With rapid innovation in the electronics industry, product obsolescence forecasting has become increasingly important. More accurate obsolescence forecasting would have cost reduction effects in product design and part procurement over a product’s lifetime. Currently many obsolescence forecasting methods require manual input or perform market analy...
Context in source publication
... Obieke et al. also proposed an emergent technology-based innovative design method to assist the generation of new design concepts . Similarly, an obsolescence forecasting model is developed to classify product parts into active, in production, or obsolete . Besides, reinforcement learning is used to ensure that the choice of technologies is aligned with corporate goals . ...
In today’s manufacturing industry, companies are striving to provide customized products to maintain competitiveness. The challenge of design customization lies in the company’s ability to balance product variety, responsiveness, and cost-effectiveness simultaneously. Today, the large volume of data in tandem with powerful computation capabilities has made machine learning a promising technology to address various challenges in engineering design, leading to new opportunities for customization. However, few efforts have been devoted to systemically reviewing these new methods, nor to assessing how they are aligned with customization. Against this background, this article presents a systematic literature review on machine learning for engineering design from the customization perspective. A thorough search of relevant works resulted in a total of 116 most relevant articles, based on which, different machine learning applications are mapped to corresponding design stages of an engineering design process. The potential and advantages of machine learning for fulfilling different customization requirements are discussed. Finally, some promising directions for future investigation are outlined.
With the rapid development of technologies, product lifecycle becomes shorter, which brings great challenges to obsolescence management. An efficient obsolescence forecasting method is in need. This research proposes a two-stage obsolescence forecasting model. The first stage identifies the key product features for obsolescence with ELECTRE I method. The second stage calculates the obsolescence probability based on radial basis function neural network. Three improvements are made for better predication accuracy, (1) information gain and information gain ratio are integrated to calculate the input weights; (2) an improved Particle Swarm Optimization algorithm is applied to calculate the clustering centroid; and (3) an improved gradient descent method determines the weights from hidden layer to output layer. The performance of the proposed method is compared with the existing model by using mobile dataset which contains 7000 samples. The experimental result shows that the accuracy of the predication has been improved from 92.2% to 95.23%.
Obsolescence is the fact that an entity (physical or logical) is becoming outdated or no longer possesses the required level of performance. The objectives of this article are twofold. First, it is intended to contribute to the understanding of obsolescence propagation. Secondly, two supporting approaches for the Identification and Assessment phases are proposed: the House of Obsolescence and the System Obsolescence Criticality Analysis. The former allows the mapping of obsolescence propagation via dependencies, whether imposed changes are desired or imposed, by external actors to the system architecture. Whereas, the objective of the latter is to assign an obsolescence criticality index to the identified risks in order to prioritize them for solution or mitigation determination during the analysis phase. The tools make extensive use of the modeled system knowledge through the application of Systems Engineering. The application of these approaches is presented through an illustrative study.
The popularity of electronic devices has sparked research to implement components that can achieve better performance and scalability. However, companies face significant challenges when they use systems with a long-life cycle, such as in avionics, which leads to obsolescence problems. Obsolescence can be driven by many factors, primary among which could be the rapid development of technologies that lead to a short life cycle of parts. Moreover, obsolescence problems can prove costly in terms of intermittent stock availability and unmet demand. Therefore, obsolescence forecasting appears to be one of the most efficient solutions. This paper presents a review of gaps in the actual approaches and proposes a method that can better forecast the product life cycle. The proposed approach will help companies to improve obsolescence forecasting and reduce its impact in the supply chain. The method introduces a stochastic approach to estimate the obsolescence life cycle through simulation of demand data using Markov chain and homogeneous compound Poisson process. This approach uses multiple states of the life cycle curve based on the change in demand rate and introduces hidden Markov theory to estimate the model parameters. Numerical results are provided to validate the proposed method. To examine the accuracy of this approach, the standard deviation (STD) of obsolescence time is calculated. The results showed that the life cycle curves of parts can be predicted with high accuracy.
Obsolescence occurs when system elements become outdated, and it leads to operational, logistical, reliability, and cost implications. In the U.S. military, this problem is a result of the U.S. Department of Defense's (DoD) departure from Military Specification (MILSPEC) standards in 1994 and transition to the use of Commercial Off the Shelf products. Obsolescence costs the DoD more than $750 million annually. The current risk management tools for obsolescence are based on a quantitative approach that uses cost optimization, and expert judgment is not used as a critical criterion. A review of the literature has revealed that during the design phase of technological systems, there is limited knowledge and a lack of training associated with mitigating obsolescence, and multicriteria decision‐making (MCDM) methods are not currently used to mitigate the risk of obsolescence. Thus, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS, which is a MCDM method) and Monte Carlo simulations are proposed as the foundation for this work. This paper adds to the methodology by introducing an expert judgment criterion. A case study was conducted using military and civilian experts. Expert validation showed that the TOPSIS model successfully identified the best system for mitigating obsolescence. This model can be used by system designers and other decision makers to conduct trade studies in obsolescence management.