MIMO modeling and multi-loop control based on neural network for municipal solid waste incineration

Ding, Haixu; Tang, Jian; Qiao, Junfei

doi:10.1016/j.conengprac.2022.105280

Cited by 16 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, they [157] introduced a PID control strategy that integrates components of the two loops, showcasing effective enhancement in tracking characteristics and a noteworthy improvement in the economic benefits of MSWI plants. In a similar vein, Ding et al [158] proposed a self-organizing fuzzy neural network controller based on multitask learning for simultaneous control of furnace temperature and flue gas oxygen content. Nevertheless, its applicability is constrained to a single operational condition.…”

Section: Mimo Control (1) Double Input and Double Outputmentioning

confidence: 99%

An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process

Tang,

Wang,

Xia

et al. 2024

Preprint

View full text Add to dashboard Cite

Artificial intelligence (AI) has found extensive applications in the sustainability domain. The municipal solid waste incineration (MSWI) process can achieve waste-to-energy (WTE) goals through the assistance of automation and information technologies. In theory, AI can facilitate the intelligent operation of the MSWI process, simultaneously achieving low pollution emissions and high production efficiency. This study provides an overview of AI applications in the MSWI process. Addressing fundamental challenges, the optimal control of the MSWI process is categorized into four aspects: modeling, control, optimization, and maintenance. Subsequently, this study conducts a detailed analysis and discussion of AI applications in each of these technological domains. In conclusion, this paper outlines the future research directions and provides an outlook on the fundamental issues pertaining to AI applications in the optimal control of the MSWI process.

show abstract

Section: Mimo Control (1) Double Input and Double Outputmentioning

confidence: 99%

An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process

Tang,

Wang,

Xia

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Leskens et al [86] constructed an ARX model for FGOC and SF. Furthermore, for FT, FGOC, and SF, Chen et al [36] constructed a cascade transfer function model based on adaptive weight PSO; Ding et al [34] built a T-S fuzzy neural network model; and Wang et al [48] built a hybrid ensemble model of random forest (RF) and gradient boosting decision tree (GBDT), whose strategy diagram is shown in Figure 7. The studies mentioned above support research in optimal control; however, they encounter challenges such as poor modeling accuracy and an unresolved issue regarding the model's adaptability under various operating conditions.…”

Section: Key Controlled Variablesmentioning

confidence: 99%

“…(2) Triple input and triple output For the concurrent regulation of furnace temperature, steam flow, and flue gas oxygen content, Ding et al [159] introduced a multiloop PID controller utilizing a quasidiagonal recurrent neural network. This controller exhibits the capability to dynamically adjust its parameters in response to error signals.…”

Section: Mimo Control (1) Double Input and Double Outputmentioning

confidence: 99%

“…The combustion process in MSWI faces notable challenges in achieving precise control compared to power generation processes utilizing coal and gas as input materials, primarily due to numerous interference factors and frequent fluctuations in operating conditions [101,159]. Despite the abundance of process data, their distribution is unbalanced.…”

Section: Intelligent Control Of Combustion Processmentioning

confidence: 99%

See 1 more Smart Citation

An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process

Tang,

Wang,

Xia

et al. 2024

Sustainability

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) has found widespread application across diverse domains, including residential life and product manufacturing. Municipal solid waste incineration (MSWI) represents a significant avenue for realizing waste-to-energy (WTE) objectives, emphasizing resource reuse and sustainability. Theoretically, AI holds the potential to facilitate optimal control of the MSWI process in terms of achieving minimal pollution emissions and maximal energy efficiency. However, a noticeable shortage exists in the current research of the review literature concerning AI in the field of WTE, particularly MSWI, hindering a focused understanding of future development directions. Consequently, this study conducts an exhaustive survey of AI applications for optimal control, categorizing them into four fundamental aspects: modeling, control, optimization, and maintenance. Timeline diagrams depicting the evolution of AI technologies in the MSWI process are presented to offer an intuitive visual representation. Each category undergoes meticulous classification and description, elucidating the shortcomings and challenges inherent in current research. Furthermore, the study articulates the future development trajectory of AI applications within the four fundamental categories, underscoring the contribution it makes to the field of MSWI and WTE.

show abstract

“…Ding et al used quasi-diagonal RNN to tune multivariable PID for the control of a municipal solid waste incineration plant. 25 Specific to the QT system, Xu et al showed that RNN can be adopted for solving the optimization problem of MPC for a QT system by ensuring a global minimum. 26 Bonassi and Scattolini used GRU, an RNN to model and control the QT system using IMC strategy.…”

Section: Introductionmentioning

confidence: 99%

Application of recurrent neural networks for modeling and control of a quadruple‐tank system

et al. 2023

View full text Add to dashboard Cite

The quadruple tank (QT) system consists of four interacting tanks and can switch between the minimum and non‐minimum phase behavior with changes in the positions of pump valves and is considered a benchmark control problem. In the present study, long‐short term memory (LSTM), a type of recurrent neural networks (RNN) is designed for the benchmark QT system based on the model‐based control framework. Random input–output sequences are generated from the white box model of the QT system to train an LSTM network model. The LSTM network is tuned by adjusting its hyperparameters such as the number of hidden layers, hidden units, and epochs to minimize the prediction error on the test data. The trained model is cross validated both during and after training to avoid overfitting. Once a reasonably reliable model is obtained, another LSTM network is trained for use as a controller. The network architecture is constantly modified till the controller is able to track the test setpoints with minimum error. This procedure is repeated with a gated recurrent unit (GRU) network and the servo and regulatory response of both the network models and controller are evaluated in terms of standard performance measure namely root mean square error (RMSE), integral square error (ISE), and control effort (CE). It is observed that the controller designed based on RNN performs better than a conventional centralized controller.

show abstract

MIMO modeling and multi-loop control based on neural network for municipal solid waste incineration

Cited by 16 publications

References 36 publications

An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process

An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process

An Overview of Artificial Intelligence Application for Optimal Control of Municipal Solid Waste Incineration Process

Application of recurrent neural networks for modeling and control of a quadruple‐tank system

Contact Info

Product

Resources

About