CN-121978470-A - Power supply safety state monitoring and early warning method and system for liquid cooling cable

CN121978470ACN 121978470 ACN121978470 ACN 121978470ACN-121978470-A

Abstract

The invention relates to the technical field of cable states, in particular to a monitoring and early warning method and a system for the power supply safety state of a liquid cooling cable, which construct a temperature zone self-adaptive fusion model system comprising three special monitoring units of ultralow temperature, normal temperature and ultrahigh temperature, adapt to the characteristic parameter differences of the liquid cooling cable and cooling liquid under different working conditions based on definite temperature zone division standards, through the integrated design of the temperature zone self-adaptive fusion model, the multi-source data intelligent processing and the grading linkage protection, the accuracy, the instantaneity and the reliability of the monitoring of the power supply safety state of the liquid cooling cable are remarkably improved, a powerful technical guarantee is provided for the safe and efficient operation of a liquid cooling cable system, and the problem that the traditional power supply safety state monitoring and early warning method of the liquid cooling cable is insufficient in coverage and causes insufficient recognition precision of the built model is solved.

Inventors

ZENG LINGGUO
LI ZHIJUN
PAN XIAOTIAN
ZHANG YONG
WANG YI
TAN WENLI

Assignees

渝丰科技股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260409

Claims (10)

1. The power supply safety state monitoring and early warning method for the liquid cooling cable is characterized by comprising the following steps of: S1, constructing a temperature zone self-adaptive fusion model system, wherein the temperature zone self-adaptive fusion model system comprises three groups of temperature zone dedicated monitoring units which are respectively adapted to ultra-low temperature working conditions, normal temperature working conditions and ultra-high temperature working conditions, each dedicated monitoring unit is integrated with a fusion prediction module, an intelligent decision module and a characteristic dynamic calibration module, and is used for matching characteristic parameters of liquid cooling cables and cooling liquid in different temperature zones based on a multi-source data fusion logic optimization model framework, wherein the ultra-low temperature working conditions correspond to the environment temperature of less than or equal to-25 ℃, the normal temperature working conditions correspond to the environment temperature of-25 ℃ to 40 ℃, and the ultra-high temperature working conditions correspond to the environment temperature of more than or equal to 40 ℃; S2, acquiring full life cycle operation parameters, temperature field actual measurement data and scene specificity data of the liquid cooling cable, constructing a temperature zone exclusive training data set after signal enhancement and feature screening pretreatment, introducing a migration learning mechanism to optimize a model training process, and respectively training and iterative calibration of three groups of temperature zone exclusive monitoring units to obtain a mature monitoring unit meeting preset precision requirements; S3, acquiring the running environment parameters of the liquid cooling cable in real time through a multi-dimensional environment sensing assembly, and automatically matching the special monitoring units of the corresponding temperature areas by a temperature area intelligent switching module in combination with the change trend of the temperature gradient, wherein the full temperature areas are monitored in a non-intermittent self-adaptive manner; S4, acquiring real-time operation data of the liquid cooling cable through a multi-sensor fusion technology, inputting the real-time operation data into a special monitoring unit of a currently-adapted temperature zone, outputting accurate temperature field distribution data through a fusion prediction module, and realizing weak fault signal capturing and sudden working condition diagnosis by an intelligent decision module, wherein a characteristic dynamic calibration module corrects characteristic association weights in real time so as to offset material aging and parameter drift influences; And S5, generating grading early warning information according to the diagnosis result of the exclusive monitoring unit of the temperature zone, triggering corresponding protection actions by the intelligent regulation module of the linked liquid cooling system, and realizing cross-temperature zone monitoring data interaction through a data collaboration mechanism between models.
2. The power supply safety state monitoring and early warning method for the liquid cooling cable according to claim 1 is characterized in that in step S1, the ultra-low temperature working condition is adapted to a cooling liquid viscosity sudden rise and cable terminal interface pressure change scene, the normal temperature working condition is adapted to a conventional fast charging operation scene, and the ultra-high temperature working condition is adapted to a cooling liquid boiling point drop and insulating layer thermal ageing acceleration scene.
3. The power supply safety state monitoring and early warning method of the liquid cooling cable is characterized by comprising an ultra-low temperature exclusive monitoring unit, an ultra-high temperature exclusive monitoring unit, a multi-source sensing data fusion optimization and a normal temperature exclusive monitoring unit, wherein the ultra-low temperature exclusive monitoring unit integrates a cooling liquid viscosity-temperature-pressure correlation model, optimizes a kernel function based on a Kalman filtering-Gaussian process regression fusion algorithm, introduces an interface pressure correction factor to compensate prediction deviation caused by insulation performance attenuation in a low-temperature environment, the ultra-high temperature exclusive monitoring unit is embedded into an insulation layer thermal aging rate prediction module, combines a BM3D image level denoising technology to identify overheat signals, realizes multi-source sensing data fusion optimization through the Kalman filtering-Gaussian process regression fusion algorithm, strengthens local overheat fault prediction capability, and is adaptive to large-scale quick-charge scene deployment by adopting a spectrum coding and lightweight network collaborative architecture to balance monitoring precision and real-time operation efficiency.
4. The method for monitoring and early warning the power supply safety state of the liquid cooling cable according to claim 1 or 3 is characterized in that the full life cycle operation parameters of the liquid cooling cable in step S2 comprise cooling liquid flow, cable core current, terminal interface pressure and environment temperature and humidity, and the scene specific data comprise extreme temperature region characteristic data, burst working condition simulation data, material and aging related data.
5. The power supply safety state monitoring and early warning method of the liquid cooling cable according to claim 4 is characterized in that the extreme temperature region characteristic data comprise a cooling liquid viscosity-pressure coupling curve at ultralow temperature and insulation layer dielectric loss-temperature related data at ultrahigh temperature, the sudden working condition simulation data generate power mutation, instantaneous blockage of a cooling liquid loop and terminal partial discharge scene data through multi-physical field coupling simulation, and are combined with an anti-generation network to expand a scarce fault sample, and the material and aging related data comprise a heat conductivity coefficient attenuation curve of a copper alloy and aluminum composite conductor, an insulation layer aging period parameter and cooling liquid full life cycle performance attenuation data.
6. The method for monitoring and early warning the power supply safety state of the liquid cooling cable according to claim 5, wherein in the step S2, the preprocessing is to eliminate signal noise and frequency drift by adopting an SSA-VMD-MCS algorithm, screen high-correlation and low-redundancy characteristics by improving an mRMR algorithm, migrate similar scene model parameters by combining a migration learning mechanism, and reduce sample dependence.
7. The method for monitoring and early warning the power supply safety state of the liquid cooling cable according to claim 6, wherein the multi-sensing fusion technology in the step S4 comprises an integrated phase-sensitive optical time domain reflection distributed optical fiber sensing technology, an infrared thermal imaging technology and an ultrahigh frequency sensing technology, and is used for synchronously collecting temperature fields, vibration waves, partial discharge and thermal imaging signals and realizing fault location through data level fusion.
8. The method for monitoring and early warning the power supply safety state of the liquid cooling cable according to claim 7, wherein in the step S4, the working mechanism of the characteristic dynamic calibration module comprises the following steps of firstly, establishing a multi-material characteristic database, automatically matching characteristic weights according to cable conductor materials during model initialization, and quickly adapting to different material cable monitoring requirements through migration learning; secondly, based on the correlation degree of the model aging theory real-time monitoring characteristic variable and the temperature field prediction result, triggering automatic calibration when the correlation degree is attenuated to a preset threshold value, iteratively updating the characteristic weight through Kalman filtering, and adaptively adjusting the calibration period according to the operation working condition and the environmental parameter; finally, periodically collecting cable and coolant liquid parameters, constructing a model precision attenuation prediction curve, and recording monitoring data and a calibration process by combining an encryption log; In step S3, the temperature zone intelligent switching module adopts a pre-judging switching logic, and starts the dedicated monitoring unit of the target temperature zone to preheat in advance by combining with the environmental temperature change trend, so as to realize non-perception switching; In step S5, the data collaboration mechanism realizes cross-unit data synchronization by sharing the encrypted database, and abnormal features automatically trigger the adaptation of the early warning threshold of other temperature zone units, so as to realize early warning consistency during temperature zone switching.
9. The method for monitoring and early warning the power supply safety state of the liquid cooling cable according to claim 8 is characterized in that in the step S5, three-level early warning is divided according to the severity of faults, wherein the three-level early warning comprises general early warning, serious early warning and emergency early warning, the general early warning corresponds to fluctuation of charging power and slight abnormality of cooling liquid flow, the serious early warning corresponds to sudden decrease of cooling liquid flow and slow increase of local temperature, the emergency early warning corresponds to local discharge of a terminal and super-threshold of temperature sudden change, and the intelligent regulation module of the linked liquid cooling system under each level triggers protection actions of power-down charging, dynamic regulation of flow and emergency shutdown.
10. The power supply safety state monitoring system of a liquid cooling cable is characterized by being used for realizing the power supply safety state monitoring and early warning method of the liquid cooling cable according to any one of claims 1-9, and the system comprises the following modules: The multidimensional sensing module is integrated with a phase sensitive optical time domain reflection distributed optical fiber sensor, an infrared thermal imaging sensor, an ultrahigh frequency sensor and an environment temperature and humidity sensor, and is used for synchronously collecting a liquid cooling cable temperature field, vibration waves, partial discharge, terminal interface pressure, cooling liquid flow and environment parameters and providing multisource original data for subsequent processing; The temperature zone intelligent switching module is in signal connection with the multidimensional sensing module, receives the environmental temperature and temperature gradient change data, adopts a pre-judging switching logic, and starts a dedicated monitoring unit of a target temperature zone to preheat in advance so as to realize non-sensing self-adaptive switching under the working conditions of ultralow temperature, normal temperature and ultrahigh temperature; The temperature zone self-adaptive fusion model module comprises three groups of temperature zone exclusive monitoring units, wherein each unit integrates a Kalman filtering-Gaussian process regression fusion prediction module, an intelligent decision module and a characteristic dynamic calibration module, and is respectively adapted to different temperature zone working conditions to execute temperature field prediction, burst working condition diagnosis and characteristic weight calibration tasks; The data processing and storing module is used for performing signal denoising and feature screening preprocessing by adopting an SSA-VMD-MCS algorithm and an improved mRMR algorithm, constructing a shared encryption database and storing full life cycle operation data, scene specific data, model training parameters and calibration logs; The intelligent liquid cooling system adjusting module is used as a linkage executing assembly and used for receiving instructions of the grading early warning and linkage control module, accurately adjusting the flow rate and the circulating speed of the cooling liquid and adjusting the charging power in cooperation with the charging system; The hierarchical early warning and linkage control module is used for receiving the diagnosis result of the temperature zone self-adaptive fusion model module, generating early warning information according to an early warning strategy and outputting the early warning information in a visual way, and simultaneously triggering protective actions such as power-down charging, dynamic adjustment of coolant flow, emergency stop and the like according to the early warning level in a linkage way with the intelligent liquid cooling system adjusting module; the edge calculation and communication module is used for deploying a lightweight edge calculation unit, carrying out a model part reasoning task, constructing a stable communication link and realizing data interaction among the modules and information synchronization with a remote operation and maintenance platform.

Description

Power supply safety state monitoring and early warning method and system for liquid cooling cable Technical Field The application relates to the technical field of cable states, and particularly discloses a power supply safety state monitoring and early warning method and system for a liquid cooling cable. Background The new energy automobile gradually replaces the traditional fuel automobile by virtue of the remarkable advantages of low emission, low travel cost, low noise and the like, and occupies an increasingly large market share. However, core pain points such as slow charging speed and low charging efficiency still restrict the key bottleneck that new energy automobiles further permeate, and especially in commercial vehicles and long-distance travel scenes, the quick energy supplementing requirement is more urgent. In order to solve the problem of quick charging, two technical paths are mainly formed in the industry, namely, a whole vehicle voltage platform is improved, charging current is reduced through high voltage, line loss is reduced, and the current transmission capacity of a charging pile is increased, so that charging power is directly improved. However, whatever the path taken, the charging cable is used as the core carrier for energy transfer, and is subject to severe performance challenges. Along with the rise of charging power to hundreds of kilowatts or even megawatts, a large amount of joule heat can be generated in the process of transmitting large current by the cable, if the heat cannot be timely dissipated, the ageing of a cable insulating layer can be accelerated, the service life is shortened, potential safety hazards such as cable burnout, overheat failure of a charging gun, charging pile faults and the like can be possibly caused, even fire accidents are caused in serious cases, and the safety of personnel and property is threatened. Under the background, the liquid cooling high-power charging cable technology is generated, and the liquid cooling high-power charging cable technology becomes a core scheme for solving the problem of high-power charging and heat dissipation. According to the technology, the liquid cooling circulation system is integrated in the cable, the heat generated in the conductive process of the cable is absorbed in real time by utilizing the flowing characteristic of a cooling medium such as special cooling liquid or insulating oil, so that the cable is always maintained in a reasonable working temperature range, the heat damage of heating to each part of a charging link is effectively overcome, and the safety guarantee is provided for high-current and high-power quick charging. Compared with the traditional charging cable, the liquid cooling charging cable has the remarkable advantages of smaller diameter, lighter weight and convenience in wiring operation and carrying by a user on the premise of realizing the same current transmission capability, and meanwhile, due to the integrated design of the cooling and conducting functions, the liquid cooling charging cable can adapt to a long-time high-power charging scene, the charging efficiency and the charging stability are greatly improved, and the liquid cooling charging cable gradually becomes the main technical direction of the quick charging field of new energy automobiles. However, the structural complexity of the liquid-cooled charging cable and the specificity of the working environment make the monitoring of the power supply safety state of the cable to face new challenges, and the conventional monitoring technology has difficulty in adapting to the application requirements of the cable. The safety monitoring of the traditional charging cable focuses on low-frequency signal extraction during abnormal operation, only can realize primary monitoring of serious faults such as overload and short circuit, and has three main core defects that firstly, the abnormal state identification precision is low, the cooling system faults such as leakage of cooling medium, unsmooth circulation and the like of the liquid cooling cable cannot be accurately captured, weak signal changes caused by faults of conducting sides such as local damage of an insulating layer and poor contact of a conducting core body are easily caused, false alarm and missing report phenomena are easily caused, secondly, the fault position early warning time is long, the low-frequency signal response is delayed, the abnormality can be monitored only after the faults are damaged to a certain extent, the early warning and active protection cannot be realized, the high-power and high-reliability application scene of the liquid cooling cable cannot be matched, thirdly, the monitoring dimension is single, the monitoring is only carried out aiming at the state of the conducting core body, the decisive effect of the whole safety of the running stability of the cooling system is ignored, and a collaborative monitoring closed loop cannot be formed. In fact