CN116995276B - Cooling method and system for fuel cell power generation system - Google Patents
Cooling method and system for fuel cell power generation system Download PDFInfo
- Publication number
- CN116995276B CN116995276B CN202311254187.3A CN202311254187A CN116995276B CN 116995276 B CN116995276 B CN 116995276B CN 202311254187 A CN202311254187 A CN 202311254187A CN 116995276 B CN116995276 B CN 116995276B
- Authority
- CN
- China
- Prior art keywords
- data
- fuel cell
- power generation
- temperature
- generation system
- 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
- 239000000446 fuel Substances 0.000 title claims abstract description 143
- 238000010248 power generation Methods 0.000 title claims abstract description 125
- 238000001816 cooling Methods 0.000 title claims abstract description 63
- 230000015654 memory Effects 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims abstract description 34
- 230000007787 long-term memory Effects 0.000 claims abstract description 19
- 230000006403 short-term memory Effects 0.000 claims abstract description 19
- 230000006870 function Effects 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 26
- 230000004913 activation Effects 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004088 simulation Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 239000000498 cooling water Substances 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 239000002737 fuel gas Substances 0.000 description 3
- 239000012528 membrane Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 239000003054 catalyst Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000003502 gasoline Substances 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Classifications
-
- 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
- H01M8/04694—Processes for controlling fuel cells or fuel cell systems characterised by variables to be controlled
- H01M8/04701—Temperature
-
- 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
- H01M8/04007—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids related to heat exchange
- H01M8/04029—Heat exchange using liquids
-
- 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
- H01M8/04305—Modeling, demonstration models of fuel cells, e.g. for training purposes
-
- 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
- H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
- H01M8/0432—Temperature; Ambient temperature
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- General Chemical & Material Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Fuel Cell (AREA)
- Automation & Control Theory (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
Abstract
The invention belongs to the technical field of fuel cells, and particularly relates to a cooling method and a cooling system for a fuel cell power generation system; according to the invention, a long-period memory network model is obtained through the training of the historical data of the fuel cell power generation system, and then the future temperature rise is predicted through the historical temperature and the power generation data; the prediction result is input to a cooling system, so that precise adjustment in advance is realized; meanwhile, when training the long-term and short-term memory network model, error points are removed from the historical data, so that the model training precision is improved, and further, the temperature rise prediction precision is improved, and therefore, the temperature adjustment is more accurate.
Description
Technical Field
The invention belongs to the technical field of fuel cells, and particularly relates to a cooling method and a cooling system for a fuel cell power generation system.
Background
The problems of extremely serious energy crisis, environmental pollution and the like are faced at present, and the proton exchange membrane fuel cell power generation system is developed for searching an energy source which can replace gasoline and has no pollution and high energy utilization rate. Its excellent properties, including high efficiency, high energy density, low noise, low emissions and low operating temperature, are the primary choice of this alternative.
In the working process of the fuel cell power generation system, the performance of the fuel cell power generation system can be influenced by the fuel cell system and the external environment, wherein the working temperature of the fuel cell is one of the most important parameters, the performance of the fuel cell is directly determined by the quality of temperature control, the material transmission in the fuel cell can be influenced by the overhigh temperature, the water shortage of a proton exchange membrane is caused, the membrane of the fuel cell can be irreversibly damaged, the service life is reduced, and therefore, a fast cooling of a pile is required, but if the temperature is too low, the activity of a catalyst in the fuel cell is reduced, so that the chemical reaction in the fuel cell is slowly carried out, and the output performance of the fuel cell power generation system can be influenced. After the internal temperature of the fuel cell reaches the target temperature, the control coupling between the circulating water pump and the cooling fan of the cooling system can cause the fluctuation of the target temperature, so that the fluctuation of the output performance is caused; therefore, designing a good cooling system plays a critical role.
In the prior art, cooling of a fuel cell power generation system is generally realized through a cooling fan or circulating water, for example, chinese patent (CN 108598524A) discloses a fuel cell cooling system and a temperature control method thereof, and cooling adjustment of a fuel cell is realized through detecting the temperature of the battery and adjusting the rotating speed of the fan according to the change slope of the temperature of the battery; in the prior art, a technical scheme for predicting the temperature rise of a fuel cell model is established, however, the model needs to consider various factors in the power generation process of a fuel cell power generation system, different simulation parameters are set, the prediction of the final temperature rise has great influence on the condition of inaccurate prediction, and the accurate adjustment of the temperature of the fuel cell power generation system cannot be realized;
meanwhile, in the prior art, when deep learning is adopted to predict the temperature rise of the fuel cell power generation system, because more acquisition error data exists in the process of acquiring the temperature and power data of the fuel cell, the problem of low prediction accuracy also exists when the data are adopted to predict the deep learning model.
Therefore, there is a need in the art for a method and system for cooling a fuel cell power generation system that achieves a timely response to fuel cell cooling regulation and achieves accurate temperature regulation.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a cooling method and a cooling system for a fuel cell power generation system, which can realize timely cooling adjustment response of the fuel cell and accurate adjustment.
According to an aspect of the present invention, there is provided a fuel cell power generation system cooling method comprising:
s1: acquiring temperature data of the fuel cell power generation system over a period of time;
s2: acquiring power generation data of the fuel cell power generation system for a period of time;
s3: obtaining a prediction model for predicting the temperature rise condition of the fuel cell cooling system;
s4: inputting the temperature data of the fuel cell obtained in the step 1 and the power generation power data of the fuel cell obtained in the step 2 into the long-period and short-period memory network model to obtain the predicted temperature rise data of the fuel cell power generation system;
s5: and controlling a cooling system of the fuel cell according to the temperature rise data, so as to realize temperature regulation of the fuel cell power generation system.
Preferably, the temperature data of the period of time is one of temperature data of 5 minutes, temperature data of 10 minutes, temperature data of 15 minutes, and temperature data of 20 minutes; the generated power data of the period of time is one of generated power data of 5 minutes, generated power data of 10 minutes, generated power data of 15 minutes and generated power data of 20 minutes; the period of time temperature data and the period of time in the period of time generated power data refer to the same period of time.
Preferably, the current temperature of the fuel cell power generation system is obtained by a temperature sensor, the temperature sensor is arranged at a plurality of positions of the fuel cell, and the average value of the collected values according to the plurality of temperature sensors is used as the current temperature of the fuel cell power generation system.
Preferably, the power generated by the fuel cell power generation system is obtained according to a power generation schedule of the fuel cell;
preferably, the prediction of the temperature rise condition is realized based on historical temperature data of the fuel cell power generation system and generated power data.
Preferably, the temperature rise data is predicted by using a long-term and short-term memory network model.
Preferably, the step S3 specifically includes:
s31: acquiring a data set of the long-term and short-term memory network model;
taking historical data of the operation of the fuel cell power generation system as data forming the data set; training the long-term and short-term memory network model;
specifically, the history data of the operation of the fuel cell power generation system includes: temperature and power data at different times of the fuel cell power generation system;
after temperature and power data of different time are acquired, equally dividing the data into n data sets by taking a 2t time interval as a reference;
preferably, after the data set is acquired, preprocessing is further performed on the training set;
the pretreatment comprises the following steps: identifying and deleting outliers in the dataset;
s32: establishing the long-term and short-term memory network model;
introducing a gating mechanism into the long-short-period memory network model, wherein the gating mechanism comprises a forgetting gate, an input gate, an output gate and a state unit;
the forgetting door f t The formula of (2) is:
wherein f t As a forgetting gate function, as an activation function, W f 、U f 、b f To forget the door parameter x t For input at time t, h t-1 The output of the hidden layer is the time t-1;
the forgetting gate is used for determining the reservation degree of the information transmitted at the last moment, and inputting x at the moment t t Hidden layer output h from t-1 time t-1 Through linear transformation, the activation function is applied again to obtain;
the formula of the input gate is:
wherein i is t To input gate function, W i 、U i 、b i For input gate parameters, for activation functions, x t For input at time t, h t-1 Outputting a hidden layer at the moment t-1;
the input gate is used for determining the reservation degree of input information at the moment t;
the main function of the state unit is to update the internal state of the long-short-period memory model and to update the internal state C at the last moment t-1 Update to the internal state C at the present time t ；
The output gate o t The formula of (2) is:
in the formula, o t To output gate function, to activate function, W o 、U o 、b o To output the gate parameters x t For input at time t, h t-1 The output of the hidden layer is the time t-1;
wherein h is t The hidden state output at the moment t is determined by the internal state at the moment t and the input gate together;
s33: training the long-term and short-term memory network model by adopting the data set;
and taking the first t data in each data set as the input of the long-period memory network model, taking the last t data as the output of the long-period memory network model, and training the long-period memory network model.
Preferably, the training set is adopted to train the long-period memory network model so as to obtain an initial long-period memory network model; then, re-inputting the training set into the initial long-short-period memory network model respectively, comparing the second half data in the training set with the output result of the long-short-period memory network model, and if the error between the output result and the second half data in the training set is larger than a set threshold value, considering that the data set has error data, and deleting the data set at the moment;
performing the above operation on all the data sets until the data sets with error data are deleted, and training the rest data sets on the long-period memory network model again to obtain a final long-period memory network model; through the operation, the training precision of the model can be greatly improved, and the prediction precision of the prediction data of the subsequent fuel cell power generation system is further improved.
Preferably, the cooling system is a water cooling system and consists of a cooling water circulating pump, a radiator, a thermostat, a temperature sensor and a cooling controller; the cooling controller receives the predicted temperature rise data, and controls the flow of the cooling water circulating pump according to the predicted temperature rise data, so that the accurate control of the temperature is realized, and the temperature is prevented from larger fluctuation.
According to another aspect of the present invention, there is also provided a fuel cell power generation system cooling system that performs the above-described fuel cell power generation system cooling method, comprising:
a temperature sensor module for acquiring temperature data of the fuel cell power generation system for a period of time;
the power generation power acquisition module is used for acquiring power generation data of the fuel cell power generation system for a period of time;
the prediction model acquisition module is used for acquiring a prediction model for predicting the temperature rise condition of the fuel cell cooling system; the prediction model is a long-term and short-term memory network model;
the temperature rise data prediction module is connected with the temperature sensor module, the power generation power acquisition module and the prediction model acquisition module and is used for inputting the temperature data of the fuel cell acquired by the temperature sensor module and the power generation power data of the fuel cell acquired by the power generation power acquisition module into the long-period and short-period memory network model to obtain the predicted temperature rise data of the fuel cell power generation system;
and the temperature adjusting module is connected with the temperature rise data prediction module and is used for controlling the cooling system of the fuel cell according to the temperature rise data so as to realize the temperature adjustment of the power generation system of the fuel cell.
According to another aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon a data processing program that is executed by a processor to perform the above-described fuel cell power generation system cooling method.
The invention has the following technical effects:
the invention obtains temperature data and power data of the fuel cell power generation system for a period of time; then training a deep learning model through historical data, predicting future temperature rise according to temperature and power generation, and inputting a prediction result into a fuel cell cooling system in advance, so that great fluctuation of the temperature of the fuel cell power generation system is avoided;
meanwhile, the prediction of the future temperature rise condition can be realized only by the temperature data and the power generation data, and compared with the prior art, the method has the advantages that the temperature rise condition is calculated in a simulation mode by establishing a fuel cell simulation model, the method is simple and convenient, and the prediction accuracy is improved.
In addition, when the temperature rise condition of the fuel cell power generation system is predicted through the deep learning model, according to the condition that the number of error points is large in the process of collecting the temperature and power data of the fuel cell power generation system, when the model is trained by adopting historical data, the data set is compared with the preliminary prediction result, so that the error data points are deleted as much as possible, and the data in the reserved data set is accurate, so that the model training precision is higher, the accuracy of the temperature rise prediction can be effectively improved, and the accurate adjustment of the temperature of the fuel cell power generation system is realized.
Drawings
FIG. 1 is a flow chart of a method of cooling a fuel cell power generation system provided in an embodiment of the present application;
fig. 2 is a schematic diagram of a cooling system of a fuel cell power generation system according to an embodiment of the present application.
Detailed Description
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In view of the problems in the prior art, the present application proposes a method for cooling a fuel cell power generation system, for realizing timely response of cooling adjustment of the fuel cell and realizing accurate adjustment of temperature.
FIG. 1 illustrates a flow chart of a method of cooling a fuel cell power generation system, as shown in FIG. 1, the method comprising:
s1: acquiring temperature data of the fuel cell power generation system over a period of time;
specifically, the temperature data of the period of time is one of temperature data of 5 minutes, temperature data of 10 minutes, temperature data of 15 minutes and temperature data of 20 minutes;
in general, the current temperature of the fuel cell power generation system may be obtained by a temperature sensor, and in order to improve accuracy of temperature acquisition, in this embodiment, temperature sensors may be respectively disposed at a plurality of positions of the fuel cell, and an average value of acquired values of the plurality of temperature sensors is used as the current temperature of the fuel cell power generation system;
s2: acquiring power generation data of the fuel cell power generation system for a period of time;
likewise, the generated power data for the period of time is one of generated power data for 5 minutes, generated power data for 10 minutes, generated power data for 15 minutes, and generated power data for 20 minutes;
notably, the period of time of the temperature data and the period of time of the generated power data of the period of time refer to the same period of time;
the power generation of the fuel cell is determined by the power generation schedule for the fuel cell power generation system, so that the power generation for the fuel cell power generation system is available for a period of time in the future, and therefore, the power generation of the fuel cell power generation system can be obtained according to the power generation schedule of the fuel cell;
s3: obtaining a prediction model for predicting the temperature rise condition of the fuel cell cooling system;
in the prior art, a scheme for predicting the temperature rise of a fuel cell power generation system and adjusting a cooling system is also adopted, and is generally focused on establishing a fuel cell model, and the prediction and calculation of the temperature rise are realized by a simulation method, so that not only are various factors in the power generation process of the fuel cell power generation system, such as the supply speed of fuel gas, the humidity of the fuel gas, the temperature of the fuel gas, the working state of a catalyst and the like considered; the factors are numerous, and the prediction of the final temperature rise condition is greatly affected by setting different simulation parameters.
Therefore, in the embodiment, the prediction of the temperature rise condition is realized by historical temperature rise data and generated power data of the fuel cell power generation system;
the temperature rise data is predicted by adopting a long-term and short-term memory network model;
the prediction of the temperature rise data of the fuel cell power generation system is actually to predict the temperature conditions of the fuel cell power generation system at different times in a future period, that is, to predict time series data, and the long-short-period memory network model has the advantage of high prediction accuracy in the aspect of time series data prediction, so that the embodiment adopts the long-short-period memory network model to predict the temperature rise data.
Specifically, the S3 specifically includes:
s31: acquiring a data set of the long-term and short-term memory network model;
in the present embodiment, the history data of the operation of the fuel cell power generation system is taken as the data forming the data set; training the long-term and short-term memory network model;
specifically, the history data of the operation of the fuel cell power generation system includes: temperature and power data at different times of the fuel cell power generation system;
after temperature and power data of different time are acquired, equally dividing the data into n data sets by taking a 2t time interval as a reference;
illustratively, the historical data at times 1-2t is used as a first data set, the data at times (2t+1) -4t is used as a second data set, and so on, to generate n data sets.
In addition, as a preferable scheme of the embodiment, after the data set is acquired, preprocessing is further performed on the training set;
the pretreatment comprises the following steps: identifying and deleting outliers in the dataset;
s32: establishing the long-term and short-term memory network model;
specifically, a gating mechanism is introduced into the long-period memory network model and is divided into four parts of a forgetting gate, an input gate, an output gate and a state unit;
the forgetting door f t The formula of (2) is:
wherein f t As a forgetting gate function, as an activation function, W f 、U f 、b f To forget the door parameter x t For input at time t, h t-1 The output of the hidden layer is the time t-1;
the forgetting gate is used for determining the reservation degree of the information transmitted at the last moment, and inputting x at the moment t t Hidden layer output h from t-1 time t-1 Through linear transformation, the activation function is applied again to obtain;
the formula of the input gate is:
wherein i is t To input gate function, W i 、U i 、b i For input gate parameters, for activation functions, x t For input at time t, h t-1 Outputting a hidden layer at the moment t-1;
the input gate is used for determining the reservation degree of input information at the moment t;
the main function of the state unit is to update the internal state of the long-short-period memory model and to update the internal state C at the last moment t-1 Update to the internal state C at the present time t ；
The output gate o t The formula of (2) is:
in the formula, o t To output gate function, to activate function, W o 、U o 、b o To output the gate parameters x t For input at time t, h t-1 The output of the hidden layer is the time t-1;
wherein h is t The hidden state output at the moment t is determined by the internal state at the moment t and the input gate together;
s33: training the long-term and short-term memory network model by adopting the data set;
and taking the first t data in each data set as the input of the long-period memory network model, taking the last t data as the output of the long-period memory network model, and training the long-period memory network model.
According to a preferred scheme of the present embodiment, in the prior art, the data set is generally screened, namely, trained, and for the data acquisition process of the fuel cell power generation system, sometimes, because the temperature acquisition device is inaccurate or the power acquisition is inaccurate, values at some moments cannot reflect real values, and then, the values are included in the data set to train the model, so that the training accuracy of the model is necessarily affected;
therefore, in this embodiment, the training set is first used to train the long-short-term memory network model, so as to obtain an initial long-short-term memory network model; then, re-inputting the training set into the initial long-short-period memory network model respectively, comparing the second half data in the training set with the output result of the long-short-period memory network model, and if the error between the output result and the second half data in the training set is larger than a set threshold value, considering that the data set has error data, and deleting the data set at the moment;
performing the above operation on all the data sets until the data sets with error data are deleted, and training the rest data sets on the long-period memory network model again to obtain a final long-period memory network model; through the operation, the training precision of the model can be greatly improved, and the prediction precision of the prediction data of the subsequent fuel cell power generation system is further improved.
S4: inputting the temperature data of the fuel cell obtained in the step 1 and the power generation power data of the fuel cell obtained in the step 2 into the long-period and short-period memory network model to obtain the predicted temperature rise data of the fuel cell power generation system;
s5: controlling a cooling module of the fuel cell according to the temperature rise data, thereby realizing temperature regulation of the fuel cell power generation system;
the cooling module is a water cooling system and consists of a cooling water circulating pump, a radiator, a thermostat, a temperature sensor and a cooling controller; the cooling controller receives the predicted temperature rise data, and controls the flow of the cooling water circulating pump according to the predicted temperature rise data, so that the accurate control of the temperature is realized, and the temperature is prevented from larger fluctuation.
The second embodiment includes a fuel cell power generation system cooling system that performs the fuel cell power generation system cooling method of the first embodiment, as shown in fig. 2, including:
a temperature sensor module for acquiring temperature data of the fuel cell power generation system for a period of time;
the power generation power acquisition module is used for acquiring power generation data of the fuel cell power generation system for a period of time;
the prediction model acquisition module is used for acquiring a prediction model for predicting the temperature rise condition of the fuel cell cooling system; the prediction model is a long-term and short-term memory network model;
the temperature rise data prediction module is connected with the temperature sensor module, the power generation power acquisition module and the prediction model acquisition module and is used for inputting the temperature data of the fuel cell acquired by the temperature sensor module and the power generation power data of the fuel cell acquired by the power generation power acquisition module into the long-period and short-period memory network model to obtain the predicted temperature rise data of the fuel cell power generation system;
and the temperature adjusting module is connected with the temperature rise data prediction module and is used for controlling the cooling system of the fuel cell according to the temperature rise data so as to realize the temperature adjustment of the power generation system of the fuel cell.
In a third embodiment, the present embodiment includes a computer-readable storage medium having stored thereon a data processing program that is executed by a processor to perform the fuel cell power generation system cooling method of the first embodiment.
It will be apparent to one of ordinary skill in the art that embodiments herein may be provided as a method, apparatus (device), or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, including, but not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.
The description herein is with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments herein. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements.
It should also be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," "outer," and the like indicate an orientation or a positional relationship based on that shown in the drawings, and are merely for convenience of description and simplification of the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present application. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the terms in this application will be understood by those of ordinary skill in the art in a specific context.
The above examples and/or embodiments are merely for illustrating the preferred embodiments and/or implementations of the present technology, and are not intended to limit the embodiments and implementations of the present technology in any way, and any person skilled in the art should be able to make some changes or modifications to the embodiments and/or implementations without departing from the scope of the technical means disclosed in the present disclosure, and it should be considered that the embodiments and implementations are substantially the same as the present technology.
Specific examples are set forth herein to illustrate the principles and embodiments of the present application, and the description of the examples above is only intended to assist in understanding the methods of the present application and their core ideas. The foregoing is merely a preferred embodiment of the present application, and it should be noted that, due to the limited text expressions, there is virtually no limit to the specific structure, and that, for a person skilled in the art, modifications, alterations and combinations of the above described features may be made in an appropriate manner without departing from the principles of the present application; such modifications, variations and combinations, or the direct application of the concepts and aspects of the invention in other applications without modification, are intended to be within the scope of this application.
Claims (7)
1. A method of cooling a fuel cell power generation system, comprising the steps of:
s1: acquiring temperature data of the fuel cell power generation system over a period of time;
s2: acquiring power generation data of the fuel cell power generation system for a period of time;
s3: obtaining a prediction model for predicting the temperature rise condition of the fuel cell cooling system; the prediction model is a long-term and short-term memory network model;
s4: inputting the temperature data of the fuel cell obtained in the step 1 and the power generation power data of the fuel cell obtained in the step 2 into the long-period and short-period memory network model to obtain the predicted temperature rise data of the fuel cell power generation system;
s5: controlling a cooling system of the fuel cell according to the temperature rise data, thereby realizing temperature regulation of the fuel cell power generation system;
the step S3 specifically comprises the following steps:
s31: acquiring a data set of the long-term and short-term memory network model;
taking historical data of the operation of the fuel cell power generation system as data forming the data set; training the long-term and short-term memory network model;
the historical data of the operation of the fuel cell power generation system includes: temperature and power data at different times of the fuel cell power generation system;
s32: establishing the long-term and short-term memory network model;
introducing a gating mechanism into the long-short-period memory network model, wherein the gating mechanism comprises a forgetting gate, an input gate, an output gate and a state unit;
the forgetting door f t The formula of (2) is:
wherein f t As a forgetting door function, saidTo activate the function, W f 、U f 、b f To forget the door parameter x t For input at time t, h t-1 The output of the hidden layer is the time t-1;
the forgetting gate is used for determining the reservation degree of the information transmitted at the last moment, and inputting x at the moment t t At time t-1Hidden layer output h t-1 Reapplication of the activation function by linear transformationObtaining;
the input gate i t The formula of (2) is:
wherein i is t To input gate function, W i 、U i 、b i In order to input the door parameters,to activate the function, x t For input at time t, h t-1 Outputting a hidden layer at the moment t-1;
the input gate is used for determining the reservation degree of input information at the moment t;
the main function of the state unit is to update the internal state of the long-short-period memory model and to update the internal state C at the last moment t-1 Update to the internal state C at the present time t ；
The output gate o t The formula of (2) is:
in the formula, o t In order to output the gate function,to activate the function, W o 、U o 、b o To output the gate parameters x t For input at time t, h t-1 The output of the hidden layer is the time t-1;
wherein h is t The hidden state output at the moment t is determined by the internal state at the moment t and the input gate together;
s33: training the long-term and short-term memory network model by adopting the data set;
firstly, training the long-short-term memory network model by adopting the training set so as to obtain an initial long-short-term memory network model; then, the training sets are input into the initial long-short-period memory network model again, the latter half data in each training set is compared with each output result of the long-short-period memory network model, if the error between the output result and the latter half data in the training set is larger than a set threshold value, the data set is considered to have error data, and at the moment, the data set is deleted;
and performing the operation on all the data sets until the data sets with error data are deleted, and training the long-period memory network model again by the rest data sets, thereby obtaining the final long-period memory network model.
2. The cooling method of the fuel cell power generation system according to claim 1, wherein the temperature data for the period of time is one of 5 minutes of temperature data, 10 minutes of temperature data, 15 minutes of temperature data, and 20 minutes of temperature data; the generated power data of the period of time is one of generated power data of 5 minutes, generated power data of 10 minutes, generated power data of 15 minutes and generated power data of 20 minutes; the period of time temperature data and the period of time in the period of time generated power data refer to the same period of time.
3. The cooling method of a fuel cell power generation system according to claim 1, wherein a current temperature of the fuel cell power generation system is obtained by a temperature sensor, the temperature sensor is provided at a plurality of positions of the fuel cell, and an average value of the collected values of the plurality of temperature sensors is used as the current temperature of the fuel cell power generation system; and acquiring the power generated by the fuel cell power generation system according to the power generation plan of the fuel cell.
4. The cooling method of a fuel cell power generation system according to claim 1, wherein the prediction of the temperature rise condition is achieved based on historical temperature data and generated power data of the fuel cell power generation system.
5. The cooling method according to claim 1, wherein in S31, after the temperature and power data of different times are obtained, the data are equally divided into n data sets based on a 2t time interval.
6. The cooling method of the fuel cell power generation system according to claim 1, wherein in S33, the first t data in each data set is used as an input of the long-short-term memory network model, and the last t data is used as an output of the long-short-term memory network model, and the long-short-term memory network model is trained.
7. A fuel cell power generation system cooling system that performs the fuel cell power generation system cooling method according to any one of claims 1 to 6, characterized in that the cooling system comprises:
a temperature sensor module for acquiring temperature data of the fuel cell power generation system for a period of time;
the power generation power acquisition module is used for acquiring power generation data of the fuel cell power generation system for a period of time;
the prediction model acquisition module is used for acquiring a prediction model for predicting the temperature rise condition of the fuel cell cooling system; the prediction model is a long-term and short-term memory network model;
the temperature rise data prediction module is connected with the temperature sensor module, the power generation power acquisition module and the prediction model acquisition module and is used for inputting the temperature data of the fuel cell acquired by the temperature sensor module and the power generation power data of the fuel cell acquired by the power generation power acquisition module into the long-period and short-period memory network model to obtain the predicted temperature rise data of the fuel cell power generation system;
and the temperature adjusting module is connected with the temperature rise data prediction module and is used for controlling the cooling system of the fuel cell according to the temperature rise data so as to realize the temperature adjustment of the power generation system of the fuel cell.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311254187.3A CN116995276B (en) | 2023-09-27 | 2023-09-27 | Cooling method and system for fuel cell power generation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311254187.3A CN116995276B (en) | 2023-09-27 | 2023-09-27 | Cooling method and system for fuel cell power generation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116995276A CN116995276A (en) | 2023-11-03 |
| CN116995276B true CN116995276B (en) | 2023-12-29 |
Family
ID=88525197
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311254187.3A Active CN116995276B (en) | 2023-09-27 | 2023-09-27 | Cooling method and system for fuel cell power generation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116995276B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117217031B (en) * | 2023-11-09 | 2024-02-20 | 新研氢能源科技有限公司 | Intelligent production method and system for fuel cell stack |
| CN118473067B (en) * | 2024-07-15 | 2024-09-06 | 观典防务技术股份有限公司 | High-efficiency hydrogen fuel cell power supply system for unmanned aerial vehicle |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
| CN114048772A (en) * | 2021-11-09 | 2022-02-15 | 中山大学 | Fault diagnosis method, system and storage medium for fuel cell device |
| CN114740361A (en) * | 2022-04-12 | 2022-07-12 | 湖南大学 | Fuel cell voltage prediction method based on long-short term memory neural network model |
| CN115275410A (en) * | 2022-08-16 | 2022-11-01 | 上海电享信息科技有限公司 | Battery temperature rise abnormity early warning method |
| WO2023000985A1 (en) * | 2021-07-22 | 2023-01-26 | 中国第一汽车股份有限公司 | Method and apparatus for predicting remaining life of fuel cell |
| CN115659839A (en) * | 2022-11-14 | 2023-01-31 | 新源动力股份有限公司 | Modeling optimization method of fuel cell air system simulation model |
| CN115758290A (en) * | 2022-10-10 | 2023-03-07 | 重庆大唐国际彭水水电开发有限公司 | Fan gearbox high-speed shaft temperature trend early warning method based on LSTM |
| WO2023110070A1 (en) * | 2021-12-15 | 2023-06-22 | Volvo Truck Corporation | A method for controlling a fuel cell system |
| CN116306270A (en) * | 2023-03-02 | 2023-06-23 | 新源动力股份有限公司 | Method for predicting fuel cell performance and optimizing key input parameters |
| CN116435557A (en) * | 2023-05-22 | 2023-07-14 | 深圳供电局有限公司 | Fuel cell thermal management method, device and system based on neural network |
| CN116559704A (en) * | 2023-05-19 | 2023-08-08 | 北京京深深向科技有限公司 | Method and device for predicting remaining life of fuel cell for vehicle, electronic equipment and storage medium |
| CN116663388A (en) * | 2023-04-10 | 2023-08-29 | 武汉轻工大学 | Grain pile temperature prediction method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102575043B1 (en) * | 2023-02-07 | 2023-09-07 | 주식회사 시너지 | High-efficiency fuel cell system and control method thereof |
-
2023
- 2023-09-27 CN CN202311254187.3A patent/CN116995276B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020191800A1 (en) * | 2019-03-27 | 2020-10-01 | 东北大学 | Method for predicting remaining service life of lithium-ion battery employing wde-optimized lstm network |
| WO2023000985A1 (en) * | 2021-07-22 | 2023-01-26 | 中国第一汽车股份有限公司 | Method and apparatus for predicting remaining life of fuel cell |
| CN114048772A (en) * | 2021-11-09 | 2022-02-15 | 中山大学 | Fault diagnosis method, system and storage medium for fuel cell device |
| WO2023110070A1 (en) * | 2021-12-15 | 2023-06-22 | Volvo Truck Corporation | A method for controlling a fuel cell system |
| CN114740361A (en) * | 2022-04-12 | 2022-07-12 | 湖南大学 | Fuel cell voltage prediction method based on long-short term memory neural network model |
| CN115275410A (en) * | 2022-08-16 | 2022-11-01 | 上海电享信息科技有限公司 | Battery temperature rise abnormity early warning method |
| CN115758290A (en) * | 2022-10-10 | 2023-03-07 | 重庆大唐国际彭水水电开发有限公司 | Fan gearbox high-speed shaft temperature trend early warning method based on LSTM |
| CN115659839A (en) * | 2022-11-14 | 2023-01-31 | 新源动力股份有限公司 | Modeling optimization method of fuel cell air system simulation model |
| CN116306270A (en) * | 2023-03-02 | 2023-06-23 | 新源动力股份有限公司 | Method for predicting fuel cell performance and optimizing key input parameters |
| CN116663388A (en) * | 2023-04-10 | 2023-08-29 | 武汉轻工大学 | Grain pile temperature prediction method, device, equipment and storage medium |
| CN116559704A (en) * | 2023-05-19 | 2023-08-08 | 北京京深深向科技有限公司 | Method and device for predicting remaining life of fuel cell for vehicle, electronic equipment and storage medium |
| CN116435557A (en) * | 2023-05-22 | 2023-07-14 | 深圳供电局有限公司 | Fuel cell thermal management method, device and system based on neural network |
Non-Patent Citations (4)
| Title |
|---|
| "Model-based degradation prediction on impedance data and artificial neural network for hightemperature polymer electrolyte membrane fuel cells after hydrogen starvation";Khrystyna Yezerska 等;《International journal of hydrogen energy》;第47卷;第29495-29504页 * |
| "基于BP神经网络辨识模型的PEMFC系统建模";柯超 等;《软件工程》;第23卷(第03期);第14-16、8页 * |
| "基于改进LSTM 的锂离子电池剩余使用寿命预测方法";尹皓 等;《宿州学院学报》;第38卷(第9期);第1-6页 * |
| Kyunghyun Kim,et al.."Pre-diagnosis of flooding and drying in proton exchange membrane fuel cells by bagging ensemble deep learning models using long short-term memory and convolutional neural networks".《Energy》.2022,第226卷第126441-（1-11）页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116995276A (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116995276B (en) | Cooling method and system for fuel cell power generation system | |
| CN111795484B (en) | Intelligent air conditioner control method and system | |
| CN111222674A (en) | Short-term photovoltaic power generation capacity prediction method based on long-term and short-term memory neural network | |
| Chen et al. | Temperature and voltage dynamic control of PEMFC Stack using MPC method | |
| CN115425680B (en) | Power prediction model construction and prediction method of multi-energy combined power generation system | |
| US11355937B2 (en) | Electrical grid control and optimization | |
| Chen et al. | Optimal control strategy for solid oxide fuel cell‐based hybrid energy system using deep reinforcement learning | |
| CN112949918A (en) | DGM-RNN-based day-ahead photovoltaic power prediction method and system | |
| CN115716469A (en) | Output power distribution control method of hybrid power system | |
| CN114661011B (en) | Building comprehensive energy system optimizing operation method, device and storage medium | |
| Clauß et al. | Practical challenges towards data-driven applications in buildings: lessons-learned from two real-life case studies | |
| CN116540543A (en) | Multi-target control optimization method and device for nuclear steam supply system | |
| US11735916B2 (en) | Autonomous electrical grid management | |
| CN115764855A (en) | Real-time adjustable capacity and available electric quantity prediction method for electric vehicle quick charging station | |
| KR20230076067A (en) | Energy menagement method and apparatus based on reinforcement learning | |
| CN104133369A (en) | Control method for dynamic characteristics of proton exchange membrane fuel cell | |
| Xu et al. | Modeling and control-oriented thermal characteristics under variable load of the solid oxide fuel cell | |
| CN114676866A (en) | Method, device and storage medium for correcting load prediction before day based on error correction | |
| Yang et al. | Electricity load forecasting based on long and short-term memory neural network | |
| Chew et al. | Review on Determinant Parameters of Genetic Algorithm for the Optimized Closed Loop Control | |
| CN118350290B (en) | Battery thermal management method and system based on artificial intelligence | |
| Cardoso et al. | Intelligent Micro-Cogeneration Systems for Residential Grids: A Sustainable Solution for Efficient Energy Management. Energies 2023, 16, 5215 | |
| CN118095783B (en) | Electric automobile charging planning method and device | |
| CN117232098B (en) | Automatic adjusting method and system based on energy control of frequency converter | |
| Wu | Machine Learning Approaches for Efficient Forecasting of LEED Accredited Building Energy |
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 |