DOIUrl":"https://doi.org/10.1109/ri2c48728.2019.8999925","url":null,"abstract":"","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126603435","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 : 2019-12-01DOI: 10.1109/RI2C48728.2019.8999884
P. Noiying, P. Janchaichanakun, Ekkamol Boonyapalanant
This research aims to 1) Create a commutator smooth surface measurement by using the laser displacement sensor. 2) Automatically correct and store data. 3) Develop a computer program for measuring the surface of commutator. The research methods are divided into two stages. First, design a commutator smooth surface measurement by using the laser displacement sensor and built base station in order to adjust position of the laser displacement sensor. Additionally, we create a set of motor-drive automation to stabilize the commutator speed by installing the encoder Incremental to obtain the position and angle. Second, we develop a computer program for measuring the commutator surface in real-time and compare our results of the smooth commutator surface in a polar form with commutator surface reference graphs. The results showed that, our commutator surface measuring set effectively measured the smooth surface and fault models. Moreover, our design program effectively displayed in linear graphs and polar graphs the damaged or worn surface of the commutator.
{"title":"The Instrumentation of Surface Uniformity Commutator Control Spindle Automatically","authors":"P. Noiying, P. Janchaichanakun, Ekkamol Boonyapalanant","doi":"10.1109/RI2C48728.2019.8999884","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999884","url":null,"abstract":"This research aims to 1) Create a commutator smooth surface measurement by using the laser displacement sensor. 2) Automatically correct and store data. 3) Develop a computer program for measuring the surface of commutator. The research methods are divided into two stages. First, design a commutator smooth surface measurement by using the laser displacement sensor and built base station in order to adjust position of the laser displacement sensor. Additionally, we create a set of motor-drive automation to stabilize the commutator speed by installing the encoder Incremental to obtain the position and angle. Second, we develop a computer program for measuring the commutator surface in real-time and compare our results of the smooth commutator surface in a polar form with commutator surface reference graphs. The results showed that, our commutator surface measuring set effectively measured the smooth surface and fault models. Moreover, our design program effectively displayed in linear graphs and polar graphs the damaged or worn surface of the commutator.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126661234","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 : 2019-12-01DOI: 10.1109/RI2C48728.2019.8999901
C. Joochim, Supod Kaewkorn, Alisa Kunapinun
The vision system is always applied to industrial in many applications. There are many applications that integrated with industrial robots by using vision system such as detecting position, and matching objects. Therefore, it is necessary to transfer from camera position in pixel coordination to robot position in world coordination. After calibration, robot can know the objects position and orientation, which be detected from vision system. In basic camera calibration to robot coordination, it needs at least 3 points of camera and robot positions. However, the accuracy from the algorithm will be low from human error, internal hardware such as intrinsic, extrinsic camera parameters, and installation error (Ex: tilt etc.). Thus, origianally, the process of calibration must have 3 steps, intrinsic camera calibration, extrinsic camera calibration and camera to robot base calibration. Moreover, the basic calibration cannot calculate TCP offset (Tool coordinate point offset). If tool has been installed to robot, the robot must change final position from MIF (Mechanical interface) to TIF (Tool interface). Thus, user must calculate the TCP offset before calculate camera calibration. However, there are many processes of calibration. In this paper, it will show the 9 points calibration's algorithm, which be applied from other applications of vision system. The paper will explain step-by-step how to solve the equation and how to apply with SCARA robot. Moreover, the paper will explain not only camera calibration, but also SCARA robot and TCP offset calculation.
{"title":"The 9 Points Calibration Using SCARA Robot","authors":"C. Joochim, Supod Kaewkorn, Alisa Kunapinun","doi":"10.1109/RI2C48728.2019.8999901","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999901","url":null,"abstract":"The vision system is always applied to industrial in many applications. There are many applications that integrated with industrial robots by using vision system such as detecting position, and matching objects. Therefore, it is necessary to transfer from camera position in pixel coordination to robot position in world coordination. After calibration, robot can know the objects position and orientation, which be detected from vision system. In basic camera calibration to robot coordination, it needs at least 3 points of camera and robot positions. However, the accuracy from the algorithm will be low from human error, internal hardware such as intrinsic, extrinsic camera parameters, and installation error (Ex: tilt etc.). Thus, origianally, the process of calibration must have 3 steps, intrinsic camera calibration, extrinsic camera calibration and camera to robot base calibration. Moreover, the basic calibration cannot calculate TCP offset (Tool coordinate point offset). If tool has been installed to robot, the robot must change final position from MIF (Mechanical interface) to TIF (Tool interface). Thus, user must calculate the TCP offset before calculate camera calibration. However, there are many processes of calibration. In this paper, it will show the 9 points calibration's algorithm, which be applied from other applications of vision system. The paper will explain step-by-step how to solve the equation and how to apply with SCARA robot. Moreover, the paper will explain not only camera calibration, but also SCARA robot and TCP offset calculation.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130878220","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 : 2019-12-01DOI: 10.1109/RI2C48728.2019.8999956
P. Mungporn, S. Khomfoi, P. Kumam, Z. Shah, P. Burikham, Chaiyut Kaewprapha, B. Yodwong, P. Thounthong, C. Ekkaravarodome, A. Bilsalam, B. Nahid-Mobarakeh, S. Pierfederici, D. Guilbert, N. Bizon
This paper studys a multi-phase boost converter for fuel cell (FC) applications. An original control law based on the Hamiltonian energy control principle for dc microgrid is considered. Using the port-controlled Hamiltonian property, we propose simple solutions to the system performance and stabilization problems when the interaction between power sources and constant power loads (CPLs). To corroborate the proposed control law, a prototype FC power converter (2.5-kW two-phase boost converter) is implemented in the laboratory. The Methanol FC system includes a fuel reformer that converts methanol and water liquid fuel into hydrogen gas to polymer electrolyte membrane FC (PEMFC) stack (2.5-kW, 50 V). The proposed control approach is realized with a digital estimate in a dSPACE MicroLabBox controller card. The experimental and simulation results verify that this is a good control scheme during constant power load cycles.
{"title":"Study of Hamiltonian Energy Control of Multiphase Interleaved Fuel Cell Boost Converter","authors":"P. Mungporn, S. Khomfoi, P. Kumam, Z. Shah, P. Burikham, Chaiyut Kaewprapha, B. Yodwong, P. Thounthong, C. Ekkaravarodome, A. Bilsalam, B. Nahid-Mobarakeh, S. Pierfederici, D. Guilbert, N. Bizon","doi":"10.1109/RI2C48728.2019.8999956","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999956","url":null,"abstract":"This paper studys a multi-phase boost converter for fuel cell (FC) applications. An original control law based on the Hamiltonian energy control principle for dc microgrid is considered. Using the port-controlled Hamiltonian property, we propose simple solutions to the system performance and stabilization problems when the interaction between power sources and constant power loads (CPLs). To corroborate the proposed control law, a prototype FC power converter (2.5-kW two-phase boost converter) is implemented in the laboratory. The Methanol FC system includes a fuel reformer that converts methanol and water liquid fuel into hydrogen gas to polymer electrolyte membrane FC (PEMFC) stack (2.5-kW, 50 V). The proposed control approach is realized with a digital estimate in a dSPACE MicroLabBox controller card. The experimental and simulation results verify that this is a good control scheme during constant power load cycles.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"293 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132169519","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 : 2019-12-01DOI: 10.1109/RI2C48728.2019.8999895
Chayathach Phuaksaman, Patcharapong Penpakkol
The expansion of the online retailing platform leads to the growth of logistic business. The integration between the main two activities in logistic decision which are inventory control and transportation management. The idea here is to improve overall efficiency in term of total cost of the logistic system. This research studies a multi-retailer multi-depot distribution system with multiple items. Decisions in this system include replenishment quantities of items at each retailer and its corresponding delivery route. The main objective is to provide the minimum total inventory and routing cost during considered time horizon. Three heuristic algorithms, SIOH AIRRH and AIRVH, are proposed to solve this problem. The performances of the heuristics are tested by comparing to solution obtained by IBM ILOG CPLEX 12.6 for small-sized problem and Lot-for-Lot policy for medium and large-sized problem. The computational results show that the proposed heuristics can achieve the optimal solution in small-sized problem. Moreover the heuristic AIRVH show improvement from Lot-for-Lot policy between 15-25% in average for the medium and large-sized problem.
{"title":"Heuristics for Multi-Depot Inventory Routing Problem","authors":"Chayathach Phuaksaman, Patcharapong Penpakkol","doi":"10.1109/RI2C48728.2019.8999895","DOIUrl":"https://doi.org/10.1109/RI2C48728.2019.8999895","url":null,"abstract":"The expansion of the online retailing platform leads to the growth of logistic business. The integration between the main two activities in logistic decision which are inventory control and transportation management. The idea here is to improve overall efficiency in term of total cost of the logistic system. This research studies a multi-retailer multi-depot distribution system with multiple items. Decisions in this system include replenishment quantities of items at each retailer and its corresponding delivery route. The main objective is to provide the minimum total inventory and routing cost during considered time horizon. Three heuristic algorithms, SIOH AIRRH and AIRVH, are proposed to solve this problem. The performances of the heuristics are tested by comparing to solution obtained by IBM ILOG CPLEX 12.6 for small-sized problem and Lot-for-Lot policy for medium and large-sized problem. The computational results show that the proposed heuristics can achieve the optimal solution in small-sized problem. Moreover the heuristic AIRVH show improvement from Lot-for-Lot policy between 15-25% in average for the medium and large-sized problem.","PeriodicalId":404700,"journal":{"name":"2019 Research, Invention, and Innovation Congress (RI2C)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129240381","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：