CN113671382A - Battery energy storage system state estimation method based on cloud-end digital twinning - Google Patents
Battery energy storage system state estimation method based on cloud-end digital twinning Download PDFInfo
- Publication number
- CN113671382A CN113671382A CN202111036904.6A CN202111036904A CN113671382A CN 113671382 A CN113671382 A CN 113671382A CN 202111036904 A CN202111036904 A CN 202111036904A CN 113671382 A CN113671382 A CN 113671382A
- Authority
- CN
- China
- Prior art keywords
- energy storage
- battery
- storage system
- data
- model
- 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.)
- Pending
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 230000032683 aging Effects 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 230000003993 interaction Effects 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 5
- 230000018109 developmental process Effects 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 4
- 238000003745 diagnosis Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 238000009423 ventilation Methods 0.000 claims description 2
- 230000005518 electrochemistry Effects 0.000 claims 1
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 238000013500 data storage Methods 0.000 abstract description 2
- 238000004088 simulation Methods 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 description 6
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 5
- 229910052744 lithium Inorganic materials 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004138 cluster model Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 229910001416 lithium ion Inorganic materials 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- FKNQFGJONOIPTF-UHFFFAOYSA-N Sodium cation Chemical compound [Na+] FKNQFGJONOIPTF-UHFFFAOYSA-N 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011017 operating method Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 229910001415 sodium ion Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 229910052720 vanadium Inorganic materials 0.000 description 1
- LEONUFNNVUYDNQ-UHFFFAOYSA-N vanadium atom Chemical compound [V] LEONUFNNVUYDNQ-UHFFFAOYSA-N 0.000 description 1
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]
- G01R31/367—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]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention provides a battery energy storage system state estimation method based on cloud-end digital twinning, which utilizes data storage and computing capacity of a cloud platform. By using data from a multitude of battery energy storage systems distributed at different sites. All necessary data and information are collected in the cloud platform and can be used for identifying main parameters of different models through AI algorithms. In addition, the model in the cloud can be optimized in time according to real-time data and information from the local battery energy storage system. In this way, the model is a digital twin of the actual battery energy storage system in the field. Compared with a traditional model-based control system or a simulation system, the digital twin model is more adaptive and accurate. The battery energy storage system generates a large amount of data in real time and is suitable for establishing a digital twin model.
Description
Technical Field
The invention relates to the field of electric power, in particular to a battery energy storage system state estimation method based on cloud-end digital twinning.
Background
Battery energy storage is considered to be critical for future renewable energy based power systems. Lithium batteries have potential in this area, currently occupying the largest share of the emerging energy storage market. However, the safety and optimized operation of lithium batteries remain the biggest concern in the industry. Also, control methods such as local BMS have encountered great difficulty in identifying battery state of charge and state of health due to problems with data analysis and models.
Battery Energy Storage Systems (BESS) play an increasingly important role in power systems, especially for the high permeability of renewable energy sources such as wind power and photovoltaic power generation. Battery energy storage systems are considered to be a key factor in future zero-carbon power systems. The novel energy storage technologies such as lithium ion batteries, vanadium redox flow batteries, compressed air energy storage, flywheel energy storage and sodium ion batteries have wide prospects.
Lithium ion battery energy storage systems consist of a large number of small battery cells through a typical assembly and Battery Management System (BMS). The BMS provides critical information including state of charge (SOC), state of health (SOH), and Remaining Useful Life (RUL) to a Power Conversion System (PCS) and an Energy Management System (EMS). However, currently BMS are not adequate for this task because: (1) whether the lithium battery is charged, discharged or in an idle state, the electrochemical process of the lithium battery is very complex, and a physical model and an equivalent model of the lithium battery are difficult to accurately describe through measurement and calculation. (2) Data-driven models and artificial intelligence algorithms should be more efficient, but the data of one energy storage system itself is difficult to support the evolution of the intelligent algorithms, and local controllers often do not provide enough computing power to provide large data processing and calculations. (3) Furthermore, the above model does not reflect the aging, environmental and operating conditions that are occurring over time in the battery.
Disclosure of Invention
In order to solve the technical problem, the invention provides a battery energy storage system state estimation method based on cloud-end number twinning, which utilizes the data storage and calculation capacity of a cloud platform. By utilizing the data of more battery energy storage systems distributed at different sites. All necessary data and information are collected in the cloud platform and can be used for identifying main parameters of different models through AI algorithms. In addition, the model in the cloud platform can be optimized in time according to real-time data and information from each local battery energy storage system. In this way, the model becomes a digital twin of the actual battery energy storage system on site. The digital twin is more adaptive and accurate than traditional model-based control systems or simulation systems. The battery energy storage system generates a large amount of operation data and state data and information in real time, and is suitable for establishing a digital twin DT (digital twin).
The technical scheme of the invention is as follows: a battery energy storage system state estimation method based on cloud-end digital twinning comprises the following steps:
step 2, the end processor uploads the collected and analyzed local energy storage system data and information to a cloud computing center database, the model database of the cloud computing center is configured with a plurality of typical battery system models, the model databases have a plurality of different levels of battery cores, modules, battery clusters and battery systems, and the installation mode, the operation age and the dynamic ring characteristics are different;
step 3, establishing a digital twin model of the battery energy storage system, and continuously optimizing and periodically correcting parameters of the digital twin model by a data-driven intelligent algorithm through a cloud computing center according to actual operation data and information of a large number of energy storage systems to form a digital twin body of the energy storage system; continuously comparing the predicted data of the digital twin body with the operation data of the actual energy storage system, and optimally adjusting the model parameters to ensure that the model of the twin body has strong adaptability and accuracy;
and 4, predicting the state of each battery energy storage system by the digital twin body, realizing state estimation and residual life prediction according to the predicted state of each battery energy storage system, diagnosing, predicting and early warning potential faults, timely transmitting the potential faults to an end processor by a cloud computing center, and timely adjusting basic parameters of a state computing model, early warning at each level and warning threshold values by the end processor according to received information to provide services for the optimized operation and intelligent operation and maintenance of the battery energy storage system.
Has the advantages that:
the invention collects and analyzes all real-time data from all dispersed battery energy storage systems, establishes a cloud-end combined digital twin body to analyze the battery energy storage systems in time for modeling and parameter identification, and provides corresponding state estimation and fault diagnosis prediction, thereby providing a more accurate and self-adaptive adjustment modeling solution. By collecting and processing BMS, PCS, EMS, and dynamic loop accessory data, battery system status and faults are reviewed from the entire system rather than the battery itself. The structure of the digital twin is developed and the operating mechanism is established. In addition, a battery series connection cluster model based on a machine learning algorithm and an SOC and SOH estimation method thereof are provided. This operation provides a useful reference for a safe and reliable battery energy storage system.
Drawings
FIG. 1 is a schematic diagram of a component structure of a battery energy storage system;
FIG. 2 is a digital twin map of a battery energy storage system;
FIG. 3 is a schematic diagram of a digital twin operating mechanism of the battery energy storage system;
fig. 4 is a schematic diagram of a davinin model of a series battery.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying 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, rather than all embodiments, and all other embodiments obtained by a person skilled in the art based on the embodiments of the present invention belong to the protection scope of the present invention without creative efforts.
According to an embodiment of the invention, a method for estimating a state of a battery energy storage system based on cloud-end digital twins is provided, which includes the following steps:
step 2, the end processor uploads the collected and analyzed local energy storage system data and information to a cloud computing center database, the model database of the cloud computing center database is configured with a plurality of typical battery system models, the models have a plurality of different levels of battery cores, modules, battery clusters and battery systems, and the models are different in installation mode, operation age and dynamic ring characteristics;
step 3, establishing a digital twin model of the battery energy storage system, and continuously optimizing and periodically correcting parameters of the digital twin model by a data-driven intelligent algorithm through a cloud computing center according to actual operation data and information of a large number of energy storage systems to form a digital twin body of the energy storage system; continuously comparing the predicted data of the digital twin body with the operation data of the physical entity of the energy storage system, and optimally adjusting the parameters of the model to ensure that the model of the twin body has strong adaptability and accuracy;
and 4, predicting the state of each battery energy storage system by the digital twin body, realizing state estimation and residual life prediction according to the predicted state of each battery energy storage system, predicting and early warning potential faults, timely transmitting the potential faults to the end processor by the cloud computing center, and timely adjusting basic parameters of a state computing model, early warning at each level and warning threshold values by the end processor according to received information to provide services for the optimized operation and intelligent operation and maintenance of the battery energy storage system.
Specifically, the technical scheme of the invention is explained in detail as follows:
according to an embodiment of the present invention, the battery energy storage system generally includes auxiliary devices such as a battery cell, a BMS, an Air Conditioner (AC) system, a fire protection system, a PCS, a grid-connected point, and an EMS. A schematic of a typical battery energy storage system is shown in fig. 1.
It should be noted that Pack in the figure is generally a basic unit of a battery system, and is composed of a plurality of battery modules with BMS and cooling device, and the battery modules are composed of a plurality of specially designed and assembled battery cells. Therefore, the performance of the battery system depends largely on the Pack design.
The PCS is also very important for battery energy storage systems because it is controlled to perform specific modes of operation, such as charging and discharging of batteries, grid-tie operation, islanding operation, frequency and voltage regulation. Good electrical performance on both the ac and dc sides of the PCS is important to both the grid and the battery.
For the digital twin model system, a specially designed local controller is needed as a terminal for data acquisition and processing, local control and protection of the local battery energy storage system. In addition, the local controller sends all necessary data and information to the cloud platform and receives instructions from the cloud platform to optimize model parameters and control system operation. All necessary data is collected from BMS, PCS, grid, environmental and fire systems to better understand the battery energy storage system from big data and data driven modeling aspects. Only then too can the battery be inspected, not only by the battery itself, but also by its operating process and environment.
Each battery cell, module, Pack, and other device in the battery energy storage system has its own aging or failure process. Knowing their failure modes is the basis for data-driven modeling and control by local controllers and cloud centers. The invention develops a battery energy storage system fault database, and the main relation is shown in table 1.
Detailed information identifying and characterizing the equipment aging or failure process is stored in the failure database. Once the data sent by the special battery energy storage system is identified by the database, the optimization and protection actions of the model can be triggered, and the safety and optimization of the battery energy storage system are ensured.
According to one embodiment of the invention, the proposed digital twin model of the battery energy storage system is shown in fig. 2 and comprises physical and digital parts, including an actual battery energy storage system with local controller and a cloud digital twin with data-based modeling and state estimation of the battery system.
According to one embodiment of the present invention, the actual battery energy storage system with the local controller is specifically as follows:
this local real system is similar to a conventional battery energy storage system. The local controller provides basic functions of data acquisition, processing, analysis, state estimation, protection and the like of the battery energy storage system. Data of the actual battery energy storage system is sampled by the BMS, the PCS, the EMS and the auxiliary devices together with the environmental state, and then the data is processed on the local controller. And false data is deleted, and some common data with small information amount are compressed to reduce the calculation amount of the local controller and the cloud platform.
However, one variation of the local controller of the present invention is to send necessary data and information to the cloud platform for modeling and parameter optimization, and then receive instructions from the cloud platform to adjust the state calculation of the local actual battery energy storage system and adjust the operating state in time. Another variation of the local controller is its system state analysis and control process. Conventional SOC estimation is based on open circuit voltage lookup tables or ampere-hour counts, however, these methods suffer from current and voltage acquisition errors and difficult to determine 100% state of charge points.
According to one embodiment of the invention, a cloud-based digital twin model is proposed;
the cloud-based digital twin model mathematically describes that an actual battery energy storage system contains important components and functions. The battery cells and their modules, battery packs and clusters are modeled in detail in a digital system. Other important data and information is also collected to better describe the overall system, such as moving average of battery charge/discharge power through the PCS, dc side current or voltage ripple, PCS heat sink temperature and fan speed.
According to one embodiment of the invention, the whole system adopts a cloud-end combined architecture, and the 'end' is a processor with certain data processing, analysis, calculation and control capabilities, is located in the local of each different battery energy storage system, and acquires data of BMS, PCS, EMS, dynamic loop auxiliary equipment and the like.
The BMS data includes battery system data such as cell, battery module, battery cluster, and voltage, current, temperature, CO/H of the battery system2Equal gas content, etc.; the PCS data comprises an operation control instruction, input and output electric energy indexes, the temperature of key parts of PCS equipment, such as a radiating fin, the rotating speed of a fan, the junction temperature of a main power tube such as an IGBT and the like; the EMS data comprises scheduling or upper computer instructions, grid connection point states and the like; the data of the moving-loop auxiliary equipment comprise fire fighting, air conditioning, ventilation, different distribution temperature and humidity of an energy storage system chamber, video images and the like.
The end processor is configured with a data acquisition processing function of the local energy storage system, a battery system state calculation model, a multi-stage early warning and alarming function, an inter-cluster/intra-cluster balancing function, a human-computer interaction interface and the like.
And the end processor uploads the collected, analyzed and processed local energy storage system data and information to a cloud computing center database. The model library is configured with a plurality of typical battery system models, has a plurality of different levels of a battery core, a module, a battery cluster and a battery system, and considers the differences of installation modes, operation years, moving ring characteristics and the like.
The cloud is located in a computing center of a remote server or a virtual server, is connected with each battery energy storage system through a network, and mainly comprises a database, a model library, an application development program, a human-computer interface and the like.
The cloud computing center continuously optimizes and regularly corrects the parameters of the model through a data-driven intelligent algorithm according to actual operation data and information of a large number of energy storage systems, and a digital twin body of the energy storage systems is formed. The prediction data of the digital twin body is continuously compared with the operation data of the physical entity of the energy storage system, and the model parameters are optimized and adjusted, so that the model of the twin body has strong adaptability and accuracy.
All data and information collected from different local battery energy storage systems are aggregated in the cloud platform. The present invention uses Machine Learning (ML) for parameter optimization of models. ML can be learned from data without additional manual programming, accommodating for complex and inherent variability of batteries and modules, battery packs and clusters. The parameters of the battery system may be optimized on a regular basis or when large changes occur. And then the refreshed parameters are sent to the local battery energy storage system to update the corresponding parameters.
According to one embodiment of the invention, the operation mechanism of the cloud-based digital twin model is as follows:
the cloud platform receives data and information of scattered local battery energy storage system sites. The data and information are then aggregated and compared to data from a simultaneous digital twin and judged by their error covariance or other indicators to assess their differences. If the difference between the actual energy storage system and the digital twin exceeds a certain value, parameters of the digital twin are optimized by a machine learning program.
The output of the digital twin model includes key parameters of the battery system and correlations between them. The battery model may be electrochemical-based, equivalent circuit-based, and data-driven. And reading and writing the model library according to a certain period, and issuing typical parameters such as equivalent impedance, rated capacity and the like of a certain battery energy storage system station. The local controller receives information from the digital twin model and then adjusts the parameters of the local battery model or equation.
Meanwhile, aging or faults of equipment such as a battery and the like are analyzed on the cloud platform through machine learning. The imminent failure is immediately sent to the corresponding local controller and the failure library is written into the digital twin. The operation mechanism of the digital twin model of the battery energy storage system is shown in fig. 3.
According to an embodiment of the present invention, a modeling and state estimation method of the digital twin model of the present invention is as follows.
Firstly, battery modeling is carried out, and the battery is the core of a battery energy storage system and is sensitive to internal operation states and external conditions. Therefore, modeling of the battery is most important to obtain accurate state descriptions and estimates. As described above, the battery can be modeled according to its electrochemical characteristics, equivalent circuit, and data-driven model describing input-output correlation. However, a common disadvantage of the above models is the difficulty in adapting to internal aging, operating conditions and environmental changes. Thus, an ideal model cannot be invariant in structure and parameters.
The present invention employs an Equivalent Circuit Model (ECM), as shown in fig. 4. ECM is a davinin model that is widely used in practice because of its ease of modeling and calculation. The greater the number of resistor-capacitor (RC) pairs, the greater the accuracy of the battery description. In the present invention, two pairs of RCs are used, each C as shown in FIG. 4n1/Rn1And Cn2/Rn2。UnocRepresents the open circuit voltage, RnoRepresenting ohmic resistance, UntRepresenting terminal voltage.
The cells in a battery energy storage system are typically connected in series to form a module having a certain terminal voltage. Several modules are connected in series to form a battery pack, and several battery packs form a battery pack. The cluster model is very different from a single cell. Modeling all cells in a cluster is complex and unnecessary for analysis and computation, since most cells are similar in both static and dynamic states. The invention provides a battery classification method based on a loss function, which classifies similar batteries into one class and establishes a class model with main parameters. The aim is to obtain a small loss value for the overall class in the cluster. If the characteristics of a battery vary greatly, the loss value of the class in which it resides becomes large, and it is removed from that class and moved to another class similar to it.
Based on the method, the twin body realizes state estimation and residual life prediction according to the predicted states of the battery energy storage systems, and carries out prediction and early warning on potential faults, the potential faults are issued to the end processor in time by the cloud computing center, the end processor carries out operations such as basic parameter adjustment of a state computing model, early warning at all levels, alarm threshold value adjustment and the like in time according to received information, and services are provided for optimized operation and intelligent operation and maintenance of the battery energy storage systems.
According to one embodiment of the invention, using a digital twin model, SOC estimation is performed as follows:
SOCtdefined as the current state of charge and the nominal battery capacity CNThe ratio of (2) is shown in (1).
SOCtWithout direct measurement, the SOC of the battery can be estimated based on the davinin ECM of the battery and the parameters identified by the digital twin. The open circuit voltage Uoc and its SOC are in a relative relationship based on a nonlinear relationship. However, the voltage Uoc cannot be directly measured. t represents the current time, t0 is the initial time, η is the discharge efficiency, I is the discharge current, SOC0Is in an initial state of charge; from the ECM of fig. 4, Uoc can be expressed as:
Ut＝Uoc-U1-U2-IR0 (2)
when the battery is in a stationary state, Ut may be regarded as Uoc. However, due to weak chemical reactions and ionic interactions at the microscopic level, the above conditions are only effective after a long period of time, e.g. several hours.
With machine learning algorithms, the value of Uoc can be identified by complex operating procedures and environmental conditions. This provides great convenience for accurate open circuit voltage of the battery. The value of SOC may then be obtained by looking up a table or SOC-UOC curve.
According to one embodiment of the invention, using a digital twin model, the SOH estimation is performed as follows:
the SOH of a battery is defined as its degree of aging, and may be expressed as capacity fade and internal resistance increase, as shown in (3) and (4). The current battery capacity and internal resistance can be used to estimate the SOH of the battery.
Similarly, the current battery capacity and its ohmic resistance can be identified by a machine learning program. The SOH in terms of both the capacity decay and the resistance increase can then be calculated from (3) and (4).
CcurrentIs the current actual capacity of the battery, CnominalIs the nominal capacity of the battery; r0,tFor the current internal resistance of the battery, R0,0Is the initial internal resistance of the battery.
In addition, the invention is not only limited to the battery in the data source of the battery energy storage system, but also organically combines the energy storage operation mode, the charging and discharging current characteristics, the environmental temperature and the like, so that the model has stronger adaptability.
In summary, the invention provides and develops a battery energy storage system state estimation method based on cloud-end digital twinning, so as to better estimate the state and the operation performance of the battery energy storage system. Digital twinning provides an effective solution for data-driven modeling and big data analysis, all decentralized battery energy storage system connections and data aggregation. The battery model and parameters may be iterated and identified at specific times by machine learning based algorithms. The battery energy storage system assembly and the fault mode thereof are analyzed, and a fault library is established on the cloud platform. A digital twin architecture is presented that includes a physical system, a digital system, and its mechanisms of operation. Furthermore, a method for classifying a battery cell model based on a loss function is proposed to reduce storage and calculation.
Although illustrative embodiments of the present invention have been described above to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, but various changes may be apparent to those skilled in the art, and it is intended that all inventive concepts utilizing the inventive concepts set forth herein be protected without departing from the spirit and scope of the present invention as defined and limited by the appended claims.
Claims (5)
1. A battery energy storage system state estimation method based on cloud-end digital twinning is characterized by comprising the following steps:
step 1, local end processors of different battery energy storage systems collect BMS, PCS, EMS and dynamic loop auxiliary equipment data; the end processor is configured with a data acquisition processing function of a local energy storage system, a battery system state calculation model, a multi-stage early warning and alarming function, an inter-cluster/intra-cluster balancing function and a human-computer interaction interface; the computing center of the cloud server or the virtual server is connected with each battery energy storage system through a network and mainly comprises a database, a model library, an application development program and a human-computer interface;
step 2, the end processor uploads the collected and analyzed local energy storage system data and information to a cloud computing center database, the model database of the cloud computing center database is configured with a plurality of typical battery system models, the models have a plurality of different levels of battery cores, modules, battery clusters and battery systems, and the models are different in installation mode, operation age and dynamic ring characteristics;
step 3, establishing a digital twin model of the battery energy storage system, and continuously optimizing and periodically correcting parameters of the digital twin model by a data-driven intelligent algorithm through a cloud computing center according to actual operation data and information of a large number of energy storage systems to form a digital twin body of the energy storage system; continuously comparing the predicted data of the digital twin body with the operation data of the physical entity of the energy storage system, and optimally adjusting the model parameters of the digital twin body to ensure that the model of the twin body has strong adaptability and accuracy;
and 4, predicting the state of each battery energy storage system by the digital twin body, realizing state estimation and residual life prediction according to the predicted state of each battery energy storage system, predicting and early warning potential faults, timely issuing the potential faults to an end processor by a cloud computing center, and timely performing basic parameter adjustment, early warning at each level and alarm threshold value adjustment operation on a battery energy storage system state calculation model by the end processor according to received information to provide service for the optimized operation and intelligent operation and maintenance of the battery energy storage system.
2. The cloud-end digital twin-based battery energy storage system state estimation method according to claim 1, wherein:
the BMS data includes battery system data: voltage, current, temperature, CO/H of electric core, battery module, battery cluster and battery system2Gas content;
the PCS data comprises an operation control instruction, input and output voltage/current/power indexes, the temperature of a heat radiating fin of PCS equipment, the rotating speed of a fan and the junction temperature of an IGBT main power tube;
the EMS data comprises a scheduling or upper computer instruction and a grid connection point state;
the data of the moving-loop auxiliary equipment comprise different distribution temperature, humidity and video images of a fire-fighting system, an air conditioner, a ventilation system and an energy storage system chamber.
3. The cloud-end digital twin-based battery energy storage system state estimation method according to claim 1, wherein:
in the step 3, the cloud platform receives data and information of scattered local battery energy storage system sites, summarizes the data and the information, compares the summarized data and the information with data from digital twins running simultaneously, judges through error covariance or other indexes of the data and the information to evaluate differences of the data and the information, and optimizes parameters of the digital twins through a machine learning program if the difference between a physical system and the digital twins exceeds a certain value.
4. The cloud-end digital twin-based battery energy storage system state estimation method according to claim 1, wherein:
in the step 3, the output of the digital twin model comprises key parameters of the battery system and correlation between the key parameters, and the battery model is based on electrochemistry, equivalent circuit or data driving; and the model base is updated iteratively according to a certain period, typical parameters of a certain battery energy storage system station are issued in time, and the local controller of the energy storage system station receives information from the digital twin model and then adjusts the parameters of the local battery system model or the calculation formula.
5. The cloud-end digital twin-based battery energy storage system state estimation method according to claim 1, wherein:
and in the step 3, the aging state of the equipment such as the battery and the like is analyzed or fault diagnosis is carried out on the cloud platform through machine learning, the aging state is used as a basis for optimizing operation parameters of the local energy storage system station or a basis for carrying out maintenance work, if an emergency fault is predicted, the emergency fault is immediately sent to the corresponding local controller, and a digital twin fault library is updated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111036904.6A CN113671382A (en) | 2021-09-06 | 2021-09-06 | Battery energy storage system state estimation method based on cloud-end digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111036904.6A CN113671382A (en) | 2021-09-06 | 2021-09-06 | Battery energy storage system state estimation method based on cloud-end digital twinning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113671382A true CN113671382A (en) | 2021-11-19 |
Family
ID=78548404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111036904.6A Pending CN113671382A (en) | 2021-09-06 | 2021-09-06 | Battery energy storage system state estimation method based on cloud-end digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113671382A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114154429A (en) * | 2022-02-10 | 2022-03-08 | 中国长江三峡集团有限公司 | Digital twin body construction method and device of energy storage system and storage medium |
| CN114417549A (en) * | 2021-11-29 | 2022-04-29 | 天津大学 | Digital twin target field data processing system based on supercomputer |
| CN114512741A (en) * | 2022-02-23 | 2022-05-17 | 许昌云能魔方储能技术有限公司 | Integrated distributed liquid cooling energy storage system |
| CN114706028A (en) * | 2022-02-28 | 2022-07-05 | 合肥工业大学 | Intelligent networking automobile BMS sensing array failure cloud diagnosis method based on drifting twin body |
| CN114722625A (en) * | 2022-04-24 | 2022-07-08 | 上海玫克生储能科技有限公司 | Method, system, terminal and medium for establishing monomer digital twin model of lithium battery |
| CN114865800A (en) * | 2022-07-06 | 2022-08-05 | 中安芯界控股集团有限公司 | Energy storage system capable of measuring performance of high-capacity battery |
| CN114935722A (en) * | 2022-05-30 | 2022-08-23 | 武汉理工大学 | Lithium battery edge and end cooperative management method based on digital twinning |
| CN115514100A (en) * | 2022-10-18 | 2022-12-23 | 深圳库博能源科技有限公司 | Hybrid energy storage system based on multi-element energy storage and control |
| CN116345698A (en) * | 2023-05-30 | 2023-06-27 | 中国华能集团清洁能源技术研究院有限公司 | Operation and maintenance control method, system, equipment and medium for energy storage power station |
| CN116579190A (en) * | 2023-07-13 | 2023-08-11 | 天津华泽能源信息技术有限公司 | Energy storage twin model construction method and system based on Internet of things |
| CN116581804A (en) * | 2023-07-07 | 2023-08-11 | 湖南大学 | Large-scale energy storage power station health management system and operation method |
| 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 |
| CN116722571A (en) * | 2023-08-04 | 2023-09-08 | 深圳康普盾科技股份有限公司 | Energy storage management method, system and medium based on digital twin |
| CN117332556A (en) * | 2023-08-23 | 2024-01-02 | 深圳市佳合丰新能源科技有限公司 | Battery energy storage system simulation method and device, computer equipment and storage medium |
| CN118101732A (en) * | 2024-04-25 | 2024-05-28 | 深圳市峰和数智科技有限公司 | Cloud digital twin-based flow battery operation and maintenance system and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110492186A (en) * | 2019-07-02 | 2019-11-22 | 北京航空航天大学 | A kind of management method of the power battery module based on cloud control technology |
| CN111027165A (en) * | 2019-07-19 | 2020-04-17 | 北京航空航天大学 | Power battery pack management system and method based on digital twinning |
| CN112103979A (en) * | 2020-09-22 | 2020-12-18 | 中国科学院电工研究所 | Coordination control method of integrated energy storage system |
| CN112711892A (en) * | 2020-12-07 | 2021-04-27 | 深圳先进技术研究院 | Cloud battery management system and method based on digital twin and block chain technology |
| CN112818602A (en) * | 2021-02-05 | 2021-05-18 | 清华大学 | Battery digital twin control method and device based on big data analysis |
| CN112993338A (en) * | 2021-03-04 | 2021-06-18 | 上海电气集团股份有限公司 | Monitoring method, device and equipment of energy storage system |
-
2021
- 2021-09-06 CN CN202111036904.6A patent/CN113671382A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110492186A (en) * | 2019-07-02 | 2019-11-22 | 北京航空航天大学 | A kind of management method of the power battery module based on cloud control technology |
| CN111027165A (en) * | 2019-07-19 | 2020-04-17 | 北京航空航天大学 | Power battery pack management system and method based on digital twinning |
| CN112103979A (en) * | 2020-09-22 | 2020-12-18 | 中国科学院电工研究所 | Coordination control method of integrated energy storage system |
| CN112711892A (en) * | 2020-12-07 | 2021-04-27 | 深圳先进技术研究院 | Cloud battery management system and method based on digital twin and block chain technology |
| CN112818602A (en) * | 2021-02-05 | 2021-05-18 | 清华大学 | Battery digital twin control method and device based on big data analysis |
| CN112993338A (en) * | 2021-03-04 | 2021-06-18 | 上海电气集团股份有限公司 | Monitoring method, device and equipment of energy storage system |
Non-Patent Citations (4)
| Title |
|---|
| TAESIC KIM 等: "Cloud-Based Battery Condition Monitoring and Fault Diagnosis Platform for Large-Scale Lithium-Ion Battery Energy Storage Systems", ENERGIES, vol. 11, no. 125, pages 1 - 15 * |
| WEIHAN LI等: "Digital twin for battery systems: Cloud battery management system with online state-of-charge and state-of-health estimation", JOURNAL OF ENERGY STORAGE, vol. 30, pages 101557 * |
| WENWEN WANG 等: "Application of Digital Twin in Smart Battery Management Systems", CHINESE JOURNAL OF MECHANICAL ENGINEERING, vol. 34, pages 1 - 19 * |
| 刘大同 等: "锂离子电池组健康状态估计综述", 仪器仪表学报, vol. 40, no. 11, pages 1 - 18 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114417549B (en) * | 2021-11-29 | 2023-09-22 | 天津大学 | Digital twin object field data processing system based on super computer |
| CN114417549A (en) * | 2021-11-29 | 2022-04-29 | 天津大学 | Digital twin target field data processing system based on supercomputer |
| CN114154429B (en) * | 2022-02-10 | 2022-06-14 | 中国长江三峡集团有限公司 | Digital twin body construction method and device of energy storage system and storage medium |
| CN114154429A (en) * | 2022-02-10 | 2022-03-08 | 中国长江三峡集团有限公司 | Digital twin body construction method and device of energy storage system and storage medium |
| CN114512741A (en) * | 2022-02-23 | 2022-05-17 | 许昌云能魔方储能技术有限公司 | Integrated distributed liquid cooling energy storage system |
| CN114706028B (en) * | 2022-02-28 | 2023-02-28 | 合肥工业大学 | Intelligent networking automobile BMS sensing array failure cloud diagnosis method based on drifting twin body |
| CN114706028A (en) * | 2022-02-28 | 2022-07-05 | 合肥工业大学 | Intelligent networking automobile BMS sensing array failure cloud diagnosis method based on drifting twin body |
| CN114722625A (en) * | 2022-04-24 | 2022-07-08 | 上海玫克生储能科技有限公司 | Method, system, terminal and medium for establishing monomer digital twin model of lithium battery |
| CN114935722A (en) * | 2022-05-30 | 2022-08-23 | 武汉理工大学 | Lithium battery edge and end cooperative management method based on digital twinning |
| CN114935722B (en) * | 2022-05-30 | 2024-01-12 | 武汉理工大学 | Lithium battery side end collaborative management method based on digital twin |
| CN114865800A (en) * | 2022-07-06 | 2022-08-05 | 中安芯界控股集团有限公司 | Energy storage system capable of measuring performance of high-capacity battery |
| CN115514100A (en) * | 2022-10-18 | 2022-12-23 | 深圳库博能源科技有限公司 | Hybrid energy storage system based on multi-element energy storage and control |
| 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 |
| 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 |
| CN116345698A (en) * | 2023-05-30 | 2023-06-27 | 中国华能集团清洁能源技术研究院有限公司 | Operation and maintenance control method, system, equipment and medium for energy storage power station |
| CN116581804B (en) * | 2023-07-07 | 2023-09-08 | 湖南大学 | Large-scale energy storage power station health management system and operation method |
| CN116581804A (en) * | 2023-07-07 | 2023-08-11 | 湖南大学 | Large-scale energy storage power station health management system and operation method |
| CN116579190B (en) * | 2023-07-13 | 2023-09-19 | 天津华泽能源信息技术有限公司 | Energy storage twin model construction method and system based on Internet of things |
| CN116579190A (en) * | 2023-07-13 | 2023-08-11 | 天津华泽能源信息技术有限公司 | Energy storage twin model construction method and system based on Internet of things |
| CN116722571A (en) * | 2023-08-04 | 2023-09-08 | 深圳康普盾科技股份有限公司 | Energy storage management method, system and medium based on digital twin |
| CN116722571B (en) * | 2023-08-04 | 2024-02-02 | 深圳康普盾科技股份有限公司 | Energy storage management method, system and medium based on digital twin |
| CN117332556A (en) * | 2023-08-23 | 2024-01-02 | 深圳市佳合丰新能源科技有限公司 | Battery energy storage system simulation method and device, computer equipment and storage medium |
| CN118101732A (en) * | 2024-04-25 | 2024-05-28 | 深圳市峰和数智科技有限公司 | Cloud digital twin-based flow battery operation and maintenance system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113671382A (en) | Battery energy storage system state estimation method based on cloud-end digital twinning | |
| WO2021208309A1 (en) | Method and system for online evaluation of electrochemical cell of energy storage power station | |
| WO2022253038A1 (en) | Method and system for predicting state of health of lithium battery on basis of elastic network, and device and medium | |
| CN113990054A (en) | Energy storage power station data analysis and early warning system | |
| CN116683500B (en) | Active power scheduling method and system for electrochemical energy storage power station | |
| CN117013606B (en) | Intelligent energy storage control system for photovoltaic power generation based on artificial intelligence | |
| CN116799844B (en) | Portable distributed energy storage system | |
| CN114977498A (en) | Cloud-edge-cooperated lithium battery energy storage power station safety management and control system and method | |
| CN111460656B (en) | Method and system for evaluating operation life of communication power supply of electric power machine room | |
| CN114977275A (en) | Intelligent energy storage power converter | |
| CN117498406A (en) | Cloud side end cooperative energy storage power station management system and method | |
| CN112670999A (en) | Low-voltage distribution network real-time voltage control method based on user-side flexible resources | |
| CN117879018B (en) | Configuration operation method of energy storage system for new energy consumption | |
| Yu et al. | Towards cognitive ev charging stations enabled by digital twin and parallel intelligence | |
| US20230378756A1 (en) | Large scale energy storage with ai-based grading and efficiency assessment | |
| CN117394535A (en) | Digital twin system of AC/DC hybrid power distribution network | |
| Tang et al. | Digital twin based bess state estimation and operating opimization | |
| Haq et al. | Performance analysis of energy storage in smart microgrid based on historical data of individual battery temperature and voltage changes | |
| CN115825756B (en) | Multi-stage fault diagnosis method and system for distributed energy storage power station | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| WO2023225378A1 (en) | Large scale energy storage with ai-based grading and efficiency assessment | |
| CN115693916A (en) | Intelligent online monitoring method and system for direct-current power supply of transformer substation | |
| CN114825625A (en) | Operation and maintenance system and method for battery energy storage power station | |
| Magsumbol et al. | FLi-BMS: A Fuzzy Logic-based Intelligent Battery Management System for Smart Farm | |
| CN114325394B (en) | Method, system, equipment and medium for estimating battery stack SOC |
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 |