Search for: All records

Abstract Accurate prediction of product failures and the need for repair services become critical for various reasons, including understanding the warranty performance of manufacturers, defining cost-efficient repair strategies, and compliance with safety standards. The purpose of this study is to use machine learning tools to analyze several parameters crucial for achieving a robust repair service system, including the number of repairs, the time of the next repair ticket or product failure, and the time to repair. A large data set of over 530,000 repairs and maintenance of medical devices has been investigated by employing the Support Vector Machine (SVM) tool. SVM with four kernel functions is used to forecast the timing of the next failure or repair request in the system for two different products and two different failure types, namely, random failure and physical damage. Frequency analysis is also conducted to explore the product quality level based on product failure and the time to repair it. Besides, the best probability distributions are fitted for the failure count, the time between failures, and the time to repair. The results reveal the value of data analytics and machine learning tools in analyzing post-market product performance and the cost of repair and maintenance operations. 

Products often experience different failure and repair needs during their lifespan. Prediction of the type of failure is crucial to the maintenance team for various reasons, such as realizing the device performance, creating standard strategies for repair, and analyzing the trade-off between cost and profit of repair. This study aims to apply machine learning tools to forecast failure types of medical devices and help the maintenance team properly decides on repair strategies based on a limited dataset. Two types of medical devices are used as the case study. The main challenge resides in using the limited attributes of the dataset to forecast product failure type. First, a multilayer perceptron (MLP) algorithm is used as a regression model to forecast three attributes, including the time of next failure, repair time, and repair time z-scores. Then, eight classification models, including Naïve Bayes with Bernoulli (NB-Bernoulli), Gaussian (NB-Gaussian), Multinomial (NB-Multinomial) model, Support Vector Machine with linear (SVM-Linear), polynomial (SVM-Poly), sigmoid (SVM-Sigmoid), and radical basis (SVM-RBF) function, and K-Nearest Neighbors (KNN) are used to forecast the failure type. Finally, Gaussian Mixture Model (GMM) is used to identify maintenance conditions for each product. The results reveal that the classification models could forecast failure type with similar performance, although the attributes of the dataset were limited. 

Lithium-ion batteries almost exclusively power today’s electric vehicles (EVs). Cutting battery costs is crucial to the promotion of EVs. This paper aims to develop potential solutions to lower the cost and improve battery performance by investigating its design variables: positive electrode porosity and thickness. The open-access lithium-ion battery design and cost model (BatPac) from the Argonne National Laboratory of the United States Department of Energy, has been used for the analyses. Six pouch battery systems with different positive materials are compared in this study (LMO, LFP, NMC 532/LMO, NMC 622, NMC 811, and NCA). Despite their higher positive active material price, nickel-rich batteries (NMC 622, NMC 811, and NCA) present a cheaper total pack cost per kilowatt-hour than other batteries. The higher thickness and lower porosity can reduce the battery cost, enhance the specific energy, lower the battery mass but increase the performance instability. The reliability of the results in this study is proven by comparing estimated and actual commercial EV battery parameters. In addition to the positive electrode thickness and porosity, six other factors that affect the battery's cost and performance have been discussed. They include energy storage, negative electrode porosity, separator thickness and porosity, and negative and positive current collector thickness. 

Accurate prediction of product failures and the need for repair services become critical for various reasons, including understanding the warranty performance of manufacturers, defining cost-efficient repair strategies, and compliance with safety standards. The purpose of this study is to use machine learning tools to analyze several parameters crucial for achieving a robust repair service system, including the number of repairs, the time of the next repair ticket or product failure, and the time to repair. A large dataset of over 530,000 repairs and maintenance of medical devices has been investigated by employing the Support Vector Machine (SVM) tool. SVM with four kernel functions is used to forecast the timing of the next failure or repair request in the system for two different products and two different failure types, namely random failure and physical damage. A frequency analysis is also conducted to explore the product quality level based on product failure and the time to repair it. Besides, the best probability distributions are fitted for the number of failures, the time between failures, and the time to repair. The results reveal the value of data analytics and machine learning tools in analyzing post-market product performance and the cost of repair and maintenance operations. 

Waste tracking is becoming an important concern for developed countries as well as developing regions, where municipalities aim to assure proper waste management considering environmental and economic objectives. Waste tracking is important not only for a transparent reporting system compatible with environmental regulations but also for economically viable waste collection and recovery solutions. In this paper, a waste tracking system based on the blockchain technology is introduced where different entities involved in the system will be able to retrieve required data from the platform and decide on their level of contributions. The conventional technologies do not provide a sufficient level of transparency and coordination among different entities. With the introduction of blockchain as a tamper-proof technology, municipalities can enhance the efficiency of their waste management efforts. The proposed blockchain technology can connect proper stakeholders towards collaboration and sharing information. The concept of a smart contract for waste management is discussed and further, a decision-making framework is developed to guide users of the system select proper services available to them, depending on the level of data sharing, cost, reliability, and the security level that they expect from the system. 

The objective of this study is to provide an overview of Blockchain technology and Industry 4.0 for advancing supply chains towards sustainability. First, extracted from the existing literature, we evaluate the capabilities of Industry 4.0 for sustainability under three main topics of (1) Internet of things (IoT)-enabled energy management in smart factories; (2) smart logistics and transportation; and (3) smart business models. We expand beyond Industry 4.0 with unfolding the capabilities that Blockchain offers for increasing sustainability, under four main areas: (1) design of incentive mechanisms and tokenization to promote consumer green behavior; (2) enhance visibility across the entire product lifecycle; (3) increase systems efficiency while decreasing development and operational costs; and (4) foster sustainability monitoring and reporting performance across supply chain networks. Furthermore, Blockchain technology capabilities for contributing to social and environmental sustainability, research gaps, adversary effects of Blockchain, and future research directions are discussed.