Kai Wang

Kai Wang
Central South University | CSU · School of Automation

Doctor of Philosophy
Fault diagnosis, industrial data analytics, deep learning, process monitoring

About

39
Publications
2,215
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
229
Citations

Publications

Publications (39)
Article
Missing values are ubiquitous in industrial data sets because of multisampling rates, sensor faults, and transmission failures. The incomplete data obstruct the effective use of data and degrade the performance of data-driven models. Numerous imputation algorithms have been proposed to deal with missing values, primarily based on supervised learnin...
Article
Full-text available
Due to the limitations of sampling conditions and sampling techniques in many real industrial processes, the process data under different sampling conditions subject to different sampling frequencies, which leads to irregular interval sampling characteristics of the entire process data. The dynamic historical data information reflecting the product...
Article
In actual industrial processes, the working conditions often change, resulting in frequent mode switching. Thus, there are no sufficient samples in the start-up stage of a new mode to build an effective model for anomaly monitoring. Meanwhile, the undesirable delay in collecting more modeling samples has posed a threat for real-time process monitor...
Article
Multiplicative faults generally refer to the change of process parameters or structures which are well-suited to represent the process-related anomalies. Unlike sensor faults and external disturbances that are added into process observations and independent with process states, process-related faults directly influence process states such that it i...
Chapter
The injection molding process is a typical batch process. Injection molding production often has the characteristics of low volume and high quality. Product testing in the injection molding is usually carried out in a laboratory, which presents a severe delay issue and is of considerable cost. Moreover, it is often difficult for such products to in...
Article
Residue hydrogenation process (RHP) plays an important role in efficient utilization of heavy oil resources. The high‐fidelity model of RHP is so complex that its optimization cost is expensive and even intractable. Furthermore, in the actual industrial processes, due to the low sampling frequencies of some sensors, only a few sampling points can b...
Article
Full-text available
Due to the existence of complex disturbances and frequent switching of operational conditions characteristics in the real industrial processes, the process data under different operational conditions subject to different distributions, which means there exist different manifold structures under broad operations. Globally, the entire process data ar...
Article
In industrial processes, there are usually strongly dynamic temporal relationship between process data sequence. Hence, dynamic modeling methods are popular for soft sensing of key quality variables. For the real-life industrial processes, the data series are usually sampled with different intervals for the samples. However, most of the mainstream...
Article
Complex industrial process data often exhibit nonlinear static and dynamic characteristics. Traditional deep learning methods like stacked autoencoder (SAE) have excellent nonlinear static feature learning capabilities, but they ignore the dynamic correlation existing in process data. Feature learning based on manifold learning using neighborhood s...
Article
Deep learning-based soft sensor has been widely used for quality prediction in modern industry. Traditional deep learning like stacked autoencoder (SAE) only captures the feature representations by minimizing the global reconstruction errors, which causes a loss of the intrinsic geometric structure embedded in the raw data. To address this problem,...
Article
Full-text available
Multimodal data are common in industrial processes because of switched operating conditions, varying feedstocks and changed product designs and so on. To guarantee process safety and improving process performance, a variable-wise weighted parallel stacked auto-encoder model is proposed for nonlinear multimode process monitoring. Considering the sim...
Article
Full-text available
Process complexities are characterized by strong nonlinearities, dynamics, and uncertainties. Monitoring such a complex process requires a high-quality model describing the corresponding nonlinear dynamic behavior. The proposed model is constructed using deep neural networks (DNNs) to represent the state transition and observation generation, both...
Article
Soft sensors have been extensively developed to estimate the difficult-to-measure quality variables for real-time process monitoring and control. Process nonlinearities and dynamics are two main challenges for accurate soft sensor modeling. To cope with these problems, two temporal convolutional network (TCN)-based soft sensor models are developed...
Article
One common serious issue of training a prediction model is that the process data significantly outnumber the quality data. Such discrepancy exists because of the time lag for obtaining quality data. This paper proposes semi-supervised variational autoencoder-generative adversarial network (S²-VAE/GAN), that is able to make use of all the data even...
Article
Recently, deep learning based soft sensor has been widely applied to industrial processes, which plays a vital role for process monitoring, control and optimization. However, most existing soft sensor models are established for only one quality variable, or multiple quality variables with the same sampling rate. There are very few models focusing o...
Article
Residual hydrogenation fractionation process (RHFP) is significant for extracting valuable fractions from heavy oil with a severe energy consumption. The operational optimization of RHPF for comprehensively improving product profits and reducing energy consumption costs has been studied in this paper. Considering the complex nonlinear dynamic const...
Article
Recently, deep learning has attracted increasing attention for soft sensor applications in industrial processes. Hierarchical features can be learned from massive process data by deep learning, which is the key step for quality variable prediction. However, few deep learning algorithms consider the neighborhood structure of data samples for feature...
Article
In modern industrial processes, dynamics and nonlinearities are two main difficulties for soft sensing of key quality variables. Thus, nonlinear dynamic models like long short-term memory (LSTM) network have been applied for data sequence modeling due to its powerful representation ability. Nevertheless, most dynamic methods cannot deal with data s...
Article
Operating performance evaluation (OPE) has been playing an essential role to ensure the effective operations of chemical processes. However, most of previous research focused on the deterministic evaluation strategies, without consideration of uncertainties in the evaluation indicators of OPE. Based on probabilistic fuzzy theory, an online OPE sche...
Article
Full-text available
Concurrent process-quality monitoring helps discover quality-relevant process anomalies and quality-irrelevant process anomalies. It especially works well in chemical plants with faults that cause quality problems. Traditional monitoring strategies are limitedly applied in chemical plants because quality targets in training data are insufficient. I...
Article
Full-text available
An automatic and accurate control performance diagnosis algorithm is necessary for general chemical processes with a number of control loops when a performance change occurs. The popular contribution plots for control performance diagnosis have severe smearing effects of diagnosis and the problems are still not solved. A sparse loading based contri...
Article
Developing a good soft sensor for prediction has been a major interest, given the time lag to obtain quality data. Deep learning based variational autoencoders (VAE) have been implemented in industrial plants because of their capacities in dealing with the complex stochastic nonlinearity with better probabilistic interpretation. However, unsupervis...
Article
Process complexities are characterized by strong nonlinearities, dynamics and uncertainties. Modeling such a complex process requires a flexible model with deep layers describing the corresponding strong nonlinear dynamic behavior. The proposed model is constructed by deep neural networks to represent the process of state transition and observation...
Article
Soft sensors play an important role in process industries for monitoring and control of key quality variables, and calibration of analyzers. Owing to the merits of fast learning speed and good generalization performance, extreme learning machines (ELMs) have been widely accepted to develop soft sensor models for nonlinear industrial processes. Howe...
Article
In the field of multivariate statistical process monitoring (MSPM), fault isolation has attracted increasing attention, due to its importance on ensuring process reliability and product quality. However, the existing fault isolation methods are mostly limited to linear settings with single variable isolation. For nonlinear modeling, kernel method i...
Article
Full-text available
Batch processes are often characterized by non-linear dynamics and varying oper- ating conditions. Multiphase and multimode modeling of batch processes is a common technique that offers insight into the process operation and improved online monitor- ing. However, existing monitoring methods have several drawbacks such as neglecting process dynamics...
Article
Full-text available
Deep learning models have been applied to industrial process fault detection because of their ability to approximate complex nonlinear behavior. They have been proven to outperform shallow neural network models. However, there are no good guidelines on how to build these deep models. Therefore, a good deep model is often constructed through a trial...
Article
Full-text available
Before performing any in-depth analytics, an important issue in dealing with historical dynamic data is to extract data segments from the operation data. The raw data always involve different kinds of patterns over a long series of sequences because of the operation changes or some faults. Conventional methods for identifying the patterns are based...
Article
Full-text available
Batch process quality prediction is an important application in the chemical industry. The complexity of batch processes is characterized by multiphase, nonlinearity, dynamics and uneven durations, so modeling of batch processes is very difficult. Moreover, there are other challenges in quality prediction. As the process trajectories over the whole...
Article
Full-text available
Most data-driven process monitoring approaches consider the fault detection as a binary classification issue: normal or abnormal. All deviations from the nominal operating condition can trigger the same alarms. They fail to distinguish different fluctuation patterns and locate the positions of anomalies, such as the normal deviations in operating c...
Article
It is known that feedback from outputs to inputs causes non-identifiability in many subspace identification algorithms. In this paper, a new excitation method is proposed for closed-loop subspace identification. By adding an output sampling point within two adjacent control times, a difficult closed loop identification issue is recast into an open...
Article
Full-text available
Data-driven fault diagnosis of closed loop processes has been a challenge in the process control community. The issue of the interaction between the process model and the controller model exists in models directly identified from closed loop data, because for all the measured process outputs, no matter whether they are normal or faulty, they are fe...
Article
Full-text available
The performance of dynamic principal component analysis (DPCA)-based fault detection and diagnosis in a closed-loop system is studied and its improvement by the output oversampling scheme is proposed in this paper. By the subspace decomposition technique, DPCA with the closed-loop data for fault detection does not perform better than DPCA with the...
Article
Full-text available
This paper develops a sensor fault diagnosis (SFD) scheme for a multi-input and multi-output linear dynamic system under feedback control to identify different types of sensor faults (bias, drift and precision degradation), particularly for the incipient sensor faults. Feedback control, leading to fault propagation and disguised fault rectification...

Network

Cited By