CN114004168B - Fuel cell comprehensive management system and method based on digital twinning - Google Patents
Fuel cell comprehensive management system and method based on digital twinning Download PDFInfo
- Publication number
- CN114004168B CN114004168B CN202111596655.6A CN202111596655A CN114004168B CN 114004168 B CN114004168 B CN 114004168B CN 202111596655 A CN202111596655 A CN 202111596655A CN 114004168 B CN114004168 B CN 114004168B
- Authority
- CN
- China
- Prior art keywords
- fuel cell
- data
- model
- battery
- digital twin
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04992—Processes for controlling fuel cells or fuel cell systems characterised by the implementation of mathematical or computational algorithms, e.g. feedback control loops, fuzzy logic, neural networks or artificial intelligence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/30—Hydrogen technology
- Y02E60/50—Fuel cells
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Manufacturing & Machinery (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Fuel Cell (AREA)
Abstract
The invention discloses a fuel cell comprehensive management system and a method based on digital twinning, wherein the system comprises an entity battery pack: for generating dynamic performance parameters on the fly; digital twinning model: the system is used for simulating the dynamic performance parameters of the solid fuel cell stack in real time; a data acquisition platform: the system is used for acquiring dynamic performance parameters of the operation of the entity fuel cell stack in real time, preprocessing and extracting characteristics of data, transmitting the extracted characteristic data to a digital twin model and driving the operation of the model; the fuel cell and lithium battery terminal management module: the system is a human-computer interaction interface and is used for remotely and visually presenting the running state of the digital twin model in real time and controlling the adjusting parameters of the entity fuel cell set and the digital twin model. The invention can realize remote real-time visual monitoring on a complex fuel cell system; and adjusting each relevant physical quantity of the physical equipment in time and accurately according to the operation result of the digital twin model so as to enable the performance to reach the optimal state.
Description
Technical Field
The invention relates to a comprehensive management system and a method for a proton exchange membrane fuel cell, which construct a twin model based on a digital twin technology and mainly realize real-time visualization, comprehensive regulation of an operation state and fault diagnosis of the fuel cell system.
Background
In recent years, the development of the battery industry is rapid, for fuel cell systems, particularly for medium and large-scale systems, the internal composition, the system structure, the operating conditions and the like are complex, the parameters to be monitored are many, faults are difficult to find, the workload of maintenance and disassembly is large, large-scale galvanic piles belong to complex mechanical equipment and are in harsh environments, and due to the reasons, the research on the aspects of remote real-time visual monitoring, fault diagnosis and the like of the fuel cell systems has great necessary and good prospects.
The modeling of the proton exchange membrane fuel cell is also studied to a sufficient degree in recent years, but the mechanism modeling and the data-driven modeling have self limitations, and the digital twin model can combine the advantages of the mechanism model and the data-driven model, thereby simplifying the calculation process of the model while ensuring the detailed mechanism description.
In recent years, with the progress of digital expression of physical models and the breakthrough of emerging information technology fields such as internet of things, cloud computing and big data, the digital twin technology has relatively rapid development in both theoretical and application levels. The digital twin is to establish a multi-scale, multi-discipline, multi-probability and multi-physical-quantity virtual model of the physical entity in a digital mode and reproduce the attributes, behaviors, rules and the like of the physical entity in a real environment by means of real-time data. By applying the digital twinning technology, the aim of controlling real by virtual can be achieved to a certain extent. Of course, the establishment of the twin model of the complex equipment and the application research of the digital twin model in the design, use and maintenance of the equipment are not sufficient at present, and the future research is still needed to be broken through.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a fuel cell comprehensive management system and a fuel cell comprehensive management method based on digital twinning.
In order to achieve the above object, the present invention provides a comprehensive management system for a fuel cell based on digital twin, which is characterized in that the system comprises an entity battery pack, a digital twin model, a data acquisition platform, a fuel cell and a lithium battery terminal management module,
the solid battery pack: for generating dynamic performance parameters on the fly;
the digital twin model is as follows: the system is used for simulating the dynamic performance parameters generated by the solid fuel cell pack in real time during operation, and comprises a digital cell pack, a cell operation simulation model and a fault and prediction model; the digital battery pack is a battery structure 3D model, the battery working simulation model simulates the operation process and the result of a battery, and the fault and prediction model processes fault data by combining an artificial intelligence algorithm to judge the fault condition; after one-time complete operation, the digital twin model outputs the state information and/or the fault condition of the electric pile;
the data acquisition platform: the system comprises a digital twin model, a data acquisition module, a data transmission module and a data transmission module, wherein the data acquisition module is used for acquiring dynamic performance parameters of the operation of an entity fuel cell group in real time, preprocessing and extracting characteristics of data, transmitting the extracted characteristic data to the digital twin model through an established communication protocol and driving the operation of the model;
the fuel cell and lithium battery terminal management module: the system is a human-computer interaction interface and is used for remotely and visually presenting the running state of the digital twin model in real time and controlling the adjusting parameters of the entity fuel cell set and the digital twin model.
Further, the digital battery pack maps the geometric structures, physical rules and chemical rules of the solid fuel battery and the solid lithium battery, and constructs a fuel battery digital twin and a lithium battery digital twin through operations of 3D modeling, graphic rendering and kinematic equation construction, wherein the shapes, structures, capacities and natural and scientific rules followed by the digital battery and the solid battery are the same.
Furthermore, the battery working simulation model integrates thermodynamics and dynamics principles, starts to operate after being driven by data, and simulates the physical entity operation state of the entity fuel battery in real time.
Furthermore, the fault and prediction model forms a characteristic parameter set after characteristic extraction through historical data acquired and stored by the data acquisition platform, a neural network is adopted to take the characteristic parameter set as a training and testing data set, two mature neural network models of a fault diagnosis model and a battery life prediction model are obtained after repeated optimization, and the output of the two models is the fault type and severity and the residual service life of the battery.
Furthermore, the data acquisition platform comprises an information acquisition module and an information transmission module.
Furthermore, the information acquisition module comprises data acquisition, characteristic parameter extraction, data storage, data reading and data derivation, wherein the data acquisition is to acquire key information of heating power, electric power and pressure during the operation of the battery pack in real time through various sensors and display a signal curve in real time; the characteristic parameter extraction is to perform characteristic engineering processing on the acquired related parameters to obtain a characteristic parameter set for other modules to use.
Further, the characteristic parameter extraction process is as follows:
(1) carrying out basic preprocessing operations such as standardization, normalization, polynomial characteristic transformation and the like on the state data of the galvanic pile acquired by each sensor;
(2) after data preprocessing is finished, feature selection is considered from two aspects of whether the features are diverged or not, the correlation between the features and the target and the like;
(3) and after the feature selection and extraction are finished, transmitting the feature data to a digital twin model, or inputting the feature data into a machine learning algorithm and a machine learning model for training.
Furthermore, the information transmission module adopts a one-to-one communication mode at the same time to realize data transmission between the data acquisition platform and the digital twin model based on a TCP/IP protocol.
Furthermore, the solid fuel cell group comprises a solid fuel cell and a solid lithium cell, which are both selected in the actual working process, and the solid lithium cell is used as an auxiliary system of the fuel cell to store or supplement the electric energy output by the fuel cell according to a control strategy so as to balance the dynamic output performance of the fuel cell.
Based on the above fuel cell integrated management system based on digital twinning, the invention also provides a working method of the fuel cell integrated management system based on digital twinning, which comprises the following steps:
a. according to the selected solid fuel cell and solid lithium cell, the geometric structure, the physical and chemical rules of the solid fuel cell and the solid lithium cell are mapped, and a fuel cell digital twin and a lithium cell digital twin are constructed through operations of 3D modeling, graph rendering and construction of a kinematic equation, wherein the shapes, the structures, the capacities and the followed rules of the digital cell set and the solid cell set are the same;
b. the method comprises the following steps that (1) under a given condition, an entity battery starts to work, a data acquisition platform acquires entity data generated by the operation of an entity battery pack through various sensors and backups and stores the data;
c. the data acquisition platform preprocesses the data and extracts the characteristics, matches the sending and receiving ports through the established communication protocol, transmits the characteristic data to the digital twin model and drives the model to operate;
d. the digital twin model is driven by data to perform real-time simulation description on a physical entity, the running state or the fault condition at the current moment is output, and when the physical entity is changed, the digital twin model is correspondingly changed in real time;
e. the management personnel observe the interactive interface information at the far end of the fuel cell and lithium battery terminal management module, know the running state of the fuel cell system in real time and accurately through the running result of the digital twin model, diagnose the fault of the system in real time, and then inform the relevant personnel to adjust the input conditions, and maintain or replace the physical equipment at the fault.
Compared with a general fuel cell management system, the digital twin-based fuel cell comprehensive management system provided by the invention has the following outstanding advantages:
1. a digital twin model of the fuel cell is constructed by applying a digital twin technology, a data acquisition platform is taken as a bridge, and a physical space is connected with a digital space, so that real-time interaction of an entity object and the digital object can be realized, and a complex fuel cell system can be remotely and visually monitored in real time; the relevant physical quantities of the physical equipment can be timely and accurately adjusted according to the running result of the digital twin model, so that the performance reaches the optimal state;
2. by adding a fault diagnosis and prediction model, when a fault problem occurs, complex mechanical equipment is difficult to judge in the first time. The artificial intelligence algorithm is used for training to obtain a fault diagnosis model, fault data can be rapidly processed, the type and the severity of the fault can be judged, and the visualization of the fault position when the battery working simulation model breaks down is combined, so that workers can rapidly disassemble, maintain and the like;
3. the lithium battery system is added to serve as an auxiliary system of the fuel battery, the dynamic performance of the fuel battery is poor, the lithium battery has good dynamic performance and can be charged and discharged continuously, and the lithium battery is very suitable for serving as an auxiliary energy source of the fuel battery system. In different time periods, according to the demand condition of the external circuit for electric energy, the fuel cell can charge the lithium battery and store the electric energy in the lithium battery while providing the electric energy for the external equipment in the off-peak period of electricity utilization, and the lithium battery can output the electric energy to compensate the electric energy for the fuel cell in the peak period of electricity utilization, so that the output electric power is leveled with the electric load, and the dynamic performance of the fuel cell is balanced.
Drawings
FIG. 1 is a system architecture diagram of the present invention.
Fig. 2 is a schematic flow chart of the system structure of the invention.
FIG. 3 is a flow chart of the data acquisition platform operation of the present invention.
Fig. 4 is a schematic diagram of the overall functional structure of the system of the present invention.
Detailed Description
The invention is described in further detail below with reference to the figures and specific embodiments.
As shown in fig. 1, the integrated management system of a fuel cell based on digital twin provided by the invention is a five-dimensional structure model, mainly comprising physical objects, virtual models, data, service systems and connections, and is developed based on the five-dimensional basic framework.
The structure flow chart of the proton exchange membrane fuel cell comprehensive management system based on the digital twin disclosed by the invention is shown in figure 2, and the system comprises an entity battery pack, a digital twin model, a data acquisition platform, a fuel cell and a lithium battery terminal management module.
According to the invention, the physical battery is used for generating dynamic performance parameters during operation; the digital twin model is used for simulating the dynamic performance parameters generated by the solid fuel cell stack in the running process in real time; the data acquisition platform is used for acquiring dynamic performance parameters of the operation of the entity fuel cell pack in real time, preprocessing the data and extracting characteristics, transmitting the extracted characteristic data to the digital twin model through the established communication protocol and driving the operation of the model; the fuel cell and lithium battery terminal management module is a human-computer interaction interface and is used for remotely and visually presenting the running state of the digital twin model in real time and controlling the adjustment parameters of the entity fuel cell set and the digital twin model.
The invention provides a digital twin-based fuel cell comprehensive management system, which selects NI LabVIEW as a development platform and mainly realizes remote real-time monitoring and fault diagnosis of a cell system. The obtained model operation result is used for adjusting the operation conditions of the system, including but not limited to controlling and adjusting key parameters of air inlet and outlet, pressure, humidity, temperature and the like of the proton exchange membrane fuel cell stack, so that the internal reaction gas, water balance and heat balance reach proper states. When the output of the electric pile is applied, the DC-DC conversion circuit can be called according to the target voltage required by the application to output the voltage of the electric pile, the voltage boosting or reducing treatment is carried out on the output voltage, the lithium battery is used as an auxiliary energy storage system of the fuel cell, and the electric energy output of the fuel cell system is timely and accurately stored or supplemented according to the electric energy demand condition in different time periods, so that the demand is met, and the dynamic performance of the fuel cell is balanced.
In the invention, the solid battery pack is a fuel cell and a lithium battery selected in actual work, a plurality of single fuel cells form a fuel cell stack, and a plurality of single lithium batteries form a lithium battery pack.
In the invention, the digital battery pack is a digital model of the solid battery pack, the solid battery is mapped with the geometric structure and the physical and chemical rules to obtain a digital twin body of the fuel battery and the lithium battery, and the digital twin model module mainly comprises a battery working simulation model and a fault diagnosis model besides a battery pack structure mapping model obtained through operations such as 3D modeling and the like. The digital battery model is consistent with the physical battery in terms of size, shape, structure, capacity, working mode, followed physical and chemical rules and the like.
According to the invention, a plurality of sensors are embedded in the solid cell stack to serve as data acquisition equipment, a data acquisition platform integrates the data and then carries out preprocessing, a characteristic parameter set is obtained after characteristic engineering processing, and the characteristic parameter set is transmitted to a digital space to drive a digital twin model to operate. Meanwhile, the obtained data can be stored in a data acquisition platform as historical data at a later moment.
The data acquisition platform mainly comprises an information acquisition module and an information transmission module, and the working process of the data acquisition platform is shown in fig. 3. And the data acquisition platform realizes information transmission between a digital space and a physical space of the fuel cell on a LabVIEW platform. The information acquisition module can be divided into data acquisition, characteristic parameter extraction, data storage, data reading, data export and the like. The data acquisition is to acquire key information such as heating power, electric power and pressure during the operation of the battery pack in real time through various sensors and display a signal curve in real time. The characteristic parameter extraction is to perform characteristic engineering processing on the acquired related parameters to obtain a characteristic parameter set for other modules to use. The characteristic engineering processing is a process of converting data attributes into data characteristics, the potential trend of the data is difficult to find by learning the original data, and the interference of a lot of noises can be reduced by preprocessing the data through the characteristic engineering. The characteristic parameter extraction process comprises the following steps:
(1) carrying out basic preprocessing operations such as standardization, normalization, polynomial characteristic transformation and the like on the state data of the galvanic pile acquired by each sensor;
(2) after the data preprocessing is completed, feature selection is considered from two main aspects, namely whether the features diverge and the correlation between the features and the target. In the invention, an SG filter filtering method is selected to carry out smooth denoising on data, and the SG filter can ensure that the signal is not distorted while filtering the data noise.
(3) After the feature selection and extraction are completed, feature data can be transmitted to a digital twin model or input into an algorithm and a model for machine learning to train. However, in order to ensure the speed and efficiency of system operation, the invention can adopt a linear discriminant analysis method to perform dimensionality reduction processing on data, thereby reducing the system calculation amount and shortening the model training time.
After the information acquisition module acquires data from the electric pile entity equipment, the data are processed and sent to each module of the virtual model, and then the model is driven to operate. And a communication protocol needs to be established for data transmission, and the digital twin technology realizes remote monitoring in different places, so that the high efficiency and reliability of data transmission need to be ensured. LabVIEW has powerful communication function and is internally provided with a plurality of communication protocols including TCP/IP. TCP/IP is a communication protocol based on byte stream, and data transmission is carried out by adopting a byte stream data packet mode. In this embodiment, the procedure of establishing communication is as follows: the server is in a working state, establishes contact with the port through the IP address, and waits for the client to send a connection request; the client starts TCP connection and sends a connection request to the server according to the IP address and the port number; and the server receives the request, establishes a data transmission channel with the client and communicates.
The digital twin model is a main part in a digital space and mainly comprises three parts: the system comprises a digital battery model, a battery working process simulation model and a fault diagnosis and prediction model. The digital battery model takes Autocad software as a platform to construct a structural model of the battery, and the size and the structure of the solid battery are simulated. A working process simulation model of the battery is constructed by taking Matlab as a platform, each condition parameter equation is determined according to the principles of mass conservation, energy conservation and the like, a working process calculation model of each subsystem such as air intake and exhaust, cooling circulation and the like is built in Simulink, the working process calculation model is a set of each submodule model, each subsystem model is connected, and the operation process and the result of the battery are simulated. The method is characterized in that a battery fault diagnosis and prediction model is constructed by taking Python as a platform, an artificial intelligence algorithm is combined, such as a deep neural network in machine learning, most commonly a recurrent neural network, a support vector machine and the like, historical data collected and stored by a data collection platform is subjected to feature extraction to form a feature parameter set, the neural network is taken as a data set, one part of the data set is taken as a training set, the other part of the data set is taken as a test set, two mature neural network models are obtained after repeated optimization, the two models are respectively a fault diagnosis model and a battery life prediction model, and the output of the model is mainly the type and severity of a fault and the residual service life of a battery. The three submodels are integrated in a LabVIEW platform through a set port. After one complete operation, the digital twin model outputs the state information and/or the fault condition of the electric pile.
In the invention, the battery pack terminal management module comprises a developed man-machine interaction system. Through the operation output result of the digital twin model in the digital space, managers can accurately know the working state of the solid fuel cell stack in real time, further adjust the solid fuel cell stack, and can quickly judge and diagnose the fault position and the fault type if the fault occurs, so that the disassembly and the maintenance work are convenient.
The invention takes LabVIEW as a platform development terminal management system, builds a human-computer interaction interface, takes LabVIEW software as a development platform, and has some outstanding advantages compared with other platforms: the imaging development is simple and practical; the processing capacity is strong, and the efficiency is high; and the compatibility and the expansibility are good. Through the terminal management system, a worker can use the digital twin body to perform interactive fusion and mutual mapping on the fuel cell stack entity equipment, so that the remote real-time visual presentation, real-time online simulation, fault diagnosis, service life prediction and the like of the fuel cell system are realized. And the model result is visually and efficiently displayed to the staff in the forms of a data report, a three-dimensional view, calculation analysis and the like, and the staff makes some adjustments to the operation condition of the battery system according to the result or carries out disassembly and maintenance work on the equipment at the fault position according to the judged fault type, fault degree and fault position.
The model operation of the digital space depends on the driving of the working data of the entity battery, and the real-time performance between the entity and the model is improved through the calculation of an optimization system. The regulation of the stack operating state is then mainly directed to the air inlet circuit and the cooling circuit. The air inlet loop can adjust the power of the air compressor according to the control instruction, and intelligently adjusts the flow rate (according to the set stoichiometric ratio), the temperature, the humidification degree and other related quantities of the supplied air. The cooling circulation loop can control the flow rate and the temperature of the cooling liquid according to a control command, and the cooling liquid is usually supplied from a constant temperature bath to maintain the constant working temperature of the electric pile, so that the air inlet, the humidity and the temperature of the electric pile of the proton exchange membrane fuel cell in the entity battery pack can be controlled in the expected optimal state. In addition, when the galvanic pile is applied to an actual circuit, the module can call the DC-DC voltage conversion circuit to boost or reduce the output voltage of the galvanic pile according to the voltage requirement of the actual circuit so as to meet the actual requirement.
The lithium battery terminal management module in the battery pack terminal management module controls and adjusts the discharge state of the single battery and the output power of the battery pack, and controls the lithium battery to store energy or release energy according to requirements at different times, so that auxiliary compensation is performed on the output of the fuel battery.
The overall functional structure schematic diagram of the proton exchange membrane fuel cell comprehensive management system based on the digital twin technology is shown in fig. 4. The lithium battery is used as an auxiliary system of the fuel battery, and the solid battery and the digital battery are coupled in a virtual-real mode to form the basis of a digital twin system; the data acquisition platform mainly realizes real-time visual monitoring, real-time data acquisition and characteristic engineering processing on data; the digital twin model comprises three submodules, wherein a fault diagnosis and prediction module judges the fault type and the fault degree, and the common faults include dry membrane, flooding, blocked gas channel, abnormal battery discharge, short circuit of charge and discharge caused by inconsistent parameters of single lithium batteries, battery pack faults caused by excessive discharge of single batteries and the like; the battery pack terminal management module is mainly used for adjusting the air inlet, the humidity and the working temperature of the fuel cell by workers according to results obtained by observing a human-computer interaction interface, or rapidly formulating a scheme according to fault conditions for maintenance. And when the output of the galvanic pile is applied, the DC-DC voltage conversion circuits such as Buck, Boost and the like can be called to carry out voltage boosting and voltage reducing processing on the output according to the requirements in practical application so as to meet the application requirements.
The management of the lithium battery mainly controls and adjusts the parameter consistency and the output power of the single battery, and when the fuel cell stack is actually applied, the lithium battery system plays an important role because the dynamic performance of the fuel cell is poor and the output electric power and the electric load are difficult to keep synchronous change. The lithium battery is used as an auxiliary system of the fuel battery, has good dynamic performance and quick response, and can be charged and discharged continuously. During the off-peak period of power utilization, the lithium battery can be used as an energy storage system to store surplus electric energy output by the fuel cell, and during the peak period of power utilization, the lithium battery can be used as an auxiliary energy supply system to compensate the shortage of the electric energy output by the fuel cell, so that the output electric energy of the whole system is kept consistent with the external electric load, and the dynamic performance of the system is balanced.
In recent years, the fuel cell industry is vigorously developed, and a rudiment is also seen by the digital twin, but the application of the digital twin in the fields of fuel cells and the like is less, and a great research space is provided. The digital twin technology is adopted for constructing a digital model and an interactive system of the fuel cell by taking LabVIEW and the like as a development platform, so that the remote real-time visualization of the running state of large-scale complex equipment of the fuel cell system can be realized, the conditions of various modules, parameters, faults and the like of the system can be comprehensively grasped in real time, the digital twin can accurately adjust the input conditions in time according to the performance requirements of the output of the electric pile, meanwhile, the system fault can be diagnosed, the service life of the cell can be predicted, and the safety, the stability, the durability and the output performance of the whole system are better to a great extent.
Finally, it should be noted that the above detailed description is only for illustrating the technical solution of the patent and not for limiting, although the patent is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the patent can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the patent, which should be covered by the claims of the patent.
Claims (6)
1. A fuel cell integrated management system based on digital twinning is characterized in that: the system comprises an entity battery pack, a digital twin model, a data acquisition platform, a fuel cell and lithium battery terminal management module,
the solid battery pack: the system comprises a solid battery pack, a plurality of single fuel cells, a plurality of single lithium batteries and a plurality of lithium batteries, wherein the solid battery pack is used for generating dynamic performance parameters in operation, the solid battery pack is a fuel cell and a lithium battery selected in actual work, the single fuel cells form a fuel cell stack, and the single lithium batteries form a lithium battery pack;
the digital twin model is as follows: the device is used for simulating the dynamic performance parameters generated by the solid fuel cell pack in the running process in real time, and comprises a digital cell pack, a cell working simulation model and a fault and prediction model; the digital battery pack is a 3D model of a battery structure, a structural model of the battery is constructed by taking Autocad software as a platform, and the size and the structure of an entity battery are simulated; the digital battery pack maps the geometric structures and physical and chemical rules of the solid fuel battery and the solid lithium battery, and constructs a fuel battery digital twin body and a lithium battery digital twin body through the operations of 3D modeling, graphic rendering and kinematic equation construction, wherein the shapes, structures, capacities and the followed natural and scientific rules of the digital battery and the solid battery are the same; the battery working simulation model builds air intake and exhaust and cooling circulation subsystems in Simulink, all the subsystem models are connected to simulate the operation process and the result of the battery, and the fault and prediction model processes fault data by combining an artificial intelligence algorithm to judge the fault condition; the digital battery pack, the battery working simulation model and the fault and prediction model are integrated in a LabVIEW platform through a set port; after one-time complete operation, the digital twin model outputs the state information and/or the fault condition of the electric pile; the data acquisition platform: the system comprises a digital twin model, a data acquisition module, a data transmission module and a data transmission module, wherein the data acquisition module is used for acquiring dynamic performance parameters of the operation of an entity fuel cell group in real time, preprocessing and extracting characteristics of data, transmitting the extracted characteristic data to the digital twin model through an established communication protocol and driving the operation of the model; the data acquisition platform comprises an information acquisition module and an information transmission module; the information acquisition module comprises data acquisition, characteristic parameter extraction, data storage, data reading and data derivation, wherein the data acquisition is to acquire key information of heating power, electric power and pressure during the operation of the battery pack in real time through various sensors and display a signal curve in real time; the characteristic parameter extraction is to perform characteristic engineering processing on the acquired related parameters to obtain a characteristic parameter set for other modules to use; the information transmission module realizes data transmission between the data acquisition platform and the digital twin model by adopting a one-to-one communication mode at the same time based on a TCP/IP protocol;
the fuel cell and lithium battery terminal management module: the intelligent control system is a human-computer interaction interface and is used for remotely and visually presenting the running state of the digital twin model in real time, controlling the adjustment parameters of the entity fuel cell pack and the digital twin model, controlling and adjusting the discharge state of the single battery and the output power of the battery pack, and controlling the lithium battery to store or release energy according to requirements at different times, thereby performing auxiliary compensation on the output of the fuel cell.
2. The integrated management system for a digital twin-based fuel cell as set forth in claim 1, wherein: the battery working simulation model integrates thermodynamics and dynamics principles, starts to operate after being driven by data, and simulates the physical entity operation state of the entity fuel battery in real time.
3. The integrated management system for a digital twin-based fuel cell as set forth in claim 1, wherein: the fault and prediction model forms a characteristic parameter set after characteristic extraction through historical data acquired and stored by a data acquisition platform, a neural network is adopted to take the characteristic parameter set as a training and testing data set, two mature neural network models of a fault diagnosis model and a battery life prediction model are obtained after repeated optimization, and the output of the two models is the fault type and severity and the residual service life of a battery.
4. The integrated management system for a digital twin-based fuel cell as set forth in claim 1, wherein: the characteristic parameter extraction process comprises the following steps:
(1) carrying out basic preprocessing operations such as standardization, normalization, polynomial characteristic transformation and the like on the state data of the galvanic pile acquired by each sensor;
(2) after data preprocessing is finished, feature selection is considered from two aspects of whether the features are diverged or not, the correlation between the features and the target and the like;
(3) and after the feature selection and extraction are finished, transmitting the feature data to a digital twin model, or inputting the feature data into a machine learning algorithm and a machine learning model for training.
5. The integrated management system for a digital twin-based fuel cell as set forth in claim 1, wherein: the solid fuel cell group comprises a solid fuel cell and a solid lithium cell, which are a fuel cell stack and a lithium cell group selected in the actual working process, the solid lithium cell is used as an auxiliary system of the fuel cell, and the electric energy output by the fuel cell is stored or supplemented according to a control strategy to balance the dynamic output performance of the fuel cell.
6. A working method of a digital twin-based integrated fuel cell management system is realized based on the digital twin-based integrated fuel cell management system of any one of claims 1-5, and is characterized in that: the method comprises the following steps:
a. according to the selected solid fuel cell and solid lithium cell, the geometric structure, the physical and chemical rules of the solid fuel cell and the solid lithium cell are mapped, and a fuel cell digital twin and a lithium cell digital twin are constructed through operations of 3D modeling, graph rendering and construction of a kinematic equation, wherein the shapes, the structures, the capacities and the followed rules of the digital cell set and the solid cell set are the same;
b. the method comprises the following steps that (1) under a given condition, an entity battery starts to work, a data acquisition platform acquires entity data generated by the operation of an entity battery pack through various sensors and backups and stores the data;
c. the data acquisition platform preprocesses the data and extracts the characteristics, matches the sending and receiving ports through the established communication protocol, transmits the characteristic data to the digital twin model and drives the model to operate;
d. the digital twin model is driven by data to perform real-time simulation description on a physical entity, the running state or the fault condition at the current moment is output, and when the physical entity is changed, the digital twin model is correspondingly changed in real time;
e. the management personnel observe the interactive interface information at the far end of the fuel cell and lithium battery terminal management module, know the running state of the fuel cell system in real time and accurately through the running result of the digital twin model, diagnose the fault of the system in real time, and then inform the relevant personnel to adjust the input conditions, and maintain or replace the physical equipment at the fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111596655.6A CN114004168B (en) | 2021-12-24 | 2021-12-24 | Fuel cell comprehensive management system and method based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111596655.6A CN114004168B (en) | 2021-12-24 | 2021-12-24 | Fuel cell comprehensive management system and method based on digital twinning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114004168A CN114004168A (en) | 2022-02-01 |
| CN114004168B true CN114004168B (en) | 2022-04-29 |
Family
ID=79931959
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111596655.6A Active CN114004168B (en) | 2021-12-24 | 2021-12-24 | Fuel cell comprehensive management system and method based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114004168B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| CN114357806B (en) * | 2022-03-11 | 2022-06-17 | 中国汽车技术研究中心有限公司 | Dual-mode simulation method and device of fuel cell stack based on material flow interface |
| CN114630211B (en) * | 2022-05-13 | 2022-08-05 | 苏州氢澜科技有限公司 | Fuel cell production system based on digital twinning and adjusting method thereof |
| CN114914987B (en) * | 2022-05-31 | 2023-08-22 | 浙江岭工电器股份有限公司 | Lithium battery power supply device for energy-saving warm air blower and control method |
| CN116226263A (en) * | 2023-01-03 | 2023-06-06 | 大唐可再生能源试验研究院有限公司 | Renewable energy source visual intelligent pipe control method and system |
| CN116184293B (en) * | 2023-03-01 | 2024-02-13 | 深圳市中科恒辉科技有限公司 | Fault diagnosis method and alarm system based on digital twin lithium battery system |
| CN116404205B (en) * | 2023-06-02 | 2023-09-08 | 上海重塑能源科技有限公司 | Digital twin-based fuel cell low-temperature operation control system and method |
| CN117436290B (en) * | 2023-12-21 | 2024-03-08 | 卓世未来(天津)科技有限公司 | Digital twin model response optimization method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591364A (en) * | 2021-06-08 | 2021-11-02 | 北京科技大学 | Management method and device of fuel cell management system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027165B (en) * | 2019-07-19 | 2022-05-03 | 北京航空航天大学 | Power battery pack management system and method based on digital twinning |
| CN110534823B (en) * | 2019-07-19 | 2021-05-28 | 北京航空航天大学 | Power battery balance management system and method |
| CN111581850B (en) * | 2020-05-27 | 2022-10-28 | 北京理工大学 | Full-period power battery management system applying digital twinning technology |
| CN111610448B (en) * | 2020-06-01 | 2021-05-04 | 北京理工大学 | Lithium ion battery life prediction method applying digital twinning technology |
-
2021
- 2021-12-24 CN CN202111596655.6A patent/CN114004168B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113591364A (en) * | 2021-06-08 | 2021-11-02 | 北京科技大学 | Management method and device of fuel cell management system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114004168A (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114004168B (en) | Fuel cell comprehensive management system and method based on digital twinning | |
| CN107390128A (en) | A kind of fuel cell battery hybrid system energy management test platform and method | |
| CN104571068A (en) | Optimized operation control method and system of distributed energy system | |
| CN101814768A (en) | Fuel cell based standby power system | |
| CN203561844U (en) | Digital and physical hybrid simulation platform based on NI-PXI distributed new energy power generation system | |
| CN113708365A (en) | Virtual power plant energy management and control optimization method and system based on end edge cloud architecture | |
| CN110707743A (en) | Dual-mode distributed photovoltaic power generation micro-grid control system and method based on MAS | |
| CN105720573B (en) | Honourable electricity storage station based on measured data is active and powerless control system modeling method | |
| CN104779658B (en) | Polymorphic type battery energy storage system communication management and Power Control simulation system | |
| CN109657194A (en) | A kind of real-time energy management method of hybrid vehicle operation based on Q-learning and rule | |
| Wu et al. | Fault detection and assessment for solid oxide fuel cell system gas supply unit based on novel principal component analysis | |
| KR20210074587A (en) | Communication system apparatus | |
| CN107991902A (en) | A kind of modeling of electric power system of spacecraft and emulation mode | |
| CN201821261U (en) | Backup power supply system based on fuel battery | |
| CN115238959A (en) | User-side energy comprehensive utilization-oriented digital twinning system and method | |
| CN113131515B (en) | Intelligent micro-grid AI fault detection and network optimization reconstruction system and method | |
| CN104932374B (en) | Lithium battery Intelligent remote monitoring system based on Internet of Things | |
| CN113659701A (en) | Intelligent air compression station electric energy supply system and supply method thereof | |
| CN219245670U (en) | Offline detection system of battery thermal management module | |
| CN113849988B (en) | Energy storage system | |
| KR102630120B1 (en) | System and Method for energy management of fuel cell system using digital twin | |
| CN116482975A (en) | Virtual-real fusion ship energy management strategy verification method and platform | |
| CN114280955B (en) | Intelligent hydropower plant system based on field information model and digital twin and architecture method | |
| CN108695979A (en) | A kind of control of micro-capacitance sensor and detection platform | |
| CN203812087U (en) | Wind and photovoltaic hybrid power generation system testing device |
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 |