Fault Diagnosis of Analog Circuits Based on IH-PSO Optimized Support Vector Machine

Currently, liquid crystal displays (LCDs) are the most popular type of flat panel display and are used in most applications. An LCD contains many critical optical film components that are produced in highly automated and precisely monitored facilities throughout the complex manufacturing process. However, defect detection and classification through visual inspection is very difficult during the manufacturing process. To overcome this problem, a novel framework based on machine vision known as the optical film defect detection and classification system is presented for use in the real-time inspection. First, an image acquisition system equipped with a high-resolution camera and custom-made lighting field was designed to obtain a high-quality optical film image. Second, the defects on an optical film were detected using localized cross-projection based on proposed adaptive energy analysis. Finally, the defect images were classified into four types by using the developed classification algorith-point, scratch, foreign material, and stain. The quality of the products yielded after defect detection and classification of the optical film was compared with the standard product quality of the manufacturer. Experiments were conducted using samples collected from the largest manufacturer in Taiwan to validate the performance of the proposed framework. The accurate defect detection rate is 99.6%, the classification accuracy rate is 100%, and the total operation time is short whichonly 6.129s are required on average to perform the inspection for an optical film sample. The results demonstrate that the proposed method is sound and useful for optical film inspection in industries.

Section: Optical Film Defect Classification Resultsmentioning

confidence: 99%

Novel Framework for Optical Film Defect Detection and Classification

Wang

Shih

et al. 2020

“…The proposed method is compared with other methods to accomplish its algorithm verification, which further illustrates the effectiveness and scalability of the proposed method. The regression algorithms involved in the comparison include logistic regression [37], SVM [38][39], random forest [40][41], SGD and the proposed method. The constructed model is shown in Fig.…”

Section: F Methods Comparison and Verificationmentioning

confidence: 99%

Power System Fault Classification and Prediction Based on a Three-Layer Data Mining Structure

Wang

et al. 2020

In traditional fault diagnosis methods in power systems, it is difficult to accurately classify and predict the types of faults. With the emergence of big data technology, the fault classification and prediction methods based on big data analysis and processing have been applied in power systems. To make the classification and prediction of the fault types more accurate, this paper proposes a hybrid data mining method for power system fault classification and prediction based on clustering, association rules and stochastic gradient descent. This method uses a three-layer data mining model: The first layer uses the K-means clustering algorithm to preprocess the original fault data source, and it proposes to use self-encoding to simplify the data form. The second layer effectively eliminates the data that have little impact on the prediction results by using association rules, and the highly correlated data are mined to become the regression training data. The third layer first uses the cross-validation method to obtain the optimal parameters of each fault model, and then, it uses stochastic gradient descent for data regression training to obtain a classification and prediction model for each fault type. Finally, a verification example shows that compared with a single data mining algorithm model, the proposed method is more comparative in terms of the data mining, and the established power system fault classification and prediction model has global optimality and higher prediction accuracy, which has a certain feasibility for real-time online power system fault classification and prediction. This method reduces the disturbances from low-impact or irrelevant data by mining the fault data three times, and it uses cross-validation to optimize the multiple regression parameters of the regression model to solve the problems of low accuracy, large errors and easily falling into a local optimum, given the conduct of fault classification and prediction.

“…The partial continuous parameter shifting (CPS) fault model [±20%~±50%] used in Ref. [6][7][8][9] is more practicable. This partial CPS still cannot cover all the possible parameter shifting, viz., (0, ∞).…”

Section: A Fault Locationmentioning

confidence: 99%

Genetic Algorithm Based Faulty Parameter Identification for Linear Analog Circuit

Yang

2020

Faulty parameter identification is vital to prediction of remaining useful life of circuit under test (CUT). Based on the transfer function of the CUT, we use measured faulty response to reversely deduce the possible faulty parameters. It is known that the response is the function of the analog parameters. Usually, the number of independent response is much fewer than that of the analog component. The underdetermined equations have infinite solutions. In other words, there are lots of combinations of analog parameters that can generate the same faulty response. Hence, it is more valuable to deduce the possible fault parameter range within which all faults can generate the same measured response. The deduction is accomplished by using genetic algorithm. The length of chromosome equals to the number of analog component. Each gene represents a component's parameter value. Based on the gene values and the transfer function, each individual has a simulated response. Our target is to find all possible individuals viz., parameter combinations, which minimize the difference between the simulated and measured faulty response. In the final solutions, it is easy to find the minimal and maximum fault parameters, viz., extreme points. The possible faulty parameter rage is determined by these two extreme points because that the transfer function and parameters of analog element are continuous. The effectiveness of the proposed method is examined by using filter circuit examples.