A Multi-Featured Factor Analysis and Dynamic Window Rectification Method for Remaining Useful Life Prognosis of Rolling Bearings.

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.

Real-Time Detection and Short-Term Prediction of Blast Furnace Burden Level Based on Space-Time Fusion Features.

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.

High-Precision Real-Time Detection of Blast Furnace Stockline Based on High-Dimensional Spatial Characteristics.

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.

Voltage and Current Sensor Fault Diagnosis Method for Traction Converter with Two Stator Current Sensors.

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 Monitoring Method Based on FDALM and Its Application in the Sintering Process of Ternary Cathode Material.

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.

Optimal setting strategy of electrocoagulation process in heavy metal wastewater treatment plant.

With the increasingly stringent environmental protection policies of various countries, the contradiction between the treatment cost and the purification degree of environmental pollutants has become increasingly significant, which has become a major factor restricting the efficient operation of wastewater treatment plants. Hence, keeping the ion concentration at the outlet as low as possible while reducing the cost are the main objectives of treating heavy metal wastewater by electrocoagulation (EC) process. However, due to the complicated mechanism and uncertain production conditions, it is difficult to achieve those goals by manually setting the current through operators' experience. In this paper, we develop a dynamic multi-objective optimization strategy for EC process to balance these two conflicting production targets. First, we define the removal efficiency (RE) to measure the effectiveness of the EC process. Due to the anodic passivation and cathodic polarization in the EC process, the current reversing period (CRP) is proposed and optimized to ensure the stable performance of the electrodes. Then the current setting problem is formulated as a constrained multi-objective optimization problem with competing objectives of RE and cost. An interval-adjustable control parameterization (CP) approach is developed to reduce the complexity of this optimization problem. To compute this optimization problem, a heuristic method named multi-objective state transition algorithm (MOSTA) with evaluation value is investigated. The effectiveness of our model and optimization strategy is demonstrated by a successful implementation in an EC process of a wastewater treatment plant in Chenzhou, China.

Remaining Useful Life Prediction Using Dual-Channel LSTM with Time Feature and Its Difference.

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.

A Remaining Useful Life Prognosis of Turbofan Engine Using Temporal and Spatial Feature Fusion.

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.

Convolutional Autoencoder-Based Flaw Detection for Steel Wire Ropes.

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.

A Real-Time 3D Measurement System for the Blast Furnace Burden Surface Using High-Temperature Industrial Endoscope.

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.

Production optimization for concentration and volume-limited fed-batch reactors in biochemical processes.

Since a very slight violation of constraint could cause process safety and product quality problems in biochemical processes, an adaptive approach of fed-batch reactor production optimization that can strictly satisfy constraints over the entire operating time is presented. In this approach, an improved smooth function is proposed such that the inequality constraints can be transformed into smooth constraints. Based on this, only an auxiliary state is needed to monitor violations in the augmented performance index. Combined with control variable parameterization (CVP), the dynamic optimization is executed and constraint violations are examined by calculating the sensitivities of states to ensure that the inequality constraints are satisfied everywhere inside the time interval. Three biochemical production optimization problems, including the manufacturing of ethanol, penicillin and protein, are tested as illustrations. Meanwhile, comparisons with pure penalty CVP method, famous dynamic optimization toolbox DOTcvp and literature results are carried out. Research results show that the proposed method achieves better performances in terms of optimization accuracy and computation cost.

Temperature Measurement Method for Blast Furnace Molten Iron Based on Infrared Thermography and Temperature Reduction Model.

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.

Sensitivity-based adaptive mesh refinement collocation method for dynamic optimization of chemical and biochemical processes.

Collocation on finite element (CFE) is an effective simultaneous method of dynamic optimization to increase the profitability or productivity of industrial process. The approach needs to select an optimal mesh of time interval to balance the computational cost with desired solution. A new CFE approach with non-uniform refinement procedure based on the sensitivity analysis for dynamic optimization problems is, therefore, proposed, where a subinterval is further refined if the obtained control parameters have significant effect on the performance index. To improve the efficiency, the sensitivities of state parameters with respect to control parameters are derived from the solution of the discretized dynamic system. The proposed method is illustrated by testing two classic dynamic optimization problems from chemical and biochemical engineering. The detailed comparisons among the proposed method, the CFE with uniform mesh, and other reported methods are also carried out. The research results reveal the effectiveness of the proposed approach.

Selective Search and Intensity Context Based Retina Vessel Image Segmentation.

In the framework of computer-aided diagnosis of eye disease, a new contextual image feature named influence degree of average intensity is proposed for retinal vessel image segmentation. This new feature evaluates the influence degree of current detected pixel decreasing the average intensity of the local row where that pixel located. Firstly, Hessian matrix is introduced to detect candidate regions, for the reason of accelerating segmentation. Then, the influence degree of average intensity of each pixel is extracted. Next, contextual feature vector for each pixel is constructed by concatenating the 8 feature neighbors. Finally, a classifier is built to classify each pixel into vessel or non-vessel based on its contextual feature. The effectiveness of the proposed method is demonstrated through receiver operating characteristic analysis on the benchmarked databases of DRIVE and STARE. Experiment results show that our method is comparable with the state-of-the-art methods. For example, the average accuracy, sensitivity, specificity achieved on the database DRIVE and STARE are 0.9611, 0.8174, 0.9747 and 0.9547, 0.7768, 0.9751, respectively.

[Fast Classification of Complex Sulphide Ore Based on Raman Spectroscopy].

The regional features, metallogenitic regularities and mineral composition of the hydrothermal sulphide ore have been preliminarily studied. According to the different mineralization period, the patterns of valuable minerals disseminated in ore are complicated, which causes the large changes in the properties of the sulphide ore. The different properties of the sulphide ore may increase the difficulty of the mineral processing and reduce the recovery rate of valuable minerals. Therefore a simple method for rapidly classification of sulphide ore is required to optimize mineral processing flowsheet. Laser Raman spectrometry, as an effective method to analyze the structure of the material is used to identify the component and structure of minerals. The research on the Laser Raman spectra of the large number of sulphide ore samples can reveal the reasons for the difference of the Raman spectra. A new method for classifying the complex sulphide ore using Raman spectroscopy is proposed. The experiment results demonstrate that the properties of the sulphide ore in different mineralization period vary greatly and the fluorescent scattering is mainly produced by gangue minerals. The measured Raman spectral after quenching the fluorescence scattering show the peaks of Raman spectra at 201.62, 242.54, 288.38 and 309.77 cm-1 can be used to identify this kind of complex sulphide ore. The raw ore can be divided into three categories based on the difference of the intensity of fluorescence scattering and the ratio of fluorescence and Raman intensity. The accuracy of the classification method is further validated by the industrial tests. The findings demonstrate the close relationship between Raman spectra and the properties of sulphide ore. The proposed method, which can fast classify the sulphide ore, don't need complex chemical pretreatment before spectra collection. Therefore, this method will have important application value for improving the efficiency of mineral processing.

Optimal Reconstruction of Probabilistic Boolean Networks.

In gene regulatory networks (GRNs), it is important to model gene regulation based on a priori information and experimental data. As a useful mathematical model, probabilistic Boolean networks (PBNs) have been widely applied in GRNs. This article addresses the optimal reconstruction problem of PBNs based on several priori Boolean functions and sampled data. When all candidate Boolean functions are known in advance, the optimal reconstruction problem is reformulated into an optimization problem. This problem can be well solved by a recurrent neural network approach which decreases the computational cost. When parts of candidate Boolean functions are known in advance, necessary and sufficient conditions are provided for the reconstruction of PBNs. In this case, two types of reconstruction problems are further proposed: one is aimed at minimizing the number of reconstructed Boolean functions, and the other one is aimed at maximizing the selection probability of the main dynamics under noises. At last, examples in GRNs are elaborated to demonstrate the effectiveness of the main results.

Error-Triggered Adaptive Sparse Identification for Predictive Control and Its Application to Multiple Operating Conditions Processes.

With the digital transformation of process manufacturing, identifying the system model from process data and then applying to predictive control has become the most dominant approach in process control. However, the controlled plant often operates under changing operating conditions. What is more, there are often unknown operating conditions such as first appearance operating conditions, which make traditional predictive control methods based on identified model difficult to adapt to changing operating conditions. Moreover, the control accuracy is low during operating condition switching. To solve these problems, this article proposes an error-triggered adaptive sparse identification for predictive control (ETASI4PC) method. Specifically, an initial model is established based on sparse identification. Then, a prediction error-triggered mechanism is proposed to monitor operating condition changes in real time. Next, the previously identified model is updated with the fewest modifications by identifying parameter change, structural change, and combination of changes in the dynamical equations, thus achieving precise control to multiple operating conditions. Considering the problem of low control accuracy during the operating condition switching, a novel elastic feedback correction strategy is proposed to significantly improve the control accuracy in the transition period and ensure accurate control under full operating conditions. To verify the superiority of the proposed method, a numerical simulation case and a continuous stirred tank reactor (CSTR) case are designed. Compared with some state-of-the-art methods, the proposed method can rapidly adapt to frequent changes in operating conditions, and it can achieve real-time control effects even for unknown operating conditions such as first appearance operating conditions.

A Spatial-Temporal Variational Graph Attention Autoencoder Using Interactive Information for Fault Detection in Complex Industrial Processes.

Modern industry processes are typically composed of multiple operating units with reaction interaction and energy-mass coupling, which result in a mixed time-varying and spatial-temporal coupling of process variables. It is challenging to develop a comprehensive and precise fault detection model for the multiple interconnected units by simple superposition of the individual unit models. In this study, the fault detection problem is formulated as a spatial-temporal fault detection problem utilizing process data of multiple interconnected unit processes. A spatial-temporal variational graph attention autoencoder (STVGATE) using interactive information is proposed for fault detection, which aims to effectively capture the spatial and temporal features of the interconnected unit processes. First, slow feature analysis (SFA) is implemented to extract temporal information that reveals the dynamic relevance of the process data. Then, an integration method of metric learning and prior knowledge is proposed to construct coupled spatial relationships based on temporal information. In addition, a variational graph attention autoencoder (VGATE) is suggested to extract temporal and spatial information for fault detection, which incorporates the dominances of variational inference and graph attention mechanisms. The proposed method can automatically extract and deeply mine spatial-temporal interactive feature information to boost detection performance. Finally, three industrial process experiments are performed to verify the feasibility and effectiveness of the proposed method. The results demonstrate that the proposed method dramatically increases the fault detection rate (FDR) and reduces the false alarm rate (FAR).

ADP-Based Event-Triggered Constrained Optimal Control on Spatiotemporal Process: Application to Temperature Field in Roller Kiln.

The precise control of the spatiotemporal process in a roller kiln is crucial in the production of Ni-Co-Mn layered cathode material of lithium-ion batteries. Since the product is extremely sensitive to temperature distribution, temperature field control is of great significance. In this article, an event-triggered optimal control (ETOC) method with input constraints for the temperature field is proposed, which takes up an important position in reducing the communication and computation costs. A nonquadratic cost function is adopted to describe the system performance with input constraints. First, we present the problem description of the temperature field event-triggered control, where this field is described by a partial differential equation (PDE). Then, the event-triggered condition is designed according to the information of system states and control inputs. On this basis, a framework of the event-triggered adaptive dynamic programming (ETADP) method that is based on the model reduction technology is proposed for the PDE system. A critic network is used to approach the optimal performance index by a neural network (NN) together with that an actor network is used to optimize the control strategy. Furthermore, an upper bound of the performance index and a lower bound of interexecution times, as well as the stabilities of the impulsive dynamic system and the closed-loop PDE system, are also proved. Simulation verification demonstrates the effectiveness of the proposed method.

Sparse Wasserstein stationary subspace analysis for fault detection and diagnosis of nonstationary industrial processes.

Fault detection and diagnosis of nonstationary processes are crucial for ensuring the safety of industrial production systems. However, the nonstationarity of process data poses multifaceted challenges to them. First, conventional stationary fault detection methods encounter difficulties in discerning evolving trends within nonstationary data. Secondly, the majority of current nonstationary fault detection methods directly extract features from all variables, rendering them susceptible to redundant interference. Moreover, nonstationary trends possess the capacity to conceal and modify the correlations among variables. Coupled with the smearing effect of faults, it is challenging to achieve accurate fault diagnosis. To address these challenges, this paper proposes sparse Wasserstein stationary subspace analysis (SWSSA). Specifically, a ℓ2,p-norm constraint is introduced to endow the stationary subspace model with excellent sparse representation capability. Furthermore, recognizing that fault variables within the sparse stationary subspace influence only a limited subset of stationary sources, this paper proposes a novel contribution analysis method based on local dynamic preserving projection (LDPP), termed LDPPBC, which can effectively mitigate the smearing effect on nonstationary fault diagnosis. LDPPBC establishes a LDPP matrix by extracting the latent positional information of fault variables within the stationary subspace. This allows LDPPBC to selectively analyze the contributions of variables within the latent fault subspace to achieve precise fault diagnosis while avoiding the interference of variable contributions from the fault-free subspace. Finally, the superiority of the proposed method is thoroughly validated through a numerical simulation, a continuous stirred tank reactor, and a real industrial roaster.