53results about How to "Achieving Accurate Diagnosis" patented technology

The invention discloses a vibration fault diagnosis method of a wind turbine generator rolling bearing. The method comprises the following steps of step1, using a vibration sensor to collect wind turbine generator rolling bearing inner ring fault vibration signals; step2, using a model of a bistable system to carry out noise reduction processing on the wind turbine generator rolling bearing inner ring fault vibration signals and outputting a noise reduction signal; step3, carrying out variation modal decomposition on the noise reduction signal output by the step2 so as to acquire IMF components of different frequency ranges; and step4, after the step3, carrying out spectral analysis on each IMF component acquired through VMD decomposition, finding a fault characteristic frequency of a rolling bearing and completing vibration fault diagnosis of the wind turbine generator rolling bearing. By using the vibration fault diagnosis method, accurate diagnosis to a vibration fault of the wind turbine generator rolling bearing can be realized.

The invention discloses an aero-engine intershaft bearing early weak fault diagnosis method, which belongs to the technical field of aero-engine fault detection. The method includes the following steps: the fault signal of the intershaft bearing is collected; an AR model is used to remove a deterministic signal generated by periodic rotation of the engine rotor; the processed fault signal is subjected to inverse MED filtering to enhance the shock component of the fault signal; a CEEMD method is used to decompose the processed fault signal, an effective modal component is screened according toa kurtosis value index and an autocorrelation function, and the intershaft bearing fault signal is subjected to noise reduction and reconstruction; and through a Teager energy operator, the output energy of the noise reduction signal is obtained, the envelope spectrum is calculated, and through analyzing the frequency component with a frequency component in the envelope spectrum, engine intershaftbearing early weak fault diagnosis is realized. The fault signal can be subjected to preprocessing, screening, reconstruction and demodulation, a fault characteristic signal reflecting the bearing fault is acquired, and the early weak fault of the intershaft bearing can be accurately diagnosed.

The invention discloses a robot-based intelligent road detection method, which comprises the steps of: S1, determining a road detection region; S2, and automatically planning a path according to the road detection region and executing a road detection task by means of an autonomous detection robot, acquiring real-time positioning information of the robot in the process of executing the road detection task, acquiring road surface data by means of a high-precision camera and a round penetrating radar, correlating the acquired road surface data with the positioning information corresponding to the time when the data is acquired, and storing the data and the information. The robot-based intelligent road detection method utilizes the autonomous detection robot to perform path automatic planningand execute the road detection task, utilizes the positioning equipment to acquire the positioning information of the robot in real time and utilize the data acquisition sensor to acquire the road surface data, and associates the acquired road surface data with the corresponding positioning information, thus the effect of completing the road detection task autonomously by means of the robot is realized, the operating efficiency is high, the detection data is complete, the detection data and the position information are precise, and the diseases can be precisely positioned.

The invention discloses a composite fault diagnosis method for a rotary machine based on an improved deep sparse auto-encoder network. The method comprises the following steps: 1) acquiring vibrationsignals of the rotary machine under c conditions in a normal state and different fault states respectively to obtain d groups of time domain vibration signal samples respectively; 2) carrying out Fourier transform on each sample to obtain preprocessed signal samples; 3) constructing a diagnosis sample set to serve as a training sample set; 4) building a rotary machine composite fault diagnosis model to obtain the connection weight and bias parameter of the deep sparse auto-encoder network; 5) acquiring a softmax classifier model; 6) carrying out fast Fourier transform, and selecting a test sample; 7) carrying out deep learning on the test sample by using the test sample as the input of a trained improved deep sparse auto-encoder network, and carrying out feature extraction to obtain a testsample feature signal; and 8) using test feature information as the matching feature of the test sample to obtain the composite fault diagnosis result of the rotary machine to be tested. Through theadoption of the method, the diagnosis accuracy and efficiency are improved.

The invention provides a fault diagnosis device for an electrical control circuit. The device comprises a sensor, a central processing unit and a display, wherein the sensor is connected between a power supply of the control circuit and the electrical control circuit to detect and acquire signals of actual current in electromagnetic valves or relays of the electrical control circuit and send the signals to the central processing unit, and the central processing unit outputs trigger pulses according to a preset sequence to trigger electromagnetic valves or relays of the electrical control circuit sequentially, receives the signals of the actual current in the electromagnetic valves or the relays sent by the sensor, judges whether or not faults occur in the electromagnetic valves or the relays and outputs information on failed electromagnetic valves or relays. The invention also provides a fault diagnosis method for the electrical control circuit. With the method and the device, faults of the electrical control circuit can be diagnosed quickly, simply and precisely.

The invention provides a multi-fault diagnosis method of a spacecraft attitude control system. The multi-fault diagnosis method comprises the steps: establishing a spacecraft attitude dynamic model and an attitude kinematics model; establishing a spacecraft augmented attitude dynamics model and an augmented attitude kinematics model based on the above models; designing an RBF neural network interference observer based on the augmented attitude dynamics model and the augmented attitude kinematics model, and estimating an interference value in the system; designing a robust fault detection observer, calculating a residual evaluation value, and selecting a fault detection threshold; according to the residual evaluation value and a fault detection threshold value, determining fault occurrenceparts comprising an actuator, a gyroscope, an attitude sensor or a plurality of parts; designing an RBF neural network fault isolation observer, reconstructing actuator faults, gyroscope faults and attitude sensor faults on the three axes, and selecting a fault isolation threshold; and finally determining a specific part with a fault according to the reconstructed fault value and the fault isolation threshold, thereby finishing multi-fault diagnosis.

The invention provides a leakage diagnosis method and device for a fuel evaporative emission system. The leakage diagnosis method includes the steps that when an acquired internal combustion engine state of a vehicle is a non-driving state, a fuel tank pressure value is acquired, and the leakage condition of the fuel evaporative emission system is diagnosed with a first control strategy or a second control strategy according to the fuel tank pressure value, wherein the first control strategy is to diagnose the leakage condition of the fuel evaporative emission system, and the second control strategy is to diagnose the leakage conditions of two sides of a fuel tank isolation valve respectively. According to the technical scheme, by acquiring the fuel tank pressure value and diagnosing the leakage condition of the fuel evaporative emission system with the different strategies according to the fuel tank pressure value, accurate diagnosis of the leakage condition of the fuel evaporative emission system is realized.

The invention relates to the field of mechanical vibration signal processing and fault diagnosis, and discloses a mechanical fault diagnosis method based on a parameter adaptive VMD. The signal detection capability of the VMD method in fault diagnosis is improved, and accurate mechanical fault diagnosis is realized. According to the invention, a weighted kurtosis index is used as a fitness function; a VMD decomposition parameter which best matches a signal to be analyzed is acquired through the self-adaption of an optimization algorithm; the optimal VMD decomposition parameter is used to carryout VMD decomposition on an original vibration signal; and mechanical fault feature extraction and fault diagnosis are realized. The method provided by the invention is suitable for mechanical faultdiagnosis.

The invention relates to a system for diagnosing the osteoarthritis subtype through a blood sample based on machine learning. The system comprises 1) a collection module, 2) an osteoarthritis and normal people recognition and identification module which is used for recognizing and identifying the osteoarthritis and normal people and 3) an osteoarthritis subtype recognition and identification module which is used for recognizing and identifying the osteoarthritis subtype. The invention establishes a prediction method and system tool for accurately diagnosing the osteoarthritis subtype through ablood sample based on a machine learning support vector machine, the gene expression difference between the osteoarthritis and the normal people is analyzed by the means of bioinformatics, patients of the osteoarthritis are grouped, and a diagnosis model for osteoarthritis patient and osteoarthritis subtype recognition is established by using a method of machine learning. The method can realize accurate diagnosis for the osteoarthritis patients and provide a reference for a subsequent treatment scheme.

A method for early fault diagnosis of roll bearing base on adaptive MED is disclosed, which is a method for early fault diagnosis of a bearing outer ring. Aiming at the problem that the MED noise reduction effect is affected by the filter order L, the invention studies the fault mechanism of the bearing, and proposes an adaptive MED noise reduction method using the genetic algorithm and the Teagerenergy operator envelope spectrum entropy (TESE) as an objective function. Firstly, TESE index is proposed to measure the effect of noise reduction. Then the optimal parameters of MED algorithm are optimized by using TESE as the objective function, and the weak fault features are extracted by demodulation spectrum. The method can enhance the shock component of early weak fault adaptively and extract the characteristic frequency information of early fault effectively.

The invention provides an on-site sensor fault detection method based on oil-extraction production data. The invention proposes an iteration PCA (Principal Component Analysis) method based on an SWE (Weighted Squared Prediction Error) through targeting at effects of specific characteristics, in an oil-field production process, such as sensor signal shift and electromagnetic interferences and temperature change in the oil-field production process, on a plurality of sensor devices and the like; and the iteration method is used to update a model and researches are carried out on faults in different residual-error spaces so that the accuracy of sensor fault detection is improved and thus a plurality of problems of traditional PCA methods are solved.

The invention discloses an early fault diagnosis method of a bearing outer ring based on an adaptive MCKD, which is a diagnosis method aiming at the early fault of the bearing outer ring. Aiming at the problem that the noise reduction effect of the MCKD is affected by the filter order L and the displacement order M, the invention studies the fault mechanism of the bearing, and puts forward an early fault diagnosis method of the bearing outer ring based on the adaptive MCKD. Under different M values, the average value of Teager spectrum kurtosis is calculated respectively, and the optimal displacement order M is selected. Then, taking Teager spectrum kurtosis as objective function, the optimal filter order L is searched by iterative algorithm, and the weak fault feature is extracted by envelope spectrum. Compared with the minimum entropy deconvolution (MED) algorithm, this method shows higher accuracy, which proves the accuracy of this method in early fault diagnosis of bearing outer ring.

The invention discloses a method for train bearing track-side acoustic diagnosis under a variable speed condition. The method includes the following steps that: acoustics signals emitted by a train bearing when a train passes at different speeds are acquired through microphones mounted on two sides of a track, and the acoustics signals are pre-processed; 2) 7 features such as a peak factor and variance are extracted, and the extracted 7 features, together with a vehicle speed Vs, are adopted to constitute a historical sample set with 8 feature quantities; 3) the historical sample set is adopted to train a 4-layer BP neural network; and 4) track-side acoustic signals emitted by the train bearing and a train speed at present are acquired, and the BP neural network obtained in the step 3) isadopted to perform fault diagnosis. With the method of the invention adopted, the influence of Doppler acoustic signal distortion on fault features under a variable speed condition of the train can beeliminated, and the accurate identification of the faults of the train bearing can be accurately identified under the variable speed condition; only the train speed value is required to be measured,and the required number of sensors is smaller; accurate correction can be realized without correction required, so that the amount of calculation is less; and historical data information is fully utilized, so that the reliability of diagnosis results is effectively improved.

The invention discloses a digital twin-driven intelligent drive-by-wire chassis system and a fault diagnosis method thereof. The digital twin-driven intelligent drive-by-wire chassis system comprises a drive-by-wire chassis device, a drive-by-wire chassis digital twin system and a cloud platform, the cloud platform is in data connection with the drive-by-wire chassis device and the drive-by-wire chassis digital twin system in a communication network mode. The drive-by-wire chassis device comprises a drive-by-wire steering system, a drive-by-wire braking system and a drive-by-wire driving system. The three complete corresponding steering, braking and driving actions according to a control instruction; the digital twinning system of the drive-by-wire chassis device is generated through the digital twinning technology, the digital twinning system and the drive-by-wire chassis physical entity run consistently through the data driving method, and the real-time interaction of data of the drive-by-wire chassis device and the digital twinning system is achieved.

The invention provides a battery fault diagnosis method based on a crisscrossing optimizing fuzzy BP neural network. The battery fault diagnosis method includes the steps that firstly, fuzzification is conducted on a sample, information of inaccuracy or indeterminacy and the like in fault diagnosis are processed, and thus atraining sample of the neural network is more accurate; and next, various weights and threshold valves of the neural network are optimized by using a crisscrossing algorithm, thus a convergence speed of the neural network is accelerated, local optimum cannot be trapped, a fuzzy theory is combined with optimizing of crisscrossing to the neural network, and thus diagnosis to a battery fault is more accurate. The battery fault diagnosis method based on the crisscrossing optimizing fuzzy BP neural network is applied to a series of common batteries of lithium batteries, lead batteries, other fuel batteries and the like, the battery fault can be diagnosed in real time either a standing state or a using state, and compared with other existing battery fault diagnosing methods, the method is higher in accuracy and smaller in error.

The invention discloses a gene mutation for diagnosing Marfan syndrome. The mutation is c.5651_5664del:p.D1884fs. Through second-generation sequencing, it is founded that c.5651_5664del on a FBN1 geneexists in a genome of a patient who is diagnosed with Marfan syndrome, but the mutation is not found in control population, so the gene mutation can be used as biomarkers for the diagnosis of Marfansyndrome.

The invention discloses an electric pile water management regulation and control method and device based on fixed-frequency impedance and gas pressure drop. The method comprises the following steps: periodically applying a fixed high-frequency AC voltage through DCDC to excite an electric pile of a fuel cell, so as to measure the high-frequency impedance of the electric pile; judging whether the high-frequency impedance is greater than a film dry threshold; and if the pressure value is greater than the membrane dry threshold value, judging that the fuel cell is in a membrane dry state, otherwise, collecting the pressure value of the reaction gas of the fuel cell, and judging that the fuel cell is in a flooding state when the pressure value is greater than the flooding threshold value so as to monitor the current state of the fuel cell on line. The method can realize accurate diagnosis of membrane dryness and water logging, can be applied online in real time, and is simple and easy to realize.

The invention provides a method for labeling human body model atlases for diagnosis. The method includes (1) dividing and labeling sub-regions, and dividing the central nervous system into the main sub-region of the telencephalon, the main sub-region of the hippocampus, the main sub-region of the basal nucleus, and the thalamus according to functional units. Main divisions, cerebellum main divisions, brainstem main divisions, spinal cord main divisions, further divide the nervous tissue into divisions or parts in the telencephalon main division, hippocampus main division, basal nucleus main division, thalamus main division and cerebellum main division, and then Partitions or parts are divided into several layers or blocks, and sub-regions are marked by layers and blocks. In the main spinal cord partition, the gray matter is first divided into 32 gray matter columns, and then each gray matter column is divided into upper and lower sections from different positions. (2) draw the atlas, divide the human body into 131 parts, and draw the corresponding position relationship diagram of the human body parts in each sub-division; (3) draw the atlas on each marked sub-division of the model above and marked.

The invention is suitable for the technical field of image processing, and provides a method and system for identifying fruit tree pest and disease damage types, and the method comprises the steps: obtaining a to-be-identified image, inputting the to-be-identified image into a preset classification model, and extracting sub-images of a plurality of sizes of a key position of the to-be-identified image; and determining a pre-classification result corresponding to the sub-image of each size, and determining a fruit tree pest and disease damage type corresponding to the to-be-identified image according to the pre-classification result of the sub-image of each size. By extracting the sub-images of multiple sizes at the key positions and then fusing the pre-classification results correspondingto the sub-images, image noise interference is eliminated to the maximum extent, main recognition parts (namely the key positions) are focused, accurate diagnosis of similar plant diseases and insectpests is achieved, and the accuracy of the classification results is improved.

The invention relates to a method for multi-dimensional storage of engine fault information. By the adoption of the multi-dimensional storage of the engine fault information, detection and display can be conducted in time, maintenance detection and calling are convenient, and the problems of insufficient storage space and waste caused by an oversized space during storage of data of an electronic control unit of an engine can be avoided. According to the technical scheme, the method comprises the steps that a data storage space is set in a multi-dimensional table mode in a storage chip EEPROM of the electronic control unit ECU of the engine, storage parameters in a fault information data storage table are set, and one fault information data storage table is established firstly, wherein the table contains the number of the table and feature data; an overflowing limiting quantity of the fault information is preset in the fault information data storage table, and when the amount of the fault information exceeds the overflowing limiting quantity and fault overflowing identification becomes 1, another fault information data storage table with the same content and the same storage method is established in an automatic circulation mode.

The invention discloses an underground cable early fault detection and identification method based on a DAE-CNN. The method comprises the steps of carrying out the analog simulation of the early fault of an underground cable, so as to obtain the simulation data of a current, performing feature extraction on the simulation data by adopting a noise reduction automatic encoder to obtain dimension-reduced current data, training a convolutional neural network by using the current data after dimension reduction, and generating a discriminator which can be used for detecting and identifying an early fault of the underground cable, and performing feature extraction on the current data of the underground cable to be detected by adopting a noise reduction automatic encoder to obtain dimension-reduced current data, taking the dimension-reduced current data as the input of a discriminator, and outputting an early fault identification result of the underground cable by utilizing the discriminator. Accurate diagnosis of early faults of the power distribution network can be realized.

An embodiment of the invention provides injection valve fault diagnosis method, system and equipment and a storage medium. The method comprises the steps that when a vehicle is in a first state, an actual value of an excess air coefficient of the vehicle and a first closed-loop correction factor are obtained, whether the actual value is within a first preset interval and whether the first closed-loop correction factor is within a preset factor normal interval are judged, and if the actual value is within the first preset interval and the first closed-loop correction factor is within the preset factor normal interval, after the amplified factor normal interval is obtained, a first target injection valve is closed, a second closed-loop correction factor of the excess air coefficient after the actual value is recovered to the first preset interval after the first target injection valve is closed is obtained, a first difference value between the second closed-loop correction factor corresponding to the first target injection valve and the first closed-loop correction factor is obtained, and the fault of the first target injection valve is determined through the first closed-loop correction factor and the first difference value. Accurate diagnosis of the fault of the injection valve of an engine can be achieved under the condition that the engine is not disassembled, and the general applicability is high.

The invention discloses a bearing fault diagnosis method based on parameter adaptive VMD and an optimized SVM. The method comprises the following steps: S1, collecting original vibration signals of a bearing; S2, performing the adaptive VMD on the original vibration signals to obtain K component signals; S3, screening an optimal component signal IMF from the K component signals by using a time-frequency weighted kurtosis index, and dividing the screened IMF into a training set and a test set; S4, inputting the training set into the optimized SVM for model training, and obtaining a machine learning model capable of judging bearing faults after the training is completed; and S5, inputting the test set into the machine learning model so as to output a bearing fault diagnosis result. According to the method, the problem that it is difficult for VMD parameters to be self-adaptive is solved, so that accurate diagnosis of the bearing faults is realized, the diagnosis precision is high, and a reliable basis is provided for safe and stable operation of equipment.

The invention discloses an animal epidemic situation diagnosis method based on a Bayes network and a system, wherein the method comprises the following steps of S1, constructing an animal epidemic situation diagnosis Bayes network; S2, acquiring animal signs and environment data which comprises animal gender, age, body temperature and one-day motion number-of-steps, environment temperature and humidity of the animal, and animal epidemic situation artificial diagnosis historical record; S3, discretizing the acquired animal sign and environment data; S4, training the animal epidemic situation diagnosis Bayes network by means of discretized data; S5, calculating an animal epidemic situation occurring probability according to the trained animal epidemic situation diagnosis Bayes network; and S6, performing early-warning when the animal epidemic situation occurring probability exceeds a preset threshold. According to the method and the system, remote, automatic and accurate diagnosis and early-warning can be performed on the epidemic situation according to the sign data and the environment data of the animal, thereby effectively preventing occurrence of large-scale animal epidemic diseases, and maximally ensuring high safety of meat food.

The embodiments of the invention provide an injection valve fault diagnosis method, system and equipment and a storage medium. The injection valve fault diagnosis method comprises the steps that when a vehicle is in a first state, the actual value of the excess air coefficient of the vehicle is obtained, whether the actual value of the excess air coefficient is within a first preset interval or not is judged, if yes, all injection valves are sequentially closed so that the actual value of the excess air coefficient can be located outside the first preset interval, after the condition that all the injection valves are closed is obtained, in the process that the actual value of the excess air coefficient is recovered to the first preset interval again, the corresponding relation between the maximum value and the injection valves is established according to the maximum value of the actual value of the excess air coefficient, and the fault of the target injection valve is determined through the maximum value and the average value. Under the condition that an engine is not disassembled, the fault of the injection valve of the engine can be accurately diagnosed, and the general applicability is high.

The invention discloses a nano preparation loaded with a gene diagnosis probe and / or an anti-pulmonary fibrosis drug and a preparation method of the nano preparation. The nano preparation is simultaneously loaded with the gene diagnosis probe and the anti-pulmonary fibrosis drug, the gene diagnosis probe realizes diagnosis of early pulmonary fibrosis by virtue of a fluorescence energy resonance transfer principle, and cooperates with the anti-pulmonary fibrosis drug to regulate steady-state balance of type II alveolar epithelial cells, so that the aim of treating the early pulmonary fibrosis through diagnosis and treatment in a cooperative manner is achieved. On the other hand, the nano preparation containing Reactive Oxygen Species (ROS) specific sensitive lipid fragments and a carrier thereof are utilized, and instantaneous release of the anti-pulmonary fibrosis drug is promoted by virtue of the ROS specific sensitive lipid fragments, so that the aim of regulating the early pulmonary fibrosis through diagnosis and treatment in a cooperative manner is achieved, and a new way and strategy are provided for treatment of reversing the early pulmonary fibrosis.

The invention discloses a preparation method of a mesoporous silica complex with drug controlled release and imaging functions. The preparation method comprises the following steps of (1) preparing anAu / Fe3O4@mSiO2-SH molecular probe; firstly, preparing Au nanoparticles; secondly, preparing Au / Fe3O4 nano particles with a shell-core structure; then, preparing Au / Fe3O4@mSiO2-SH nanoparticles by applying a reversed-phase microemulsion method; (2) preparing Au / Fe3O4@mSiO2 / DOX-SS-PEG-HA; adding Au / Fe3O4@mSiO2-SH nanoparticles into a DOX ethanol solution, performing dispersing of the obtained nanoparticles into a DMSO aqueous solution, and adding SH-PEG-NH2, so as to obtain nanoparticles Au / Fe3O4@mSiO2 / DOX-SS-PEG-NH2; enabling HA to be dissolved in an MES solution through a carbodiimide method,enabling EDC and NHS to be added to serve as coupling agents, and enabling Au / Fe3O4@mSiO2 / DOX-SS-PEG-NH2 to be added. The nanoprobe has three imaging functions of MRI, MPI and PAI and chemotherapy and photo-thermal treatment functions, can realize comprehensive, sensitive and targeted imaging of tumors, can perform real-time quantitative in-vivo monitoring of drug curative effects, and opens up abrand new field for accurate diagnosis and treatment of tumors at the molecular level.

A turbine pump small sample fault judgment method based on data expansion and deep transfer learning comprises preprocessing operations such as filtering, sampling, trend term removal and smoothing, noise can be effectively eliminated, and vibration signals are made to have better robustness; on the other hand, the generative adversarial network is fully utilized, a high-quality time-frequency spectrum sample generated based on the WGAN-GP model can further enrich an original data set, and the robustness of the diagnosis model is improved; finally, a feature extraction part in the mature ImageNet model is fully utilized for model migration, and then accurate diagnosis of the turbine pump is achieved.

The invention discloses a network diagnosis and repair method and device, equipment and a medium. The method comprises the following steps: acquiring network state information which is sent by a wireless access point and aims at a target client in a wireless local area network; constructing an information association database for the target client based on the network state information; diagnosingwhether the target client has a network problem based on the information association database, and performing corresponding repair operation on the wireless access point according to a diagnosis result. According to the method, the network state information of the target client is acquired, the information association database is constructed for the target client according to the network state information, and the network of the target client can be analyzed in real time through the constructed information association database so as to determine the specific network fault; and the corresponding wireless access point is automatically repaired, so that the maintenance cost is effectively saved, and the diagnosis and repair capabilities of the network are improved.