A CNN-ABiGRU method for Gearbox Fault Diagnosis

As a key part of modern industrial machinery, there has been a lot of fault diagnosis methods for gearbox. However, traditional fault diagnosis methods suffer from dependence on prior knowledge. This paper proposed an end-to-end method based on convolutional neural network (CNN), Bidirectional gated recurrent unit (BiGRU), and Attention Mechanism. Among them, the application of BiGRU not only made perfect use of the time sequence of signal, but also saved computing resources more than the same type of networks because of the low amount of calculation. In order to verify the effectiveness and generalization performance of the proposed method, experiments are carried out on two datasets, and the accuracy is calculated by the ten-fold crossvalidation. Compared with the existing fault diagnosis methods, the experimental results show that the proposed model has higher accuracy.

Vehicle Motion State Prediction Method Integrating Point Cloud Time Series Multiview Features and Multitarget Interactive Information

A vehicle motion state prediction algorithm integrating point cloud timing multiview features and multitarget interaction information is proposed in this work to effectively predict the motion states of traffic participants around intelligent vehicles in complex scenes. The algorithm analyzes the characteristics of object motion that are affected by the surrounding environment and the interaction of nearby objects and is based on the complex traffic environment perception dual multiline light detection and ranging (LiDAR) technology. The time sequence aerial view map and time sequence front view depth map are obtained using real-time point cloud information perceived by the LiDAR. Time sequence high-level abstract combination features in the multiview scene are then extracted by an improved VGG19 network model and are fused with the potential spatiotemporal interaction of the multitarget operation state data extraction features detected by the laser radar by using a one-dimensional convolution neural network. A temporal feature vector is constructed as the input data of the bidirectional long-term and short-term memory (BiLSTM) network, and the desired input-output mapping relationship is trained to predict the motion state of traffic participants. According to the test results, the proposed BiLSTM model based on point cloud multiview and vehicle interaction information is better than other methods in predicting the state of target vehicles. The results can provide support for the research to evaluate the risk of intelligent vehicle operation environment.

Algorithm of axial compressor stall warning based on BP neural network and fuzzy logic

Stall warning of axial compressor is very challenging and the existing warning margin is not enough. A algorithm based on BP neural network fusion fuzzy logic is proposed. Firstly, BP neural network is used for training recognition, next the identification results are fused with fuzzy logic reasoning to form the result judgment of time sequence, finally the stall early warning of axial compressor is realized. The simulation results of the experimental data show that the stall data at all speeds are at least 0.1s in advance of the early warning. Compared with other methods, this method has a better surge early warning margin performance and engineering practicability.

Time Synthesis in Organization of Sensorimotor Action

Time synthesis of sensorimotor action is reviewed as a process of a coherence setting action duration (expected duration), time sequence of required operations and significant changes in conditions. Aim: to experimentally set up the connection of time synthesis success and efficiency of realization sensorimotor action in changeable conditions. Hypothesis: successful time synthesis of the setting duration and the temporal sequence of operations in the mental organization of sensorimotor action in changing conditions is realized in accordance with the corresponding operational meaning and is allowed by anticipatory effects and an increase in the effectiveness of the action, materials and methods. An experimental study involved 152 male and female students. Participants of the investigation solved experimental tasks, implemented in a computer version, according to schemes of a simple visual-motor reaction and a choice reaction (separately and in combination), according to a scheme of sensorimotor action with a warning signal when the apperceptive scheme, setting duration and sequence of required operations were changed promptly. Results were reviewed in the aspect of disclosing the features of the subject's elimination of the uncertainty of the moment of achieving the goal in the future and the construction of a sequence of operations of sensorimotor actions in a connection with changes in external conditions, typical for the time deficit regime. The conditionality of the time synthesis of sensorimotor action by the actual operational meaning was established revealing that the successful temporal synthesis of sensorimotor action in changing conditions is associated with the fastest acceptance of an adequate apperceptive scheme, with effective anticipation of the moment of achieving the goal and the formation of a detailed setting duration of action, with the formation of a temporal sequence of required operations. Conclusions. The levels of success of the time synthesis of sensorimotor action in changing conditions are highlighted: “quite successful; moderately successful; unsuccessful.”

Initial development of precipitation and onset of cloud electrification in thunderstorms at Pune

Using one-minute interval data of electric field and the records of rainfall measured at the ground surface, time sequence in the initial registration of precipitation and the onset of cloud electrification was examined for a series of 14 thunderstorms of the year 1973 at Pune to study the relationship between the initial development of precipitation and intensification of cloud electrification. The combined result of the 14 storms studied, each of which yielded precipitation, indicated in-cloud development of precipitation at least 3-7 minutes in advance of onset of cloud electrification. It is inferred from the other supplementing studies published by other workers and from the above result that in most cases the precipitation development in thunderstorms is initiated well before the electric field begins to intensify. This result is in close agreement with the result of previous studies.

CNN-Based Fault Detection for Smart Manufacturing

A smart factory is a highly digitized and networked production facility based on smart manufacturing. A smart manufacturing plant is the result of intelligent systems deployed in the factory. Smart factories have higher production volumes and are prone to machine failures when operating in almost all applications on a daily basis. With the growing concept of smart manufacturing required for Industry 4.0, intelligent methods for detecting and classifying bearing faults have become a subject of scientific research and interest. In this paper, a deep learning-based 1-D convolutional neural network is proposed using the time-sequence bearing data from the Case Western Reserve University (CWRU) bearing database. Four different sets of data are used. The proposed method achieves state-of-the-art accuracy even with a small amount of training data. For the sensitivity analysis of the proposed method, metrics such as precision, recall, and f-measure are determined. Next, we compare the proposed method with a 2-D CNN that uses two-dimensional image illustrations of raw data as input. This method shows the effectiveness of using 1-D CNNs over 2-D CNNs for time-sequence data. The proposed method is computationally inexpensive and outperforms the most complex and computationally intensive algorithms used for bearing fault detection and diagnosis.

Tractor-trailer-train braking time sequence detection based on monocular vision

The tractor-trailer-train at the braking process prone to braking instability caused by asynchronous braking between the shafts. With respect to the lack of intelligent detection of Braking Time Sequence (BTS), a non-contact dynamic detection scheme of intelligent vehicle BTS is proposed. Based on the monocular vision principle, the edge markers of tractor-trailer train tires are identified, and the tire slip rate is solved. The noise reduction of the collected image is processed. The marker area is obtained by Blob analysis. This region at the image to be matched is identified by the template matching algorithm based on contour. The camera is calibrated by Zhang’s calibration method. In order to verify the effectiveness of the detection scheme, the real vehicle test was carried out. The test results show that the error of slip rate solution is below 4.2%.