41results about How to "Effective diagnosis" patented technology

The invention relates to the technical field of intelligent fault diagnosis systems, in particular to an intelligent fault diagnosis system and method for multi-sensor data fusion, and the system comprises an online diagnosis module and an offline training module, the online diagnosis module comprises a self-adaptive balance sub-module and a prototype network sub-module, and is used for processing sensor data in real time and carrying out fault diagnosis; the offline training module comprises a data preprocessing sub-module, a data fusion sub-module, a fault diagnosis sub-module, a data balance sub-module and a data interpretation sub-module, and is used for optimizing a diagnosis model; the data interpretation sub-module comprises an SHAP value extraction unit which is used for interpreting a diagnosis result; an online diagnosis module and an offline training module of the system form a closed-loop optimization mechanism, so that the diagnosis model can continuously learn and adapt to a new fault mode. The design ingeniously balances the requirement of real-time diagnosis and the requirement of continuous optimization of the model, and the long-term effectiveness of the system is greatly improved.

The invention provides a camera quality centralized diagnosis method and system. The method comprises the following steps: regularly obtaining video frames or video streams of a transformer substation camera; determining a quality state of the camera based on the video frame or the video stream; the method specifically comprises the following steps: analyzing the video frame or the video stream, and diagnosing the quality state of the camera according to the quality state of the video frame or the video stream; and if the quality state of the camera is abnormal, triggering an alarm. According to the method, additional equipment is not needed, the state of the camera body is effectively diagnosed by processing and analyzing the pictures or videos output by the camera and combining related judgment rules, the abnormal state of the camera can be found in time, related personnel can be notified, the working reliability and stability of the camera are guaranteed, and the working efficiency is improved. The method can be widely applied to the fields of security monitoring and the like.

The invention relates to the technical field of equipment fault detection, and discloses an equipment fault prediction and diagnosis method which is applied to an ATE system, and the method comprises the steps: collecting the real-time operation data of equipment through a plurality of sensors, and dynamically scheduling the sensors through an adaptive algorithm, so as to adjust the data collection frequency and range according to the state of the equipment; the collected data is preprocessed; training a plurality of machine learning models based on the historical fault data and the operation data, and deploying the models to an ATE system for real-time analysis; predicting an equipment fault according to the model, generating alarm information when a potential fault is detected, and sending the alarm information to an operator through a user interface or a notification system; generating a fault diagnosis report according to an analysis result and providing a repair suggestion; recording a fault instance and data, and updating and retraining the machine learning model to improve prediction and diagnosis accuracy; and generating a digital twin model of the equipment based on real-time and historical data, simulating the running state of the equipment, predicting future faults, and evaluating the health condition of the equipment.

The invention discloses a nuclear power device fault diagnosis method based on feature vectors and Bayesian reasoning, belongs to the technical field of Bayesian reasoning, and particularly relates to nuclear power device fault diagnosis. The method solves the problem that a traditional Bayesian model only uses parameter values as a fault reasoning basis and ignores a large amount of parameter time-frequency feature information, so that the model is difficult to distinguish feature similar faults and realize accurate positioning of the faults, and the fault diagnosis accuracy and the model robustness are affected. The method comprises the following steps: a model learning step: performing structure learning and parameter learning on a Bayesian model according to fault historical operation data to obtain a Bayesian vector reasoning model; the nuclear power device fault diagnosis method based on the feature vector and Bayesian reasoning is suitable for fault diagnosis of a nuclear power device.

The invention relates to the technical field of molecular biological detection, and particularly discloses a quadruple fluorescent PCR primer probe combination, a reaction system and a detection method for identifying a mycoplasma gallisepticum wild strain and a vaccine strain. The quadruple fluorescent PCR primer probe combination for identifying the mycoplasma gallisepticum wild strain and the vaccine strain comprises a universal primer probe group for detecting mycoplasma gallisepticum and a specific primer probe group specially aiming at three vaccine strains F-36, TS-11 and 6 / 85 respectively. According to the quadruple fluorescent PCR primer probe combination, the reaction system and the method for identifying the mycoplasma gallisepticum wild strain and the vaccine strain, the purpose of simultaneously detecting and distinguishing DNA of the mycoplasma gallisepticum wild strain and DNA of three different vaccine strains (F-36, TS-11 and 6 / 85) of the mycoplasma gallisepticum wild strain can be achieved, so that detection and differential diagnosis are more efficient, economical, simple and convenient; the kit has the advantages of high sensitivity, good specificity, rapidness, high flux, simplicity and convenience in operation and the like.

The present invention belongs to the field of medical technology, and discloses a liposome that actively targets atherosclerotic plaques and its application in diagnosis. The carrier material forming the liposome includes a targeting peptide R8 modified with methoxy polyethylene glycol phospholipid (R8-DSPE-PEG), polysulfide propylene-polyethylene glycol (PPS-PEG) and cholesterol (CH), and the sequence of the targeting peptide R8 is Asp-Ser-Ser-Ser-Gln-Cys-His-Arg. The liposome of the present invention can increase the enrichment concentration of fluorescent dyes or drugs in the local lesion, has the advantages of low toxicity and high efficiency, and the obtained targeted liposome has a good effect on the diagnosis of atherosclerosis.

The invention provides an asynchronous motor speed sensor fault diagnosis method, which comprises the following steps of: acquiring a rotating speed signal analog quantity, analyzing the acquired rotating speed signal analog quantity, and realizing asynchronous motor speed sensor fault diagnosis according to different rotating speed signal analog quantity analysis results. Analysis of the analog quantity of the collected rotating speed signals comprises a logic sequence of level conversion, the duty ratio of signals of the same channel, the period deviation ratio of signals of different channels, edge signal time prediction of different channels and high and low level voltage values. According to the method, the fault of the speed sensor can be effectively diagnosed by comprehensively analyzing the analog quantity of the collected rotating speed signal from different angles, and the method is simple to implement, small in calculated amount and high in practicability.

The invention relates to the technical field of nuclear power plant safety, and discloses a nuclear power plant fault diagnosis method based on interpretable deep transfer learning, which comprises the following steps: acquiring and preprocessing operation data or simulation data under multiple power levels, and dividing a source domain and a target domain; constructing and preliminarily training a multivariable interpretable gating cycle unit model, and screening features; training a source domain fault diagnosis model based on an adaptive focus loss function; training by adopting a self-adaptive focus mixed maximum mean value difference loss function, and migrating the source domain model to a target domain; and finally, integrating the source domain model and the target domain model to form a diagnosis system, and inputting to-be-tested data clusters and allocating the to-be-tested data clusters to the corresponding models to obtain a fault diagnosis result. According to the method, fault diagnosis tasks under different power levels can be effectively processed, operation condition data under the power levels are integrated and transmitted into a single model for training diagnosis, the accuracy and interpretability of the model are improved, and nuclear power plant operators can be further assisted in decision making.

The embodiment of the invention provides a bearing fault diagnosis method and system for optimizing filtering MCKD, and the method comprises the steps: collecting a vibration signal, and carrying out the Fourier transform of a frequency spectrum of the vibration signal, and obtaining a key function; setting an initial interception length, performing inverse Fourier transform on the key function based on the initial interception length to obtain a frequency spectrum trend, dividing filtering frequency bands with different bandwidths and center frequencies by taking a minimum value of a trend spectrum as a boundary of frequency spectrum segmentation, increasing the interception length, repeating the steps, and recording all results; designing a Mayer wavelet filter based on the obtained filtering frequency band, and taking a designed Mayer wavelet filter coefficient as an initial filter coefficient of MCKD; mCKD filtering results of different initial filter coefficients are calculated, the fault characteristics of all filtering signals are quantized through harmonic spectrum kurtosis HSK, the filtering result corresponding to the maximum HSK value is selected as the global optimal solution of MCKD, and fault diagnosis is completed.

The invention discloses a PCIe link state monitoring system and a monitoring method thereof. The PCIe link state monitoring system comprises a PCIe monitoring subsystem, a PCIe controller subsystem and a PHY (Physical Layer) module, wherein the PCIe controller subsystem and the PHY module are connected through a PIPE interface, and the PCIe monitoring subsystem is used for monitoring state information of a PCIe link; four levels of leaky bucket modules are integrated on the same layer of the PCIe monitoring subsystem, and the four levels of leaky bucket modules are used for dropping correctable error information in the state information of the PCIe link into leaky buckets, carrying out overflow counting to obtain leaky bucket overflow times, carrying out error pattern recognition according to the leaky bucket overflow times and preset different execution thresholds, and outputting the error pattern recognition result. Link recovery is carried out by adopting a progressive link recovery strategy; therefore, extra special equipment does not need to be introduced into the PCIe link, the observability of the PCIe link can be improved, and correctable errors caused by the signal integrity problem on the link can be analyzed and diagnosed in real time, so that a corresponding link recovery strategy is adopted.

The invention discloses an open-circuit fault diagnosis method and equipment applied to an inverter power supply of a hybrid power device. The method comprises the following steps: acquiring an output voltage or an output current in a current state; obtaining a current state, and obtaining each harmonic amplitude and a total harmonic distortion rate of a normal state; obtaining each harmonic amplitude offset and the total harmonic distortion rate offset of the current state; respectively comparing each subharmonic amplitude offset and the total harmonic distortion rate offset of the current state with the judgment threshold of the corresponding subharmonic amplitude offset and the judgment threshold of the total harmonic distortion rate offset; and determining that the open-circuit fault exists in the current state if the same specific subharmonic amplitude offset of the current state is greater than the judgment threshold of the corresponding subharmonic amplitude offset, or the total harmonic distortion rate offset of the current state is greater than the judgment threshold of the total harmonic distortion rate offset. According to the invention, the open-circuit fault of the inverter power supply of the hybrid power device can be diagnosed.

The present invention provides a method, system and electronic device for identifying a diseased area, including: obtaining initial image data of a region to be identified; preprocessing the initial image data to determine image data to be segmented; segmenting the image data to be segmented based on a preset grayscale threshold parameter to obtain a preset type of tissue region, and determining a grayscale digital signal corresponding to the tissue region; and, collecting Raman molecular information of the tissue region through Raman spectroscopy acquisition technology to obtain spectral data of the tissue region; mapping the spectral data to a grayscale digital signal according to the position information of the tissue region corresponding to the spectral data to obtain mapped spectral data; inputting the mapped spectral data into a pre-trained convolutional neural network model, and outputting the diagnostic result of the mapped spectral data. The method combines image segmentation, Raman spectroscopy acquisition and convolutional neural network analysis to achieve accurate positioning and efficient diagnosis of diseased tissues.

The charging pile fault diagnosis method based on deep self-perception cycle network comprises the following steps: collecting multi-dimensional electrical time sequence signals during the operation of a charging pile power module and preprocessing to obtain preprocessed time sequence signals; simultaneously extracting forward and backward long-time dependence features of the sequence through a long short-term memory network to obtain a fused bidirectional hidden state sequence; inputting the obtained bidirectional hidden state sequence into a self-attention mechanism layer, calculating attention weights through scaled dot product to adaptively enhance the representation of key fault feature periods, and outputting a fault diagnosis result through a fully connected classification layer and a normalized exponential function; using an adaptive matrix estimator optimizer with weight decay to end-to-end train a diagnosis model, updating model parameters through decoupled weight decay and adaptive learning rate, and completing model optimization and deployment. The method has strong bidirectional time sequence dependence modeling capability, high generalization capability and faster convergence speed in the fault diagnosis task.

The invention provides a multi-source data cooperative monitoring method for faults of a transmission drum of a belt conveyor, relates to the field of state monitoring and fault diagnosis of mechanical equipment, and solves the problem of automatic monitoring and analysis of the transmission drum. The method comprises the following steps: collecting multi-source data required by transmission roller fault analysis and transmitting the multi-source data in real time; judging whether the analysis algorithm needs to be subjected to first training and incremental training or not, if any training needs to be carried out, entering an algorithm training step, and otherwise, skipping to a cooperative monitoring step; the analysis algorithm is trained and updated by using multi-source data, and the updated analysis algorithm is transmitted to the cooperative monitoring step; rotating speed analysis, visual analysis and time sequence analysis are executed in a parallel mode, analysis results are output, real-time judgment and prediction results of faults of the transmission roller are obtained, and data are collected again for the next monitoring cycle; according to the invention, real-time and omnibearing monitoring of the running state of the transmission roller is realized, and the overall running efficiency and safety of the belt conveyor are effectively improved.

The invention discloses a fuel cell system stack flooding fault on-line diagnosis method comprising the following steps: S1, obtaining stack state parameters, and determining that a stack has a fault according to a first set condition; s2, the cathode flow is increased, and it is judged that the stack cathode breaks down according to a second set condition; and S3, applying instantaneous pulse current excitation to the galvanic pile, recording the voltage change condition of each single cell of the galvanic pile, and judging that the anode of the galvanic pile has a fault according to a third set condition. According to the fuel cell system stack flooding fault on-line diagnosis method, the instantaneous current pulse is applied to the stack through the load, and the corresponding voltage signal is detected in real time, so that the low-frequency impedance characteristic of the cell is simulated, the flooding problem in the stack can be effectively diagnosed, additional equipment is not needed, the cost is low, and the fault diagnosis efficiency is high. The invention also discloses diagnosis equipment for implementing the on-line diagnosis method for the electric pile flooding fault of the fuel cell system.

This application discloses a single-chip integrated miniature wireless pH detection device and system based on ISFET, relating to the field of in vivo pH detection technology. The device includes: a housing; a wireless sensing chip integrating a pH sensing module, the sensing interface of which is exposed to the measured environment through the housing; a signal processing module connected to the pH sensing module for processing the pH sensing signal detected by the pH sensing module; and a wireless communication and power supply module connected to the signal processing module for transmitting the pH sensing signal processed by the signal processing module and supplying power to the modules on the wireless sensing chip. This application integrates the pH detection module, signal processing module, and wireless communication module into a single on-chip system, utilizing CMOS technology, wireless power transfer technology, and backscattered reverse communication technology, effectively reducing the size of the pH detection device and improving the accuracy of pH detection.

The invention relates to a method for diagnosing at least one first switch and at least one second switch of a switching unit with loading by a single-tank voltage and a vehicle electrical system voltage, comprising at least the following steps: a) providing at least one first switch with at least one first single-tank-sided sub-switch and at least one first vehicle-sided sub-switch arranged in series; b) providing at least one second switch with at least one second single-tank-sided sub-switch and at least one second vehicle-sided sub-switch arranged in series; c) measuring at least one first voltage at a central tap between the sub-switches when the first switch is open or at least one second voltage when the second switch is open, wherein a first test is carried out; d) closing at least one single-tank-sided sub-switch, wherein a second test is carried out; e) opening the single-tank-sided sub-switch and closing the vehicle-sided sub-switch, wherein a third test is carried out; wherein a connection voltage is continuously maintained.

The invention discloses a mechanical intelligent fault diagnosis method and device based on a multi-modal sensing signal, and belongs to the field of mechanical equipment fault diagnosis, and the method comprises the steps: multi-modal data collection and preprocessing: collecting three-channel original signals of two vibration channels and one current channel of mechanical rotating equipment under normal and multiple fault working conditions, intercepting equal-length fragments to form a sample; constructing and training a convolutional neural network model, and performing deep feature learning on the multi-modal sample; and inputting a to-be-detected multi-modal signal into the trained model, performing fault diagnosis reasoning, and outputting a corresponding diagnosis result. According to the invention, multi-sensor information and a deep learning algorithm are fused, and high-accuracy fault detection and health state intelligent evaluation of the mechanical rotating part are realized.

The invention discloses a kidney cancer early detection kit and application, and relates to the technical field of biology. The invention provides application of a reagent for detecting the methylation level of a methylation site marker of kidney cancer in preparation of a kidney cancer detection product. The reagent comprises a methylation detection primer pair, the methylation detection primer pair comprises primer pairs used for detecting sites cg01362243, cg07351192, cg06829686 and cg26595643, the kidney cancer can be effectively diagnosed in the early stage, the survival rate of patients is increased, and the methylation detection primer pair is easy and convenient to operate, accurate in result and high in specificity.

Disclosed is a battery cell diagnosing apparatus, which includes at least one sensor; and a first control unit configured to obtain data including at least one of voltage, current or temperature of a battery cell from the at least one sensor, obtain a first diagnostic information based on the data, transmit the data to an external device, receive second diagnostic information of battery cell based on the data from the external device, and diagnose an abnormal state of the battery cell based on the first diagnostic information and the second diagnostic information.

The invention discloses an intelligent voltage regulating transformer fault diagnosis method and system based on an improved CNN-BiLSTM model. The method comprises the following steps: firstly, collecting historical data of a voltage regulating transformer for preprocessing; then training is carried out based on historical data of the voltage regulating transformer to obtain a transformer fault diagnosis model, the transformer fault diagnosis model is an improved CNN-BiLSTM model, and an ECA-TAM attention mechanism is introduced into the CNN-BiLSTM model; and finally, inputting the current operation data of the voltage regulating transformer into the transformer fault diagnosis model to obtain a fault diagnosis result of the voltage regulating transformer. According to the method, an ECA-TAM attention mechanism is introduced into the CNN-BiLSTM network model for voltage regulating transformer fault diagnosis, purer and more representative feature input can be provided, interference of redundant information on time sequence modeling is reduced, the key dynamic learning ability is improved, efficient and accurate diagnosis of voltage regulating transformer fault types is achieved, and the fault diagnosis efficiency is improved. The accuracy and timeliness of transformer fault prediction are improved, and stable and safe operation of an electric power system is guaranteed.

The invention belongs to the technical field of fault diagnosis, and provides an unmanned mine car braking system fault diagnosis method based on model identification. According to the diagnosis method, a brake system reference model is established by adopting a model identification method based on a large amount of normal driving data accumulated in historical operation of the unmanned mine car, and whether a fault occurs or not is judged by calculating the deviation between brake system model output and brake system reference model output. The problem that the traditional fault detection depends on artificial experience and lacks reliable reference is solved, and the accuracy of fault detection can be improved.

According to one embodiment disclosed in the present document, a battery diagnostic device can include an interface unit that, for each of a plurality of battery cells, acquires a post-charge SOC for each charge cycle; and one or more processors that, based on the post-charge SOC, calculate a charge amount relative to an average for each of the plurality of battery cells; calculate a degree of change in the charge amount relative to the average for each of the plurality of battery cells according to the charge cycle; calculate an index value by applying a weight value for each cycle to the degree of change in the charge amount relative to the average for a battery cell being diagnosed among the plurality of battery cells; and diagnose an anomaly in the battery cell being diagnosed based on the index value for each cycle of the battery cell being diagnosed.

The invention provides an interface data transmission mode for data transmission, pushing and synchronization, and relates to the field of metal coiled material controllers. The interface data transmission mode based on data transmission, pushing and synchronization comprises the steps that a pluggable data adapter makes contact with an interface of a device, the data adapter is used as a bridge of the interface, a universal data model is defined through JSON Schema, data exchange and verification are allowed between different assemblies, the universal schema is designed, common fields such as i d, name and type are included, and the interface data transmission mode based on data transmission, pushing and synchronization is achieved. And custom fields are allowed to be expanded, a rule engine is used for realizing automatic conversion of data, and a data transmission channel is realized by adopting a factory mode. By simplifying the integration process among heterogeneous systems, developers do not need to write special conversion logic for each pair of systems, but utilize a uniform interface to perform data interaction, so that the complexity of system integration is remarkably reduced, and the development efficiency is improved.

The present invention belongs to the field of medical equipment, and specifically relates to a cardiovascular multimodal fusion analysis method, system, device and storage medium, wherein the method steps include: acquiring at least two diagnostic images; obtaining corresponding control signals and corresponding image information according to the at least two diagnostic images; obtaining corresponding fused images according to the at least two diagnostic images, the corresponding control signals and the corresponding image information; integrating the corresponding fused images to obtain a fused image; and also providing a system and device using the method. The method provided by the present invention and the system and device using the method have the beneficial effect of being easy to operate, and can enable doctors to diagnose and treat diseases efficiently.

The application provides an application of a method taking a protein as an action object in diagnosis and treatment of a KRAS gene mutation related disease, the method is to detect the expression of the protein to achieve the purpose of diagnosing the disease, or to inhibit or eliminate the activity of the protein, reduce or remove the protein to achieve the purpose of treating the disease. The application has the beneficial effect that the application of the method taking the protein as the action object in diagnosis and treatment of the KRAS gene mutation related disease, wherein the protein (RASON) has been proved to be overexpressed in a malignant tumor, especially a malignant tumor induced by the KRAS gene mutation, therefore, the protein is applied to a product for diagnosing and treating the malignant tumor, can effectively utilize the self characteristics to diagnose and treat the malignant tumor, and has wide market application prospect.

The invention relates to the technical field of pathogenic microorganism detection, in particular to a detection reagent for simultaneously detecting BTV, AKAV and EHDV and application of the detection reagent. The invention provides a one-step-method triple fluorescent RT-PCR (reverse transcription-polymerase chain reaction) detection reagent for detecting three arthrovirus diseases, namely bluetongue virus, Acamovirus and deer epidemic hemorrhagic fever virus, of ruminants such as cattle and sheep, and the detection reagent has no cross amplification reaction with other easily infected viruses of cattle and sheep. The kit can be used for efficiently and quickly detecting and diagnosing epidemic diseases of cattle and sheep susceptible to arbo viruses, and particularly has outstanding advantages in large-flux quick screening of a large number of sample virus nucleic acids.

In order to determine presence or absence of abnormality in an internal organ or muscle, a method of determining presence or absence of abnormality in an internal organ or muscle may comprise obtaining at least one image of the internal organ or muscle, determining at least one feature matrix for the at least one image, determining a feature value for measuring a tissue phenotype from the at least one feature matrix, and determining presence or absence of the abnormality in the internal organ or muscle using a trained artificial intelligence model. The feature value may comprise items selected as information indicating the tissue phenotype of the internal organ or muscle, and the items may be selected using a machine learning model among candidate feature values determinable from the at least one feature matrix.

A diagnostic system 10 includes: a first sensor apparatus 20a installed on the upstream side of a pipe 12 as a power transmission path; a second sensor apparatus 20b installed on the downstream side of the pipe 12; and a diagnostic apparatus 22. The diagnostic apparatus 22 acquires a detection result of the first sensor apparatus 20a and a detection result of the second sensor apparatus 20b. The diagnostic apparatus 22 estimates the state of the pipe 12 between the first sensor apparatus 20a and the second sensor apparatus 20b based on the detection result of the first sensor apparatus 20a and the detection result of the second sensor apparatus 20b.

The invention discloses a motor fault diagnosis method based on voiceprint feature extraction and transfer learning, and belongs to the technical field of equipment fault diagnosis, and the method comprises the following steps: S1, obtaining a sound signal of a working state of a motor, and extracting voiceprint features through an empirical mode decomposition and Mel-frequency cepstral coefficient method; s2, constructing a voiceprint feature data set according to the extracted voiceprint features; and S3, inputting the voiceprint feature data set into a CNN + ResNet network to obtain a motor fault diagnosis result. According to the method, the limitation of a traditional contact type method can be overcome, the maintenance cost is reduced, more accurate diagnosis information can be provided at the early stage of a motor fault, and the operation safety and reliability of motor equipment are improved. Data analysis and fault classification are carried out through a voiceprint feature extraction technology in combination with a deep learning model, a new direction is developed for motor fault diagnosis, and the method has important research value and application prospect.