10results about How to "Improve diagnostic reliability" patented technology

The invention discloses an on-line electrochemical impedance spectroscopy measurement method and device for a fuel cell and a storage medium, and the method comprises the steps: obtaining an initial value of an influence parameter which influences an EIS test result when the fuel cell is started, the influence parameters at least comprise the stack temperature, the stack voltage, the stack current and the low-frequency impedance; acquiring an actual measurement value of the influence parameter when the fuel cell runs; determining a target output value of each influence parameter according to the initial value of each influence parameter and the measured value of each influence parameter; and coupling the target output values of the influence parameters to obtain a high-frequency impedance value. By adopting the method, accurate online EIS diagnosis can be realized, and the diagnosis reliability of the battery state is improved.

The application discloses a power transmission and distribution network end cloud collaborative risk prevention and control method and system based on dynamic routing, relates to the technical field of power system automation, and comprises the following steps: collecting high-frequency time sequence electrical data in real time and constructing normalized time sequence characteristic vectors; inputting the time sequence characteristic vectors into a semantic routing network to calculate routing scores, comparing the routing scores with a preset threshold, and performing dynamic shunting after the comparison; when a local processing path on the end side is activated, a control instruction or a protection action signal is output by an end side execution model reasoning; when an end cloud collaborative processing path is activated, visual semantic features are extracted and jointly transmitted to a station end together with the time sequence features, and a station end cognitive large model is used for multi-modal fusion reasoning, to generate a treatment suggestion and return the treatment suggestion. Through the dynamic routing mechanism, the application realizes asymmetric collaboration of end cloud computing power, guarantees millisecond-level response speed, improves the research and judgment accuracy of complex faults, and significantly reduces communication bandwidth occupation and end side power consumption.

The invention relates to the technical field of medical image processing, in particular to a CT image automatic noise reduction processing method based on multi-scale feature fusion. The method comprises the following steps: performing frequency domain analysis on a CT image, dividing the CT image into a plurality of scale spaces, performing edge detection on each scale space, determining a coincident edge of adjacent scale spaces, determining a real tissue edge by calculating gradient direction consistency and cross-scale gradient stability of pixel points on two sides of the coincident edge, and marking other edges as noise; and determining an optimal scale combination according to the noise coverage rate and the noise priority, carrying out noise reduction processing by adopting different denoising algorithms, and finally fusing the denoised scale space and the non-denoised scale space to obtain a denoised CT image. The real tissue structure and the noise can be effectively distinguished, the details of the tissue structure are kept to the maximum extent while the noise is restrained, and the reliability of CT image diagnosis is improved.

The present application relates to the technical field of in-situ leaching uranium process monitoring and gas-liquid two-phase flow detection, and discloses a kind of in-situ leaching uranium pipeline gas block state determination method, device, medium and equipment, method includes the pressure fluctuation signal of multiple measuring points along fluid flow direction on injection pipeline is collected, and pressure fluctuation signal is preprocessed, obtain pressure time history signal;Pressure time history signal is respectively subjected to multi-scale time-frequency decomposition and time domain correlation analysis, and two kinds of characteristic indexes are extracted;According to two kinds of characteristic indexes, the gas block risk state at the corresponding measuring point is determined, and according to the change trend of the characteristic indexes at multiple measuring points along the fluid flow direction, the evolution trend of the gas block in the pipeline is judged, and the corresponding early warning signal is output.The above-mentioned method early warns before the formation of gas block, fully excavates the flow characteristic information in pressure signal from two dimensions of frequency domain and time domain, and uses double-index joint determination to improve the reliability of diagnosis, information is fully utilized, and the judgment accuracy is high.

The invention discloses an oxygen sensor diagnosis method, device and equipment, a storage medium and a program product, and belongs to the technical field of vehicles. The method comprises the steps that under the condition that the diagnosis activation condition of the oxygen sensor is met, the actual combustion state of the engine is determined according to the measurement Lambda of the oxygen sensor; executing a diagnosis task of the oxygen sensor according to the actual combustion state; for each single-side degradation diagnosis, acquiring a delay time integral and a climbing time integral in the process of changing the measurement Lambda of the oxygen sensor to a target Lambda corresponding to the single-side degradation diagnosis; according to the delay time integral and the climbing time integral of each thin-to-thick single-side degradation diagnosis in the diagnosis task, determining a thin-to-thick single-side degradation diagnosis result of the oxygen sensor; and according to the delay time integral and the climbing time integral of each thick-to-thin single-side degradation diagnosis in the diagnosis task, determining a thick-to-thin single-side degradation diagnosis result of the oxygen sensor. The diagnosis reliability of the oxygen sensor can be improved.

The invention relates to a method for imaging in computed tomography, the method comprising the following steps: - providing a CT data set (D) of an object (O), wherein the CT data set (D) has been recorded by means of a multispectral recording method; - suppressing contrast caused by tissue types (G1, G2) and generating a contrast-suppressed data set (K); - analyzing the CT data set (D) and / or the contrast-suppressed data set (K) by means of a machine learning algorithm, wherein the analysis is configured to identify at least one change within the tissue types (G1, G2). The invention also relates to a corresponding device (6), a control device (10) for a computed tomography system (1) or a diagnostic system, as well as a diagnostic system and a computed tomography system (1).

The present invention discloses a method and system for diagnosing faults of electric power equipment based on a cloud-edge-end collaborative architecture, the method comprising: obtaining the voiceprint vibration data of the target electric power equipment; extracting feature vectors from the voiceprint vibration data using a neural network that incorporates the voiceprint vibration propagation mechanism to obtain multiple feature vectors, and performing weight adaptive calculation and weighted fusion on the multiple feature vectors to obtain a mixed feature vector; using a deep residual network to perform fault identification and classification on the mixed feature vector; and outputting the results of fault identification and classification. The present invention can improve the accuracy and stability of fault diagnosis of electric power equipment while ensuring real-time performance.

The invention relates to a GIS equipment multi-mode diagnosis method and device. The method comprises the following steps: acquiring acquired data of GIS equipment, and preprocessing the acquired data; performing time-space dimension multi-modal feature extraction and fusion on the preprocessed acquisition data to obtain a high-dimensional feature vector; obtaining a comprehensive health index based on the high-dimensional feature vector, and obtaining a degradation track prediction result of the comprehensive health index; and performing hierarchical diagnosis according to the comprehensive health index and the degradation track prediction result to obtain a diagnosis result of the GIS equipment. According to the invention, the diagnosis reliability of the GIS equipment can be improved.

The invention provides a fault diagnosis method and device for a heating relay, electronic equipment and a readable storage medium. The relay fault diagnosis method comprises the steps that when charging preheating is started (at the moment, an insulation monitoring function is closed), a heating relay is controlled to be closed, and whether the heating relay is stuck and cannot be closed or not is diagnosed according to the voltage relation of all nodes in a charging preheating equivalent circuit. And when charging preheating is finished (at the moment, the insulation monitoring function is closed), the heating relay is controlled to be switched off, and whether the heating relay is stuck and cannot be switched on or not is diagnosed according to the voltage relation of the nodes in the charging preheating equivalent circuit. The negative influence of insulation monitoring can be avoided, and the reliability of a diagnosis result is remarkably improved; no hardware cost is added, and logic is simple and easy to implement.

The application relates to a carotid artery plaque detection and evaluation method and system based on multi-modal image feature analysis, wherein the method comprises the following steps: inputting a pretreated carotid artery ultrasound image into a target positioning model to obtain a carotid artery ROI region and a plaque ROI region; inputting the carotid artery ROI region and the plaque ROI region into corresponding structure segmentation models respectively to obtain carotid artery segmentation results and plaque segmentation results, and performing post-processing on the carotid artery segmentation results and the plaque segmentation results respectively to obtain a carotid artery binary mask image and a plaque binary mask image; extracting all contours from the carotid artery binary mask image and the plaque binary mask image by using a contour extraction algorithm, and selecting the largest contour as a carotid artery main contour and a plaque main contour; calculating plaque quantitative features according to the plaque main contour; and determining plaque smoothness according to the plaque quantitative features and the carotid artery main contour. The application can improve detection accuracy.