CN113581015A - Safety early warning method and device for fuel cell system - Google Patents
Safety early warning method and device for fuel cell system Download PDFInfo
- Publication number
- CN113581015A CN113581015A CN202110636368.7A CN202110636368A CN113581015A CN 113581015 A CN113581015 A CN 113581015A CN 202110636368 A CN202110636368 A CN 202110636368A CN 113581015 A CN113581015 A CN 113581015A
- Authority
- CN
- China
- Prior art keywords
- data
- risk
- vehicle
- charging
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/30—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling fuel cells
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q3/00—Arrangement of lighting devices for vehicle interiors; Lighting devices specially adapted for vehicle interiors
- B60Q3/60—Arrangement of lighting devices for vehicle interiors; Lighting devices specially adapted for vehicle interiors characterised by optical aspects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q3/00—Arrangement of lighting devices for vehicle interiors; Lighting devices specially adapted for vehicle interiors
- B60Q3/70—Arrangement of lighting devices for vehicle interiors; Lighting devices specially adapted for vehicle interiors characterised by the purpose
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
- B60Q3/00—Arrangement of lighting devices for vehicle interiors; Lighting devices specially adapted for vehicle interiors
- B60Q3/80—Circuits; Control arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/40—Application of hydrogen technology to transportation, e.g. using fuel cells
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Fuel Cell (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention discloses a safety early warning method and a safety early warning device for a fuel cell system, wherein the method comprises the following steps: acquiring vehicle data of a vehicle, wherein the vehicle data comprises charging data and/or operating data; carrying out normalized discrete wavelet decomposition processing on the vehicle data to obtain abnormal charging data and/or abnormal operation data; judging whether the abnormal charging data meet risk conditions and/or judging whether the abnormal operating data meet early warning conditions; and when the risk condition is met, judging that the vehicle has risk, controlling the vehicle to stop charging and simultaneously carrying out charging risk prompt, and/or when the early warning condition is met, generating risk prompt information and/or safety information and sending the risk prompt information and/or safety information value to a preset terminal. The method realizes the on-line identification and accurate positioning of early risk signals and realizes the multi-stage risk early warning for the real vehicle fuel cell system.
Description
Technical Field
The invention relates to the technical field of fuel cells, in particular to a safety early warning method and device of a fuel cell system.
Background
In order to prevent serious faults and optimize the maintenance period of the battery, accurate advance prediction and early warning of the possible safety risks of the battery are very important for ensuring the driving safety of vehicles and the personal safety of drivers and passengers.
The following methods are mainly used in the related art: (1) estimating SOH (State Of Health, battery Health) Of the battery by adopting an SVM (Support Vector Machine) method based on laboratory data and battery online operation data respectively, obtaining the variation trend Of parameters such as battery internal resistance and the like by a knowledge-based method, predicting the possible safety risk Of the battery by an experience-based method and giving the real-time Health State Of the battery; (2) the safety risk early warning research of the machine learning type fuel cell system is developed. The sample entropy of the short voltage sequence is used as an effective characteristic of battery capacity loss, an advanced sparse Bayesian prediction model is adopted to obtain a basic corresponding relation between the capacity loss and the sample entropy, and the battery safety risk can be predicted and early warned by combining a guided sampling concept and the SBPM; (3) common fault risks such as fuel cell SOC (state of charge) jump, monomer overvoltage, monomer under-voltage, monomer over-temperature, pressure difference overlarge and temperature difference overlarge are analyzed in detail from two aspects of short-term safety early warning and long-term health early warning, a fault tree of monomer overvoltage, monomer over-temperature and SOC jump is given, and the root cause and early warning method of safety risk generation are analyzed.
However, the operation of the real vehicle is affected by various complex stresses such as environmental stress, aging stress, driving behavior, dynamic load and the like, so that the extraction difficulty of the early risk signal is high, the method in the related technology is difficult to realize the online identification and accurate positioning of the early risk signal, and a multistage risk early warning strategy facing a real vehicle fuel cell system is yet to be perfected.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, an object of the present invention is to provide a safety warning method for a fuel cell system, which realizes online identification and accurate positioning of an early risk signal, and realizes multi-stage risk warning for a fuel cell system of an actual vehicle.
Another object of the present invention is to provide a safety precaution device for a fuel cell system.
In order to achieve the above object, an embodiment of the invention provides a safety warning method for a fuel cell system, which includes the following steps: acquiring vehicle data of a vehicle, wherein the vehicle data comprises charging data and/or operating data; carrying out normalized discrete wavelet decomposition processing on the vehicle data to obtain abnormal charging data and/or abnormal operation data; judging whether the charging abnormal data meet risk conditions and/or judging whether the operation abnormal data meet early warning conditions; and when the risk condition is met, judging that the vehicle has a risk, controlling the vehicle to stop charging and simultaneously carrying out charging risk prompt, and/or when the early warning condition is met, generating risk prompt information and/or safety information, and sending the risk prompt information and/or safety information value preset terminal.
According to the safety early warning method of the fuel cell system, disclosed by the embodiment of the invention, the early risk signals are subjected to multi-scale screening and amplification extraction based on an improved multi-scale entropy method, and the early risk signals are accurately identified and positioned by a normalized discrete wavelet decomposition method, so that the online identification and accurate positioning of the early risk signals are realized, and the multi-level risk early warning for the real vehicle fuel cell system is realized.
In addition, the safety precaution method of the fuel cell system according to the above embodiment of the present invention may further have the following additional technical features:
further, in an embodiment of the present invention, the performing a normalized discrete wavelet decomposition process on the vehicle data to obtain abnormal charging data and/or abnormal operating data includes: obtaining a high-frequency signal after the vehicle data are decomposed through a high-pass filter; abrupt change data having temporal characteristics of the early risk signal is identified from the high frequency signal.
Further, in an embodiment of the present invention, the performing a normalized discrete wavelet decomposition process on the vehicle data to obtain abnormal charging data and/or abnormal operating data further includes: and carrying out secondary inspection on the vehicle data by utilizing a multi-scale entropy method, searching data with gradual change characteristics, and analyzing the disorder degree of the data with gradual change characteristics.
Further, in an embodiment of the present invention, the method further includes: and generating a corresponding reminding mode according to the charging abnormal data and/or the running abnormal data and the difference value between the corresponding risk condition and the early warning condition, wherein the reminding mode comprises the intensity of a reminding action and the color identification of a reminding signal.
Further, in one embodiment of the present invention, the risk condition includes a first safety threshold, and the pre-warning condition includes a second safety threshold and a third safety threshold, wherein the third safety threshold is greater than the second safety threshold.
In order to achieve the above object, according to another embodiment of the present invention, a safety precaution device for a fuel cell system is provided, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring vehicle data of a vehicle, and the vehicle data comprises charging data and/or operation data; the processing module is used for carrying out normalized discrete wavelet decomposition processing on the vehicle data to obtain abnormal charging data and/or abnormal operation data; the judging module is used for judging whether the charging abnormal data meet risk conditions and/or judging whether the operation abnormal data meet early warning conditions; and the control module is used for judging that the vehicle has a risk when the risk condition is met, controlling the vehicle to stop charging and simultaneously carrying out charging risk prompt, and/or generating risk prompt information and/or safety information and sending the risk prompt information and/or safety information value preset terminal when the early warning condition is met.
The safety early warning device of the fuel cell system provided by the embodiment of the invention is used for carrying out multi-scale screening and amplification extraction on the early-stage risk signals based on the improved multi-scale entropy method, and accurately identifying and positioning the early-stage risk signals by the normalized discrete wavelet decomposition method, so that the on-line identification and accurate positioning of the early-stage risk signals are realized, and the multi-stage risk early warning for the real-vehicle fuel cell system is realized.
In addition, the safety warning apparatus of the fuel cell system according to the above embodiment of the present invention may further have the following additional technical features:
further, in an embodiment of the present invention, the processing module is specifically configured to: obtaining a high-frequency signal after the vehicle data are decomposed through a high-pass filter; abrupt change data having temporal characteristics of the early risk signal is identified from the high frequency signal.
Further, in an embodiment of the present invention, the processing module is further configured to: and carrying out secondary inspection on the vehicle data by utilizing a multi-scale entropy method, searching data with gradual change characteristics, and analyzing the disorder degree of the data with gradual change characteristics.
Further, in an embodiment of the present invention, the method further includes: and the generating module is used for generating a corresponding reminding mode according to the charging abnormal data and/or the running abnormal data and a difference value between a corresponding risk condition and an early warning condition, wherein the reminding mode comprises the intensity of a reminding action and the color identification of a reminding signal.
Further, in one embodiment of the present invention, the risk condition includes a first safety threshold, and the pre-warning condition includes a second safety threshold and a third safety threshold, wherein the third safety threshold is greater than the second safety threshold.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart of a safety precaution method of a fuel cell system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a discrete wavelet decomposition method according to the present invention;
fig. 3 is a block schematic diagram of a safety precaution system of a fuel cell system according to the present invention;
fig. 4 is a flowchart of a safety warning method of a fuel cell system according to an embodiment of the present invention;
fig. 5 is a block diagram schematically illustrating a safety warning apparatus of a fuel cell system according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The following describes a safety warning method and apparatus for a fuel cell system according to an embodiment of the present invention with reference to the accompanying drawings, and first, a safety warning method for a fuel cell system according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Fig. 1 is a flowchart of a safety warning method of a fuel cell system according to an embodiment of the present invention.
As shown in fig. 1, the safety warning method of the fuel cell system includes:
in step S101, vehicle data of a vehicle is acquired, wherein the vehicle data includes charging data and/or operating data.
In step S102, the vehicle data is subjected to normalized discrete wavelet decomposition processing to obtain abnormal charging data and/or abnormal operating data.
It should be understood that discrete wavelet decomposition may use a wavelet function (wavelet function) and a scale function (scale function) to analyze the high frequency signal and the low frequency signal, respectively, i.e., a high pass filter and a low pass filter. The decomposition process is as follows:
1) the signal is passed through a half-band low-pass filter with impulse response, which can eliminate the low-frequency part of the signal and reduce the resolution of the signal by half.
2) And performing down-sampling according to the Nyquist theorem, removing sample points at intervals, and doubling the scale by leaving half the sample points for the signal. (the filtering operation does not affect the scale of the signal) this half is high-pass filtered.
3) And further decomposing, namely dividing the result of the high-pass filter into two parts again, and performing high-pass filtering and low-pass filtering.
As a possible implementation manner, in an embodiment of the present invention, performing a normalized discrete wavelet decomposition process on the vehicle data to obtain charging abnormality data and/or operation abnormality data includes: obtaining a high-frequency signal after vehicle data decomposition through a high-pass filter; abrupt change data having temporal characteristics of the early risk signal is identified from the high frequency signal.
Specifically, the embodiment of the application can collect the collected real vehicle operation data and perform safety early warning and fault diagnosis through discrete wavelet decomposition.
Specifically, in the embodiment of the present application, discrete wavelet decomposition may be performed on a signal first, and this process mainly searches for data with a sudden change, and obtains a decomposed high-frequency signal through a high-pass filter, so as to obtain a time-domain characteristic of an early-stage risk signal.
As another possible implementation manner, in an embodiment of the present invention, the performing a normalized discrete wavelet decomposition process on the vehicle data to obtain charging abnormality data and/or operation abnormality data further includes: and carrying out secondary inspection on the vehicle data by using a multi-scale entropy method, searching data with gradual change characteristics, and analyzing the disorder degree of the data with gradual change characteristics.
Specifically, if the mutation data cannot be found, the embodiment of the application can perform secondary inspection by using a multi-scale entropy method, and the process mainly searches for data with gradual change and analyzes the data disorder degree.
For ease of understanding, the discrete wavelet decomposition (NDWD) algorithm is described in detail below with reference to fig. 2.
Specifically, the core of the discrete wavelet transform: the signals of different frequencies are analyzed with filters of different frequencies, mainly high pass filters and low pass filters. Resolution of the signal: and measuring the abundance of information carried by the signal, wherein the higher the sampling rate, the higher the resolution, and vice versa. DWT uses wavelet functions (wavelet functions) and scale functions (scale functions) to analyze high and low frequency signals, i.e., high and low pass filters, respectively.
DWT decomposition process:
(1) the signal x n is passed through a half-band low-pass filter with an impulse response h n, which rejects the part of the signal with a frequency lower than p/2 (the highest frequency of the signal is p), and the signal resolution is reduced by half.
() And performing down-sampling according to the Nyquist theorem, removing sample points at intervals, and doubling the scale by leaving half the sample points for the signal. (the filtering operation does not affect the scale of the signal) this half is high-pass filtered. 3. This is the first stage of decomposition and if further decomposition is desired, the result of the high pass filter is again split in two, with high pass filtering and low pass filtering.
It can be seen that the number of levels of decomposition is no more than 2 to the nth power of the signal length. Difference from fourier transform: time location information of the frequency is preserved.
Further, the data processing is carried out by utilizing a discrete wavelet decomposition algorithm, and the method comprises the following steps:
(1) determining input network parameters: determining the number of input network types and the number of output network types according to the parameter data of the fuel cell system;
(2) discrete wavelet transform: performing discrete wavelet transform on the parameter data, selecting basic wavelet types according to the parameter data, and obtaining a de-noised training sample through the discrete wavelet transform;
(3) training an extreme learning machine neural network: determining a training sample and a testing sample, calculating a hidden layer output matrix and an output weight by randomly selecting an input weight and a hidden layer deviation by using an extreme learning machine, and solving the inverse process of the output weight by an evolutionary algorithm to predict and output a prediction result.
The method comprises the following steps of adding an evolutionary algorithm into an extreme learning machine, wherein the evolutionary algorithm comprises the following steps: firstly, randomly selecting input weight and hidden layer deviation as an initial generation population; then calculating the fitness of each individual in the population; evaluating the fitness, outputting the corresponding individual with the fitness meeting the stopping standard as a prediction result, and if the fitness does not meet the stopping standard, evaluating the fitness of the next individual; and finally outputting all the prediction results after the optimization is completed.
And in the process of evaluating the fitness of the next individual if the fitness of the next individual is not met, carrying out mutation, intersection and selection on the fitness of the individual, and reserving the high-quality individual in the fitness to the next generation. The evolutionary algorithm carries out variation, crossing and selection processes on the initial generation population by optimizing two parameters, namely randomly selected input weight and hidden layer deviation, and individuals with better fitness are reserved to the next generation. Meanwhile, through discrete wavelet transformation, data characteristic information can be better acquired, and an extreme learning machine neural network can be better established, so that the prediction precision and the prediction time are further improved.
In step S103, it is determined whether the abnormal charging data meets a risk condition and/or whether the abnormal operating data meets an early warning condition.
Further, in one embodiment of the invention, the risk condition comprises a first safety threshold and the pre-alarm condition comprises a second safety threshold and a third safety threshold, wherein the third safety threshold is greater than the second safety threshold.
Further, in an embodiment of the present invention, the early warning condition is to determine that the data turbulence thereof reaches a multi-level threshold.
In step S104, when the risk condition is satisfied, it is determined that the vehicle has a risk, the vehicle is controlled to stop charging while charging risk prompt is performed, and/or when the early warning condition is satisfied, risk prompt information and/or safety information is generated and sent to a risk prompt information and/or safety information value preset terminal.
Specifically, for the charging data, if the absolute value of the charging data of any single battery is greater than or equal to 0.015, the fuel cell system is judged to have abnormality in the charging and discharging process, and the charging is stopped and a contact person checks the battery; otherwise, the fuel cell system is in a safe state and the vehicle can run normally.
If the operation data of any single battery is greater than or equal to 0.8, performing primary alarm, immediately stopping and getting off the vehicle when the fuel cell system has high risk of thermal runaway, and calling to wait for rescue; if the operation data of any single battery is more than or equal to 0.6 and less than 0.8, performing secondary alarm, and the fuel cell system has potential risk of thermal runaway, driving to a safe place to stop, and calling a contact person to check the battery; if the operation data of all the single batteries is less than 0.6, the fuel cell system is in a safe state, and the vehicle can run normally.
Further, in an embodiment of the present invention, the method further includes: and generating a corresponding reminding mode according to the charging abnormal data and/or the running abnormal data and the difference value between the corresponding risk condition and the early warning condition, wherein the reminding mode comprises the intensity of a reminding action and the color identification of a reminding signal.
For example, the reminding of different conditions can be realized by the color of an LED (light-emitting diode), the LED is normally green under normal conditions, the secondary early warning LED is yellow, and the primary early warning LED is red. Note that the abnormality risk coefficient a in the vehicle running stateD(i.e., operating anomaly data) can be obtained by the following equation:
driving state abnormality risk coefficient:
AD＝DWDd_nor-DWDd_ave；
wherein DWDd is discrete wavelet value of single voltage in driving state, DWDd_minIs the discrete wavelet minimum of the cell voltage; DWDd_maxIs the maximum discrete wavelet of the cell voltage; DWDd_norIs the discrete wavelet minimum of the cell voltage after normalization; DWDd_aveIs the discrete wavelet average of the cell voltage; a. theDIs an abnormal risk coefficient under the running state of the vehicle.
Abnormal risk coefficient A in vehicle charging stateCThe (i.e., charging abnormality data) can be obtained by the following formula:
AC＝DWDc-DWDc_ave；
wherein, DWDcDiscrete wavelet values, DWD, of cell voltagesc_aveIs the discrete wavelet average of the cell voltage.
In order to enable those skilled in the art to further understand the safety precaution method of the fuel cell system of the embodiment of the present application, the following detailed description is made with reference to specific embodiments.
As shown in fig. 3, the warning system related to the safety warning method of the fuel cell system according to the embodiment of the present application mainly includes: the system comprises a fuel cell system, a battery management system and a multi-stage early warning system. Wherein, the fuel cell system includes: fuel cells 1 … … n; the battery management system includes: collection module, balanced module and host system, multistage early warning system includes: LED indicator lights (green, yellow, red) and buzzers; the collection module includes: a voltage sensor, a current sensor, and a temperature sensor.
Further, as shown in fig. 4, fig. 4 is a flowchart of a safety precaution method of a fuel cell system according to an embodiment of the present application.
As can be seen from fig. 4, in the embodiment of the present application, vehicle data can be obtained in real time, the vehicle data is divided into charging data and operating data (data generated during driving and standing is operating data, and data generated during charging is charging data), and the charging data and the operating data are respectively processed by a normalized discrete wavelet decomposition method to obtain abnormal charging data and abnormal operating data; comparing the abnormal charging data with a first preset threshold value, and judging whether the fuel cell system has risks; and comparing the abnormal operation data with a second preset threshold and a third preset threshold to generate corresponding risk prompt information or safety information. Wherein, any monomer: any one battery can meet the condition; all monomers: all batteries are subject to the conditions.
According to the safety early warning method of the fuel cell system provided by the embodiment of the invention, the early-stage risk signals are subjected to multi-scale screening and amplification extraction based on an improved multi-scale entropy method, and the early-stage risk signals are accurately identified and positioned by a normalized discrete wavelet decomposition method, so that the online identification and accurate positioning of the early-stage risk signals are realized, and the multi-stage risk early warning for the real vehicle fuel cell system is realized.
Next, a safety warning apparatus of a fuel cell system according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Fig. 5 is a block diagram schematically showing a safety warning apparatus of a fuel cell system according to an embodiment of the present invention.
As shown in fig. 5, the safety warning apparatus 10 of the fuel cell system includes: an acquisition module 100, a processing module 200, a judgment module 300 and a control module 400.
The acquiring module 100 is configured to acquire vehicle data of a vehicle, where the vehicle data includes charging data and/or operating data; the processing module 200 is configured to perform normalized discrete wavelet decomposition processing on the vehicle data to obtain abnormal charging data and/or abnormal operating data; the judging module 300 is configured to judge whether the charging abnormal data meets a risk condition and/or judge whether the operation abnormal data meets an early warning condition; the control module 400 is configured to determine that a risk exists in the vehicle when a risk condition is met, control the vehicle to stop charging and perform charging risk prompt at the same time, and/or generate risk prompt information and/or safety information and send the risk prompt information and/or safety information value to a preset terminal when an early warning condition is met.
Further, in an embodiment of the present invention, the processing module 200 is specifically configured to: obtaining a high-frequency signal after vehicle data decomposition through a high-pass filter; abrupt change data having temporal characteristics of the early risk signal is identified from the high frequency signal.
Further, in an embodiment of the present invention, the processing module 200 is further configured to: and carrying out secondary inspection on the vehicle data by using a multi-scale entropy method, searching data with gradual change characteristics, and analyzing the disorder degree of the data with gradual change characteristics.
Further, in an embodiment of the present invention, the method further includes: and the generating module is used for generating a corresponding reminding mode according to the charging abnormal data and/or the running abnormal data and the difference value between the corresponding risk condition and the early warning condition, wherein the reminding mode comprises the intensity of a reminding action and the color identification of a reminding signal.
Further, in one embodiment of the invention, the risk condition comprises a first safety threshold and the pre-alarm condition comprises a second safety threshold and a third safety threshold, wherein the third safety threshold is greater than the second safety threshold.
It should be noted that the above explanation of the embodiment of the safety warning method for a fuel cell system is also applicable to the safety warning device for a fuel cell system of this embodiment, and is not repeated here.
According to the safety early warning device of the fuel cell system, provided by the embodiment of the invention, the early-stage risk signals are subjected to multi-scale screening and amplification extraction based on an improved multi-scale entropy method, and the early-stage risk signals are accurately identified and positioned by a normalized discrete wavelet decomposition method, so that the online identification and accurate positioning of the early-stage risk signals are realized, and the multi-stage risk early warning for the real vehicle fuel cell system is realized.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A safety early warning method of a fuel cell system is characterized by comprising the following steps:
acquiring vehicle data of a vehicle, wherein the vehicle data comprises charging data and/or operating data;
carrying out normalized discrete wavelet decomposition processing on the vehicle data to obtain abnormal charging data and/or abnormal operation data;
judging whether the charging abnormal data meet risk conditions and/or judging whether the operation abnormal data meet early warning conditions; and
and when the risk condition is met, judging that the vehicle has a risk, controlling the vehicle to stop charging and simultaneously carrying out charging risk prompt, and/or when the early warning condition is met, generating risk prompt information and/or safety information, and sending the risk prompt information and/or safety information value preset terminal.
2. The method according to claim 1, wherein the subjecting the vehicle data to normalized discrete wavelet decomposition processing to obtain abnormal charging data and/or abnormal operating data comprises:
obtaining a high-frequency signal after the vehicle data are decomposed through a high-pass filter;
abrupt change data having temporal characteristics of the early risk signal is identified from the high frequency signal.
3. The method according to claim 2, wherein the performing a normalized discrete wavelet decomposition process on the vehicle data to obtain abnormal charging data and/or abnormal operating data further comprises:
and carrying out secondary inspection on the vehicle data by utilizing a multi-scale entropy method, searching data with gradual change characteristics, and analyzing the disorder degree of the data with gradual change characteristics.
4. The method of claim 1, further comprising:
and generating a corresponding reminding mode according to the charging abnormal data and/or the running abnormal data and the difference value between the corresponding risk condition and the early warning condition, wherein the reminding mode comprises the intensity of a reminding action and the color identification of a reminding signal.
5. The method of claim 4, wherein the risk condition comprises a first safety threshold and the pre-warning condition comprises a second safety threshold and a third safety threshold, wherein the third safety threshold is greater than the second safety threshold.
6. A safety warning device of a fuel cell system, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring vehicle data of a vehicle, and the vehicle data comprises charging data and/or operation data;
the processing module is used for carrying out normalized discrete wavelet decomposition processing on the vehicle data to obtain abnormal charging data and/or abnormal operation data;
the judging module is used for judging whether the charging abnormal data meet risk conditions and/or judging whether the operation abnormal data meet early warning conditions; and
and the control module is used for judging that the vehicle has a risk when the risk condition is met, controlling the vehicle to stop charging and simultaneously carrying out charging risk prompt, and/or generating risk prompt information and/or safety information and sending the risk prompt information and/or safety information value preset terminal when the early warning condition is met.
7. The apparatus of claim 6, wherein the processing module is specifically configured to:
obtaining a high-frequency signal after the vehicle data are decomposed through a high-pass filter;
abrupt change data having temporal characteristics of the early risk signal is identified from the high frequency signal.
8. The apparatus of claim 7, wherein the processing module is further configured to:
and carrying out secondary inspection on the vehicle data by utilizing a multi-scale entropy method, searching data with gradual change characteristics, and analyzing the disorder degree of the data with gradual change characteristics.
9. The apparatus of claim 6, further comprising:
and the generating module is used for generating a corresponding reminding mode according to the charging abnormal data and/or the running abnormal data and a difference value between a corresponding risk condition and an early warning condition, wherein the reminding mode comprises the intensity of a reminding action and the color identification of a reminding signal.
10. The apparatus of claim 9, wherein the risk condition comprises a first safety threshold, wherein the pre-alarm condition comprises a second safety threshold and a third safety threshold, wherein the third safety threshold is greater than the second safety threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636368.7A CN113581015B (en) | 2021-06-08 | 2021-06-08 | Safety early warning method and device for fuel cell system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110636368.7A CN113581015B (en) | 2021-06-08 | 2021-06-08 | Safety early warning method and device for fuel cell system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113581015A true CN113581015A (en) | 2021-11-02 |
| CN113581015B CN113581015B (en) | 2023-09-29 |
Family
ID=78243471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110636368.7A Active CN113581015B (en) | 2021-06-08 | 2021-06-08 | Safety early warning method and device for fuel cell system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113581015B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115219903A (en) * | 2022-03-11 | 2022-10-21 | 中国第一汽车股份有限公司 | Battery self-discharge rate abnormity judgment method and device based on Internet of vehicles data analysis |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101436672A (en) * | 2007-11-15 | 2009-05-20 | 北京科技大学 | Fuel battery generating system and method |
| CN103454590A (en) * | 2012-05-28 | 2013-12-18 | 索尼公司 | Method of estimating state of charge of secondary cell, state-of-charge estimation device, cell pack, electronic apparatus, and electric vehicle |
| CN105196877A (en) * | 2015-09-30 | 2015-12-30 | 上海交通大学 | Health state diagnosis early-warning circuit and method of electric automobile high-voltage system |
| CN205176232U (en) * | 2015-10-19 | 2016-04-20 | 中国东方电气集团有限公司 | Battery running state's monitoring devices and fuel cell |
| CN110224160A (en) * | 2019-06-12 | 2019-09-10 | 北京亿华通科技股份有限公司 | A kind of fuel cell system method for diagnosing faults |
| CN112285587A (en) * | 2020-11-11 | 2021-01-29 | 同济大学 | Online vehicle-mounted hydrogen fuel cell impedance spectrum measuring device and measuring method |
| CN112373352A (en) * | 2020-11-12 | 2021-02-19 | 吉林大学 | Fault diagnosis and fault tolerance control method for fuel cell system |
-
2021
- 2021-06-08 CN CN202110636368.7A patent/CN113581015B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101436672A (en) * | 2007-11-15 | 2009-05-20 | 北京科技大学 | Fuel battery generating system and method |
| CN103454590A (en) * | 2012-05-28 | 2013-12-18 | 索尼公司 | Method of estimating state of charge of secondary cell, state-of-charge estimation device, cell pack, electronic apparatus, and electric vehicle |
| CN105196877A (en) * | 2015-09-30 | 2015-12-30 | 上海交通大学 | Health state diagnosis early-warning circuit and method of electric automobile high-voltage system |
| CN205176232U (en) * | 2015-10-19 | 2016-04-20 | 中国东方电气集团有限公司 | Battery running state's monitoring devices and fuel cell |
| CN110224160A (en) * | 2019-06-12 | 2019-09-10 | 北京亿华通科技股份有限公司 | A kind of fuel cell system method for diagnosing faults |
| CN112285587A (en) * | 2020-11-11 | 2021-01-29 | 同济大学 | Online vehicle-mounted hydrogen fuel cell impedance spectrum measuring device and measuring method |
| CN112373352A (en) * | 2020-11-12 | 2021-02-19 | 吉林大学 | Fault diagnosis and fault tolerance control method for fuel cell system |
Non-Patent Citations (1)
| Title |
|---|
| 刘嘉蔚、李奇、陈维荣、余嘉熹、燕雨: "基于在线序列超限学习机和主成分分析的蒸汽冷却型燃料电池系统快速故障诊断方法", 《基于在线序列超限学习机和主成分分析的蒸汽冷却型燃料电池系统快速故障诊断方法》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115219903A (en) * | 2022-03-11 | 2022-10-21 | 中国第一汽车股份有限公司 | Battery self-discharge rate abnormity judgment method and device based on Internet of vehicles data analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113581015B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112092675B (en) | Battery thermal runaway early warning method, system and server | |
| Yao et al. | A novel intelligent method for fault diagnosis of electric vehicle battery system based on wavelet neural network | |
| CN112731159B (en) | Method for pre-judging and positioning battery faults of battery compartment of energy storage power station | |
| CN109186813B (en) | Temperature sensor self-checking device and method | |
| CN109116242B (en) | Data processing method and device for power battery | |
| CN103838229B (en) | Diagnosis method and device of electric car | |
| CN104021238A (en) | Lead-acid power battery system fault diagnosis method | |
| KR102215107B1 (en) | Vehicle state predicting system and method based on driving data | |
| CN112946485A (en) | Vehicle battery detection method, storage medium and device | |
| CN111157908A (en) | Battery health degree prediction method based on big data machine learning | |
| CN113581015B (en) | Safety early warning method and device for fuel cell system | |
| CN115877205A (en) | Intelligent fault diagnosis system and method for servo motor | |
| CN116643178A (en) | SOC estimation method and related device of battery management system | |
| CN117330987B (en) | Method, system, medium and apparatus for time-based battery state of health assessment | |
| Pau et al. | Microcontroller architectures for battery state of charge prediction with tiny neural networks | |
| CN116400244B (en) | Abnormality detection method and device for energy storage battery | |
| CN117630672A (en) | Method and device for predicting a device battery of a diagnostic device using a converter model | |
| CN113723496A (en) | Reactor iron core loosening fault diagnosis method, device and equipment | |
| US20230133120A1 (en) | Big-data-based battery diagnostic system and control method therefor | |
| AU2021104319A4 (en) | A system for traction inverter fault detection and a method thereof | |
| CN115169405A (en) | Hotel guest room equipment fault diagnosis method and system based on support vector machine | |
| CN114492636A (en) | Transformer winding state signal acquisition system | |
| CN112070535A (en) | Electric vehicle price prediction method and device | |
| CN118024886B (en) | On-line detection control method and system for lithium battery pack for vehicle | |
| CN114564110B (en) | Driving learning ability detection method and system based on brain electrical data |
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 |