A fault diagnosis approach based on multi-sensor data fusion is a promising tool to deal with complicated damage detection problems of mechanical systems. Nevertheless, this approach suffers from two challenges, which are (1) the feature extraction from various types of sensory data and (2) the selection of a suitable fusion level. It is usually difficult to choose an optimal feature or fusion level for a specific fault diagnosis task, and extensive domain expertise and human labor are also highly required during these selections. To address these two challenges, we propose an adaptive multi-sensor data fusion method based on deep convolutional neural networks (DCNN) for fault diagnosis. The proposed method can learn features from raw data and optimize a combination of different fusion levels adaptively to satisfy the requirements of any fault diagnosis task. The proposed method is tested through a planetary gearbox test rig. Handcraft features, manual-selected fusion levels, single sensory data, and two traditional intelligent models, back-propagation neural networks (BPNN) and a support vector machine (SVM), are used as comparisons in the experiment. The results demonstrate that the proposed method is able to detect the conditions of the planetary gearbox effectively with the best diagnosis accuracy among all comparative methods in the experiment.

Data-driven methods with multi-sensor time series data are the most promising approaches for monitoring machine health. Extracting fault-sensitive features from multi-sensor time series is a daunting task for both traditional data-driven methods and current deep learning models. A novel hybrid end-to-end deep learning framework named Time-distributed ConvLSTM model (TDConvLSTM) is proposed in the paper for machine health monitoring, which works directly on raw multi-sensor time series. In TDConvLSTM, the normalized multi-sensor data is first segmented into a collection of subsequences by a sliding window along the temporal dimension. Time-distributed local feature extractors are simultaneously applied to each subsequence to extract local spatiotemporal features. Then a holistic ConvLSTM layer is designed to extract holistic spatiotemporal features between subsequences. At last, a fully-connected layer and a supervised learning layer are stacked on the top of the model to obtain the target. TDConvLSTM can extract spatiotemporal features on different time scales without any handcrafted feature engineering. The proposed model can achieve better performance in both time series classification tasks and regression prediction tasks than some state-of-the-art models, which has been verified in the gearbox fault diagnosis experiment and the tool wear prediction experiment.

This paper presents an effective multi-sensor approach for improving the accuracy of laser scanner by using a tactile probe to perform rapid and accurate reverse engineering of complex objects. The proposed system is unique in that it includes not only the physical integration of the two digitizers but also their combination at the measurement information level. With the coordinate data acquired using the optical scanner, intelligent data segmentation and feature recognition algorithm are proposed to divide the original point set into geometric elements and free-form surfaces. The tactile probe is guided to re-measure each feature with a small number of sampling points. Then different data fusion algorithms are proposed to compensate the scanned data patches of geometric features and free-form features with the accurate tactile probing data. Finally, the compensated point data can be exploited for accurate reverse engineering of a CAD model. Through the fusion of different sensor’s information, both sensors complement each other with their advantages. Experimental results show that for the measurement of geometric surface, the proposed method can improve the accuracy of optical measurement to the accuracy of contact measurement. For free-form surface measurement, the proposed method reduces the optical measurement error from +0.032/-0.019mm to ±0.016 mm, and the standard deviation from 0.012 mm to 0.004 mm. The measurement efficiency of proposed method is 4.5 times higher than that of contact measurement alone.

Feature extraction of vibration signal is the key factor of machine fault diagnosis. This paper proposes a novel method of capturing shock energy based on multi-scale weight evaluation of high definition time-frequency map. Specifically, the proposed method is conducted by the following steps. First, ensemble empirical mode decomposition (EEMD) preprocessor-based Hilbert-Huang Transform (HHT) is applied to the raw signal for high definition time-frequency map acquisition. Second, an original algorithm named multi-scale binary spectrum was applied to extract impulsive energy features with different frequency characteristics. Then weights of energy can be calculated by dimensionality reduction of each binary spectrum and merged by summation after blank processing. Finally, power spectrum of compound weight of energy can reveal characteristic frequency corresponding to specific fault. In this method, the key point is enhancement of frequency spectrum using higher dimension details. The process of multi-scale binarization and weight summation were aligned and the effectiveness is verified by simulated signal processing and actual case of train bearing experiment.

A dual-wave Quasi-CW Nd:YAG laser has been demonstrated at the wavelengths of 1319 nm and 660nm. The radiation energy level of the 1319nm transition was analyzed. The critical technology of restraining resonance of 1064nm so as to improve that of 660nm was discussed. Sophisticated optical coating and cavity structure was studied. And a maximum CW Output power of 43W at 1319nm was acquired. Based 1319nm laser, an intracavity frequency-doubling laser of 660nm was also demonstrated by using KTP crystal and an acousto-optically Q-switch. And a Quasi-CW red light output power of 2W at 660nm was acquired, accordingly, dual-wave output was realized.

Rolling linear guide pairs are extensively utilized in CNC machine tool industry and other industries. To efficiently and accurately assess the performance indicators of guide pairs, a multi-parameter test bench has been developed. Parameters measured on the test bench include motion accuracy, preload drag force, vibration, and temperature rise, and fatigue life of rolling linear guides. The mechanical structure and measurement control system of the test bench were designed according to measurement principles and methods. ANSYS software was utilized to investigate statics analysis of the gantry, modal analysis of the upper bed, and simulation analysis of the impact of loading block thickness on load distribution uniformity for the tested guide pairs. The analysis results validated the rationality of the structural design. In order to validate the accuracy of the multi-parameter test bench, comparative experiments were conducted using Hilectro LGD35 model guide pairs as the research object. The experiments focused on assessing the motion accuracy, preload drag force, and fatigue life of the targeted guide pairs. The experimental results demonstrated that the test bench achieves a high level of accuracy, and verified the correctness of the derivation equations for motion accuracy measurement.