scholarly journals An Incremental Learning Ensemble Strategy for Industrial Process Soft Sensors

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-12
Author(s):  
Huixin Tian ◽  
Minwei Shuai ◽  
Kun Li ◽  
Xiao Peng
Keyword(s):  
Industrial Production ◽  
Incremental Learning ◽  
Industrial Process ◽  
Soft Sensor ◽  
Process Data ◽  
Data Set ◽  
Sensor Model ◽  
New Information ◽  
Ensemble Strategy ◽  
Learning Machine

With the continuous improvement of automation in industrial production, industrial process data tends to arrive continuously in many cases. The ability to handle large amounts of data incrementally and efficiently is indispensable for modern machine learning (ML) algorithms. According to the characteristics of industrial production process, we address an ILES (incremental learning ensemble strategy) that incorporates incremental learning to extract information efficiently from constantly incoming data. The ILES aggregates multiple sublearning machines by different weights for better accuracy. When new data set arrives, a new submachine will be trained and aggregated into ensemble soft sensor model according to its weight. The other submachines' weights will be updated at the same time. Then a new updated soft sensor ensemble model can be obtained. The weight updating rules are designed by considering the prediction accuracy of submachines with new arrived data. So the update can fit the data change and obtain new information efficiently. The sizing percentage soft sensor model is established to learn the information from the production data in the sizing of industrial processes and to test the performance of ILES, where the ELM (Extreme Learning Machine) is selected as the sublearning machine. The comparison is done among new method, single ELM, AdaBoost.R ELM, and OS-ELM, and the test of the extensions is done with three test functions. The results of the experiments demonstrate that the soft sensor model based on the ILES has the best accuracy and ability of online updating.

scholarly journals A Novel Isomap-SVR Soft Sensor Model and Its Application in Rotary Kiln Calcination Zone Temperature Prediction

Symmetry ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 167 ◽  
Author(s):  
Jialun Liu ◽  
Yukun Wang ◽  
Yong Zhang
Keyword(s):  
Rotary Kiln ◽  
Soft Sensor ◽  
Modeling Method ◽  
Support Vector ◽  
Data Set ◽  
Generalization Ability ◽  
Sensor Model ◽  
Learning Speed ◽  
Proposed Model ◽  
Cauchy Mutation

Soft sensing technology has been proved to be an effective tool for the online estimation of unmeasured or variables that are difficult to directly measure. The performance of a soft sensor depends heavily on its convergence speed and generalization ability to a great extent. Based on this idea, we propose a new soft sensor model, Isomap-SVR. First, the sample data set is divided into training set and testing set by using self-organizing map (SOM) neural network to ensure the fairness and symmetry of data segmentation. Isometric feature mapping (Isomap) method is used for dimensionality reduction of the model input data, which could not only reduce the structure complexity of the proposed model but speed up learning speed, and then the Support Vector Machine Regression (SVR) is applied to the regression model. A novel bat algorithm based on Cauchy mutation and Lévy flight strategy is used to optimize parameters of Isomap and SVR to improve the accuracy of the proposed model. Finally, the model is applied to the prediction of the temperature of rotary kiln calcination zone, which is difficult to measure directly. The simulation results show that the proposed soft sensor modeling method has higher learning speed and better generalization ability. Compared with other algorithms, this algorithm has obvious advantages and is an effective modeling method.

scholarly journals Adaptive Hybrid Soft-Sensor Model of Grinding Process Based on Regularized Extreme Learning Machine and Least Squares Support Vector Machine Optimized by Golden Sine Harris Hawk Optimization Algorithm

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-26 ◽  
Author(s):  
Wei Xie ◽  
Jie-sheng Wang ◽  
Cheng Xing ◽  
Sha-Sha Guo ◽  
Meng-wei Guo ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Extreme Learning Machine ◽  
Prediction Accuracy ◽  
Soft Sensor ◽  
Support Vector ◽  
Structure Parameters ◽  
Generalization Ability ◽  
Sensor Model ◽  
Learning Machine

Soft-sensor technology plays a vital role in tracking and monitoring the key production indicators of the grinding and classifying process. Least squares support vector machine (LSSVM), as a soft-sensor model with strong generalization ability, can be used to predict key production indicators in complex grinding processes. The traditional crossvalidation method cannot obtain the ideal structure parameters of LSSVM. In order to improve the prediction accuracy of LSSVM, a golden sine Harris Hawk optimization (GSHHO) algorithm was proposed to optimize the structure parameters of LSSVM models with linear kernel, sigmoid kernel, polynomial kernel, and radial basis kernel, and the influences of GSHHO algorithm on the prediction accuracy under these LSSVM models were studied. In order to deal with the problem that the prediction accuracy of the model decreases due to changes of industrial status, this paper adopts moving window (MW) strategy to adaptively revise the LSSVM (MW-LSSVM), which greatly improves the prediction accuracy of the LSSVM. The prediction accuracy of the regularized extreme learning machine with MW strategy (MW-RELM) is higher than that of MW-LSSVM at some moments. Based on the training errors of LSSVM and RELM within the window, this paper proposes an adaptive hybrid soft-sensing model that switches between LSSVM and RELM. Compared with the previous MW-LSSVM, MW-neural network trained with extended Kalman filter(MW-KNN), and MW-RELM, the prediction accuracy of the hybrid model is further improved. Simulation results show that the proposed hybrid adaptive soft-sensor model has good generalization ability and prediction accuracy.

Soft Sensor Modeling Based on Multiple Extreme Learning Machine

2012 ◽  
Vol 433-440 ◽  
pp. 3003-3010
Author(s):  
Gai Tang Wang ◽  
Ping Li ◽  
Cheng Li Su
Keyword(s):  
Extreme Learning Machine ◽  
Soft Sensor ◽  
Regression Method ◽  
Multiple Model ◽  
Delayed Coking ◽  
Sensor Model ◽  
Affinity Propagation Clustering ◽  
Learning Machine ◽  
Sensor Modeling ◽  
Secondary Variable

Presented is a multiple model soft sensing method based on extreme learning machine (MELM) algorithm, to solve the problem that single ELM model has lower predictive precision and over-fitting problems. The method adopts Gaussian process to choose secondary variable for soft sensor model. Then, samples data are divided into several groups of data by adaptive affinity propagation clustering, and the sub-models are estimated by ELM regression method. Finally, ELM is regarded as output synthesizer of sub-models. The proposed method has been applied to predict the end point of crude gasoline in delayed coking unit. Compared with single ELM modeling, the simulation results show that the algorithm has better predictive precision and good generalization performance.

scholarly journals Seepage Time Soft Sensor Model of Nonwoven Fabric Based on the Extreme Learning Machine Integrating Monte Carlo

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2377
Author(s):  
Jing Zhang ◽  
Yiqiang Fan ◽  
Lulu Zhang ◽  
Chi Xu ◽  
Xiaobin Dong ◽  
...  
Keyword(s):  
Neural Network ◽  
Monte Carlo ◽  
Prediction Model ◽  
Structural Characteristics ◽  
Nonwoven Fabric ◽  
Soft Sensor ◽  
Sensor Model ◽  
Learning Machine ◽  
Fiber Materials ◽  
Nonwoven Fiber

Nonwoven fiber materials are materials with multifunctional purposes, and are widely used to make masks for preventing the new Coronavirus Disease 2019. Because of the complexity and particularity of their structure, it becomes difficult to model the penetration and flow characteristics of liquid in nonwoven fiber materials. In this paper, a novel seepage time soft sensor model of nonwoven fabric, based on Monte Carlo (MC), integrating extreme learning machine (ELM) (MCELM) is proposed. The Monte Carlo method is used to expand data samples. Then, an ELM method is used to establish the prediction model of the dyeing time of the nonwoven fiber material overlaps with the porous medium, as well as the insertion degree and height of the different quantity of hides. Compared with the back propagation (BP) neural network and radial basis function (RBF) neural network, the results show that the prediction model based on the MCELM method has significant power in terms of accuracy and prediction speed, which is conducive to the precise and rapid manufacture of nonwoven fiber materials in practical applications between liquid seepage characteristics and structural characteristics of porous media. Furthermore, the relationship between the proposed models has certain value for predicting the behavior and use of nonwoven fiber materials with different structural characteristics and related research processes.

scholarly journals Industrial Semi-Supervised Dynamic Soft-Sensor Modeling Approach Based on Deep Relevant Representation Learning

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3430
Author(s):  
Jean Mário Moreira de Lima ◽  
Fábio Meneghetti Ugulino de Araújo
Keyword(s):  
Short Term Memory ◽  
Soft Sensor ◽  
Fine Tuning ◽  
Current Layer ◽  
Layer By Layer ◽  
Linear Processes ◽  
Method Performance ◽  
Modeling Approach ◽  
Ensemble Strategy ◽  
Sensor Modeling

Soft sensors based on deep learning have been growing in industrial process applications, inferring hard-to-measure but crucial quality-related variables. However, applications may present strong non-linearity, dynamicity, and a lack of labeled data. To deal with the above-cited problems, the extraction of relevant features is becoming a field of interest in soft-sensing. A novel deep representative learning soft-sensor modeling approach is proposed based on stacked autoencoder (SAE), mutual information (MI), and long-short term memory (LSTM). SAE is trained layer by layer with MI evaluation performed between extracted features and targeted output to evaluate the relevance of learned representation in each layer. This approach highlights relevant information and eliminates irrelevant information from the current layer. Thus, deep output-related representative features are retrieved. In the supervised fine-tuning stage, an LSTM is coupled to the tail of the SAE to address system inherent dynamic behavior. Also, a k-fold cross-validation ensemble strategy is applied to enhance the soft-sensor reliability. Two real-world industrial non-linear processes are employed to evaluate the proposed method performance. The obtained results show improved prediction performance in comparison to other traditional and state-of-art methods. Compared to the other methods, the proposed model can generate more than 38.6% and 39.4% improvement of RMSE for the two analyzed industrial cases.

Sign in / Sign up

Export Citation Format

Share Document