Abstract
Industrial Internet of Things (IoT) is a ubiquitous network integrating various sensing technologies and communication technologies to provide intelligent information processing and smart control abilities for the manufacturing enterprises. The aim of applying industrial IoT is to assist manufacturers manage and optimize the entire product manufacturing process to improve product quality and production efficiency. Data-driven product development is considered as one of the critical application scenarios of industrial IoT, which is used to acquire the satisfied and robust design solution according to customer demands. Performance analysis is an effective tool to identify whether the key performance have reached the requirements in data-driven product development. The existing performance analysis approaches mainly focus on the metamodel construction, however, the uncertainty and complexity in product development process are rarely considered. In response, this paper investigates a robust performance analysis approach in industrial IoT environment to help product developers forecast the performance parameters accurately. The service-oriented layered architecture of industrial IoT for product development is first described. Then a dimension reduction approach based on mutual information (MI) and outlier detection is proposed. A metamodel based on least squares support vector regression (LSSVR) is established to conduct performance prediction process. Furthermore, the predicted performance analysis method based on confidence interval estimation is developed to deal with the uncertainty to improve the robustness of the forecasting results. Finally, a case study is given to show the feasibility and effectiveness of the proposed approach.
Highlights
With the rapid integrated development of information technologies such as artificial intelligence, big data and Internet of Things in the manufacturing industries, industrial IoT is considered a crucial manufacturing infrastructure to efficiently change how the products are customized, manufactured and delivered [1,2]
This paper introduces particle swarm optimization (PSO) algorithm to obtain the optimal solution for the meta-model construction of performance prediction
To simplify the product development process, mutual information (MI) is used to assess the relationship between the overall performance and design variables, and Table 2 shows the value of MI between the design variables and the overall performance
Summary
With the rapid integrated development of information technologies such as artificial intelligence, big data and Internet of Things in the manufacturing industries, industrial IoT is considered a crucial manufacturing infrastructure to efficiently change how the products are customized, manufactured and delivered [1,2]. It is always difficult for designers to analyze and validate product performance efficiently and effectively due to the limited professional knowledge and black-box models (a black-box model is an unknown function description that is given a list of design variables, and corresponding performance outputs can be acquired without knowing its expression) To ease this problem, performance analysis has become a hot topic for both academics and practitioners. To reduce the computational expense, Zheng et al developed an improved metamodeling approach based prior-knowledge and LSSVR to gain an accurate approximation for performance analysis and optimization [29]. In order to deal with the complexity of performance analysis, extracting key design variables is a considerable issue for model simplification in data-driven product development. Through the collected data from industrial IoT, a robust predicted performance analysis approach is proposed.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call