We propose a bearing health management framework leveraging large language models (BearLLM), a novel multimodal model that unifies multiple bearing-related tasks by processing user prompts and vibration signals. Specifically, we introduce a prior knowledge-enhanced unified vibration signal representation to handle various working conditions across multiple datasets. This involves adaptively sampling the vibration signals based on the sampling rate of the sensor, incorporating the frequency domain to unify input dimensions, and using a fault-free reference signal as an auxiliary input. To extract features from vibration signals, we first train a fault classification network, then convert and align the extracted features into word embedding, and finally concatenate these with text embedding as input to an LLM. To evaluate the performance of the proposed method, we constructed the first large-scale multimodal bearing health management (MBHM) dataset, including paired vibration signals and textual descriptions. With our unified vibration signal representation, BearLLM using one set of pre-trained weights achieves state-of-the-art performance on nine publicly available fault diagnosis benchmarks, outperforming specific methods designed for individual datasets. We provide a dataset, our model, and code to inspire future research on building more capable industrial multimodal models.

Continuous waveform (CW) radar is widely used in intelligent transportation systems, vehicle assisted driving, and other fields because of its simple structure, low cost and high integration. There are several waveforms which have been developed in the last years. The chirp sequence waveform has the ability to extract the range and velocity parameters of multiple targets. However, conventional chirp sequence waveforms suffer from the Doppler ambiguity problem. This paper proposes a new waveform that follows the practical application requirements, high precision requirements, and low system complexity requirements. The new waveform consists of two chirp sequences, which are intertwined to each other. Each chirp signal has the same frequency modulation, the same bandwidth and the same chirp duration. The carrier frequencies are different and there is a frequency shift which is large enough to ensure that the Doppler frequencies for the same moving target are different. According to the sign and numerical relationship of the Doppler frequencies (possibly frequency aliasing), the Doppler frequency ambiguity problem is solved in eight cases. Theoretical analysis and simulation results verify that the new radar waveform is capable of measuring range and radial velocity simultaneously and unambiguously, with high accuracy and resolution even in multi-target situations.

This paper considers the detection of fluctuating targets in heavy-tailed clutter through the use of dynamic programming based on track-before-detect (DP–TBD) in radar systems. The clutter is modeled in terms of K-distribution, which can be widely used to describe non-Gaussian clutter received from high-resolution radars and radars working at small grazing angles. Swerling type 1 is considered to describe the target fluctuation between scans. Conventional TBD techniques suffer from significant performance loss in heavy-tailed environments due to the more frequent occurrences of target-like outliers. In this paper, we resort to a DP–TBD algorithm based on prior information, which can enhance the detection performance by using the environment and target fluctuating information during the integration process of TBD. Under non-Gaussian background, the expressions of the likelihood ratio merit function for Swerling type 1 targets are derived first. However, the closed-form of the merit function is difficult to obtain. In order to reduce the complexity of evaluating the merit function and the computational load, an efficient approximation method as well as a two-stage detection approach is proposed and used in the integration process. Finally, several numerical simulations of the new strategy and the comparisons are presented to verify that the proposed algorithm can improve the detection performance, especially for fluctuating targets in heavy-tailed clutter.

The accuracy of data-driven intelligent prediction for machining quality relies on the training samples. However, in actual applications, the continuous operation of machining equipment leads to gradual distribution shifts between the process data and the training samples for modeling. The shifts result in a degradation in the performance of predictive model, previous studies have often overlooked this issue. To tackle with the intricate problem, this research proposes a real-time model optimization approach. Firstly, a method for detecting machining data distribution shifts based on the two-sample Kolmogorov–Smirnov test is proposed. Then, an adaptive hybrid prediction model (AHPM) capable of real-time optimization is developed. This model consists of a deep neural network (DNN) and a broad learning system (BLS). DNN plays a primary role in prediction within the hybrid model with excellent generalization capability. BLS quickly completes optimization prior to DNN with its unique parameter update mechanism to compensate for prediction loss. Experimental results indicate that AHPM achieves the shortest optimization time while maintaining high accuracy, with post-optimization error reduction rates for mean squared error, mean absolute error, and mean absolute percentage error all exceeding 10%. In the test of application to actual machining cases, accuracy improved by 8.88% compared to traditional methods without optimization.

In the process of metal surface defect detection, it is difficult to detect and segment small defects. In order to solve this problem, this paper uses weighted object variance algorithm to detect metal surface defects. Then the feature of defect area is extracted and the defect classification model based on support vector machine is trained. In order to verify the effectiveness of the method, this paper takes the metal surface of bearing cylindrical roller as the specific research object. The experimental results show that the method meets the production requirements.

This paper considers the detection of fluctuating target in heavy-tailed clutter through the use of dynamic programming based on track-before-detect (DP-TBD) in radar systems. The clutter is modeled in terms of K-distribution, which can be widely used to describe non-Gaussian clutter received from high-resolution radars and radars working at small grazing angle. Swerling type 1 is considered to describe the target fluctuation between scans. Conventional TBD techniques suffer from significant performance loss in heavy-tailed environments due to the more frequent occurrences of target-like outliers. In this paper, we resort to DP-TBD algorithm based on prior information, which can enhance the detection performance by using the environment and target fluctuating information during the integration process of TBD. Under non-Gaussian background, the expressions of the likelihood ratio merit function for Swerling type 1 target are derived first. However, the closed analytical form of the merit function is difficult to be obtained. In order to reduce the complexity of evaluating the merit function and the computational load, an efficient approximation method as well as a two-stage detection approach is proposed and used in the integration process. Finally, several numerical simulations of the new strategy and the comparisons are presented to verify that the proposed algorithm can improve the detection performance, especially for fluctuating target in heavy-tailed clutter.