As users continually request additional functionality, software systems will continue to grow in their complexity, as well as in their susceptibility to failures. Particularly for sensitive systems requiring higher levels of reliability, faulty system modules may increase development and maintenance cost. Hence, identifying them early would support the development of reliable systems through improved scheduling and quality control. Research effort to predict software modules likely to contain faults, as a consequence, has been substantial. Although a wide range of fault prediction models have been proposed, we remain far from having reliable tools that can be widely applied to real industrial systems. For projects with known fault histories, numerous research studies show that statistical models can provide reasonable estimates at predicting faulty modules using software metrics. However, as context-specific metrics differ from project to project, the task of predicting across projects is difficult to achieve. Prediction models obtained from one project experience are ineffective in their ability to predict fault-prone modules when applied to other projects. Hence, taking full benefit of the existing work in software development community has been substantially limited. As a step towards solving this problem, in this dissertation we propose a fault prediction approach that exploits existing prediction models, adapting them to improve their ability to predict faulty system modules across different software projects.

No description available.

Background: The gearbox and machinery faults prediction are expensive both in terms of repair and loss output in production. These losses or faults may lead to complete machinery or plant breakdown.  Objective: The goal of this study was to apply advanced machine learning techniques to avoid these losses and faults and replace them with predictive maintenance. To identify and predict the faults in industrial machinery using Machine Learning (ML)  and Deep Learning (DL) approaches.  Methods: Our study was based on two types of datasets which includes gearbox and rotatory machinery dataset. These datasets were analyzed to predict the faults using machine learning and deep neural network models. The performance of the model was evaluated for both the datasets with binary and multi-classification problems using the different machine learning models and their statistics. Results: In the case of the gearbox fault dataset with a binary classification problem, we observed random forest and deep neural network models performed equally well, with the highest F1-score and AUC score of around 0.98 and with the least error rate of 7%.  In addition to this, in the case of the multi-classification rotatory machinery fault prediction dataset, the random forest model outperformed the deep neural network model with an AUC score of 0.98.  Conclusions: In conclusion classification efficiency of the Machine Learning (ML) and Deep Neural Network (DNN) model were tested and evaluated. Our results show Random Forest (RF) and Deep Neural Network (DNN) models have better fault prediction ability to identify the different types of rotatory machinery and gearbox faults as compared to the decision tree and AdaBoost.  Keywords: Machine Learning, Deep Learning, Big Data, Predictive Maintenance, Rotatory Machinery Fault Prediction, Gearbox Fault Prediction, Machinery Fault Database, Internet of Things (IoT), Spectra quest machinery fault simulator, Cloud Computing, Industry 4.0

This master thesis is made in 2001 at Blekinge Institute of Technology and Symbian, which is a software company in Ronneby, Sweden. The purpose of the thesis is to find a suitable prediction and estimation model for the test effort. To do this, we have studied the State of the Art in cost/effort estimation and fault prediction. The conclusion of this thesis is that it is hard to make a general proposal, which is applicable for all organisations. For Symbian we have proposed a model based on use and test cases to predict the test effort.

Software defect prediction is motivated by the huge costs incurred as a result of software failures. In an effort to reduce these costs, researchers have been utilising software metrics to try and build predictive models capable of locating the most defect-prone parts of a system. These areas can then be subject to some form of further analysis, such as a manual code review. It is hoped that such defect predictors will enable software to be produced more cost effectively, and/or be of higher quality. In this dissertation I identify many data quality and methodological issues in previous defect prediction studies. The main data source is the NASA Metrics Data Program Repository. The issues discovered with these well-utilised data sets include many examples of seemingly impossible values, and much redundant data. The redundant, or repeated data points are shown to be the cause of potentially serious data mining problems. Other methodological issues discovered include the violation of basic data mining principles, and the misleading reporting of classifier predictive performance. The issues discovered lead to a new proposed methodology for software defect prediction. The methodology is focused around data analysis, as this appears to have been overlooked in many prior studies. The aim of the methodology is to be able to obtain a realistic estimate of potential real-world predictive performance, and also to have simple performance baselines with which to compare against the actual performance achieved. This is important as quantifying predictive performance appropriately is a difficult task. The findings of this dissertation raise questions about the current defect prediction body of knowledge. So many data-related and/or methodological errors have previously occurred that it may now be time to revisit the fundamental aspects of this research area, to determine what we really know, and how we should proceed.

A atividade de teste é essencial para a garantia de qualidade do software e deveria ser empregada durante todo o processo de desenvolvimento. Entretanto, o esforço para a sua aplicação e o alto custo envolvido, comprometem sua utilização de maneira adequada. Durante o processo de desenvolvimento ágil, onde o tempo é um fator crítico, otimizar a atividade de testes sem afetar a qualidade é uma tarefa desafiadora. Apesar do crescente interesse em pesquisas sobre testes no contexto de métodos ágeis, poucas evidências são encontradas sobre avaliação do esforço para elaboração, evolução e manutenção dos testes nesse contexto. Este trabalho propõe uma abordagem para predição de defeitos desenvolvida para o contexto do desenvolvimento ágil e, portanto, considerando as características deste processo de desenvolvimento. Essa abordagem pode ser aplicada quando se considera ou não o desenvolvimento dirigido a testes. A abordagem permite priorizar a execução dos testes com base em uma lista de arquivos que apresentam maior probabilidade de apresentarem defeitos. A abordagem proposta foi avaliada por meio de um estudo de caso conduzido em um ambiente real de desenvolvimento. Como resultado obtido, observou-se que a abordagem melhorou a qualidade do projeto desenvolvido, sem aumentar o esforço durante a atividade de teste de software. / The testing activity is essential to ensure the software quality and should be applied during all steps of the developing process. However the required effort to do this and the high cost involved, compromises its proper usage. During the agile development process, in which time is a critical factor, optimizing the testing activity without affecting quality is a challenge. Despite the growing interest in research based agile method testing, few works are found on the evaluation of the effort to prepare, develop and maintain test cases in this context. This paper proposes an approach for fault prediction in the context of agile development and therefore considering the characteristics of this development process. This approach can be applied both when considering test-driven development or not. It allows prioritizing the execution of tests based on a list containing files most likely to fail. The proposed approach was evaluated by a case study conducted in a real development environment. The results indicate that the approach can improve the quality of the projects without increasing the effort during the testing activity.

The rapid growth of wind turbines in terms of turbine size, number of installations and rated capacity has a huge impact on its operations and maintenance costs. Monitoring the performance of wind turbines and early fault prediction is highly desirable. To date, traditional maintenance strategies such as reactive maintenance, periodic maintenance etc. are more prevalent in wind industry. However, over the last couple of years, the research pertaining to wind turbine has been shifted towards the condition monitoring and maintenance. Condition monitoring approaches have shown their potential in wind industry by providing continuous monitoring of the wind turbines, and identifying fault signatures in the event of faults. However, most of the studies reported in literature are based on the simulated dataset, or in constrained experiments. In reality, the external environment plays an important role in governing the turbine operations. Moreover, the cost associated with condition monitoring cannot be justified as it often requires installations of specific sensors, equipment. Another stream of research focuses on utilizing historical turbine data for turbine performance assessment in real time. The cost associated with such approaches is almost negligible as most of the wind farms are equipped with SCADA systems which records turbine performance data in regular time-interval. Such approaches are called as performance monitoring. In this dissertation, the performance monitoring of wind turbines is accomplished using the historical wind turbine data. The information from SCADA operational data, and fault logs is used to construct accurate models predicting the critical wind turbine faults. Depending upon the nature of turbine faults, monitoring wind turbines with different objectives is studied to accomplish different research goals. Two research directions of wind turbines performance are pursued, (1) identification and prediction of critical turbine faults, and (2) monitoring the performance of overall wind farm. The goal of predicting critical faults is to facilitate planned maintenance, whereas, monitoring the performance of overall wind farm provides the status-quo of all wind turbines installed in a wind farm. Depending on the requirement, the performance of overall wind farm can be assessed on a daily, weekly, or monthly basis. Solution methodologies presented in the dissertation are generic enough to be applicable to other industries such as wastewater treatment facilities, flood prediction, etc.

Software fault prediction (SFP) has an important role in the process of improving software product quality by identifying fault-prone modules. Constructing quality models includes a usage of metrics that describe real world entities defined by numbers or attributes. Examining the nature of machine learning (ML), researchers proposed its algorithms as suitable for fault prediction. Moreover, information that software metrics contain will be used as statistical data necessary to build models for a certain ML algorithm. One of the most used ML algorithms is a Bayesian network (BN), which is represented as a graph, with a set of variables and relations between them. This thesis will be focused on the usage of process and static code metrics with BN learners for SFP. First, we provided an informal review on non-static code metrics. Furthermore, we created models that contained different combinations of process and static code metrics, and then we used them to conduct an experiment. The results of the experiment were statistically analyzed using a non-parametric test, the Kruskal-Wallis test. The informal review reported that non-static code metrics are beneficial for the prediction process and its usage is highly recommended for industrial projects. Finally, experimental results did not provide a conclusion which process metric gives a statistically significant result; therefore, a further investigation is needed.

A atividade de teste é essencial para a garantia de qualidade do software e deveria ser empregada durante todo o processo de desenvolvimento. Entretanto, o esforço para a sua aplicação e o alto custo envolvido, comprometem sua utilização de maneira adequada. Durante o processo de desenvolvimento ágil, onde o tempo é um fator crítico, otimizar a atividade de testes sem afetar a qualidade é uma tarefa desafiadora. Apesar do crescente interesse em pesquisas sobre testes no contexto de métodos ágeis, poucas evidências são encontradas sobre avaliação do esforço para elaboração, evolução e manutenção dos testes nesse contexto. Este trabalho propõe uma abordagem para predição de defeitos desenvolvida para o contexto do desenvolvimento ágil e, portanto, considerando as características deste processo de desenvolvimento. Essa abordagem pode ser aplicada quando se considera ou não o desenvolvimento dirigido a testes. A abordagem permite priorizar a execução dos testes com base em uma lista de arquivos que apresentam maior probabilidade de apresentarem defeitos. A abordagem proposta foi avaliada por meio de um estudo de caso conduzido em um ambiente real de desenvolvimento. Como resultado obtido, observou-se que a abordagem melhorou a qualidade do projeto desenvolvido, sem aumentar o esforço durante a atividade de teste de software. / The testing activity is essential to ensure the software quality and should be applied during all steps of the developing process. However the required effort to do this and the high cost involved, compromises its proper usage. During the agile development process, in which time is a critical factor, optimizing the testing activity without affecting quality is a challenge. Despite the growing interest in research based agile method testing, few works are found on the evaluation of the effort to prepare, develop and maintain test cases in this context. This paper proposes an approach for fault prediction in the context of agile development and therefore considering the characteristics of this development process. This approach can be applied both when considering test-driven development or not. It allows prioritizing the execution of tests based on a list containing files most likely to fail. The proposed approach was evaluated by a case study conducted in a real development environment. The results indicate that the approach can improve the quality of the projects without increasing the effort during the testing activity.

No description available.