Digital twin (DT) is a key technology for realizing the interconnection and intelligent operation of the physical world and the world of information and provides a new paradigm for fault diagnosis. Traditional machine learning algorithms require a balanced dataset. Training and testing sets must have the same distribution. Training a good generalization model is difficult in an actual production line operation process. Fault diagnosis technology based on the digital twin uses its ultrarealistic, multisystem, and high-precision characteristics to simulate fault data that are difficult to obtain in an actual production line to train a reliable fault diagnosis model. In this article, we first propose an improved random forest (IRF) algorithm, which reselects decision trees with high accuracy and large differences through hierarchical clustering and gives them weights. Digital twin technology is used to simulate a large number of balanced datasets to train the model, and the trained model can be transferred to a physical production line through transfer learning for fault diagnosis. Finally, the feasibility of our proposed algorithm is verified through a case study of an automobile rear axle assembly line, for which the accuracy of the proposed algorithm reaches 97.8%. The traditional machine learning plus digital twin fault diagnosis method proposed in this paper involves some generalization, and thus has practical value when extended to other fields.

Due to the rapid development of industrial internet technology, the traditional manufacturing industry is in urgent need of digital transformation, and one of the key technologies to achieve this is multi-source data fusion. For this problem, this paper proposes an improved entropy-weighted topsis method for a multi-source data fusion evaluation system. It adds a fusion evaluation system based on the decision-level fusion algorithm and proposes a dynamic fusion strategy. The fusion evaluation system effectively solves the problem of data scale inconsistency among multi-source data, which leads to difficulties in fusing models and low fusion accuracy, and obtains optimal fusion results. The paper then verifies the effectiveness of the fusion evaluation system through experiments on the multilayer feature fusion of single-source data and the decision-level fusion of multi-source data, respectively. The results of this paper can be used in intelligent production and assembly plants in the discrete industry and provide the corresponding management and decision support with a certain practical value.

The traditional shop floor scheduling problem mainly focuses on the static environment, which is unrealistic in actual production. To solve this problem, this paper proposes a digital twin-driven shop floor adaptive scheduling method. Firstly, a digital twin model of the actual production line is established to monitor the operation of the actual production line in real time and provide a real-time data source for subsequent scheduling; secondly, to address the problem that the solution quality and efficiency of the traditional genetic algorithm cannot meet the actual production demand, the key parameters in the genetic algorithm are dynamically adjusted using a reinforcement learning enhanced genetic algorithm to improve the solution efficiency and quality. Finally, the digital twin system captures dynamic events and issues warnings when dynamic events occur in the actual production process, and adaptively optimizes the initial scheduling scheme. The effectiveness of the proposed method is verified through the construction of the digital twin system, extensive dynamic scheduling experiments, and validation in a laboratory environment. It achieves real-time monitoring of the scheduling environment, accurately captures abnormal events in the production process, and combines with the scheduling algorithm to effectively solve a key problem in smart manufacturing.

Quality-related prediction in the continuous-casting process is important for the quality and process control of casting slabs. As intelligent manufacturing technologies continue to evolve, numerous data-driven techniques have been available for industrial applications. This case study was aimed at developing a machine-learning algorithm, capable of predicting slag inclusion defects in continuous-casting slabs, based on process condition sensor data. A large dataset consisting of sensor data from nearly 7300 casting samples has been analyzed, with the empirical mode decomposition (EMD) algorithm utilized to process the multi-modal time series. The following machine-learning algorithms have been examined: K-Nearest neighbors, support vector classifier (linear and nonlinear kernels), decision trees, random forests, AdaBoost, and Artificial Neural Networks. Four over-sampling or under-sampling algorithms have been adopted to solve imbalanced data distribution. In the experiment, the optimized random forest outperformed other machine-learning algorithms in terms of recall and ROC AUC, which could provide valuable insights for quality control.