Figure - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
Online prediction of key parameters (e.g., process indices) is essential in many industrial processes because online measurement is not available. Data-based modeling is widely used for parameter prediction. However, model mismatch usually occurs owing to the variation of the feed properties, which changes the process dynamics. The current neural n...
Citations
... • However, the above methods used to evaluate the flexural strength of recycled aggregate concrete has disadvantages as follow: • Laboratory testing involves casting, curing and testing samples, which requires a large amount of cost, substantial effort and time (Jamei et al., 2021), especially considering the influence of multiple factors on the flexural strength of recycled aggregate concrete, the amount of work will increase exponentially. • Some researchers have realized that the prediction effect of hybrid machine learning models is better than that of single machine learning models (Guo and Wang, 2017;Wang et al., 2019;Zhu et al., 2021;Hasanipanah et al., 2022), and studied the evaluation effect of hybrid machine learning models, but it is necessary to compare the evaluation effect of different hybrid machine learning models and select the model with higher prediction effect. • In order to compare the prediction effect of different hybrid machine learning models on the FS of recycled concrete, and select the model with high prediction accuracy for engineers as an environmentally friendly tool to evaluate the FS of recycled concrete, this study proposed to use the SVM-FA, DT-FA and MLR-FA to predict the FS of recycled concrete. ...
Recycled concrete from construction waste used as road material is a current sustainable approach. To provide feasible suggestions for civil engineers to prepare recycled concrete with high flexural strength (FS) for the road pavement, the present study proposed three hybrid machine learning models by combining support vector machine (SVM), decision tree (DT) and multiple linear regression (MLR) with the firefly algorithm (FA) for the computational optimization, named as SVM-FA, DT-FA, and MLR-FA, respectively. Effective water-cement ratio (WC), aggregate-cement ratio (AC), recycled concrete aggregate replacement ratio (RCA), nominal maximum recycled concrete aggregate size (NMR), nominal maximum normal aggregate size (NMN), bulk density of recycled concrete aggregate (BDR), bulk density of normal aggregate (BDN), water absorption of RCA (WAR) and water absorption of NA (WAN) were employed as the input variables. To determine the predicting results of varying hybrid models, root mean square error (RMSE) and correlation coefficient (R) were used as performance indexes. The results showed that the SVM-FA demonstrated the highest R values and the lowest RMSE values, and the fitting effect of the predicted values and the actual values of the FS of recycled concrete is the best. All the above analysis proving that the SVM optimized by FA hyperparameters has the highest prediction accuracy and SVM-FA can provide engineers a more accurate and convenient tool to evaluate the FS of recycled concrete. The results of sensitivity analysis showed that WC has the most significant influence on the FS of recycled concrete, while RCA has the weakest influence on the FS, which should be noticed when engineers apply recycled concrete to road design in the future.
... In recent years, artificial intelligence algorithms, such as long short-term memory networks (LSTM) [20][21][22] and extreme learning machine(s) (ELM) [23][24][25][26] have also been used in soft sensor modeling. The basic assumption for LSTM is that process data are sampled at even and unified frequencies; it is very difficult to meet these conditions for 'process data measurements' in industrial processes, especially for quality variables. ...
In a regenerative aluminum smelting furnace, real-time liquid aluminum temperature measurements are essential for process control. However, it is often very expensive to achieve accurate temperature measurements. To address this issue, a just-in-time learning-based triple-weighted regularized extreme learning machine (JITL-TWRELM) soft sensor modeling method is proposed for liquid aluminum temperature prediction. In this method, a weighted JITL method (WJITL) is adopted for updating the online local models to deal with the process time-varying problem. Moreover, a regularized extreme learning machine model considering both the sample similarities and the variable correlations was established as the local modeling method. The effectiveness of the proposed method is demonstrated in an industrial aluminum smelting process. The results show that the proposed method can meet the requirements of prediction accuracy of the regenerative aluminum smelting furnace.
Soft sensors are software libraries or techniques that can estimate status as well as predict important performance indicators. MVA (multivariate analysis) and ML methods have been developed in data-driven monitoring as well as fault detection method. Here this research proposes supervisory Just-in-time neural network (SJITNN) based CPS monitoring and predictive maintenance integrated with partial least squares key indicator (PLSKI) in linear systems and large scale complex systems which mitigate noise, complexity and improve the network robustness, accuracy of predictive maintenance, RMSE, recall, F-1 score and precision. Furthermore, by allowing user to design analysis chains themselves, framework presents a user-friendly predictive maintenance method. Aside from this, framework is based on containerization techniques to make platform versatile, durable, and scalable in a variety of production situations. The experimental results shows that the proposed technique obtained accuracy of 91.8%, precision of 87.6%, recall of 88%, F-1 score of 72% and RMSE of 50%.
