1287 results about "Insulation resistance" patented technology

The invention discloses a photovoltaic inverter insulation resistance intelligent detection system and method, and particularly relates to the technical field of photovoltaic equipment operation safety monitoring, and the method comprises the following steps: generating frozen window shielding interference data through collecting a bus voltage in a state transition stage and constructing a dynamic convergence model; identifying an abnormal trend based on resistance derivative change in a stable state, inputting a dual-path decision process by combining environment and power grid parameters, and dynamically outputting an operation state level; control strategies such as remote prompt, power drop adjustment or output disconnection are executed according to the state grade, and accurate identification and grading response control of the insulation state are achieved; according to the invention, by constructing a voltage disturbance shielding mechanism, a trend derivative identification and delay confirmation strategy and a double-path safety state decision process with dynamic switching capability, high accuracy of insulation abnormity judgment, stability of trend identification and adaptability of a decision strategy are realized, and robustness and application range of a detection system are improved.

The invention discloses an insulation detection method for an electric automobile, belongs to the technical field of high-voltage safety monitoring of the electric automobile, and solves the problem that the insulation detection precision is reduced due to electromagnetic interference, impedance fluctuation and capacitive effect coupling in a dynamic load switching process. According to the scheme, a test sequence of discrete frequency points is applied to a high-voltage system; measuring a response current value through a current sensor and calculating a ground distributed capacitance value; connecting a test voltage source between positive and negative electrodes of the high-voltage system through a coupling circuit; applying a first pulse signal during no-load, dynamically setting the width according to the capacitance value, measuring a first response current value, and calculating an initial insulation resistance value; a second pulse signal with the same parameter is applied in the load state window, a second response current value is measured, and differential filtering is carried out in combination with the initial value to eliminate load noise; and comparing the filtered insulation resistance value with a threshold value, and outputting a fault signal when the insulation resistance value is lower than the threshold value. The method is used for monitoring the insulation state of the high-voltage system in real time and accurately early warning faults.

The invention relates to a low-voltage motor insulation resistance online monitoring and early warning method, system and device and a medium. The method comprises the following steps: firstly, acquiring multi-dimensional operation data through a data acquisition link to form an original monitoring data set; preprocessing the original monitoring data set, and focusing core information through dimension reduction processing to obtain a key parameter set; and then inputting the key parameter set into a dynamic correlation model constructed based on a long short-term memory network, and outputting a prediction result of the variation trend of the insulation resistance value along with time and the deterioration degree quantification. And finally, carrying out early warning analysis based on a prediction result, and generating early warning fault features in combination with a real degradation judgment process. According to the method, the insulation resistance trend and the degradation degree are accurately predicted, the defect of insufficient real-time performance of off-line detection is overcome, the accuracy and the pertinence of fault early warning are improved, and equipment shutdown and safety risks caused by insulation faults are effectively reduced.

The invention belongs to the technical field of low-voltage switch cabinet operation control, and particularly discloses an intelligent low-voltage switch cabinet system based on a building intelligent function, which comprises an operation sensing module, a spatial topology module, a fusion diagnosis module, a fault positioning module and a dynamic protection module, current and insulation resistance are synchronously detected at a circuit wiring terminal of the low-voltage switch cabinet, temperature and humidity distribution data of the surrounding environment are collected, and then coupling characteristics between the current and temperature rise are fused. And carrying out visual display of coupling and time sequence correlation in the built three-dimensional heat-electricity correlation topological graph in the switch cabinet by utilizing the time sequence correlation between the insulation resistance and the humidity change, so as to realize comprehensive identification of potential faults. According to the method, the sensitivity and the accuracy of fault identification are effectively improved, early fault symptoms such as poor contact and insulation degradation can be found earlier, the early warning capability of the system is enhanced, and the safety and the stability of operation of the switch cabinet are guaranteed.

The invention belongs to the technical field of electrical safety, and particularly discloses an insulation resistance intelligent detection system and method for an energy storage converter, and the system is based on a bridge balance structure, integrates a temperature and humidity sensor and a voltage sensor, and collects environment parameters and bridge unbalance signals in real time. A digital potentiometer and a resistor array are driven through a PID algorithm to dynamically adjust bridge balance, and environmental interference is eliminated in combination with a temperature and humidity compensation model; and carrying out intelligent analysis on the preprocessed multi-dimensional data by utilizing a band-pass filtering and detection model, and outputting a high-precision insulation resistance value. The method achieves full-automatic detection, is high in precision, is quick in response, is suitable for complex working conditions, and remarkably improves the reliability of the insulation performance evaluation of the energy storage converter.

The invention discloses a water pump motor fault detection method and system, and belongs to the technical field of detection, and the method comprises the steps: building an electrical operation state model based on current, voltage and three-phase balance degree, and outputting an electrical state coefficient; predicting a resistance degradation trend by using the historical winding / insulation resistance data set, and generating a resistance prediction coefficient; combining the electrical state, the amplitude under the load and the flow of the water pump to construct a vibration-flow matching coefficient; fusing the resistance prediction coefficient, the noise index and the temperature index, and outputting a fault evaluation coefficient through a fault evaluation model; and when the fault evaluation coefficient exceeds a threshold value, shutdown is triggered. The system correspondingly comprises an electrical analysis module, a resistance prediction module, a state evaluation module and a fault decision module. According to the invention, early fault accurate detection is realized by fusing multiple parameters, and the reliability of the water pump motor is improved.

The invention discloses an insulation resistance and capacitance measuring circuit and method based on monopulse double-edge analysis, and relates to the related field of the electrical insulation online monitoring technology, and the circuit comprises a detected object and an insulation detection circuit. The insulation detection circuit comprises a controlled pulse voltage source, a coupling resistance network, a current sensor, a switch control module, a signal modulation circuit and a processor. The measurement method implemented based on the circuit comprises the following steps: injecting a common-mode voltage pulse into a transmission line of the power transmission system by adopting a pulse transmitter; pulse current response is collected in real time, a current oscillogram is drawn, and a three-point sampling method is introduced to record a current value for insulation impedance parameter calculation; according to a load condition, a double-edge verification method is applied based on a pulse current attenuation characteristic, and insulation impedance parameters including a resistive component and a capacitive component are independently calculated by analyzing a pulse current rising edge and a pulse current falling edge. According to the invention, non-intrusive synchronous monitoring of resistive and capacitive components of line-to-ground impedance is realized, and the detection precision is improved.

The invention discloses a comprehensive management system for intelligent power distribution, and the system comprises a sensing layer which is provided with a plurality of sensors, the sensors are disposed on power distribution equipment, and are used for collecting the operation data of a power distribution system in real time, and the operation data comprise a current I, a voltage U, a power P, an equipment temperature T, a power factor cos phi, and an insulation resistance R; the transmission layer is used for transmitting the operation data to a data layer; the data layer is used for preprocessing the operation data to generate standardized data, and preprocessing comprises data cleaning and normalization conversion; and the application layer comprises a fault early warning module, a predictive maintenance module, an energy consumption analysis module and a remote control module, and the application layer realizes collaborative management by calling the standardized data. Multi-dimensional data fusion, a dynamic intelligent algorithm and a module interaction mechanism are introduced, and full-process intelligence of power distribution management is achieved.

The invention relates to the technical field of power electronics, in particular to a direct-current charging pile insulation monitoring method and system, and the method comprises the following steps: monitoring the voltage deviation between a branch and a bus in real time, adjusting a measurement compensation parameter, correcting a branch insulation resistance measurement value, recognizing leakage current drift, positioning a leakage branch, triggering relay control, and sending alarm information. And generating a charging pile monitoring record. According to the method, the branch voltage deviation trend and the voltage compensation parameters are combined, the branch voltage measurement consistency is improved, the insulation resistance fluctuation is utilized to compare and correct the observation error, the measurement precision is optimized, the current deviation compensation in the no-load state is adopted to eliminate the zero drift interference of the sensor, and the measurement accuracy is improved. A current jump amplitude and a voltage direction are combined to identify an electric leakage branch, positioning accuracy is enhanced, a relay control and event information linkage mode is used, alarm response and equipment state records form a closed loop, and real-time performance and integrity of system monitoring are improved.

The invention discloses a square lithium ion battery external insulation damage detection method, system, medium and equipment, and the method comprises the steps: carrying out the electrochemical impedance spectrum measurement of a square battery with an external insulation state to be detected, and obtaining an electrochemical impedance spectrum; building an equivalent circuit based on the electrochemical impedance spectrum to obtain each characterization electrical element parameter in the equivalent circuit; high-frequency insulation resistance and interface capacitance in the equivalent circuit are extracted, and the damage condition of the outer insulation film of the square lithium ion battery is detected through parameter differences.

The invention relates to the technical field of on-line monitoring, in particular to an insulation fault on-line monitoring method and system for a medical IT system control cabinet. The method comprises the following steps: selecting a non-integer frequency multiplication detection frequency according to equivalent ground distributed capacitance in a previous monitoring period, and superposing the non-integer frequency multiplication detection frequency with a fundamental frequency to form a composite signal injection system; collecting signals to calculate a voltage instantaneous harmonic distortion rate change gradient, and selecting a time window to split the leakage current according to the change gradient; on the basis of dispersion estimation signal-to-noise ratio weighted fusion current vectors, insulation resistance and distributed capacitance are calculated; constructing a four-dimensional original feature vector composed of the insulation parameter, the phase difference and the intermodulation component energy; constructing a diagonal weighting matrix based on the resistance-capacitance ratio and the gradient to transform a feature vector, and determining the fault attribution through the Mahalanobis distance calculation with the fault template library. According to the scheme, harmonic interference can be avoided, calculation stability can be improved, insulation instantaneous sudden change can be quickly responded, and different fault types can be accurately distinguished to guide maintenance.

The invention relates to the field of lightning arrester parameter measurement, in particular to a lightning arrester parameter measurement system and method.The lightning arrester parameter measurement system comprises an induction unit, a detection unit, a data processing unit and a control and positioning unit and is used for generating and focusing laser on the surface of a lightning arrester, collecting an electrical signal and an optical signal of plasma and sending the electrical signal and the optical signal to a processor; the feature quantity is obtained through a feature extraction algorithm, and core parameters of the inversion lightning arrester are calculated through mechanical learning. Plasma is generated through laser focusing, reduction of errors caused by direct electrical connection and contact resistance with a lightning arrester is avoided, the problems of potential safety hazards and interference of traditional contact type measurement are solved, laser focus global scanning, real-time dynamic monitoring and efficient measurement are achieved through the three-dimensional electric translation platform, and the measurement precision is improved. All key areas on the surface of the lightning arrester are covered, compared with single parameter inversion in the prior art, multiple parameters and microscopic parameters are considered, and the prediction precision of key core parameters such as insulation resistance based on the random forest model is further improved.

The invention belongs to the technical field of power distribution switches, and particularly discloses a test mechanism suitable for a switch cabinet handle, which comprises a substrate, the upper end of the substrate is fixedly connected with a plurality of support frames, the upper ends of the support frames are fixedly connected with a support plate, and the upper end of the support plate is provided with a transmission groove. A rotating assembly used for rotating the handle is arranged on the base plate corresponding to the transmission groove, a detection assembly used for detecting the insulation state of the rotating handle is arranged on the side, close to the rotating assembly, of the supporting plate, and when the handle rotates along with the second square rod, the first square rod, the transmission block and the trigger protruding block are driven to rotate synchronously. The trigger bump can instantly extrude the micro-touch switch, the power supply module and the resistance detector are started, through a detection loop formed by a lead, insulation resistance changes of the connection part of the handle and the square rod under the action of mechanical friction and stress in the rotation process are accurately captured, dynamic insulation data of the handle are captured, and an electrical property detection test of the handle is realized.

The invention relates to the technical field of cable fault positioning, in particular to a cable fault accurate positioning method based on multi-channel synchronous acquisition, which comprises the following steps: S1, constructing a multi-channel adaptive acquisition system which comprises a main controller, a multi-channel acquisition module, a synchronous control module and a data transmission module; s2, multi-channel data synchronous acquisition is carried out through the synchronous control module, wherein the multi-channel data comprises impedance data, temperature data, partial discharge signals and insulation resistance data; during use, through a multi-channel adaptive acquisition design, monitoring channels can be flexibly selected according to cable materials, operation years and environmental conditions, different aging fault characteristics are comprehensively covered, the fault omission ratio and the false alarm rate are reduced, different types of low-voltage cables are adapted, a synchronous scheme of constant-temperature crystal oscillator and hardware triggering is adopted, and the reliability of the system is improved. The method does not need to depend on a GPS / PTP time service module, is favorable for saving cost input, and eliminates environmental interference and single parameter false triggering.

The invention discloses a detection circuit and a calculation method for insulation resistance in a strong induced electricity environment, and relates to the technical field of insulation resistance measurement. The detection circuit for the insulation resistance in the strong induced electricity environment comprises a current sampling module, an induced electricity processing module and a data calculation module, the induced electricity processing module is used for removing interference of induced electricity, and the current sampling module is used for sampling a dynamic current value of the insulation resistance of a direct current system. According to the detection circuit and the calculation method for the insulation resistance in the strong induced electricity environment, the detection speed and accuracy of the insulation resistance of a direct-current system for a transformer substation in the induced electricity environment are superior to those of a traditional test technology. According to the method, the insulation resistance of the direct current system for the transformer substation in the induced electricity environment can be quickly calculated on the premise of accuracy, and the method has the characteristics of short response time, high robustness and relatively strong anti-interference capability to external induced electricity.

The invention, which belongs to the technical field of the direct-current charging pile, provides a direct-current charging pile rapid detection diagnosis debugging system comprising a detection host, a multi-channel data acquisition module, an electric energy quality analysis module, an insulation resistance test module, a grounding resistance test module, a communication protocol analysis module, a temperature monitoring module and a fault simulation module. Parallel data acquisition is realized by adopting 16 independent analog signal acquisition channels and 8 digital signal acquisition channels, a parallel processing unit matched with the number of detection channels is started by utilizing a CUDA flow technology, preliminary fault screening is carried out at a GPU end through a rapid shallow model, and a layered diagnosis mechanism of accurate fault analysis is carried out at a CPU end through a deep model. And in combination with the charging pile fault identification model, real-time monitoring of the operation state of the charging pile and accurate identification and positioning of the fault are realized, and the technical problems of low real-time processing efficiency of multi-channel data and insufficient fault diagnosis accuracy are solved.

The invention provides a photovoltaic system and an insulation resistance detection method thereof, the photovoltaic system comprises a plurality of photovoltaic modules, a plurality of low-voltage switches, a plurality of high-voltage switches and a detection control circuit, the low-voltage switches are connected with one or more photovoltaic modules to form a second photovoltaic module, and the high-voltage switches are connected with the detection control circuit. The high-voltage switches are connected with one or more second photovoltaic modules which are connected in parallel, and the detection control circuit is connected with the low-voltage switches and the high-voltage switches, controls the high-voltage switches to be turned off in sequence, controls the corresponding low-voltage switches to be switched to a second switch state, determines the faulted first photovoltaic module according to the insulation resistance of the photovoltaic system, and ends the operation. The method does not need to employ a mode of manually plugging and unplugging the string or changing the voltage of the string, can achieve the detection of all fault assemblies, improves the detection precision, and improves the detection range.

The invention provides an energy recovery type intelligent charging pile. The energy recovery type intelligent charging pile comprises a charging pile body, a charging module, a control module, an insulation monitoring module, a fault early warning module, an energy recovery module and an active repairing module. The insulation resistance value of the charging cable is monitored in real time through the insulation monitoring module; a multi-stage processing mechanism including early warning, power reduction charging and circuit breaking is triggered through a fault early warning module according to the comparison data; when the fault triggering data comprises triggering power reduction or circuit breaking, residual electric energy in a charging loop is stored through an energy recovery module; the active repair module generates a high-voltage pulse with a preset peak frequency by using the electric energy stored by the energy recovery module, and performs physical repair on an insulation damaged part of the charging cable. Through real-time sensing of the insulation monitoring module, intelligent decision making of the fault early warning module, closed-loop management of the energy recovery module and physical intervention of the active repair module, early warning and active repair are carried out on the insulation fault of the charging cable, and the usability of the charging pile is improved.

The embodiment of the invention relates to the technical field of data processing, and provides a cable insulation and loop detection method and a related device, and the method comprises the steps: inputting a reference test voltage to a to-be-detected object; acquiring a current signal flowing through the to-be-detected object to which the reference test voltage is applied; determining an initial insulation resistance value according to the reference test voltage and the current signal; obtaining correction environment parameters of the to-be-detected object; generating target correction information according to the correction environment parameters; and correcting the initial insulation resistance value by using the target correction information to obtain a target insulation resistance value, thereby improving the accuracy of performing cable insulation and loop detection on the to-be-detected object.

The invention discloses a processing process fault prediction method for essential oil production, and relates to the technical field of essential oil processing, and the method comprises the steps: constructing an environment equipment coupling model, and drawing an electrical equipment insulation resistance attenuation curve through a salt mist deposition experiment; environment disturbance variables are introduced into the generative adversarial network, and an anomaly detector capable of recognizing salt spray corrosion characteristics and humidity condensation characteristics is trained; capturing time-space correlation between temperature mutation and quality fluctuation through a self-attention mechanism; calculating a probability density function of the residual service life of the equipment in real time, and automatically correcting a temperature over-limit threshold value based on the residual service life distribution; calculating the contribution degree of each node to the fault through intervention simulation; and constructing a digital twinborn model containing thermodynamic and hydrodynamic characteristics. Through environment dynamic modeling, causal reasoning and digital twinning methods, the key problems of low fault prediction precision, poor traceability efficiency and lack of quantitative support in decision making in essential oil production are solved.

The invention discloses a transformer substation secondary equipment fault detection platform and an analysis method. The platform comprises a mobile bearing unit, an instrument integration unit, an integrated power supply and safety protection unit, an image acquisition unit and a data fusion analysis unit. The platform carries a relay protection tester, a mutual inductor comprehensive characteristic tester and an insulation resistance meter in an integrated manner, and is equipped with an image acquisition system, so that convenient movement and multi-source data acquisition of detection equipment are realized. And the data fusion analysis unit adopts a multi-modal fusion deep learning model to carry out collaborative analysis on the electrical detection data and the visual data, and outputs a diagnosis conclusion containing accurate fault positioning and basic causes through feature extraction and fusion. According to the method, the problems of low efficiency and inaccurate diagnosis caused by inconvenient equipment carrying and data isolated analysis in traditional debugging are effectively solved, and the intelligent level, the safety and the reliability of operation and maintenance of the secondary equipment of the transformer substation are remarkably improved.

The invention provides a GIS equipment withstand voltage test system and method, and relates to the technical field of GIS equipment withstand voltage test. Comprising the steps of obtaining parameter information and installation environment data of GIS equipment, constructing a three-dimensional digital twinborn model of the GIS equipment in combination with an electric field simulation engine, generating a withstand voltage test scheme and planning an optimal path. Acquiring partial discharge data and insulation resistance data under different voltage stresses by using an AI noise reduction algorithm according to the optimal path, carrying out multi-modal fusion processing on the partial discharge data and the insulation resistance data, extracting features by using a deep learning model, obtaining insulation defect and performance attenuation data, and carrying out multi-modal fusion processing on the insulation defect and performance attenuation data. And carrying out space mapping association with the three-dimensional digital twinborn model to generate a GIS equipment withstand voltage test evaluation report, thereby providing a powerful basis for equipment operation and maintenance. According to the invention, the three-dimensional digital twinborn model is constructed to generate the GIS equipment voltage withstanding test evaluation report, so that the accuracy of the GIS equipment voltage withstanding test is improved.

The invention discloses an insulation state monitoring system and method for a rotor winding of a pumped storage unit, and relates to the technical field of insulation state monitoring. Electrical performance parameters and environmental parameters of the rotor winding are analyzed, an insulation resistance model is constructed, and the insulation resistance of the rotor winding is output through an insulation resistance model expression; according to the mode, online monitoring of the insulation state can be achieved, meanwhile, the accuracy of insulation state monitoring is effectively improved through multi-parameter coupling analysis, then the monitored insulation state corresponds to fault characteristics of the pumped storage unit, and when the pumped storage unit breaks down, the fault of the pumped storage unit can be monitored. According to the method, fault causes can be accurately positioned, the monitored insulation resistance values are fitted to obtain an insulation state change curve, the insulation deterioration trend is warned in advance, and therefore the sudden fault risk is reduced.

The invention relates to a cable early-stage fault parameter extraction method and system fusing temperature rise process data, and relates to the technical field of cable fault monitoring, and the method comprises the steps: receiving multi-node temperature rise data uploaded by a temperature measurement optical fiber for a to-be-detected cable in a conduction state, comparing the multi-node temperature rise data with a cable rated condition, extracting deviation information with a standard temperature rise curve, and calculating the temperature rise process data of the to-be-detected cable; setting first and second fault characteristic indexes; drawing up a fault parameter extraction atlas in combination with the deviation information and the first and second fault characteristic indexes; and according to the attenuation coefficient, the early fault calorific value under different equivalent insulation resistances is taken as a core association feature, a fault influence range is evaluated, and a dynamic threshold adjustment rule is used for fault reminding. The cable fault detection method solves the problems that in traditional cable fault detection, early fault feature capture is not sensitive, missing detection is prone to occurring, and the fault judgment accuracy is insufficient due to the fact that the cable operation state and environmental factors are not fully combined.

The invention discloses an insulation resistance detection device and an energy storage cabinet, and belongs to the technical field of energy storage, and the device comprises a bridge arm circuit which is connected with a sampling resistor and a change-over switch in series, and is used for carrying out the insulation resistance detection of a battery cluster in a target energy storage cabinet; the control chip is connected with the bridge arm circuit and is used for controlling the sampling resistor and the change-over switch through different switch time sequences so as to trigger the bridge arm circuit to carry out insulation resistance detection on the battery cluster; the isolation ADC circuit is connected with the control chip and used for converting the control signal sent by the control chip into a target digital signal; and the signal conditioning circuit is used for performing signal processing on the target digital signal to obtain a target processing signal so as to assist the control chip to complete insulation resistance detection on the battery cluster by using the target processing signal. By means of the device, the problems that in the prior art, when insulation resistance detection is conducted on the battery cluster, detection precision is poor, and safety is not high can be solved.

The invention belongs to the technical field of electric leakage safety protection, and discloses a remotely controllable electric leakage safety protection plug, which comprises an electric leakage risk preliminary identification module, a magnetic core saturation risk identification module, an advanced electric leakage risk diagnosis module and an abnormal remote difference control module. By setting a magnetic core saturation and electric leakage risk collaborative diagnosis mechanism, parameters such as direct current offset percentage and the like can be analyzed in real time to judge the magnetic core saturation risk, and then the electric leakage risk judgment result is combined to comprehensively identify the operation refusal risk, trigger voltage and current phase analysis and insulation resistance test, so that the electric leakage detection accuracy is improved, and the operation refusal caused by magnetic core saturation is prevented; and the power utilization safety is ensured. By setting a four-stage progressive diagnosis mechanism of preliminary electric leakage identification, magnetic core risk screening, advanced electric leakage risk diagnosis and differential management and control, electric leakage can be accurately identified, magnetic core saturation refusal operation can be prevented, remote intelligent management and control can be realized, and power utilization safety and management efficiency can be improved.

The invention relates to the technical field of power testing, in particular to multifunctional comprehensive test conversion integrated equipment which comprises a conversion integrated device and test instrument connecting line, a conversion integrated device and a multifunctional comprehensive test line. The conversion integration device and test instrument connecting line is used for connecting the conversion integration device and a test instrument; the conversion integrated device is used for quickly adapting to different test instruments and tested equipment and discharging before and after a test; and the multifunctional comprehensive test line is used for connecting the conversion integrated device and the tested equipment. Test items supported by the device are insulation resistance, dielectric loss capacitance, direct current resistance, transformation ratio and demagnetization tests, all power failure routine test items of the transformer can be completed without replacing a test line, the time of the power failure routine test of the transformer and the frequency of high-altitude operation can be obviously reduced, the working efficiency is greatly improved, and the test cost is reduced. And the safety risk in the test operation process is reduced.

The invention relates to the technical field of power grid planning, in particular to a power distribution network dynamic planning system based on digital twinning, which comprises an acquisition module, a simulation module, a first judgment module, a determination module, a second judgment module, an adjustment module, a correction module and an output module. According to the invention, the current and voltage of the equipment and the post-earthquake position offset, inclination angle and insulation resistance value are collected in real time, and the simulation analysis of the digital twin model is combined, so that fault equipment and abnormal equipment can be accurately identified; an acquisition period and a coincidence rate threshold value are dynamically adjusted, monitoring efficiency and accuracy are optimized, a power distribution planning report is generated at the same time, and a scientific basis is provided for optimized operation of the power distribution network; especially in emergency situations such as after an earthquake, quick response and power supply recovery can be realized, the influence of disasters on a power grid is reduced, and the problems of inaccurate monitoring and inflexible planning caused by complex influence of the earthquake and excessive dependence on static parameters are effectively solved.

The invention relates to the technical field of insulation degradation detection, in particular to an insulation characteristic degradation detection method for an underwater wet-plugging electric connector, which is characterized in that a multi-angle appearance image of the connector is acquired through a pressure-resistant underwater camera device, and the image quality and the recognition accuracy are improved by adopting a defogging and color correction technology. And further extracting defect characteristics such as cracks, corrosion and aging on the surface of the connector through an image by virtue of a graph neural network model, realizing automatic identification and positioning of defect types, and then executing a local electrical test on the identified defect region to obtain electrical parameters such as insulation resistance, capacitance value and medium absorption ratio. Image recognition information and electrical test data are constructed into a feature matrix, a fusion evaluation model composed of a logistic regression model and a weighted scoring mechanism is input, an insulation degradation degree value is output, and a detection result is generated, so that the accuracy of insulation detection of the underwater wet-plugging electric connector is improved, and the detection time is effectively shortened.

The invention belongs to the technical field of cross-linked polyethylene insulated cables, and discloses a cross-linked polyethylene insulated cable and a preparation method thereof.The cross-linked polyethylene insulated cable comprises an inner core conductor, an insulating layer and a protective layer which are sequentially arranged from inside to outside; the protective layer is prepared by processing the following raw materials in parts by weight: 60-100 parts of polyethylene, 10-35 parts of epoxy resin, 0.5-3.5 parts of a cross-linking agent, 5-15 parts of polyurethane, 1-5 parts of maleic anhydride, 5-10 parts of rare earth oxide, 0.5-2 parts of an adhesive and 0.1-0.5 part of an initiator. The insulation resistance value of the obtained cross-linked polyethylene insulated cable reaches up to 3000 M omega.km, the tensile strength is 35 Mpa, the elongation at break is 430%, after an aging test, the retention rate of the tensile strength reaches up to 95%, the elongation at break reaches up to 85%, after a wear resistance test, the mass loss is 30 mg / 1000 turns, and the cross-linked polyethylene insulated cable has excellent insulation performance, mechanical performance, wear resistance and aging resistance.