Search

The zinc oxide rotary kiln, as an essential piece of equipment in the zinc smelting industrial process, is presenting new challenges in process control. China’s strategy of achieving a carbon peak and carbon neutrality is putting new demands on the industry, including green production and the use of fewer resources; thus, traditional stability control is no longer suitable for multi-objective control tasks. Although researchers have revealed the principle of the rotary kiln and set up computational fluid dynamics (CFD) simulation models to study its dynamics, these models cannot be directly applied to process control due to their high computational complexity. To address these issues, this paper proposes a multi-objective adaptive optimization model predictive control (MAO-MPC) method based on sparse identification. More specifically, with a large amount of data collected from a CFD model, a sparse regression problem is first formulated and solved to obtain a reduction model. Then, a two-layered control framework including real-time optimization (RTO) and model predictive control (MPC) is designed. In the RTO layer, an optimization problem with the goal of achieving optimal operation performance and the lowest possible resource consumption is set up. By solving the optimization problem in real time, a suitable setting value is sent to the MPC layer to ensure that the zinc oxide rotary kiln always functions in an optimal state. Our experiments show the strength and reliability of the proposed method, which reduces the usage of coal while maintaining high profits.

This paper proposes a dynamic-projection-integrated particle-filtering-based identification strategy for the friction characteristic curve of a train wheelset under the slipping fault condition. This strategy aims to achieve the identification of the fault friction characteristic curve (FFCC) in the early slipping fault stage. First, a multi-dimensional integrated particle-filtering (MDIPF)-based parameters correction method is proposed. The MDIPF constructs an error particle state transition model encompassing multi-dimensional parameters, which integrates inter-particle correlation to facilitate error fusion during the state transition process. Then, a dynamic projection domain (DPD)-based particle refinement method is proposed. The DPD constructed the contraction factors to dynamically fine-tune the particle projection domain. Finally, a multi-level evaluation-based identification method for the FFCC is proposed. And the dynamic-projection-integrated particle-filtering-based identification strategy is validated, which can actualize the rapid and accurate identification of the FFCC.

Abstract In turbofan engine datasets, to address problems, such as noise interference, diverse data types, large data volumes, complex feature extraction, inability to effectively describe degradation trends, and poor remaining useful life (RUL) prognosis effects, a remaining useful life prognosis model combining an improved stack sparse autoencoder (imSSAE) and an improved echo state network (imESN) is proposed in this paper. First, the 3-sigma criterion is adopted to remove the noise and reconstruct the data, and then the deep features of the engine are extracted by using an imSSAE and fused into health indicator (HI) curves describing the engine degradation trend. Finally, an attention mechanism is introduced into an imESN to adaptively process different types of data and obtain the RUL. The experimental results based on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset show that compared with the other popular RUL prediction models, the combined model proposed in this paper has higher prediction accuracy, and the evaluation indices also show the effectiveness and superiority of the model.

Currently, the research on the predictions of remaining useful life (RUL) of rotating machinery mainly focuses on the process of health indicator (HI) construction and the determination of the first prediction time (FPT). In complex industrial environments, the influence of environmental factors such as noise may affect the accuracy of RUL predictions. Accurately estimating the remaining useful life of bearings plays a vital role in reducing costly unscheduled maintenance and increasing machine reliability. To overcome these problems, a health indicator construction and prediction method based on multi-featured factor analysis are proposed. Compared with the existing methods, the advantages of this method are the use of factor analysis, to mine hidden common factors from multiple features, and the construction of health indicators based on the maximization of variance contribution after rotation. A dynamic window rectification method is designed to reduce and weaken the stochastic fluctuations in the health indicators. The first prediction time was determined by the cumulative gradient change in the trajectory of the HI. A regression-based adaptive prediction model is used to learn the evolutionary trend of the HI and estimate the RUL of the bearings. The experimental results of two publicly available bearing datasets show the advantages of the method.

Abstract This paper proposes an analytical delay propagation model for single railway lines based on the max‐plus algebra theory. The scheduling measures taken by dispatchers, including re‐timing and re‐ordering, will be incorporated into our delay propagation model using a matrix transformation method. An analysis of delay propagation under some typical emergencies such as segment blockages and train speed limitation is performed. Numerical simulations show that the proposed train delay propagation model can predict emergency‐induced train delays under different scheduling strategies, thus may give a guidance to improve the traffic management. In the high‐speed railway train system, the scheduling measures taken by dispatchers, such as re‐timing and re‐ordering, can be formulated as a delay propagation model using a matrix transformation method.

Cell voltage is a widely used signal that can be measured online from an industrial aluminum electrolysis cell. A variety of parameters for the analysis and control of industrial cells are calculated using the cell voltage. In this paper, the frequency segmentation of cell voltage is used as the basis for designing filters to obtain these parameters. Based on the qualitative analysis of the cell voltage, the sub-band instantaneous energy spectrum (SIEP) is first proposed, which is then used to quantitatively represent the characteristics of the designated frequency bands of the cell voltage under various cell conditions. Ultimately, a cell condition-sensitive frequency segmentation method is given. The proposed frequency segmentation method divides the effective frequency band into the [0, 0.001] Hz band of low-frequency signals and the [0.001, 0.050] Hz band of low-frequency noise, and subdivides the low-frequency noise into the [0.001, 0.010] Hz band of metal pad abnormal rolling and the [0.01, 0.05] Hz band of sub-low-frequency noise. Compared with the instantaneous energy spectrum based on empirical mode decomposition, the SIEP more finely represents the law of energy change with time in any designated frequency band within the effective frequency band of the cell voltage. The proposed frequency segmentation method is more sensitive to cell condition changes and can obtain more elaborate details of online cell condition information, thus providing a more reliable and accurate online basis for cell condition monitoring and control decisions.

Data-driven process-monitoring methods have been the mainstream for complex industrial systems due to their universality and the reduced need for reaction mechanisms and first-principles knowledge. However, most data-driven process-monitoring methods assume that historical training data and online testing data follow the same distribution. In fact, due to the harsh environment of industrial systems, the collected data from real industrial processes are always affected by many factors, such as the changeable operating environment, variation in the raw materials, and production indexes. These factors often cause the distributions of online monitoring data and historical training data to differ, which induces a model mismatch in the process-monitoring task. Thus, it is difficult to achieve accurate process monitoring when a model learned from training data is applied to actual online monitoring. In order to resolve the problem of the distribution divergence between historical training data and online testing data that is induced by changeable operation environments, a robust transfer dictionary learning (RTDL) algorithm is proposed in this paper for industrial process monitoring. The RTDL is a synergy of representative learning and domain adaptive transfer learning. The proposed method regards historical training data and online testing data as the source domain and the target domain, respectively, in the transfer learning problem. Maximum mean discrepancy regularization and linear discriminant analysis-like regularization are then incorporated into the dictionary learning framework, which can reduce the distribution divergence between the source domain and target domain. In this way, a robust dictionary can be learned even if the characteristics of the source domain and target domain are evidently different under the interference of a realistic and changeable operation environment. Such a dictionary can effectively improve the performance of process monitoring and mode classification. Extensive experiments including a numerical simulation and two industrial systems are conducted to verify the efficiency and superiority of the proposed method.

The accurate and timely online estimation of the alumina concentration in an industrial aluminum electrolysis cell can improve its feed control performance. By using the proposed marginal kurtosis (MK), marginal kurtosis dominant frequency (MK-DF), integral feed frequency and sensitive frequency band (SFB), this study reveals that a normalized cell voltage with different current intensities and feed schemes has different alumina concentration SFBs and determines the general formula for calculating the SFB. On this basis, a general algorithm for acquiring the pseudo alumina concentration (PAC) using translation-invariant filtering is proposed in which the upper limit of the SFB provides the cutoff frequency of the low-pass filter. The PAC was used to estimate the absolute and relative concentrations of alumina. The absolute concentrations are validated using measured concentrations. Additionally, improved feed control performance of the industrial cells is presented using the relative concentration PAC-slope.

Deep learning is an artificial intelligence technique developed in recent years.Compared with traditional shallow models,deep learning has a strong ability of feature representation and function fitting.It can extract hierarchical features from massive data,which has great potential for data-driven modeling in process industries.Firstly,the history of deep learning was introduced.Then,four widely used deep networks and their applications were introduced in data-driven modeling of process industries.At last,the conclusions about deep learning and its applications in process in dustries were given.

Inspired by the empirical mode decomposition (EMD)-enhanced gas detection work, this paper develops a further improved signal reconstruction method (namely EWT-ASG) for the demodulated harmonics of tunable diode laser absorption spectroscopy (TDLAS), which is mainly based on empirical wavelet transform (EWT) and Savitzky-Golay (S-G) filtering. First, the imported EWT performs better on the decomposition precision as it successfully bypasses the mode aliasing problem of EMD resulting by the lack of mathematical basis. Second, the improved S-G filter effectively suppresses the noisy components of the wavelet coefficients by updating its one key parameter (i.e., window size w) dynamically according to the correlation coefficients between the raw signals and the decomposed wavelet coefficients. The EWT-ASG scheme was first applied on the oxygen concentration detection for pharmaceutical glass vials. The preliminary experimental results indicate that the EWT-ASG method performs better than recent state-of-the-arts, with an average correct discrimination rate of 98.14% when the normalized SNR is 1. Even when the normalized SNR is degenerated from 1 to 0.85, our detection system still survived well, with a highest average correct discrimination rate of 90.45%. The detection system precision is also improved to a large extent, with a minimal Allan deviation of 0.856@(117s).

The goethite iron-removal process is an important procedure to remove the iron ions from the zinc hydrometallurgy. However, as a coherent system with complex reaction mechanism, associated uncertainties, and interconnected adjacent reactors, it is difficult for the process to accurately control the ion concentration. Because a large amount of historical data can be obtained during the process, an optimal control algorithm based on off-policy reinforcement learning is proposed in this paper to overcome these difficulties. According to the historical data, the weights of neural network are learned offline, and the optimal control strategy is solved online. Firstly, a bounded function is introduced to define the maximum effect of the coherent system on the subsystem cost function and to extend the cost function of the nominal system, so that the decentralized guaranteed cost control problem can be expressed as the optimal control problem of the nominal system. Then, an approximate iterative control algorithm based on actor-critic structure is proposed. The actor and critic neural networks are used to approximate control strategies and cost functions respectively. To achieve complete off-line, a new neural network is added to the actor-critic structure to approximate a part of the unknown system structure, and the three neural network parameters are optimized by the state transition algorithm. Finally, the strategy update and strategy iteration operations are performed alternately to learn optimal control strategies. The effectiveness and flexibility of the proposed off-policy optimal control method is validated by data from a real industrial goethite iron-removal process.

The lithium-ion batteries in the electric vehicles are nonlinear systems with complex electrochemical dynamics, and estimation of battery state-of-charge (SOC) is affected by factors such as environmental temperature and battery current. Considering the above problems, the accurate estimation of battery SOC has always been a difficult and the critical issue of battery management system (BMS). In this paper, the constant phase element (CPE) is introduced to the traditional time domain circuit model by analyzing the electrochemical impedance spectra of lithium-ion batteries. Accordingly, an equivalent circuit model based on electrochemical impedance is constructed by using fractional order theory, which has specific physical significant, leading to the improved estimation accuracy to represent battery voltage. Moreover, the polarization resistance in the model is replaced by Butler-Volmer (BV) equation, which can solve the problem caused by large current and temperature variation during the actual operation of electric vehicles. Next, based on the model, an $\text{H}\infty $ observer is designed for battery SOC estimation, and the proposed SOC observer is tested by real-time experimental data of battery. The efficiency of the proposed model and observer are validated by some simulations and experiment tests.

Industrial equipment health management is an extension of traditional fault diagnosis, which is a frontier research field of information science. The definition and application area of industrial equipment health management are first clarified, and then technologies related to health management are introduced, including feature analysis, fault diagnosis, fault prognosis and other technologies. The difficulties and bottlenecks of various technologies are expounded through comparative analysis, and a feasible scheme for future health management and integration is also discussed in this article.

In the aluminum reduction process, aluminum fluoride (AlF3) is added to lower the liquidus temperature of the electrolyte and increase the electrolytic efficiency. Making the decision on the amount of AlF3 addition (referred to in this work as MDAAA) is a complex and knowledge-based task that must take into consideration a variety of interrelated functions; in practice, this decision-making step is performed manually. Due to technician subjectivity and the complexity of the aluminum reduction cell, it is difficult to guarantee the accuracy of MDAAA based on knowledge-driven or data-driven methods alone. Existing strategies for MDAAA have difficulty covering these complex causalities. In this work, a data and knowledge collaboration strategy for MDAAA based on augmented fuzzy cognitive maps (FCMs) is proposed. In the proposed strategy, the fuzzy rules are extracted by extended fuzzy k-means (EFKM) and fuzzy decision trees, which are used to amend the initial structure provided by experts. The state transition algorithm (STA) is introduced to detect weight matrices that lead the FCMs to desired steady states. This study then experimentally compares the proposed strategy with some existing research. The results of the comparison show that the speed of FCMs convergence into a stable region based on the STA using the proposed strategy is faster than when using the differential Hebbian learning (DHL), particle swarm optimization (PSO), or genetic algorithm (GA) strategies. In addition, the accuracy of MDAAA based on the proposed method is better than those based on other methods. Accordingly, this paper provides a feasible and effective strategy for MDAAA. Keywords: AlF3 addition, Fuzzy cognitive maps, Learning algorithms, State transition algorithm, Fuzzy decision trees

At present, the research on the prediction of the remaining useful life (RUL) of machinery mainly focuses on multi-sensor feature extraction and then uses the features to predict RUL. In complex operations and multiple abnormal environments, the impact of noise may result in increased model complexity and decreased accuracy of RUL predictions. At the same time, how to use the sensor characteristics of time is also a problem. To overcome these issues, this paper proposes a dual-channel long short-term memory (LSTM) neural network model. Compared with the existing methods, the advantage of this method is to adaptively select the time feature and then perform first-order processing on the time feature value and use LSTM to extract the time feature and first-order time feature information. As the RUL curve predicted by the neural network is zigzag, we creatively designed a momentum-smoothing module to smooth the predicted RUL curve and improve the prediction accuracy. Experimental verification on the commercial modular aerospace propulsion system simulation (C-MAPSS) dataset proves the effectiveness and stability of the proposed method.

In industrial processes, the composition of raw material and the production environment are complex and changeable, which makes the production process have multiple steady states. In this situation, it is difficult for the traditional single-mode monitoring methods to accurately detect the process abnormalities. To this end, a multimode monitoring method based on the factor dynamic autoregressive hidden variable model (FDALM) for industrial processes is proposed in this paper. First, an improved affine propagation clustering algorithm to learn the model modal factors is adopted, and the FDALM is constructed by combining multiple high-order hidden state Markov chains through the factor modeling technology. Secondly, a fusion algorithm based on Bayesian filtering, smoothing, and expectation-maximization is adopted to identify model parameters. The Lagrange multiplier formula is additionally constructed to update the factor coefficients by using the factor constraints in the solving. Moreover, the online Bayesian inference is adopted to fuse the information of different factor modes and obtain the fault posterior probability, which can improve the overall monitoring effect of the model. Finally, the proposed method is applied in the sintering process of ternary cathode material. The results show that the fault detection rate and false alarm rate of this method are improved obviously compared with the traditional methods.

The fine control of endpoint temperatures of the dome and exhaust gas is the key to improving the heat storage efficiency and capacity of the pebble stove combustion process. However, owing to nonlinearity, time delay, uncertain endpoint time, and strong coupling issues of the combustion process, it is difficult to achieve the desired dome and exhaust gas endpoint temperatures, simultaneously. Therefore, a two-stage (fast heating stage and heat storage stage) control system for the endpoint temperature is developed for the combustion process of the pebble stove. According to the heat transfer theory and the principle of conservation of heat, a transient heat transfer model between the flue gas and the regenerator is developed for the combustion process of the pebble stove. Based on the transient heat transfer model, prediction models of the dome and exhaust gas endpoint temperatures are obtained by a finite-difference method. Moreover, to solve the strong coupling between the dome temperature in the fast heating period and the exhaust gas temperature in the thermal storage period, a two-stage intelligent proportion-integral-derivative decoupling control algorithm is developed based on a self-refreshing recurrent neural network to realize the decoupling control of the dome and exhaust gas endpoint temperatures. The performance of the developed system is demonstrated with simulation and industrial experiments. The results show that compared to the conventional control system, the developed system effectively shortens the adjusting time of the dome endpoint temperature by 13 min with a reduced temperature fluctuation from ±14 °C to ±4 °C and increases the exhaust gas endpoint temperature from 328.3 °C to 348.0 °C. The enhanced temperature control performance demonstrates the validity of the established system.

Generally, the main task of the optimal operation in the industrial process is to satisfy the process technical requirements, and the PID controller is a well-known controller in industrial control applications. Nevertheless, due to the complicated mechanisms and the dynamic characteristics of a complex industrial process, the conventional PID controller fails to provide effective control to such systems. In this paper, we develop a novel discrete-time fractional order PID (DFOPID) control strategy to achieve the technical requirements of the complex industrial process. The proposed work is conducted through a combination of three novel interdependent efforts. First, on the basis of the widely used Tustin operator and its Taylor series, a digital structure of the DFOPID is proposed. Second, in order to solve the stability problem of the complex industrial process, an optimal setting of the approximation function's order (N) and five parameters (λ, μ, Kp, Ki, Kd) is necessary. Hence, an integral time absolute error (ITAE) criterion is applied to convert the optimal setting problem to a nonconvex optimization problem. Finally, a novel intelligent optimization search algorithm called state transition algorithm is employed to carry out the aforementioned design procedure. Furthermore, the performance of the DFOPID control strategy in some practical industrial control systems, including the copper removal process and the electrochemical process of zinc are also investigated.

Considering the presence of time-delay in actuators and nonvanishing disturbance, a data-driven control technique is developed based on adaptive dynamic programming (ADP) to solve the reagents control problem for flotation processes. First, the reagents control problem is converted into an optimal regulator control problem. Second, a policy iteration (PI) algorithm has been adopted to find desirable adaptive suboptimal controllers. Unlike conventional controllers (PID, MPC) design, the proposed method can achieve the desired control performance by only employing online production data without the complete knowledge of the underlying flotation process dynamics. Specifically, the flotation indexes (tailing grade and concentrate grade) are forced to track the desired values with disturbance rejection and keep reagents consumption to a minimum. The convergence and stability of the proposed data-driven optimal control method are given, and the efficacy is validated in the simulation environment with industrial data.

The real-time, continuity, and accuracy of blast furnace stockline information are of great significance in reducing energy consumption and improving smelting efficiency. However, the traditional mechanical measurement method has the problem of measuring point discontinuity, while the radar measurement method exhibits problems such as weak anti-interference ability, low accuracy, and poor stability. Therefore, a high-dimensional, spatial feature stockline detection method based on the maximum likelihood radial basis function model (MLRBFM) and structural dynamic self-optimization RBF neural network (SDSO-RBFNN) is proposed. Firstly, the discrete time series joint partition method is used to extract the time dimension periodic features of the blast furnace stockline. Based on MLRBFM, the high-dimensional spatial features of the stockline are then obtained. Finally, an SDSO-RBFNN is constructed based on an eigen orthogonal matrix and a right triangular matrix decomposition (QR) direct clustering algorithm with spatial–temporal features as input, so as to obtain continuous, high-precision stockline information. Both the simulation results and industrial validation indicate that the proposed method can provide real-time and accurate stockline information, and has great practical value for industrial production.

Real-time, continuous and accurate blast furnace burden level information is of great significance for controlling the charging process, ensuring a smooth operation of a blast furnace, reducing energy consumption and emissions and improving blast furnace output. However, the burden level information measured by conventional mechanical stock rods and radar probes exhibit problems of weak anti-interference ability, large fluctuations in accuracy, poor stability and discontinuity. Therefore, a space-time fusion prediction and detection method of burden level based on a long-term focus memory network (LFMN) and an efficient structure self-tuning RBF neural network (ESST-RBFNN) is proposed. First, the space dimensional features are extracted by the space regression model based on radar data. Then, the LFMN is designed to predict the burden level and extract the time dimensional features. Finally, the ESST-RBFNN based on a proposed fast eigenvector space clustering algorithm (ESC) is constructed to obtain reliable and continuous burden level information with high accuracy. Both the simulation results and industrial verification indicate that the proposed method can provide real-time and continuous burden level information in real-time, which has great practical value for industrial production.

This paper presents a method for use in estimating the state of charge (SOC) of lithium-ion batteries which is based on an electrochemical impedance equivalent circuit model with a controlled source. Considering that the open-circuit voltage of a battery varies with the SOC, an equivalent circuit model with a controlled source is proposed which the voltage source and current source interact with each other. On this basis, the radial basis function (RBF) neural network is adopted to estimate the uncertainty in the battery model online, and a non-linear observer based on the radial basis function of the RBF neural network is designed to estimate the SOC of batteries. It is proved that the SOC estimation error is ultimately bounded by Lyapunov stability analysis, and the error bound can be arbitrarily small. The high accuracy and validity of the non-linear observer based on the RBF neural network in SOC estimation are verified with experimental simulation results. The SOC estimation results of the extended Kalman filter (EKF) are compared with the proposed method. It improves convergence speed and accuracy.

The traction converter is one of the key components of high-speed trains. Current and voltage sensor faults in the converter may lead to feedback values deviation and system degradation, which will bring security risks to the train. This paper proposes a real-time fault diagnosis method for grid current, DC-link voltage and stator current sensor faults in the traction converter with two stator current sensors, which can not only detect and locate faults but also identify the types of faults. Moreover, the faults considered in this paper are incipient. First, the DC-link model is established, and the fault is detected by the residual of the DC-link voltage. Next, the differential of DC-link voltage residual is calculated, which is applied to fault location. Then, according to the change of the differential values, different fault types are determined. Finally, the hardware-in-the-loop (HIL) platform is built and the effectiveness and accuracy of the proposed method are verified by the HIL tests.

A reasonable ultrasonic vibration network can improve the casting quality of aluminum alloy. Ultrasonic vibration network based on a honeycomb structure has been designed, referred to as a new vibration network. The new vibration network can solve the problems of nonuniform distribution of power ultrasonic wave, small working area and low volume of ultrasonic vibration network, low efficiency of the frequency spectrum and power spectrum, and poor quality of aluminum alloy casting. The number of vibration nodes can be determined based on the number of layers of the vibration source nodes. The edge length of regular hexagonal honeycomb cells can be determined based on the size of the casting ingot. The output power and resonant frequency of the ultrasonic vibration network can be adjusted in real time according to the status of aluminum alloy melt. A seven-node new ultrasonic network and a four-node ultrasonic network with a traditional structure were selected and used in the experiment and simulation of a 500 mm diameter 2219 aluminum alloy ingot. In comparison with the traditional four-node ultrasonic network, the effective volume and area, frequency spectrum efficiency, and comprehensive coverage probability of the seven-node new ultrasonic vibration network increased by 34.06%, 23.12%, 17.25%, and 0.308, respectively. The difference between the desired value and average efficiency of the power spectrum was 0.292 W/cm2, and the average grain size of aluminum alloy decreased by 34.98 microns. These results indicate that the efficiency of ultrasonic-vibration-assisted casting system and the quality of aluminum alloy casting can be improved using the new ultrasonic vibration network.

The goethite process is complicated since its chemical reactions interact with each other, making its control and optimization in industrial production difficult. The goal of the goethite process is to make the outlet ion concentration satisfy the technical requirements with minimal process consumption. To simplify the difficulties of optimization in the goethite process, an optimization method based on a setpoint tracking strategy is proposed. The set-point tracking strategy is used to transform the complex state constraints into an additional objective. Therefore, the single optimization control problem for the goethite process is transformed into a bi-objective optimization control problem. Furthermore, PID controllers are adopted to control the addition amounts of zinc oxide and oxygen in the goethite process. The optimal parameters of the PID controllers are obtained via a multi-objective state transition algorithm (MOSTA). The performance of MOSTA is verified by several benchmark test functions with performance matrices. The control performance reveals that the proposed method is an effective way to control the process and can not only reduce the zinc oxide and oxygen addition amounts compared with manual operation and traditional PID control but also reject disturbances. The proposed method can satisfy the industrial requirements with less energy consumption.

This paper is concerned with the issue of adaptive fuzzy sliding mode control for fuzzy underactuated translational oscillator with rotating actuator (TORA). Since the system considered in this paper is accompanied by strong inputs coupling and nonlinear characteristics, the feedback decoupling and fuzzy technique are introduced to establish a linear fuzzy underactuated TORA system. The two-order fuzzy sliding surface with adaptive parameters is designed, where the adaptive control is introduced to adjust the parameters of sliding surface such that the system performance could be improved. The sliding mode control law is synthesized to guarantee the sliding mode dynamics to be asymptotically stable and robust, and the reachability analysis is presented to ensure that the system trajectories can be driven onto the sliding mode surface and remain there for the subsequent time. Simulation results are provided to compare with the existing results and validate the effectiveness and feasibility of the proposed scheme.

Due to the ubiquitous dynamics of industrial processes, the variable time lag raises great challenge to the high-precision industrial process monitoring. To this end, a process monitoring method based on the dynamic autoregressive latent variable model is proposed in this paper. First, from the perspective of process data, a dynamic autoregressive latent variable model (DALM) with process variables as input and quality variables as output is constructed to adapt to the variable time lag characteristic. In addition, a fusion Bayesian filtering, smoothing and expectation maximization algorithm is used to identify model parameters. Then, the process monitoring method based on DALM is constructed, in which the process data are filtered online to obtain the latent space distribution of the current state, and T2 statistics are constructed. Finally, by comparing with an existing method, the feasibility and effectiveness of the proposed method is tested on the sintering process of ternary cathode materials. Detailed comparisons show the superiority of the proposed method.

This paper investigates the problem of guaranteed cost control of an interval type-2 Takagi-Sugeno fuzzy descriptor systems with time-varying delays satisfying probabilistic characteristics. In order to fully consider the delay distributions, the delay segmentation approach is introduced. Then, an interval type-2 fuzzy controller is designed such that the closed-loop fuzzy descriptor system is regular, causal, mean square asymptotically stable, and the corresponding quadratic cost function is guaranteed which lower than a certain upper bound. Finally, one simulation example is given to demonstrate the effectiveness of the proposed method.

In complex industrial processes, the knowledge has properties of multi-source heterogeneity, polymorphism, and uncertainty. When the conventional knowledge representation methods are used to represent this type of knowledge, they often result in misunderstanding, inexplicability, and ambiguity. To solve this problem, a semantic network based on intuitionistic fuzzy directed hyper-graphs (SN-IFDHGs) model is proposed. First, qualitative knowledge is transformed to quantitative knowledge using an intuitionistic fuzzy algorithm. In the SN-IFDHG model, an edge set can connect multiple vertexes, which mean multi-source knowledge elements. Meanwhile, to present uncertain knowledge, the weights between semantic nodes are characterized by simultaneously containing both membership and non-membership. Then, to reduce the space complexity and facilitate the reconstruction of the SN-IFDHG model, a novel storage structure based on in-degree index list is proposed. Finally, a knowledge reasoning method based on entropy weight of SN-IFDHG is proposed and applied to aluminum electrolysis cell condition identification. The experimental results show that the proposed knowledge reasoning method is more effective and accurate than other existing algorithms.

In the manufacturing process of ternary cathode material, batching, mixing, loading, and sintering procedures play decisive roles in product quality, and data generated by these procedures are collected by the ternary cathode material cyber-physical system (TCM-CPS). However, the data of the process are heterogeneous and have different properties, and sampling of key quality variables is difficult. On this basis, on-line evaluation of product quality is hard. In this study, a data fusion based on-line product quality evaluation method of TCM-CPS is proposed. Data features of each procedure are firstly extracted and fused by combining feature indices and kernel principal component analysis. Then, in order to establish the model between the extracted data features and the key quality variables such as particle size and surface-free lithium content, a semi-supervised double-weighted probabilistic principal component regression is proposed. After that, a distance cost index is brought to cluster and grade the two quality variables, which are predicted by the semi-supervised model. Moreover, the on-line evaluation of product performance is achieved by setting a rule table in accordance with production experience. Finally, an industrial application verifies the proposed method, of which the effective and accuracy can be acquired from results.

Fault diagnosis under the condition of data sets or samples with only a few fault labels has become a hot spot in the field of machinery fault diagnosis. To solve this problem, a fault diagnosis method based on deep transfer learning is proposed. Firstly, the discriminator of the generative adversarial network (GAN) is improved by enhancing its sparsity, and then adopts the adversarial mechanism to continuously optimize the recognition ability of the discriminator; finally, the parameter transfer learning (PTL) method is applied to transfer the trained discriminator to target domain to solve the fault diagnosis problem with only a small number of label samples. Experimental results show that this method has good fault diagnosis performance.

The prognosis of the remaining useful life (RUL) of turbofan engine provides an important basis for predictive maintenance and remanufacturing, and plays a major role in reducing failure rate and maintenance costs. The main problem of traditional methods based on the single neural network of shallow machine learning is the RUL prognosis based on single feature extraction, and the prediction accuracy is generally not high, a method for predicting RUL based on the combination of one-dimensional convolutional neural networks with full convolutional layer (1-FCLCNN) and long short-term memory (LSTM) is proposed. In this method, LSTM and 1- FCLCNN are adopted to extract temporal and spatial features of FD001 andFD003 datasets generated by turbofan engine respectively. The fusion of these two kinds of features is for the input of the next convolutional neural networks (CNN) to obtain the target RUL. Compared with the currently popular RUL prediction models, the results show that the model proposed has higher prediction accuracy than other models in RUL prediction. The final evaluation index also shows the effectiveness and superiority of the model.

Visual perception-based methods are a promising means of capturing the surface damage state of wire ropes and hence provide a potential way to monitor the condition of wire ropes. Previous methods mainly concentrated on the handcrafted feature-based flaw representation, and a classifier was constructed to realize fault recognition. However, appearances of outdoor wire ropes are seriously affected by noises like lubricating oil, dust, and light. In addition, in real applications, it is difficult to prepare a sufficient amount of flaw data to train a fault classifier. In the context of these issues, this study proposes a new flaw detection method based on the convolutional denoising autoencoder (CDAE) and Isolation Forest (iForest). CDAE is first trained by using an image reconstruction loss. Then, it is finetuned to minimize a cost function that penalizes the iForest-based flaw score difference between normal data and flaw data. Real hauling rope images of mine cableways were used to test the effectiveness and advantages of the newly developed method. Comparisons of various methods showed the CDAE-iForest method performed better in discriminative feature learning and flaw isolation with a small amount of flaw training data.

Capturing the three-dimensional (3D) shape of the burden surface of a blast furnace (BF) in real-time with high accuracy is crucial for improving gas flow distribution, optimizing coke operation, and stabilizing BF operation. However, it is difficult to perform 3D shape measurement of the burden surface in real-time during the ironmaking process because of the high-temperature, high-dust, and lightless enclosed environment inside the BF. To solve this problem, a real-time 3D measurement system is developed in this study by combining an industrial endoscope with a virtual multi-head camera array 3D reconstruction method. First, images of the original burden surface are captured using a purpose-built industrial endoscope. Second, a novel micro-pixel luminance polarization method is proposed and applied to compensate for the heavy noise in the backlit images due to high dust levels and poor light in the enclosed environment. Third, to extract depth information, a multifeature-based depth key frame classifier is designed to filter out images with high levels of clarity and displacement. Finally, a 3D shape burden surface reconstruction method based on a virtual multi-head camera array is proposed for capturing the real-time 3D shape of the burden surface in an operational BF. The results of an industrial experiment illustrate that the proposed method can measure the 3D shape of the entire burden surface and provide reliable burden surface shape information for BF control.

The cerebellum contains 80% of all neurons in the human brain and contributes prominently to implicit learning and predictive processing across motor, sensory, and cognitive domains. As morphological features of the cerebellum in atypically developing individuals remain unexplored in-vivo, this is the first study to use high-resolution 3D fractal analysis to estimate fractal dimension (FD), a measure of structural complexity of an object, of the left and right cerebellar cortex (automatically segmented from Magnetic Resonance Images using FreeSurfer), in male children with Autism Spectrum Disorders (ASD) (N = 20; mean age: 8.8 years old, range: 7.13-10.27) and sex, age, verbal-IQ, and cerebellar volume-matched typically developing (TD) boys (N = 18; mean age: 8.9 years old, range: 6.47-10.52). We focus on an age range within the 'middle and late childhood' period of brain development, between 6 and 12 years. A Mann-Whitney U test revealed a significant reduction in the FD of the right cerebellar cortex in ASD relative to TD boys (P = 0.0063, Bonferroni-corrected), indicating flatter and less regular surface protrusions in ASD relative to TD males. Consistent with the prediction that the cerebellum participates in implicit learning, those ASD boys with a higher (vs. lower) PIQ>VIQ difference showed higher, more normative complexity values, closer to TD children, providing new insight on our understanding of the neurological basis of differences in verbal and performance cognitive abilities that often characterize individuals with ASD.

Texture pattern classification has long been an essential issue in computer vision (CV). However, texture is a kind of perceptual concept of human beings in scene observation or content understanding, which cannot be defined or described clearly in CV. Visually, the visual appearance of the complex spatial structure (CSS) of texture pattern (TP) generally depends on the random organization (or layout) of local homogeneous fragments (LHFs) in the imaged surface. Hence, it is essential to investigate the latent statistical distribution (LSD) behavior of LHFs for distinctive CSS feature characterization to achieve good classification performance. This work presents an image statistical modeling-based TP identification (ISM-TPI) method. It firstly makes a theoretical explanation of the Weibull distribution (WD) behavior of the LHFs of the imaged surface in the imaging process based on the sequential fragmentation theory (SFT), which consequently derives a symmetrical WD model (SWDM) to characterize the LSD of the TP’s SS. Multidirectional and multiscale TP features are then characterized by the SWDM parameters based on the oriented differential operators; in other words, texture images are convolved with multiscale and multidirectional Gaussian derivative filters (GDFs), including the steerable isotropic GDFs (SIGDFs) and the oriented anisotropic GDFs (OAGDFs), for the omnidirectional and multiscale SS detail exhibition with low computational complexity. Finally, SWDM-based TP feature parameters, demonstrated to be directly related to the human vision perception system with significant physical perception meaning, are extracted and used to TP classification with a partial least squares-discriminant analysis- (PLS-DA-) based classifier. The effectiveness of the proposed ISM-TPI method is verified by extensive experiments on three texture image databases. The classification results demonstrate the superiority of the proposed methods over several state-of-the-art TP classification methods.

The optimal regulation properties of multi-input and multioutput (MIMO) discrete-time networked control systems (NCSs), over additive white Gaussian noise (AWGN) fading channels, based on state space representation, are investigated. The average performance index is introduced. Moreover, the regulation performance is measured by the control energy and the error energy of the system, and fundamental limitations are obtained. Two kinds of network parameters, fading and the additive white Gaussian noise, are considered. The best attainable regulation performance limitations can be obtained by the limiting steady state solution of the corresponding algebraic Riccati equation (ARE). The simulation results are given to demonstrate the main results of the theoretical development.

A failure of adaptive inference-misinterpreting available sensory information for appropriate perception and action-is at the heart of clinical manifestations of schizophrenia, implicating key subcortical structures in the brain including the hippocampus. We used high-resolution, three-dimensional (3D) fractal geometry analysis to study subtle and potentially biologically relevant structural alterations (in the geometry of protrusions, gyri and indentations, sulci) in subcortical gray matter (GM) in patients with schizophrenia relative to healthy individuals. In particular, we focus on utilizing Fractal Dimension (FD), a compact shape descriptor that can be computed using inputs with irregular (i.e., not necessarily smooth) surfaces in order to quantify complexity (of geometrical properties and configurations of structures across spatial scales) of subcortical GM in this disorder. Probabilistic (entropy-based) information FD was computed based on the box-counting approach for each of the seven subcortical structures, bilaterally, as well as the brainstem from high-resolution magnetic resonance (MR) images in chronic patients with schizophrenia (n = 19) and age-matched healthy controls (n = 19) (age ranges: patients, 22.7-54.3 and healthy controls, 24.9-51.6 years old). We found a significant reduction of FD in the left hippocampus (median: 2.1460, range: 2.07-2.18 vs. median: 2.1730, range: 2.15-2.23, p

The temperature measurement of blast furnace (BF) molten iron is a mandatory requirement in the ironmaking process, and the molten iron temperature is significant in estimating the molten iron quality and control blast furnace condition. However, it is not easy to realize real-time measurement of molten iron temperature because of the harsh environment in the blast furnace casthouse and the high-temperature characteristics of molten iron. To achieve continuous detection of the molten iron temperature of the blast furnace, this paper proposes a temperature measurement method based on infrared thermography and a temperature reduction model. Firstly, an infrared thermal imager is applied to capture the infrared thermal image of the molten iron flow after the skimmer. Then, based on the temperature distribution of the molten iron flow region, a temperature mapping model is established to measure the molten iron temperature after the skimmer. Finally, a temperature reduction model is developed to describe the relationship between the molten iron temperature at the taphole and skimmer, and the molten iron temperature at the taphole is calculated according to the temperature reduction model and the molten iron temperature after the skimmer. Industrial experiment results illustrate that the proposed method can achieve simultaneous measurement of molten iron temperature at the skimmer and taphole and provide reliable temperature data for regulating the blast furnace.

Froth flotation is a vital mineral concentration process. Froth surface behavior is the knowledge about flotation working condition. However, in computer vision aided froth surface behavior control, there are still two challenges that need to be tackled seriously. Against the difficulty in the froth surface behavior representation, this paper proposes to combine the bubble size distribution (BSD) and froth velocity distribution. As far as we know, this is the first time that the froth velocity distribution is presented. Against the difficulty in the adaptive generation of the optimal froth surface behavior feature (optimal setpoint), this paper introduces the fuzzy apriori to mine the association rule between the current working condition and the optimal setpoint. Then, a fuzzy inference module is constructed to generate optimal setpoint for current working condition adaptively. Many validation experiments and comparison experiments demonstrate the superiority and robustness of the proposed methods.

In flotation processes, concentrate grade is the key production index but is difficult to be measured online. The mechanism models reflect the basic tendency of concentrate grade changes but cannot provide adequate prediction precision. The data-driven models based on froth image features provide accurate prediction within well-sampled space but rely heavily on sample data with less generalization capability. So, a hybrid intelligent model combining the two kinds of model is proposed in this paper. Since the information of image features is enormous, and the relationship between image features and concentrate grade is nonlinear, a B-spline partial least squares (BS-PLS) method is adopted to construct the data-driven model for concentrate grade prediction. In order to gain better generalization capability and prediction accuracy, information entropy is introduced to integrate the mechanism model and the BS-PLS model together and modify the model output online through an output deviation compensation strategy. Moreover, a slide window scheme is employed to update the hybrid model in order to improve its adaptability. The industrial practical data testing results show that the performance of the hybrid model is better than either of the two single models and it satisfies the accuracy and stability requirements in industrial applications.

A novel froth image analysis based production condition recognition method is presented to identify the froth phases under various production conditions. Gabor wavelet transformation is employed to froth image processing firstly due to the ability of Gabor functions in simulating the response of the simple cells in the visual cortex. Successively, the statistical distribution profiles based feature parameters of the Gabor filter responses rather than the conventional mean and variance are extracted to delineate the essential statistical information of the froth images. The amplitude and phase representations of the Gabor filter responses are both taken into account by empirical marginal and joint statistical modeling. At last, a simple learning vector quantization (LVQ) neural network model is used to learn an effective classifier to recognize the froth production conditions. The effectiveness of this method is validated by the real production data on industrial scale from a bauxite dressing plant.

The grinding-classification is the prerequisite process for full recovery of the nonrenewable minerals with both production quality and quantity objectives concerned. Its natural formulation is a constrained multiobjective optimization problem of complex expression since the process is composed of one grinding machine and two classification machines. In this paper, a hybrid differential evolution (DE) algorithm with multi-population is proposed. Some infeasible solutions with better performance are allowed to be saved, and they participate randomly in the evolution. In order to exploit the meaningful infeasible solutions, a functionally partitioned multi-population mechanism is designed to find an optimal solution from all possible directions. Meanwhile, a simplex method for local search is inserted into the evolution process to enhance the searching strategy in the optimization process. Simulation results from the test of some benchmark problems indicate that the proposed algorithm tends to converge quickly and effectively to the Pareto frontier with better distribution. Finally, the proposed algorithm is applied to solve a multiobjective optimization model of a grinding and classification process. Based on the technique for order performance by similarity to ideal solution (TOPSIS), the satisfactory solution is obtained by using a decision-making method for multiple attributes.

In this paper, an adaptive segmentation based image processing method is presented for mineral flotation processes so as to obtain an optimal quality profile measure. An optimal structural element (SE) is firstly provided for initial image segmentation where fuzzy c-means (FCM) algorithm is combined with a watershed algorithm. Then, the extracted fuzzy texture spectrum feature is discriminated as either under-segmentation or over-segmentation regions. Finally, the segmentation results are subsequently processed to estimate the output probability density function (PDF) of bubble size distribution, which is the basis of the fault detection and real-time control for flotation processes. Experimental results demonstrate that the proposed method avoids both over-segmentation and under segmentation, and reveal the reliability of bubble size distribution nonparametric density estimation.