Fault Detection Using Random Projections and k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes

Zhou, Zhe; Wen, Chenglin; Yang, Chunjie

doi:10.1109/tsm.2014.2374339

Cited by 81 publications

(20 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Practically, it is very important to diminish or eliminate any unusual variation presented in the entire semiconductor production processes through a quick and exact detection and diagnosis of faults (i.e., abnormal trends or behaviors) for maintaining consistent and safe production [56]. Thus, FDC in semiconductor manufacturing has been recognized as one of the key components of the APC (advanced process control) framework to enhance overall production efficiency (i.e., yield and machine utilization) as well as reducing variations in processes [21,[56][57][58][59][60][61][62][63][64][65][66][67][68]. In the semiconductor industry, several FDC approaches have been developed and adopted to detect faults in the processes and identify the corresponding root causes.…”

Section: Industrial Applications Of Fault Detection and Diagnosis Methodsmentioning

confidence: 99%

A Review on Fault Detection and Process Diagnostics in Industrial Processes

2020

View full text Add to dashboard Cite

The main roles of fault detection and diagnosis (FDD) for industrial processes are to make an effective indicator which can identify faulty status of a process and then to take a proper action against a future failure or unfavorable accidents. In order to enhance many process performances (e.g., quality and throughput), FDD has attracted great attention from various industrial sectors. Many traditional FDD techniques have been developed for checking the existence of a trend or pattern in the process or whether a certain process variable behaves normally or not. However, they might fail to produce several hidden characteristics of the process or fail to discover the faults in processes due to underlying process dynamics. In this paper, we present current research and developments of FDD approaches for process monitoring as well as a broad literature review of many useful FDD approaches.

show abstract

Section: Industrial Applications Of Fault Detection and Diagnosis Methodsmentioning

confidence: 99%

A Review on Fault Detection and Process Diagnostics in Industrial Processes

2020

View full text Add to dashboard Cite

show abstract

“…Although the kNN rule has been successfully applied to detect the abnormal in the process industry [7,[15][16][17][18], how to identify the faulty variables using by kNN method without prior fault information is still a challenge problem.…”

Section: Variable Contribution By Knnmentioning

confidence: 99%

“…To explicitly account for these characteristics, He and Wang [7] developed an alternative fault detection method based on k-nearest neighbor rule (FD-kNN), it uses the kNN distance as an index to measure the discrepancy between the online data sample and the normal operation conditions (NOC) data samples. Compared to those of MSPM methods, FD-kNN has shown its superiority in analyzing nonlinear, multi-mode, and non-Gaussian distribution data [7,[15][16][17][18][19]. Moreover, as a nonlinear classifier, kNN is naturally possible to handle nonlinearity in the data [7].…”

Section: Introductionmentioning

confidence: 99%

Fault Identification Using Fast k-Nearest Neighbor Reconstruction

Zhou¹,

Li²,

Cai³

2019

Processes

Self Cite

View full text Add to dashboard Cite

Data with characteristics like nonlinear and non-Gaussian are common in industrial processes. As a non-parametric method, k-nearest neighbor (kNN) rule has shown its superiority in handling the data set with these complex characteristics. Once a fault is detected, to further identify the faulty variables is useful for finding the root cause and important for the process recovery. Without prior fault information, due to the increasing number of process variables, the existing kNN reconstruction-based identification methods need to exhaust all the combinations of variables, which is extremely time-consuming. Our previous work finds that the variable contribution by kNN (VCkNN), which defined in original variable space, can significantly reduce the ratio of false diagnosis. This reliable ranking of the variable contribution can be used to guide the variable selection in the identification procedure. In this paper, we propose a fast kNN reconstruction method by virtue of the ranking of VCkNN for multiple faulty variables identification. The proposed method significantly reduces the computation complexity of identification procedure while improves the missing reconstruction ratio. Experiments on a numerical case and Tennessee Eastman problem are used to demonstrate the performance of the proposed method.

show abstract

“…However, the distances of samples in the original observation space cannot be maintained in the principle component subspace because the idea of using PCA is to express data samples using as few principle components as possible. Zhou et al [28] proposed a fault detection method named RPkNN, which integrates the kNN rule and random projection to address the problems of multi-modality and non-linearity. The random projection can maintain the distances of data samples in the random subspace with great probability.…”

Section: Introductionmentioning

confidence: 99%

“…Generally speaking, all of the above kNN-based fault detection methods (e.g., FD-kNN [25], PC-kNN [27], RPkNN [28], FS-kNN [29], k-NND [30]) select the k-nearest training samples as neighbours of the new test sample and calculate the average squared distance between the test sample and these neighbours. Therefore, the kNN rule has to calculate the distance between each training sample and the test sample in order to choose the k-nearest neighbours.…”

Section: Introductionmentioning

confidence: 99%

Fault Detection Using the Clustering-kNN Rule for Gas Sensor Arrays

Yang

Sun

Chen

2016

Sensors

View full text Add to dashboard Cite

The k-nearest neighbour (kNN) rule, which naturally handles the possible non-linearity of data, is introduced to solve the fault detection problem of gas sensor arrays. In traditional fault detection methods based on the kNN rule, the detection process of each new test sample involves all samples in the entire training sample set. Therefore, these methods can be computation intensive in monitoring processes with a large volume of variables and training samples and may be impossible for real-time monitoring. To address this problem, a novel clustering-kNN rule is presented. The landmark-based spectral clustering (LSC) algorithm, which has low computational complexity, is employed to divide the entire training sample set into several clusters. Further, the kNN rule is only conducted in the cluster that is nearest to the test sample; thus, the efficiency of the fault detection methods can be enhanced by reducing the number of training samples involved in the detection process of each test sample. The performance of the proposed clustering-kNN rule is fully verified in numerical simulations with both linear and non-linear models and a real gas sensor array experimental system with different kinds of faults. The results of simulations and experiments demonstrate that the clustering-kNN rule can greatly enhance both the accuracy and efficiency of fault detection methods and provide an excellent solution to reliable and real-time monitoring of gas sensor arrays.

show abstract

Fault Detection Using Random Projections and k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes

Cited by 81 publications

References 34 publications

A Review on Fault Detection and Process Diagnostics in Industrial Processes

A Review on Fault Detection and Process Diagnostics in Industrial Processes

Fault Identification Using Fast k-Nearest Neighbor Reconstruction

Fault Detection Using the Clustering-kNN Rule for Gas Sensor Arrays

Contact Info

Product

Resources

About