Bolted joints are one of the most common fastening methods in engineering applications. To meet the requirements of structural parts, the torque method is often used for controlling the bolted joint performance. However, only a few investigations have been carried out on the conversion efficiency of bolt torque to the tensile force, leading to uncertainty and potential safety hazards during the bolt tightening. In order to study the input torque distribution and overcome problems caused by the Motosh method and experimental investigations, a new energy-based torque distribution model is established in the present study. In the proposed model, numerous affecting parameters, including the connector compression work, effective bearing radius, effective thread contact radius, and spiral angle are considered. Then a parameterized thread mesh model using finite element technology is proposed to analyze the influence of different bolt friction coefficients on the bolt tightening process. Based on 16 types of tightening analyses, it is concluded that as bolt friction coefficient increases, the corresponding torque conversion rate decreases from 14.45% to 7.89%. Compared with the Motosh method, the torque conversion rate obtained by the proposed method is relatively large, which makes the actual pre-tightening force larger than the design value. However, there is still a possibility of bolt failure.

The computer numerically controlled (CNC) system is the key functional component of CNC machine tool control systems, and the servo drive system is an important part of CNC systems. The complex working environment will lead to frequent failure of servo drive systems. Taking effective health management measures is the key to ensure the normal operation of CNC machine tools. In this paper, the comprehensive effect of fault prediction and fault diagnosis is considered for the first time, and a health management system for machine tool servo drive systems is proposed and applied to operation and maintenance management. According to the data collected by the system and related indicators, the technology can predict the state trend of equipment operation, identify the hidden fault characteristics in the data, and further diagnose the fault types. A health management system mainly includes fault prediction and fault diagnosis. The core of fault prediction is the gated recurrent unit (GRU). The attention mechanism is introduced into a GRU neural network, which can solve the long-term dependence problem and improve the model performance. At the same time, the Nadam optimizer is used to update the model parameters, which improves the convergence speed and generalization ability of the model and makes it suitable for solving the prediction problem of large-scale data. The core of fault diagnosis is the self-organizing mapping (SOM) neural network, which performs cluster analysis on data with different characteristics, to realize fault diagnosis. In addition, feature standardization and principal component analysis (PCA) are introduced to balance the influence of different feature scales, enhance the feature of fault data, and achieve data dimensionality reduction. Compared with the other two algorithms and their improved versions, the superiority of the health management system with high-dimensional data and the enhancement effect of fault identification are verified. The relative relationship between fault prediction and diagnosis is further revealed, and the adjustment idea of the production plan is provided for decision makers. The rationality and effectiveness of the system in practical application are verified by a series of tests of fault data sets.

For complex equipment, it is easy to over-evaluate the impact of failure on production by estimating the reliability level only through failure probability. To remedy this problem, this paper proposes a statistical evaluation method based on fuzzy failure data considering the multi-state characteristics of equipment failures. In this method, the new reliability-evaluation scheme is firstly presented based on the traditional statistical analysis method using the Weibull distribution function. For this scheme, the failure-grade index is defined, and a fuzzy-evaluation method is also proposed by comprehensively considering failure severity, failure maintenance, time, and cost; this is then combined with the time between failures to characterize the failure state. Based on the fuzzy failure data, an improved adaptive-failure small-sample-expansion method is proposed based on the classical bootstrap method and the deviation judgment between distributions of the original and newborn samples. Finally, a novel reliability-evaluation model, related to the failure grade and its membership degree, is established to quantify the reliability level of equipment more realistically. Example cases for three methods of the scheme (the failure-grade fuzzy-evaluation method, the sample-expansion method, and the reliability-evaluation modeling method) are presented, respectively, to validate the effectiveness and significance of the proposed reliability-evaluation technology.

Since the emergence of artificial intelligence and deep learning methods, the fault diagnosis of bearings in rotating machinery has gradually been realized, reducing the high costs of bearing faults. However, in the actual work of the equipment, faults rarely occur, resulting in less fault data. Therefore, it is necessary to study small sample fault data. For the case of less fault data, the Maml–Triplet fault classification learning framework based on the combination of maml and the triplet neural network is proposed. In the framework of Maml-Triplet fault classification, firstly, an initial signal feature extractor is obtained using the Maml training method. Secondly, the feature vectors corresponding to signal data are obtained using depth distance measurement learning in the triplet neural network, and the fault type is judged based on the feature vectors of unknown signal. The results show that the accuracy of the Maml–Triplet model is 2% higher than that of the triplet model alone and 5% higher than that of the Maml–CNN meta learning method. When there are fewer data samples, the accuracy gap is more obvious. Therefore, in the case of less data, the Maml–Triplet model has an excellent fault identification ability.