Transductive transfer broad learning for cross-domain information exploration and multigrade soft sensor application

Zhu, Jialiang; Jia, Mingwei; Zhang, Ying; Deng, Hui‐Xiong; Liu, Yi

doi:10.1016/j.chemolab.2023.104778

Cited by 7 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many ML and deep learning approaches were not explored in this work (like [36][37][38][39]) and may have some advantages and drawbacks compared to those we have used. Due to the very large choice of such approaches, it is impossible to be exhaustive, so we have selected the ones most used and cited in the literature.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Alternatives to Response Surface Models

Ghattas

Manzon

2023

Mathematics

View full text Add to dashboard Cite

In the Design of Experiments, we seek to relate response variables to explanatory factors. Response Surface methodology (RSM) approximates the relation between output variables and a polynomial transform of the explanatory variables using a linear model. Some researchers have tried to adjust other types of models, mainly nonlinear and nonparametric. We present a large panel of Machine Learning approaches that may be good alternatives to the classical RSM approximation. The state of the art of such approaches is given, including classification and regression trees, ensemble methods, support vector machines, neural networks and also direct multi-output approaches. We survey the subject and illustrate the use of ten such approaches using simulations and a real use case. In our simulations, the underlying model is linear in the explanatory factors for one response and nonlinear for the others. We focus on the advantages and disadvantages of the different approaches and show how their hyperparameters may be tuned. Our simulations show that even when the underlying relation between the response and the explanatory variables is linear, the RSM approach is outperformed by the direct neural network multivariate model, for any sample size (<50) and much more for very small samples (15 or 20). When the underlying relation is nonlinear, the RSM approach is outperformed by most of the machine learning approaches for small samples (n ≤ 30).

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning Alternatives to Response Surface Models

Ghattas

Manzon

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Batch processes are frequently employed in industries characterized by high-quality standards, diversified product offerings, and relatively low production volumes, such as fine chemicals, biopharmaceuticals, and food fermentation, in contrast to continuous processes commonly found in large-scale manufacturing facilities [1][2][3]. In a continuous process, the operation typically remains at the optimal economic point; in contrast, the operational conditions of a batch process change dynamically from beginning to end.…”

Section: Introductionmentioning

confidence: 99%

Particle Swarm Optimization-Based Model-Free Adaptive Control for Time-Varying Batch Processes

Wang,

Sadun,

Jalaludin

et al. 2024

Int. J. Automot. Mech. Eng.

View full text Add to dashboard Cite

The batch process is a production process with strong nonlinearity, which usually suffers from time-varying parameters and uncertainty of disturbances. Concerning the mentioned problems, this study proposes to investigate the application of the particle swarm optimization-based model-free adaptive control (PSO-MFAC) method for time-varying batch processes. Model-Free Adaptive Control (MFAC) is a data-driven control method, which is one of the promising methods to solve the nonlinear process. Firstly, a Full Form Dynamic Linearization Model-Free Adaptive Control method has been adopted for the control of batch processes. Further, considering that the adopted model-free adaptive control involves seven control parameters, such as cognitive scaling factor (φ1), social scaling factor (φ2), inertia weight (φ3), learning rate (η), control parameter update rate, exploration rate and learning rate for MFAC obtained by a particle swarm optimization (PSO) algorithm in combination with a criterion function performance index. Finally, by comparing it with the existing methods, a typical batch fermentation was applied to verify that PSO-MFAC had a good control effect. The findings indicate that the PSO-MFAC controller exhibits a preference for exploiting the optimal option due to its φ3 value less than 0.1. The efficacy and feasibility of the PSO-MFAC control effect have been proven by obtaining the lowest integral square error (ISE) value of 1.1192 regarding the nonlinearity of the batch process due to time-varying challenges.

show abstract

“…In TL training, given a source domain D s and learning task T s , and a target domain D T and a learning task T T , TL aims to help the learning of the target predictive function f T (·) for the target domain using the knowledge in D s and T s , where D s ≠ D T and T s ≠ T T . The remarkable success of TL has been shown in fields such as materials informatics, − process modeling, − and process monitoring. − In these works, researchers have used different sets of data types including simulated data from empirical or process simulation, , experimental data from related studies, and fake data from generative models to pretrain the ML model before fine-tuning the target problem. Generally, these works showed the positive application of how to use TL to address data limitations affecting the development of accurate data-driven modeling.…”

Section: Introductionmentioning

confidence: 99%

Empowering Capacitive Devices: Harnessing Transfer Learning for Enhanced Data-Driven Optimization

Olayiwola,

Kumar,

Romagnoli

2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Developing data-driven models has found successful applications in engineering tasks, such as material design, process modeling, and process monitoring. In capacitive devices like deionization and supercapacitors, there exists potential for applying this data-driven machine learning (ML) model in optimizing its potential use in energy-efficient separations or energy generation. However, these models are faced with limited datasets, and even in large quantities, the datasets are incomplete, limiting their potential use for successful data-driven modeling. Here, the success of transfer learning in resolving the challenges with limited datasets was exploited. A two-step data-driven ML modeling framework named ImputeNet involving training with ML-imputed datasets and then with clean datasets was explored. Through data imputation and transfer learning, it is possible to develop a datadriven model with acceptable metrics mirroring experimental measurements. By using the model, optimization studies using the genetic algorithm were implemented to analyze the solution under the Pareto optimality. This early insight can be used in the initial stage of experimental measurements to rapidly identify experimental conditions worthy of further investigation. Moreover, we expect that the insights from these results will drive accurate predictive modeling in other fields including healthcare, genomic data analysis, and environmental monitoring with incomplete datasets.

show abstract

Transductive transfer broad learning for cross-domain information exploration and multigrade soft sensor application

Cited by 7 publications

References 29 publications

Machine Learning Alternatives to Response Surface Models

Machine Learning Alternatives to Response Surface Models

Particle Swarm Optimization-Based Model-Free Adaptive Control for Time-Varying Batch Processes

Empowering Capacitive Devices: Harnessing Transfer Learning for Enhanced Data-Driven Optimization

Contact Info

Product

Resources

About