Fault diagnosis in rolling bearings is critical important in preventing machinery damage. Current deep learning-based approaches for rolling bearing fault diagnosis mainly rely on complex models that require significant hardware storage and computing power. In this paper, we introduce a multiscale Depth-wise Separable Convolutions and network pruning (MS-DWSC-PN) approach for lightweight rolling bearing fault diagnosis. Initially, the original one-dimensional vibration signals are transformed into two-dimensional time-frequency images using continuous wavelet transform (CWT), rendering them suitable for MS-DWSC-PN. Secondly, the datasets and an adaptive learning rate reduction algorithm are utilized to train the model, and the lightweight network model is achieved through network pruning. Subsequently, the results obtained from extensive experiments on identical datasets using AlexNet, VGG16, and LeNet confirm that the proposed model exhibits lower FLOPs and reduced iteration time. Finally, the generalizability of the model under variable operating conditions is discussed. Compared to with other intelligent diagnosis methods, the presented approaches can achieve smaller model size and higher accuracy under both constant and variable working conditions.

In recent years, single-source-data-based deep learning methods have made considerable strides in the field of fault diagnosis. Nevertheless, the extraction of useful information from multi-source data remains a challenge. In this paper, we propose a novel approach called the Genetic Simulated Annealing Optimization (GASA) method with a multi-source data convolutional neural network (MSCNN) for the fault diagnosis of rolling bearing. This method aims to identify bearing faults more accurately and make full use of multi-source data. Initially, the bearing vibration signal is transformed into a time–frequency graph using the continuous wavelet transform (CWT) and the signal is integrated with the motor current signal and fed into the network model. Then, a GASA-MSCNN fault diagnosis method is established to better capture the crucial information within the signal and identify various bearing health conditions. Finally, a rolling bearing dataset under different noisy environments is employed to validate the robustness of the proposed model. The experimental results demonstrate that the proposed method is capable of accurately identifying various types of rolling bearing faults, with an accuracy rate reaching up to 98% or higher even in variable noise environments. The experiments reveal that the new method significantly improves fault detection accuracy.

In deep-hole boring processes, boring bars with a large length-to-diameter ratio are typically employed. However, excessive overhang significantly reduces the boring bar’s stiffness, inducing vibrational effects that severely degrade machining precision and surface quality. To address this, the research objective is to suppress vibrations using a tunable-parameter boring bar. This paper proposes a novel Tunable Dynamic Vibration Absorber (TDVA) boring bar and designs its fundamental parameters. Based on the derived dynamic model, the vibration characteristics of the proposed boring bar are analyzed, revealing the variation in damping performance under different excitation frequencies. By establishing the relationship between TDVA stiffness, damping, and the axial compression of rubber bushings, optimal parameter combinations can be precisely identified for specific excitation frequencies. Ultimately, adjusting the TDVA’s axial compression displacement (0.1–0.5 mm) significantly expands the effective machining frequency range compared to conventional designs while maintaining operational reliability. This study proposes a novel Tunable Dynamic Vibration Absorber (TDVA) that innovatively integrates axial compression to achieve coupled stiffness and damping adjustments, addressing the rigidity–adaptability trade-off in deep-hole boring tools.

In deep-hole boring processes, boring bars with a large length-to-diameter ratio are typically employed. However, excessive overhang significantly reduces the boring bar’s stiffness, inducing vibrational effects that severely degrade machining precision and surface quality. To address this, the research objective is to suppress vibrations using a tunable-parameter boring bar. This paper proposes a novel Tunable Dynamic Vibration Absorber (TDVA) boring bar and designs its fundamental parameters. Based on the derived dynamic model, the vibration characteristics of the proposed boring bar are analyzed, revealing the variation in damping performance under different excitation frequencies. By establishing the relationship between TDVA stiffness, damping, and the axial compression of rubber bushings, optimal parameter combinations can be precisely identified for specific excitation frequencies. Ultimately, adjusting the TDVA’s axial compression displacement (0.1–0.5 mm) achieves a 22% expansion in the effective machining frequency range.

To reduce ram deflection and positional deviation at the boring spindle front end of a floor-type milling and boring machine under large extension, a ram-boring spindle assembly was investigated. A finite element model was established based on the actual structure, guideway support, and spindle assembly. Gravity-induced deformation and vertical displacement at the boring spindle front end under different extension conditions were analyzed to identify weak regions. The Solid Isotropic Material with Penalization method was then used to optimize the adjustable internal region of the ram with the objective of reducing structural compliance. The topology–density distribution and the deformation characteristics under different extension conditions were then used to guide an engineering reconstruction of the internal stiffeners, considering casting, assembly, internal space constraints, and engineering experience. Static analysis, displacement testing, and modal analysis were performed to verify the optimized structure. Results show that the maximum total deformation under simultaneous maximum extension decreased from 0.10268 mm to 0.097325 mm, while the mass decreased from 2424 kg to 2363 kg. The measured vertical displacement decreased from 0.114 mm to 0.108 mm. The first six natural frequencies increased by 1.48–5.91%. The proposed reconstruction improves deformation control and dynamic performance while reducing mass.