CN110161418B - Method, system and computer readable storage medium for predicting health of storage battery - Google Patents
Method, system and computer readable storage medium for predicting health of storage battery Download PDFInfo
- Publication number
- CN110161418B CN110161418B CN201910477284.6A CN201910477284A CN110161418B CN 110161418 B CN110161418 B CN 110161418B CN 201910477284 A CN201910477284 A CN 201910477284A CN 110161418 B CN110161418 B CN 110161418B
- Authority
- CN
- China
- Prior art keywords
- battery
- data
- storage battery
- health
- parameter
- 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 - Reinstated
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
Abstract
The invention discloses a method, a system and a computer readable storage medium for predicting the health degree of a storage battery, wherein the method comprises the following steps: obtaining time series historical data of battery operating parameters in a battery system, the battery operating parameters including at least one parameter type; calculating the transfer probability of the multi-order fault symptoms corresponding to each battery operation parameter according to the obtained time series historical data of the battery operation parameters in the battery system; and calculating and obtaining the health degree information of the storage battery system according to the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters. By implementing the method and the device, the health degree of the storage battery system can be accurately and effectively predicted.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a method and a system for predicting the health degree of a storage battery and a computer-readable storage medium.
Background
Health detection for battery systems is an important task in routine maintenance. In the prior art, a timing detection method is generally adopted, and faults of the storage battery system are judged and predicted directly according to measurement parameter results. The existing method cannot accurately and effectively predict the health degree, cannot accurately and intuitively predict the faults of the storage battery system, and cannot intuitively and effectively obtain the health degree change condition and trend analysis result of the storage battery system.
Disclosure of Invention
In view of the above, the present invention provides a method, system and computer readable storage medium for predicting health of a storage battery, so as to solve at least the above technical problems in the prior art.
One aspect of the present invention provides a method for predicting the health degree of a storage battery, including:
obtaining time series historical data of battery operating parameters in a battery system, the battery operating parameters including at least one parameter type;
calculating the transfer probability of the multi-order fault symptoms corresponding to each battery operation parameter according to the obtained time series historical data of the battery operation parameters in the battery system;
and calculating and obtaining the health degree information of the storage battery system according to the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters.
In one embodiment, the obtaining time series historical data of battery operating parameters in a battery system comprises:
obtaining historical detection analog signals of the operation parameters of each battery in the storage battery system;
and carrying out discrete processing on the historical detection analog signals of the battery operation parameters to convert the historical detection analog signals into corresponding historical detection digital signals serving as time series historical data of the battery operation parameters.
In an implementation manner, the calculating the transition probability of the multi-order fault symptom corresponding to each battery operating parameter includes:
respectively aiming at each battery operation parameter, arranging corresponding numerical values of the historical detection digital signals according to a time sequence to obtain a numerical value sequence { q ] ordered according to time1、q2、…、qn-1、qn}；
Aiming at the ith data in the numerical value sequence, under the condition that the state of the ith data is known, the conditional probability values [ p ] of the ith data after the ith data appears are respectively calculated for the ith-1 th data, the ith-2 … th data and the 1 st data1、p2、…、pi-2、pi-1](ii) a Wherein i is more than 1 and less than or equal to n, and n represents the number of numerical values in the numerical value sequence;
the conditional probability value [ p ]1、p2、…、pi-2、pi-1]And forming a one-dimensional matrix of the transition probability of the multi-order fault symptoms of the corresponding battery operation parameters, namely the transition probability matrix of the multi-order fault symptoms of the corresponding battery operation parameters.
In an implementation manner, the calculating and obtaining the health degree information of the battery operating parameters according to the transition probability of the multi-order fault symptoms corresponding to each battery operating parameter includes:
for each battery operation parameter, linearly combining all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a linear combination result as a health degree value of the corresponding battery operation parameter corresponding to the health degree value of the battery operation parameter;
linearly combining the values of the degree of health of all the battery operating parameters in the battery systems again, and determining the result of the linear combination as the value of the degree of health of the corresponding battery system.
In a possible embodiment, the linear combination is a summation, a multiplication or an averaging.
In one embodiment, the battery operating parameters include at least one of the following parameter types: the storage battery single body voltage, the storage battery group voltage, the storage battery single body internal resistance, the storage battery single body temperature, the storage battery single body current and the storage battery group current.
Another aspect of the present invention provides a system for predicting health of a battery, the system including:
a history data obtaining unit for obtaining time series history data of each battery operation parameter in the battery system, wherein the battery operation parameter comprises at least one parameter type;
the symptom occurrence probability obtaining unit is used for calculating the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters according to the obtained time series historical data of the battery operation parameters in the battery system;
and the health degree information obtaining unit is used for calculating and obtaining the health degree information of the storage battery system according to the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters.
In one embodiment, the history data obtaining unit includes:
the analog signal acquisition subunit is used for acquiring historical detection analog signals of the operating parameters of each battery in the battery system;
and the discrete processing subunit is used for performing discrete processing on the historical detection analog signals of the battery operation parameters to convert the historical detection analog signals into corresponding historical detection digital signals serving as time series historical data of the battery operation parameters.
In one embodiment, the symptom occurrence probability obtaining unit includes:
a sequencing subunit, configured to sequence, according to each battery operating parameter, the corresponding values of the historical detection digital signals according to a time sequence, so as to obtain a time-sequenced value sequence { q }1、q2、…、qn-1、qn}；
A conditional probability calculation subunit, configured to calculate, for the ith data in the numerical value sequence, conditional probability values [ p ] of the ith data after the ith data appears, in which the state of the ith data is known, and the ith-1, ith-2 …, and 1 st data after the ith data appears, respectively1、p2、…、pi-2、pi-1](ii) a Wherein i is more than 1 and less than or equal to n, and n represents the number of numerical values in the numerical value sequence;
a matrix obtaining subunit for obtaining the conditional probability value [ p ]1、p2、…、pi-2、pi-1]And forming a one-dimensional matrix of the transition probability of the multi-order fault symptoms of the corresponding battery operation parameters as a transition probability matrix of the multi-order fault symptoms of the corresponding battery operation parameters.
In an embodiment, the health information obtaining unit is further configured to,
for each battery operation parameter, linearly combining all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a linear combination result as a health degree value of the corresponding battery operation parameter corresponding to the health degree value of the battery operation parameter;
linearly combining the values of the degree of health of all the battery operating parameters in the battery systems again, and determining the result of the linear combination as the value of the degree of health of the corresponding battery system.
In a possible embodiment, the linear combination is a summation, a multiplication or an averaging.
In one embodiment, the battery operating parameters include at least one of the following parameter types: the storage battery single body voltage, the storage battery group voltage, the storage battery single body internal resistance, the storage battery single body temperature, the storage battery single body current and the storage battery group current.
Yet another aspect of the present invention provides a computer-readable storage medium comprising a set of computer-executable instructions that, when executed, perform a method for battery health prediction according to the present invention.
By implementing the method and the system, the accurate and effective health degree prediction of the storage battery system can be realized, the faults can be accurately and visually predicted, and the health degree change condition and trend analysis result of the storage battery system can be visually and effectively obtained.
Drawings
Fig. 1 is a schematic flow chart illustrating a method for predicting health of a storage battery according to a first embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a method for predicting the health degree of a storage battery according to a second embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a configuration of a battery health degree prediction system according to a first embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a configuration of a battery health degree prediction system according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
Referring to fig. 1, a method for predicting the health degree of a battery system according to a first embodiment of the present invention mainly includes:
In particular, the battery operating parameters may include at least one of the following parameter types: the storage battery single body voltage, the storage battery group voltage, the storage battery single body internal resistance, the storage battery single body temperature, the storage battery single body current and the storage battery group current.
That is, the operation of step 101 may be performed only for one parameter type of battery cell voltage, battery pack voltage, battery cell internal resistance, battery cell temperature, battery cell current, and battery pack current. Of course, the operation of step 101 may also be performed for two or more parameter types of the battery cell voltage, the battery pack voltage, the battery cell internal resistance, the battery cell temperature, the battery cell current, and the battery pack current.
In an implementation manner, step 101 specifically includes:
obtaining historical detection analog signals of the operation parameters of each battery in the storage battery system;
and carrying out discrete processing on the historical detection analog signals of the battery operation parameters to convert the historical detection analog signals into corresponding historical detection digital signals serving as time series historical data of the battery operation parameters.
The analog signal can be acquired by the sensor on site in real time, the digital signal and the discrete processing thereof are realized by an A/D conversion system, and the historical data is stored in a binary information storage medium which can store the data for a long time.
For example, one:
if step 101 is the only operation performed on pack voltages, then the process of obtaining time series historical data for pack voltages is:
a sensor of the storage battery system acquires historical detection analog signals of the voltage of the storage battery pack in real time, the historical detection analog signals are converted into corresponding digital signals through A/D conversion, corresponding historical detection digital signals are obtained through data discrete processing and serve as time series historical data of the voltage of the storage battery pack, and the historical data are stored in a binary information storage medium (such as a memory, a hard disk, a magnetic disk, a U disk and the like) capable of storing data for a long time.
Example two:
if step 101 is the only operation performed on pack voltage and pack current, then the process of obtaining time series historical data for pack voltage and pack current is:
a sensor of a storage battery system acquires historical detection analog signals of the voltage of a storage battery pack in real time, the historical detection analog signals are converted into corresponding digital signals through A/D conversion, corresponding historical detection digital signals are obtained through data discrete processing and are used as time series historical data of the voltage of the storage battery pack, and the historical data are stored in a binary information storage medium (such as a memory, a hard disk, a magnetic disk, a U disk and the like) capable of storing data for a long time;
a sensor of a storage battery system acquires historical detection analog signals of the current of the storage battery pack in real time, the historical detection analog signals are converted into corresponding digital signals through A/D conversion, corresponding historical detection digital signals are obtained through data discrete processing and are used as time series historical data of the current of the storage battery pack, and the historical data are stored in a binary information storage medium (such as a memory, a hard disk, a magnetic disk, a U disk and the like) capable of storing data for a long time.
Through the implementation process, time series historical data corresponding to the battery operation parameters in the battery system can be obtained.
And 102, calculating the transition probability of the multi-order fault symptoms corresponding to each battery operation parameter according to the obtained time series historical data of the battery operation parameters in the storage battery system.
The process of calculating the transition probability of the multi-order fault symptoms corresponding to each battery operating parameter may include:
respectively aiming at each battery operation parameter, arranging corresponding numerical values of the historical detection digital signals according to a time sequence to obtain a numerical value sequence { q ] ordered according to time1、q2、…、qn-1、qn}；
For the ith data in the numerical value sequence, at the ithUnder the condition that the state of the data is known, the conditional probability values [ p ] of the ith data after the ith-1 th data, the ith-2 … th data and the 1 st data appear are respectively calculated1、p2、…、pi-2、pi-1](ii) a Wherein i is more than 1 and less than or equal to n, and n represents the number of numerical values in the numerical value sequence;
from conditional probability values [ p ]1、p2、…、pi-2、pi-1]And forming a one-dimensional matrix of the transition probability of the multi-order fault symptoms of the corresponding battery operation parameters, namely the transition probability matrix of the multi-order fault symptoms of the corresponding battery operation parameters.
Wherein the time series of the history data may be represented as follows: 1. 2, … i-2, i-1, i +1, i +2 ….
"… i-2, i-1, i, i time, the first 1 to i-1 time is also called the historical time of the ith time after the digital signal of i time; for the data obtained at the ith moment, the conditional probability values of the ith data after the ith data appear, namely [ p ], of the ith-1, the ith-2 … and the 1 st data can be calculated1、p2、…、pi-2、pi-1](ii) a Similarly, after the digital signal at the (i + 1) th time is obtained, the previous 1 to i times are also referred to as historical times of the (i + 1) th time; for the data obtained at the (i + 1) th moment, the conditional probability values of the (i + 1) th data after the (i, i-1) th, i-2 …) th and 1 st data appear, namely [ p ]1、p2、…、pi-2、pi-1、pi](ii) a By analogy, for the historical data obtained at each moment, the transition probability matrix of the multi-order fault symptoms of the battery operation parameters corresponding to the moment can be obtained through calculation by the method, and the transition probability matrix corresponding to each moment is a one-dimensional matrix formed by corresponding conditional probability values.
It should be noted that, for different battery operating parameter types, the operation of step 102 is performed separately for each battery operating parameter type.
And 103, calculating and obtaining the health degree information of the storage battery system according to the transition probability of the multi-stage fault symptoms corresponding to the battery operation parameters.
In one implementation, the implementation of step 103 is as follows:
for each battery operation parameter, linearly combining all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a linear combination result as a health degree value of the corresponding battery operation parameter corresponding to the health degree value of the battery operation parameter;
linearly combining the values of the degree of health of all the battery operating parameters in the battery systems again, and determining the result of the linear combination as the value of the degree of health of the corresponding battery system.
Where linear combination is summation, integration or averaging.
For example: for each battery operation parameter, summing all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a summation result as a value of the health degree of the corresponding battery operation parameter; summing the values of the health degrees of all the battery operating parameters in the battery system, and determining the result of the summation as the value of the health degree of the corresponding battery system;
or, for each battery operation parameter, performing product operation on all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a product operation result as a value of the health degree of the corresponding battery operation parameter; the method comprises the steps of performing product calculation on the health degree values of all battery operation parameters in the storage battery system, and determining the product calculation result as the health degree value of the corresponding storage battery system;
or, for each battery operation parameter, averaging all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining an averaging result as a value of the health degree of the corresponding battery operation parameter; and averaging the health degree values of all the battery operation parameters in the battery system, and determining the averaging result as the health degree value of the corresponding battery system.
If the health degree information of the storage battery system at a certain moment is calculated, all probability values in a transition probability matrix of the multi-order fault symptoms of each battery operation parameter at the corresponding moment need to be respectively summed/integrated/averaged, and the summed/integrated/averaged result is determined as the health degree value of the corresponding battery operation parameter at the corresponding moment; and summing/integrating/averaging the health degree values of all the battery operating parameters in the battery system at the corresponding moment, so that the summing/integrating/averaging result is determined as the health degree value of the battery system at the corresponding moment, namely the health degree information.
Therefore, the health degree values of the storage battery system at different moments finally form a curve reflecting the health degree of the storage battery system, the health degree change trend of the storage battery system can be fully reflected through the curve, and the risk of potential faults of the storage battery system can be well predicted.
It should be noted that the embodiment of the present invention provides three calculation methods of the health value: summing, integrating and averaging. Of course, the embodiment of the present invention is not limited to the above three calculation manners, and any method that can calculate information for evaluating the health degree of the battery system by using the probability values in the transition probability matrix in practical applications should belong to the protection scope of the embodiment of the present invention.
Example two
As shown in fig. 2, the method for predicting the health degree of a storage battery according to the second embodiment of the present invention, after step 103 of the first embodiment, further includes:
and 104, analyzing and determining potential fault source information according to the health degree information. The method specifically comprises the following steps:
presetting fault source information corresponding to each order of fault symptom in a transition probability matrix with multiple orders of fault symptoms;
and calculating to obtain probability information of target faults caused by corresponding fault sources according to the transition probability matrix of the multi-order fault symptoms corresponding to the health degree.
And analyzing the health degree curve of the storage battery system, and judging that a potential fault risk exists if the change trend of the reaction in the health degree curve and the value of the health degree meet preset fault early warning conditions. In practical application, fault source information corresponding to each order of fault symptom in the transition probability matrix can be preset according to actual operation experience data, and then probability information of target fault occurrence caused by the corresponding fault source can be calculated and obtained according to the transition probability matrix of multiple orders of fault symptoms corresponding to the health degree, so that the potential fault source can be determined according to the probability information of target fault occurrence caused by the fault source, and therefore the potential fault source can be obtained through data analysis before the fault occurs, and the situation that the fault occurs in the bud can be prevented.
EXAMPLE III
Corresponding to the method for predicting the health degree of the storage battery in the embodiment of the present invention, the embodiment of the present invention further provides a system for predicting the health degree of the storage battery, as shown in fig. 3, the system mainly includes:
a history data obtaining unit 10 for obtaining time series history data of each battery operating parameter in the battery system, the battery operating parameter including at least one parameter type;
a symptom occurrence probability obtaining unit 20, configured to calculate a transition probability of a multi-step fault symptom corresponding to each battery operating parameter according to the obtained time series historical data of the battery operating parameters in the battery system;
and a health degree information obtaining unit 30, configured to calculate and obtain health degree information of the battery system according to transition probabilities of the multiple-order fault symptoms corresponding to the battery operating parameters.
In one embodiment, the history data obtaining unit 10 includes:
an analog signal obtaining subunit 11, configured to obtain historical detection analog signals of operating parameters of each battery in the battery system;
and the discrete processing subunit 12 is configured to perform discrete processing on the historical detection analog signal of each battery operating parameter to convert the historical detection analog signal into a corresponding historical detection digital signal, which is used as time-series historical data of the battery operating parameter.
In another possible embodiment, the symptom occurrence probability obtaining unit 20 includes:
a sorting subunit 21, configured to sort, according to each battery operating parameter, the corresponding values of the historical detection digital signals according to a time sequence, so as to obtain a time-sorted value sequence { q }1、q2、…、qn-1、qn}；
A conditional probability calculation subunit 22, configured to calculate, for the ith data in the numerical sequence, conditional probability values [ p ] of the ith data after the ith data appears, under the condition that the state of the ith data is known, and the ith data is the i-1 th data, the i-2 th 2 …, and the 1 st data after the ith data appears respectively1、p2、…、pi-2、pi-1](ii) a Wherein i is more than 1 and less than or equal to n, and n represents the number of numerical values in the numerical value sequence;
a matrix obtaining subunit 23 for obtaining the conditional probability value [ p ]1、p2、…、pi-2、pi-1]And forming a one-dimensional matrix of the transition probability of the multi-order fault symptoms of the corresponding battery operation parameters as a transition probability matrix of the multi-order fault symptoms of the corresponding battery operation parameters.
In another possible embodiment, the health information obtaining unit 30 is further configured to,
for each battery operation parameter, linearly combining all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a linear combination result as a health degree value of the corresponding battery operation parameter corresponding to the health degree value of the battery operation parameter;
the values of the degrees of health of all the battery operating parameters in the battery systems are linearly combined again, and the result of the linear combination is determined as the value of the degree of health of the corresponding battery system.
The linear combination may be summation, integration or averaging.
For example: for each battery operation parameter, summing all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a summation result as a value of the health degree of the corresponding battery operation parameter; summing the values of the health degrees of all the battery operating parameters in the battery system, and determining the result of the summation as the value of the health degree of the corresponding battery system;
or, for each battery operation parameter, performing product operation on all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a product operation result as a value of the health degree of the corresponding battery operation parameter; the method comprises the steps of performing product calculation on the health degree values of all battery operation parameters in the storage battery system, and determining the product calculation result as the health degree value of the corresponding storage battery system;
or, for each battery operation parameter, averaging all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining an averaging result as a value of the health degree of the corresponding battery operation parameter; and averaging the health degree values of all the battery operation parameters in the battery system, and determining the averaging result as the health degree value of the corresponding battery system.
The health degree values of the storage battery system at different moments finally form a curve reflecting the health degree of the storage battery system, the health degree change trend of the storage battery system can be fully reflected through the curve, and the risk of potential faults of the storage battery system can be well predicted.
Example four
As shown in fig. 4, the system for predicting the degree of health of a storage battery according to the fourth embodiment further includes, in addition to the third embodiment: the fault source analysis unit 40 is configured to analyze and determine potential fault source information according to the health degree information, and specifically includes:
presetting fault source information corresponding to each order of fault symptom in a transition probability matrix with multiple orders of fault symptoms;
and calculating to obtain probability information of target faults caused by corresponding fault sources according to the transition probability matrix of the multi-order fault symptoms corresponding to the health degree.
And analyzing the health degree curve of the storage battery system, and judging that a potential fault risk exists if the change trend of the reaction in the health degree curve and the value of the health degree meet preset fault early warning conditions. In practical application, fault source information corresponding to each order of fault symptom in the transition probability matrix can be preset according to actual operation experience data, and then probability information of target fault occurrence caused by the corresponding fault source can be calculated and obtained according to the transition probability matrix of multiple orders of fault symptoms corresponding to the health degree, so that the potential fault source can be determined according to the probability information of target fault occurrence caused by the fault source, and therefore the potential fault source can be obtained through data analysis before the fault occurs, and the situation that the fault occurs in the bud can be prevented.
EXAMPLE five
The following describes in detail an application scheme of the method for predicting the health degree of the storage battery in the embodiment of the invention in an actual scene by taking the battery operation parameter as the voltage of the storage battery pack as an example.
Firstly, recording time series historical data of the voltage of a storage battery pack of the storage battery system, wherein the specific process is as follows: the method comprises the steps that corresponding historical detection analog voltage signals are acquired by a sensor of a storage battery system in real time, the historical detection analog voltage signals are converted into corresponding digital voltage signals through A/D conversion, the corresponding historical detection digital voltage signals are obtained through data discrete processing and serve as time series historical data of storage battery pack voltage, and the time series historical data are stored in a binary information storage medium capable of storing data for a long time.
Secondly, according to the time sequence historical data of the voltage of the storage battery pack, the transition probability of the corresponding multi-order fault symptoms is calculated, and the specific process is as follows:
arranging corresponding numerical values of historical detection digital signals of the voltage of the storage battery pack according to a time sequence respectively to obtain a numerical value sequence { q ] ordered according to time1、q2、…、qn-1、qn}；
From a sequence of values of the battery pack voltage { q1、q2、…、qn-1、qnCalculating conditional probability value [ p ] of data at each moment1、p2、…、pi-2、pi-1]；
From conditional probability values p at each time instant1、p2、…、pi-2、pi-1]And forming a one-dimensional matrix, namely, a transition probability matrix which is used as a multi-order fault symptom of the voltage of the corresponding storage battery pack at different moments.
And then, according to the transition probability matrix of the voltage of the storage battery pack, summing all probability values in the transition probability matrix respectively, and determining the summation result as the value of the overall health degree of the storage battery system at the corresponding moment.
Finally, the values of the health degree of the storage battery system at different moments form a curve reflecting the health degree of the storage battery system, the change trend of the health degree of the storage battery system can be fully reflected through the curve, and the risk of potential faults of the storage battery system can be well predicted.
EXAMPLE six
The following further elaborates an application scheme of the method for predicting the health degree of the storage battery in the embodiment of the invention in an actual scene by taking the battery operation parameters as the voltage of the storage battery and the current of the storage battery as examples.
Firstly, respectively recording time sequence historical data of the voltage of a storage battery pack and the current of the storage battery pack in the storage battery system, wherein the specific process comprises the following steps: the method comprises the steps that corresponding historical detection analog signals are acquired by sensors of storage battery pack voltage and storage battery pack current in real time, the historical detection analog signals are converted into corresponding digital signals through A/D conversion, corresponding historical detection digital signals are acquired through data discrete processing and are respectively used as time series historical data of the storage battery pack voltage and the storage battery pack current, and the time series historical data are stored in a binary information storage medium capable of storing data for a long time.
Secondly, respectively calculating the corresponding transition probability of the multi-order fault symptoms according to the respective time sequence historical data of the voltage and the current of the storage battery pack, and the specific process is as follows:
arranging corresponding numerical values of respective historical detection digital signals of the voltage and the current of the storage battery pack according to a time sequence to obtain a numerical value sequence { q ] ordered according to time1、q2、…、qn-1、qn}；
According to the respective value sequences { q ] of the battery voltage and the battery current1、q2、…、qn-1、qnCalculating conditional probability value [ p ] of data at each moment1、p2、…、pi-2、pi-1]；
From conditional probability values p at each time instant1、p2、…、pi-2、pi-1]Formed one-dimensional matrices, i.e. each as a respectiveA transition probability matrix of multi-order fault symptoms of the storage battery pack voltage and the storage battery pack current at different moments.
Then, according to the respective transition probability matrixes of the voltage and the current of the storage battery pack, summing all probability values in the respective transition probability matrixes respectively, and determining the summation result as the value of the health degree of the voltage and the current of the storage battery pack respectively; and then the values of the health degree of the voltage of the storage battery pack and the current of the storage battery pack are summed, so that the final summation result is determined as the value of the overall health degree of the storage battery system at the corresponding moment.
Finally, the values of the health degree of the storage battery system at different moments form a curve reflecting the health degree of the storage battery system, the change trend of the health degree of the storage battery system can be fully reflected through the curve, and the risk of potential faults of the storage battery system can be well predicted.
In addition, the health degree curve of the storage battery system is analyzed, and if the change trend of the reaction in the health degree curve and the value of the health degree meet preset fault early warning conditions, the potential fault risk is judged to exist. In practical application, the fault source information corresponding to each order of fault symptom in the transition probability matrix can be preset according to actual operation experience data, so that the probability information of target fault occurrence caused by the corresponding fault source can be calculated according to the transition probability matrix of multiple orders of fault symptoms corresponding to the health degree, and the potential fault source can be determined according to the probability information of target fault occurrence caused by the fault source, so that the potential fault source can be obtained through data analysis before the fault occurs.
Embodiments of the present invention also provide a computer-readable storage medium, which includes a set of computer-executable instructions, and when executed, the computer-readable storage medium is used for implementing the method for predicting health of a storage battery according to an embodiment of the present invention.
In conclusion, by implementing the embodiment of the invention, the health degree of the storage battery system can be accurately and effectively predicted, the fault can be accurately and intuitively predicted, and the health degree change condition and trend analysis result of the storage battery system can be intuitively and effectively obtained; in addition, the fault source information corresponding to each order of fault symptom in the transition probability matrix of the multiple orders of fault symptoms is preset according to the actual operation experience of the storage battery system, and the probability information of target faults caused by corresponding fault sources can be calculated according to the transition probability matrix of the multiple orders of fault symptoms, so that the potential fault source information can be determined, and the predictability and traceability of the fault sources are realized.
It should be further noted that, in the embodiment of the present invention, the selection of the battery cell voltage, the battery pack voltage, the battery cell internal resistance, the battery cell temperature, the battery cell current, and the battery pack current as the battery operation parameters is a parameter that is verified to be usable for the health prediction of the battery system.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (11)
1. A method for predicting the health of a battery, the method comprising:
obtaining time series historical data of battery operating parameters in a battery system, the battery operating parameters including at least one parameter type;
calculating the transfer probability of the multi-order fault symptoms corresponding to each battery operation parameter according to the obtained time series historical data of the battery operation parameters in the battery system;
calculating and obtaining health degree information of the storage battery system according to the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters;
wherein, the calculating the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters comprises:
respectively aiming at each battery operation parameter, arranging corresponding numerical values of the historical detection digital signals according to a time sequence to obtain a numerical value sequence { q ] ordered according to time1、q2、…、qn-1、qn}；
Aiming at the ith data in the numerical value sequence, under the condition that the state of the ith data is known, the conditional probability values [ p ] of the ith data after the ith data appears are respectively calculated for the ith-1 th data, the ith-2 … th data and the 1 st data1、p2、…、pi-2、pi-1](ii) a Wherein i is more than 1 and less than or equal to n, and n represents the number of numerical values in the numerical value sequence;
the conditional probability value [ p ]1、p2、…、pi-2、pi-1]Forming a one-dimensional matrix of transition probabilities of the multiple order symptoms of the corresponding battery operating parameter, i.e. the transition of the multiple order symptoms of the corresponding battery operating parameterAnd shifting the probability matrix.
2. The method of claim 1, wherein obtaining time series historical data of battery operating parameters in a battery system comprises:
obtaining historical detection analog signals of the operation parameters of each battery in the storage battery system;
and carrying out discrete processing on the historical detection analog signals of the battery operation parameters to convert the historical detection analog signals into corresponding historical detection digital signals serving as time series historical data of the battery operation parameters.
3. The method of claim 2, wherein the calculating the health information of the battery operating parameters according to the transition probabilities of the multiple stages of fault symptoms corresponding to the battery operating parameters comprises:
for each battery operation parameter, linearly combining all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a linear combination result as a health degree value of the corresponding battery operation parameter corresponding to the health degree value of the battery operation parameter;
linearly combining the values of the degree of health of all the battery operating parameters in the battery systems again, and determining the result of the linear combination as the value of the degree of health of the corresponding battery system.
4. The method of claim 3, wherein the linear combination is summation, multiplication, or averaging.
5. The method of any of claims 1 to 4, wherein the battery operating parameters comprise at least one of the following parameter types: the storage battery single body voltage, the storage battery group voltage, the storage battery single body internal resistance, the storage battery single body temperature, the storage battery single body current and the storage battery group current.
6. A system for predicting the health of a battery, the system comprising:
a history data obtaining unit for obtaining time series history data of each battery operation parameter in the battery system, wherein the battery operation parameter comprises at least one parameter type;
the symptom occurrence probability obtaining unit is used for calculating the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters according to the obtained time series historical data of the battery operation parameters in the battery system;
the health degree information obtaining unit is used for calculating and obtaining the health degree information of the storage battery system according to the transition probability of the multi-order fault symptoms corresponding to the battery operation parameters;
wherein the symptom occurrence probability obtaining unit includes:
a sequencing subunit, configured to sequence, according to each battery operating parameter, the corresponding values of the historical detection digital signals according to a time sequence, so as to obtain a time-sequenced value sequence { q }1、q2、…、qn-1、qn}；
A conditional probability calculation subunit, configured to calculate, for the ith data in the numerical value sequence, conditional probability values [ p ] of the ith data after the ith data appears, in which the state of the ith data is known, and the ith-1, ith-2 …, and 1 st data after the ith data appears, respectively1、p2、…、pi-2、pi-1](ii) a Wherein i is more than 1 and less than or equal to n, and n represents the number of numerical values in the numerical value sequence;
a matrix obtaining subunit for obtaining the conditional probability value [ p ]1、p2、…、pi-2、pi-1]And forming a one-dimensional matrix of the transition probability of the multi-order fault symptoms of the corresponding battery operation parameters as a transition probability matrix of the multi-order fault symptoms of the corresponding battery operation parameters.
7. The system according to claim 6, wherein the history data obtaining unit comprises:
the analog signal acquisition subunit is used for acquiring historical detection analog signals of the operating parameters of each battery in the battery system;
and the discrete processing subunit is used for performing discrete processing on the historical detection analog signals of the battery operation parameters to convert the historical detection analog signals into corresponding historical detection digital signals serving as time series historical data of the battery operation parameters.
8. The system of claim 7, wherein the health information obtaining unit is further configured to,
for each battery operation parameter, linearly combining all probability values in a transition probability matrix of the multi-order fault symptom of each battery operation parameter, and determining a linear combination result as a health degree value of the corresponding battery operation parameter corresponding to the health degree value of the battery operation parameter;
linearly combining the values of the degree of health of all the battery operating parameters in the battery systems again, and determining the result of the linear combination as the value of the degree of health of the corresponding battery system.
9. The system of claim 8, wherein the linear combination is summation, multiplication, or averaging.
10. The system of any of claims 6-9, wherein the battery operating parameters include at least one of the following parameter types: the storage battery single body voltage, the storage battery group voltage, the storage battery single body internal resistance, the storage battery single body temperature, the storage battery single body current and the storage battery group current.
11. A computer-readable storage medium comprising a set of computer-executable instructions that, when executed, perform the method of predicting the health of a battery of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477284.6A CN110161418B (en) | 2019-06-03 | 2019-06-03 | Method, system and computer readable storage medium for predicting health of storage battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910477284.6A CN110161418B (en) | 2019-06-03 | 2019-06-03 | Method, system and computer readable storage medium for predicting health of storage battery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110161418A CN110161418A (en) | 2019-08-23 |
| CN110161418B true CN110161418B (en) | 2020-07-03 |
Family
ID=67627502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910477284.6A Active - Reinstated CN110161418B (en) | 2019-06-03 | 2019-06-03 | Method, system and computer readable storage medium for predicting health of storage battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110161418B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111458643B (en) * | 2020-05-22 | 2022-04-15 | 清华四川能源互联网研究院 | Abnormal battery screening method and device, electronic equipment and readable storage medium |
| CN113156326B (en) * | 2021-04-07 | 2022-08-19 | 力高(山东)新能源技术有限公司 | Lithium battery health degree early warning method based on big data |
| CN114415049B (en) * | 2022-01-07 | 2024-03-29 | 中国第一汽车股份有限公司 | Method, device, equipment and storage medium for determining storage battery health degree scoring card |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278777B (en) * | 2013-05-24 | 2015-08-19 | 杭州电子科技大学 | A kind of lithium battery health condition estimation method based on dynamic bayesian network |
| CN103714401A (en) * | 2014-01-21 | 2014-04-09 | 国家电网公司 | Method for predicting distribution and transformation fault frequency of electric network |
| CN105760287B (en) * | 2016-02-19 | 2018-03-20 | 浪潮(北京)电子信息产业有限公司 | The Forecasting Methodology and device of a kind of computer system errors |
| CN108108831B (en) * | 2016-11-24 | 2020-12-04 | 中国移动通信有限公司研究院 | Destination prediction method and device |
| US10719639B2 (en) * | 2017-01-09 | 2020-07-21 | General Electric Company | Massively accelerated Bayesian machine |
| CN108335021B (en) * | 2018-01-19 | 2020-12-08 | 华中科技大学 | Method for evaluating state reliability of wind turbine and maintenance decision optimization |
| CN108564206B (en) * | 2018-03-27 | 2021-08-17 | 中国农业大学 | Wind power prediction method based on distributed optimization and spatial correlation |
-
2019
- 2019-06-03 CN CN201910477284.6A patent/CN110161418B/en active Active - Reinstated
Also Published As
| Publication number | Publication date |
|---|---|
| CN110161418A (en) | 2019-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110161418B (en) | Method, system and computer readable storage medium for predicting health of storage battery | |
| KR101842347B1 (en) | Plant system, and fault detecting method thereof | |
| CN105579922B (en) | Information processing unit and analysis method | |
| CN110909822B (en) | Satellite anomaly detection method based on improved Gaussian process regression model | |
| KR102025145B1 (en) | Apparatus and Method for Predicting Plant Data | |
| CN111767930A (en) | Method for detecting abnormal time series data of Internet of things and related equipment thereof | |
| CN110686633B (en) | Landslide displacement prediction method and device and electronic equipment | |
| EP3674827B1 (en) | Monitoring target selecting device, monitoring target selecting method and program | |
| CN109738220B (en) | Sensor optimal arrangement method based on multi-load working condition structure response correlation | |
| CN110188961B (en) | Method, system and computer readable storage medium for predicting health of power distribution system | |
| CN111984513A (en) | Predictive maintenance method, device, equipment and storage medium | |
| CN114236393B (en) | Method and system for detecting battery abnormality on line based on big data | |
| JP6164311B1 (en) | Information processing apparatus, information processing method, and program | |
| CN110866682B (en) | Underground cable early warning method and device based on historical data | |
| CN110163451B (en) | Health degree prediction method and system for heating and ventilation system and computer readable storage medium | |
| CN110133539B (en) | UPS health degree prediction method, system and computer readable storage medium | |
| CN112380073B (en) | Fault position detection method and device and readable storage medium | |
| CN110175270B (en) | Big data processing method, system and computer readable storage medium | |
| WO2002006953A1 (en) | Soft sensor device and device for evaluating the same | |
| CN112596081B (en) | Health state monitoring method based on correlation health baseline | |
| Chen et al. | Degradation-trend-dependent remaining useful life prediction for bearing with BiLSTM and attention mechanism | |
| CN113569324A (en) | Slope deformation monitoring abnormal data analysis and optimization method | |
| Duan et al. | Prognostics for deteriorating systems under indirect discrete monitoring and random failure | |
| JP2020052676A (en) | State monitor and wind power generator using the same | |
| CN116227239B (en) | Acceleration test data analysis method, device and equipment based on gray prediction model |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200703 Termination date: 20210603 |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| RR01 | Reinstatement of patent right |
Former decision: Termination of patent rights for unpaid annual fees Former decision publication date: 20220607 |
|
| RR01 | Reinstatement of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230413 Address after: 405, West Block, Building 1, Shuntai Plaza, High-tech Zone, Jinan, Shandong Province, 250000 Patentee after: Yunke (Shandong) Electronic Technology Co.,Ltd. Address before: 100012 411, 4th floor, building 5, yard 19, Beiyuan East Road, Chaoyang District, Beijing Patentee before: Beijing Zhongke Austria Creation Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |