Journal of Process Control最新文献

The reliable assessment of the operational status during the silicon single crystal growth process is a prerequisite for ensuring system safety and improving crystal quality. However, in the actual silicon single crystal growth process, due to limitations in manpower, material resources, financial resources, and current technical methods, the establishment of monitoring models is still in its infancy. To address this issue, this paper proposes a hybrid deep belief network (HDBN) algorithm aided by the digital twin (DT) model to achieve real-time monitoring of equipment operational status. Firstly, this study constructs the DT model based on the basic principles of crystal growth, mainly to achieve high-precision simulation of the actual silicon single crystal growth process and generate abnormal data for the equipment. This operation can expand the sample set, enhance the diversity and coverage of data, and effectively solve the problem of insufficient sample size. Secondly, this study uses the variational mode decomposition (VMD) algorithm to decompose the dataset composed of obtained abnormal and normal data, and constructs sub-deep belief network (DBN) for the decomposed subsequences to capture deep feature information at different frequencies of the data. Subsequently, based on the concept of ensemble learning, the outputs of each sub-DBN network are used as inputs to construct the overall DBN network, achieving monitoring of the equipment operational status. Through the combination of VMD decomposition and DBN networks, this algorithm can better capture the frequency characteristics and time-domain features of the signal, enhancing monitoring accuracy. Experimental results show that this algorithm can accurately identify abnormal equipment states, effectively improve monitoring performance, and is of significant importance for the optimization and control of the semiconductor-grade silicon single crystal growth process, contributing to increased production efficiency and product quality.

The temperature within the sintering furnace is a decisive factor influencing the quality of the sintered ore in the iron ore sintering process. In practical operations, the temperature at the bellows directly linked to the bed layer indirectly signifies the internal furnace temperature. Maintaining a stable temperature at the bellows, particularly at the burn-through point, is vital for minimizing gas emissions, improving carbon efficiency, and enhancing the quality of the sintered ore. This paper proposes an intelligent temperature control system based on Spatial–Temporal Graph Convolutional and Disentangled Baseline-Volatility (STGCDBV) prediction. The STGCDBV network comprises three parallel modules: Adaptive Graph Convolution Network (AGCN), Baseline and Volatility Disentangler (BVD), and a residual link, along with a Temporal–Nodal Encoder–Decoder (TNED) module. The AGCN constructs a graph reflecting the characteristics of bellows temperature, effectively merging static spatial data with dynamic thermal information. The BVD module captures the nonlinear trend data inherent in the sintering process. In contrast, the TNED synergizes the insights from the parallel modules using cross encoding and decoding functionalities. For controlling the sintering gas flow rate, a Model Reference Adaptive Control (MRAC) system is implemented, which utilizes a control scheme founded on a temperature reference model and iterative parameter adjustments. Extensive experiments using actual time-series data from a steel plant have been conducted. Moreover, comparisons between the performance of pre- and post-control interventions demonstrate that the STGCDBV-MRAC system can stabilize temperature fluctuations and exhibit exemplary control proficiency.

Industrial processes frequently exhibit nonstationary characteristics due to factors like load fluctuations and external interference. Accurate monitoring of nonstationary industrial processes is of vital importance in ensuring production stability and safety. Unfortunately, most existing monitoring methods overlook the manifold structure presented in nonstationary data due to nonstationary features, causing the loss of critical information and poor interpretability. As a consequence, monitoring performance is compromised. To address this issue, this paper proposes a manifold embedding stationary subspace analysis (MESSA) algorithm. By embedding a neighborhood preservation term into the objective function of SSA, MESSA effectively mitigates the impact of nonstationarity on manifold structure. The extracted features incorporate both global stationarity and local manifold characteristics, facilitating a more comprehensive reconstruction of the intricate underlying mechanisms in industrial processes. This contributes to a substantial enhancement in the accuracy and reliability of process monitoring. A set of nonstationary swiss-roll dataset is designed to visually demonstrate the capability of MESSA in extracting manifold structure. Case studies including a numerical case, a continuous stirred tank reactor system and a real industrial roasting process validate the superior monitoring performance of the proposed method.

Circulating fluidized bed (CFB) units are extensively operated in China due to their wide fuel adaptability, low emissions and high combustion efficiency. Nevertheless, CFB units are facing many control challenges due to their strong nonlinearity and large lag characteristics. To handle these control challenges, a modified active disturbance rejection control based on gain scheduling is structured in this paper. Firstly, a decentralized active disturbance rejection control strategy based on gain scheduling is designed by analyzing control difficulties of CFB units. Then, the parameter tuning and scheduling methods are provided, and the convergence of the extended state observer during the scheduling process is derived theoretically. The advantages of the proposed method in tracking performance, disturbance rejection performance, and ability to reject fuel quality fluctuation and uncertain heat transfer coefficients are illustrated by comparative simulations. Finally, the proposed control strategy is practically applied to the main steam pressure system of a 300 MW CFB unit. Running data demonstrate that it has a faster tracking performance and better disturbance rejection ability in [50$\sim$100]% of the rated load, where the hourly average integral absolute error index has decreased obviously, and it shows a good field application prospect.

The supply temperature in district heating systems has traditionally been controlled using feedforward – a robust and well-validated approach for district heating networks with few producers and relatively high supply temperatures. The transition towards lower temperature district heating networks allows for efficient reuse of excess heat from, e.g., industrial processes and data centers. Excess heat is often intermittent, cannot always be assumed to be possible to control with a centralized controller, and can cause temperature disturbances in the grid. Closing the loop using PID control is challenging due to the process’s time-varying nature and long time delays. Model Predictive Control (MPC) suffers from a higher complexity, long computational times, and the need for a well-validated and maintained centralized model. The paper suggests a semi-decentralized approach using the Smith predictor with an event-driven assignment of active controllers and sensors. A reduced order model based on a more comprehensive state space model is derived and used for gain scheduling and input–output pairing using the normalized relative gain array. The focus is on temperature disturbance rejection, and appropriate tuning rules and controller structures are suggested. Simulation results show that the proposed control structure can handle various types of temperature disturbances, even in the presence of model estimation errors.

In many engineering fields, controlling the transient temperature field of the heat conduction process is significant practically. For the temperature field control problem, a spatiotemporal-response-correlation-based model predictive control (STRC-MPC) method is developed. In this method, a spatiotemporal mapping eigenvector of control inputs to temperature field is determined by transient heat conduction equations. According to the correlation degree between the temporal mapping eigenvectors of different spatial points, a finite number of representative spatial points (RPs) are extracted, of which can cover the full mapping characteristic of the temperature field. Meanwhile, the predictive model of the temperature field is reduced offline to temperature predictive models of the RPs. Then, the predictive models of the RPs are applied to design a model predictive controller of the temperature field. In addition, a correlation formulation between the temperature responses of the RPs and that of the measurement points (MPs) is derived by making the control inputs as intermediate variable, and a correlation model between the predictive errors of the two kinds of points is established. Combining the correlation model and the predictive errors of the MPs, the predictive errors at the RPs are estimated and the feedback correction of the predictive model of the RPs is achieved. The STRC-MPC method is employed to control the preheating temperature field of a die casting mold by numerical simulations. The model predictive controller and the feedback correction scheme involved in the proposed control method are verified respectively.

It is widely known that uncertainties, unknown disturbances, asynchronous switching, and partial actuator faults are the major factors that affect system stability during actual industrial production. For the above problems, a method of iterative learning robust MPC hybrid fault-tolerant control for multi-phase batch processes with asynchronous switching in two-dimensional systems is proposed. Exceptionally, an equivalent extended asynchronous switching fault-tolerant control model, including a synchronous sub-model and an asynchronous sub-model, is built. Then, Lyapunov theory, switching system theory, and so on are used as the theoretical basis, and the sufficient conditions to guarantee the stable operation of the system are given. Combined with the given conditions, the control law gain, the shortest running time, and the longest running time are solved in real time to eliminate the asynchronous switching situation problem. The state deviations of the system are corrected in time by avoiding the accumulation of the system state deviations over time, thus improving the control performance of the system. Meanwhile, by combining real-time control law gains with information about the batch direction, the method can significantly reduce the learning period of the controller and provide better control performance along the batch direction. Finally, the feasibility of the proposed method is verified with simulation experiments of the injection molding process.

A novel big data-driven predictive control (BDPC) approach for nonlinear processes is proposed. To deal with nonlinear process behaviours, the process behaviour space, represented by a set of input–output variable trajectories, is partitioned into linear sub-behaviour spaces (clusters), based on linear inclusion of nonlinear behaviours. A behaviour space (represented using Hankel matrices) partitioning approach is developed based on subspace angles. During online control, the BDPC controller locates the most relevant linear sub-behaviour based on the current online trajectory, which is then used to determine predictive control actions using receding horizon optimisation. The incremental stability and dissipativity conditions are developed to attenuate the effect of the error of approximating linear sub-behaviours on the output and guarantee closed-loop stability. These conditions are implemented as additional constraints during online data-driven predictive control. An example of controlling the Hall–Héroult process is used to illustrate the proposed approach.

Behavioral interventions (such as those developed to increase physical activity, achieve smoking cessation, or weight loss) can be represented as dynamic process systems incorporating a multitude of factors, ranging from cognitive (internal) to environmental (external) influences. This facilitates the application of system identification and control engineering methods to address questions such as: what drives individuals to improve health behaviors (such as engaging in physical activity)? In this paper, the goal is to efficiently estimate personalized, dynamic models which in turn will lead to control systems that can optimize this behavior. This problem is examined in system identification applied to the Just Walk study that aimed to increase walking behavior in sedentary adults. The paper presents a Discrete Simultaneous Perturbation Stochastic Approximation (DSPSA)-based modeling of the Goal Attainment construct estimated using AutoRegressive with eXogenous inputs (ARX) models. Feature selection of participants and ARX order selection is achieved through the DSPSA algorithm, which efficiently handles computationally expensive calculations. DSPSA can search over large sets of features as well as regressor structures in an informed, principled manner to model behavioral data within reasonable computational time. DSPSA estimation highlights the large individual variability in motivating factors among participants in Just Walk, thus emphasizing the importance of a personalized approach for optimized behavioral interventions.

In this paper, we present results with clinical data to enable a 2x2 input–output multivariable patient model for hypnosis and analgesia. Nonlinear multi-drug interaction models are identified from data recorded from 70 patients undergoing surgery during total intravenous anesthesia (TIVA) with several medical monitors for variables such as Bispectral Index, Nociception level (Medasense), skin conductance (Medstorm) and advanced spectral analysis conductance (AnspecPro). Bispectral index measures the depth of hypnosis (lack of consciousness), while nociception related indices from Medasense, Medstorm, and AnspecPro devices measure levels related to analgesia (lack of reaction to noxious stimuli). A comparison is given among three response surface model (RSM) structures – Minto, Greco, and Reduced Greco – for hypnotic and analgesic states during Propofol–Remifentanil interaction. The identified models capture the pharmacodynamic properties of dose–effect concentrations of Propofol/Remifentanil while the pharmacokinetic part of the patient model is calculated from patient’s biometric values using Schnider/Minto (SM), and Eleveld/Eleveld (EE) models. In presence of strict clinical protocols delivering data under poor identifiability conditions, we propose two methods of identification: (i) based on steady-state gains, and (ii) using all available data which includes part of the dynamic transient. The model parameters are optimized with Genetic Algorithm based on a goodness of fit performance measure complemented with root mean square error. The results suggest that the EE model combination is advantageous for Bispectral index pharmacokinetic modeling at the cost of numerical complexity, therefore reducing the uncertainty left to be identified in the pharmacodynamic part of the patient model. By contrast, the SM model combination is less computationally demanding and provides some improvement in the RSM accuracy for nociception level indicators. The comparison of three devices for nociception levels evaluation suggests that clinical data captured with the Medasense monitor provides best fitted RSMs with the Reduced Greco RSM structure, despite having fewer parameters.