Search

The adaptability plays a significant role in moving detection. The diverse scenarios in real world still challenge this problem. Therefore, in this paper, we proposed an adaptive moving detection method, namely Adaptive Random-based Self-Organizing back- ground subtraction (ABSOBS) method. This method can adaptively extract the moving objects in various conditions and eliminate the “ghost” pixels simultaneously. Therefore, a robust initialization strategy is proposed to remove the noise pixels caused by the initialized frames. The proposed method uses a random- based scheme which allows the foreground pixels to up- date the neural network with a small probability. This strategy allows our algorithm to efficiently handle scene changes. Moreover, a foreground filter based on random rule is designed to eliminate the “ghost” pixel. More importantly, ABSOBS adopts a regulator to control the updating rate in different conditions. It makes our method easy-to-used and need not to set the parameters manually. The experiment results on various scenarios show that our method improves the detection accuracy for the SOBS and outperforms other state-of- the-art methods.

The current dynamic gesture contour feature extraction method has the problems that the recognition rate of dynamic gesture contour feature and the recognition accuracy of dynamic gesture type are low, the recognition time is long, and comprehensive is poor. Therefore, we propose a dynamic gesture contour feature extraction method using residual network transfer learning. Sensors are used to integrate dynamic gesture information. The distance between the dynamic gesture and the acquisition device is detected by transfer learning, the dynamic gesture image is segmented, and the characteristic contour image is initialized. The residual network method is used to accurately identify the contour and texture features of dynamic gestures. Fusion processing weights are used to trace the contour features of dynamic gestures frame by frame, and the contour area of dynamic gestures is processed by gray and binarization to realize the extraction of contour features of dynamic gestures. The results show that the dynamic gesture contour feature recognition rate of the proposed method is 91%, the recognition time is 11.6 s, and the dynamic gesture type recognition accuracy rate is 92%. Therefore, this method can effectively improve the recognition rate and type recognition accuracy of dynamic gesture contour features and shorten the time for dynamic gesture contour feature recognition, and the F value is 0.92, with good comprehensive performance.

Based on cloud model and matter element theory, and combining the uncertain reasoning characteristics of the cloud model and qualitative and quantitative analysis can be carried out at the same time by matter element theory, a power transformer fault diagnosis method is proposed, which effectively solves the problem of fewer data samples, especially fewer fault data samples. Taking the actual data as an example, the improved matter-element theory model and correlation calculation data are compared, and the results show that the improved matter element theory model has higher diagnostic accuracy than traditional methods. Example analysis verifies the correctness and effectiveness of the method.

SIFT matching algorithm is used to carry out the binocular three-dimensional imaging. Active projection is introduced to solve the problem of low feature quantity and poor matching results in the matching process. By means of projection random speckle, the matching feature is increased, and the matching quality is greatly improved. According to the train running part of the three-dimensional imaging experiment, achieved a good imaging result. Compared with the Fourier profilometry in the active three-dimensional imaging technology. The experimental results show that the structured light projection binocular three-dimensional imaging has a better effect.

Scraper conveyor is one of main electrical and mechanical equipment in the mining face, and its reliability has an important significance to production safety. In scraper conveyor reliability life analysis, the linear parameter method is often used to estimate reliability life parameters in traditional Weibull distribution model. But the error of prediction results is larger due to the nonlinear characteristics of fault data. To solve this problem, a simulated annealing algorithm is proposed to optimize the model parameters for the scraper conveyor reliability life prediction. Research results show that the simulated annealing algorithm has small life prediction error, and raises the accuracy of the scraper conveyor reliability life prediction.

Support vector machine is a machine learning algorithm developed by Vapnik from the statistical learning theory for data classification via study from a small sample of fault data. For fault data it can isolate the fault categories accurately even though only has the small sample of data. In the present work, support vector machine's classification mechanism and its application in mechanical fault diagnosis are introduced. Therefore, give an instance the support vector machine makes fault classification for the coal mine scraper conveyor's faults. Last but not the least, put forward some of the shortcomings of the support vector machine and look forward to the direction of development of the support vector machine fault diagnosis in the future.

In order to avoid losses, which is caused by electromechanical failure in the coal large transport equipments, this article introduced a model that integrated by breakdown extraction, failure diagnosis and fault analysis in the large-scale scraper chain conveyor breakdown. The weak signal of mechanical vibration detection by ANFIS is adopted. And it is also used for Troubleshooting effectively and accurately. Lastly, an effective diagnosis suggestion is given through the instrumentation KS-2000. And by this way, we not only proved the feasibility and superiority of this plan, but also achieved predictive maintenance in the true sense.

This paper studies the Fractional Kalman Filter and its applications to the extraction of image texture in electronic image processing. Firstly, with the introduction of fractional calculus, Fractional recursive equation is presented. Next, a state space model of a given image and, based on this, the Fractional Kalman Filter algorithm are proposed. Finally, an example of electronic image processing is given to demonstrate the effectiveness of proposed algorithm and the simulation result shows that the details of the image are enhanced, while the background noise of the image is attenuated efficiently.

The belt conveyor is the main transport equipments in coal field, and its controllable dirve system directly impacts on the running safety reliability and cost in coal production. Starting speed is unsmoothed in the traditional electrical drive system, which causes the belt off tracking or split and even safty accident. Therefore it is theory and practical significant to introduce a novel direct torque control (DTC) system of AC machine to the belt conveyor for solving the problem in coal mine. In allusion to the optimization of PID parameters in the speed regulators of the belt conveyor, the paper presents the improved genetic algorithm based on genetic algorithms and tabu search for the design of variable parameters of PID controller, and its ability of stronger climbing and faster finding the global optimum results are verified through the De Jong function. Compared with the traditional means, the rise time of the suggested system is faster, overshoot and regulating time is shorter, anti-disturbance is stronger, robust is better. So the optimization performance of control system is improved greatly.

A novel intelligent instrument design for curing tinnitus is introduced in this paper. According to different extent tinnitus, the many different testing sounds such as square wave, sine wave and natural sounds can be produced and the signal frequency and sound intensity level can be adjusted in order to cure tinnitus disease by this new intelligent instrument. The system is constructed in the upper computer and lower microcontroller C8051F410 as the master chip, the data communication is completed with CAN. Based on the C++ Builder, the interface which can display the data and receive the order is designed so the some information of the tinnitus suffers can be achieved in the upper computer for doctor management. This system has been put into practice and has great application value. Keywordsintelligent instrument, curing tinnitus, C++ Builder, C8051F410

Based on multi-sensor information fusion theory, a Gas fire-extinguishing control panel is introduced in this paper. The intelligent algorithm of neural network and fuzzy consequence is used to get the fire probability. According this principle, we designed an information fusion module which would send the probability to the main control panel to carry out the alarm and linkage. The practical application results indicate that the proposed method can effectively decrease the mistake rate of the fire detector and fire extinguisher.

In coal mine the forecast on fire is mainly based on the smoke, gas and temperature parameters for recognizing, and sometimes it has leak check and wrong check, therefore a novel method for mine fire based on image processing is presented. First the data are obtained by infrared CCD, then the blaze characters are extracted and entered into the fuzzy neural network model after being quantization, finally the fire can be detected. The experiment results show that this method can recognize fire signals and it reduced leak forecast, and also it is more reliable and has stronger antijamming ability. It will inevitably play an important role in coal mine safety production.

According to main distribution regions of coal resource and the characteristic of gangues, a novel image process method of separating gangues from coal is proposed with wavelet analysis in this article. Under the different frequency ranges, a series of image processing approaches are exerted on coal gangue images with wavelet transform. Images of gangues and coal are first collected by means of the measurement system, and then are denoised. The image edges are detected by fast multi-scale edge detection. Images are segmented by algorithm of self-adaptive threshold. Using the multi-resolution merit of wavelet analysis, gangues images decomposition are especially stressed on, which provides the important data for selecting gangues from the coal. The coal gangues automatic separation system is realized by means of a newly ARM microprocessor, which has characteristics of high-performance, low power dissipation and low-cost exactly. The experiments result reveals that the proposed methods are efficient and practicable compared to traditional methods. And the suggested system is satisfied with accuracy requirements and real-time performance.

A novel neural network speed identification scheme for the speed sensorless direct torque control (DTC) of an induction motor drive system is presented in the paper. The system uses current and voltage sensors for rotor speed and rotor flux estimation with a digital signal processor (DSP) TMS320F240 in a closed loop control system. Rotor speed identification is based on the model reference adaptive control (MRAC) theory with a neural network using the backpropagation (BP) algorithm. The suggested speed identification method has been validated by a simulation study.