105results about How to "Realize intelligent diagnosis" patented technology

The present invention discloses an integrated support vector machine mixed intelligent diagnosis method of machine failure. Said method includes the following steps: respectively adopting and lifting small wave packet, utilizing frequency band and empirical mode decomposition process to decompose vibration signal according to the eigen mode component and extract time domain statistical character of decomposed signal to form total characteristic set; providing characteristic distance evaluation technique and characteristic evaluation index; utilizing said characteristic evaluation index to select most sensitive characteristic set from the total characteristic set; using said most sensitive characteristic set as diagnosis characteristics and creating integrated support vector machine mixed intelligent diagnosis model so as to implement intelligent diagnosis of machine failure state.

The invention discloses application of deep learning based on fuzzy processing in fault diagnosis of hydraulic equipment. The application comprises the following steps of: (1) introducing a time label and fuzzy weight to pre-process operation monitoring data of the hydraulic equipment, and dividing the operation monitoring data into a training data set and a test data set; (2) taking the training data set as an input vector of a sparse self-coding network to carry out non-supervision pre-training; (3) taking label data and no-label data as an input vector training Softmax classifier of a Softmax classifier; (4) utilizing a BP algorithm to carry out fine adjustment on deep learning network parameters; and (5) carrying out intelligent diagnosis on a fault condition. According to the application disclosed by the invention, firstly, a method of introducing the time label and fuzzy weight is adopted to carry out pre-processing on data; then, sparse self-coding is used to complete high-level feature extraction of sample data, and the Softmax classifier is used to carry out classifying diagnosis on an equipment fault state to construct an ICM model; and finally, the BP algorithm is utilized to carry out fine adjustment on global optimal parameters of the whole network, so that intelligent diagnosis on the fault state is realized.

The invention relates to a design method of an establishing method of a rolling bearing intelligent diagnosis model based on a convolutional neural network. Firstly a one-dimensional vibration signalis mapped into two-dimensional image information, and the two-dimensional image data are used for training a network model; and then the structural parameters of the convolutional neural network in the application process are analyzed and the better network parameters are selected so that the convolutional neural network structure having high mechanical fault classification capacity is obtained. Accurate identification and classification of the mechanical fault under the complex condition of different loads and different rotating speed can be realized; and the convolutional neural network model can greatly enhance the feature extraction capacity of the neural network by establishing the multilayer network, mastering of manual technology for mass signal processing and dependence on the diagnosis experience can be overcome, the fault features can be directly acquired from the original time domain signal through the learning mode to perform diagnosis, and adaptive extraction of the faultfeatures and intelligent diagnosis of the state of health under the condition of TB level data volume per hour can be realized.

The invention provides a software remote fault diagnosis and repair method based on a knowledge base, which comprises the steps of modeling and storing the operation conditions, dependence relationship, fault performance characteristics and repair strategy of each software component in a diagnosed software system to form a fault diagnosis and repair knowledge base; storing the knowledge base on a service terminal of the diagnosed software system; installing a client-side agent in the diagnosed software system, installing a server-side program on the service terminal, acquiring the diagnosis information of the diagnosed software system in real time by use of the client-side agent, and transferring the diagnosis information to the server-side program through the network; generating a decision command by the server-side program according to the acquired diagnosis information and the knowledge base, and transferring the decision command to the client-side agent through the network; executing the decision command by the client-side agent to realize the diagnosis and repair of the software fault. By adopting the method provided by the invention, intelligent diagnosis and repair of software faults are realized, and the efficiency and automation degree of software fault diagnosis and repair are improved.

The invention relates to a stacked SAE (Sparse Autoencoder) deep neural network-based bearing fault diagnosis method. The first layer of a network is applied to the qualitative judgment of a bearing fault, that is, the first layer of the network is applied to the fault type judgment of the bearing fault; and the second layer of the network is applied to the quantitative judgment of the bearing fault, that is, the second layer of the network is applied to the severity judgment of the bearing fault. According to the method of the invention, empirical mode decomposition (EMD) and an autoregressive (AR) model are combined together to perform pre-processing on original bearing signals, the parameters of the AR model are extracted and are adopted as the input of the network, and therefore, the input dimensions of the network can be greatly reduced, the simplification of calculation can be facilitated, and the training and testing of the network can be accelerated; a deep neural network on which the method of the invention is based can further automatically extract features of the input and qualitatively and quantitatively determine the bearing fault automatically, and therefore, the diagnostic accuracy of the method of the present invention can be ensured, and at the same time, dependence on signal processing expertise can be decreased, manual judgment is not required, the consumption of manpower can be decreased; and thus, the method has a higher practical value in the era of big data.

The invention discloses an intelligent heart sound diagnostic system and method based on in-depth learning and relates to the fields of bio-signal processing, pattern recognition, big data and in-depth learning. The method comprises the following steps: 1) acquiring heart sound audio data by a user through heart sound acquisition equipment or intelligent wearable equipment; 2) transmitting the data to a cloud server through a network, and storing and archiving the heart sound audio data; 3) segmenting the heart sound data on the cloud server by adopting a heart sound segmentation algorithm based on a logistic regression-hidden semi-Markov model, and performing automatic characteristic extraction and classification on the segmented heart sound data by using a one-dimensional convolutional neural network; 4) feeding diagnostic results to the user through a network and storing the results on a cloud so as to be provided for related institutions and designated hospitals as clinical historyreference of the user; and 5) expanding the heart sound data of the user confirmed by a professional doctor serving as training data into a heart sound database of a cloud server, so that the diagnostic capability of the heart sound diagnostic system is continuously improved.

This invention relates to online quality test control method and to mechanic process and computer software field and comprises the following steps: a, establishing case base and rules and recording each quality abnormal case, reasons and resolutions and analyzing each case property; in rules data, the specialist knowledge and related rules digging to establish each case rules; in the test process, finding out abnormal case; processing abnormal case diagnose to get resolution.

The invention provides an ABS brake anti-lock device based on DSP 56F8346. The device comprises an electric control device which takes the high-performance digital signal processor 56F8346 as a CPU, a vehicle wheel rotation speed sensor and a hydraulic system. The electric control device outputs sine wave electric signals according to the four vehicle wheel rotation speed sensors; the signals are then converted to the counting pulses in direct proportion with the wheel speed through a hardware circuit; the CPU collects the counting values and calculates the rotation speed of the four vehicle wheels; the electric control device controls the work of the hydraulic system according to a certain control principle, thus respectively implementing the anti-lock brake and control to the two front wheels respectively and the two rear wheels synchronously and implementing the safe deceleration and the stable driving of the vehicle. The ABS brake anti-lock device of the invention implements the intelligentization and the integration and has wide market application prospect.

The invention discloses an intelligent disease diagnosis and treatment device which comprises a main symptom diagnosis unit, a main symptom selection unit, an accompanying symptom selection unit and a diagnosis result output unit. The main symptom diagnosis unit is used for inputting the information a plurality of main symptoms of a disease. The main symptom selection unit is used for selecting the information of one main symptom from the information of the main symptoms and inputting the information of a plurality of accompanying symptoms. The accompanying symptom selection unit is used for selecting the information of one accompanying symptom and inputting the subunit information, and the subunit information comprises a symptom subunit, a physical sign subunit and an auxiliary detection subunit. The diagnosis result output unit is used for outputting diagnosis results of the subunit information. The invention further discloses an intelligent disease diagnosis and treatment system. The intelligent disease diagnosis and treatment device and system can solve the problem that in the prior art, intelligent disease diagnosis can not be achieved, the accuracy of diagnosis and treatment can not be guaranteed, diagnosis results can not be unified, and medical knowledge can not be intelligently inquired.

The present invention discloses a software system failure diagnosis method. The method comprises: acquiring a failure attribute of a to-be-diagnosed software system by means of a network management system; and performing a match in a preset rule database according to the failure attribute, and generating a failure diagnosis decision list according to a matching degree of the failure attribute and the preset rule database. The present invention further discloses a software system failure diagnosis server and system. According to the software system failure diagnosis method, server and system disclosed by the present invention, intelligent diagnosis and repairing of software system failures, real-time software system failure monitoring and online update of diagnosis rules are achieved, the efficiency and automation degree of software failure diagnosis and repairing are greatly improved, and maintenance and improvement efficiency of the diagnosis system are improved, and thus the technical problems of high learning costs and inconvenience of the existing software system maintenance are solved.

The invention belongs to the field of power primary equipment state evaluation and relates to an intelligent operation and maintenance and full-life-cycle management method for a transformer substation. According to the method, service life evaluation on an oil-immersed power transformer in the transformer substation and quantitative evaluation on the overload capacity of the oil-immersed power transformer in the transformer substation through a preset intelligent algorithm on the basis of data obtained from the comprehensive protection measurement and control background and environment temperature control instrument of the transformer substation, and therefore, the availability and reliability of electric energy are improved. With the intelligent operation and maintenance and full-life-cycle management method for the transformer substation and the cloud management platform for transformer substation of the invention, service life evaluation on the oil-immersed power transformer in thetransformer substation and quantitative evaluation on the overload capacity of the oil-immersed power transformer in the transformer substation are realized.

The invention discloses a regularization sparse filtering method suitable for gear fault diagnosis under variable rotating speed, and relates to the field of fault diagnosis of rotating machinery vibration signals. The method comprises the following steps of firstly, obtaining time-varying rotating speed vibration signals of a gear box under different fault types; secondly, establishing a sparse filtering model (L1/2-sparse filtering) based on L1/2 norm regularization, directly inputting a vibration signal into the model for training, and extracting features; and finally, inputting the extracted features into a Softmax classifier for intelligent diagnosis. According to the regularization method disclosed by the invention, the feature extraction capability of sparse filtering is improved, and the intelligent fault diagnosis of the gear box under the time-varying rotating speed is accurately and reliably realized.

The invention provides a field fault handling system for an electric energy meter. The field fault handling system comprises a field application management platform and metering field handheld equipment. The field fault handling system is suitable for all types of smart electric energy meters and can download corresponding self diagnosis templates for different types of electric energy meter. The field fault handling system is advantageous in that accurate and reliable diagnosis result is realized; special equipment is equipped for emergency-repairing personnel; and experience and working capability of the emergency-repairing personnel are not required in fault checking and fault positioning.

The invention provides a method for identifying a dicrotic notch point in an arterial tension signal, which is used for carrying out comprehensive analysis by combining with a waveform outline of the arterial tension signal, can overcome the influence of baseline drift of the arterial tension signal by using a differential vector between points as basic characteristics with translation and rotational invariance and adopting a log polar transformation distribution model, and is sensitive to adjacent waveform morphological characteristics, and can be used for capturing overall outline information of waveform, thus the antijamming capability of the identification of the dicrotic notch point is integrally improved; meanwhile, in an identifying process, the data calculated amount in the identifying process is greatly simplified through curvature differential identification, the integral robustness and the identification accuracy of the method provided by the invnetion are improved by adopting a chisquare statistic check as a matching means and the advantages of strong robustness and high accuracy of the chisquare statistic check. The method provided by the invention realizes that the dicrotic notch point in the arterial tension signal is identified by a computer, and has a wide application prospect.

An intercity or urban rapid air rail transport system comprises stations, supporting columns, rails, turnouts, rail cars, a power supply system and a control system. The rails are erected in the air by means of the supporting columns. The stations are arranged at endpoints or client sides of the rails. The stations, the rails and the turnouts form a rail transport network system like the Internet. The rail cars move along the rails by means of the power supply system and the control system. The intercity or urban rapid air rail transport system can be manufactured at low cost within a short period of time in batches, transport efficiency can be greatly improved, transport cost can be reduced, traffic accidents can be eradicated, and the intercity or urban problems of traffic jam and environment pollution are effectively solved.

The invention discloses an intelligent citrus disease and pest diagnosis method and system based on deep learning. The intelligent citrus disease and pest diagnosis method comprises the steps: 1, establishing an image data set of six citrus diseases including Huanglongbing, anthracnose, canker, black spot, sand paper rust and scabis based on expert experience; 2, expanding the training set and the test set by using five data enhancement methods; using the enhanced training set and verification set to train the simplified DenseNet network, and storing the model in the system; evaluating the performance of the model by using the test set; and 3, establishing a citrus disease diagnosis system on the basis of the WeChat applet, photographing/uploading images by a user through a mobile phone by using the applet, performing diagnosis through the uploaded trained convolutional network model, and returning an intelligent diagnosis result and pest control suggestions to the user to realize intelligent diagnosis of citrus diseases and pests.

The invention discloses a medicine matching system based on big data analysis. The medicine matching system comprises the components of a memory which comprises a first storage module for storing patient information and a second storage module for storing medicine information; a big data analysis module which can call the patient information and the medicine information in the memories and performs analysis according to the symptom main description of the patient for analyzing the affected disease and matches the suitable medicine in the medicine information according to the patient information; an information exchange module which is used for information exchange. The invention further provides a coupling method of the medicine matching system based on big data analysis. The medical records, the medicines and the diagnosis of million patients are stored as samples. Modeling is performed through big data analysis. Then the disease is diagnosed according to the information such as symptom main description of the patient. Furthermore all in-selling medicine information of a pharmacy is recorded in the system. When the information such as patient symptom and allergy is input, the suitable medicine can be accurately matched, thereby realizing high effect for new medicine popularization.

The present invention provides an automatic heart disease detection system based on a convolutional neural network. The automatic heart disease detection system comprises a database, a lesion information processing module, a key frame extraction module, a data cleaning module, an information fusion and storage module, a convolutional neural network learning module, a model storage and screening module and a lesion detection module. The invention relates to the fields of deep learning, medical treatment and computer vision. By design of scientific optimization, a set of automatic intelligent detection system for coronary artery calcification, complete occlusion and thrombosis based on the convolutional neural network is created and achieved, aiming at the requirements of diagnosis on resultaccuracy and timeliness, the design structure is ingenious, a high-quality auxiliary diagnosis detection result can be output without any manual assistance, and convenience is brought to coronary artery patients and doctors.

The invention provides a predictive maintenance closed-loop method based on a fault mode, fault information and state monitoring information are precise to a fault mode level which serves as a node connecting predictive maintenance technology and reliability technology, and the predictive maintenance technology and the reliability technology are effectively combined to form a predictive maintenance closed-loop system. The formed predictive maintenance closed-loop system includes future event prediction through reliability retrospect, determining of the current state of equipment through state monitoring and a reliability and predictive maintenance closed loop. The steps of the future event prediction through reliability retrospect include collecting data; obtaining a fault mode of the equipment and parts thereof through data obtained in Step a; establishing a reliability model; utilizing the model in Step c to perform analog simulation; analyzing a result in Step d, and obtaining a shape function and expected life of each failure mode; using a result of Step e to guide implementation of predictive maintenance; and for different shape functions, driving different maintenance policies.

The invention discloses a fault intelligent identification method for a transformer winding. The method comprises the following steps: actively injecting the pulse signal into a transformer device to obtain a network curve of a transformer winding; obtaining a transformer vibration frequency response curve based on a vibration frequency response method; extracting the characteristics of the obtained network curve of the transformer winding; extracting the characteristics of the obtained vibration frequency response curve; extracting the winding network curve characteristics of the transformer winding fault database and the vibration frequency response curve characteristics for training a support vector machine SVM; inputting the winding network curve characteristics and the vibration frequency response curve characteristics newly detected into the SVM for identifying the winding fault, and confirming whether the interior of the transformer device has the winding fault. The scientificity, high efficiency and accuracy of the fault detection and diagnosis of the transformer winding are improved.

The invention disclose a quick intelligent diagnosis method for the infant pneumonia on the basis of a hybrid deep learning model, and solves the problem that the body of an infant is injured since existing infant pneumonia diagnosis time is overlong or a misdiagnosis happens. The quick intelligent diagnosis method comprises the following steps of: S1: measuring and collecting each piece of physiological index data of the infant, and according to whether the infant suffers from the pneumonia or not, marking the data; S2: carrying out data cleaning and abnormal data rejection on non-breathing audio data, and constructing a dataset used for training a pneumonia diagnosis model; S3: constructing a dataset used for training a rale identification model; S4: carrying out long short-term memory (LSTM) training; and S5: carrying out deep neural network (DNN) training for interpreting each piece of physiological index data of a patient so as to judge whether the patient suffers from the pneumonia or not. According to the quick intelligent diagnosis method disclosed by the invention, the diagnosis rate and the accuracy of the infant pneumonia can be effectively improved, and serious injuriescaused for the body of the infant due to overlong diagnosis waiting time or the misdiagnosis can be avoided.