Aerofoil noise as self-noise is detrimental to system performance, in this paper NACA 0012 optimization parameters are presented for reduction in noise. Designing an aerofoil with little noise is a fundamental objective of designing an aircraft that physically and functionally meets the requirements. Aerofoil self-noise is the noise created by aerofoils interacting with their boundary layers. Using neural networks, the suggested method predicts aerofoil self-noise. For parameter optimization, the quasi-Newtonian method is utilised. The input variables, such as angle of attack and chord length, are used as training parameters for neural networks. The output of a neural network is the sound pressure level, and the Quasi Newton method further optimises these parameters. When compared to the results of regression analysis, the values produced after training a neural network are enhanced.
{"title":"A novel approach for noise prediction using Neural network trained with an efficient optimization technique","authors":"Naren Shankar Radha Krishnan, Shiva Prasad Uppu","doi":"10.1051/smdo/2023002","DOIUrl":"https://doi.org/10.1051/smdo/2023002","url":null,"abstract":"Aerofoil noise as self-noise is detrimental to system performance, in this paper NACA 0012 optimization parameters are presented for reduction in noise. Designing an aerofoil with little noise is a fundamental objective of designing an aircraft that physically and functionally meets the requirements. Aerofoil self-noise is the noise created by aerofoils interacting with their boundary layers. Using neural networks, the suggested method predicts aerofoil self-noise. For parameter optimization, the quasi-Newtonian method is utilised. The input variables, such as angle of attack and chord length, are used as training parameters for neural networks. The output of a neural network is the sound pressure level, and the Quasi Newton method further optimises these parameters. When compared to the results of regression analysis, the values produced after training a neural network are enhanced.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"58006471","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}
To manufacture high-quality products with low manufacturing costs and optimal performance, better design concepts are required. The initial design concept can lead to inefficient structural design and higher manufacturing costs if the topology is not optimal. Topology optimization enables designers to reach their design goals faster, more accurately, and cost-effectively. However, the geometry obtained through topology optimization is not manufacturing-ready due to non-smooth boundaries and gray level images, which require post-processing design implementation by engineers. Various researchers have used different image processing techniques to convert the gray image into a binary map to address this issue. This paper focuses on using image processing to evaluate the differences in optimal designs induced by meshing. This study aims to aid in the parametric understanding of different designs targeting the same application by introducing two new parameters: similarity ratio and conformity ratio. The results compare an optimal geometry obtained using structured and unstructured meshes. Topological optimization algorithms applied to mechanical problems allow for reducing a structure's mass while ensuring its rigidity. However, the final structures may differ for the same problem depending on whether they were meshed regularly or irregularly. This article characterizes the differences between the two final structures using an image processing approach.
{"title":"Integration of digital imagery for topology optimization","authors":"Z. Atmani, Alexis Iung, J. Radoux, N. Lebaal","doi":"10.1051/smdo/2023004","DOIUrl":"https://doi.org/10.1051/smdo/2023004","url":null,"abstract":"To manufacture high-quality products with low manufacturing costs and optimal performance, better design concepts are required. The initial design concept can lead to inefficient structural design and higher manufacturing costs if the topology is not optimal. Topology optimization enables designers to reach their design goals faster, more accurately, and cost-effectively. However, the geometry obtained through topology optimization is not manufacturing-ready due to non-smooth boundaries and gray level images, which require post-processing design implementation by engineers. Various researchers have used different image processing techniques to convert the gray image into a binary map to address this issue. This paper focuses on using image processing to evaluate the differences in optimal designs induced by meshing. This study aims to aid in the parametric understanding of different designs targeting the same application by introducing two new parameters: similarity ratio and conformity ratio. The results compare an optimal geometry obtained using structured and unstructured meshes. Topological optimization algorithms applied to mechanical problems allow for reducing a structure's mass while ensuring its rigidity. However, the final structures may differ for the same problem depending on whether they were meshed regularly or irregularly. This article characterizes the differences between the two final structures using an image processing approach.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"58006685","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 main goal of this research is to compare group and individual replacement models based on fuzzy replacement theory and intuitionistic fuzzy replacement theory. The capital costs are assumed to be triangular fuzzy numbers, triangular intuitionistic fuzzy numbers, and trapezoidal intuitionistic fuzzy numbers, respectively. As a result, interpreting the direct relationship between volatility and ambiguity is critical. It is difficult to predict when specific equipment will unexpectedly fail. This problem can be solved by calculating the probability of failure distribution. Furthermore, the failure is assumed to occur only at the end of period t. In this situation, two types of replacement policies are used. The first is the Individual Replacement Policy, which states that if an item fails, it will be replaced immediately. The Group Replacement Policy states that all items must be replaced after a certain time period, with the option of replacing any item before the optimal time. The dimensions of the prosecution are fuzzy, and they are then assessed using mathematical and logical procedures. The fuzzy assessment criteria of the replacement model are provided as a set of outcomes, whereas the intuitionistic fuzzy replacement model has many advantages. A methodological technique is used to determine quality measurements in which fuzzy costs or values are kept without being merged into crisp values, allowing us to draw mathematical inferences in an uncertain setting. A comparison conceptualise is created for each fuzzy number, and in an uncertain environment, a comparison study on group and individual replacement was also conducted.
{"title":"A comparative analysis of the fuzzy and intuitionistic fuzzy environment for group and individual equipment replacement Models in order to achieve the optimized results","authors":"Vijaya Kumar Saranya, Shanmuga Sundari Murugan","doi":"10.1051/smdo/2023006","DOIUrl":"https://doi.org/10.1051/smdo/2023006","url":null,"abstract":"The main goal of this research is to compare group and individual replacement models based on fuzzy replacement theory and intuitionistic fuzzy replacement theory. The capital costs are assumed to be triangular fuzzy numbers, triangular intuitionistic fuzzy numbers, and trapezoidal intuitionistic fuzzy numbers, respectively. As a result, interpreting the direct relationship between volatility and ambiguity is critical. It is difficult to predict when specific equipment will unexpectedly fail. This problem can be solved by calculating the probability of failure distribution. Furthermore, the failure is assumed to occur only at the end of period t. In this situation, two types of replacement policies are used. The first is the Individual Replacement Policy, which states that if an item fails, it will be replaced immediately. The Group Replacement Policy states that all items must be replaced after a certain time period, with the option of replacing any item before the optimal time. The dimensions of the prosecution are fuzzy, and they are then assessed using mathematical and logical procedures. The fuzzy assessment criteria of the replacement model are provided as a set of outcomes, whereas the intuitionistic fuzzy replacement model has many advantages. A methodological technique is used to determine quality measurements in which fuzzy costs or values are kept without being merged into crisp values, allowing us to draw mathematical inferences in an uncertain setting. A comparison conceptualise is created for each fuzzy number, and in an uncertain environment, a comparison study on group and individual replacement was also conducted.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"58006783","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}
Machine learning algorithms are widely used in many intelligent applications and cloud services. Currently, the hottest topic in this field is Deep Learning represented often by neural network structures. Deep learning is fully known as deep neural network, and artificial neural network is a typical machine learning method and an important way of deep learning. With the massive growth of data, deep learning research has made significant achievements and is widely used in natural language processing (NLP), image recognition, and autonomous driving. However, there are still many breakthroughs needed in the training time and energy consumption of deep learning. Based on our previous research on fast learning architecture for neural network, in this paper, a solution to minimize the learning time of a fully connected neural network is analysed theoretically. Therefore, we propose a new parallel algorithm structure and a training method with over-tuned parameters. This strategy finally leads to an adaptation delay and the impact of this delay on the learning performance is analyzed using a simple benchmark case study. It is shown that a reduction of the adaptation step size could be proposed to compensate errors due to the delayed adaptation, then the gain in processing time for the learning phase is analysed as a function of the network parameters chosen in this study. Finally, to realize the real-time learning, this solution is implemented with a FPGA due to the parallelism architecture and flexibility, this integration shows a good performance and low power consumption.
{"title":"Real-time fast learning hardware implementation","authors":"M. Zhang, Samuel Garcia, M. Terré","doi":"10.1051/smdo/2023001","DOIUrl":"https://doi.org/10.1051/smdo/2023001","url":null,"abstract":"Machine learning algorithms are widely used in many intelligent applications and cloud services. Currently, the hottest topic in this field is Deep Learning represented often by neural network structures. Deep learning is fully known as deep neural network, and artificial neural network is a typical machine learning method and an important way of deep learning. With the massive growth of data, deep learning research has made significant achievements and is widely used in natural language processing (NLP), image recognition, and autonomous driving. However, there are still many breakthroughs needed in the training time and energy consumption of deep learning. Based on our previous research on fast learning architecture for neural network, in this paper, a solution to minimize the learning time of a fully connected neural network is analysed theoretically. Therefore, we propose a new parallel algorithm structure and a training method with over-tuned parameters. This strategy finally leads to an adaptation delay and the impact of this delay on the learning performance is analyzed using a simple benchmark case study. It is shown that a reduction of the adaptation step size could be proposed to compensate errors due to the delayed adaptation, then the gain in processing time for the learning phase is analysed as a function of the network parameters chosen in this study. Finally, to realize the real-time learning, this solution is implemented with a FPGA due to the parallelism architecture and flexibility, this integration shows a good performance and low power consumption.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"58006818","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}
Amani Idris A. Sayed, Shamsul Rijal Muhammad Sabri
The Generalized Gamma Distribution (GGD) is one of the most popular distributions in analyzing real lifetime datasets. Estimating the parameters of a high dimensional probability distribution is challenging due to the complexities associated with the resulting objectives function. When traditional estimation techniques fail due to complexity in the model objectives function, other powerful computational approaches are employed. In this study, a Bayesian approach to Generalized Gamma Distribution (GGD) based on Markov Chain Monte-Carlo (MCMC) has been employed to estimate model parameters. This study considers the Bayesian approach to GGD parameters using the Adaptive Rejection Metropolis Sampling (ARMS) technique of random variable generation within the Gibbs sampler. The MCMC approach has been used for estimating the multi-dimensional objectives function distribution. The results of the ARMS were compared to the existing Simulated annealing (SA) algorithm and Method of Moment (MM) based on modified internal rate of return data (MIRR). The performances of various derived estimators were recorded using the Markov chain Monte Carlo simulation technique for different sample sizes. The study reveals that ARMS's performance is marginally better than the existing SA and MA approaches. The efficiency of ARMS does not require a larger sample size as the SA does, in the case of simulated data. The performances of ARMS and SA are similar comparing them to the MM as an initial assumption in the case of real MIRR data. However, ARMS gives an acceptable estimated parameter for the different sample sizes due to its ability to evaluate the conditional distributions easily and sample from them exactly.
{"title":"Generalized gamma distribution based on the Bayesian approach with application to investment modelling","authors":"Amani Idris A. Sayed, Shamsul Rijal Muhammad Sabri","doi":"10.1051/smdo/2023011","DOIUrl":"https://doi.org/10.1051/smdo/2023011","url":null,"abstract":"The Generalized Gamma Distribution (GGD) is one of the most popular distributions in analyzing real lifetime datasets. Estimating the parameters of a high dimensional probability distribution is challenging due to the complexities associated with the resulting objectives function. When traditional estimation techniques fail due to complexity in the model objectives function, other powerful computational approaches are employed. In this study, a Bayesian approach to Generalized Gamma Distribution (GGD) based on Markov Chain Monte-Carlo (MCMC) has been employed to estimate model parameters. This study considers the Bayesian approach to GGD parameters using the Adaptive Rejection Metropolis Sampling (ARMS) technique of random variable generation within the Gibbs sampler. The MCMC approach has been used for estimating the multi-dimensional objectives function distribution. The results of the ARMS were compared to the existing Simulated annealing (SA) algorithm and Method of Moment (MM) based on modified internal rate of return data (MIRR). The performances of various derived estimators were recorded using the Markov chain Monte Carlo simulation technique for different sample sizes. The study reveals that ARMS's performance is marginally better than the existing SA and MA approaches. The efficiency of ARMS does not require a larger sample size as the SA does, in the case of simulated data. The performances of ARMS and SA are similar comparing them to the MM as an initial assumption in the case of real MIRR data. However, ARMS gives an acceptable estimated parameter for the different sample sizes due to its ability to evaluate the conditional distributions easily and sample from them exactly.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135750640","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}
David Bassir, Hugo Lodge, Haochen Chang, Jüri Majak, Gongfa Chen
Quality control is very important aspect in Building Information Modelling (BIM) workflows. Whatever stage of the lifecycle it is important to get and to follow building indicators. The BIM it is very data consuming field and analysis of these data require advance numerical tools from image processing to big data analysis. Artificial intelligent (AI) and machine learning (ML) had proven their efficiency to deal with automate processes and extract useful sources of data in different industries. In addition to the indicators tracking, AI and ML can make a good prediction about when and where to provide maintenance and/or quality control. In this article, a review of the AI and ML application in BIM will be presented. Further suggestions and challenges will be also discussed. The aim is to provide knowledge on the needs nowadays into building and landscaping domain, and to give a wide understanding on how those technics would impact industries and future studies.
{"title":"Application of artificial intelligence and machine learning for BIM: review","authors":"David Bassir, Hugo Lodge, Haochen Chang, Jüri Majak, Gongfa Chen","doi":"10.1051/smdo/2023005","DOIUrl":"https://doi.org/10.1051/smdo/2023005","url":null,"abstract":"Quality control is very important aspect in Building Information Modelling (BIM) workflows. Whatever stage of the lifecycle it is important to get and to follow building indicators. The BIM it is very data consuming field and analysis of these data require advance numerical tools from image processing to big data analysis. Artificial intelligent (AI) and machine learning (ML) had proven their efficiency to deal with automate processes and extract useful sources of data in different industries. In addition to the indicators tracking, AI and ML can make a good prediction about when and where to provide maintenance and/or quality control. In this article, a review of the AI and ML application in BIM will be presented. Further suggestions and challenges will be also discussed. The aim is to provide knowledge on the needs nowadays into building and landscaping domain, and to give a wide understanding on how those technics would impact industries and future studies.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135182593","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}
Issam El Khadiri, Maria Zemzami, Nhan-Quy Nguyen, Mohamed Abouelmajd, Nabil Hmina, Soufiane Belhouideg
Topology optimization is widely recognized for its ability to determine the best distribution of material in a structure to optimize its stiffness. This process often leads to creative configurations that produce complicated geometries challenging to construct using traditional techniques. Additive manufacturing has recently received a lot of interest from academics as well as industry. When compared to traditional methods, additive manufacturing or 3D printing offers considerable benefits (direct manufacture, time savings, fabrication of complex geometries, etc.). Recently, additive manufacturing techniques are increasingly being employed in industry to create complex components that cannot be produced using standard methods. The primary benefit of these techniques is the amount of creative flexibility they give designers. Additive manufacturing technology with higher resolution output capabilities has created a wealth of options for bridging the topology optimization and product application gap. This paper is a preliminary attempt to determine the key aspects of research on the integration of topology optimization and additive manufacturing, to outline topology optimization methods for these aspects with a review of various scientific and industry applications during the last years.
{"title":"Topology optimization methods for additive manufacturing: a review","authors":"Issam El Khadiri, Maria Zemzami, Nhan-Quy Nguyen, Mohamed Abouelmajd, Nabil Hmina, Soufiane Belhouideg","doi":"10.1051/smdo/2023015","DOIUrl":"https://doi.org/10.1051/smdo/2023015","url":null,"abstract":"Topology optimization is widely recognized for its ability to determine the best distribution of material in a structure to optimize its stiffness. This process often leads to creative configurations that produce complicated geometries challenging to construct using traditional techniques. Additive manufacturing has recently received a lot of interest from academics as well as industry. When compared to traditional methods, additive manufacturing or 3D printing offers considerable benefits (direct manufacture, time savings, fabrication of complex geometries, etc.). Recently, additive manufacturing techniques are increasingly being employed in industry to create complex components that cannot be produced using standard methods. The primary benefit of these techniques is the amount of creative flexibility they give designers. Additive manufacturing technology with higher resolution output capabilities has created a wealth of options for bridging the topology optimization and product application gap. This paper is a preliminary attempt to determine the key aspects of research on the integration of topology optimization and additive manufacturing, to outline topology optimization methods for these aspects with a review of various scientific and industry applications during the last years.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135211882","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 planning problem of supply chain network is highly related to logistics cost and product quality. In this paper, for the optimization of supply chain network planning problem, an agricultural product supply chain network under the direct docking model between farmers and supermarkets was taken as an example to establish an agricultural product supply chain network planning model with the lowest cost as the objective. Then, an improved genetic algorithm (GA) was designed to solve the model. The analysis of the arithmetic example showed that compared with the traditional GA, the total cost obtained by the improved GA was lower, at 39,004.48 $, which was 6.5% less than that of the traditional GA; the solution result of the improved GA was also superior to that of other heuristic algorithms, such as particle swarm optimization and ant colony optimization. The experimental results demonstrate the optimization effectiveness of the improved GA for the supply chain network planning problem, and it can be applied in practice.
{"title":"Optimization of the supply chain network planning problem using an improved genetic algorithm","authors":"Liang Zhao, Jing Xie","doi":"10.1051/smdo/2023014","DOIUrl":"https://doi.org/10.1051/smdo/2023014","url":null,"abstract":"The planning problem of supply chain network is highly related to logistics cost and product quality. In this paper, for the optimization of supply chain network planning problem, an agricultural product supply chain network under the direct docking model between farmers and supermarkets was taken as an example to establish an agricultural product supply chain network planning model with the lowest cost as the objective. Then, an improved genetic algorithm (GA) was designed to solve the model. The analysis of the arithmetic example showed that compared with the traditional GA, the total cost obtained by the improved GA was lower, at 39,004.48 $, which was 6.5% less than that of the traditional GA; the solution result of the improved GA was also superior to that of other heuristic algorithms, such as particle swarm optimization and ant colony optimization. The experimental results demonstrate the optimization effectiveness of the improved GA for the supply chain network planning problem, and it can be applied in practice.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135555704","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}
Accurately predicting stock returns can help reduce market risk. This paper briefly introduced the long short-term memory (LSTM) algorithm model for predicting stock returns and combined it with principal component analysis (PCA) to improve the prediction accuracy. Simulation experiments were conducted on 80 stocks, and the PCA-LSTM model was compared with back-propagation neural network (BPNN) and LSTM models. The results showed that the PCA analysis method effectively identified the principal components of variable indicators. During the training iteration convergence, the PCA-LSTM model not only converged faster but also had smaller errors after stabilization. Moreover, the PCA-LSTM model had the highest prediction accuracy, the LSTM model was the second, and the BPNN model was the worst.
{"title":"Application of PCA-LSTM algorithm for financial market stock return prediction and optimization model","authors":"Yanxiang Mi, Donghai Xu, Tielin Gao","doi":"10.1051/smdo/2023009","DOIUrl":"https://doi.org/10.1051/smdo/2023009","url":null,"abstract":"Accurately predicting stock returns can help reduce market risk. This paper briefly introduced the long short-term memory (LSTM) algorithm model for predicting stock returns and combined it with principal component analysis (PCA) to improve the prediction accuracy. Simulation experiments were conducted on 80 stocks, and the PCA-LSTM model was compared with back-propagation neural network (BPNN) and LSTM models. The results showed that the PCA analysis method effectively identified the principal components of variable indicators. During the training iteration convergence, the PCA-LSTM model not only converged faster but also had smaller errors after stabilization. Moreover, the PCA-LSTM model had the highest prediction accuracy, the LSTM model was the second, and the BPNN model was the worst.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"58007125","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}
A fuzzy optimization model was implemented in this study as a decision-making approach to optimize pollutant degradation processes in facultative ponds of domestic wastewater treatment plants. The fuzzy parameters are due to uncertain situations, which eliminate the need for managers to collect data, particularly when the data are no longer represent the real situation. The managers formulate the fuzzy parameters in the problem based on their intuition and experience in using the provided decision-making tool. Also, the fuzzy optimization model proposed in this study was solved using the fuzzy-based programming approach with the generalized gradient algorithm performed in LINGO 19.0 optimization software. In addition, the numerical experiment was conducted with secondary and generated data for the certain and fuzzy parameters, respectively. The results showed that optimal decisions were achieved and the manager can then use the proposed model in managing domestic wastewater treatment plants.
{"title":"Decision-making support for optimizing pollutant degradation processes in domestic wastewater treatment plants involving uncertain parameters via fuzzy programming approaches","authors":"Sunarsih Sunarsih, Dwi Purwantoro Sasongko, Siti Khabibah, Sutrisno Sutrisno","doi":"10.1051/smdo/2023010","DOIUrl":"https://doi.org/10.1051/smdo/2023010","url":null,"abstract":"A fuzzy optimization model was implemented in this study as a decision-making approach to optimize pollutant degradation processes in facultative ponds of domestic wastewater treatment plants. The fuzzy parameters are due to uncertain situations, which eliminate the need for managers to collect data, particularly when the data are no longer represent the real situation. The managers formulate the fuzzy parameters in the problem based on their intuition and experience in using the provided decision-making tool. Also, the fuzzy optimization model proposed in this study was solved using the fuzzy-based programming approach with the generalized gradient algorithm performed in LINGO 19.0 optimization software. In addition, the numerical experiment was conducted with secondary and generated data for the certain and fuzzy parameters, respectively. The results showed that optimal decisions were achieved and the manager can then use the proposed model in managing domestic wastewater treatment plants.","PeriodicalId":37601,"journal":{"name":"International Journal for Simulation and Multidisciplinary Design Optimization","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135006858","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：