As the most important session of the intelligent yard, this paper considers the optimization of steel plate yard outbound operation that orients to multiple cutting lines. According to the cutting requirements, the yard should retrieve cutting plates distributed in different places, during which outbound orders of cutting plates and relocation strategy of blocking plates should be considered. Since outbound and cutting operations are performed simultaneously, cutting influence should be considered when formulating outbound operations. Therefore, instead of improving the outbound efficiency only, this problem aims to reduce the makespan of the entire process. We introduce a hybrid BVNS-RSP algorithm to solve this problem. The algorithm uses basic variable neighborhood search to decide outbound order and implements a relocation sub-problem model to determine the relocation strategy. Two initial heuristics are developed to fasten the search efficiency. Experimenting with actual data demonstrates the performance of the algorithm. Besides, results under different cut time variations illustrate their effect on makespan, thus providing suggestions for cutting plan formulation. Note to Practitioners—This paper considers a practical problem in shipbuilding’s steel plate yard. Currently, the outbound operation of steel plate yards mainly relies on manual experience, which is inefficient. With upgrading technologies such as wireless sensors and the Internet of Things, it is possible to establish an intelligent yard. So that, given the cutting plan, the required plates can be retrieved and sent to cutting lines automatically without human intervention. The efficiency of outbound operation is vital to the whole process, and the operational planning session that translates complex cutting plans into executable operation instructions is the most crucial part of this system. This work fills in this section and improves the outbound efficiency by optimizing the crane’s trajectory and eliminating redundant moves. Besides, this paper also provides some constructive suggestions for cutting plan development, helping the shipbuilding technical center to formulate cutting plans more scientifically.

During the age of the Industrial Internet of Things (IIoT), extensive sensors are deployed on steel production lines to construct intelligent monitoring systems. A fan is a crucial piece of machinery in steel production lines, making its fault diagnosis imperative to prevent air pollution and casualties. DNN (Deep Neural Network) with powerful real-time IIoT data analysis has achieved outstanding performance in recognizing faults. Due to the black-box nature of DNNs, these models cannot provide reasonable explanations for their diagnostic decisions. It is still challenging for experts to make reliable and trustworthy conclusions. To address the issue, this paper introduces a new neural-symbolic model, termed Confidence and Classification DBN (CC-DBN), where confidence and classification rules are extracted from a Deep Belief Network (DBN) to provide an explainable representation of DBN feature learning and reasoning. In order to extract confidence rules, this paper develops a new clustering logic Restricted Boltzmann Machine (C-LRBM). Confidence rules can generate latent features of the raw vibration data of the fan and simultaneously explain the hierarchical reasoning of stacked RBM. Besides, to make trustworthy fan diagnosis decisions, classification rules are extracted to provide an explainable symbolic representation between input and output feature spaces. The experiment is performed on an industrial fan dataset from a leading steel production line in Shanghai. The results demonstrate that the proposed CC-DBN can effectively discover knowledge for fan diagnostic decisions and simultaneously achieve superior fault discrimination over typical classifiers and DBNs.

Complex problem solving is recognized as an important resource of empirical knowledge accumulation. Learners can acquire and consolidate their empirical knowledge based on practical experience in the complex problem solving. Although many studies on complex problem solving have documented the effects of problem solving on knowledge accumulation, few have addressed the detailed process of empirical knowledge accumulation in the complex problem solving. The purpose of this study is to explore the process of novices' empirical knowledge accumulation in solving complex problem. A multi-stage experiment based on a real-world engineering problem is presented in the study. By means of analysis of the difference between novice and experts, a novel concept of “inflection point” and a novel “four period novices' empirical knowledge accumulation curve” are presented, which can be used to explain the novices' empirical knowledge accumulation process in solving complex problem.