Owing to its precise positioning capability and fast dynamic behavior, the permanent magnet synchronous linear motor (PMSLM) has found broad application in advanced manufacturing and related industrial systems. However, air-gap nonuniformity faults, which are typical faults in PMSLMs, can cause thrust fluctuations and other adverse effects, thereby impairing stable equipment operation and potentially leading to safety accidents. Therefore, accurate diagnosis of these faults is essential. To address this issue, a dual-branch multiscale diagnostic method based on complementary feature utilization and joint decision-making is proposed. First, a 1-D diagnostic branch is developed to extract discriminative features from subtle fault-induced variations in the external magnetic field signal. Meanwhile, a Hankel-matrix mapping converts each 1-D external magnetic field signal into a grayscale image, which is subsequently processed by a dedicated 2-D branch to capture spatial structures and multiscale texture patterns. Finally, a joint decision layer is designed to comprehensively exploit the outputs of the two branches for fault identification. Simulation results show that the proposed method achieves a fault diagnosis accuracy of 99.83% under noise-free conditions and maintains an accuracy of 93.53% under white Gaussian noise at an SNR of 20 dB. Experiments using measured data collected from the developed PMSLM experimental platform, together with deployment experiments on edge computing platforms, further verify the effectiveness of the proposed model.

The maximum classifier discrepancy domain adaptation (DA) method based on a dual-classifier structure has achieved some success in fault diagnosis of cross-working condition, yet its reliance on the dual-classifier structure may fail to effectively represent the data characteristics of the target domain and may suffers from insufficient classification boundary discrimination. To address this, this paper extends the aforementioned structure to multiple classifiers and proposes a multi-classifier discrepancy (MuCD)-driven DA approach, which enhances the representation of target domain data characteristics, through exploiting the discrepancies among multiple classifier pairs. Additionally, given the uncertainty of multi-classifier outputs, the harmonic mean is calculated and a screening threshold is set. Combined with the self-supervised learning losses for target domain, a confidence pseudo-label strategy-guided self-supervised learning (CPSL) mechanism is designed, to guide and enhance discriminative learning among different fault classes in target domain, thereby improving the model’s diagnosis performance. Furthermore, by specifically integrating CPSL into the MuCD framework, a cross-working condition fault diagnosis method based on multi-classifier discrepancy-driven learning enhanced by confidence pseudo-label self-supervision (CPSL-MuCD) is proposed. Finally, comparative experiments and ablation studies on bearing fault, gear fault, and bearing-gear compound fault datasets verify the effectiveness and generalizability of the proposed CPSL-MuCD.

Although condition monitoring systems (CMS) provide detailed information about the health of critical wind turbine components, their practical application in wind farm operations and maintenance (O&M) remains limited, significantly diminishing their value. The reasons for this situation are not merely technical issues, rather, a complex interplay of various factors besides the condition monitoring algorithms themselves. The purpose of the paper is to investigate these reasons and propose a potential solution. Through in-depth analysis, two gaps are identified. The first gap is the Data-Model Gap, in which operational wind turbine data do not adequately satisfy the assumptions and quality requirements of condition monitoring algorithms. The second is the Model-Decision Gap, where the CMS output fails to provide sufficient information to support maintenance decisions. Based on this, a Data-Model-Decision Gap (DMDG) framework is further developed to explain how maintenance requirements can be used to determine the CMS outputs and, subsequently, the wind turbine condition monitoring data that are needed to produce these CMS outputs. Such a CMS design logic reverses the usual data-to-model development sequence by starting from understanding what kind of CMS outputs can actually support decision-making in practical wind farm O&M. This new CMS design approach emphasizes the alignment of data, models, and decision processes through an iterative and integrated design strategy. Research findings indicate that merely improving algorithm accuracy is insufficient to enhance the practical value of CMS. Bridging the aforementioned gaps is the key to transforming the CMS design from “monitoring-oriented” to “decision-oriented” and in the end, providing “prescriptive maintenance solutions”. This change is critical for unlocking the full potential of CMS in wind farm O&M.