125results about How to "Realize judgment" patented technology

The invention discloses a fatigue driving monitoring and early warning method based on multi-dimensional feature fusion, and relates to the field of intelligent traffic and safe driving, and the method comprises the steps: carrying out the feature extraction of a collected face image of a vehicle driver through a feature extraction model based on a convolutional neural network, and obtaining a face key point; then calculating the eye closing rate, the mouth opening rate, the head posture data and the facial muscle data to finally obtain multi-dimensional features, and fusing the multi-dimensional features by using a multi-layer perceptron to obtain fused facial features; and then, a fatigue state detection model obtained based on recurrent neural network training is utilized to detect the facial feature time sequence at a plurality of continuous sampling moments so as to detect whether a fatigue driving state occurs and trigger alarm feedback. According to the method, the fatigue state of the driver can be identified and judged more accurately through combination of multi-dimensional data fusion and a time sequence analysis algorithm, and the monitoring and early warning accuracy and reliability are improved. And the system can keep high robustness even in an illumination change or complex driving environment.

The invention discloses a field monitoring method based on engineering informatization, and the method comprises the steps: collecting the tightness data of a rope in real time through a tension sensor integrated on a protection rope, and transmitting the data to a field monitoring system; the method comprises the following steps: acquiring a worker operation picture shot by video monitoring equipment deployed in a construction site, and extracting posture features such as a body inclination angle and arm extension length of a worker in the picture; determining a real-time position coordinate of the worker according to the information of the positioning tag worn by the worker, and judging whether the coordinate is in a preset dangerous area electronic fence or not; according to the distance relation between the connection points of the worker and the protection rope, the swing track of the protection rope and the movement track calculated by the position coordinate change of the worker are analyzed, and whether the worker breaks away from the protection rope illegally or not is judged; if it is judged that the worker is separated from the protection rope, the position of a connection point of the protection rope suspected to fall off is marked in the monitoring picture according to the material characteristic and the color characteristic of the protection rope.

The invention discloses a GIS partial discharge fault detection device and method based on D-S evidence multi-source information fusion, and relates to the technical field of power system control, and the device comprises a signal collection module which is used for collecting an electromagnetic wave signal, a mechanical vibration signal, an ultrasonic signal and a partial discharge optical radiation signal generated by the partial discharge in GIS equipment; the GIS partial discharge fault detection module is used for processing, storing and sending the signals acquired by the signal acquisition module; the coordinator is used for realizing data transmission between the GIS partial discharge fault detection module and the background terminal; and the background terminal is used for receiving the processing information of the GIS partial discharge fault detection module and judging the fault type of the GIS equipment. According to the GIS partial discharge fault diagnosis system, various signals generated by partial discharge in the GIS equipment are detected through the information acquisition module, and the relationship between the characteristic data and the GIS partial discharge fault is established, so that diagnosis of the GIS partial discharge fault is realized, and the fault judgment efficiency of the background terminal is improved.

The invention relates to a welding self-adaptive visual control method and device and a storage medium. The method comprises the steps that a current electrical parameter combination, a welding image, welding gun relative weld joint position data and surface temperature distribution data in the welding process are collected in real time; inputting the welding image into a pre-trained molten pool recognition model, and outputting internal molten pool form data; the relative welding seam position of the welding gun, the surface temperature distribution data and the internal molten pool form data are input into a pre-trained welding process state space model, a welding state recognition result is output, and the welding state recognition result is selected from normal or abnormal; whether the welding state recognition result is abnormal or not is judged; if yes, according to the real-time evaluation result of the welding quality, a model is generated through a pre-trained strategy, and a new electrical parameter combination is output; the new electrical parameter combination is sent to a welding execution module, and the current electrical parameter combination is replaced with the new electrical parameter combination; therefore, precise self-adaptive adjustment in the welding process is achieved.

The invention discloses a method for detecting an external load of an automobile emergency starting power supply, and relates to the technical field of automobile emergency starting, in the step S2, after an output circuit is closed, a system monitors dynamic current and load state changes, extracts related transmission data and calculates an abnormal coefficient, and once the abnormal coefficient exceeds a preset abnormal threshold value, the system is started; and the system sends a start stopping instruction in time, so that excessive loss of a storage battery or a starting power supply is further avoided, and the safety of equipment and a vehicle is effectively guaranteed. And S3 and S4, constructing a starting result recognition model by using the change coefficient and the abnormal coefficient, and fitting a judgment index after performing linear normalization processing on the data by virtue of a deep learning technology. By comparing the judgment index Pdzs with the qualified threshold value, the system can intelligently judge whether starting is successful or not, automatically control power output, avoid excessive current output and prolong the service life of equipment.

The invention discloses an aging detection method, device and equipment for transformer oil and a medium, and the method comprises the steps: obtaining offline detection data and oil visual data corresponding to a plurality of aging stages of the transformer oil by responding to a modeling request; carrying out pixel classification and labeling on the oil visual data to obtain a classification labeling image; training a preset feature segmentation model by using the offline detection data and the associated feature pair of the classification annotation image to obtain a target feature segmentation model; when the sample data and the sample image of the to-be-detected transformer oil are received, the target feature segmentation model is called to be combined with the quantitative weight, and the aging grade of the to-be-detected transformer oil is determined. Therefore, the machine learning method is applied to realize the identification of the aging characteristics of the transformer oil and the judgment of the aging grade, and the aging characteristics can be identified and judged more comprehensively and more accurately in a mode of combining the aging characteristic detection indexes and the visual images.

The invention relates to the field of visual inspection in the disc part assembling process, and provides a method for detecting in-place installation of double interlocking pieces of disc parts based on a collaborative robot. The method specifically comprises the steps that firstly, a robot moves to the position over a servo assembly base, a short-focus lens camera is adopted to integrally photograph a disc part, a hole position deviation angle alpha is calculated according to 16 fixing hole positions distributed in the circumferential direction, and the servo assembly base is controlled to automatically rotate by the deviation angle alpha; as the angle positions of the circumferential fixing holes of the disc parts are in one-to-one correspondence with the angle positions of the double interlocking pieces, the sampling positions of the double interlocking pieces are fixed by rotating the deviation angle alpha; a robot is moved to a sampling position at the circumferential edge of a disc part, and a telephoto lens camera is adopted to irradiate the position of a double-interlocking piece, so that a group of complete double-interlocking piece image acquisition is realized; complete image acquisition of eight groups of double-interlocking sheets in the circumferential direction is realized by controlling the servo assembly seat to rotate in a circle in an eight-indexing manner; by labeling and training various lock plate sample conditions, whether the double interlocking plates of the disc parts are installed in place or not is judged.

The invention relates to the technical field of medical equipment management, in particular to a medical equipment management system based on artificial intelligence, which comprises a calling acquisition module, an information acquisition module, a medical equipment management module, a medical equipment management module and a medical equipment management module, and is characterized in that the calling acquisition module is used for acquiring calling application information, warehouse position coordinates and equipment inventory information of medical equipment warehouses in hospitals; the information acquisition module is used for acquiring regional information and equipment calling records of a hospital and also used for periodically acquiring equipment information after medical equipment is called out of a warehouse, and the position analysis module is used for analyzing equipment use departments and equipment position parameters; the operation analysis module is used for analyzing the equipment operation parameters; the historical analysis module is used for analyzing the historical operation parameters; the score analysis module is used for analyzing the score of the user; and the equipment management module is used for managing the calling of the medical equipment according to the calling application information, the equipment inventory information and the user score. According to the invention, accurate management of medical equipment calling is realized.

The invention belongs to the field of construction risk comprehensive evaluation and prediction, and provides a deep shaft typical construction risk comprehensive evaluation and prediction method. Comprising the steps of obtaining a water inrush characteristic value, a rockburst index characteristic value and a heat damage characteristic value, constructing a water inrush index matrix, calculating a water inrush index weight, matching a water inrush risk grade, calculating a rockburst index weight, calculating an attribution degree, matching the rockburst risk grade, calculating heat damage heat dissipating capacity data, matching the heat damage risk grade and controlling signal lamps. According to the method, through the water inrush risk grade, the rockburst risk grade and the heat damage risk grade, comprehensive evaluation and prediction of construction risks and autonomous classification of risk degrees are realized, and the accuracy and reliability of risk prediction are improved.

The invention provides a method, a system, equipment and a medium for evaluating the curative effect of Parkinson's disease, and relates to the technical field of medical care informatics. Through comprehensive analysis of motion state data and physiological parameters, gait variation coefficients are generated, and through establishment of calibration coefficients, multiple physiological indexes can be fully utilized, so that the curative effect of Parkinson's disease is evaluated. Dynamic adjustment and judgment on the gait stability of the patient are realized; the implementation of the method is helpful for realizing a more efficient and more personalized treatment scheme in clinical practice, obviously improving the optimization ability of a DBS stimulation strategy, not only being helpful for reducing the dyskinesia performance of a patient, but also improving the life quality of the patient.

The invention relates to a water leakage detection method and device, a water purifier, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring historical water consumption data of a target water consumption area; determining normal water consumption parameters of the target water consumption area in any water consumption time period in the future according to the historical water consumption data; wherein the normal water consumption parameter is used for representing the water consumption condition of the target water consumption area when water leakage does not occur; acquiring real-time water consumption data of the target water consumption area; and detecting whether water leakage occurs or not according to the water consumption time period of the real-time water consumption data and the normal water consumption parameters corresponding to the water consumption time period. Through the technical scheme provided by the invention, the normal water consumption parameters for water leakage detection are combined with the historical water consumption data to determine and reflect the actual water consumption condition, the defects that a traditional detection scheme depends on a fixed threshold value and is difficult to adapt to complex and changeable water consumption scenes are overcome, and the accuracy of water leakage detection is improved.

The present invention proposes a multi-factor special fund reporting overdue prediction method, system, medium and equipment, which belongs to the technical field of fund reporting progress supervision. The method obtains historical project information and a complete reporting path containing node information, extracts time-series evaluation factors including node status, reporting deadline, and fund amount, inputs the trained LSTM model element fusion features, and uses the element fusion features to train and optimize the overdue prediction model to minimize the loss. Subsequently, the current project information is obtained, the element fusion features are extracted and input into the model, the current project reporting path and nodes are predicted, the reporting time is calculated according to the node position, and compared with the warning threshold to realize overdue judgment and warning. The present invention overcomes the problems of difficulty in real-time monitoring, management and supervision of special fund reporting, and low prediction accuracy, and effectively improves the efficiency and accuracy of special fund reporting management.

The invention discloses a reactor core basket pre-tightening state degradation prediction method and device and a medium, and the method comprises the steps: building a statics model of a core basket structure and a core basket modal analysis model for a nuclear power plant core basket based on statics analysis and prestress modal analysis technologies; based on a reactor core hanging basket modal analysis model, obtaining a mapping relation between a reactor core hanging basket pre-tightening state degradation state and a reactor core hanging basket structure vibration response characteristic; constructing a reactor core hanging basket vibration characteristic trend prediction model according to the historical reactor core hanging basket vibration characteristic change data, and obtaining the prediction trend of the reactor core hanging basket vibration characteristics; and obtaining a prediction trend of the pre-tightening degradation state of the reactor core hanging basket according to the historical vibration characteristic change data of the reactor core hanging basket and the prediction trend of the vibration characteristics of the reactor core hanging basket in combination with the mapping relation. According to the method, the accurate change rule of the pre-tightening degradation state of the reactor core hanging basket can be predicted, and a foundation is laid for construction of a subsequent nuclear power key equipment health management system.

The invention discloses an indoor bicycle parking device, which comprises a horizontal pulley track, a front tire and a rear tire, the first clamping mechanism is arranged on the horizontal pulley track in a sliding manner and is used for clamping a rear wheel of the bicycle; the vertical pulley track is vertically connected to one end of the horizontal pulley track and is used for limiting a front wheel of the bicycle; the second clamping mechanism is arranged on the vertical pulley track in a sliding mode and used for clamping a front wheel of the bicycle; each of the first clamping mechanism and the second clamping mechanism comprises two clamping jaws and a clamping driving device used for driving the two clamping jaws to perform butt clamping action, and the clamping jaws are of arc-shaped rod structures and are used for being attached to the inner side face of a tire rim; the front wheel and the rear wheel are stably fixed through the synergistic effect of the second clamping mechanism and the first clamping mechanism, and deviation and shaking of the wheels in the bicycle lifting process are prevented; and the clamping jaws of the arc-shaped rod structures can be matched with the shape of a bicycle hub, so that the clamping stability is improved.

The utility model discloses an IOT (Internet of Things) circuit breaker aging test device, which comprises a Hall element arranged on an IOT circuit breaker and connected with a main circuit board of the IOT circuit breaker; the controller and the electromagnetic component are arranged on the aging table; wherein the controller is connected with the electromagnetic component and is used for sending a power-on instruction to the electromagnetic component and controlling the electromagnetic component to generate an electromagnetic signal in a specific direction, the Hall element outputs a trigger signal to the main circuit board for reading and judging after sensing the electromagnetic signal, and the controller controls the type of the electromagnetic signal. And switching of the Internet of Things circuit breaker between the aging mode and the normal working mode is realized. A Hall element is arranged on a circuit breaker of the internet of things, an electromagnetic component is arranged on an aging table, the controller controls the electromagnetic component to be powered on, an aging mode is started after a specific electromagnetic signal is received, a main circuit board reads and judges, signal transmission and judgment are achieved, and an aging test method is achieved conveniently without damaging the appearance structure.

The present application relates to the technical field of electrical equipment fault prediction, in particular to an electrical equipment fault prediction method and system based on digital twinning; the method comprises the following steps: obtaining equipment basic data, acquisition node configuration data, excitation configuration data and segmentation rule data of a target electrical equipment, constructing a healthy digital twin, establishing local constraint parameters, generating an encoded excitation sequence and a benchmark echo constraint set; collecting echo response data to form an echo response sequence, performing piecewise corresponding alignment and local correction search to obtain a minimum correction set and determine a sensitive constraint axis; generating a single-step misplacement compression sequence based on the sensitive constraint axis, obtaining compression echo response data and generating a compression minimum correction set; comparing the compression minimum correction set with the minimum correction set to determine a fault critical preposition state and output a predicted fault result. The present application realizes preposition identification of electrical equipment implicit local deterioration state and accurate determination of fault critical preposition state.

The invention discloses a method, system and device for judging the stability condition of a grid-following type converter, a medium and a product, and relates to the technical field of power grid detection, and the method comprises the steps: determining the initial value of each state variable based on each operation data after a power grid breaks down; based on the initial value of each state variable, solving the fourth-order nonlinear transient model within a preset time period after the initial prediction moment according to a preset time step, and obtaining a prediction value of each state variable at each prediction moment within the preset time period; drawing a power angle time-varying curve of the grid-following type converter based on the predicted value of the power angle of the grid-following type converter at each prediction moment; the transverse axis of the power angle time-varying curve of the following grid type converter is the prediction moment, and the longitudinal axis is the prediction value of the power angle of the following grid type converter; and based on the power angle time-varying curve of the grid-following type converter, determining the stability condition of the grid-following type converter in a preset time period. According to the invention, judgment of the stability condition of the grid-following type converter is realized.

The application belongs to the technical field of ferromagnetic part testing, and discloses a magnetic performance testing device and testing method for magnetic materials. The testing device comprises a testing table, which is provided with a plurality of testing holes and a sample placing hole. A proximity sensor and a testing block are arranged in the testing hole, and the testing block is an iron core block. A pressure sensor is arranged above the testing block. The testing device further comprises an analysis system, and data received by the proximity sensor and the pressure sensor is transmitted to the analysis system. The testing method comprises the following steps: placing a sample block to be tested into a limiting sleeve, placing a moving part on a fixed part, aligning the sample placing hole with the testing hole, transmitting data received by the proximity sensor and the pressure sensor to the analysis system, and completing the testing of the magnetic force intensity of the sample block to be tested; rotating the moving part to make the sample placing hole communicate with the testing hole, and judging the magnetic pole of the sample block by the approach or departure of the sample block and a standard magnetic part. The application can complete the testing of the magnetic performance by the attraction between the sample to be tested and the testing block.

The present invention relates to the field of construction engineering, and specifically to a construction engineering construction supervision system based on big data analysis, which is used to solve the problems of low efficiency, untimely information and inaccurate data in traditional construction engineering construction supervision methods, resulting in low precision and efficiency of construction engineering construction supervision, affecting construction efficiency, reducing quality level, and even construction risks; the system includes a construction environment supervision module, a construction information analysis module, a construction abnormality judgment module, a safe construction supervision module and a construction equipment supervision module; the system adopts the Internet of Things technology to realize the real-time collection and transmission of construction site data, improves the real-time and accuracy of data, and uses big data analysis technology to deeply mine and analyze the construction environment and equipment status, improves the precision and efficiency of supervision, improves construction efficiency and quality level, ensures project quality, reduces construction costs, and improves user experience.

The invention discloses a process for identifying microscopic damage of granite mineral components, and belongs to the technical field of rock mineral damage determination and characterization. The method comprises the following steps: manufacturing a mineral slice, and carrying out identification analysis based on equipment such as a polarizing microscope, a scanning electron microscope and an energy disperse spectroscopy in sequence, determining the element composition of mineral components through the polarizing microscope, determining the element composition of mineral components through the scanning electron microscope, and determining the element composition of mineral components through the energy disperse spectroscopy. According to the method, the section morphology, namely the microscopic destruction mode of the area, is determined through a scanning electron microscope, and the mineral components of the specific area are determined through an energy disperse spectroscopy, so that the microscopic destruction mode of the mineral components is determined in the whole process. The method not only fills the blank of mineral component microscomic failure mode identification, but also provides a new direction for exploring the rock failure mode.

The present application provides a power transmission line hidden nest detection method, system, device and storage medium, to solve the problem that the existing nest detection cannot accurately determine whether the insulator and the nest are located at the same depth, and it is difficult to define ordinary nests and hidden nests, and relates to the technical field of deep learning. Including: acquiring the power transmission line image to be detected shot by the unmanned aerial vehicle inspection; inputting the power transmission line image to be detected into the pre-trained nest detection model for identification; the nest detection model adopts the yolov8 model framework, and the original bounding box regression loss function of the yolov8 model framework is replaced by the EIOU loss function; output the identification result. The method can combine the advantages of target detection and depth estimation model, and realize high-precision discrimination of hidden nests. Through the coordinate relationship, the nests located above the insulator are screened out as hidden nest candidates, and then whether the insulator and the nest are in the same depth range is judged according to the depth map, realizing the discrimination of hidden nests.

This invention belongs to the field of measurement technology, particularly the field of radio orientation technology, and specifically relates to a marine radio wave navigation and positioning system and method, comprising: a powered lifebuoy, on which a first radio positioning device is mounted; a second radio positioning device, adapted to be worn by a person who has fallen into the water; the first radio positioning device and the second radio positioning device are adapted to transmit radio signals to each other, and the first radio positioning device is configured to determine the distance and relative positional relationship between the first radio positioning device and the second radio positioning device based on the received radio signals; the invention achieves the determination of the position between the powered lifebuoy and the person who has fallen into the water, and then generates a path based on the position between the two to facilitate the movement of the powered lifebuoy toward the person who has fallen into the water.

The application discloses a resource visualization method, device and system based on pipeline optical cable management, relates to the technical field of optical cable data analysis, and solves the problem that pipeline optical cable maintenance resources cannot be visually adjusted based on vibration sensitivity. The method comprises the following steps: calculating the theoretical attenuation of optical signals in the pipeline optical cable according to the length and the bending radius; analyzing whether the pipeline optical cable is a vibration-sensitive optical cable according to the change trend of the attenuation deviation value and the vibration amplitude; dividing the analysis time period into different maintenance interval time periods according to different maintenance times, and calculating reference vibration data of the vibration-sensitive optical cable; constructing a maintenance judgment interval, and calculating the actual vibration data of the vibration-sensitive optical cable in the maintenance judgment interval; and judging whether the vibration-sensitive optical cable needs to be maintained in advance according to the reference vibration data and the actual vibration data. The application realizes the visual adjustment of pipeline optical cable maintenance resources based on vibration sensitivity.

The utility model discloses a low power circuit integration junction box, including casing, modular interface array, embedded control module and safety protection module, wherein, the modular interface array contains at least three kinds of specifications test terminal, and each test terminal is connected with the measured circuit board through the elastic contact, embedded control module contains microprocessor, programmable signal generator and AD conversion unit. In addition, the low power circuit integration junction box still includes power module and wireless communication module. The utility model provides junction box through using S3C2451 embedded control processor to realize the automatic measurement and judgement of low power point fast, and can save the various measurement parameters of detected through programmable signal generator and AD conversion unit, then through wireless communication module carries out data transmission, and the convenient implementation detection result inquiry and transmission have improved the detection efficiency, and the detection result also has higher measurement accuracy and good repeatability.

The invention relates to a method for detecting ridge line breakage in a crystal pulling process, a detection device using the method and electronic equipment, and adopts the technical scheme that an image to be detected in a monocrystalline silicon equal-diameter process is obtained, and the image to be detected is processed by using a line breakage detection model; and detecting whether a broken line exists in the area where the monocrystalline silicon ridge line is located in the image to be detected through the sample label representing whether the broken line exists in the area where the monocrystalline silicon ridge line is located in the image to be detected of the broken line detection model, and forming broken line alarm information for alarming. The broken line detection method has the advantages that the broken line detection model with the machine learning model capability is used for learning the broken line characteristics of the ridge line, whether the broken line occurs on the single crystal silicon ridge line or not can be rapidly detected through the broken line detection model, and therefore the broken line detection efficiency of the single crystal silicon ridge line is improved.

The invention belongs to the technical field of measurement, in particular to the technical field of radio orientation, and particularly relates to a maritime radio wave navigation positioning system and method, and the system comprises a power life buoy which is provided with a first radio positioning device; the second radio positioning device is suitable for being worn on a person falling into water; the first radio positioning device and the second radio positioning device are suitable for transmitting radio signals to each other, and the first radio positioning device is configured to judge the distance and the relative position relation between the first radio positioning device and the second radio positioning device according to the received radio signals; the position between the power life buoy and the person falling into water is judged, and then the path is generated according to the position between the power life buoy and the person falling into water, so that the power life buoy moves towards the person falling into water.

The invention relates to the field of electric power thermal power generating unit operation control, in particular to an electric power thermal power generating unit operation method. Screening basic data in the historical operation data according to the stability data, then selecting a plurality of groups of data with the maximum total relevancy according to the total relevancy among the groups of basic data to obtain standard data, and then performing working condition division on the standard data according to variable types and variable data to obtain a plurality of first working conditions; then, abnormal standard data are removed through a Gaussian mixture model to obtain a third working condition, so that an operation parameter library is established according to the third working condition, and operation parameters of all devices are configured according to the current working condition of the electric power thermal power generating unit; the problem that in the prior art, redundant data in the obtained operation data of all the devices are difficult to accurately screen out, so that when the operation parameter library is automatically generated and updated to control operation of all the devices in the electric power thermal power generating unit, preset requirements are difficult to meet is solved.

The invention belongs to the field of identification, classification and safety management of dangerous chemicals, and particularly relates to a solid treatment device and a solid oxidability testing method. The device comprises a working box, and a grinding assembly, a sieve plate assembly and a collecting assembly which are sequentially arranged in the working box from top to bottom. The grinding assembly is constructed to be capable of grinding solids into solid particles and pouring the solid particles onto the sieve plate assembly, the sieve plate assembly is constructed to be capable of screening the solid particles, and the collecting assembly is constructed to be capable of collecting screened solid samples. According to the device, the controllability degree of factors such as granularity and humidity of a solid sample prepared when the solid is subjected to an oxidability test is improved, so that the accuracy, the precision and the test efficiency of a solid oxidability test result are improved.

The invention provides a method for early warning monitoring of interference of power cables to railway signal cables based on point cloud array, which belongs to the technical field of power cables, including setting a number of sampling points, collecting the cable spacing and influencing current at the sampling points, calculating the induced voltage, and dividing the collected data into two groups according to whether there is a train passing by during sampling; the two groups of collected data are respectively established with the cable spacing as the x-axis, the influencing current as the y-axis, and the induced voltage as the z-axis, and a three-dimensional coordinate system is established, and the data corresponding to each group of sampling data is marked in the three-dimensional coordinate system, one group forms a dynamic point cloud array, and the other group forms a static point cloud array; the point cloud array is fitted to obtain the corresponding fitting surface; the two groups of fitting surfaces are placed in the same coordinate system for comparison to determine whether there are hidden danger features, and if hidden danger features appear, an alarm is issued. The method can dynamically judge the influence of power cables on signal cables and accurately grasp the safety hazards.