A detection system and method for safety warning of fuel cell vehicles

Abstract

The present invention provides a detection system and method for safety warning of fuel cell vehicles, and the detection method for safety warning of fuel cell vehicles includes the following steps: obtaining the real-time hydrogen concentration of the fuel cell vehicle; detecting and obtaining the remaining amount of hydrogen in the hydrogen bottle of the fuel cell vehicle; detecting and obtaining the real-time output power of the fuel cell vehicle; detecting and obtaining the real-time pressure drop value of the hydrogen bottle of the fuel cell vehicle; obtaining the predicted pressure drop value of the hydrogen bottle of the fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power; calculating the predicted hydrogen concentration of the fuel cell vehicle according to the real-time hydrogen concentration, the real-time pressure drop value and the predicted pressure drop value; when the predicted hydrogen concentration is greater than or equal to the preset hydrogen concentration threshold, issuing a safety alarm. The present invention can improve the calculation accuracy of the predicted hydrogen concentration by taking into account the influence of the remaining amount of hydrogen and the real-time output power of the hydrogen fuel cell vehicle on the predicted hydrogen concentration.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cell vehicles, and in particular to a detection system and method for safety warning of fuel cell vehicles. Background Art

[0002] The hydrogen leakage detection of the fuel cell system directly determines whether there is a hydrogen leakage method by measuring the pressure drop of hydrogen pressure or the concentration of hydrogen leakage. However, the existing hydrogen leakage detection method can only unilaterally obtain the leakage situation through hydrogen concentration or pressure change, which has many restrictive factors, slow reaction speed, low monitoring efficiency, long measurement reaction time of hydrogen concentration sensor, and random fluctuation of hydrogen pressure in the actual operation of fuel cell, which is easy to misreport.

[0003] In order to solve the above problems, the Chinese invention patent with application number CN2021102606980 discloses a hydrogen leakage monitoring alarm method and system for fuel cell vehicles. The method includes: obtaining the current hydrogen concentration of the fuel cell vehicle; judging whether the current hydrogen concentration is 0, if not, obtaining the measured hydrogen concentration, the hydrogen pressure drop value, and the normal pressure interval generated when the current hydrogen concentration of the fuel cell vehicle is 0; judging whether the hydrogen pressure drop value exceeds the normal pressure interval, if so, determining the predicted hydrogen concentration based on the measured hydrogen concentration and the hydrogen pressure drop value; judging whether the predicted hydrogen concentration exceeds the hydrogen leakage alarm threshold, if so, determining hydrogen leakage and issuing an alarm. The invention can make the hydrogen concentration alarm limit reach in advance, thereby shortening the hydrogen leakage monitoring alarm time.

[0004] However, the hydrogen pressure drop value of a fuel cell vehicle is not only related to hydrogen leakage, but also to the remaining amount of hydrogen and the real-time output power of the hydrogen fuel cell vehicle. The above-mentioned hydrogen leakage monitoring and alarm method and system for fuel cell vehicles do not take into account the remaining amount of hydrogen and the real-time output power of the hydrogen fuel cell vehicle when calculating the predicted hydrogen concentration. The calculation result of the predicted hydrogen concentration is not accurate enough and needs to be improved. Summary of the invention

[0005] Based on this, in order to improve the accuracy of the calculation results of the predicted hydrogen concentration, the present invention provides a detection system and method for safety warning of fuel cell vehicles, and its specific technical solution is as follows:

[0006] A detection system for safety warning of fuel cell vehicles includes a concentration detection module, a remaining quantity acquisition module, a real-time power acquisition module, a first pressure difference acquisition module, a concentration prediction module and an early warning module.

[0007] The concentration detection module is used to obtain the real-time hydrogen concentration Con of the fuel cell vehicle. h2 The remaining amount acquisition module is used to detect and obtain the remaining amount of hydrogen in the hydrogen tank of the fuel cell vehicle.

[0008] The real-time power acquisition module is used to detect and acquire the real-time output power of the fuel cell vehicle; the first pressure difference acquisition module is used to detect and acquire the real-time pressure drop value Δp1 of the hydrogen tank of the fuel cell vehicle.

[0009] The second pressure difference acquisition module is used to obtain the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power;

[0010] The concentration prediction module is used to predict the concentration of hydrogen based on the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ.

[0011] The early warning module is used to issue a safety alarm when the predicted hydrogen concentration is greater than or equal to a preset hydrogen concentration threshold.

[0012] Among them, ε represents the hydrogen pressure difference concentration compensation coefficient, and λ represents the hydrogen bottle temperature compensation coefficient.

[0013] The fuel cell vehicle safety warning detection system obtains the real-time output power of the fuel cell vehicle and the remaining amount of hydrogen in the hydrogen bottle, obtains the predicted pressure drop value Δp2 of the fuel cell vehicle hydrogen bottle according to the remaining amount of hydrogen and the real-time output power, and on this basis, combines the real-time hydrogen concentration Con h2 , predicted pressure drop value Δp2 and real-time pressure drop value Δp1 are used to calculate the predicted hydrogen concentration of the fuel cell vehicle. The predicted hydrogen concentration can be calculated with improved accuracy by taking into account the influence of the remaining hydrogen amount and the real-time output power of the hydrogen fuel cell vehicle on the predicted hydrogen concentration. This solves the problem that the existing hydrogen leakage monitoring and alarm method and system for fuel cell vehicles do not take into account the remaining hydrogen amount and the real-time output power of the hydrogen fuel cell vehicle when calculating the predicted hydrogen concentration, resulting in inaccurate calculation results of the predicted hydrogen concentration.

[0014] Furthermore, the second pressure difference acquisition module includes a training data acquisition unit, a real-time data acquisition unit and a neural network unit.

[0015] The training data acquisition unit is used to collect the historical hydrogen remaining amounts of different fuel cell vehicles, the different historical output powers under different historical hydrogen remaining amounts, and the actual pressure drop values ​​of the hydrogen bottles of the fuel cell vehicles corresponding to the different historical output powers; the real-time data acquisition unit is used to collect the hydrogen remaining amounts and real-time output powers of the fuel cell vehicles.

[0016] The neural network unit is used to train through the collected historical hydrogen remaining amounts of different fuel cell vehicles, different historical output powers under different historical hydrogen remaining amounts, and actual pressure drop values ​​of the hydrogen bottles of fuel cell vehicles corresponding to different historical output powers. After training, the predicted pressure drop value Δp2 of the hydrogen bottle of the fuel cell vehicle is obtained according to the hydrogen remaining amount and real-time output power of the fuel cell vehicle.

[0017] Furthermore, the warning module is also used to calculate the warning time when the predicted hydrogen concentration is less than a preset hydrogen concentration threshold.

[0018] Furthermore, the fuel cell vehicle safety warning detection system also includes a temperature acquisition module.

[0019] The temperature acquisition module is used to detect and obtain the real-time temperature T of the hydrogen tank of the fuel cell vehicle.

[0020] The concentration prediction module is based on the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1, predicted pressure drop value Δp2 and real-time temperature T, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ.

[0021] A fuel cell vehicle safety warning detection method is applied to the fuel cell vehicle safety warning detection system, which comprises the following steps:

[0022] Get the real-time hydrogen concentration Con of fuel cell vehicles h2 ;

[0023] Detect and obtain the remaining amount of hydrogen in the hydrogen tank of a fuel cell vehicle;

[0024] Detect and obtain the real-time output power of fuel cell vehicles;

[0025] Detect and obtain the real-time pressure drop value Δp1 of the hydrogen tank of the fuel cell vehicle;

[0026] Obtain the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power;

[0027] According to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ;

[0028] When the predicted hydrogen concentration is greater than or equal to the preset hydrogen concentration threshold, a safety alarm is issued;

[0029] Among them, ε represents the hydrogen pressure difference concentration compensation coefficient, and λ represents the hydrogen bottle temperature compensation coefficient.

[0030] Furthermore, a specific method for obtaining a predicted pressure drop value Δp2 of a hydrogen tank of a fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power includes the following steps:

[0031] Collect the historical remaining hydrogen amounts of different fuel cell vehicles, the different historical output powers under different historical remaining hydrogen amounts, and the actual pressure drop values ​​of the hydrogen tanks of the fuel cell vehicles corresponding to the different historical output powers;

[0032] Collect the remaining hydrogen and real-time output power of fuel cell vehicles;

[0033] Construct neural network units;

[0034] The neural network unit is trained by collecting the historical remaining amounts of hydrogen of different fuel cell vehicles, the different historical output powers under different historical remaining amounts of hydrogen, and the actual pressure drop values ​​of the hydrogen bottles of the fuel cell vehicles corresponding to the different historical output powers;

[0035] Based on the trained neural network unit and according to the remaining hydrogen amount and real-time output power of the fuel cell vehicle, the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle is obtained.

[0036] Further, according to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 The specific method of +(Δp1-Δp2)*ε*λ includes the following steps:

[0037] Detect and obtain the real-time temperature T of the hydrogen tank of the fuel cell vehicle;

[0038] According to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1, predicted pressure drop value Δp2 and real-time temperature T, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ.

[0039] Furthermore, the fuel cell vehicle safety warning detection method further includes the following steps:

[0040] When the predicted hydrogen concentration is less than the preset hydrogen concentration threshold, the warning time is calculated.

[0041] A computer-readable storage medium stores a computer program, which implements the fuel cell vehicle safety warning detection method when the computer program is executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0043] Figure 1 It is a schematic diagram of the overall process of a detection method for safety warning of a fuel cell vehicle in one embodiment of the present invention;

[0044] Figure 2 It is a schematic diagram of the overall process of a fuel cell vehicle safety warning detection method in another embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with its embodiments. It should be understood that the specific implementation methods described herein are only used to explain the present invention and do not limit the protection scope of the present invention.

[0046] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only and do not represent the only implementation method.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0048] The “first” and “second” mentioned in the present invention do not represent specific quantities and orders, but are merely used to distinguish names.

[0049] A fuel cell vehicle safety warning detection system in one embodiment of the present invention includes a concentration detection module, a remaining quantity acquisition module, a real-time power acquisition module, a first pressure difference acquisition module, a concentration prediction module and a warning module.

[0050] The concentration detection module is used to obtain the real-time hydrogen concentration Con of the fuel cell vehicle. h2 The remaining amount acquisition module is used to detect and obtain the remaining amount of hydrogen in the hydrogen tank of the fuel cell vehicle.

[0051] The concentration detection module includes but is not limited to a hydrogen concentration sensor. The installation location of the concentration detection module includes but is not limited to a hydrogen bottle storage area, an engine compartment, and a cockpit of a fuel cell vehicle.

[0052] The remaining amount acquisition module can obtain the remaining amount of hydrogen in the hydrogen bottle of the fuel cell vehicle by obtaining the pressure of the bottle mouth valve of the hydrogen bottle and calculating it according to the pressure of the bottle mouth valve and the volume of the hydrogen bottle. Of course, the remaining amount acquisition module can also detect and obtain the remaining amount of hydrogen in the hydrogen bottle of the fuel cell vehicle by other methods.

[0053] Since the method for obtaining the remaining amount of hydrogen in the hydrogen tank of a fuel cell vehicle is a conventional technical means in the field, it will not be described here in detail.

[0054] The real-time power acquisition module is used to detect and acquire the real-time output power of the fuel cell vehicle; the first pressure difference acquisition module is used to detect and acquire the real-time pressure drop value Δp1 of the hydrogen tank of the fuel cell vehicle.

[0055] The real-time power acquisition module can communicate with the fuel cell vehicle main control system and acquire the real-time output power of the fuel cell vehicle through the fuel cell vehicle main control system. Since the acquisition of real-time output power belongs to conventional technical means in this field, it will not be described here.

[0056] The second pressure difference acquisition module is used to obtain the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power.

[0057] Specifically, the second pressure difference acquisition module includes a training data acquisition unit, a real-time data acquisition unit and a neural network unit.

[0058] The training data acquisition unit is used to collect the historical hydrogen remaining amounts of different fuel cell vehicles, the different historical output powers under different historical hydrogen remaining amounts, and the actual pressure drop values ​​of the hydrogen bottles of the fuel cell vehicles corresponding to the different historical output powers; the real-time data acquisition unit is used to collect the hydrogen remaining amounts and real-time output powers of the fuel cell vehicles.

[0059] The neural network unit is used to train through the collected historical hydrogen remaining amounts of different fuel cell vehicles, different historical output powers under different historical hydrogen remaining amounts, and actual pressure drop values ​​of the hydrogen bottles of fuel cell vehicles corresponding to different historical output powers. After training, the predicted pressure drop value Δp2 of the hydrogen bottle of the fuel cell vehicle is obtained according to the hydrogen remaining amount and real-time output power of the fuel cell vehicle.

[0060] That is to say, the actual pressure drop values ​​corresponding to different historical output powers of the fuel cell vehicle under different historical hydrogen remaining amounts can be obtained in advance, and the neural network unit can be trained using the collected fuel cell vehicle data (including historical hydrogen remaining amounts, historical output powers and corresponding actual pressure drop values).

[0061] In order to reduce the amount of training data collected and facilitate the use of the collected data to train the neural network unit, preferably, the second pressure difference acquisition module also includes a classification unit and a screening processing unit. The classification unit is used to divide a plurality of different hydrogen remaining ranges and a plurality of different output power ranges. The screening processing unit is used to screen and process a plurality of actual pressure drop values ​​whose historical hydrogen remaining amounts belong to the same hydrogen remaining range and whose historical output powers belong to the same output power range; the specific method of the screening and processing is: eliminating the maximum value and the minimum value among the plurality of actual pressure drop values ​​whose historical hydrogen remaining amounts belong to the same hydrogen remaining range and whose historical output powers belong to the same output power range, and calculating the pressure drop average of the plurality of actual pressure drop values ​​after eliminating the maximum value and the minimum value, and using the pressure drop average as the standard pressure drop value corresponding to the hydrogen remaining range and the output power range.

[0062] First, based on big data technology, a large number of historical hydrogen remaining amounts of fuel cell vehicles, historical output powers under historical hydrogen remaining amounts, and actual pressure drop values ​​of hydrogen bottles of fuel cell vehicles corresponding to historical output powers are obtained. Then, a large number of historical hydrogen remaining amounts of fuel cell vehicles, historical output powers under historical hydrogen remaining amounts, and actual pressure drop values ​​of hydrogen bottles of fuel cell vehicles corresponding to historical output powers are screened and processed by a screening processing unit to obtain standard pressure drop values ​​corresponding to different output power ranges under different hydrogen remaining amount ranges. Finally, the neural network unit is trained according to the obtained standard pressure drop values ​​corresponding to different output power ranges under different hydrogen remaining amount ranges.

[0063] After obtaining the remaining hydrogen and real-time output power of the fuel cell vehicle, the trained neural network unit obtains the standard pressure drop values ​​corresponding to the corresponding remaining hydrogen range and output power range by identifying the remaining hydrogen range and the output power range corresponding to the real-time output power, and uses the corresponding standard pressure drop value as the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle.

[0064] Based on big data technology, the standard pressure drop values ​​corresponding to different output power ranges under different hydrogen remaining ranges are calculated. Finally, the neural network unit is trained using the large amount of collected data, which can quickly identify the remaining hydrogen amount of the fuel cell vehicle and the predicted pressure drop value Δp2 of the hydrogen bottle of the fuel cell vehicle corresponding to the real-time output power.

[0065] The predicted pressure drop value Δp2 of the hydrogen bottle of the fuel cell vehicle can be understood as the normal pressure drop of the hydrogen bottle of the fuel cell vehicle. If there is a hydrogen leakage problem in the fuel cell vehicle, there will be a certain difference between the actual pressure drop value Δp1 of the hydrogen bottle mouth valve measured and the predicted pressure drop value Δp2. At this time, the predicted hydrogen concentration of the fuel cell vehicle is calculated based on the actual pressure drop value Δp1, the predicted pressure drop value Δp2 and the real-time hydrogen concentration, so that a more accurate predicted hydrogen concentration can be obtained.

[0066] It should be noted that the above-mentioned large number of historical hydrogen remaining amounts of fuel cell vehicles, historical output powers under historical hydrogen remaining amounts, and actual pressure drop values ​​of hydrogen bottles of fuel cell vehicles corresponding to historical output powers refer to those collected when there is no hydrogen leakage in the fuel cell vehicles. The above-mentioned standard pressure drop values ​​also refer to the standard pressure drop values ​​when there is no hydrogen leakage in the fuel cell vehicles.

[0067] The concentration prediction module is used to predict the concentration of hydrogen based on the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ.

[0068] The early warning module is used to issue a safety alarm when the predicted hydrogen concentration is greater than or equal to a preset hydrogen concentration threshold.

[0069] Among them, ε represents the hydrogen pressure difference concentration compensation coefficient, and λ represents the hydrogen bottle temperature compensation coefficient.

[0070] Preferably, the hydrogen bottle temperature compensation coefficient λ is 1. The concentration prediction module calculates the concentration of hydrogen according to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ, first determine the real-time hydrogen concentration Con h2 Is it greater than the first concentration threshold? If so, the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ.

[0071] In this case, only the real-time hydrogen concentration Con h2 When the concentration is greater than the first concentration threshold, the predicted hydrogen concentration of the fuel cell vehicle is calculated to reduce the amount of calculation.

[0072] For the hydrogen pressure difference concentration compensation coefficient, we can first obtain multiple different pressure drop values ​​Δp of the fuel cell vehicle in the case of hydrogen leakage. i The corresponding hydrogen pressure difference concentration value, that is, different pressure drop values ​​Δp i The real-time hydrogen concentration change value ΔC of the fuel cell vehicle under i Then calculate the unit hydrogen concentration change mean of the real-time hydrogen concentration change value corresponding to different pressure drop values, and obtain the hydrogen pressure difference concentration compensation coefficient Wherein, n is the number of different pressure drop values.

[0073] The fuel cell vehicle safety warning detection system obtains the real-time output power of the fuel cell vehicle and the remaining amount of hydrogen in the hydrogen bottle, obtains the predicted pressure drop value Δp2 of the fuel cell vehicle hydrogen bottle according to the remaining amount of hydrogen and the real-time output power, and on this basis, combines the real-time hydrogen concentration Con h2 , predicted pressure drop value Δp2 and real-time pressure drop value Δp1 are used to calculate the predicted hydrogen concentration of the fuel cell vehicle. The predicted hydrogen concentration can be calculated with improved accuracy by taking into account the influence of the remaining hydrogen amount and the real-time output power of the hydrogen fuel cell vehicle on the predicted hydrogen concentration. This solves the problem that the existing hydrogen leakage monitoring and alarm method and system for fuel cell vehicles do not take into account the remaining hydrogen amount and the real-time output power of the hydrogen fuel cell vehicle when calculating the predicted hydrogen concentration, resulting in inaccurate calculation results of the predicted hydrogen concentration.

[0074] In addition, according to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ, which can also solve the problem in the prior art that after hydrogen leakage in a fuel cell vehicle, the hydrogen leakage cannot be quickly detected due to the long response time of the sensor.

[0075] In one of the embodiments, the warning module is further used to calculate the warning time when the predicted hydrogen concentration is less than a preset hydrogen concentration threshold.

[0076] Specifically, when the predicted hydrogen concentration is less than the preset hydrogen concentration value, the unit change value ΔC' of the predicted hydrogen concentration is obtained, and the difference ΔC" between the current predicted hydrogen concentration and the preset hydrogen concentration threshold is calculated, and the warning time = ΔC" / ΔC'.

[0077] By calculating the warning time, fuel cell vehicle users can easily learn the time required for the predicted hydrogen concentration to reach the preset hydrogen concentration threshold, which helps users determine the specific situation of hydrogen leakage in the fuel cell vehicle.

[0078] In one of the embodiments, the fuel cell vehicle safety warning detection system also includes a temperature acquisition module.

[0079] The temperature acquisition module is used to detect and obtain the real-time temperature T of the hydrogen tank of the fuel cell vehicle.

[0080] The concentration prediction module is based on the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1, predicted pressure drop value Δp2 and real-time temperature T, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ.

[0081] Due to the different temperatures of the hydrogen bottles of fuel cell vehicles, the predicted hydrogen concentration calculation value of the fuel cell vehicle will also be affected. h2 , real-time pressure drop value Δp1, predicted pressure drop value Δp2 and real-time temperature T, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ, the accuracy of predicting hydrogen concentration can be further improved.

[0082] In one embodiment, if Figure 1 As shown, a fuel cell vehicle safety warning detection method is applied to the fuel cell vehicle safety warning detection system, which includes the following steps:

[0083] S1, obtain the real-time hydrogen concentration Con of the fuel cell vehicle h2

[0084] S2, detecting and obtaining the remaining amount of hydrogen in the hydrogen tank of the fuel cell vehicle.

[0085] S3, detecting and obtaining the real-time output power of the fuel cell vehicle.

[0086] S4, detect and obtain the real-time pressure drop value Δp1 of the hydrogen tank of the fuel cell vehicle

[0087] S5, obtaining the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power

[0088] S6, according to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ

[0089] S7 issues a safety alarm when the predicted hydrogen concentration is greater than or equal to the preset hydrogen concentration threshold.

[0090] Among them, ε represents the hydrogen pressure difference concentration compensation coefficient, and λ represents the hydrogen bottle temperature compensation coefficient.

[0091] In this embodiment, the value of the hydrogen bottle temperature compensation coefficient λ is 1.

[0092] The detection method for safety warning of fuel cell vehicle obtains the real-time output power of fuel cell vehicle and the remaining amount of hydrogen in the hydrogen bottle, obtains the predicted pressure drop value Δp2 of the hydrogen bottle of fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power, and on this basis, combines the real-time hydrogen concentration Con h2 , predicted pressure drop value Δp2 and real-time pressure drop value Δp1 are used to calculate the predicted hydrogen concentration of the fuel cell vehicle. The predicted hydrogen concentration can be calculated with improved accuracy by taking into account the influence of the remaining hydrogen amount and the real-time output power of the hydrogen fuel cell vehicle on the predicted hydrogen concentration. This solves the problem that the existing hydrogen leakage monitoring and alarm method and system for fuel cell vehicles do not take into account the remaining hydrogen amount and the real-time output power of the hydrogen fuel cell vehicle when calculating the predicted hydrogen concentration, resulting in inaccurate calculation results of the predicted hydrogen concentration.

[0093] In one embodiment, if Figure 2 As shown, in step S5, the specific method for obtaining the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle according to the remaining amount of hydrogen and the real-time output power includes the following steps:

[0094] S50, collecting historical remaining hydrogen amounts of different fuel cell vehicles, different historical output powers at different historical remaining hydrogen amounts, and actual pressure drop values ​​of hydrogen bottles of fuel cell vehicles corresponding to different historical output powers.

[0095] S51, collecting the remaining amount of hydrogen and real-time output power of the fuel cell vehicle.

[0096] S52, construct a neural network unit.

[0097] S53, training the neural network unit by collecting historical hydrogen remaining amounts of different fuel cell vehicles, different historical output powers under different historical hydrogen remaining amounts, and actual pressure drop values ​​of hydrogen bottles of fuel cell vehicles corresponding to different historical output powers.

[0098] S54, based on the trained neural network unit and according to the remaining hydrogen amount and real-time output power of the fuel cell vehicle, obtain the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle.

[0099] Specifically, in step S53, the specific method for training the neural network unit by collecting the historical hydrogen remaining amounts of different fuel cell vehicles, the different historical output powers under different historical hydrogen remaining amounts, and the actual pressure drop values ​​of the hydrogen bottles of the fuel cell vehicles corresponding to the different historical output powers includes the following steps:

[0100] S530, dividing into a plurality of different hydrogen remaining amount ranges and a plurality of different output power ranges.

[0101] S531, process screening of multiple actual pressure drop values ​​whose historical hydrogen remaining amounts belong to the same hydrogen remaining amount range and whose historical output powers belong to the same output power range, and remove the maximum value and the minimum value among the multiple actual pressure drop values ​​whose historical hydrogen remaining amounts belong to the same hydrogen remaining amount range and whose historical output powers belong to the same output power range.

[0102] S532, calculating the pressure drop average of multiple actual pressure drop values ​​after removing the maximum value and the minimum value, and taking the pressure drop average as the standard pressure drop value corresponding to the hydrogen remaining amount range and the output power range.

[0103] S533, obtaining standard pressure drop values ​​corresponding to different output power ranges under different hydrogen remaining amount ranges, and training the neural network unit according to the obtained standard pressure drop values ​​corresponding to different output power ranges under different hydrogen remaining amount ranges.

[0104] In step S54, based on the trained neural network unit and according to the remaining hydrogen amount and the real-time output power of the fuel cell vehicle, a specific method for obtaining the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle includes the following steps: identifying the hydrogen remaining amount range corresponding to the remaining hydrogen amount and the output power range corresponding to the real-time output power through the trained neural network unit, obtaining the corresponding standard pressure drop values ​​under the corresponding remaining hydrogen amount range and output power range, and using the corresponding standard pressure drop value as the predicted pressure drop value Δp2 of the hydrogen tank of the fuel cell vehicle.

[0105] Based on big data technology, the standard pressure drop values ​​corresponding to different output power ranges under different hydrogen remaining ranges are calculated. Finally, the neural network unit is trained using the large amount of collected data, which can quickly identify the remaining hydrogen amount of the fuel cell vehicle and the predicted pressure drop value Δp2 of the hydrogen bottle of the fuel cell vehicle corresponding to the real-time output power.

[0106] In one embodiment, according to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1 and predicted pressure drop value Δp2, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2The specific method of +(Δp1-Δp2)*ε*λ includes the following steps:

[0107] Detect and obtain the real-time temperature T of the hydrogen tank of the fuel cell vehicle;

[0108] According to the real-time hydrogen concentration Con h2 , real-time pressure drop value Δp1, predicted pressure drop value Δp2 and real-time temperature T, calculate the predicted hydrogen concentration Pre of the fuel cell vehicle h2 =Con h2 +(Δp1-Δp2)*ε*λ.

[0109] Specifically, after detecting and obtaining the real-time temperature of the hydrogen bottle of the fuel cell vehicle, the temperature compensation coefficient λ of the hydrogen bottle is obtained according to the real-time temperature.

[0110] The specific method for obtaining the hydrogen bottle temperature compensation coefficient λ according to the real-time temperature includes the following steps:

[0111] The first step is to obtain the final hydrogen concentration and predicted hydrogen concentration of the fuel cell vehicle under different temperature ranges based on big data technology, and adjust the temperature compensation coefficient λ according to the final hydrogen concentration and the predicted hydrogen concentration so that the final hydrogen concentration is equal to the predicted hydrogen concentration.

[0112] Here, the final hydrogen concentration may be the real-time hydrogen concentration value measured at time t+t1 after the predicted hydrogen concentration is calculated at a certain time t when there is a hydrogen leakage problem in the fuel cell vehicle.

[0113] Among them, t1 represents the preset time width, which can be set according to actual needs. Generally speaking, after a hydrogen bottle leaks, the hydrogen concentration in the hydrogen bottle storage area, engine compartment or cockpit of the fuel cell vehicle will not reach the predicted hydrogen concentration immediately, and there is a time lag. The preset time width represented by t1 is recorded as the time required for the real-time hydrogen concentration in the hydrogen bottle storage area, engine compartment or cockpit of the fuel cell vehicle to reach the predicted hydrogen concentration after a hydrogen bottle leaks.

[0114] In the second step, a plurality of temperature compensation coefficients λ are obtained in each temperature range, and an average value of the plurality of temperature compensation coefficients λ is taken as the temperature compensation coefficient corresponding to each temperature range.

[0115] The third step is to obtain the temperature compensation coefficient corresponding to the temperature range to which the real-time temperature belongs, and use the corresponding temperature compensation coefficient as the hydrogen bottle temperature compensation coefficient λ.

[0116] In one embodiment, the fuel cell vehicle safety warning detection method further includes the following steps:

[0117] When the predicted hydrogen concentration is less than the preset hydrogen concentration threshold, the warning time is calculated.

[0118] By calculating the warning time, fuel cell vehicle users can easily learn the time required for the predicted hydrogen concentration to reach the preset hydrogen concentration threshold, which helps users determine the specific situation of hydrogen leakage in the fuel cell vehicle.

[0119] In one of the embodiments, the present invention further provides a computer-readable storage medium storing a computer program, which implements the fuel cell vehicle safety warning detection method when the computer program is executed by a processor.

[0120] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0121] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A fuel cell vehicle safety warning detection system, characterized in that: The fuel cell vehicle safety warning detection system includes: Concentration detection module, used to obtain the real-time hydrogen concentration of fuel cell vehicles ; A remaining amount acquisition module is used to detect and obtain the remaining amount of hydrogen in the hydrogen tank of a fuel cell vehicle; A real-time power acquisition module, used to detect and acquire the real-time output power of the fuel cell vehicle; The first pressure difference acquisition module is used to detect and obtain the real-time pressure drop value of the hydrogen tank of the fuel cell vehicle ; The second pressure difference acquisition module is used to obtain the predicted pressure drop value of the hydrogen tank of the fuel cell vehicle according to the remaining hydrogen amount and the real-time output power. ; Concentration prediction module is used to predict the concentration of hydrogen based on the real-time , Real-time pressure drop value And the predicted pressure drop value , calculate the predicted hydrogen concentration for fuel cell vehicles ; An early warning module is used to issue a safety alarm when the predicted hydrogen concentration is greater than or equal to a preset hydrogen concentration threshold; The second pressure difference acquisition module includes: A training data acquisition unit, used to collect historical hydrogen remaining amounts of different fuel cell vehicles, different historical output powers under different historical hydrogen remaining amounts, and actual pressure drop values ​​of hydrogen bottles of fuel cell vehicles corresponding to different historical output powers; A real-time data acquisition unit, used to collect the remaining amount of hydrogen and real-time output power of the fuel cell vehicle; The neural network unit is used to train the collected historical hydrogen remaining amounts of different fuel cell vehicles, different historical output powers under different historical hydrogen remaining amounts, and actual pressure drop values ​​of the hydrogen bottles of the fuel cell vehicles corresponding to different historical output powers. After training, the predicted pressure drop value of the hydrogen bottle of the fuel cell vehicle is obtained according to the hydrogen remaining amount and real-time output power of the fuel cell vehicle. ; in, Indicates the hydrogen pressure difference concentration compensation coefficient, Indicates the temperature compensation coefficient of the hydrogen bottle.

2. A fuel cell vehicle safety warning detection system as claimed in claim 1, characterized in that: The warning module is also used to calculate the warning time when the predicted hydrogen concentration is less than a preset hydrogen concentration threshold.

3. A fuel cell vehicle safety warning detection system as claimed in claim 2, characterized in that: The fuel cell vehicle safety warning detection system also includes: Temperature acquisition module, used to detect and obtain the real-time temperature of the hydrogen tank of the fuel cell vehicle ; Among them, the concentration prediction module is based on the real-time hydrogen concentration , Real-time pressure drop value , predicted pressure drop value And real-time temperature , calculate the predicted hydrogen concentration for fuel cell vehicles .

4. A fuel cell vehicle safety warning detection method, applied to the fuel cell vehicle safety warning detection system as claimed in any one of claims 1 to 3, characterized in that: The detection method of the fuel cell vehicle safety warning comprises the following steps: Obtaining real-time hydrogen concentration for fuel cell vehicles ; Detect and obtain the remaining amount of hydrogen in the hydrogen tank of a fuel cell vehicle; Detect and obtain the real-time output power of fuel cell vehicles; Detect and obtain the real-time pressure drop value of the hydrogen tank of the fuel cell vehicle ; Obtain the predicted pressure drop value of the hydrogen tank of a fuel cell vehicle based on the remaining hydrogen amount and real-time output power ; According to the real-time hydrogen concentration , Real-time pressure drop value And the predicted pressure drop value , calculate the predicted hydrogen concentration for fuel cell vehicles ; When the predicted hydrogen concentration is greater than or equal to the preset hydrogen concentration threshold, a safety alarm is issued; Obtain the predicted pressure drop value of the hydrogen tank of a fuel cell vehicle based on the remaining hydrogen amount and real-time output power The specific method includes the following steps: Collect the historical remaining hydrogen amounts of different fuel cell vehicles, the different historical output powers under different historical remaining hydrogen amounts, and the actual pressure drop values ​​of the hydrogen tanks of the fuel cell vehicles corresponding to the different historical output powers; Collect the remaining hydrogen and real-time output power of fuel cell vehicles; Construct neural network units; The neural network unit is trained by collecting the historical remaining amounts of hydrogen of different fuel cell vehicles, the different historical output powers under different historical remaining amounts of hydrogen, and the actual pressure drop values ​​of the hydrogen bottles of the fuel cell vehicles corresponding to the different historical output powers; Based on the trained neural network unit and the remaining hydrogen amount and real-time output power of the fuel cell vehicle, the predicted pressure drop value of the hydrogen tank of the fuel cell vehicle is obtained. ; in, Indicates the hydrogen pressure difference concentration compensation coefficient, Indicates the temperature compensation coefficient of the hydrogen bottle.

5. A fuel cell vehicle safety warning detection method as claimed in claim 4, characterized in that: According to the real-time hydrogen concentration , Real-time pressure drop value And the predicted pressure drop value , calculate the predicted hydrogen concentration for fuel cell vehicles The specific method includes the following steps: Detect and obtain the real-time temperature of the hydrogen tank of the fuel cell vehicle ; According to the real-time hydrogen concentration , Real-time pressure drop value , predicted pressure drop value And real-time temperature , calculate the predicted hydrogen concentration for fuel cell vehicles .

6. A fuel cell vehicle safety warning detection method as claimed in claim 5, characterized in that: The fuel cell vehicle safety warning detection method also includes the following steps: When the predicted hydrogen concentration is less than the preset hydrogen concentration threshold, the warning time is calculated.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting safety warning of a fuel cell vehicle as described in any one of claims 4 to 6 is implemented.

Images