Chapter 10 - Error Traceability and Error Prediction using Machine Learning Techniques to Improve the Quality of Vehicle Modeling in Computer-Aided Engineering

Abstract

Modeling an automobile according to the client requirements is one of the important roles in computer-aided engineering (CAE). CAE helps computer software by simulating the performance to improve vehicle designs. CAE comprises the process of preprocessing, deciphering, and postprocessing steps. In the preprocessing stage, engineers design the geometry, a convention representation, physical properties and loads applied. By using the mathematical functions and applications of physics the model is solved. In the postprocessing stage, results are represented by the designer for review. While designing a vehicle, the designer follows a step-by-step process to reduce the unintended software behavior to complete the model. Locating errors in industry-size software systems is time-consuming and challenging. Hence an automated approach is proposed to trace the errors helps the CAD engineer to complete the designing task in less time. Error traceability and error prediction are the two major tasks focused in the designing stage. Software fault prediction techniques are used to predict the faults in the software and machine-learning techniques is playing an important role in detecting the software default. Bug prediction and correction of bugs improve the software quality and reduce the maintenance cost. In this chapter, it is discussed how machine learning techniques playing the role of bug prediction and effectively increases the accuracy rate. With the help of the back propagation method, the designer can predict the errors and rectify them so that time spent on rework will be reduced. Industry-size software systems are time-consuming and challenging. Hence an automated approach for assisting the process of tracing errors is proposed which helps the CAD engineer easily complete the designing task in less time. Error traceability and error prediction are the two major tasks focused in the designing stage. Software fault prediction techniques are used to predict the faults in the software and machine-learning techniques playing an important role in detecting the software default. Bug prediction and correction of bugs improve the software quality and reduce the maintenance cost. In this chapter, it is discussed how machine learning techniques playing the role of bug prediction and effectively increases the accuracy rate. With the help of the back propagation method, the designer can predict the errors and rectify them so that time spent on rework will be reduced.