Machine learning techniques for monitoring the sludge profile in a secondary settler tank
Abstract The aim of this paper is to evaluate and compare the performance of two machine learning methods, Gaussian process regression (GPR) and Gaussian mixture models (GMMs), as two possible methods for monitoring the sludge profile in a secondary settler tank (SST). In GPR, the prediction of the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2019-07-01
|
| Series: | Applied Water Science |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s13201-019-1018-5 |
| _version_ | 1818656880819437568 |
|---|---|
| author | Jesús Zambrano Oscar Samuelsson Bengt Carlsson |
| author_facet | Jesús Zambrano Oscar Samuelsson Bengt Carlsson |
| author_sort | Jesús Zambrano |
| collection | DOAJ |
| description | Abstract The aim of this paper is to evaluate and compare the performance of two machine learning methods, Gaussian process regression (GPR) and Gaussian mixture models (GMMs), as two possible methods for monitoring the sludge profile in a secondary settler tank (SST). In GPR, the prediction of the response variable is given as a Gaussian probability density function, whereas in the GMM the probability density function is built as a weighted sum of Gaussian distributions. In both approaches, a residual is calculated and a fault detection criterion is implemented via a recursive decision rule. As case study, GMM and GPR were tested using real data from a sensor measuring the suspended solids concentration as a function of the SST level in a wastewater treatment plant in Bromma, Sweden. Results suggest that GMM gives a faster response but is also more sensitive than GPR to changes during normal conditions. |
| first_indexed | 2024-12-17T03:32:37Z |
| format | Article |
| id | doaj.art-f157921d4ac84207b60548d3b6c00696 |
| institution | Directory Open Access Journal |
| issn | 2190-5487 2190-5495 |
| language | English |
| last_indexed | 2024-12-17T03:32:37Z |
| publishDate | 2019-07-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Applied Water Science |
| spelling | doaj.art-f157921d4ac84207b60548d3b6c006962022-12-21T22:05:13ZengSpringerOpenApplied Water Science2190-54872190-54952019-07-019611110.1007/s13201-019-1018-5Machine learning techniques for monitoring the sludge profile in a secondary settler tankJesús Zambrano0Oscar Samuelsson1Bengt Carlsson2School of Business, Society and Engineering, Mälardalen UniversityIVL Swedish Environmental Research InstituteDepartment of Information Technology, Uppsala UniversityAbstract The aim of this paper is to evaluate and compare the performance of two machine learning methods, Gaussian process regression (GPR) and Gaussian mixture models (GMMs), as two possible methods for monitoring the sludge profile in a secondary settler tank (SST). In GPR, the prediction of the response variable is given as a Gaussian probability density function, whereas in the GMM the probability density function is built as a weighted sum of Gaussian distributions. In both approaches, a residual is calculated and a fault detection criterion is implemented via a recursive decision rule. As case study, GMM and GPR were tested using real data from a sensor measuring the suspended solids concentration as a function of the SST level in a wastewater treatment plant in Bromma, Sweden. Results suggest that GMM gives a faster response but is also more sensitive than GPR to changes during normal conditions.http://link.springer.com/article/10.1007/s13201-019-1018-5Covariance functionFault detectionGaussian mixture modelsGaussian process regressionMonitoring |
| spellingShingle | Jesús Zambrano Oscar Samuelsson Bengt Carlsson Machine learning techniques for monitoring the sludge profile in a secondary settler tank Applied Water Science Covariance function Fault detection Gaussian mixture models Gaussian process regression Monitoring |
| title | Machine learning techniques for monitoring the sludge profile in a secondary settler tank |
| title_full | Machine learning techniques for monitoring the sludge profile in a secondary settler tank |
| title_fullStr | Machine learning techniques for monitoring the sludge profile in a secondary settler tank |
| title_full_unstemmed | Machine learning techniques for monitoring the sludge profile in a secondary settler tank |
| title_short | Machine learning techniques for monitoring the sludge profile in a secondary settler tank |
| title_sort | machine learning techniques for monitoring the sludge profile in a secondary settler tank |
| topic | Covariance function Fault detection Gaussian mixture models Gaussian process regression Monitoring |
| url | http://link.springer.com/article/10.1007/s13201-019-1018-5 |
| work_keys_str_mv | AT jesuszambrano machinelearningtechniquesformonitoringthesludgeprofileinasecondarysettlertank AT oscarsamuelsson machinelearningtechniquesformonitoringthesludgeprofileinasecondarysettlertank AT bengtcarlsson machinelearningtechniquesformonitoringthesludgeprofileinasecondarysettlertank |