CN117976948B - Small-sized air-cooled hydrogen fuel cell operation monitoring method and system - Google Patents
Small-sized air-cooled hydrogen fuel cell operation monitoring method and system Download PDFInfo
- Publication number
- CN117976948B CN117976948B CN202410369783.4A CN202410369783A CN117976948B CN 117976948 B CN117976948 B CN 117976948B CN 202410369783 A CN202410369783 A CN 202410369783A CN 117976948 B CN117976948 B CN 117976948B
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- value
- current time
- time period
- moment
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 206
- 239000000446 fuel Substances 0.000 title claims abstract description 83
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 title claims abstract description 67
- 239000001257 hydrogen Substances 0.000 title claims abstract description 67
- 229910052739 hydrogen Inorganic materials 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 37
- 239000011159 matrix material Substances 0.000 claims abstract description 83
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000001914 filtration Methods 0.000 claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims description 63
- 238000012512 characterization method Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000015556 catabolic process Effects 0.000 description 7
- 238000006731 degradation reaction Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000017525 heat dissipation Effects 0.000 description 3
- 239000001301 oxygen Substances 0.000 description 3
- 229910052760 oxygen Inorganic materials 0.000 description 3
- UXFQFBNBSPQBJW-UHFFFAOYSA-N 2-amino-2-methylpropane-1,3-diol Chemical compound OCC(N)(C)CO UXFQFBNBSPQBJW-UHFFFAOYSA-N 0.000 description 2
- 101150035093 AMPD gene Proteins 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000003487 electrochemical reaction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- H01M8/04992—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
-
- 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
- H01M8/04313—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
- H01M8/04328—Temperature; Ambient temperature of anode reactants at the inlet or inside the fuel cell
-
- 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
- H01M8/04335—Temperature; Ambient temperature of cathode reactants at the inlet or inside the fuel cell
-
- 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
- H01M8/0438—Pressure; Ambient pressure; Flow
-
- 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
- H01M8/0438—Pressure; Ambient pressure; Flow
- H01M8/04388—Pressure; Ambient pressure; Flow of anode reactants at the inlet or inside the fuel cell
-
- 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
- H01M8/0438—Pressure; Ambient pressure; Flow
- H01M8/04395—Pressure; Ambient pressure; Flow of cathode reactants at the inlet or inside the fuel cell
-
- 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
- H01M8/04492—Humidity; Ambient humidity; Water content
-
- 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
- H01M8/04537—Electric variables
- H01M8/04544—Voltage
-
- 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
- H01M8/04537—Electric variables
- H01M8/04574—Current
-
- 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)
- 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 relates to the technical field of battery data monitoring, in particular to a method and a system for monitoring the operation of a small-sized air-cooled hydrogen fuel cell. The method comprises the following steps: acquiring monitoring data of a small-sized air-cooled hydrogen fuel cell in a current time period; acquiring a noise matrix corresponding to the current moment based on the monitoring data of each moment and a volume Kalman filtering algorithm; determining a target noise matrix according to the difference between the fluctuation condition of each monitoring data in the current time period and the fluctuation condition of each monitoring data in the period of the current time and the noise matrix corresponding to the current time; and obtaining predicted data of the next moment based on the monitored data of the current moment and the target noise matrix, and judging the running state of the small-sized air-cooled hydrogen fuel cell. The invention improves the accuracy of the prediction result of the monitoring data of the small-sized air-cooled hydrogen fuel cell and the accuracy of the monitoring result of the running state of the small-sized air-cooled hydrogen fuel cell.
Description
Technical Field
The invention relates to the technical field of battery data monitoring, in particular to a method and a system for monitoring the operation of a small-sized air-cooled hydrogen fuel cell.
Background
A small-sized air-cooled hydrogen fuel cell is an apparatus for generating electric power by chemical reaction of hydrogen and oxygen, which generates electricity by electrochemical reaction while generating water and a small amount of heat energy by inputting hydrogen and oxygen into the fuel cell. Air cooling refers to the use of a fan or cooling system to dissipate heat generated in the fuel cell to maintain the operating temperature of the fuel cell. The operation state and the performance parameters of the fuel cell are monitored, the operation state of the fuel cell can be monitored in time, abnormal conditions and faults are found, related personnel can take measures in time to repair and maintain, fault expansion and chain reaction are avoided, the working efficiency, the energy conversion efficiency and the like of the fuel cell can be evaluated, the service life of the fuel cell can be predicted by monitoring the operation time, the heat balance condition and the like of the fuel cell, and more reasonable maintenance plans and updating strategies are formulated.
In the prior art, the Kalman filtering is often adopted to sense the operation state of the fuel cell and estimate the operation state of the fuel cell at the next moment, however, the operation state of the hydrogen fuel cell is influenced by the outside to present the characteristic of nonlinear noise, the characteristic of low filtering precision of Unscented Kalman filtering (Unscented KALMAN FILTER, UKF) under high-dimensional data can be overcome by the volumetric Kalman filtering (Cubature KALMAN FILTER, CKF), and the method is more suitable for sensing the system state under the condition of more data dimensions caused by more monitoring indexes. When CKF carries out continuous time sequence prediction, the phenomenon of battery performance degradation occurs to the fuel cell along with the increase of the using time length, so as to influence the change characteristic of the monitoring value, and when the existing CKF carries out noise matrix updating, the fluctuation range of the monitoring value is changed due to the battery performance degradation, but the noise matrix can not quickly and accurately convert the information in the noise matrix into the system noise condition after the battery performance degradation due to the use of global data, so that the CKF generates larger deviation between the prediction result of the monitoring data of the small-sized air-cooled hydrogen fuel cell and the actual battery operation condition, and further the monitoring of the operation state of the small-sized air-cooled hydrogen fuel cell is influenced.
Disclosure of Invention
In order to solve the problem that the predicted result and the actual result have larger deviation when the existing CKF predicts the monitoring data of the small-sized air-cooled hydrogen fuel cell, the invention aims to provide a method and a system for monitoring the operation of the small-sized air-cooled hydrogen fuel cell, and the adopted technical scheme is as follows:
In a first aspect, the present invention provides a method for monitoring operation of a small-sized air-cooled hydrogen fuel cell, the method comprising the steps of:
Different kinds of monitoring data of each moment in each period of the small-sized air-cooled hydrogen fuel cell in the current time period are obtained;
Acquiring a noise matrix corresponding to the current moment based on all monitoring data of each moment and a volume Kalman filtering algorithm; obtaining a fluctuation evaluation value of each monitoring data in the current time period according to the fluctuation condition of each monitoring data in the current time period; obtaining a fluctuation evaluation value of each monitoring data in the period of the current moment according to the fluctuation condition of each monitoring data in the period of the current moment;
Obtaining a battery state representation value at the current moment according to the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period at the current moment and the element value in the noise matrix corresponding to the current moment; determining a target noise matrix based on the battery state characterization value;
Acquiring all prediction data of the next moment based on all monitoring data of the current moment, the target noise matrix and a volume Kalman filtering algorithm; and judging the running state of the small-sized air-cooled hydrogen fuel cell based on the prediction data.
Preferably, the obtaining the fluctuation evaluation value of each monitoring data in the current time period according to the fluctuation condition of each monitoring data in the current time period includes:
For the kth monitoring data:
Performing curve fitting on all k-th monitoring data in the current time period to obtain a fitting curve corresponding to the k-th monitoring data in the current time period;
Respectively obtaining the time intervals between every two adjacent extreme points of the kth monitoring data on the fitting curve corresponding to the current time period, and recording the average value of the time intervals between all the adjacent extreme points of the kth monitoring data on the fitting curve corresponding to the current time period as the average value of the time intervals corresponding to the kth monitoring data;
Respectively acquiring the ordinate of the minimum value point adjacent to each maximum value point in the time interval closest to the k-th monitoring data on a fitting curve corresponding to the current time period, and taking the ordinate as a reference value corresponding to each maximum value point;
And obtaining the fluctuation evaluation value of the kth monitoring data in the current time period according to the ordinate of the maximum points of the kth monitoring data on the fitting curve corresponding to the current time period, the reference value corresponding to each maximum point, the time sequence interval average value, the number of the maximum points and the number of the minimum points of the kth monitoring data on the fitting curve corresponding to the current time period.
Preferably, the fluctuation evaluation value of the kth monitoring data in the current period is calculated using the following formula:
;
Wherein A k represents the fluctuation evaluation value of the kth monitoring data in the current time period, R k represents the number of maximum points of the kth monitoring data on the fitting curve corresponding to the current time period, Ordinate representing the (r) th maximum point of the fitted curve corresponding to the current time period of the kth monitoring data,/>Mean value of reference values corresponding to all maximum value points on a fitting curve corresponding to the current time period of kth monitoring data is expressed, namely/>The average value of time intervals corresponding to the kth monitoring data is represented, N k represents the number of minimum value points of the kth monitoring data on a fitting curve corresponding to the current time period, sinc () represents a sine function, and I represents taking absolute value symbols.
Preferably, the obtaining a battery state representation value at the current time according to the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period where the current time is located and the element value in the noise matrix corresponding to the current time includes:
respectively taking the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period of the current moment as the evaluation value difference of each monitoring data;
respectively calculating the average value and standard deviation of all elements in the noise matrix corresponding to the current moment;
And obtaining a battery state representation value at the current moment based on the evaluation value difference of each monitoring data and the average value and standard deviation of all elements in the noise matrix corresponding to the current moment.
Preferably, the battery state characterization value at the current time is calculated using the following formula:
;
Wherein M 0 represents a battery state characterization value at the current time, K represents the number of kinds of monitoring data, A k represents a fluctuation evaluation value of kth monitoring data in the current time period, Representing the fluctuation evaluation value of the kth monitoring data in the current time period, z i represents the ith element in the noise matrix corresponding to the current time, n represents the number of elements in the noise matrix corresponding to the current time,/>The average value of all elements in the noise matrix corresponding to the current moment is represented, sigma represents the standard deviation of all elements in the noise matrix corresponding to the current moment, and 'I' represents taking absolute value sign, simoid () is a normalization function.
Preferably, the obtaining the noise matrix corresponding to the current time based on all the monitoring data and the volume kalman filtering algorithm at each time includes:
For any time instant: all the monitoring data at the moment form a characteristic vector at the moment;
And taking the characteristic vector of each moment as the input of a volume Kalman filtering algorithm to obtain a noise matrix corresponding to the current moment.
Preferably, the determining the target noise matrix based on the battery state characterization value includes:
If the battery state representation value is smaller than a preset representation threshold, taking a noise matrix corresponding to the current moment as a target noise matrix;
And if the battery state representation value is larger than or equal to a preset representation threshold value, inputting the feature vector of each moment in the period of the current moment into a volume Kalman filtering algorithm to obtain a target noise matrix.
Preferably, based on all the monitoring data at the current moment, the target noise matrix and the volume kalman filtering algorithm, all the prediction data at the next moment are obtained, including:
And returning the characteristic vector at the current moment and the target noise matrix to a volume Kalman filtering algorithm to obtain all prediction data at the next moment.
Preferably, the determining the operation state of the small-sized air-cooled hydrogen fuel cell based on the prediction data includes:
Judging whether the predicted data is in a standard range, if so, judging that the running state of the small-sized air-cooled hydrogen fuel cell is normal; if not, the operation state of the small-sized air-cooled hydrogen fuel cell is judged to be abnormal.
In a second aspect, the present invention provides a small-sized air-cooled hydrogen fuel cell operation monitoring system, which includes a memory and a processor, where the processor executes a computer program stored in the memory, so as to implement the small-sized air-cooled hydrogen fuel cell operation monitoring method.
The invention has at least the following beneficial effects:
According to the invention, the monitoring data of the small-sized air-cooled hydrogen fuel cell in the current time period is input into the volume Kalman filtering algorithm to obtain a corresponding noise matrix, elements in the noise matrix can reflect the interference degree of noise on various monitoring data, the difference between the fluctuation condition of each monitoring data in the current time period and the fluctuation condition of each monitoring data in the period of the current time period and the element value in the noise matrix corresponding to the current time are combined, the battery state representation value of the current time is determined, the noise matrix in the volume Kalman filtering algorithm is updated based on the battery state representation value of the current time to obtain a target noise matrix, the running state of the small-sized air-cooled hydrogen fuel cell is further predicted based on the prediction result, the difference of the change amplitude of the different monitoring data and the influence of the different monitoring data on the noise matrix in the prediction process of the volume Kalman filtering algorithm are considered, the target noise matrix is respectively determined by analyzing the different monitoring data, compared with the traditional battery state of the volume Kalman filtering algorithm, the accuracy is improved, the running state of the battery is more accurately identified, and the running state of the battery is more accurately identified by the global state than the conventional Kalman filtering algorithm.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for monitoring operation of a small-sized air-cooled hydrogen fuel cell according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given to a small-sized air-cooled hydrogen fuel cell operation monitoring method and system according to the invention by combining the accompanying drawings and the preferred embodiment.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a method and a system for monitoring the operation of a small-sized air-cooled hydrogen fuel cell, which are specifically described below with reference to the accompanying drawings.
An embodiment of a small-sized air-cooled hydrogen fuel cell operation monitoring method comprises the following steps:
The specific scene aimed at by this embodiment is: when predicting the monitoring data of the small-sized air-cooled hydrogen fuel cell at the future moment, the capacity Kalman filter can overcome the characteristic that the unscented Kalman filter has low filtering precision under high-dimensional data, and is more suitable for sensing the system state under the condition of more data dimensions caused by more monitoring indexes, so that the embodiment predicts the monitoring data of the small-sized air-cooled hydrogen fuel cell at the next moment by adopting the capacity Kalman filter and evaluates the running state of the small-sized air-cooled hydrogen fuel cell at the next moment based on a prediction result.
The embodiment provides a method for monitoring the operation of a small-sized air-cooled hydrogen fuel cell, as shown in fig. 1, which comprises the following steps:
Step S1, different kinds of monitoring data of each moment in each period of the small-sized air-cooled hydrogen fuel cell in the current time period are obtained.
In this embodiment, first, different kinds of sensors are disposed at suitable positions for collecting different kinds of monitoring data of a small-sized air-cooled hydrogen fuel cell, where the monitoring data collected in this embodiment includes hydrogen flow, oxygen flow, overall temperature of the fuel cell, internal pressure of the fuel cell, stack temperature of the fuel cell, inlet temperature of the fuel cell, outlet temperature of the fuel cell, output current, output voltage, and humidity of an auxiliary system, where the units of flow are milliliters/second, the units of temperature are degrees celsius, the units of pressure are bars, the units of current are amperes, the units of voltage are volts, and the units of humidity are relative humidity. In this embodiment, all kinds of monitoring data of the small-sized air-cooled hydrogen fuel cell in the current time period are collected, in this embodiment, the current time period is a set formed by all historical time points with a time interval smaller than or equal to a preset time length from the current time point, the preset time length in this embodiment is 60 hours, the collection frequency of the monitoring data is set to be one time per second, that is, all kinds of monitoring data are collected every second in the current time period, and in specific application, an implementer can set the collection frequency of the monitoring data and the kinds of the monitoring data according to specific situations.
Thus, the embodiment collects different kinds of monitoring data of each collection time of the small-sized air-cooled hydrogen fuel cell in the current time period, and the embodiment takes every 12 hours as one period, namely the current time period is divided into a plurality of periods, namely different kinds of monitoring data of each time of the small-sized air-cooled hydrogen fuel cell in each period in the current time period are obtained.
Step S2, obtaining a noise matrix corresponding to the current moment based on all monitoring data of each moment and a volume Kalman filtering algorithm; obtaining a fluctuation evaluation value of each monitoring data in the current time period according to the fluctuation condition of each monitoring data in the current time period; and obtaining a fluctuation evaluation value of the period of each monitoring data at the current moment according to the fluctuation condition of each monitoring data in the period of the current moment.
Because the stability of the device is often higher in the initial stage of the operation of the fuel cell, the difference condition between the monitoring value and the predicted value is smaller, so that the data fluctuation of the monitoring value of a single type in the operation process of the corresponding cell can be analyzed through the fluctuation condition of the monitoring value of the single type, and the performance degradation characteristic of the fuel cell in the operation process can be reflected by the deviation degree of the variation condition of the monitoring value of the type and the fluctuation condition of the historical data in the subsequent moment, so that the performance degradation evaluation of the cell is comprehensively judged through the analysis of the deviation condition of the monitoring values of multiple types.
For any time within the current time period: all the monitoring data at that moment constitute a feature vector at that moment. By adopting the method, the characteristic vector of each moment in the current time period can be obtained. And taking the characteristic vector of each moment in the current time period as the input of a volume Kalman filtering algorithm, and obtaining a noise matrix corresponding to the current moment. The volumetric kalman filter algorithm is prior art and will not be described in detail here.
Considering that the fluctuation condition of the monitoring data in the current time period can be reflected by the difference condition between the extreme points on the fitting curve, the embodiment can evaluate the data fluctuation condition of each monitoring data in the local time sequence range through the difference condition between the adjacent extreme points on the fitting curve, and further analyze the fluctuation frequency of the curve by combining the interval between the extreme points to judge whether each monitoring data is easier to generate larger numerical fluctuation condition.
Specifically, for the kth monitoring data:
performing curve fitting on all k-th monitoring data in the current time period to obtain a fitted curve corresponding to the k-th monitoring data in the current time period, wherein the abscissa of the fitted curve is the corresponding acquisition time, and the ordinate is the monitoring data value; detecting a fitting curve by adopting an AMPD algorithm to obtain a maximum value point and a minimum value point on the fitting curve; both curve fitting and AMPD algorithms are prior art and will not be described in detail here. Respectively obtaining the time intervals between every two adjacent extreme points of the kth monitoring data on the fitting curve corresponding to the current time period, and recording the average value of the time intervals between all the adjacent extreme points of the kth monitoring data on the fitting curve corresponding to the current time period as the average value of the time intervals corresponding to the kth monitoring data; the extreme points include a maximum point and a minimum point. Respectively acquiring the ordinate of the minimum value point adjacent to each maximum value point in the time interval closest to the k-th monitoring data on a fitting curve corresponding to the current time period, and taking the ordinate as a reference value corresponding to each maximum value point; it should be noted that: for any maximum point on the fitted curve: if the number of minimum value points adjacent to the maximum value point in the time interval is 2, taking the average value of the ordinate of the two minimum value points as the reference value corresponding to the maximum value point. And obtaining the fluctuation evaluation value of the kth monitoring data in the current time period according to the ordinate of the maximum points of the kth monitoring data on the fitting curve corresponding to the current time period, the reference value corresponding to each maximum point, the time sequence interval average value, the number of the maximum points and the number of the minimum points of the kth monitoring data on the fitting curve corresponding to the current time period. The specific calculation formula of the fluctuation evaluation value of the kth monitoring data in the current time period is as follows:
;
Wherein A k represents the fluctuation evaluation value of the kth monitoring data in the current time period, R k represents the number of maximum points of the kth monitoring data on the fitting curve corresponding to the current time period, Ordinate representing the (r) th maximum point of the fitted curve corresponding to the current time period of the kth monitoring data,/>Mean value of reference values corresponding to all maximum value points on a fitting curve corresponding to the current time period of kth monitoring data is expressed, namely/>The average value of time intervals corresponding to the kth monitoring data is represented, N k represents the number of minimum value points of the kth monitoring data on a fitting curve corresponding to the current time period, sinc () represents a sine function, and I represents taking absolute value symbols.
The larger the value of the (k) th monitoring data is, the fewer data fluctuation conditions exist on the fitting curve corresponding to the current time period, meanwhile, the lower the data fluctuation range is, the more slight the state change of the working state of the battery represented by the k (k) th monitoring data in the running process of the battery is reflected, namely the judgment of the working performance decline condition of the battery is more accurate by using the data fluctuation condition of the k (k) th monitoring data. /(I)The greater the value of the sinc function value tends to be 1 when the independent variable tends to be 0, which is the mapping value of the ratio of the extreme values, the more stable the overall fluctuation of the kth monitoring data in the current time period is.
By adopting the method, the fluctuation evaluation value of each monitoring data in the current time period can be obtained. Analogy to the above method, for any one of the monitored data in the period of the current time: performing curve fitting on all the monitoring data in the period of the current moment to obtain a fitting curve corresponding to the monitoring data in the current period, and then analogizing a calculation method of the fluctuation evaluation value of the kth monitoring data in the current time period to obtain the fluctuation evaluation value of the monitoring data in the period of the current moment; it should be noted that: the calculation method of the fluctuation evaluation value of the period of each kind of monitoring data at the current moment is similar to that of the kth kind of monitoring data in the current time period, but the data amount is reduced, and because the calculation method of the fluctuation evaluation value of the kth kind of monitoring data in the current time period has been specifically described, the detailed description of the calculation method of the fluctuation evaluation value of the period of each kind of monitoring data at the current moment is omitted here.
Thus far, the present embodiment acquires the fluctuation evaluation value of each kind of monitoring data in the current time period and the fluctuation evaluation value of the period in which each kind of monitoring data is located at the current time.
Step S3, obtaining a battery state representation value at the current moment according to the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period at the current moment and the element value in the noise matrix corresponding to the current moment; and determining a target noise matrix based on the battery state characterization value.
When the performance of the battery is degraded, the running stability is reduced, and the fluctuation condition of various monitoring data is larger than the value fluctuation difference in the current time period, so that the battery state evaluation at the current moment can be carried out through the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period at the current moment and the element value in the noise matrix corresponding to the current moment, and the state transition node generated by the battery operation can be conveniently determined. The battery state characterization value at the current moment is obtained according to the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period where the current moment is located and the element value in the noise matrix corresponding to the current moment.
Specifically, the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period at the current time is respectively taken as the evaluation value difference of each monitoring data; each of the monitoring data corresponds to one evaluation value difference. Respectively calculating the average value and standard deviation of all elements in the noise matrix corresponding to the current moment; and obtaining a battery state representation value at the current moment based on the evaluation value difference of each monitoring data and the average value and standard deviation of all elements in the noise matrix corresponding to the current moment. The specific calculation formula of the battery state representation value at the current moment is as follows:
;
Wherein M 0 represents a battery state characterization value at the current time, K represents the number of kinds of monitoring data, A k represents a fluctuation evaluation value of kth monitoring data in the current time period, Representing the fluctuation evaluation value of the kth monitoring data in the current time period, z i represents the ith element in the noise matrix corresponding to the current time, n represents the number of elements in the noise matrix corresponding to the current time,/>The average value of all elements in the noise matrix corresponding to the current moment is represented, sigma represents the standard deviation of all elements in the noise matrix corresponding to the current moment, and 'I' represents taking absolute value sign, simoid () is a normalization function.
The difference of evaluation values of the kth monitoring data is represented and used for representing the difference between the fluctuation evaluation value of the kth monitoring data in the current time period and the fluctuation evaluation value of the period in which the current time is located, and the larger the difference is, the larger the deviation difference is formed between the monitoring data in the period in which the current time is located and the battery operation initial stage, so that the degree of attenuation of the battery state is more obvious, namely the larger the battery state representation value of the current time is; The method can reflect the aggregation condition generated by each element in the noise matrix compared with the element mean value, and because each element in the noise matrix represents the degree of noise interference of various monitoring data, the larger the value is, the worse the overall noise influence condition in the monitoring value is, the more serious the working condition performance degradation of the battery is represented, and the noise matrix is required to be updated at the moment so as to represent the actual noise interference condition after the working condition degradation of the battery, namely the larger the battery state representation value at the current moment is.
By adopting the method, the battery state representation value at the current moment is obtained, and if the battery state representation value is smaller than the preset representation threshold, the noise matrix corresponding to the current moment is used as the target noise matrix, namely the noise matrix in the volume Kalman filtering algorithm is not updated; if the battery state representation value is larger than or equal to a preset representation threshold value, the feature vector of each moment in the period of the current moment is input into a volume Kalman filtering algorithm to obtain a new noise matrix, and the noise matrix obtained at the moment is recorded as a target noise matrix, namely the noise matrix in the volume Kalman filtering algorithm is updated. In this embodiment, the preset characterization threshold is 0.79, and in a specific application, the practitioner can set according to the specific situation.
Step S4, all prediction data of the next moment are obtained based on all monitoring data of the current moment, the target noise matrix and a volume Kalman filtering algorithm; and judging the running state of the small-sized air-cooled hydrogen fuel cell based on the prediction data.
In this embodiment, the target noise matrix of the volume kalman filter algorithm is determined in step S3, and then the present embodiment predicts the monitoring data of the small-sized air-cooled hydrogen fuel cell at the next moment based on the volume kalman filter algorithm.
Specifically, the eigenvector and the target noise matrix at the current moment are returned to a volume Kalman filtering algorithm, and all prediction data at the next moment are obtained. It should be noted that: each type of monitoring data has its corresponding prediction data. Judging whether the predicted data is in a standard range, if so, judging that the running state of the small-sized air-cooled hydrogen fuel cell is normal; if not, judging that the running state of the small-sized air-cooled hydrogen fuel cell is abnormal, and when the running state of the small-sized air-cooled hydrogen fuel cell is abnormal, adopting corresponding treatment measures according to specific conditions to ensure safety and recover normal running as soon as possible, wherein the following common treatment methods are as follows: firstly, the central computer immediately cuts off the power supply, stops the operation of the fuel cell, and avoids further damage to equipment; the hydrogen supply module immediately interrupts hydrogen supply, closes the air supply valve, and disconnects the system from the power supply, and meanwhile, the heat dissipation module dissipates heat with maximum power to avoid overheating of the fuel cell or abnormality of the heat dissipation module, and the heat dissipation module dissipates heat with maximum power to ensure that the temperature of the fuel cell is reduced in time. In a specific application, a standard range implementer sets a standard range corresponding to different kinds of monitoring data according to specific situations.
The method provided by the embodiment is adopted to monitor the running state of the small-sized air-cooled hydrogen fuel cell.
According to the embodiment, firstly, monitoring data of a small-sized air-cooled hydrogen fuel cell in a current time period are input into a volume Kalman filtering algorithm to obtain a corresponding noise matrix, elements in the noise matrix can reflect the interference degree of noise on various monitoring data, the embodiment combines the difference between the fluctuation condition of each monitoring data in the current time period and the fluctuation condition of each monitoring data in a period of the current time period and element values in the noise matrix corresponding to the current time, a battery state representation value of the current time is determined, the noise matrix in the volume Kalman filtering algorithm is updated based on the battery state representation value of the current time to obtain a target noise matrix, further, the running state of the small-sized air-cooled hydrogen fuel cell is predicted based on a prediction result, the influence of the fluctuation condition of different types of monitoring data and the influence of the different changes of the different types of monitoring data in the prediction process of the volume Kalman filtering algorithm on the noise matrix is considered, the battery state representation value of the different types of monitoring data is respectively determined, compared with the traditional battery state of the volume Kalman filtering algorithm is accurately identified, and the running state of the battery is more accurately identified, and the accuracy of the battery is more accurately identified by the battery state is better than the traditional state of the battery state prediction algorithm.
A small-sized air-cooled hydrogen fuel cell operation monitoring system embodiment:
the small-sized air-cooled hydrogen fuel cell operation monitoring system comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the small-sized air-cooled hydrogen fuel cell operation monitoring method.
Since a small-sized air-cooled hydrogen fuel cell operation monitoring method has been described in an embodiment of a small-sized air-cooled hydrogen fuel cell operation monitoring method, the embodiment will not be repeated.
It should be noted that: the foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (6)
1. A method for monitoring the operation of a small-sized air-cooled hydrogen fuel cell, comprising the steps of:
Different kinds of monitoring data of each moment in each period of the small-sized air-cooled hydrogen fuel cell in the current time period are obtained;
Acquiring a noise matrix corresponding to the current moment based on all monitoring data of each moment and a volume Kalman filtering algorithm; obtaining a fluctuation evaluation value of each monitoring data in the current time period according to the fluctuation condition of each monitoring data in the current time period; obtaining a fluctuation evaluation value of each monitoring data in the period of the current moment according to the fluctuation condition of each monitoring data in the period of the current moment;
Obtaining a battery state representation value at the current moment according to the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period at the current moment and the element value in the noise matrix corresponding to the current moment; determining a target noise matrix based on the battery state characterization value;
Acquiring all prediction data of the next moment based on all monitoring data of the current moment, the target noise matrix and a volume Kalman filtering algorithm; judging the running state of the small-sized air-cooled hydrogen fuel cell based on the prediction data;
According to the fluctuation condition of each monitoring data in the current time period, obtaining a fluctuation evaluation value of each monitoring data in the current time period, wherein the method comprises the following steps:
For the kth monitoring data:
Performing curve fitting on all k-th monitoring data in the current time period to obtain a fitting curve corresponding to the k-th monitoring data in the current time period;
Respectively obtaining the time intervals between every two adjacent extreme points of the kth monitoring data on the fitting curve corresponding to the current time period, and recording the average value of the time intervals between all the adjacent extreme points of the kth monitoring data on the fitting curve corresponding to the current time period as the average value of the time intervals corresponding to the kth monitoring data;
Respectively acquiring the ordinate of the minimum value point adjacent to each maximum value point in the time interval closest to the k-th monitoring data on a fitting curve corresponding to the current time period, and taking the ordinate as a reference value corresponding to each maximum value point;
obtaining a fluctuation evaluation value of the kth monitoring data in the current time period according to the ordinate of the maximum points of the kth monitoring data on the fitting curve corresponding to the current time period, the reference value corresponding to each maximum point, the time sequence interval average value, the number of the maximum points and the number of the minimum points of the kth monitoring data on the fitting curve corresponding to the current time period;
calculating a fluctuation evaluation value of kth monitoring data in the current time period by adopting the following formula:
;
Wherein A k represents the fluctuation evaluation value of the kth monitoring data in the current time period, R k represents the number of maximum points of the kth monitoring data on the fitting curve corresponding to the current time period, Ordinate representing the (r) th maximum point of the fitted curve corresponding to the current time period of the kth monitoring data,/>Mean value of reference values corresponding to all maximum value points on a fitting curve corresponding to the current time period of kth monitoring data is expressed, namely/>Representing a time sequence interval mean value corresponding to kth monitoring data, N k represents the number of minimum value points of the kth monitoring data on a fitting curve corresponding to the current time period, sinc () represents a sine function, and I represents taking an absolute value symbol;
obtaining a battery state representation value at the current moment according to the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period at the current moment and the element value in the noise matrix corresponding to the current moment, wherein the battery state representation value comprises the following components:
respectively taking the difference between the fluctuation evaluation value of each monitoring data in the current time period and the fluctuation evaluation value of the period of the current moment as the evaluation value difference of each monitoring data;
respectively calculating the average value and standard deviation of all elements in the noise matrix corresponding to the current moment;
obtaining a battery state representation value at the current moment based on the evaluation value difference of each monitoring data and the average value and standard deviation of all elements in the noise matrix corresponding to the current moment;
Calculating a battery state representation value at the current moment by adopting the following formula:
;
Wherein M 0 represents a battery state characterization value at the current time, K represents the number of kinds of monitoring data, A k represents a fluctuation evaluation value of kth monitoring data in the current time period, The fluctuation evaluation value of the period of the kth monitoring data at the current moment is represented, z i represents the ith element in the noise matrix corresponding to the current moment, n represents the number of elements in the noise matrix corresponding to the current moment, and/>The average value of all elements in the noise matrix corresponding to the current moment is represented, sigma represents the standard deviation of all elements in the noise matrix corresponding to the current moment, and 'I' represents taking absolute value sign, simoid () is a normalization function.
2. The method for monitoring the operation of a small-sized air-cooled hydrogen fuel cell according to claim 1, wherein the obtaining the noise matrix corresponding to the current time based on all the monitored data and the volume kalman filter algorithm at each time comprises:
For any time instant: all the monitoring data at the moment form a characteristic vector at the moment;
And taking the characteristic vector of each moment as the input of a volume Kalman filtering algorithm to obtain a noise matrix corresponding to the current moment.
3. The method for monitoring operation of a small-sized air-cooled hydrogen fuel cell according to claim 2, wherein the determining a target noise matrix based on the battery state characterization value comprises:
If the battery state representation value is smaller than a preset representation threshold, taking a noise matrix corresponding to the current moment as a target noise matrix;
And if the battery state representation value is larger than or equal to a preset representation threshold value, inputting the feature vector of each moment in the period of the current moment into a volume Kalman filtering algorithm to obtain a target noise matrix.
4. The method for monitoring operation of a small-sized air-cooled hydrogen fuel cell according to claim 2, wherein obtaining all predicted data at a next time based on all monitored data at a current time, the target noise matrix and a volume kalman filter algorithm comprises:
And returning the characteristic vector at the current moment and the target noise matrix to a volume Kalman filtering algorithm to obtain all prediction data at the next moment.
5. The method for monitoring operation of a small-sized air-cooled hydrogen fuel cell according to claim 1, wherein the determining the operation state of the small-sized air-cooled hydrogen fuel cell based on the prediction data comprises:
Judging whether the predicted data is in a standard range, if so, judging that the running state of the small-sized air-cooled hydrogen fuel cell is normal; if not, the operation state of the small-sized air-cooled hydrogen fuel cell is judged to be abnormal.
6. A small-sized air-cooled hydrogen fuel cell operation monitoring system comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement a small-sized air-cooled hydrogen fuel cell operation monitoring method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410369783.4A CN117976948B (en) | 2024-03-29 | 2024-03-29 | Small-sized air-cooled hydrogen fuel cell operation monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410369783.4A CN117976948B (en) | 2024-03-29 | 2024-03-29 | Small-sized air-cooled hydrogen fuel cell operation monitoring method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117976948A CN117976948A (en) | 2024-05-03 |
| CN117976948B true CN117976948B (en) | 2024-06-04 |
Family
ID=90846330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410369783.4A Active CN117976948B (en) | 2024-03-29 | 2024-03-29 | Small-sized air-cooled hydrogen fuel cell operation monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117976948B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108594135A (en) * | 2018-06-28 | 2018-09-28 | 南京理工大学 | A kind of SOC estimation method for the control of lithium battery balance charge/discharge |
| CN110596593A (en) * | 2019-08-26 | 2019-12-20 | 浙江大学 | Lithium ion battery SOC estimation method based on intelligent adaptive extended Kalman filtering |
| CN115932591A (en) * | 2022-08-30 | 2023-04-07 | 上海玫克生储能科技有限公司 | Lithium battery SOC estimation method, system, medium and electronic equipment based on PID-EKF |
| CN117031315A (en) * | 2023-08-31 | 2023-11-10 | 合肥国轩高科动力能源有限公司 | Method and device for determining remaining charge state of lithium battery and electronic equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102160274B1 (en) * | 2017-09-07 | 2020-09-25 | 주식회사 엘지화학 | Apparatus and method for estimating state of charge for battery and method thereof |
-
2024
- 2024-03-29 CN CN202410369783.4A patent/CN117976948B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108594135A (en) * | 2018-06-28 | 2018-09-28 | 南京理工大学 | A kind of SOC estimation method for the control of lithium battery balance charge/discharge |
| CN110596593A (en) * | 2019-08-26 | 2019-12-20 | 浙江大学 | Lithium ion battery SOC estimation method based on intelligent adaptive extended Kalman filtering |
| CN115932591A (en) * | 2022-08-30 | 2023-04-07 | 上海玫克生储能科技有限公司 | Lithium battery SOC estimation method, system, medium and electronic equipment based on PID-EKF |
| CN117031315A (en) * | 2023-08-31 | 2023-11-10 | 合肥国轩高科动力能源有限公司 | Method and device for determining remaining charge state of lithium battery and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117976948A (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110190306B (en) | Online fault diagnosis method for fuel cell system | |
| CN110646194B (en) | Converter valve cooling capacity multidimensional analysis early warning method and system | |
| CN117354171B (en) | Platform health condition early warning method and system based on Internet of things platform | |
| JP2002330558A (en) | Monitoring method for electric power transmission and distribution system, and electric power transmission and distribution system | |
| JP2011090382A (en) | Monitoring system | |
| CN116976707B (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
| CN116683061B (en) | Power battery thermal runaway prediction and suppression integrated system, method and storage medium | |
| CN118199130B (en) | Super capacitor energy storage capacity distribution method and system considering history error influence | |
| CN117459073B (en) | Intelligent management method for heat pump system operation data | |
| CN117075483B (en) | State monitoring method and device of liquid cooling energy storage system and storage medium | |
| CN117289168B (en) | Product quality monitoring system based on sensor data and intelligent algorithm | |
| CN111275295A (en) | Distributed photovoltaic fault diagnosis method based on inverse distance weight interpolation | |
| CN115127194B (en) | Method, equipment and medium for detecting faults of central air conditioner water chilling unit | |
| JP2010243092A (en) | Method and system of detecting deterioration of refrigerating machine | |
| CN118203260A (en) | Intelligent analysis-based dust collector state evaluation method and system | |
| CN117976948B (en) | Small-sized air-cooled hydrogen fuel cell operation monitoring method and system | |
| CN117117258B (en) | Fault monitoring method and device for hydrogen fuel cell system | |
| CN118244812A (en) | Control method of constant-temperature-forming and volume-dividing equipment | |
| CN116400239B (en) | Intelligent energy storage monitoring method for iron-chromium flow battery | |
| CN113240151A (en) | Method and device for predicting performance parameters of condenser of direct air cooling unit | |
| CN115909697A (en) | Alarm state prediction method and system based on amplitude change trend probability inference | |
| WO2020123420A1 (en) | Methods and systems for automated condition-based maintenance of mechanical systems | |
| KR20070067804A (en) | A monitoring device for intercooler of a compressor and a control method thereof | |
| CN112610330B (en) | Monitoring and analyzing system and method for running state of internal combustion engine | |
| CN118224792B (en) | Heating refrigeration cycle system fault early warning method and system |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240703 Address after: No. 22 Xipu Street, Muzidian Town, Macheng City, Huanggang City, Hubei Province 438000 Patentee after: Bi Hongtao Country or region after: China Address before: 215600 No.14, Fenghuang Avenue, Fenghuang Town, Zhangjiagang City, Suzhou City, Jiangsu Province Patentee before: Suzhou xuantu Information Technology Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right |