42results about How to "Accurate discovery" patented technology

The invention relates to the technical field of monitoring and early warning of power equipment, in particular to a monitoring and early warning method and system for substation power equipment. Comprising a data acquisition module, an intelligent diagnosis module, a risk assessment module, a collaborative early warning module and an interaction control module. The data acquisition module acquires equipment operation data including current, voltage, temperature and humidity and vibration signals. And the intelligent diagnosis module identifies equipment abnormity through the generative adversarial network and the graph neural network. The risk assessment module generates a risk assessment curve based on a fractional order differential model and a reinforcement learning algorithm. And the collaborative early warning module generates a graded early warning scheme by utilizing edge calculation. And the interaction control module displays a state and optimizes a control strategy through a human-computer interface. The intelligent monitoring and management level of the power equipment of the transformer substation is improved, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.

The invention discloses a working face earth surface rock movement digital intelligent observation and through-structure safety intelligent prediction method, and belongs to the technical field of mining industry and information, and the method comprises the following steps: determining a structure movement deformation safety early warning value; moving deformation data are collected and preprocessed; analyzing a dynamic change rule of surface movement deformation by applying finite element analysis; building a structure movement deformation prediction model; the structure movement deformation prediction model is trained and verified, and the trained model is used for structure movement deformation prediction; comprehensively evaluating safety and stability; and correcting parameters of the prediction model and continuously evaluating until the structure is safely pushed and mined. The invention provides a novel way with great potential for accurately predicting the rock migration trend and guaranteeing the safety of important facilities such as structures.

The invention discloses a wind power plant blade icing prediction method and device, equipment and a medium, and relates to the field of wind power generation. The method comprises the following steps: acquiring predicted meteorological data of a wind power plant in a future preset time period, wherein the predicted meteorological data comprises temperature and humidity; and inputting the predicted meteorological data into a pre-trained blade icing prediction model, processing the predicted meteorological data by the blade icing prediction model, and outputting a blade icing prediction result of the wind power plant, the blade icing prediction result representing a blade icing condition in a future preset time period. The blade icing prediction model is obtained through training according to historical sample data of the wind power plant, the historical sample data comprises meteorological data in historical icing time and meteorological data in historical non-icing time, the meteorological data comprises temperature and humidity, and the historical sample data has labels used for representing blade icing conditions corresponding to the meteorological data. According to the embodiment of the invention, the safety risk of the wind power plant can be reduced.

The invention discloses a computer network information security monitoring method, which relates to the technical field of network information security monitoring, and comprises the following steps of: monitoring and collecting network flow data in real time by using a monitoring and collecting module, extracting and recording historical network flow data, judging the abnormal degree of the current flow by using a comprehensive evaluation and adjustment module, and judging the abnormal degree of the current flow. The method comprises the following steps: evaluating the overall risk level of network security, adjusting a network security policy, generating a policy adjustment report, executing the adjusted network security policy by using a security execution module based on the policy adjustment report, and continuously monitoring network traffic by using a monitoring acquisition module. The beneficial effects and optimization innovation of comprehensive assessment, dynamic risk assessment, flexible strategy adjustment and sensitivity improvement are realized, and the optimization and innovation not only solve the problems and defects in the prior art, but also improve the accuracy and reliability of the monitoring system. And a more comprehensive and effective guarantee is provided for computer network information security.

The invention provides a fault detection method and system for a series diesel-electric hybrid power system. The fault detection method comprises the steps that a rotating speed signal is collected; decomposing the rotating speed signal once to obtain a plurality of IMF signals, performing data processing on the IMF signals to obtain corresponding Hurst indexes, and dividing the plurality of Hurst indexes to obtain IMF signals with noise as a main part and IMF signals with effective signals as a main part; deep decomposition processing is carried out on the IMF signals with noise as the main part, secondary reconstruction is carried out on the IMF signals after deep decomposition processing and the IMF signals with effective signals as the main part, and rotating speed signals after quality improvement are obtained; and inputting the rotating speed signal into a pre-constructed xLSTM deep neural network model to detect whether the current power system has a fault or not. The diesel engine rotating speed data of the system can be analyzed, the system problem can be found accurately and timely, and the safety of the series diesel-electric hybrid power system is guaranteed.

The invention relates to the field of astronomy transient source recognition combining astronomy and artificial intelligence, and when a transient source recognition task in mass data shot by a large-view-field high-sampling-rate telescope is carried out, an existing method generally uses a single classification model only depending on image data and is difficult to deal with complex and changeable data. The invention provides an astronomical transient source identification method for dynamically updating a multi-modal model. The method comprises the following steps: constructing the multi-modal model for classification by combining image data, a point spread function and physical information; and in combination with manual examination, selecting samples with wrong classification and possible transient source candidates, storing the samples and the possible transient source candidates as a new sample set, injecting the new sample set into the original training set, and loading the weight of the last training for retraining, so that dynamic adjustment and optimization of the model are realized. The method can effectively cope with mass data generated by a telescope with a large field of view and a high sampling rate, and ensures that the model always keeps efficient and accurate recognition performance under a complex background and weak signals.

The invention discloses an ammonia gas test method applied to detection of gas tightness of welding seams of a liquefied natural gas film storage tank and a marine film cabin. The ammonia gas test method comprises the following steps: 1) preparing detection equipment and chemical reagents; 2) cleaning a welding seam of the film storage tank and spraying a reaction type coating; (3) vacuumizing the main heat insulation layer, injecting a nitrogen-ammonia gas mixture, waiting for a certain reaction time, and periodically detecting the ammonia gas concentration and supplementing the ammonia gas during the period; 4) after the reaction time, emptying the nitrogen-ammonia gas mixture, observing from the inner side of the film storage tank, marking a weld leakage point, and repairing; and (5) after the leakage point is not found any more, post-processing is conducted on the heat insulation layer space of the storage tank. According to the gas tightness detection method, the precision and reliability of gas tightness detection of the welding seam are improved; the method is suitable for large-scale liquefied natural gas storage tank detection, and time and cost are saved; a detection blind area possibly existing in a traditional method is effectively avoided; and a detailed leakage repair and detection scheme is provided.

The invention discloses a bidding and tendering data screening recommendation method, and relates to the technical field of data governance and large model application. Comprising the steps of (1) collecting bidding and tendering data, (2) preprocessing the bidding and tendering data, (3) carrying out keyword extraction on the preprocessed bidding and tendering data, (4) constructing a business opportunity evaluation model, and (5) recommending bidding and tendering projects with higher scores to enterprises and providing project analysis reports according to scoring results of the business opportunity evaluation model. And 6, monitoring the found bidding and tendering project in real time, obtaining the latest progress and change information of the bidding and tendering project in time, and dynamically adjusting the evaluation result.

The invention belongs to the technical field of electricity charge management, and discloses an electricity charge business online management method and system. The method comprises the following steps: establishing a digital twin model based on a cloud data center, and constructing an electric charge business data analysis model and an electric energy scheduling model; based on the data transmission base station, a plurality of pieces of real-time electricity charge service data are collected and uploaded to the cloud data center; performing data analysis on a plurality of pieces of real-time electricity charge service data by using an electricity charge service data analysis model and a digital twin model; performing electric energy scheduling on the real-time data analysis result by using an electric energy scheduling model; and based on the cloud data center, a digital twin model is used to visualize a plurality of pieces of real-time electric charge business data, real-time data analysis results and real-time electric energy scheduling strategies of the electric charge business service subareas. According to the method, the problems of high cost investment, low efficiency, lack of information interaction, low practicability, poor intuition and poor data processing capability in the prior art are solved.

The invention discloses a network attack log processing method, a medium, electronic equipment and a program product. The method comprises the following steps: for each attack log in an attack log set, determining an attack type of the attack log according to a target attack mode corresponding to the attack log; and for each determined attack type, inputting the basic alarm information, the interface information and the target attack mode corresponding to each attack log belonging to the attack type in the set and the model cue word into a first large language model to obtain a first attack behavior analysis report corresponding to the attack type. Automatic aggregation analysis of attack logs can be realized, and the safety operation efficiency is improved. A large language model is utilized to aggregate and analyze knowledge of multiple dimensions, hidden attack events can be accurately found, and a readable attack behavior analysis report is output according to attack types in a classified mode. The method can be applied to various network firewalls, such as a Web application firewall, a large model security firewall and the like.

The invention discloses a segmented quantitative analysis method for uplift pressure of a gravity dam. The uplift pressure of the gravity dam is influenced by various factors, and safety monitoring data of the gravity dam often have the problems of multiple collinearity and small samples. The method comprises the following steps: introducing a BFAST time sequence decomposition method, decomposing original uplift pressure monitoring data into a trend component and a seasonal component, and obtaining trend segment points and seasonal segment points; a Bayesian model average modeling method integrating Bayesian model selection is introduced, and a gravity dam uplift pressure statistical model is established in a segmented mode; and finally, upstream and downstream water pressure components of the uplift pressure are separated according to the average multiple models, and quantitative analysis of the uplift pressure of the gravity dam is achieved. According to the method, more accurate fitting and component separation effects can be obtained, and accurate quantitative analysis of the uplift pressure of the gravity dam can be realized.

The utility model discloses a battery cell structure and a battery, and relates to the technical field of batteries. The battery cell structure comprises a naked battery cell, a battery cell cover plate, a battery management unit and a sensor assembly, the battery management unit comprises a wireless transmitting and receiving device; the battery management unit and the sensor assembly are arranged on the internal surface of the battery cell cover plate, and the internal surface is the surface, close to one side of the naked battery cell, of the battery cell cover plate; the sensor assembly is used for acquiring cell information of the bare cell; the battery management unit is used for acquiring cell information from the sensor assembly; and through the wireless transmitting and receiving device, the cell information is wirelessly communicated with the outside through the cell cover plate. Therefore, the battery cell information is monitored in real time, and the battery cell information is sent to the outside in a wireless communication mode, so that related technicians can timely and accurately find the abnormal condition of the battery based on the battery cell information.

A comprehensive supervision method and system for health management proposed in the present application involves the field of big data analysis, makes full use of big data to analyze health anomalies, and determines the information acquisition frequency of the monitored institution by comprehensively utilizing the average values ​​of the monitored institution and similar institutions with the highest degree of comprehensive relevance. The determined information acquisition frequency is more in line with actual needs, and information acquisition methods are separately formulated for different items to be monitored, thereby ensuring the accuracy of health management data. In addition, based on frequent item sets, the correlation between data can be accurately utilized to accurately discover abnormal problems.

The invention provides an unmanned aerial vehicle cluster collaborative inspection method and system for an ultra-high voltage power transmission line, relates to the technical field of power transmission line operation and maintenance, and solves the limitation problems of low collaborative efficiency, difficulty in data synchronization and the like of the current unmanned aerial vehicle cluster technology in line inspection. The method comprises the following steps: firstly, establishing a line three-dimensional digital twinborn model, dividing a to-be-patrolled line into a plurality of patrolling areas, and planning an initial patrolling path for each unmanned aerial vehicle in an unmanned aerial vehicle cluster; the unmanned aerial vehicles are classified into main unmanned aerial vehicles, detection unmanned aerial vehicles and operation unmanned aerial vehicles, the detection unmanned aerial vehicles collect environment information in advance according to the initial patrol path, and the main unmanned aerial vehicles dynamically adjust the flight path of the operation unmanned aerial vehicles accordingly; the operation unmanned aerial vehicle performs preprocessing and standardized packaging on the collected multi-source data, and a formed data packet is uploaded to the cloud platform by the main unmanned aerial vehicle to analyze and identify line defects. The system has the advantages and characteristics of full coverage, high efficiency and high precision of ultra-high voltage transmission line inspection.

The present invention provides a processing method, device, electronic device and storage medium for illegal countermeasures against unmanned aerial vehicles, which specifically include: monitoring whether a communication signal of a unmanned aerial vehicle occurs a specified abnormal event; the specified abnormal event can indicate that: the communication signal is interfered by a countermeasure device; if the specified abnormal event is monitored, then: according to the positions of multiple target unmanned aerial vehicles where the abnormal event occurs, determining the preliminary position information of the target countermeasure device; the target countermeasure device refers to: a countermeasure device that sends an illegal countermeasure signal and causes the specified abnormal event to occur; and locating the target countermeasure device according to the preliminary position information.

The invention provides a security vulnerability detection system based on an API interface, and relates to the technical field of security vulnerability detection.The system firstly analyzes the API interface through an analysis module to obtain calling information, and then analyzes calling of the API interface through a static analysis module and a dynamic analysis module to obtain calling information; according to the method, a calling graph capable of representing calling relations among different APIs is generated, a detection queue is generated according to the calling graph, and test parameters of the APIs are generated according to the calling graph, so that the generation efficiency of the test parameters is improved, the security vulnerability detection efficiency is improved, and finally, the method calling when the APIs process the test parameters is analyzed, so that the security vulnerability detection efficiency is improved. The API interface with the recursive structure with vulnerability suspicion is marked as possible security vulnerabilities, so that the system can more efficiently and accurately help testers to find related types of security vulnerabilities in the API interface, and then can timely optimize the API interface to defend attacks against the vulnerabilities.

This invention provides a method for identifying low-speed, small targets using radar echoes based on optical flow. The method includes receiving radar echo data in real time and redrawing the images to form a series of multi-frame radar echo images; using the pyramid LK optical flow method, sequentially performing layered analysis on the formed multi-frame radar echo images to obtain the optical flow vector of each frame; comparing the optical flow vectors of each frame to determine dynamic and static targets in each frame; and based on the dynamic and static target identification results fed back by the radar, determining whether one or more dynamic targets in each frame have not been identified by the radar. If so, the unidentified dynamic targets in each frame are considered low-speed, small targets before being acquired. Implementing this invention solves the problem of insufficient radar detection capability for low-speed, small targets and improves target acquisition efficiency.

The present invention relates to the field of family environment evaluation, and specifically to a family growth environment perception system for teenagers. The invention uses the feelings that teenagers have about their family members to select clothes and colors that can represent their personal feelings for family member models representing different personalities, based on the different connotations given by the system to clothes of different parts and the different scores given to the colors of different clothes. Thus, the real feelings of the teenagers about the family atmosphere and family members of different personalities can be distinguished through specific scores. This method can better help family members and therapists understand the teenagers, and improve the family atmosphere and correct the words and deeds of family members in a targeted manner. It solves the problem that some teenagers are unwilling to express or cannot accurately express the family atmosphere in words, which makes it difficult for psychotherapists to accurately understand the teenagers and their family situations, and thus difficult to carry out targeted treatment.

The invention relates to the technical field of application software anomaly detection, in particular to an artificial intelligence application software anomaly detection device and method, and the method is realized based on an artificial intelligence application software anomaly detection system. The system comprises a data collection module, a preliminary data analysis module, a three-number middle-taking method partition detection module, a recursion detection module, a double-shaft rapid sorting anomaly detection module and an anomaly diagnosis classification module. The method sequentially comprises the following steps of data acquisition, benchmark test, partition anomaly detection, recursion anomaly detection, double-shaft rapid sorting anomaly detection and anomaly diagnosis and repair, and can comprehensively detect whether the logic of an algorithm is correct or not, including a partition process and a recursion process, so that potential logic errors are found, and the accuracy of the algorithm is improved. And algorithm logic anomaly detection is quickly carried out on the artificial intelligence application software.

This invention provides a method and apparatus for event detection in a video surveillance system. The method includes: acquiring core process information of each primary and backup server in the video surveillance system, wherein the primary and backup servers include a primary server and a backup server with a redundant backup relationship with the primary server; determining whether a primary / backup switchover event exists for each of the primary and backup servers in the video surveillance system based on the core process information at the previous moment and the core process information at the current moment; and generating a corresponding event detection result based on the primary / backup server where the switchover event occurred if there is a primary / backup server in the video surveillance system. This invention effectively solves the problem of low efficiency in manual event detection and can detect primary / backup switchover events more promptly and accurately.

The present invention relates to the field of image processing technology, and in particular to a method for monitoring the quality of new printed materials based on computer vision. The method acquires an image of a new printed material; acquires the degree of speckle in the closed area according to the edge roughness and position distribution of the closed area in the image; acquires the background possibility degree according to the edge roughness and speckle degree of the closed area in each suspected background closed area; acquires the clustering distance of any two closed areas according to the difference in the background possibility degree and speckle degree of the suspected background closed area in which any two closed areas are located, and then clusters the closed areas to obtain cluster clusters; detects speckle defects according to the edge roughness of the closed area in the cluster cluster. The present invention accurately divides the closed areas in the image by acquiring the clustering distance, avoids the interference of normal areas on speckle defects, and is conducive to accurately identifying the speckle defect area.

The invention provides a motor vibration monitoring system, and belongs to the technical field of motor control. The motor vibration monitoring system comprises a vibration sensor arranged on a motor rotor and / or a motor bearing and used for monitoring a vibration signal of a motor to obtain vibration data; the electrical parameter monitoring module is used for monitoring electrical parameters of the motor to obtain electrical data; the electrical parameter monitoring module comprises a voltage detection circuit, a current detection circuit and a power factor detection circuit; the output end of the vibration sensor, the output end of the voltage detection circuit, the output end of the current detection circuit and the output end of the power factor detection circuit are all connected with the controller, and the controller is used for analyzing the vibration state of the motor based on the vibration data and the electrical data. And obtaining a motor vibration state analysis result. The problem that motor vibration fault detection is not timely can be solved.

The application belongs to the technical field of geotechnical engineering construction, and specifically provides a disordered high fill site pre-ramming and humidification and dynamic compaction combined construction method, which comprises the following steps: 1) detecting cracks and cavities in the target site; 2) pre-ramming to eliminate cracks and cavities in the target site; 3) water injection and humidification of the target site after pre-ramming; and 4) dynamic compaction construction of the humidified target site until the requirements are met. The application solves the problems of uneven humidification and poor reinforcement effect in the existing dynamic compaction foundation treatment of disordered high fill soil sites, avoids the problem of uneven water injection and humidification caused by uneven upper and lower strata, and has the characteristics of good treatment effect, fast construction speed and small residual settlement.

The invention relates to the technical field of pipeline measurement and control, in particular to an intelligent gas pipeline safety monitoring and management system based on the Internet of Things, and the system judges whether gas leakage occurs or not by detecting the gas concentration of each region and each time point of a gas pipeline. Obtaining each leakage point of the gas pipeline according to the pressure value of each leakage detection point of the gas pipeline at each time point, obtaining the corrosion degree of the gas pipeline according to the external corrosion degree and the internal corrosion degree of the gas pipeline, and judging whether the pressure of the gas pipeline needs to be adjusted or not according to the gas consumption of the gas pipeline at each time period. And the response sensitivity of pressure regulation of the gas pipeline is analyzed, so that the comprehensive evaluation index of the gas pipeline is obtained through comprehensive analysis, and the comprehensive evaluation index is fed back, so that the safety of gas use is greatly improved, and the risk of gas accidents is reduced.

This invention relates to the field of measurement and provides a shoe sole measuring mechanism, including a chassis frame and a lifting rod. A slide rail is mounted on the top surface of the chassis frame, and a baffle is also mounted on the chassis frame. A push plate is mounted on the slide rail. A slider that moves vertically is mounted on the lifting rod, and a groove is provided on the baffle. The baffle has a first scale, and the chassis frame has a second scale. The slide rail drives the push plate to move, and in conjunction with the data on the second scale, the length of the shoe sole is obtained. Then, by adjusting the lifting rod, the slider's horizontal height is changed, and in conjunction with the first scale, the height of the forefoot tilt of the shoe sole is obtained. This acquisition of key shoe sole data allows for the determination of whether there are errors in the shoe sole produced by the mold, achieving the purpose of inspection. Simultaneously, the shoe sole measuring mechanism has high flexibility, can adapt to different shoe sole models for measurement, and obtains accurate measurement data, solving the problem of cumbersome manual or simple tool measurements.

The invention discloses a steel rail welding seam flaw detection scanning device and a flaw detection method thereof. The steel rail welding seam flaw detection scanning device comprises a scanning support, a guide rail sliding block mechanism and a guide rail probe mechanism, wherein the scanning support can be mounted on a steel rail in a falling manner and is automatically positioned on the steel rail or is automatically separated from the steel rail through lifting; the guide rail sliding block mechanism comprises a first guide rail arranged in the length direction of the steel rail, a guide rail sliding block arranged on the first guide rail and a sliding block driving mechanism used for driving the guide rail sliding block to reciprocate along the first guide rail, and a rail surface probe capable of being attached to the rail surface of the steel rail is fixed to the bottom of the guide rail sliding block. The second guide rail is located below the first guide rail and is parallel to the first guide rail, the probe support is arranged on the second guide rail in a sliding mode, a rail side probe is fixed in the probe support, the guide rail sliding block can drive the probe support to reciprocate along the second guide rail, and the guide rail probe mechanism and the scanning support are of a linkage structure. The steel rail welding seam flaw detection scanning device and the flaw detection method based on the same are convenient and efficient to operate.

The invention discloses a verification method and system for a scientific calculation-oriented hybrid programming model, and relates to the technical field of information, and the method comprises the steps: carrying out the difference analysis of an original programming model and a high-performance programming model; performing initialization of physical parameters and calculation parameters and distributed topology on the original programming model; analyzing the original programming model by adopting a performance analysis tool to obtain a hotspot function; establishing a matching mapping mechanism of the original programming model and the high-performance programming model, and performing hotspot function transplantation; and constructing a verification function, carrying out hybrid compiling with the original programming model, respectively carrying out unit testing and integration testing, and outputting to obtain a verification result. Program vulnerabilities in the transplantation process can be found, and the overload workload of a large amount of output data manual comparison results is avoided. The method supports verification of various hybrid programming models, and can be used as an intermediate process method for conversion of two or more kinds of programming to verify correctness of target codes.

The invention discloses an electric drive system NVH dynamic test system and method based on XIL. The system comprises a driver-in-the-loop module, a real object-in-the-loop module and an NVH data acquisition system. The driver in-the-loop module is used for collecting a driver real-time operation signal and providing a virtual driving environment; the real object in-the-loop module receives a signal through a real-time simulation machine, and a co-simulation model is used for resolving vehicle dynamic operation parameters; and the rack system drives the dynamometer to apply a dynamic load to the tested electric driving system by adopting a composite control framework based on rotating speed closed-loop control and combined with dynamic compensation according to the parameters. By constructing a human-vehicle-road closed-loop coupling mechanism, the problem that transient load change in a complex driving scene cannot be reproduced in a traditional rack test is solved, working conditions such as urgent acceleration and braking can be simulated in a high-fidelity manner, vibration and noise response of an electric driving system in real dynamic operation can be accurately captured, and the reliability of the electric driving system is improved. And the authenticity and the effectiveness of the NVH test are obviously improved.

The invention discloses an electricity meter tamper-proof identification method and system based on a BERT model, and belongs to the technical field of electric power metrology, the identification method comprises the steps of preprocessing collected structured data and text data, respectively forming feature data and a text sequence, extracting [CLS] vectors according to the text sequence and the BERT model, and fusing the [CLS] vectors and the feature data to obtain an electricity meter tamper-proof identification result. Obtaining a feature vector; and inputting the feature vector into a trained classifier, outputting a risk probability and a risk type that the ammeter has a tampering risk, carrying out association analysis in combination with pre-obtained association information, and generating an alarm work order. According to the method, the structural data and the text data are fully utilized, so that the hidden tampering method can be found and captured more accurately, and an effective basis is provided for subsequent countering attacks. According to the invention, the corresponding response threshold is adjusted according to the associated information, so that a specific application scene can be more accurately adapted, and the alarm accuracy is improved.

The present invention belongs to the technical field of alarm devices, and specifically relates to a high-temperature alarm device and system for an LED explosion-proof lamp, wherein the high-temperature alarm device includes a lamp body substrate, a lamp strip body, a heat pipe, a heat-conducting part, an electromagnetic ring, an insulating connecting rod, a central column, a reset part and a thermal stress switch. The heat-conducting part includes an insulating ring, a heat conductor and an armature body. The heat conductor can selectively contact the heat pipe. The insulating ring can establish a thermal connection with the heat conductor. The electromagnetic ring is arranged on the lamp body substrate and connected to a controller. The lower end of the insulating connecting rod is connected to the armature body and establishes a thermal connection with the insulating ring. The central column is connected to the upper end of the insulating connecting rod. The thermal stress switch is arranged on a thermally conductive substrate on the central column and connected to an alarm circuit module in the controller. The lower end of the reset part is connected to the lamp body substrate, and the upper end is connected to the central column, and an upward elastic thrust can be applied to the central column. This patent can be used to monitor the high temperature condition of the LED explosion-proof lamp and to alarm, which helps to avoid accidents.