An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor Modeling
In industrial production, soft sensors play very important roles in ensuring product quality and production safety. Traditionally, global modeling methods, which use historical data to construct models offline, are often used to develop soft sensors. However, because of various complex and unknown c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/19/4099 |
| _version_ | 1828113638198607872 |
|---|---|
| author | Minglun Ren Yueli Song Wei Chu |
| author_facet | Minglun Ren Yueli Song Wei Chu |
| author_sort | Minglun Ren |
| collection | DOAJ |
| description | In industrial production, soft sensors play very important roles in ensuring product quality and production safety. Traditionally, global modeling methods, which use historical data to construct models offline, are often used to develop soft sensors. However, because of various complex and unknown changes in industrial production processes, the performance of global models deteriorates over time, and frequent model maintenance is difficult. In this study, locally weighted partial least squares (LWPLS) is adopted as a just-in-time learning method for industrial soft sensor modeling. In LWPLS, the bandwidth parameter h has an important impact on the performance of the algorithm, since it decides the range of the neighborhood and affects how the weight changes. Therefore, we propose a two-phase bandwidth optimization strategy that combines particle swarm optimization (PSO) and LWPLS. A numerical simulation example and an industrial application case were studied to estimate the performance of the proposed PSO−LWPLS method. The results show that, compared to the traditional global methods and the LWPLS with a fixed bandwidth, the proposed PSO−LWPLS can achieve a better prediction performance. The results also prove that the proposed method has apparent advantages over other methods in the case of data density changes. |
| first_indexed | 2024-04-11T12:11:59Z |
| format | Article |
| id | doaj.art-a7938d88058742f1b791e8b75b753b81 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T12:11:59Z |
| publishDate | 2019-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a7938d88058742f1b791e8b75b753b812022-12-22T04:24:36ZengMDPI AGSensors1424-82202019-09-011919409910.3390/s19194099s19194099An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor ModelingMinglun Ren0Yueli Song1Wei Chu2School of Management, Hefei University of Technology, Hefei 230009, ChinaSchool of Management, Hefei University of Technology, Hefei 230009, ChinaSchool of Management, Hefei University of Technology, Hefei 230009, ChinaIn industrial production, soft sensors play very important roles in ensuring product quality and production safety. Traditionally, global modeling methods, which use historical data to construct models offline, are often used to develop soft sensors. However, because of various complex and unknown changes in industrial production processes, the performance of global models deteriorates over time, and frequent model maintenance is difficult. In this study, locally weighted partial least squares (LWPLS) is adopted as a just-in-time learning method for industrial soft sensor modeling. In LWPLS, the bandwidth parameter h has an important impact on the performance of the algorithm, since it decides the range of the neighborhood and affects how the weight changes. Therefore, we propose a two-phase bandwidth optimization strategy that combines particle swarm optimization (PSO) and LWPLS. A numerical simulation example and an industrial application case were studied to estimate the performance of the proposed PSO−LWPLS method. The results show that, compared to the traditional global methods and the LWPLS with a fixed bandwidth, the proposed PSO−LWPLS can achieve a better prediction performance. The results also prove that the proposed method has apparent advantages over other methods in the case of data density changes.https://www.mdpi.com/1424-8220/19/19/4099locally weighted PLSparticle swarm optimizationjust-in-time learningbandwidth parametersoft sensor |
| spellingShingle | Minglun Ren Yueli Song Wei Chu An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor Modeling Sensors locally weighted PLS particle swarm optimization just-in-time learning bandwidth parameter soft sensor |
| title | An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor Modeling |
| title_full | An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor Modeling |
| title_fullStr | An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor Modeling |
| title_full_unstemmed | An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor Modeling |
| title_short | An Improved Locally Weighted PLS Based on Particle Swarm Optimization for Industrial Soft Sensor Modeling |
| title_sort | improved locally weighted pls based on particle swarm optimization for industrial soft sensor modeling |
| topic | locally weighted PLS particle swarm optimization just-in-time learning bandwidth parameter soft sensor |
| url | https://www.mdpi.com/1424-8220/19/19/4099 |
| work_keys_str_mv | AT minglunren animprovedlocallyweightedplsbasedonparticleswarmoptimizationforindustrialsoftsensormodeling AT yuelisong animprovedlocallyweightedplsbasedonparticleswarmoptimizationforindustrialsoftsensormodeling AT weichu animprovedlocallyweightedplsbasedonparticleswarmoptimizationforindustrialsoftsensormodeling AT minglunren improvedlocallyweightedplsbasedonparticleswarmoptimizationforindustrialsoftsensormodeling AT yuelisong improvedlocallyweightedplsbasedonparticleswarmoptimizationforindustrialsoftsensormodeling AT weichu improvedlocallyweightedplsbasedonparticleswarmoptimizationforindustrialsoftsensormodeling |