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.

Extracting robust fault sensitive features of vibration signals remains a challenge for rotating machinery fault diagnosis under variable operating conditions. Most existing fault diagnosis methods based on the convolutional neural network (CNN) can only extract single-scale features, which not only loss fault sensitive information on other scales, but also suffer from the domain shift problem. In this work, a novel end-to-end deep learning network named adaptive weighted multiscale convolutional neural network (AWMSCNN) is proposed to adaptively extract robust and discriminative multiscale fusion features from raw vibration signals. The AWMSCNN consists of three main components: the denoising layer, the adaptive weighted multiscale convolutional (AWMSC) block, and the multiscale feature fusion layer. The AWMSC block can learn rich and complementary features on multiple scales in parallel. Then, an adaptive weight vector is introduced to modulate multiscale features to emphasize fault sensitive features and suppress features that are sensitive to operating conditions. The train wheelset bearing dataset and the bearing dataset provided by Case Western Reserve University (CWRU) are used to verify the superiority of the proposed model over the basic CNN and other multiscale CNN models. The experiment results show that the proposed model has strong fault discriminative ability and domain adaptive ability against variable operating conditions.

Traditional energy-saving optimization of shop scheduling often separates the coupling relationship between a single machine and the shop system, which not only limits the potential of energy-saving but also leads to a large deviation between the optimized result and the actual application. In practice, cutting-tool degradation during operation is inevitable, which will not only lead to the increase in actual machining power but also the resulting tool change operation will disrupt the rhythm of production scheduling. Therefore, to make the energy consumption calculation in scheduling optimization more consistent with the actual machining conditions and reduce the impact of tool degradation on the manufacturing shop, this paper constructs an integrated optimization model including a flexible job shop scheduling problem (FJSP), machining power prediction, tool life prediction and energy-saving strategy. First, an exponential function is formulated using actual cutting experiment data under certain machining conditions to express cutting-tool degradation. Utilizing this function, a reasonable cutting-tool change schedule is obtained. A hybrid energy-saving strategy that combines a cutting-tool change with machine tool turn-on/off schedules to reduce the difference between the simulated and actual machining power while optimizing the energy savings is then proposed. Second, a multi-objective optimization model was established to reduce the makespan, total machine tool load, number of times machine tools are turned on/off and cutting tools are changed, and the total energy consumption of the workshop and the fast and elitist multi-objective genetic algorithm (NSGA-II) is used to solve the model. Finally, combined with the workshop production cost evaluation indicator, a practical FJSP example is presented to demonstrate the proposed optimization model. The prediction accuracy of the machining power is more than 93%. The hybrid energy-saving strategy can further reduce the energy consumption of the workshop by 4.44% and the production cost by 2.44% on the basis of saving 93.5% of non-processing energy consumption by the machine on/off energy-saving strategy.

A production information management system based on industrial Internet of Things (IoT) technology is designed, which makes the manufactory enterprise have the ability of dynamic shop floor scheduling. To solve the rescheduling problem, a hybrid method combining the game theory method and the rolling horizon rescheduling strategy (HGR) is proposed. In a computational experiment, the values of the relative error (RE) and mean ideal distance (MID) are 11.3 and 13.74, respectively, which illustrates the feasibility and efficiency of the proposed HGR method. An engineering experiment shows that the proposed method can handle the practical engineering problems.

This article presents a novel method for estimating normals on unorganized point clouds that preserves sharp features. Many existing methods are unable to reliably estimate normals for points around sharp features since the neighborhood employed for the normal estimation would enclose points belonging to different surface patches across the sharp feature. To address this challenging issue, a neighborhood reconstruction-based normal estimation method is developed to find a proper neighborhood for points around sharp features. A robust statistics-based method is proposed to identify points that near sharp features and classify the points into two categories: edge points and non-edge points. Two specific neighborhood reconstruction strategies are designed for these two types of points to generate a neighborhood clear of sharp features. The normal of the current point can thus be reliably estimated by principal component analysis using the generated isotropic neighborhood. Numerous case studies have been carried out to compare the reliability and robustness of the proposed method against various existing methods. The experiment results show that the proposed approach performs better than the state-of-the-art methods most of the time and offers an ideal compromise between precision, speed, and robustness.