Software Fault Prediction at Design Phase

Singh, Pradeep,Verma, Shrish,Vyas, O.P. The Korean Institute of Electrical Engineers 2014 Journal of Electrical Engineering & Technology Vol.9 No.5

Prediction of fault-prone modules continues to attract researcher's interest due to its significant impact on software development cost. The most important goal of such techniques is to correctly identify the modules where faults are most likely to present in early phases of software development lifecycle. Various software metrics related to modules level fault data have been successfully used for prediction of fault-prone modules. Goal of this research is to predict the faulty modules at design phase using design metrics of modules and faults related to modules. We have analyzed the effect of pre-processing and different machine learning schemes on eleven projects from NASA Metrics Data Program which offers design metrics and its related faults. Using seven machine learning and four preprocessing techniques we confirmed that models built from design metrics are surprisingly good at fault proneness prediction. The result shows that we should choose Naïve Bayes or Voting feature intervals with discretization for different data sets as they outperformed out of 28 schemes. Naive Bayes and Voting feature intervals has performed AUC > 0.7 on average of eleven projects. Our proposed framework is effective and can predict an acceptable level of fault at design phases.

Software Fault Prediction at Design Phase

Pradeep Singh,Shrish Verma,O. P Vyas 대한전기학회 2014 Journal of Electrical Engineering & Technology Vol.9 No.5

Prediction of fault-prone modules continues to attract researcher’s interest due to its significant impact on software development cost. The most important goal of such techniques is to correctly identify the modules where faults are most likely to present in early phases of software development lifecycle. Various software metrics related to modules level fault data have been successfully used for prediction of fault-prone modules. Goal of this research is to predict the faulty modules at design phase using design metrics of modules and faults related to modules. We have analyzed the effect of pre-processing and different machine learning schemes on eleven projects from NASA Metrics Data Program which offers design metrics and its related faults. Using seven machine learning and four preprocessing techniques we confirmed that models built from design metrics are surprisingly good at fault proneness prediction. The result shows that we should choose Naive Bayes or Voting feature intervals with discretization for different data sets as they outperformed out of 28 schemes. Naive Bayes and Voting feature intervals has performed AUC > 0.7 on average of eleven projects. Our proposed framework is effective and can predict an acceptable level of fault at design phases.

MPC-based FTC with FDD against Actuator Faults of UAVs

Bin Yu,Youmin Zhang,Yaohong Qu 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10

The increasing development of unmanned aerial vehicles (UAVs) and the requirements of high autonomy and safety levels require that the controller of UAVs should possess fault-tolerant/reconfigurable function to accommodate unpredicted situations such as actuator faults, sensor faults, or aircraft damage. This paper addresses the partial loss of control effectiveness (LOE) of actuators in a quadrotor UAV using model predictive control (MPC) with terminal constraints, which allows to track a reference command even if in the presence of actuator faults. The proposed faulttolerant control system (FTCS) adopts MPC technique to design fault-tolerant controller and state-augmented Kalman filter (SAKF) to achieve fault detection and diagnosis (FDD) function. Simulation results based on a quadrotor UAV demonstrate that the proposed fault-tolerant controller has a good performance in accommodating actuator faults.

Fault-Tolerant Control of Five-Phase Permanent Magnet Synchronous Hub Motor Based on Improved Model Predictive Current Control

Li Teng,Yao Ming,Sun Xiaodong 대한전기학회 2024 Journal of Electrical Engineering & Technology Vol.19 No.1

To further improve the reliability of wheel-driven electric vehicles, this paper studies the fault-tolerant control operation of a fve-phase permanent magnet synchronous hub motor (PMSHM). A fault-tolerant scheme based on model predictive current control (MPCC) is proposed for the fve-phase PMSHM under single-phase open-circuit fault and two-phase open-circuit fault operation. In the implementation of this scheme, the fve-phase PMSHM model during fault operation is discussed, and the coordinate transformation matrices for single-phase fault, adjacent two-phase fault and non-adjacent two-phase fault are derived respectively. Through further analysis, the ofset voltage vector at the time of open-circuit fault can be obtained, and the newly obtained voltage vector can be used as the candidate set for model predictive control. The MPCC method combines duty cycle control and the vector preselection method. Compared with the traditional MPCC scheme, the improved MPCC scheme not only reduces the computation time but also enhances the steady-state performance of the control scheme. Finally, it is verifed that the proposed fault-tolerant scheme based on MPCC can efectively address the diference in open-loop fault operation and improve the reliability of the hub drive system.

결함 심각도에 기반한 소프트웨어 품질 예측

홍의석(Euy-Seok Hong) 한국컴퓨터정보학회 2015 韓國컴퓨터情報學會論文誌 Vol.20 No.5

소프트웨어 결함 예측 연구들의 대부분은 입력 개체의 결함 유무를 예측하는 이진 분류 모델들에 관한 것들이다. 하지만 모든 결함들이 같은 심각도를 갖지는 않으므로 예측 모델이 입력 개체의 결함경향성을 몇 개의 심각도 범주로 분류할 수 있다면 훨씬 유용하게 사용될 수 있다. 본 논문에서는 전통적인 복잡도와 크기 메트릭들을 입력으로 하는 심각도 기반 결함 예측 모델을 제안하였다. 학습 알고리즘은 많이 사용되는 네 개의 기계학습 기법들을 사용하였으며, 모델 구조는 삼진 분류 모델로 하였다. 모델 성능 평가를 위해 실험 데이터는 두 개의 NASA 공개 데이터 집합을 사용하였고, 평가 측정치는 Accuracy를 이용하였다. 평가 실험 결과는 역전파 신경망 모델이 두 데이터 집합에 대해 각각 81%와 88% 정도의 Accuracy 값으로 가장 좋은 성능을 보였다. Most of the software fault prediction studies focused on the binary classification model that predicts whether an input entity has faults or not. However the ability to predict entity fault-proneness in various severity categories is more useful because not all faults have the same severity. In this paper, we propose fault prediction models at different severity levels of faults using traditional size and complexity metrics. They are ternary classification models and use four machine learning algorithms for their training. Empirical analysis is performed using two NASA public data sets and a performance measure, accuracy. The evaluation results show that backpropagation neural network model outperforms other models on both data sets, with about 81% and 88% in terms of accuracy score respectively.

A Risk Prediction Method for Water or Mud Inrush from Water-bearing Faults in Subsea Tunnel based on Cusp Catastrophe Model

Yiguo Xue,Dan Wang,Shucai Li,Daohong Qiu,Zhiqiang Li,Jianye Zhu 대한토목학회 2017 KSCE JOURNAL OF CIVIL ENGINEERING Vol.21 No.7

Constructing a subsea tunnel is exceptionally difficult because of the complex geological conditions involved in the process. Water or mud inrush is a geological hazard that occurs suddenly during the construction of a cross-harbor tunnel, thereby causing major disasters and economic losses. The weak structural planes in a fault zone are the naturally preferred planes for water inrush. It is necessary to analyze the mechanism and to develop a risk prediction method for water or mud inrush from such faults. In order to effectively predict the risk of water or mud inrush during the construction of a subsea tunnel, this paper analyzes the mechanism of water or mud inrush from extensional faults, shear faults and compressive faults based on cusp catastrophe model. The potential function for the risk of water or mud inrush is built, and then the index of water inrush (IP) is obtained based on the equations of equilibrium for the fault surface. Water or mud inrush occurs only when . The proposed method of risk prediction is successfully used in Qingdao Kiaochow Bay subsea tunnel to prove its applicability and feasibility.

Analyzing Machine Learning Techniques for Fault Prediction Using Web Applications

Malhotra, Ruchika,Sharma, Anjali Korea Information Processing Society 2018 Journal of information processing systems Vol.14 No.3

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

Analyzing Machine Learning Techniques for Fault Prediction Using Web Applications

Ruchika Malhotra,Anjali Sharma 한국정보처리학회 2018 Journal of information processing systems Vol.14 No.3

Web applications are indispensable in the software industry and continuously evolve either meeting a newercriteria and/or including new functionalities. However, despite assuring quality via testing, what hinders astraightforward development is the presence of defects. Several factors contribute to defects and are oftenminimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases ofsoftware development is important. Therefore, a fault prediction model for identifying fault-prone classes in aweb application is highly desired. In this work, we compare 14 machine learning techniques to analyse therelationship between object oriented metrics and fault prediction in web applications. The study is carried outusing various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, theinput basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statisticalanalysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of thesemetrics in the defect prediction of web applications. The overall predictive ability of different fault predictionmodels is first ranked using Friedman technique and then statistically compared using Nemenyi post-hocanalysis. The results not only upholds the predictive capability of machine learning models for faulty classesusing web applications, but also finds that ensemble algorithms are most appropriate for defect prediction inApache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique andthe statistical analysis of the datasets.

Fault and Failure Tolerant Model Predictive Control of Quadrotor UAV

정우영,방효충 한국항공우주학회 2021 International Journal of Aeronautical and Space Sc Vol.22 No.3

This paper presents fault tolerance control (FTC) of a quadrotor under actuator faults. A complete FTC design approach with fault detection and diagnosis (FDD) is addressed. The proposed FTC is based on the model predictive control, which can be applied to nonlinear systems using the so-called successive convexification algorithm, which converts a nonconvex function to a convex function in a successive manner through linearization. The faults are parameterized in the form of loss of effectiveness (LOE) of a quadrotor actuator and estimated using a two-stage Kalman filter. Compared with other FTC, the proposed FTC is capable of controlling not only partial loss of actuator effectiveness defined as a fault but also a complete loss of actuator effectiveness defined as failure. Controller switching is not required, while an actuator saturation limit is also considered. The proposed FTC approach has been validated under various actuator fault conditions through nonlinear simulation studies.

Fault-Tolerant Control for 5L-HNPC Inverter-Fed Induction Motor Drives with Finite Control Set Model Predictive Control Based on Hierarchical Optimization

Li, Chunjie,Wang, Guifeng,Li, Fei,Li, Hongmei,Xia, Zhenglong,Liu, Zhan The Korean Institute of Power Electronics 2019 JOURNAL OF POWER ELECTRONICS Vol.19 No.4

This paper proposes a fault-tolerant control strategy with finite control set model predictive control (FCS-MPC) based on hierarchical optimization for five-level H-bridge neutral-point-clamped (5L-HNPC) inverter-fed induction motor drives. Fault-tolerant operation is analyzed, and the fault-tolerant control algorithm is improved. Adopting FCS-MPC based on hierarchical optimization, where the voltage is used as the controlled objective, called model predictive voltage control (MPVC), the postfault controller is simplified as a two layer control. The first layer is the voltage jump limit, and the second layer is the voltage following control, which adopts the optimal control strategy to ensure the current following performance and uniqueness of the optimal solution. Finally, simulation and experimental results verify that 5L-HNPC inverter-fed induction motor drives have strong fault tolerant capability and that the FCS-MPVC based on hierarchical optimization is feasible.