108results about How to "Realize automatic diagnosis" patented technology

The invention discloses an electrocardiogram diagnosis method and system based on a deep convolution neural network. The diagnosis method comprises the steps that a collected original electrocardiogram of the human body is preprocessed to obtain a plurality of heartbeat fragments with a preset length; the heartbeat fragments are input into a trained deep convolution neural network model, and a prediction value of each category is obtained; the category of a single heartbeat corresponding to the maximum prediction value and the time interval of the heartbeat and a previous heartbeat are recorded, and a time series is formed; on the basis of a preset mapping relation between a clinical diagnosis criterion and the time series, the time series is matched with the diagnosis criterion, and a corresponding diagnosis result is obtained. Any feature in the electrocardiogram is not required to be extracted, so that valid information loss, noise data introduction and other problems caused by manual screening and processing are avoided to the largest extent, and the influence of manual characteristic extraction on the diagnosis accuracy is reduced.

The invention relates to the field of bearing fault diagnosis, discloses a rolling bearing fault diagnosis method based on conditional empirical wavelet transformation, and aims to improve the accuracy of fault feature extraction and fault type identification of a bearing. The method is characterized by comprising the following steps of firstly, acquiring a bearing vibration signal; secondly, setting n frequency spectrum maximum values, and carrying out conditional empirical wavelet transformation on the bearing vibration signal on the basis of the n frequency spectrum maximum values; thirdly,calculating cyclic component ratios of modes after transformation, and storing the maximum values and the modes corresponding to the maximum values; fourthly, if the currently stored maximum cyclic component ratio is larger than a reference cyclic component ratio, defining that n=n+1, taking the currently stored maximum cyclic component ratio as a new reference cyclic component ratio, and repeating the operation; fifthly, selecting out the mode corresponding to the maximum cyclic component ratio stored each time again; and finally, calculating a square envelope spectrum of the selected mode.The method is suitable for the rolling bearing fault diagnosis.

The invention discloses a locomotive motor bearing automatic diagnostic method based on a vibration acceleration signal, comprising the steps of: acquiring a vibration acceleration signal and a speed key phase signal of a motor bearing; performing order tracking and constant-angle incremental sampling, and converting the vibration acceleration signal into an angular-domain vibration acceleration signal; calculating an FFT spectrum and an EEVS enhanced envelope spectrum; setting effective frequency bands in the FFT spectrum and the EEVS enhanced envelope spectrum according to a bearing fault frequency; calculating the fault probability of each component of the bearing according to the band energy in the FFT spectrum and the EEVS enhanced envelope spectrum; setting weights and calculating the weighted probability of each component of the bearing; comparing a preset fault reference probability with the weighted probability of the current bearing so as to automatically determine a fault type and representing the severity of the fault by the weighted probability.

The invention discloses a vascular stenosis detection method and device. The method comprises the steps of acquiring a computed tomography angiography (CTA) image for a blood vessel to be detected; straightening and imaging the CTA image at a plurality of set angles to obtain a plurality of straightened images at a plurality of set angles; carrying out width measurement on the straightened imagesone by one, and outputting a width curve corresponding to the straightened image with the set angle; and performing plaque positioning screening on the width curve one by one, and determining a narrowarea of the blood vessel to be detected according to a plaque positioning screening result. By implementing the method and the equipment provided by the invention, the accuracy of vascular stenosis detection can be improved.

This invention relates to an intelligent and healthy monitoring system for large complex roof web structure, which comprises sensor system, collection communication interface and data base for storing data and is characterized by the following: there are located with intelligent alarming system of the web structure working status and intelligent system to support steel racket work status and web structure pole and ball joint self diagnose system for welding crack and web structure anti-elapse safe real time valuation system between the communication interface and the data base to store data. This invention can realize the real-time automatic working status alarming , structure damage self-diagnose and structure anti-elapse safe valuation to ensure the safety in the use of the web structure.

The embodiment of the invention provides an artificial intelligence medical image automatic diagnosis system and method. The method comprises the steps: collecting medical microscope images and corresponding diagnosis data; labeling the medical microscope images to obtain labeling data corresponding to the medical microscope images; and constructing a training set and a test set based on the diagnosis data and the annotation data corresponding to the medical microscope images, and performing training based on a deep learning model to obtain an optimal AI classification model and an optimal AIsemantic segmentation model, thereby realizing automatic diagnosis of the medical microscope images of a detection sample. According to the embodiment of the invention, human resources can be effectively saved, diagnosis time is shortened, and diagnosis accuracy is improved.

The invention relates to a CAN bus fault diagnosis method and system. The method comprises the steps that A) a control command is emitted, and present CAN bus data communication is stopped; B) a pre-determined current is output to a CAN bus circuit; C) the voltage value at the two ends of a terminal resistor in the CAN bus circuit is collected; and D) when the voltage value is greater than a first or second preset threshold, a connected circuit of the terminal resistor is determined to be abnormal. The method and system can automatically diagnose faults of the terminal resistor.

The invention relates to a vehicle failure remote diagnosis system which comprises a fault on-site signal processing unit and a fault diagnosis and treatment unit. The fault on-site signal processing unit and the fault diagnosis and treatment unit are interconnected with each other through a network. The fault on-site signal processing unit comprises a first server, a camera, a first microphone and a first audio output device, wherein the first server is respectively connected with the camera, the first microphone and the first audio output device. The fault diagnosis and treatment unit comprises a second server, a display, a second microphone, a second audio output device and a memory, wherein the second server is respectively connected with the display, the second microphone, the second audio output device and the memory. According to the invention, fault vehicle video information and language information of faults from fault on-site diagnosis personnel can be acquired and rapidly transmitted through a network to experts of a diagnosis center. Omnibearing fault information description is conducive to fault diagnosis of experts, and diagnosis efficiency is raised. In addition, automatic diagnosis of faults can also be realized through fault code comparison.

The embodiment of the invention discloses a device for diagnosing faults of relays of a start stop device. The device comprises a first switch, a second switch, a collecting module and a processing module. The first switch is used for controlling the start stop chain relay to be turned on and turned off; the second switch is used for controlling the transmission chain relay to be turned on and turned off; the processing module is used for controlling the on-off states of the first switch and the second switch; the collecting module is used for collecting the voltage of the corresponding input end and/or the corresponding output end of the start stop chain relay and/or the transmission chain relay; the processing module is further used for diagnosing the faults of the start stop chain relay or the transmission chain relay according to the collected voltage of the corresponding input end and/or the corresponding output end of the start stop chain relay and/or the transmission chain relay. The embodiment of the invention further discloses a method for diagnosing the faults of the relays of the start stop device and a start stop system. The method and device can diagnose the faults of the relays of the start stop device and facilitate repair of the start stop device.

The invention relates to a cloud platform for conducting on-line monitoring on tail gas of a diesel vehicle. The diesel vehicle comprises a tail gas treatment system. The tail gas treatment system comprises a low-temperature heater, an oxidation type catalyst, a particle catcher and a tail gas pipe bypass. The low-temperature heater, the oxidation type catalyst and the particle catcher are connected to the tail end of a tail gas pipe of a diesel engine sequentially. The tail gas pipe bypass and the particle catcher are in parallel connection. The cloud platform comprises a wireless transmission module. The wireless transmission module achieves bidirectional data exchange with an electronic control unit and a local display module, is used for receiving GPS data, and achieves bidirectional data exchange with transmission link equipment of an operator. The transmission link equipment of the operator achieves bidirectional data exchange with a cloud intelligent platform server. The cloud intelligent platform server achieves bidirectional data exchange with a cloud memory, a PC client/intelligent terminal device and a command center. The electronic control unit comprises an automatic monitoring module, an automatic diagnosis module and an automatic repair module.

The invention provides an equipment fault diagnosis method and device, a storage medium and equipment. The method comprises the steps of: acquiring fault information of the equipment; performing inference based on the acquired fault information to obtain a fault hypothesis; and verifying the fault hypothesis obtained by inference to obtain a fault diagnosis result. The method and the device can realize automatic diagnosis on equipment faults and can provide a fault solution strategy.

The invention relates to a detection method of pneumoconiosis nodules. The method comprises the following steps: S1, converting a CT image of a DICOM format into a lung image of a numpy array format,and reading CT image data information; S2, carrying out morphological operations to obtain a parenchyma image retaining only lung parenchyma; S3, dividing the parenchyma image into multiple small blocks of small-block images; S4, sending the small-block images into a convolutional neural network for screening and diagnosis of the pneumoconiosis nodules, and obtaining a detection result; and S5, storing the detection result as a csv format. According to the method, the number of the pneumoconiosis nodules and coordinate areas where the same are located are detected through converting, the morphological operations and screening of the CT image, automatic diagnosis of a pneumoconiosis symptom is realized, and the problem that pneumoconiosis identification requires massive medical resources isalleviated.

The invention relates to the field of rail monitoring, in particular to an urban rail intelligent safety monitoring and early warning system, which comprises a public safety analysis system, and the public safety analysis system comprises a big database, an intelligent prediction and early warning model and a visual display module. The public safety analysis system stores fault data information or early warning data information in the passenger flow intelligent analysis system, the pantograph-catenary relationship online monitoring system, the train running gear monitoring system and the wheel-rail state monitoring system in a large database by using a wireless transmission system; the public safety analysis system establishes the intelligent prediction and early warning model by using the fault data information or early warning data information of the big database, and outputs early warning information by using the intelligent prediction and early warning model. And the visual display module is used for displaying the early warning information output by the intelligent prediction early warning model.

The invention relates to the technical field of server heat dissipation test, which provides a CPU heat dissipation performance test method and a system. In the process of diagnosis and detection of the server, a pre-generated CPU pressurization program script tool is called to exert pressure on the CPU. When the pressure of the CPU is stable, collecting the temperature of each logic core of the CPU every other fixed period of time within a preset first time threshold, wherein N temperature parameter values are collected, and the N is greater than or equal to 2; Analyze and process the collected N temperature parameter values to judge the heat dissipation performance of CPU, so as to realize the automatic diagnosis of the heat dissipation performance of CPU, reduce the human participationin the heat dissipation test process, simplify the test process and improve the test efficiency.

The invention discloses a method for guiding and segmenting teeth by utilizing morphological data. The method comprises the following steps: S1, acquiring three-dimensional volume data of a patient and three-dimensional surface data of the teeth; S2, carrying out volume rendering; S3, extracting a gingival edge line; S4, performing model registration on the data; S5, carrying out voxel segmentation of tooth attributes; S6, carrying out data verification, and deleting the part which does not belong to the tooth attribute; S7, performing three-dimensional reconstruction; and S8, segmenting the data of the teeth according to the tooth positions. According to the invention, automatic segmentation can be carried out on teeth in an image; operation is simple, and each tooth can be segmented; andautomatic recognition of the teeth, periodontal tissues and other tissues is achieved, the clinical requirements of oral medicine are better met, development of the oral medicine is promoted, automatic diagnosis of oral diseases is achieved through the digitization technology, and a technical foundation is laid for development of automatic orthodontic tooth arrangement, automatic diagnosis of periodontal recovery and the like special for orthodontics.

The invention provides a pipeline heating diagnosis method of an unmanned aerial vehicle infrared video for crude oil pipeline inspection. The pipeline heating diagnosis method comprises the followingsteps: step 1, performing shooting to obtain a video picture of a pipeline by utilizing infrared equipment carried by an unmanned aerial vehicle; step 2, splicing the images according to a matching method of a neural network; 3, performing inter-frame difference according to the spliced images; 4, extracting the main direction of the long-distance pipeline from the processed image; 5, extractinguseful long-distance pipeline information from the infrared image by taking the extracted main direction as priori knowledge; and step 6, identifying and judging faults and damages existing in the long-distance pipeline along the obtained main direction of the pipeline area according to a pipeline abnormality judgment criterion. According to the pipeline heating diagnosis method of the unmanned aerial vehicle infrared video for crude oil pipeline inspection, a high-quality image can be obtained, and automatic positioning and diagnosis of an abnormal heating crude oil pipeline based on the infrared video are realized.