A KPI-Based Probabilistic Soft Sensor Development Approach that Maximizes the Coefficient of Determination

Zhang, Yue; Yang, Xu; Shardt, Yuri A.W.; Cui, Jiarui; Tong, Chaonan

doi:10.3390/s18093058

Cited by 13 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practice, the activation function of neurons is a generally hyperbolic tangent function described in Equation (3). The key issue of ESN is to identify the output connection weight W out using known samples [43].…”

Section: Basic Esnmentioning

confidence: 99%

“…For example, the sampling time of some process variables is irregular, since they may have been tested in the laboratory, which could result in varying time delay. Even if some state variables can be measured directly, the measured data may be extremely unreliable [1][2][3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, the proposed method is even more adaptive for the modern industrial requirement. (3) The established model in this paper is applicable to estimate alumina concentration in an aluminum reduction cell. To the best of our knowledge, this is the first utilization of an ESN model in this field.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Soft Sensor Approach Based on an Echo State Network Optimized by Improved Genetic Algorithm

Huang

Cao³

2020

Sensors

View full text Add to dashboard Cite

In the process of fault diagnosis and the health and safety operation evaluation of modern industrial processes, it is crucial to measure important state variables, which cannot be directly detected due to limitations of economy, technology, environment and space. Therefore, this paper proposes a data-driven soft sensor approach based on an echo state network (ESN) optimized by an improved genetic algorithm (IGA). Firstly, with an ESN, a data-driven model (DDM) between secondary variables and dominant variables is established. Secondly, in order to improve the prediction performance, the IGA is utilized to optimize the parameters of the ESN. Then, the immigration strategy is introduced and the crossover and mutation operators are changed adaptively to improve the convergence speed of the algorithm and address the problem that the algorithm falls into the local optimum. Finally, a soft sensor model of an ESN optimized by an IGA is established (IGA-ESN), and the advantages and performance of the proposed method are verified by estimating the alumina concentration in an aluminum reduction cell. The experimental results illustrated that the proposed method is efficient, and the error was significantly reduced compared with the traditional algorithm.

show abstract

Section: Basic Esnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Soft Sensor Approach Based on an Echo State Network Optimized by Improved Genetic Algorithm

Huang

Cao³

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…In industrial processes, a large number of sensors are required to obtain state information. − The information can be used for process safety, control scheme adjustments, and decision-making assistants. − However, some crucial information may be hard to obtain through hardware sensors or need offline analysis, which would cause intolerable delays. , The above-mentioned shortcomings can be mitigated by soft sensors, which can provide reliable quality online predictions using the available process data. − Soft sensors are formed using the input and output variables to construct analytical models or black-box models. ,− Analytical methods provide a first-principles model which is complicated or even is hard to simulate when dealing with a complex process. However, data-driven methods can obtain black-box models to provide predictions in a complex process, which is easier than analytical methods …”

Section: Introductionmentioning

confidence: 99%

Variable-Scale Probabilistic Just-in-Time Learning for Soft Sensor Development with Missing Data

Huang

Peng

Jiang

et al. 2020

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Just-in-time learning (JITL) has been widely applied to data-driven modeling to deal with the nonlinearity problems in industrial processes. To mitigate the effects of noise existing in JITL, probabilistic JITL (PJITL) selects samples based on the probability distributions. Considering the existence of missing data situation, the PJITL algorithm could also cope with that. However, traditional JITL-based methods, including PJITL, cannot flexibly select the number of training samples for each query sample, which would in return influence the accuracy of prediction for a part of query samples. To solve this problem, we proposed a method named “variable-scale PJITL” (VS-PJITL) which can determine the sizes of the local models for each query sample using a new sample selection criterion. Based on the Euclidean distance, the sample selection criterion also applies to the variable-scale JITL (VS-JITL). Then, comparisons of VS-PJITL, PJITL, JITL, and VS-JITL are tested on a simulated data set and a real industrial data set from the catalytic naphtha reforming process. By analyzing the two cases above, VS-PJITL is considered to have superior performance to the original PJITL (root-mean-square error reduced by 0.3355 and 0.4778).

show abstract

“…R 2 and RMSE are popular performance metrics for evaluating model performance in regression problems. Their combined evaluation proves useful in applications involving plantings and sensor networks [86][87][88].…”

mentioning

confidence: 99%

A Machine Learning Framework for Olive Farms Profit Prediction

Christias

Mocanu

2021

Water

View full text Add to dashboard Cite

Agricultural systems are constantly stressed due to higher demands for products. Consequently, water resources consumed on irrigation are increased. In combination with the climatic change, those are major obstacles to maintaining sustainable development, especially in a semi-arid land. This paper presents an end-to-end Machine Learning framework for predicting the potential profit from olive farms. The objective is to estimate the optimal economic gain while preserving water resources on irrigation by considering various related factors such as climatic conditions, crop management practices, soil characteristics, and crop yield. The case study focuses on olive tree farms located on the Hellenic Island of Crete. Real data from the farms and the weather in the area will be used. The target is to build a framework that will preprocess input data, compare the results among a group of Machine Learning algorithms and propose the best-predicted value of economic profit. Various aspects during this process will be thoroughly examined such as the bias-variance tradeoff and the problem of overfitting, data transforms, feature engineering and selection, ensemble methods as well as pursuing optimal resampling towards better model accuracy. Results indicated that through data preprocessing and resampling, Machine Learning algorithms performance is enhanced. Ultimately, prediction accuracy and reliability are greatly improved compared to algorithms’ performances without the framework’s operation.

show abstract

A KPI-Based Probabilistic Soft Sensor Development Approach that Maximizes the Coefficient of Determination

Cited by 13 publications

References 33 publications

A Soft Sensor Approach Based on an Echo State Network Optimized by Improved Genetic Algorithm

A Soft Sensor Approach Based on an Echo State Network Optimized by Improved Genetic Algorithm

Variable-Scale Probabilistic Just-in-Time Learning for Soft Sensor Development with Missing Data

A Machine Learning Framework for Olive Farms Profit Prediction

Contact Info

Product

Resources

About