Bing Song

Dr. Bing Song


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 September 2019 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
YTYang Tao
Yang Tao
HSHongbo Shi
Hongbo Shi
BSBing Song
Bing Song
STShuai Tan
Shuai Tan
Traditional monitoring algorithms use the normal data for modeling, which are universal for different types of faults. However, these algorithms may perform poorly sometimes because of the lack of fault information. In order to further increase the fault detection rate while preserving the universality of the algorithm, a novel dynamic weight principal component analysis (DWPCA) algorithm and a hierarchical monitoring strategy are proposed. In the first layer, the dynamic PCA is used for fault detection and diagnosis, if no fault is detected, the following DWPCA based second layer monitoring will be triggered. In the second layer, the principal components (PCs) are weighted according to its ability in distinguishing between the normal and fault conditions, then the PCs which own larger weight are selected to construct the monitoring model. Compared to the DPCA method, the proposed DWPCA algorithm establishes the monitoring model by combining the information of fault. Afterwards, the DWPCA based variable relative contribution and a novel control limit for the variable relative contribution are presented for the fault diagnosis. Finally, the superiority of the proposed method is demonstrated by a numerical case and the Tennessee Eastman (TE) process.

10 September 2018 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
BSBing Song
Bing Song
XZXinggui Zhou
Xinggui Zhou
HSHongbo Shi
Hongbo Shi
YTYang Tao
Yang Tao
Process monitoring is an effective means to ensure process safety and improve product quality. On the one hand, it is possible that the fault will not affect process safety or product quality. On the other hand, not every fault affects both process safety and product quality simultaneously. To make process monitoring more purposeful and more accurate, a novel performance indicator oriented concurrent subspace (PIOCS) process monitoring method containing three subspaces with different degrees of importance is proposed. The first one is safety related subspace (SRS), the second one is safety unrelated-quality related subspace (SUQRS), and the third one is safety-quality unrelated subspace (SQUS). Through subspace division and construction, the fault can be categorized as safety related fault, safety unrelated-quality related fault and safety-quality unrelated fault. For mining safety and quality related information, both mechanism analysis and data analysis are used. In order to show the effectiveness and superiority, the proposed PIOCS method is tested under a number example and an industrial case study. Compared with traditional process monitoring methods, the proposed PIOCS method can obtain richer information, which is easy to show process operation condition clearly.

7 August 2020 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
BSBing Song
Bing Song
HSHongbo Shi
Hongbo Shi
STShuai Tan
Shuai Tan
YTYang Tao
Yang Tao
Plant-wide processes often have the characteristics of large-scale and multiple operating units. Moreover, due to the closed-loop control, it is possible that the fault never affects product quality. In this article, a novel data-driven method called multisubspace orthogonal canonical correlation analysis (CCA) is proposed, which can not only tell whether the fault occurs but can also judge whether the fault affects the product quality in real time. First, to reduce process analysis complexity and to construct an accurate monitoring model, the original process variable space is divided into four subspaces. Second, the developed orthogonal CCA is conducted on process data and quality data for correlation feature extraction. Then, the quality-related and quality-unrelated features are obtained. Afterward, a total of six monitoring statistics are constructed and integrated to four statistics with physical interpretation via the Bayesian fusion strategy. Finally, the developed method is tested under an industrial case.

2 November 2021 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
JZJiazhen Zhu
Jiazhen Zhu
HSHongbo Shi
Hongbo Shi
BSBing Song
Bing Song
YTYang Tao
Yang Tao
STShuai Tan
Shuai Tan
As industrial technology develops, industrial processes become increasingly large and complex, the traditional methods are difficult to extract features that can represent the condition of the whole process and the effect of fault on quality indicators. Therefore, a novel multiblock decouple convolutional neural network (multiblock DCN) algorithm is proposed. First, key process variables are selected, and process variables are grouped into multiple blocks for the following monitoring. Then, in each block, the proposed DCN constructs a regression model between key process variables and quality indicators, in which the regression model utilizes an improved convolutional neural network as a feature extractor and a decoupling layer as a feature regularizer. Afterward, the monitoring results of each block are integrated into a global monitoring index based on Bayesian theory. After fault detection, variable oblivion contribution plot is presented to locate faulty variables. Finally, two industrial cases are used to demonstrate the effectiveness of multiblock DCN.

5 February 2018 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
BSBing Song
Bing Song
HSHongbo Shi
Hongbo Shi
In the practical process, various faults occur, which may affect the quality of products. Meanwhile, due to the presence of the feedback closed loop, the effects of certain faults might be compensated. Consequently, not all faults occurring in the system will affect the product quality. According to the impacts of faults on the quality, the faults can be categorized as a quality-unrelated fault, quality-semirelated fault, and quality-related fault. For different categories of faults, corresponding responses should be adopted. Motivated by this, a novel quality-supervised double-layer method (QSDLM) is proposed in this paper to detect and classify the faults simultaneously. The first layer is used for fault detection using principal component analysis (PCA). The second layer is to detect the occurrence of quality-related fault based on the proposed key variable-orthogonal weight PCA. By comparing the result of the first layer with that of the second layer, whether the fault is related to the product quality can be identified, and the fault classification can be conducted. The proposed QSDLM is used in the Tennessee Eastman process to prove its effectiveness. Compared with three typical methods, the proposed QSDLM method can obtain the best results.

16 December 2019 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
BSBing Song
Bing Song
Huaicheng YanHuaicheng Yan
Huaicheng Yan
HSHongbo Shi
Hongbo Shi
STShuai Tan
Shuai Tan
In this paper, a novel multimode quality related process monitoring method called multi-subspace elastic network (MSEN) is proposed. To make mode partition more precisely, this paper develops a novel clustering algorithm based on the neighborhood information and subtractive clustering algorithm. In each single mode, unlike conventional process monitoring models which only focus on whether the fault occurs, a novel elastic network (EN) based quality related process monitoring model is established to judge whether the fault is quality related or not. In addition, to select the most suitable monitoring model for online data, the k nearest neighbor rule and the voting strategy are applied. Once the fault is detected, the contribution plot method is conducted in both quality related and unrelated subspace for fault diagnosis. At last, the proposed MSEN method is tested under the continuous stirred tank reactor (CSTR) to verify its superiority and advantage.