CN117325699B - Safety monitoring system for liquid cooling and super-charging technology - Google Patents

Safety monitoring system for liquid cooling and super-charging technology Download PDF

Info

Publication number
CN117325699B
CN117325699B CN202311291612.6A CN202311291612A CN117325699B CN 117325699 B CN117325699 B CN 117325699B CN 202311291612 A CN202311291612 A CN 202311291612A CN 117325699 B CN117325699 B CN 117325699B
Authority
CN
China
Prior art keywords
charging pile
degree
use process
dimension
aging
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311291612.6A
Other languages
Chinese (zh)
Other versions
CN117325699A (en
Inventor
吴晓峰
伍刚
单翔
李林
陈琴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Zilong New Energy Technology Co ltd
Original Assignee
Jiangsu Zilong New Energy Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Zilong New Energy Technology Co ltd filed Critical Jiangsu Zilong New Energy Technology Co ltd
Priority to CN202311291612.6A priority Critical patent/CN117325699B/en
Publication of CN117325699A publication Critical patent/CN117325699A/en
Application granted granted Critical
Publication of CN117325699B publication Critical patent/CN117325699B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • B60L53/60—Monitoring or controlling charging stations
    • B60L53/67—Controlling two or more charging stations
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • B60L53/30—Constructional details of charging stations
    • B60L53/302—Cooling of charging equipment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Power Engineering (AREA)
  • Probability & Statistics with Applications (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The invention relates to the technical field of data processing, and provides a safety monitoring system for a liquid cooling and super-charging technology, which comprises the following components: collecting use data of a plurality of charging piles and charging piles to be tested; obtaining a reference charging pile and a non-reference charging pile, and obtaining the aging degree of each using process for the reference charging pile; obtaining correction weight values among using processes of different reference charging piles, and matching the aging degrees of the different reference charging piles according to the correction weight values to obtain a standard aging change curve; obtaining the aging degree of each non-reference charging pile in each use process, clustering the use processes according to the aging degree, and completing the construction of a dynamic model of the charging pile to be tested for temperature; and (3) performing Kalman filtering on the dynamic model to complete temperature monitoring and early warning of the charging pile to be tested. The invention aims to solve the problem that the monitoring result is inaccurate due to inaccurate dynamic model caused by excessive factors affecting equipment in the process of monitoring the equipment temperature through Kalman filtering.

Description

Safety monitoring system for liquid cooling and super-charging technology
Technical Field
The invention relates to the technical field of data processing, in particular to a safety monitoring system for a liquid cooling and super-charging technology.
Background
The liquid cooling super-charging technology is used as a high-efficiency and rapid charging mode, and becomes an important solution mode for slower charging process of equipment such as new energy electric vehicles; however, because the liquid cooling system involves links such as high-temperature cooling and the like and has a certain safety risk, developing a safety monitoring system to ensure the safety of the liquid cooling overcharge technology becomes an important research direction; in the liquid cooling and super-charging technology, the temperature is one of the important factors affecting the safety of the system, and because a large amount of heat is generated in the high-power charging process, when the liquid cooling system can not effectively reduce the temperature, the cable or other components can be overheated, so that serious consequences such as fire disaster or equipment failure are caused; therefore, the temperature of the liquid cooling and super-charging system needs to be monitored in real time, so that the safety and the application of the equipment are ensured.
In the process of monitoring the temperature, the traditional method predicts the temperature of the equipment through Kalman filtering, so that the real-time monitoring of the temperature is realized, the temperature prediction needs to acquire the temperature change process of the equipment, the temperature change is a nonlinear process, and meanwhile, factors affecting the temperature of a cable and a charging gun in a liquid cooling and super-charging system are more and more complex, so that the temperature prediction and monitoring are directly carried out according to the temperature acquired by a temperature sensor in the system, the construction of a dynamic model of the system is inaccurate, and the condition estimation of the equipment is not matched with the actual condition, so that an estimation error is generated, and the accuracy and reliability of a temperature monitoring result are reduced.
Disclosure of Invention
The invention provides a safety monitoring system for a liquid cooling overcharge technology, which aims to solve the problem that a monitoring result is inaccurate due to inaccurate dynamic model caused by excessive factors affecting equipment in the existing process of monitoring equipment temperature through Kalman filtering, and adopts the following specific technical scheme:
one embodiment of the present invention provides a safety monitoring system for liquid cooling and overcharge technology, the system comprising:
the charging data acquisition module acquires use data of a plurality of dimensions of each use process of a plurality of charging piles and charging piles to be detected, and corresponding time of each use process, wherein the use data of the plurality of dimensions comprises equipment temperature data, charging amount data, charging power data, current data, voltage data and environmental temperature data;
the dynamic model building module: according to the voltage data and the charging power data of each charging pile in each use process, acquiring the reference degree of each charging pile and obtaining a reference charging pile and a non-reference charging pile; according to the change of the charge quantity and the charge power in each use process of the reference charging pile and the reference degree, the aging degree of each use process of each reference charging pile is obtained;
Clustering the use data of the same dimensionality in all the use processes of different reference charging piles, and acquiring correction weight values between the use processes of any two different reference charging piles according to clustering results; performing DTW matching on aging degree change curves of different reference charging piles according to the correction weight values to obtain standard aging change curves;
according to the standard aging change curve and the usage data of multiple dimensions of each usage process of each charging pile, the aging degree of each usage process of each non-reference charging pile is obtained; clustering all charging piles according to the aging degree in the using process, and constructing a dynamic model of the charging piles to be tested for temperature;
and the temperature monitoring and early warning module is used for completing the temperature monitoring and early warning of the charging pile to be tested by carrying out Kalman filtering on a dynamic model of the temperature of the charging pile to be tested and combining the actually acquired temperature data.
Further, the specific method for obtaining the reference degree of each charging pile and obtaining the reference charging pile and the non-reference charging pile includes the following steps:
for any use process of any charging pile, acquiring the average value of voltage data of the use process, and recording the average value as the use voltage of the use process; acquiring the variance of the charging power data in the using process, and recording the variance as the power fluctuation degree in the using process; acquiring the use voltage and the power fluctuation degree of each charging pile and each use process of the charging pile to be tested; reference degree alpha of ith charging pile i The calculation method of (1) is as follows:
；
wherein J is i Indicating the number of using processes of the ith charging pile, u i,j Representing the voltage used by the jth course of use of the ith charging stake,representing the average value of the voltages used in all the use processes of all the charging piles, and sigma (u) represents the standard deviation, delta, of the voltages used in all the use processes of all the charging piles i,j Indicating the power fluctuation degree of the jth use process of the ith charging pile, +.>Mean value of power fluctuation degree of all charging piles in all using processes, sigma (delta) is standard deviation of power fluctuation degree of all charging piles in all using processes, and +.>Representing the minimum value of the two ratios obtained by adding and subtracting respectively, ||represents the absolute value, exp { } represents an exponential function based on a natural constant;
obtaining the reference degree of each charging pile, taking the charging pile with the reference degree larger than the reference threshold value as a reference charging pile, and taking the charging pile with the reference degree smaller than or equal to the reference threshold value as a non-reference charging pile; and taking the charging pile with the largest number of using processes as a reference charging pile.
Further, the aging degree of each reference charging pile in each use process is specifically obtained by the following steps:
for any use process of any reference charging pile, removing the use process and recalculating the reference degree of the reference charging pile, wherein the obtained result is recorded as the heart-removing reference degree of the reference charging pile in the use process; recording a period of time with continuous unchanged charging power data in the using process as a period of stable time in the using process, accumulating the charging quantity data in the stable time as accumulated charging quantity of the stable time, recording the time length of the stable time, and obtaining a plurality of periods of stable time in the using process and accumulated charging quantity and time length of each period of stable time; obtaining the coring reference degree of each reference charging pile in each use process, a plurality of stable time periods in each use process, and the accumulated charge quantity and the time length of each stable time period;
The g used of the h reference charging pileDegree of aging ε of the process h,g The calculation method of (1) is as follows:
;
wherein beta is h,g Representing the coring ratio of the g using process of the h reference charging pile, wherein the coring ratio is the ratio of the coring reference degree to the reference degree of the reference charging pile; f (beta) h,g ) A mapping value representing a decorrelation ratio of a g-th use process of the h-th reference charging pile, wherein if the decorrelation reference degree is greater than the reference degree, the mapping value is a sum of 1 and the decorrelation ratio; if the coring reference level is less than the reference level, the mapping value is 1 minus the difference of the coring ratio; n (N) h,g The number of segments representing the stabilization time in the g-th use process of the h reference charging pile T h,g Representing the duration of the g-th use of the h-th reference charging pile,representing the remaining time of the h reference charging pile in the g using process, wherein the remaining time is obtained by subtracting the sum of the time lengths of all the stabilizing times from the duration of the using process; t is t h,g,n Representing the time length, w, of the nth stabilization time in the g-th use process of the h reference charging pile h,g,n Representing the accumulated charge amount of the nth stable time in the g-th use process of the h reference charging pile, exp () representing an exponential function based on a natural constant;
The aging degree of each use process of each reference charging pile is obtained.
Further, the method for obtaining the correction weight value between the using processes of any two different reference charging piles according to the clustering result comprises the following specific steps:
for any one reference charging pile, arranging the aging degrees of all the using processes of the reference charging pile according to the sequence of the using processes to obtain an aging degree sequence of the reference charging pile; for any use process and any dimension of the reference charging pile, taking the average value of all use data of the dimension in the use process as the data value of the use process in the dimension; acquiring an aging degree sequence of each reference charging pile and a data value of each use process of each reference charging pile in each dimension;
according to the aging degree sequence and the data value of each reference charging pile in each dimension in each using process, a first weight value of any two different reference charging piles in each dimension in the using process and a second weight value of each reference charging pile in each dimension are obtained;
for any two different using processes of the reference charging piles, taking the average value of the second weight values of the dimension in the two reference charging piles as the third weight value of the two using processes in the dimension, obtaining the third weight value of the two using processes in each dimension, and carrying out weighted summation on the first weight values of the two using processes in each dimension according to the third weight value, wherein the obtained sum value is recorded as the correction weight value of the two using processes; and acquiring correction weight values between the using processes of any two different reference charging piles.
Further, the method for obtaining the first weight value of any two different reference charging piles in each dimension and the second weight value of each reference charging pile in each dimension includes the following specific steps:
for any dimension, clustering data values of all the reference charging piles in the dimension in all the using processes, and marking each cluster as a category in the obtained clustering result; for the use process of any two different reference charging piles, if the data values of the two use processes in the dimension belong to the same category, setting the first weight value of the two use processes in the dimension asWherein->Representing the absolute value of the difference between the data values of the two usage processes in this dimension, d max Representing the maximum of all distances; if two using processesThe data values in the dimension do not belong to the same category, and the first weight value of the two using processes in the dimension is set to 0; acquiring a first weight value of any two different reference charging piles in each dimension in the using process;
for any dimension and any reference charging pile, arranging data values of all using processes of the reference charging pile in the dimension according to the sequence of the using processes to obtain a data change sequence of the reference charging pile in the dimension, and obtaining a pearson correlation coefficient of the data change sequence and an aging degree sequence; acquiring pearson correlation coefficients of a data change sequence and an aging degree sequence of each dimension of the reference charging pile, and carrying out softmax normalization on all pearson correlation coefficients, wherein the obtained result is used as a second weight value of each dimension in the reference charging pile; and acquiring a second weight value of each dimension in each reference charging pile.
Further, the method for obtaining the standard aging change curve comprises the following specific steps:
arranging the reference charging piles according to the sequence of the reference degree from large to small, and marking the reference charging piles as a reference sequence; obtaining an aging degree change curve of each reference charging pile; performing DTW matching on the aging degree change curve of each reference charging pile and the aging degree change curve of the next adjacent reference charging pile in the reference sequence, and adjusting the Euclidean distance between the using processes in the DTW matching process through correcting the weight value to obtain a matching result between the adjacent reference charging piles in the reference sequence;
obtaining the reference charging piles with the largest using process number in all the reference charging piles, and marking the reference charging piles as standard charging piles; updating the aging degree of each use process of the reference charging piles with the minimum reference degree in the two reference charging piles according to the sequence from the large reference degree to the small reference degree, acquiring an updated aging change curve and continuously updating the next adjacent reference charging pile in the reference sequence until the updated aging change curve of the standard charging pile is acquired;
Correcting the aging degree of each use process of the reference charging pile with the largest reference degree in the two reference charging piles according to the sequence from the smaller reference degree to the larger reference degree, acquiring a corrected aging change curve, and continuously correcting the adjacent previous reference charging pile in the reference sequence until the corrected aging change curve of the standard charging pile is acquired;
and (3) averaging the updated aging change curve and the corrected aging change curve of the standard charging pile, wherein the obtained result is used as the standard aging change curve.
Further, the method for obtaining the aging degree of each non-reference charging pile in each use process comprises the following specific steps:
according to the standard aging change curve and the data value of each charging pile in each dimension in each using process, obtaining the difference weight value of each non-reference charging pile and each using process of the charging pile to be tested; for any one use process of any non-reference charging pile, acquiring the use process of the same ordinal number of the use process in a standard aging sequence, recording as a reference process of the use process, adding the sum of the difference weight values to 1, and taking the product of the sum of the difference weight values and the aging degree of the reference process of the use process as the aging degree of the use process;
And obtaining the aging degree of each non-reference charging pile and each using process of the charging pile to be tested.
Further, the specific obtaining method of the differential weight value of each non-reference charging pile and each using process of the charging pile to be tested is as follows:
obtaining a standard aging change curve through DTW matching according to the aging degree change curve of the reference charging pile, and combining the reference degree of the reference charging pile to obtain reference data of each use process in each dimension in the standard aging sequence;
for any non-reference charging pile, acquiring a data value of each non-reference charging pile in each dimension in each using process, and acquiring a second weight value of each dimension in the non-reference charging pile; for any one use process and any one dimension of the non-reference charging pile, obtaining a difference value obtained by subtracting reference data of a reference process in the dimension from a data value of the use process in the dimension, marking the difference value as a deviation degree of the use process in the dimension, and obtaining an absolute value of the difference value as a difference degree of the use process in the dimension; obtaining the deviation degree and the difference degree of each use process of the non-reference charging pile in the dimension, carrying out linear normalization on all the difference degrees, adding a negative sign to the normalized value if the deviation degree is smaller than 0, and if the deviation degree is larger than or equal to 0, not adjusting the normalized value, and recording the adjusted normalized value as a difference coefficient of each use process of the non-reference charging pile in the dimension; obtaining a difference coefficient of each use process of the non-reference charging pile in each dimension;
For any use process of the non-reference charging pile, carrying out weighted summation on the difference coefficient of the use process in each dimension according to the second weight value of the non-reference charging pile in each dimension, and taking the obtained result as the difference weight value of the use process; and obtaining the differential weight value of each non-reference charging pile and each using process of the charging pile to be tested.
Further, the specific method for obtaining the reference data of each usage process in each dimension in the standard aging sequence includes:
obtaining a standard aging sequence and a plurality of using processes of the standard aging sequence according to the standard aging change curve; for any one use process in the standard aging sequence, acquiring the use process, and recording the use process of all the reference charging piles participating in updating or correcting the aging degree of the use process in the process of acquiring the standard aging change curve by DTW matching as a matching process of the use process; carrying out softmax normalization on the reference degrees of all the reference charging piles, and taking the obtained result as a matching weight value of each reference charging pile;
for any dimension, acquiring data values of the dimension in all matching processes, carrying out weighted summation on the acquired data values according to the matching weight values of the reference charging piles corresponding to the matching processes, and recording the obtained result as reference data of the using process in the dimension; reference data in each dimension for each usage procedure in the standard burn-in sequence is obtained.
Further, the method for constructing the dynamic model of the charging pile to be tested for temperature comprises the following specific steps:
acquiring corresponding time for each use process of each charging pile; constructing a coordinate system by taking the aging degree as an abscissa and the corresponding time as an ordinate, converting all using processes of all charging piles into coordinate points in the coordinate system, and clustering all the coordinate points to obtain a plurality of clusters;
for any use process of the charging pile to be tested, acquiring a cluster where a coordinate point corresponding to the use process is located, and taking the average value of data values of the use processes corresponding to all coordinate points except the coordinate point corresponding to the use process in the cluster in the dimension of equipment temperature data as correction temperature data of the use process; and acquiring correction temperature data of each use process of the charging pile to be measured, and arranging according to the sequence of the use processes to obtain a correction temperature change curve of the charging pile to be measured, and marking the correction temperature change curve as a dynamic model of the charging pile to be measured for temperature.
The beneficial effects of the invention are as follows: the invention provides a method for adaptively acquiring a dynamic model of a system, which ensures an accurate temperature monitoring result acquired by Kalman filtering; the invention expects to acquire an accurate Kalman filtering dynamic model, wherein the dynamic model is characterized by the change of temperature along with time, the standard aging change curve of the charging pile is acquired, the standard aging change curve is adaptively adjusted according to the acquired use data of different use processes of the charging pile, the aging degree of each use process of each charging pile is further obtained, the equipment temperature data of each use process of the charging pile to be detected is corrected according to the clustering result by combining the aging degree with the corresponding time, namely the use process that the aging degree is similar to the corresponding time of the use process of the charging pile to be detected is acquired in the charging pile, the corrected temperature data is further obtained, and the dynamic model of the charging pile to be detected for the temperature is obtained in a quantification mode; the problem that the temperature data are corrected under the condition that the influence factors of equipment are more and complex is guaranteed, the problem that a dynamic model is inaccurate due to the interference of other influence factors in the traditional Kalman filtering process, and then the temperature is predicted and monitored inaccurately is solved, so that the temperature monitoring of the charging pile of the liquid cooling super-charging technology is more accurate, and accurate early warning is performed.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a block diagram of a security monitoring system for a liquid cooling and overcharge technology according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a block diagram of a security monitoring system for liquid cooling and overcharge technology according to an embodiment of the invention is shown, where the system includes:
The charging data acquisition module 101 acquires the use data of each use process of the charging piles and the charging piles to be tested of a plurality of liquid cooling super-charging technologies.
The purpose of the embodiment is to construct a dynamic model according to the temperature change of each use process of the charging pile, predict the temperature through Kalman filtering, compare with the temperature data obtained in practice according to the predicted value, and realize the temperature monitoring and early warning of the charging pile of the liquid cooling super-charging technology; it is therefore necessary to acquire several usage data of each usage process of the charging pile to be detected and several usage data of each usage process of the same model of charging pile first.
Specifically, in this embodiment, the charging pile to be detected is recorded as a charging pile to be detected, where the time from factory delivery to current use of the charging pile to be detected is described by taking two years as an example, and a plurality of usage data of each usage process of the charging pile to be detected is obtained, where the usage data includes a plurality of types of data, each type of data is used as data of one dimension, and the usage data in this embodiment includes equipment temperature data, that is, temperature data of a charging cable of the charging pile; the method comprises the steps of collecting charge quantity data, charging power data, current data, voltage data and environmental temperature data through a temperature sensor, wherein the two types of temperature data can be directly obtained through a charging pile, the sampling time interval of data in each dimension is 1 second, and meanwhile, corresponding time is obtained for each use process, and the fact that the corresponding time is required to obtain a month range and year is not required to obtain because the environmental temperature data are involved is required; the data of multiple dimensions of each use process of the charging pile to be tested are obtained; according to the method, after a plurality of charging piles of the same type as the charging pile to be tested are obtained from factory to two years of use, the data of multiple dimensions of each use process and the time corresponding to each use process are obtained, wherein two years are described as an example of the embodiment, an implementer can set the time range of the use process of the charging piles of the same type according to the use time of the charging pile to be tested, and the embodiment obtains 20 charging piles of the same type to carry out subsequent analysis.
So far, the use data of a plurality of charging piles and each use process of the charging piles to be tested are obtained.
Dynamic model building module 102:
it should be noted that, in this embodiment, it is expected to obtain an accurate kalman filtering dynamic model, where the dynamic model represents a change of temperature with time, and due to excessive and complex factors affecting equipment, the dynamic model of the system obtained in the process of processing the kalman filtering algorithm is inaccurate, that is, the obtained change process of temperature with time is inaccurate; in order to obtain an accurate time-dependent temperature change relationship, however, since the temperature change is affected by a plurality of factors, a plurality of clustering results are obtained by clustering the use process, and each cluster is analyzed to obtain the time-dependent temperature change process in each use process. In the clustering process, if the clustering is inaccurate only according to the temperature data, because the corresponding environmental temperature data have differences, and the aging degree of the equipment is different along with the increment of the use process of the charging pile and the difference of the charging amount and the charging power in each use process, the corresponding temperature data are different; therefore, the aging degree of the equipment is quantified, clustering is carried out according to the aging degree and the time corresponding to the using process, and a dynamic model of the charging pile to be tested for temperature is constructed through the temperature change of each using process in the clusters.
(1) According to the voltage data and the charging power data of each charging pile in each use process, the reference degree of each charging pile is obtained, the reference charging pile and the non-reference charging pile are obtained according to the reference degree, and according to the change of the charging quantity and the charging power of each reference charging pile in each use process, the aging degree of each reference charging pile in each use process is obtained by combining the reference degree.
It should be noted that, with the increment of the use process of the charging pile and the difference of the charging amount and the charging power in each use process, the aging degree of the device is different, that is, the increment aging degree is increased along with the use process; the aging degree is quantified according to the change of the charging amount and the charging power of each using process; meanwhile, for the quantification of the aging degree, the reliability of corresponding use data is lower due to the fact that the use process of some charging piles is not operated properly or is influenced by other factors, namely the use data is possibly generated in a non-normal use process, so that a normal reference charging pile is required to be obtained for the analysis of the subsequent aging degree, and the reference degree of each charging pile is required to be obtained; the reference degree is quantified according to the voltage change and the charging power difference in the using process of the charging pile.
Specifically, for any one use process of any charging pile, acquiring the average value of voltage data of the use process, recording the average value as the use voltage of the use process, and simultaneously acquiring the variance of charging power data of the use process, recording the variance as the power fluctuation degree of the use process; obtaining the using voltage and the power fluctuation degree of each charging pile and each using process of the charging pile to be tested according to the method, taking the ith charging pile as an example, and the reference degree alpha of the charging pile i The calculation method of (1) is as follows:
；
wherein J is i Indicating the number of using processes of the ith charging pile, u i,j Representing the voltage used by the jth course of use of the ith charging stake,representing the average value of the voltages used in all the use processes of all the charging piles, and sigma (u) represents the standard deviation, delta, of the voltages used in all the use processes of all the charging piles i,j Indicating the power fluctuation degree of the jth use process of the ith charging pile, +.>Mean value of power fluctuation degree of all charging piles in all using processes, sigma (delta) is standard deviation of power fluctuation degree of all charging piles in all using processes, and +.>The minimum value of the two ratios obtained by adding and subtracting are represented, absolute value is represented, exp { } represents an exponential function based on a natural constant, the inverse proportion relation and normalization processing are represented by adopting exp { - } function, and an implementer can set an inverse proportion function and a normalization function according to actual conditions;
The reference degree is obtained through quantification by using the voltage and power fluctuation degree, meanwhile, the range of the fluctuation degree of the voltage or the power is quantified by means of the mean value and the standard deviation, the ratio is obtained, the closer the ratio is to 1, the closer the fluctuation degree of the voltage or the power is to the fluctuation degree of the voltage or the power in a normal state, the larger the corresponding reference degree is, and the combination is carried out on the quantification value of the voltage or the quantification value of the power fluctuation degree through L2 norm, so that the mean value is obtained on the combination value of all the using processes, and the reference degree is finally obtained; meanwhile, along with the increment of the using process, the larger the fluctuation degree allowed for the range of the normal state is, namely, the standard deviation of mean addition and subtraction is limited through the duty ratio of the sequence value and the total number of the using process, so that the ratio is obtained, and the ratio is compared with 1; according to the method, the reference degree of each charging pile is obtained, a reference threshold value is preset, the reference threshold value of the embodiment is described by adopting 0.68, the charging pile with the reference degree larger than the reference threshold value is used as the reference charging pile, and the charging pile with the reference degree smaller than or equal to the reference threshold value is used as the non-reference charging pile; and if the reference degree of the charging pile (including the charging pile to be measured) with the largest using process number is smaller than or equal to the reference threshold value, the charging pile is also used as the reference charging pile.
Further, for any use process of any reference charging pile, removing the use process and recalculating the reference degree of the reference charging pile, and recording the obtained result as the heart-removing reference degree of the reference charging pile in the use process; meanwhile, for the using process, corresponding charging power data and charging quantity data exist in each second, a period of time when the charging power data are continuously unchanged is recorded as a period of stable time of the using process, the charging quantity data in the stable time are accumulated and recorded as accumulated charging quantity of the stable time, and meanwhile, the time length of the stable time is recorded, and a plurality of periods of stable time of the using process and accumulated charging quantity and time length of each period of stable time are obtained; the coring reference degree of each use process of each reference charging pile, a plurality of stable time periods in each use process, and the accumulated charge quantity and the time length of each stable time are obtained according to the method.
Further, taking the g-th use process of the h reference charging pile as an example, the aging degree epsilon of the use process h,g Is of the meter(s)The calculation method comprises the following steps:
;
wherein beta is h,g The center removing ratio of the g using process of the h reference charging pile is represented, wherein the center removing ratio is the ratio of the center removing reference degree to the reference degree of the reference charging pile, and the ratio is obtained by a small value to a large value; f (beta) h,g ) A mapping value representing a coring rate of a g-th use of the h-th reference charging pile, wherein if the coring reference level is greater than the reference level, the use indicates that the reference level is reduced by the use process, i.e., improper use exists, resulting in an increase in aging level, and the mapping value is 1 plus the sum of the coring rate; if the decoring reference degree is smaller than the reference degree, the using process is normal, the aging degree needs to be reduced, and the mapping value is 1 minus the difference of the decoring ratio;
wherein N is h,g The number of segments representing the stabilization time in the g-th use process of the h reference charging pile T h,g The duration of the g use process of the h reference charging pile is indicated, and the duration can be directly obtained according to the use process, which is not described in detail in this embodiment;representing the remaining time of the h reference charging pile in the g using process, and subtracting the sum of the time lengths of all the stable times from the duration of the using process; t is t h,g,n Representing the time length, w, of the nth stabilization time in the g-th use process of the h reference charging pile h,g,n Representing the accumulated charge amount of the nth stage of stable time in the g use process of the h reference charging pile, exp () representing an exponential function based on a natural constant, wherein the exp (-) function is adopted to represent inverse proportion relation and normalization processing, and an implementer can set the inverse proportion function and the normalization function according to actual conditions; for each stable time in the using process, the larger the accumulated charge amount is, the larger the time length is, the smaller the influence on the aging degree is, the smaller the corresponding aging degree is, and the time length of the stable time is The duty ratio of the duration of each use process is taken as a weight to quantify the influence of the stabilization time on the aging degree; meanwhile, for the residual time, the residual time represents a period of unstable charging power, and the larger the proportion of the duration, the larger the influence on the aging degree and the larger the aging degree are; and obtaining the aging degree of each use process of each reference charging pile according to the method.
Thus, a plurality of reference charging piles and the aging degree of each use process in each reference charging pile are obtained.
(2) Obtaining an aging degree change curve of each reference charging pile according to the aging degree, clustering a plurality of use data of each use process of different reference charging piles, obtaining correction weight values among the use processes of different reference charging piles according to a clustering result, and matching the aging degree change curves of different reference charging piles according to the correction weight values to obtain a standard aging change curve.
After the aging degree is obtained, an aging degree change curve is obtained for each reference charging pile, and the standard aging change curves are obtained through DTW matching and fusion of the different aging degree change curves and are used for carrying out cluster analysis on the aging degree of the charging pile to be tested subsequently; in the DTW matching process, as the data of a plurality of dimensions corresponding to each using process have differences, euclidean distances among data points in the DTW matching process are adjusted according to the differences, and then the DTW matching is completed.
Specifically, for any reference charging pile, arranging the aging degrees of all the using processes of the reference charging pile according to the sequence of the using processes to obtain an aging degree sequence of the reference charging pile, and simultaneously obtaining an aging degree change curve of the reference charging pile; and obtaining an aging degree sequence and an aging degree change curve of each reference charging pile according to the method.
Further, for any dimension, taking the average value of all the use data of the dimension in each use process of each reference charging pile as the data value of each use process in the dimension, and obtaining the average value of all the use data of all the reference charging pilesClustering is carried out on the data values of the dimension by using a process, wherein the distance between the data values adopts the absolute value of the difference value between the data values, the clustering method adopts K-means clustering, wherein the K value is described by adopting 5 in the embodiment, and each cluster in the obtained clustering result is marked as a category; for the use process of any two different reference charging piles, if the data values of the two use processes in the dimension belong to the same category, setting the first weight value of the two use processes in the dimension asWherein->Representing the absolute value of the difference between the data values of the two usage processes in this dimension, d max Representing the maximum of all distances; if the data values of the two using processes in the dimension do not belong to the same category, setting the first weight value of the two using processes in the dimension to be 0; acquiring a first weight value of any two different reference charging piles in the dimension in the using process according to the method; and acquiring a first weight value of the use process of any two different reference charging piles in each dimension.
Further, for any one dimension and any one reference charging pile, arranging data values of all the using processes of the reference charging pile in the dimension according to the sequence of the using processes to obtain a data change sequence of the reference charging pile in the dimension, and obtaining a pearson correlation coefficient of the data change sequence and the aging degree sequence; acquiring pearson correlation coefficients of a data change sequence and an aging degree sequence of each dimension of the reference charging pile, and carrying out softmax normalization on all pearson correlation coefficients, wherein the obtained result is used as a second weight value of each dimension in the reference charging pile; and acquiring a second weight value of each dimension in each reference charging pile according to the method.
Further, for any two different using processes of the reference charging piles, taking the average value of the second weight values of the dimension in the two reference charging piles as the third weight value of the two using processes in the dimension, obtaining the third weight value of the two using processes in each dimension, and carrying out weighted summation on the first weight values of the two using processes in each dimension according to the third weight value, wherein the obtained sum value is recorded as the correction weight value of the two using processes; and obtaining the correction weight value between the using processes of any two different reference charging piles according to the method.
Further, arranging the reference charging piles according to the sequence from the large reference degree to the small reference degree, and marking the reference charging piles as a reference sequence; performing DTW matching on the aging degree change curve of each reference charging pile and the aging degree change curve of the next adjacent reference charging pile in the reference sequence, and adjusting the Euclidean distance between the using processes in the DTW matching process through correcting the weight value to obtain a matching result between the adjacent reference charging piles in the reference sequence; obtaining the reference charging piles with the largest using process number in all the reference charging piles, marking the reference charging piles as standard charging piles, and correcting the aging degree change curve of the standard charging piles to obtain a standard change curve; in the correction process, correction is carried out according to a matching result, a plurality of corresponding relations exist in the matching result, the corresponding relations comprise one-to-one, one-to-many and many-to-one, the corresponding relations are expressed according to the reference degree from big to small, for two adjacent reference charging piles with the reference degree more than or equal to that of a standard charging pile, if the corresponding relations are one-to-one or many-to-one, the average value of the aging degrees of all the using processes in the corresponding relations is given to the corresponding using process of the reference charging pile with the minimum reference degree in the two reference charging piles, and the updating of the aging degree of the using process is completed; if the corresponding relation is one-to-many, the aging degree of each using process in the reference charging pile with the minimum reference degree in the two reference charging piles in the corresponding relation is averaged with the corresponding aging degree in the corresponding relation, and the aging degree of each using process is updated through the average; and updating the aging degree of each use process in the two adjacent reference charging piles with the reference degree larger than or equal to the reference degree of the standard charging pile according to the sequence from large to small, obtaining an updated aging change curve of the reference charging pile with the minimum reference degree in the two adjacent reference charging piles, continuously updating the next adjacent reference charging pile according to the updated aging change curve, and updating by combining the matching result until the updated aging change curve of the standard charging pile is obtained.
Further, according to the sequence from the small reference degree to the large reference degree, correcting the aging degree of each use process in the two adjacent reference charging piles with the reference degree smaller than or equal to the standard charging pile and with the largest reference degree, wherein the correction process is the same as the updating process, the difference part is the aging degree of the use process of the reference charging pile with the smallest reference degree, the aging degree of the use process of the reference charging pile with the largest reference degree is given, the other parts are the same, a corrected aging change curve is obtained, the adjacent previous reference charging pile in the reference sequence is continuously corrected according to the corrected aging curve, and the correction is carried out by combining the matching result until the corrected aging change curve of the standard charging pile is obtained; and (3) averaging the updated aging change curve and the corrected aging change curve of the standard charging pile, wherein the obtained result is used as the standard aging change curve.
Thus, a standard aging change curve is obtained, which is used for representing the change of the aging degree of the normal use process.
(3) According to the standard aging change curve and the use data of each use process of each charging pile, the aging degree of each use process of each non-reference charging pile is obtained, the use processes are clustered according to the aging degree, the correction temperature data of each use process of the charging pile to be tested is obtained, and the construction of the dynamic model of the charging pile to be tested for temperature is completed.
It should be noted that, because the non-reference charging pile has an abnormal use process, the aging degree change curve of the non-reference charging pile needs to be obtained through the standard aging change curve, so as to obtain the aging degree of each charging pile (including the charging pile to be tested), clustering is performed through the aging degree, and the correction temperature data of each use process of the charging pile to be tested is obtained according to the clustering result, so that the construction of the dynamic model of the temperature is completed.
Specifically, for a standard aging change curve, the abscissa is the use process, the ordinate is the aging degree, and the ordinate is extracted to obtain a standard aging sequence; meanwhile, for any one use process in the standard aging sequence, acquiring all the use processes of the reference charging piles which participate in updating or correcting the aging degree of the use process in the process of acquiring the standard aging change curve by DTW matching, and recording the use processes as the matching process of the use process (comprising the use process per se), namely updating or correcting according to the corresponding relationship, and acquiring all the corresponding relationship finally related to the use process and all the use processes included in the corresponding relationship; the method comprises the steps of carrying out softmax normalization on the reference degree of all reference charging piles, obtaining a result as a matching weight value of each reference charging pile, for any dimension, obtaining a data value of the dimension in all matching processes, namely, obtaining a mean value of each using process in each dimension in the step S003, carrying out weighted summation on the obtained data value according to the matching weight value of the reference charging pile corresponding to the matching process, and recording the obtained result as reference data of the using process in the dimension, wherein the number of the matching processes obtained by each reference charging pile is possibly one or more, and for one data value, directly participating in weighted summation, and for the data values of a plurality of matching processes, firstly solving a mean value of the data values of a plurality of matching processes of the reference charging piles, and then carrying out weighted summation according to the matching weight values; the reference data of each usage process in each dimension in the standard aging sequence is obtained according to the method.
Further, for any non-reference charging pile, acquiring a data value of each non-reference charging pile in each dimension in each using process according to the calculating method in the step S003, and acquiring a second weight value of each dimension in the non-reference charging pile according to the calculating method in the step S003; for any one use process of the non-reference charging pile, acquiring the use process of the use process with the same ordinal number in a standard aging sequence, marking the use process as a reference process of the use process, for any one dimension, acquiring a difference value obtained by subtracting reference data of the reference process in the dimension from a data value of the use process in the dimension, marking the difference value as a deviation degree of the use process in the dimension, and obtaining an absolute value of the difference value, marking the difference value as a difference degree of the use process in the dimension; obtaining the deviation degree and the difference degree of each use process of the non-reference charging pile in the dimension according to the method, carrying out linear normalization on all the difference degrees, adding a negative sign to the normalized value if the deviation degree is smaller than 0, and not adjusting the normalized value if the deviation degree is larger than or equal to 0, and marking the adjusted normalized value as a difference coefficient of each use process of the non-reference charging pile in the dimension; obtaining the difference coefficient of each use process of the non-reference charging pile in each dimension according to the method; for any use process of the non-reference charging pile, carrying out weighted summation on the difference coefficient of the use process in each dimension according to the second weight value of the non-reference charging pile in each dimension, taking the obtained result as the difference weight value of the use process, adding the sum of the difference weight values to 1, and taking the product of the sum of the difference weight values and the aging degree of the reference process of the use process (namely, the element value corresponding to the reference process in a standard aging sequence) as the aging degree of the use process; according to the method, the aging degree of each use process of the non-reference charging pile is obtained; and obtaining the aging degree of each non-reference charging pile and each using process of the charging pile to be tested according to the method.
It should be further noted that, for the reference charging pile, the non-reference charging pile and the charging pile to be tested, the aging degree of each use process is already obtained, and then clustering is performed according to the aging degree and the time corresponding to the use process, and the corrected temperature data of each use process of the charging pile to be tested is obtained by obtaining the clusters to which the charging pile to be tested belongs, so that the construction of the dynamic model of the temperature is completed.
Specifically, for any one use process of any one charging pile (including a reference charging pile, a non-reference charging pile and a charging pile to be tested), the start and the end of the use process respectively correspond to a time point (the corresponding time from the end to the month range acquired in the step S001), and the average value of the two time points is taken as the corresponding time of the use process, so as to acquire the corresponding time of each use process of each charging pile; constructing a coordinate system by taking the aging degree as an abscissa and the corresponding time as an ordinate, converting all the using processes into coordinate points in the coordinate system, performing DBSCAN clustering on all the coordinate points, and measuring the distance between the coordinate points by adopting Euclidean distance to obtain a plurality of clusters; for any use process of the charging pile to be tested, acquiring a cluster where a coordinate point corresponding to the use process is located, and taking the average value of data values of the use processes corresponding to all coordinate points except the coordinate point corresponding to the use process in the cluster in the dimension of equipment temperature data as correction temperature data of the use process; according to the method, the corrected temperature data of each use process of the charging pile to be measured is obtained, the corrected temperature change curve of the charging pile to be measured can be obtained according to the corrected temperature data of each use process and the sequence of the use processes, and the corrected temperature change curve is recorded as a dynamic model of the charging pile to be measured for temperature.
The aging degree of each use process of the non-reference charging pile and the charging pile to be tested is obtained by combining the standard aging change curve according to the use data of the non-reference charging pile and the charging pile to be tested, the correction temperature data of each use process of the charging pile to be tested is obtained by clustering the aging degree of all the charging piles, and finally the construction of the dynamic model of the charging pile to be tested to the temperature is completed.
And the temperature monitoring and early warning module 103 obtains a temperature predicted value in the using process through Kalman filtering according to a dynamic model of the charging pile to be detected for temperature, and completes temperature monitoring and early warning of the charging pile to be detected by combining the actually obtained temperature data.
Inputting the dynamic model into a Kalman filtering algorithm, outputting a temperature predicted value which can be obtained in the next use process of the charging pile to be tested, wherein the Kalman filtering is a known technology for data prediction, and the embodiment is not repeated; in the next use process, early warning is carried out according to the absolute value of the difference value between the equipment temperature data and the temperature predicted value in the use process, an early warning threshold value is preset, the early warning threshold value is described by 15 ℃, if the absolute value of the difference value exceeds the early warning threshold value, equipment early warning is carried out, the fact that the temperature of the charging pile to be tested is abnormal in the current use process and equipment problems need to be timely checked is shown, and safety monitoring based on the temperature of the charging pile of the liquid cooling super-charging technology is achieved.
Thus, the construction of the safety monitoring system based on the temperature for the charging pile of the liquid cooling super-charging technology is completed.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.

Claims (9)

1. A safety monitoring system for liquid cooling overcharge technique, which is characterized in that the system comprises:
the charging data acquisition module acquires use data of a plurality of dimensions of each use process of a plurality of charging piles and charging piles to be detected, and corresponding time of each use process, wherein the use data of the plurality of dimensions comprises equipment temperature data, charging amount data, charging power data, current data, voltage data and environmental temperature data;
the dynamic model building module: according to the voltage data and the charging power data of each charging pile in each use process, acquiring the reference degree of each charging pile and obtaining a reference charging pile and a non-reference charging pile;
the specific method for obtaining the reference degree of each charging pile and obtaining the reference charging pile and the non-reference charging pile comprises the following steps:
For any use process of any charging pile, acquiring the average value of voltage data of the use process, and recording the average value as the use voltage of the use process; acquiring the variance of the charging power data in the using process, and recording the variance as the power fluctuation degree in the using process; acquiring the use voltage and the power fluctuation degree of each charging pile and each use process of the charging pile to be tested; reference degree alpha of ith charging pile i The calculation method of (1) is as follows:
;
wherein J is i Indicating the number of using processes of the ith charging pile, u i,j Representing the voltage used by the jth course of use of the ith charging stake,representing the average value of the voltages used in all the use processes of all the charging piles, and sigma (u) represents the standard deviation, delta, of the voltages used in all the use processes of all the charging piles i,j Indicating the power fluctuation degree of the jth use process of the ith charging pile, +.>Mean value of power fluctuation degree of all charging piles in all using processes, sigma (delta) is standard deviation of power fluctuation degree of all charging piles in all using processes, and +.>Representing the minimum value of the two ratios obtained by adding and subtracting respectively, ||represents the absolute value, exp { } represents an exponential function based on a natural constant;
obtaining the reference degree of each charging pile, taking the charging pile with the reference degree larger than the reference threshold value as a reference charging pile, and taking the charging pile with the reference degree smaller than or equal to the reference threshold value as a non-reference charging pile; taking the charging pile with the largest using process number as a reference charging pile;
According to the change of the charge quantity and the charge power in each use process of the reference charging pile and the reference degree, the aging degree of each use process of each reference charging pile is obtained;
clustering the use data of the same dimensionality in all the use processes of different reference charging piles, and acquiring correction weight values between the use processes of any two different reference charging piles according to clustering results; performing DTW matching on aging degree change curves of different reference charging piles according to the correction weight values to obtain standard aging change curves;
according to the standard aging change curve and the usage data of multiple dimensions of each usage process of each charging pile, the aging degree of each usage process of each non-reference charging pile is obtained; clustering all charging piles according to the aging degree in the using process, and constructing a dynamic model of the charging piles to be tested for temperature;
and the temperature monitoring and early warning module is used for completing the temperature monitoring and early warning of the charging pile to be tested by carrying out Kalman filtering on a dynamic model of the temperature of the charging pile to be tested and combining the actually acquired temperature data.
2. The safety monitoring system for the liquid cooling and super-charging technology according to claim 1, wherein the aging degree of each use process of each reference charging pile is obtained by the following specific method:
For any use process of any reference charging pile, removing the use process and recalculating the reference degree of the reference charging pile, wherein the obtained result is recorded as the heart-removing reference degree of the reference charging pile in the use process; recording a period of time with continuous unchanged charging power data in the using process as a period of stable time in the using process, accumulating the charging quantity data in the stable time as accumulated charging quantity of the stable time, recording the time length of the stable time, and obtaining a plurality of periods of stable time in the using process and accumulated charging quantity and time length of each period of stable time; obtaining the coring reference degree of each reference charging pile in each use process, a plurality of stable time periods in each use process, and the accumulated charge quantity and the time length of each stable time period;
aging degree epsilon of g-th use process of h reference charging pile h,g The calculation method of (1) is as follows:
;
wherein beta is h,g Representing the coring ratio of the g-th use process of the h reference charging pile, wherein the coring ratio is the ratio of the coring reference degree to the reference degree of the reference charging pileA value; f (beta) h,g ) A mapping value representing a decorrelation ratio of a g-th use process of the h-th reference charging pile, wherein if the decorrelation reference degree is greater than the reference degree, the mapping value is a sum of 1 and the decorrelation ratio; if the coring reference level is less than the reference level, the mapping value is 1 minus the difference of the coring ratio; n (N) h,g The number of segments representing the stabilization time in the g-th use process of the h reference charging pile T h,g Representing the duration of the g-th use of the h-th reference charging pile,representing the remaining time of the h reference charging pile in the g using process, wherein the remaining time is obtained by subtracting the sum of the time lengths of all the stabilizing times from the duration of the using process; t is t h,g,n Representing the time length, w, of the nth stabilization time in the g-th use process of the h reference charging pile h,g,n Representing the accumulated charge amount of the nth stable time in the g-th use process of the h reference charging pile, exp () representing an exponential function based on a natural constant;
the aging degree of each use process of each reference charging pile is obtained.
3. The safety monitoring system for the liquid cooling overcharge technology of claim 1, wherein the method for obtaining the correction weight value between the use processes of any two different reference charging piles according to the clustering result comprises the following specific steps:
for any one reference charging pile, arranging the aging degrees of all the using processes of the reference charging pile according to the sequence of the using processes to obtain an aging degree sequence of the reference charging pile; for any use process and any dimension of the reference charging pile, taking the average value of all use data of the dimension in the use process as the data value of the use process in the dimension; acquiring an aging degree sequence of each reference charging pile and a data value of each use process of each reference charging pile in each dimension;
According to the aging degree sequence and the data value of each reference charging pile in each dimension in each using process, a first weight value of any two different reference charging piles in each dimension in the using process and a second weight value of each reference charging pile in each dimension are obtained;
for any two different using processes of the reference charging piles, taking the average value of the second weight values of the dimension in the two reference charging piles as the third weight value of the two using processes in the dimension, obtaining the third weight value of the two using processes in each dimension, and carrying out weighted summation on the first weight values of the two using processes in each dimension according to the third weight value, wherein the obtained sum value is recorded as the correction weight value of the two using processes; and acquiring correction weight values between the using processes of any two different reference charging piles.
4. The safety monitoring system for liquid cooling and overcharge technology according to claim 3, wherein the specific method for obtaining the first weight value of any two different reference charging piles in each dimension and the second weight value of any two different reference charging piles in each dimension comprises the following steps:
For any dimension, clustering data values of all the reference charging piles in the dimension in all the using processes, and marking each cluster as a category in the obtained clustering result; for the use process of any two different reference charging piles, if the data values of the two use processes in the dimension belong to the same category, setting the first weight value of the two use processes in the dimension asWherein->Representing the absolute value of the difference between the data values of the two usage processes in this dimension, d max Representing the maximum of all distances; if the data values of the two using processes in the dimension do not belong to the same category, setting the first weight value of the two using processes in the dimension to be 0; obtaining the obtainedTaking a first weight value of any two different reference charging piles in each dimension in the using process;
for any dimension and any reference charging pile, arranging data values of all using processes of the reference charging pile in the dimension according to the sequence of the using processes to obtain a data change sequence of the reference charging pile in the dimension, and obtaining a pearson correlation coefficient of the data change sequence and an aging degree sequence; acquiring pearson correlation coefficients of a data change sequence and an aging degree sequence of each dimension of the reference charging pile, and carrying out softmax normalization on all pearson correlation coefficients, wherein the obtained result is used as a second weight value of each dimension in the reference charging pile; and acquiring a second weight value of each dimension in each reference charging pile.
5. The safety monitoring system for liquid cooling and overcharging technology according to claim 1, wherein the obtaining the standard aging change curve comprises the following specific steps:
arranging the reference charging piles according to the sequence of the reference degree from large to small, and marking the reference charging piles as a reference sequence; obtaining an aging degree change curve of each reference charging pile; performing DTW matching on the aging degree change curve of each reference charging pile and the aging degree change curve of the next adjacent reference charging pile in the reference sequence, and adjusting the Euclidean distance between the using processes in the DTW matching process through correcting the weight value to obtain a matching result between the adjacent reference charging piles in the reference sequence;
obtaining the reference charging piles with the largest using process number in all the reference charging piles, and marking the reference charging piles as standard charging piles; updating the aging degree of each use process of the reference charging piles with the minimum reference degree in the two reference charging piles according to the sequence from the large reference degree to the small reference degree, acquiring an updated aging change curve and continuously updating the next adjacent reference charging pile in the reference sequence until the updated aging change curve of the standard charging pile is acquired;
Correcting the aging degree of each use process of the reference charging pile with the largest reference degree in the two reference charging piles according to the sequence from the smaller reference degree to the larger reference degree, acquiring a corrected aging change curve, and continuously correcting the adjacent previous reference charging pile in the reference sequence until the corrected aging change curve of the standard charging pile is acquired;
and (3) averaging the updated aging change curve and the corrected aging change curve of the standard charging pile, wherein the obtained result is used as the standard aging change curve.
6. The safety monitoring system for liquid cooling and overcharge technology of claim 4, wherein said means for obtaining the aging level of each use of each non-reference charging pile comprises the following steps:
according to the standard aging change curve and the data value of each charging pile in each dimension in each using process, obtaining the difference weight value of each non-reference charging pile and each using process of the charging pile to be tested; for any one use process of any non-reference charging pile, acquiring the use process of the same ordinal number of the use process in a standard aging sequence, recording as a reference process of the use process, adding the sum of the difference weight values to 1, and taking the product of the sum of the difference weight values and the aging degree of the reference process of the use process as the aging degree of the use process;
And obtaining the aging degree of each non-reference charging pile and each using process of the charging pile to be tested.
7. The safety monitoring system for liquid cooling and superfilling technology according to claim 5 or 6, wherein the specific obtaining method is as follows:
obtaining a standard aging change curve through DTW matching according to the aging degree change curve of the reference charging pile, and combining the reference degree of the reference charging pile to obtain reference data of each use process in each dimension in the standard aging sequence;
for any non-reference charging pile, acquiring a data value of each non-reference charging pile in each dimension in each using process, and acquiring a second weight value of each dimension in the non-reference charging pile; for any one use process and any one dimension of the non-reference charging pile, obtaining a difference value obtained by subtracting reference data of a reference process in the dimension from a data value of the use process in the dimension, marking the difference value as a deviation degree of the use process in the dimension, and obtaining an absolute value of the difference value as a difference degree of the use process in the dimension; obtaining the deviation degree and the difference degree of each use process of the non-reference charging pile in the dimension, carrying out linear normalization on all the difference degrees, adding a negative sign to the normalized value if the deviation degree is smaller than 0, and if the deviation degree is larger than or equal to 0, not adjusting the normalized value, and recording the adjusted normalized value as a difference coefficient of each use process of the non-reference charging pile in the dimension; obtaining a difference coefficient of each use process of the non-reference charging pile in each dimension;
For any use process of the non-reference charging pile, carrying out weighted summation on the difference coefficient of the use process in each dimension according to the second weight value of the non-reference charging pile in each dimension, and taking the obtained result as the difference weight value of the use process; and obtaining the differential weight value of each non-reference charging pile and each using process of the charging pile to be tested.
8. The safety monitoring system for liquid cooling and overcharging technology according to claim 7, wherein the specific method for obtaining the reference data of each usage process in each dimension in the standard aging sequence comprises the following steps:
obtaining a standard aging sequence and a plurality of using processes of the standard aging sequence according to the standard aging change curve; for any one use process in the standard aging sequence, acquiring the use process, and recording the use process of all the reference charging piles participating in updating or correcting the aging degree of the use process in the process of acquiring the standard aging change curve by DTW matching as a matching process of the use process; carrying out softmax normalization on the reference degrees of all the reference charging piles, and taking the obtained result as a matching weight value of each reference charging pile;
For any dimension, acquiring data values of the dimension in all matching processes, carrying out weighted summation on the acquired data values according to the matching weight values of the reference charging piles corresponding to the matching processes, and recording the obtained result as reference data of the using process in the dimension; reference data in each dimension for each usage procedure in the standard burn-in sequence is obtained.
9. The safety monitoring system for liquid cooling and super-charging technology according to claim 7, wherein the construction of the dynamic model of the charging pile to be tested for temperature comprises the following specific steps:
acquiring corresponding time for each use process of each charging pile; constructing a coordinate system by taking the aging degree as an abscissa and the corresponding time as an ordinate, converting all using processes of all charging piles into coordinate points in the coordinate system, and clustering all the coordinate points to obtain a plurality of clusters;
for any use process of the charging pile to be tested, acquiring a cluster where a coordinate point corresponding to the use process is located, and taking the average value of data values of the use processes corresponding to all coordinate points except the coordinate point corresponding to the use process in the cluster in the dimension of equipment temperature data as correction temperature data of the use process; and acquiring correction temperature data of each use process of the charging pile to be measured, and arranging according to the sequence of the use processes to obtain a correction temperature change curve of the charging pile to be measured, and marking the correction temperature change curve as a dynamic model of the charging pile to be measured for temperature.
CN202311291612.6A 2023-10-08 2023-10-08 Safety monitoring system for liquid cooling and super-charging technology Active CN117325699B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311291612.6A CN117325699B (en) 2023-10-08 2023-10-08 Safety monitoring system for liquid cooling and super-charging technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311291612.6A CN117325699B (en) 2023-10-08 2023-10-08 Safety monitoring system for liquid cooling and super-charging technology

Publications (2)

Publication Number Publication Date
CN117325699A CN117325699A (en) 2024-01-02
CN117325699B true CN117325699B (en) 2024-03-26

Family

ID=89275054

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311291612.6A Active CN117325699B (en) 2023-10-08 2023-10-08 Safety monitoring system for liquid cooling and super-charging technology

Country Status (1)

Country Link
CN (1) CN117325699B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112699605A (en) * 2020-12-28 2021-04-23 山东鲁能软件技术有限公司智能电气分公司 Charging pile fault element prediction method and system
CN113541317A (en) * 2021-07-26 2021-10-22 国网吉林省电力有限公司 Real-time remote monitoring method for mass charging piles
CN114407713A (en) * 2021-12-30 2022-04-29 广东劲天科技有限公司 Charging pile management system, method and device based on big data and storage medium
WO2023105093A1 (en) * 2021-12-12 2023-06-15 eClever Entwicklungs OHG Method for checking charging columns and their range of functions
CN116394794A (en) * 2023-05-25 2023-07-07 安徽海迪拉电气科技股份有限公司 High security intelligence fills electric pile
CN116664015A (en) * 2023-07-26 2023-08-29 深圳市森树强电子科技有限公司 Intelligent charging pile management system and method thereof

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112699605A (en) * 2020-12-28 2021-04-23 山东鲁能软件技术有限公司智能电气分公司 Charging pile fault element prediction method and system
CN113541317A (en) * 2021-07-26 2021-10-22 国网吉林省电力有限公司 Real-time remote monitoring method for mass charging piles
WO2023105093A1 (en) * 2021-12-12 2023-06-15 eClever Entwicklungs OHG Method for checking charging columns and their range of functions
CN114407713A (en) * 2021-12-30 2022-04-29 广东劲天科技有限公司 Charging pile management system, method and device based on big data and storage medium
CN116394794A (en) * 2023-05-25 2023-07-07 安徽海迪拉电气科技股份有限公司 High security intelligence fills electric pile
CN116664015A (en) * 2023-07-26 2023-08-29 深圳市森树强电子科技有限公司 Intelligent charging pile management system and method thereof

Also Published As

Publication number Publication date
CN117325699A (en) 2024-01-02

Similar Documents

Publication Publication Date Title
CN112241608B (en) Lithium battery life prediction method based on LSTM network and transfer learning
CN117093879B (en) Intelligent operation management method and system for data center
CN110851980B (en) Method and system for predicting residual life of equipment
CN107957562B (en) Online prediction method for residual life of lithium ion battery
CN109828220B (en) Linear evaluation method for health state of lithium ion battery
WO2015188610A1 (en) Method and device for estimating state of charge of battery
CN111965559B (en) On-line estimation method for SOH of lithium ion battery
CN115902647B (en) Intelligent battery state monitoring method
CN111220920B (en) Retired lithium ion battery state of charge calculation method based on H-infinity unscented Kalman filtering algorithm
CN104569844A (en) Valve control seal type lead-acid storage battery health condition monitoring method
CN111753416A (en) Lithium ion battery RUL prediction method based on two-stage Wiener process
CN108693483A (en) A kind of computational methods and system of battery pack state-of-charge
CN112379272B (en) Lithium ion battery system SOC estimation method based on artificial intelligence
CN112989690A (en) Multi-time scale state of charge estimation method for lithium battery of hybrid electric vehicle
CN113962154A (en) Lithium battery nuclear temperature evaluation method and system based on transfer learning
CN113359048A (en) Indirect prediction method for remaining service life of lithium ion battery
CN114330647A (en) Model training method and device and silicon rod weight prediction method
CN113406503A (en) Lithium battery SOH online estimation method based on deep neural network
CN115656848A (en) Lithium battery SOC estimation method based on capacity correction
CN115908051A (en) Method for determining energy storage capacity of power system
CN117325699B (en) Safety monitoring system for liquid cooling and super-charging technology
CN116577686B (en) Multi-working condition SOH estimation method and system based on local stage charging data
CN113420444A (en) Lithium ion battery SOC estimation method based on parameter online identification
Wang et al. Remaining useful life prediction of lithium-ion battery based on cycle-consistency learning
CN115308611B (en) Lithium ion battery residual life prediction method considering temperature compensation

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant