CN112881930A - Energy storage battery health management prediction method and system based on Internet of things - Google Patents

Energy storage battery health management prediction method and system based on Internet of things Download PDF

Info

Publication number
CN112881930A
CN112881930A CN202110069586.7A CN202110069586A CN112881930A CN 112881930 A CN112881930 A CN 112881930A CN 202110069586 A CN202110069586 A CN 202110069586A CN 112881930 A CN112881930 A CN 112881930A
Authority
CN
China
Prior art keywords
data
soh
weight
layer
voltage
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.)
Granted
Application number
CN202110069586.7A
Other languages
Chinese (zh)
Other versions
CN112881930B (en
Inventor
魏龙飞
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.)
Beijing Kinglong New Energy Technology Co ltd
Original Assignee
Beijing Kinglong 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 Beijing Kinglong New Energy Technology Co ltd filed Critical Beijing Kinglong New Energy Technology Co ltd
Priority to CN202110069586.7A priority Critical patent/CN112881930B/en
Publication of CN112881930A publication Critical patent/CN112881930A/en
Application granted granted Critical
Publication of CN112881930B publication Critical patent/CN112881930B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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]
    • G01R31/392—Determining battery ageing or deterioration, e.g. state of health
    • 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]
    • G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
    • 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
    • G01R31/387—Determining ampere-hour charge capacity or SoC
    • G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)

Abstract

The invention discloses an energy storage battery health management prediction method and system based on the Internet of things, wherein the prediction method comprises the following steps: step 1: the local BMS module samples and uploads real-time data to the cloud platform through the communication module by combining with the built-in parameters; step 2: the cloud platform acquires data participating in calculation according to the real-time data; and step 3: the cloud platform establishes a battery health model; and 4, step 4: the cloud platform trains the battery health model through data sampled for many times; and 5: the cloud platform obtains an actual SOH value through calculation, and transmits the actual SOH value back to the human-computer interaction module, and the human-computer interaction module displays the actual SOH value.

Description

Energy storage battery health management prediction method and system based on Internet of things
Technical Field
The invention relates to the field of lithium battery health management, in particular to an energy storage battery health management prediction method and system based on the Internet of things.
Background
With the increasing growth of energy storage markets, lithium batteries have started to replace lead-acid batteries due to the characteristics of high energy density, long service life, large power bearing capacity and the like, and meanwhile, the safety of lithium batteries is a certain gap compared with that of lead-acid batteries, so that the health management of batteries becomes an indispensable part in lithium battery systems. In the battery health management, the battery health (state of health, hereinafter referred to as soh) is one of the two most important parameters, and directly determines how much electric energy can be stored in the energy storage system, and is closely related to the calculation of the battery capacity soh, so the importance thereof is needless to say. If the health state and the service life of each battery can be accurately predicted in a complex dynamic use environment, the method has great significance for the echelon utilization of the batteries and the detection of battery faults, and plays a particularly positive role in the safety of a system.
At present, there are two common calculation methods of soh, which are:
first, soh ═ 100% of (ampere-hour integrated electric quantity/open-circuit voltage method electric quantity). The calculation method can obtain the battery health state which is relatively close to the true value only by calculation when the current is stable and low, and in the actual energy storage project, the battery health state is generally in a high-power working state with continuously-changed current. Therefore, it is difficult to reach the condition of calculation soh;
secondly, the health state of the battery is obtained according to the change of the internal resistance of the battery. In the method, the internal resistance of the battery is difficult to obtain intuitively in the actual energy storage project.
Therefore, in an actual energy storage project, how to intuitively and accurately acquire soh of the lithium battery system becomes a problem to be solved in the industry.
Disclosure of Invention
In order to solve the problems, the invention provides an energy storage battery health management prediction system and method based on the internet of things, the relation between the temperature, the cut-off voltage, the current, the current voltage, the battery working time, the cycle times, the soc value (state of charge, which is the percentage of the remaining battery capacity, hereinafter referred to as soc) and the rated capacity and the battery cell soh is established through the training of a platform of the internet of things and a cloud database through a BP neural network algorithm, and under the condition that the more cloud data, the more the battery cell soh is close to the real value, the more the battery cell can be used for intuitively and accurately acquiring soh of a lithium battery system in an actual energy storage project.
In order to achieve the purpose, the invention provides an energy storage battery health management prediction method based on the internet of things, which comprises the following steps:
step 1: the local BMS module samples to combine built-in parameter to pass through communication module to high in the clouds platform upload real-time data, wherein, real-time data includes: current, current soc, current temperature, battery operating time, rated capacity, cycle number, current voltage, charge cutoff voltage, and discharge cutoff voltage;
step 2: the cloud platform acquires data participating in calculation according to the real-time data, wherein the data participating in calculation comprises discharge rate, overcharge and overdischarge times and discharge depth;
and step 3: the cloud platform establishes a battery health model by using the current temperature, discharge rate, discharge depth, cycle times, overcharge and overdischarge times and the current soc obtained in the steps 1 and 2, wherein the battery health model comprises an input layer, a hidden layer and an output layer;
and 4, step 4: the cloud platform trains the battery health model through data sampled for many times;
and 5: the cloud platform obtains an actual SOH value through calculation, and transmits the actual SOH value back to the human-computer interaction module, and the human-computer interaction module displays the actual SOH value.
In an embodiment of the present invention, the method for real-time data sampling in step 1 specifically includes:
acquiring current once every 5 seconds, wherein the current is represented by I and the unit is A;
acquiring a current SOC once every 5 seconds, wherein the current SOC is represented by SOC;
acquiring the current temperature of the battery every 5 seconds, wherein the current temperature is represented by T and has the unit of;
recording the working Time of the battery, wherein the working Time of the battery is represented by Time and the unit is hour;
the rated capacity is obtained only once, and is represented by Cap, and the unit is AH;
recording the number of cycles, which is indicated by CYC;
acquiring current voltage once every 5 seconds, wherein the current voltage is represented by U and the unit is v;
the charge cut-off voltage and the discharge cut-off voltage are obtained only once, and the charge cut-off voltage is VoverThe discharge cut-off voltage is represented by VunderIndicating said charge cut-off voltage and said discharge cut-off voltageThe units are all v.
In an embodiment of the present invention, a specific method for acquiring data involved in the calculation in step 2 is as follows:
discharge rate, calculated by formula C ═ I/Cap, where the discharge rate is C;
the number of overcharge and overdischarge times is expressed by Error, if the current voltage U is>Cut-off voltage V for chargingoverThen, the number of overcharge and overdischarge times Error + 1; if the current voltage U is<Discharge cut-off voltage VunderThen, the number of overcharge and overdischarge times Error + 1; if continuous overcharge and overdischarge exist in the charging and discharging process, the overcharge and overdischarge times Error are accumulated only once;
the depth of discharge, indicated by DOD, is obtained by recording the current soc value at the last occurrence of a current I of 0A.
In an embodiment of the present invention, the input layer, the hidden layer, and the output layer in step 3 are specifically:
the input layer is a data input part of the battery health model, and input data comprise current temperature T, discharge rate C, discharge depth DOD, cycle times CYC and overcharge and overdischarge times Error;
the hidden layer comprises a first layer and a second layer, wherein the first layer comprises two neurons which are respectively H11 and H12; the second layer contains two neurons, H21 and H22 respectively;
the output layer, with SOH values, is represented by SOH.
In an embodiment of the present invention, a specific calculation process of the battery health model on any one acquired data includes first calculating a forward transmission error value of the data, and then calculating a reverse transmission error value, specifically:
s31: from the input layer to the first layer of the hidden layer, the specific calculation process is as follows:
H11＝T×WTH11+C×WCH11+DOD×WDODH11+CYC×WCYCH11+Error×WErrorH11
H12＝T×WTH12+C×WCH12+DOD×WDODH12+CYC×WCYCH12+Error×WErrorH12
in the formula, WTH11Weight between T and H11, WCH11Is a weight between C and H11, WDODH11Is a weight between DOD and H11, WCYCH11Is a weight between CYC and H11, WErrorH11Is a weight between Error and H11, WTH12Weight between T and H12, WCH12Is a weight between C and H12, WDODH12Is a weight between DOD and H12, WCYCH12Is a weight between CYC and H12, WErrorH12Is the weight between Error to H12;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
H11out＝1/(1+eH11)
H12out＝1/(1+eH12)
in the formula, H11outIs an output value of H11, H12outIs the output value of H12, e is a natural constant;
s32: from the first layer of the hidden layer to the second layer of the hidden layer, the specific calculation process is as follows:
H21＝H11out×WH11H21+H12out×WH12H21
H22＝H11out×WH11H22+H12out×WH12H22
in the formula, WH11H21Is a weight between H11 and H21, WH12H21Is a weight between H12 and H21, WH11H22Is a weight between H11 and H22, WH12H22Is a weight between H12 and H22;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
H21out＝1/(1+eH21)
H22out＝1/(1+eH22)
in the formula, H21outIs an output value of H21, H22outAn output value of H22;
s33: from the second layer of the hidden layer to the output layer, the specific calculation process is as follows:
SOH＝H21out×WH21SOH+H22out×WH22SOH
in the formula, WH21SOHWeight between H21 and SOH, WH22SOHWeight between H22 to SOH;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
SOHout＝1/(1+eSOH)
in the formula, SOHoutIs the output value of SOH;
s34: the reverse transmission calculation error value specifically includes:
ETOTAL＝0.5×(SOHT-SOHOUT)2
in the formula, ETOTALAs a total error value, SOHTThe SOH value in the training data, namely the factory SOH value stored in the cloud database.
In an embodiment of the present invention, step 4 specifically includes:
s41: the cloud platform calls factory data prestored in a cloud database;
s42: presetting initial weighted values of all items as 0.1;
s43: training is carried out by continuously repeating the processes of the step 1 to the step 3, and the value of each weight is updated according to the training result each time for the next calculation;
s44: when S43 is repeated 10 ten thousand times, training is stopped, and the weight values at this time are obtained as weights for final calculation.
In an embodiment of the present invention, any weight calculation in step S43 is obtained by combining the chain rule with the forward derivation formula principle, and is represented by WH21SOHFor example, the specific calculation process is as follows:
Figure BDA0002905272330000051
Figure BDA0002905272330000052
in the formula, eta is the learning rate,preset to 0.5; wH21SOH +For the weights between H21 and SOH for the next sample computation,
in the same way, WH11H21The specific calculation process is as follows:
Figure BDA0002905272330000053
Figure BDA0002905272330000054
in the formula, WH11H21 +For the weights between H11 and H21 for the next sample computation,
similarly, the calculation process of other weights adopts the same algorithm.
In an embodiment of the present invention, the specific calculation process of the actual SOH value in step 5 is as follows:
s51: step 1 and step 2 are executed again to obtain real-time sampling data of the lithium battery;
s52: and (4) substituting the weights for each final calculation obtained through training in the step (4) into the calculation process in the step (3) for calculation to obtain the actual SOH value.
In order to achieve the above object, the present invention further provides an energy storage battery health management prediction system based on the internet of things, which includes a local BMS module, a communication module, a human-computer interaction module, a cloud platform and a cloud database, wherein:
the local BMS module is connected with the communication module and used for acquiring battery temperature, real-time current and real-time voltage data and sending the acquired data to the communication module, and the local BMS module comprises an RMU module of a commercial energy storage BMS controller;
the human-computer interaction module is connected with the communication module and used for displaying data, and comprises a CMU module of a commercial energy storage BMS controller;
the communication module is also connected with the cloud platform and used for sending data collected by the local BMS module to the cloud platform, and the communication module comprises WIFI and a 100M network card carried by the CMU module;
the cloud platform is connected with the human-computer interaction module and used for calculating the acquired data and displaying the calculated data to the human-computer interaction module;
the cloud database is connected with the cloud platform and used for storing and calling data.
Compared with the prior art, the invention has the following advantages:
1) by using the cloud end to perform data processing and neural network model training, more effective data can be obtained, meanwhile, the calculation speed is improved, and the problem that the health of the battery cannot be quantized due to the influence of various factors is solved;
2) the real-time calculation of soh is carried out by using the cloud platform, so that a large amount of test time at a Battery Management System (BMS) end is reduced, the functions of a BMS board are simplified, a complex internal resistance test circuit and a complex internal resistance calculation method are not needed any more, and the calculation efficiency is high;
3) the generation of accumulated errors is reduced through the training of the training model, meanwhile, various factors influencing the health of the battery are considered, and the precision and the accuracy of soh are remarkably improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of a battery health model according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating weight calculation and update in a battery health model according to an embodiment of the present invention;
FIG. 3 is a system architecture diagram of an embodiment of the present invention;
description of reference numerals: 101-local BMS module; 102-a communication module; 103-a human-computer interaction module; 104-cloud platform; 105-cloud database.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious 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 obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
An embodiment of the invention provides an energy storage battery health management prediction method based on the Internet of things, which comprises the following steps:
step 1: local BMS module samples to combine built-in parameter etc. to upload real-time data to high in the clouds platform through communication module, wherein the real-time data of uploading includes: current, current soc, current temperature, battery operating time, rated capacity, cycle number, current voltage, charge cutoff voltage, discharge cutoff voltage.
The method for sampling the real-time data specifically comprises the following steps:
acquiring current once every 5 seconds, wherein the current is represented by I and the unit is A;
acquiring the current SOC once every 5 seconds, wherein the current SOC is represented by SOC;
acquiring the current temperature of the battery every 5 seconds, wherein the current temperature is represented by T and the unit is;
recording the working Time of the battery, wherein the working Time of the battery is represented by Time and the unit is hour;
the rated capacity is obtained only once, and is represented by Cap, and the unit is AH;
recording the cycle times, which are indicated by CYC;
acquiring current voltage every 5 seconds, wherein the current voltage is represented by U and the unit is v;
the charge cut-off voltage and the discharge cut-off voltage are obtained only once, and the charge cut-off voltage is VoverIndicating that the discharge cut-off voltage is VunderIndicating, charge cut-off voltage and dischargeThe units of the cut-off voltage are v.
Step 2: the cloud platform acquires data participating in calculation according to the acquired real-time data, wherein the data participating in calculation comprises discharge multiplying power, overcharge and overdischarge times and discharge depth.
The specific acquisition method of the data participating in the calculation specifically comprises the following steps:
the discharge multiplying power is calculated by a formula C-I/Cap, wherein the discharge multiplying power is C;
the number of overcharge and overdischarge times is expressed by Error, if the current voltage U is>Cut-off voltage V for chargingoverThen, the number of overcharge and overdischarge times Error + 1; if the current voltage U is<Discharge cut-off voltage VunderThen, the number of overcharge and overdischarge times Error + 1; if continuous overcharge and overdischarge exist in the charging and discharging process, the overcharge and overdischarge times Error are accumulated only once;
the depth of discharge, indicated by DOD, is obtained by recording the current soc value at the last occurrence of a current I of 0A.
And step 3: the cloud platform establishes a battery health model by using the current temperature T, the discharge rate C, the discharge depth DOD, the cycle times CYC, the overcharge and overdischarge times Error and the current soc (battery health parameter) obtained in the steps 1 and 2, wherein the battery health model comprises an input layer, a hidden layer and an output layer.
Fig. 1 is a schematic structural diagram of a battery health model according to an embodiment of the present invention, as shown in fig. 1, wherein the input layer, the hidden layer, and the output layer in step 3 are specifically:
the input layer is a data input part of the battery health model, and input data comprise current temperature T, discharge rate C, discharge depth DOD, cycle times CYC and overcharge and overdischarge times Error;
the hidden layer comprises a first layer and a second layer, wherein the first layer comprises two neurons which are respectively H11 and H12; the second layer contains two neurons, H21 and H22 respectively;
the output layer, with SOH values, is represented by SOH.
In this embodiment, the specific calculation process of the battery health model on any one acquired data is to calculate forward transmission of data first, and then calculate an error value by backward transmission, specifically:
s31: from the input layer to the first layer of the hidden layer, the specific calculation process is as follows:
H11＝T×WTH11+C×WCH11+DOD×WDODH11+CYC×WCYCH11+Error×WErrorH11
H12＝T×WTH12+C×WCH12+DOD×WDODH12+CYC×WCYCH12+Error×WErrorH12
in the formula, WTH11Weight between T and H11, WCH11Is a weight between C and H11, WDODH11Is a weight between DOD and H11, WCYCH11Is a weight between CYC and H11, WErrorH11Is a weight between Error and H11, WTH12Weight between T and H12, WCH12Is a weight between C and H12, WDODH12Is a weight between DOD and H12, WCYCH12Is a weight between CYC and H12, WErrorH12Is the weight between Error to H12;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
H11out＝1/(1+eH11)
H12out＝1/(1+eH12)
in the formula, H11outIs an output value of H11, H12outH12, e is a natural constant (with a value of about 2.718281828459045);
s32: from the first layer of the hidden layer to the second layer of the hidden layer, the specific calculation process is as follows:
H21＝H11out×WH11H21+H12out×WH12H21
H22＝H11out×WH11H22+H12out×WH12H22
in the formula, WH11H21Is a weight between H11 and H21, WH12H21Is a weight between H12 and H21, WH11H22Is a weight between H11 and H22, WH12H22Is a weight between H12 and H22;
use ofActivation function y (x) 1/(1+ e)x) Processing the data to obtain:
H21out＝1/(1+eH21)
H22out＝1/(1+eH22)
in the formula, H21outIs an output value of H21, H22outAn output value of H22;
s33: from the second layer of the hidden layer to the output layer, the specific calculation process is as follows:
SOH＝H21out×WH21SOH+H22out×WH22SOH
in the formula, WH21SOHWeight between H21 and SOH, WH22SOHWeight between H22 to SOH;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
SOHout＝1/(1+eSOH)
in the formula, SOHoutIs the output value of SOH;
s34: the reverse transmission calculation error value specifically includes:
ETOTAL＝0.5×(SOHT-SOHOUT)2
in the formula, ETOTALAs a total error value, SOHTThe SOH value in the training data, namely the factory SOH value stored in the cloud database. Generally, a battery manufacturer will give a factory-specified SOH value, and in this embodiment, the factory-specified SOH value is prestored in the cloud database as the SOH value of the training data, which is used for training the battery health model to obtain a more accurate actual SOH value.
And 4, step 4: and the cloud platform trains the battery health model through the data sampled for many times.
Wherein, the step 4 is specifically as follows:
s41: the cloud platform calls factory data prestored in a cloud database; in this embodiment, the factory data pre-stored in the cloud database includes, for example, the factory SOH value and the factory values of the data used in the calculation process of the present invention.
S42: presetting initial weighted values of all items as 0.1;
s43: training is carried out by continuously repeating the processes of the step 1 to the step 3, and the value of each weight is updated according to the training result each time for the next calculation;
s44: when S43 is repeated for 10 ten thousand times, the training is stopped, and the weight values at the moment are obtained as the weights for final calculation, wherein each weight is WH21SOH、WTH11、WCH11、WDODH11、WCYCH11、WErrorH11、WTH12、WCH12、WDODH12、WCYCH12、WErrorH12、WH11H21、WH12H21、WH11H22、WH12H22And WH22SOH。
In an embodiment of the present invention, weights of the battery health model in the training process are dynamic values, the weights of the battery health model in the first sampling calculation are preset values, and from the second sampling, the weights of the battery health model in each sampling calculation are calculated and updated according to the trained values of the previous sampling, fig. 2 is a schematic diagram of weight calculation and update in the battery health model in an embodiment of the present invention, as shown in fig. 2, any weight calculation in step S43 is obtained by combining a chain rule with a forward derivation formula principle, and W is calculated according to a W lawH21SOHFor example, the specific calculation process is as follows:
Figure BDA0002905272330000111
Figure BDA0002905272330000112
where η is the learning rate, which is preset to 0.5 in this embodiment; wH21SOH +For the weights between H21 and SOH for the next sample computation,
in the same way, WH11H21The specific calculation process is as follows:
Figure BDA0002905272330000113
Figure BDA0002905272330000114
in the formula, WH11H21 +For the weights between H11 and H21 for the next sample computation,
similarly, the calculation processes of other weights adopt the same algorithm, and are not described herein again.
And 5: the cloud platform obtains an actual SOH value through calculation, and transmits the actual SOH value back to the human-computer interaction module, and the human-computer interaction module displays the actual SOH value.
Wherein, the actual SOH value in step 5 is calculated in the following specific process:
s51: step 1 and step 2 are executed again to obtain real-time sampling data of the lithium battery;
s52: and (4) substituting the weights for each final calculation obtained through training in the step (4) into the calculation process in the step (3) for calculation to obtain the actual SOH value.
Fig. 3 is a system architecture diagram of an embodiment of the present invention, and as shown in fig. 3, an embodiment of the present invention provides an energy storage battery health management prediction system based on the internet of things, which includes a local BMS module (101), a communication module (102), a human-computer interaction module (103), a cloud platform (104), and a cloud database (105), wherein:
the local BMS module (101) is connected with the communication module (102) and is used for acquiring battery temperature, real-time current and real-time voltage data and sending the acquired data to the communication module (102), and the local BMS module (101) comprises an RMU module of a commercial energy storage BMS controller, wherein an RMU (remote management unit) is a remote monitoring unit and is hereinafter referred to as RMU;
the man-machine interaction module (103) is connected with the communication module (102) and used for displaying data, and the man-machine interaction module (103) comprises a CMU (cell monitor Unit) module of the commercial energy storage BMS controller, wherein the CMU is a single monitoring unit, which is hereinafter referred to as CMU for short;
the communication module (102) is also connected with the cloud end platform (104) and is used for sending data acquired by the local BMS module (101) to the cloud end platform (104), and the communication module (102) comprises WIFI and a 100M network card of a CMU module of the man-machine interaction module (103);
the cloud platform (104) is connected with the human-computer interaction module (103) and is used for calculating the acquired data and displaying the calculated data to the human-computer interaction module (103);
the cloud database (105) is connected with the cloud platform (104) and used for storing and calling data.
According to the invention, the cloud is used for data processing and neural network model training, so that more effective data can be obtained, the calculation speed is increased, and the problem that the health of the battery cannot be quantized due to the influence of various factors is solved; the real-time calculation of soh is carried out by using the cloud platform, so that a large amount of test time of a BMS terminal is reduced, the functions of a BMS board are simplified, a complex internal resistance test circuit and a calculation method are not needed, and the calculation efficiency is high; in addition, the generation of accumulated errors is reduced through the training of the training model, various factors influencing the health of the battery are considered, and the accuracy and the precision of soh are obviously improved.
Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (9)

1. An energy storage battery health management prediction method based on the Internet of things is characterized by comprising the following steps:
step 1: the local BMS module samples to combine built-in parameter to pass through communication module to high in the clouds platform upload real-time data, wherein, real-time data includes: current, current soc, current temperature, battery operating time, rated capacity, cycle number, current voltage, charge cutoff voltage, and discharge cutoff voltage;
step 2: the cloud platform acquires data participating in calculation according to the real-time data, wherein the data participating in calculation comprises discharge rate, overcharge and overdischarge times and discharge depth;
and step 3: the cloud platform establishes a battery health model by using the current temperature, discharge rate, discharge depth, cycle times, overcharge and overdischarge times and the current soc obtained in the steps 1 and 2, wherein the battery health model comprises an input layer, a hidden layer and an output layer;
and 4, step 4: the cloud platform trains the battery health model through data sampled for many times;
and 5: the cloud platform obtains an actual SOH value through calculation, and transmits the actual SOH value back to the human-computer interaction module, and the human-computer interaction module displays the actual SOH value.
2. The method according to claim 1, wherein the real-time data sampling method in step 1 specifically comprises:
acquiring current once every 5 seconds, wherein the current is represented by I and the unit is A;
acquiring a current SOC once every 5 seconds, wherein the current SOC is represented by SOC;
acquiring the current temperature of the battery every 5 seconds, wherein the current temperature is represented by T and has the unit of;
recording the working Time of the battery, wherein the working Time of the battery is represented by Time and the unit is hour;
the rated capacity is obtained only once, and is represented by Cap, and the unit is AH;
recording the number of cycles, which is indicated by CYC;
acquiring current voltage once every 5 seconds, wherein the current voltage is represented by U and the unit is v;
the charge cut-off voltage and the discharge cut-off voltage are obtained only once, and the charge cut-off voltage is VoverThe discharge cut-off voltage is represented by VunderThe charge cut-off voltage and the discharge cut-off voltage are both expressed in units of v.
3. The method according to claim 1, wherein the specific acquisition method of the data involved in the calculation in the step 2 is as follows:
discharge rate, calculated by formula C ═ I/Cap, where the discharge rate is C;
the number of overcharge and overdischarge times is expressed by Error, if the current voltage U is>Cut-off voltage V for chargingoverThen, the number of overcharge and overdischarge times Error + 1; if the current voltage U is<Discharge cut-off voltage VunderThen, the number of overcharge and overdischarge times Error + 1; if continuous overcharge and overdischarge exist in the charging and discharging process, the overcharge and overdischarge times Error are accumulated only once;
the depth of discharge, indicated by DOD, is obtained by recording the current soc value at the last occurrence of a current I of 0A.
4. The method according to claim 1, wherein the input layer, the hidden layer and the output layer in step 3 are specifically:
the input layer is a data input part of the battery health model, and input data comprise current temperature T, discharge rate C, discharge depth DOD, cycle times CYC and overcharge and overdischarge times Error;
the hidden layer comprises a first layer and a second layer, wherein the first layer comprises two neurons which are respectively H11 and H12; the second layer comprises two neurons, H21 and H22, respectively;
the output layer, having a value of SOH, is represented by SOH.
5. The method according to claim 4, wherein the specific calculation process of the battery health model for any one collected data is to calculate forward transmission of data first and then calculate an error value by backward transmission, specifically:
s31: from the input layer to the first layer of the hidden layer, the specific calculation process is as follows:
H11＝T×WTH11+C×WCH11+DOD×WDODH11+CYC×WCYCH11+Error×WErrorH11
H12＝T×WTH12+C×WCH12+DOD×WDODH12+CYC×WCYCH12+Error×WErrorH12
in the formula, WTH11Weight between T and H11, WCH11Is a weight between C and H11, WDODH11Is a weight between DOD and H11, WCYCH11Is a weight between CYC and H11, WErrorH11Is a weight between Error and H11, WTH12Weight between T and H12, WCH12Is a weight between C and H12, WDODH12Is a weight between DOD and H12, WCYCH12Is a weight between CYC and H12, WErrorH12Is the weight between Error to H12;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
H11out＝1/(1+eH11)
H12out＝1/(1+eH12)
in the formula, H11outIs an output value of H11, H12outIs the output value of H12, e is a natural constant;
s32: from the first layer of the hidden layer to the second layer of the hidden layer, the specific calculation process is as follows:
H21＝H11out×WH11H21+H12out×WH12H21
H22＝H11out×WH11H22+H12out×WH12H22
in the formula, WH11H21Is a weight between H11 and H21, WH12H21Is a weight between H12 and H21, WH11H22Is a weight between H11 and H22, WH12H22Is a weight between H12 and H22;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
H21out＝1/(1+eH21)
H22out＝1/(1+eH22)
in the formula, H21outIs an output value of H21, H22outAn output value of H22;
s33: from the second layer of the hidden layer to the output layer, the specific calculation process is as follows:
SOH＝H21out×WH21SOH+H22out×WH22SOH
in the formula, WH21SOHWeight between H21 and SOH, WH22SOHWeight between H22 to SOH;
using the activation function y (x) 1/(1+ e)x) Processing the data to obtain:
SOHout＝1/(1+eSOH)
in the formula, SOHoutIs the output value of SOH;
s34: the reverse transmission calculation error value specifically includes:
ETOTAL＝0.5×(SOHT-SOHOUT)2
in the formula, ETOTALAs a total error value, SOHTThe SOH value in the training data, namely the factory SOH value stored in the cloud database.
6. The method according to claim 1, wherein step 4 is specifically:
s41: the cloud platform calls factory data prestored in a cloud database;
s42: presetting initial weighted values of all items as 0.1;
s43: training is carried out by continuously repeating the processes of the step 1 to the step 3, and the value of each weight is updated according to the training result each time for the next calculation;
s44: when S43 is repeated 10 ten thousand times, training is stopped, and the weight values at this time are obtained as weights for final calculation.
7. The method according to claim 6, wherein the weight calculation in step S43 is performed by a chain rule combined with a forward derivation formula principle, and W is used as the weight calculation ruleH21SOHFor example, the specific calculation process is as follows:
Figure FDA0002905272320000041
Figure FDA0002905272320000042
in the formula, eta is a learning rate and is preset to be 0.5; wH21SOH +For the weights between H21 and SOH for the next sample computation,
in the same way, WH11H21The specific calculation process is as follows:
Figure FDA0002905272320000043
Figure FDA0002905272320000044
in the formula, WH11H21 +For the weights between H11 and H21 for the next sample computation,
similarly, the calculation process of other weights adopts the same algorithm.
8. The method of claim 7, wherein the actual SOH value in step 5 is calculated by:
s51: step 1 and step 2 are executed again to obtain real-time sampling data of the lithium battery;
s52: and (4) substituting the weights for each final calculation obtained through training in the step (4) into the calculation process in the step (3) for calculation to obtain the actual SOH value.
9. The utility model provides an energy storage battery health management prediction system based on thing networking, its characterized in that includes local BMS module, communication module, human-computer interaction module, high in the clouds platform and high in the clouds database, wherein:
the local BMS module is connected with the communication module and used for acquiring battery temperature, real-time current and real-time voltage data and sending the acquired data to the communication module, and the local BMS module comprises an RMU module of a commercial energy storage BMS controller;
the human-computer interaction module is connected with the communication module and used for displaying data, and comprises a CMU module of a commercial energy storage BMS controller;
the communication module is also connected with the cloud platform and used for sending data collected by the local BMS module to the cloud platform, and the communication module comprises WIFI and a 100M network card carried by the CMU module;
the cloud platform is connected with the human-computer interaction module and used for calculating the acquired data and displaying the calculated data to the human-computer interaction module;
the cloud database is connected with the cloud platform and used for storing and calling data.
CN202110069586.7A 2021-01-19 2021-01-19 Energy storage battery health management prediction method and system based on Internet of things Active CN112881930B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110069586.7A CN112881930B (en) 2021-01-19 2021-01-19 Energy storage battery health management prediction method and system based on Internet of things

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110069586.7A CN112881930B (en) 2021-01-19 2021-01-19 Energy storage battery health management prediction method and system based on Internet of things

Publications (2)

Publication Number Publication Date
CN112881930A true CN112881930A (en) 2021-06-01
CN112881930B CN112881930B (en) 2023-07-18

Family

ID=76049793

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110069586.7A Active CN112881930B (en) 2021-01-19 2021-01-19 Energy storage battery health management prediction method and system based on Internet of things

Country Status (1)

Country Link
CN (1) CN112881930B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113612269A (en) * 2021-07-02 2021-11-05 国网山东省电力公司莱芜供电公司 Battery monomer charging and discharging control method and system for lead-acid storage battery energy storage station
CN114089190A (en) * 2021-11-11 2022-02-25 力高(山东)新能源技术有限公司 Battery SOC estimation method based on neural network
CN115792627A (en) * 2022-11-14 2023-03-14 上海玫克生储能科技有限公司 Lithium battery SOH analysis and prediction method and device, electronic equipment and storage medium
CN116400227A (en) * 2023-06-08 2023-07-07 长安大学 SOH prediction method, system, equipment and medium for power battery of electric automobile
CN116609686A (en) * 2023-04-18 2023-08-18 江苏果下科技有限公司 Battery cell consistency assessment method based on cloud platform big data

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109633452A (en) * 2018-12-24 2019-04-16 广东省智能制造研究所 A kind of battery health degree detection method and detection device
CN109768589A (en) * 2018-12-20 2019-05-17 北京昆兰新能源技术有限公司 A kind of battery voltage balanced equipment
CN110015162A (en) * 2017-06-30 2019-07-16 宝沃汽车（中国）有限公司 Cell health state detection method, device and system and storage medium
CN110386027A (en) * 2019-06-19 2019-10-29 东北大学 The battery for electric automobile management system that cloud computing and edge calculations combine
CN110659722A (en) * 2019-08-30 2020-01-07 江苏大学 AdaBoost-CBP neural network-based electric vehicle lithium ion battery health state estimation method
CN111157897A (en) * 2019-12-31 2020-05-15 国网北京市电力公司 Method and device for evaluating power battery, storage medium and processor
CN111366848A (en) * 2019-12-31 2020-07-03 安徽师范大学 Battery health state prediction method based on PSO-ELM algorithm
US20200300920A1 (en) * 2019-03-19 2020-09-24 Battelle Energy Alliance, Llc Multispectral impedance determination under dynamic load conditions
CN112098845A (en) * 2020-08-17 2020-12-18 四川大学 Lithium battery state estimation method for distributed energy storage system

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110015162A (en) * 2017-06-30 2019-07-16 宝沃汽车（中国）有限公司 Cell health state detection method, device and system and storage medium
CN109768589A (en) * 2018-12-20 2019-05-17 北京昆兰新能源技术有限公司 A kind of battery voltage balanced equipment
CN109633452A (en) * 2018-12-24 2019-04-16 广东省智能制造研究所 A kind of battery health degree detection method and detection device
US20200300920A1 (en) * 2019-03-19 2020-09-24 Battelle Energy Alliance, Llc Multispectral impedance determination under dynamic load conditions
CN110386027A (en) * 2019-06-19 2019-10-29 东北大学 The battery for electric automobile management system that cloud computing and edge calculations combine
CN110659722A (en) * 2019-08-30 2020-01-07 江苏大学 AdaBoost-CBP neural network-based electric vehicle lithium ion battery health state estimation method
CN111157897A (en) * 2019-12-31 2020-05-15 国网北京市电力公司 Method and device for evaluating power battery, storage medium and processor
CN111366848A (en) * 2019-12-31 2020-07-03 安徽师范大学 Battery health state prediction method based on PSO-ELM algorithm
CN112098845A (en) * 2020-08-17 2020-12-18 四川大学 Lithium battery state estimation method for distributed energy storage system

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
刘大同 等: "锂离子电池健康评估和寿命预测综述", 仪器仪表学报, no. 01, pages 5 - 20 *
李超然 等: "基于卷积神经网络的锂离子电池SOH估算", 电工技术学报, no. 19, pages 116 - 129 *
熊杰 等: "基于BP神经网络的超声波温湿度补偿算法研究与应用", 《现代电子技术》 *
熊杰 等: "基于BP神经网络的超声波温湿度补偿算法研究与应用", 《现代电子技术》, vol. 43, no. 09, 31 May 2020 (2020-05-31), pages 113 - 116 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113612269A (en) * 2021-07-02 2021-11-05 国网山东省电力公司莱芜供电公司 Battery monomer charging and discharging control method and system for lead-acid storage battery energy storage station
CN113612269B (en) * 2021-07-02 2023-06-27 国网山东省电力公司莱芜供电公司 Method and system for controlling charge and discharge of battery monomer of lead-acid storage battery energy storage station
CN114089190A (en) * 2021-11-11 2022-02-25 力高(山东)新能源技术有限公司 Battery SOC estimation method based on neural network
CN114089190B (en) * 2021-11-11 2023-08-22 深圳力高新能技术有限公司 Battery SOC estimation method based on neural network
CN115792627A (en) * 2022-11-14 2023-03-14 上海玫克生储能科技有限公司 Lithium battery SOH analysis and prediction method and device, electronic equipment and storage medium
CN116609686A (en) * 2023-04-18 2023-08-18 江苏果下科技有限公司 Battery cell consistency assessment method based on cloud platform big data
CN116609686B (en) * 2023-04-18 2024-01-05 江苏果下科技有限公司 Battery cell consistency assessment method based on cloud platform big data
CN116400227A (en) * 2023-06-08 2023-07-07 长安大学 SOH prediction method, system, equipment and medium for power battery of electric automobile

Also Published As

Publication number Publication date
CN112881930B (en) 2023-07-18

Similar Documents

Publication Publication Date Title
CN112881930A (en) Energy storage battery health management prediction method and system based on Internet of things
CN107957562B (en) Online prediction method for residual life of lithium ion battery
CN106093778B (en) Battery status prediction technique and system
CN106443473A (en) SOC estimation method for power lithium ion battery group
CN115114878B (en) Method and device for online prediction of battery life of energy storage power station and storage medium
FR3013514A1 (en) DEVICE AND METHOD FOR RECHARGING ELECTRIC OR HYBRID VEHICLES
Zhu et al. The SOH estimation of LiFePO4 battery based on internal resistance with Grey Markov Chain
CN107769335A (en) A kind of multi-mode lithium battery intelligent charging management method and device
Lu et al. Modeling discharge characteristics for predicting battery remaining life
CN113777501A (en) SOH estimation method of battery module
CN114624604A (en) Battery life prediction model generation method, battery life prediction model prediction method, battery life prediction device, and electronic equipment
CN112946480B (en) Lithium battery circuit model simplification method for improving SOC estimation real-time performance
CN117074955A (en) Cloud-end correction OCV-based lithium battery state joint estimation method
CN115577750A (en) Method, device and equipment for estimating system-level state of charge of energy storage power station
CN109633468B (en) Method for testing power characteristics of lithium ion battery
CN114764124A (en) Lithium battery SOC estimation method based on GAN and LSTM
CN114492182A (en) Method for predicting cycle life of battery pack in any topological structure
Kim et al. Design of State of Charge and Health Estimation for Li-ion Battery Management System
Bu et al. State of charge estimation of lithium-ion battery considering aging degree and external factors based on gradient boosting regression tree
CN112798974B (en) Storage battery SOH on-line monitoring method and system for isolated base station hybrid power supply system
CN113391225B (en) Lithium battery state-of-charge estimation method considering capacity degradation
Zhao An Improved EKF Algorithm for SOC Estimation of Lithium Battery Considering Temperature Effects
CN204462348U (en) The acquisition equipment of battery charge state
CN113866654A (en) BMS structure based on proprietary SOC estimation and proprietary equalization algorithm
Liu et al. SOC Estimation of Ship Lithium Battery Based on UKF-VFFRLS

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