156results about How to "Avoid Manual Inspection" patented technology

The invention provides an intelligent assistant analysis system for power system fault, which comprises a server and multiple data acquisition terminals in communication connection with the server through GPRS or an optical fiber, wherein the data acquisition terminal is arranged on a monitored substation or a monitored power device; the data acquisition terminal is used for acquiring data inside the monitored substation or the monitored power device and uploading the acquired data to the server; the system acquires data of the power device and the substation in real time through the data acquisition terminals and uploads the acquired data to the server; and the server processes and analyzes the acquired data information. A manual inspection mode is avoided; the working efficiency is improved; detected data can be managed in an integrated mode; and the data can be analyzed and processed afterwards.

The invention provides a monitoring device which is used for the high voltage cable connector status in a mine roadway, wherein, a temperature sensor, a humidity sensor and a current transformer are connected with a data acquisition unit through signal wires; the data acquisition unit, a data storage unit, a keyboard, a display unit, a clock unit and an acousto-optic warning unit are connected with a microcontroller unit through an I/O port; and the microcontroller unit is formed by the connection between a serial port and a communication unit. The invention is simple in structure, low in cost, safe and reliable in performance, and can monitor the temperature, current and humidity of the cable connector in real time, thus being applicable to the monitoring of high pressure cable connection device in the mine roadway and other high voltage electric power equipment.

The invention provides an intelligent and safe all-around early warning and control system for power distribution network. A server, based on the classification, statistics, calculation and analysis result of the data acquired and transmitted by an onsite data acquisition terminal in combination with the historical data information saved in a database, provides a series of functions such as information inquiry and customized report and analysis report formation so as to support its comprehensive applications in finding out the reasons for a power failure and reliability data statistics. The various data of the power distribution network contain the real time data, the non-real-time data and the quasi-real-time data. The detailed function modules comprise: power distribution network fault cause classification and analysis; scheduling and work plan search and analysis; scheduling operation ticket statistics and classification; power-off work classification and work evaluation; power supply reliability analysis and statistics; and other comprehensive applications carried out especially for the requirement of a user.

The invention provides a line-loss anomaly detection method for an electric power measurement automation system. The method comprises the steps of S1, acquiring a line loss daily fluctuation index and a line loss variation tendency index of each line through the calculation of a line loss data table; S2, respectively judging whether the line loss daily fluctuation index of each line exceeds a first threshold value or not and respectively judging whether the line loss variation tendency index of each line exceeds a second threshold value or not; S3, judging a line with the line loss daily fluctuation index thereof to exceed the first threshold value or the line loss variation tendency index thereof to exceed the second threshold value as a line loss abnormal line. According to the technical scheme of the invention, two abnormal conditions, namely the line loss mutation anomaly and the line loss variation tendency anomaly, can be found out based on the line loss daily fluctuation index and the line loss variation tendency index of each line. Meanwhile, through adjusting the above threshold values, the anomalies of different degrees can be found out. The number of daily abnormal lines can be adopted to evaluate the health degree of the entire power grid. Therefore, the finding sensitivity of the existing system for line loss anomalies is improved. The defect that the manual inspection and discovery is not timely can be overcome. The reasons for line loss anomalies can be further detected.

The invention provides a monitoring system used for a power system and provided with a video intelligent monitoring power distribution apparatus. The monitoring system comprises a server and a plurality of field data acquisition terminals are in communication connection with the server through GPRS or optical fibers; a Web server provides functions through which a camera can be accessed through a browser and can be controlled; a user accesses the browser through a PC client and enters the code of the camera to obtain video information captured by the corresponding camera; control on the action of the camera can be also realized; the camera can be adjusted and controlled in a horizontal direction and can be also adjusted and controlled in a vertical direction; zoom adjustment control instructions can be issued; and therefore, the user can adjust the capture direction of the camera in real time according to needs, and multi-angle comprehensive monitoring and management on a monitored substation or monitored power equipment can be realized.

The invention relates to a music rhythm detection method and a music rhythm detection device. The music rhythm detection method comprises the steps of acquiring an audio signal of a piece of detected music, calculating a cross-correlation function between the audio signal of the detected music and audio signals of preset music rhythm models, acquiring the number of the preset music rhythm models included in the detected music according to the type of the detected music and the number of times that each peak position of a cross-correlation function curve appears in the detected music, and comparing the number of the preset music rhythm models included in the detected music and preset rhythm information to determine the rhythm of the detected music. The speed of music rhythm detection is improved, and higher detection accuracy can be achieved.

The invention discloses a vegetation coverage detection method and device thereof in a grazing sheep feeding path of a grassland. The vegetation coverage detection method comprises the following stepsof 1 collecting and pre-processing a vegetation image; 2 establishing a vegetation characteristic database; 3 segmenting the vegetation image and calculating the coverage degree of various vegetation. The detection device comprises an image acquisition mechanism, an image preprocessing module, a feature library training module and a vegetation segmentation module. The method and the system of theinvention can correct the focal length of the camera and the coefficient when the image pixel is calculated by comparing the vegetation image with the calibration image of the artificial method, thereby improving the accuracy of the vegetation image. By adopting the principal component analysis method to reduce the dimension of the image, the redundancy of the characteristic parameters can be reduced. The method and the system of the invention conveniently divide a vegetation image into a plurality of single vegetation images by establishing a BP neural network training model, thereby calculating the coverage of each vegetation and improving the detection efficiency of the vegetation coverage in the grazing sheep feeding path.

The invention discloses an article detection method and apparatus. The invention aims to solve the problem of low accuracy of human eye-based identification which is caused by misdetection and misseddetection caused by the fatigue of human eyes. According to the embodiments of the present invention, the method includes the following steps that: a plurality of different neural networks are adoptedto extract article features in a target image, so that feature images corresponding to each neural network are obtained; the feature images corresponding to each neural network are subjected to feature fusion, so that a fused image can be obtained; and the fused image is matched with an image corresponding to a preset item, and an item included in the target image is determined according to a matching result. Since the neural networks are adopted to realize the method provided by the embodiments, manual inspection is avoided, and therefore, the phenomena of misdetection and missed detection are reduced, and accuracy is improved.

The invention provides a detection device and method for insulation resistance of a double-winding motor. The device comprises a control unit, a voltage and current detecting unit and an insulation resistance calculating unit, wherein the control unit is used for controlling a converter to apply direct-current bus voltage in the same direction and direct-current bus voltage in the reverse direction, the voltage and current detecting unit is used for detecting the voltage and the current of the output end of a first winding and the voltage and the current of the output end of a second winding relative to a grounding point under the state of applying the direct-current bus voltage in the same direction and the direct-current bus voltage in the reverse direction, and the insulation resistance calculating unit is used for calculating the insulation resistance according to the detected voltage and the detected current. The direct-current bus voltage different in direction is applied to the windings by controlling the converter of the double-winding motor, voltage values and current values of measuring circuits under the direct-current bus voltage different in direction are measured, and then the insulation resistance value is calculated. It is avoided that a maintainer manually detects the insulation resistance of the motor by carrying an insulation resistance tester, and the insulation resistance of the motor can be detected intelligently in a normalization mode.

The embodiment of the invention discloses a mobile terminal and an information processing method. The mobile terminal comprises an image acquisition unit used for acquiring a first image and sending the first image to an image processing unit; the image processing unit used for dividing the first image into N*M regions and obtaining an average grey value of each region, wherein N and M are positive integers; and a judging and determining unit used for calculating a difference value of the average grey values of a first region and a second region, judging whether the difference value of the average grey values of the first region and the second region is greater than a first threshold value, obtaining a judgment result, and determining that a first sub-region of the image acquisition unit of the mobile terminal corresponding to the first region is in an abnormal state or a second sub-region of the image acquisition unit of the mobile terminal corresponding to the second region is in the abnormal state when the judgment result shows that the difference value of the average grey values of the first region and the second region is greater than the first threshold value.

The invention relates to the field of image processing, in particular to a metal surface scratch detection method and device, and the method specifically comprises the steps: obtaining a first image of a to-be-detected surface; performing Fourier transform on the first image to obtain a frequency domain graph; processing the frequency domain graph through a filter, and removing high and low frequency parts in the frequency domain graph; performing inverse Fourier transform on the removed frequency domain image to obtain a second image of the to-be-detected surface; judging whether a standard scratch exists in the second image or not, and displaying a judgment result. The device specifically comprises an acquisition module, a filter module and a judgment module. The acquisition module is composed of a calling sub-module and an image acquisition sub-module, the filter module is composed of a filter parameter setting sub-module, a frequency domain image acquisition and conversion sub-module and a third image acquisition sub-module, and the judgment module is composed of a scratch area detection sub-module, a feature area acquisition sub-module and a standard scratch judgment sub-module.

The invention relates to a power inspection system. The system comprises an augmented reality technology AR mobile terminal and a server, the AR mobile terminal is in communication connection with theserver; the AR mobile terminal is used for acquiring an equipment identification of the target inspection equipment, and sending the equipment identification to the server; the server is used for determining the inspection guidance information corresponding to the equipment identification, and sending the inspection guidance information to the AR mobile terminal; and the AR mobile terminal is further used for performing the inspection operation on the target inspection equipment according to the inspection guidance information. Conducting the inspection through the communication between the augmented reality technology AR mobile terminal and the server by the power inspection system, so that manual inspection is avoided entirely, and the inspection work efficiency is greatly improved.

The present invention discloses a tappet automatic comprehensive detection device, which comprises a feeding mechanism, a detection mechanism, a station transfer mechanism, a marking device, a defective product classifying mechanism, a fuel injection device, a qualified product receiving and loading mechanism and a control system. The feeding mechanism is used for transferring to-be-detected tappets located at correct positions to the first detection station of the detection mechanism. The detection mechanism is used for conducting the multi-term detection for the above tappets fed by the feeding mechanism with the assistance of the station transfer mechanism. The defective product classifying mechanism is used for classifying unqualified tappets that have been detected and marked. The qualified product receiving and loading mechanism is used for loading qualified tappets that have been subjected to oil injection treatment into a packaging mold box. Due to the adoption of the above technical scheme of the invention, tappets only need to be placed upwardly on a feeding belt of the feeding mechanism, and then a plurality of quality detection items on the tappets can be automatically completed. Meanwhile, according to a detection result, qualified tappets are loaded into the packaging mold box and unqualified tappets are classified and recovered according to specific unqualified items thereof. Therefore, the complicated manual detection is avoided. The device is time-saving, labor-saving and good in reliability.

The invention discloses a device and a method for diagnosing bolt looseness of a power transmission tower pole material connection node. The device for diagnosing bolt looseness of a power transmission tower pole material connection node comprises a strain data acquisition device, a wireless sensor network system, a bolt looseness diagnosis module and a diagnosis result display terminal. At leasttwo strain data acquisition devices are installed near node bolts of a rod material connection node of a power transmission tower, and are used for acquiring real-time strain response data at the rodmaterial connection node, transmitting the real-time strain response data to the bolt looseness diagnosis module through the wireless sensor network system, judging the bolt looseness failure condition through the bolt looseness diagnosis module, and finally a node bolt looseness failure diagnosis result is displayed through the diagnosis result display terminal. According to the invention, intelligent diagnosis of bolt loosening failure is realized, manual detection consuming a lot of manpower and material resources is avoided, and the problems of node bolt detection and operation maintenanceare effectively solved.

The invention provides a document scanning image correction method and device, and relates to the technical field of archive management. The document scanning image correction method comprises the following steps: correcting a document scanning image; obtaining scanned document images and projection values of light beams of the document images in different angle directions; the deflection angle ofthe document image is determined according to the projection values of the light beams in different angle directions of the document image; judging whether the deflection angle of the document imageis greater than a preset threshold value or not, if yes, determining the document image as the deflection image, and obtaining a corrected image of the deflection image based on the picture generationnetwork model and the training weight value of the picture generation network model, so that the labor cost is reduced, and meanwhile, the document scanning efficiency is improved.

The invention discloses an aerial photography power transmission line broken strand identification method and device based on semantic segmentation. The method comprises the steps: acquiring aerial photography power transmission line sample images to form a sample library; constructing a semantic segmentation convolutional neural network model, and training the constructed semantic segmentation convolutional neural network model by using the aerial power transmission line sample image; using the trained semantic segmentation convolutional neural network model to detect an aerial power transmission line image to be detected, and outputting a segmentation mask graph of a detected normal conductor and a suspected broken strand; and judging whether a detection result is correct or not by utilizing a spatial context relationship between the normal wire and the broken strand according to the segmented mask pattern. According to the invention, the accuracy and the detection efficiency are improved, manual detection is avoided, and manpower and material resources are saved.

The invention provides a land oil and gas pipeline defect diagnosis method based on a hyperspectral remote sensing technology, and the method comprises the steps of inputting an oil and gas pipeline hyperspectral image generated by a spectral imager into a computer through the hyperspectral remote sensing technology, and marking and training oil and gas pipeline spectral data obtained through an experiment through a BP neural network and a machine learning method; extracting hyperspectral images and spectral characteristics of oil and gas pipelines with leakage, defects and the like, and determining leakage areas and defect positions of the oil and gas pipelines; grading the oil and gas pipeline surface data through an unsupervised machine learning entropy method, then performing automaticclassification according to defect levels through a BP neural network, and performing early warning display according to normality, faults and alarms. The invention solves the problem that the existing oil and gas pipeline leakage and defect area detection needs a large amount of manpower and is difficult to position, realizes artificial intelligent inspection of the land oil and gas pipeline byutilizing a hyperspectral remote sensing technology, and has the characteristics of good economy, wide application scene and wide application object.

The invention discloses a method for testing consistency of FRU information. The method comprises the steps that the FRU information is written into a text file, and an FRU refreshing script is executed to refresh the FRU information; the refreshed FRU information is compared with the FRU information in the text file, and whether the FRU information is successfully refreshed is judged. According to the method, whether the FRU information is consistent can be judged by directly checking text file content, manual checking is avoided, and working efficiency and accuracy are improved.

The invention relates to the field of image processing, and discloses a scratch detection method and device. The scratch detection method comprises the steps of acquiring a first image of the surface of an object to be detected; performing denoising processing on the first image to obtain a second image of the surface of the object to be detected after denoising processing; and judging whether there is a standard scratch in the second image or not, and displaying a judgment result. The embodiment of the invention further provides a scratch detection device. Scratches on the surface of the object to be detected can be effectively detected according to the invention. Meanwhile, a lot of manpower can be saved.

The invention relates to a semantics based oil well indicator diagram measuring method. The semantics based oil well indicator diagram measuring method comprises the steps of firstly semantically packaging data information of an oil well, and then performing indicator diagram oil gauging based on the semantically packaged data. Due to introduction of a semantic technology, an indicator diagram oil gauging system provides a standard noumenal interface to a user, so that more users with limited computer knowledge can visit the indicator diagram oil gauging system, configuration becomes simpler and more convenient and operation becomes easier when the indicator diagram oil gauging system is used; on the other hand, as the mode of analyzing the indicator diagram is adopted to measure the yield of the oil well, the original oil gauging mode of performing manual routing inspection for the oil well and measuring with a need of stopping the well is avoided. Therefore, the well does not have to be stopped while the manpower resource is saved, and the oil production efficiency of the oil well is increased indirectly.

The invention relates to the field of industrial sewage treatment, and in particular to a sewage treatment device and a tunnel wastewater treatment system and a method. The tunnel wastewater treatment system comprises an adjusting tank, a conveying device, a mixer, a sewage treatment device and a clean water tank, wherein the adjusting tank, the conveying device, the mixer, the sewage treatment device and the clean water tank are connected in sequence through pipelines; and the sewage treatment device comprises a flocculation tank, a precipitation tank and a filtering tank. The invention aims to provide the sewage treatment device and the tunnel wastewater treatment system and the method, and the problems that a conventional tunnel wastewater treatment technique is too simple, process parameters are not reasonably designed, the discharged water retention time is short, the reaction speed is slow, the quality of effluent is not stable and up-to-standard emission cannot be ensured, are solved.

The invention discloses a charging station video monitoring intelligent operation and maintenance management platform which comprises a charging station, an operator and an operation and maintenance center. The system comprises a network camera, a network video recorder, a switch, an intelligent operation and maintenance management module and a video diagnosis server. The video diagnosis server isin communication connection with an operator and is also in communication connection with the video acquisition assembly; The operation and maintenance center comprises a platform server and a receiving gateway, and the receiving gateway is in communication connection with an operator and is also in communication connection with the platform server; Wherein the network camera is connected with the network video recorder, the network video recorder is connected with the switch, the network video recorder is further connected with the intelligent operation and maintenance management module, theintelligent operation and maintenance management module is connected with the switch, the switch is connected with the video diagnosis server, and the video diagnosis server is in communication connection with an operator; According to the invention, a large number of monitoring devices can be managed conveniently, the overall operation condition can be mastered conveniently, automatic detectionis improved, and manual inspection is avoided.