A method for managing hydrogen-electricity conversion efficiency
Through screening test vehicles, testing and machine learning model verification, combined with road conditions collection process, the hydrogen-electric conversion efficiency is monitored in real time, and the problems of hydrogen-electric conversion efficiency control and optimization are solved, and the precise monitoring of hydrogen-electric conversion efficiency and long-term efficient utilization are achieved. Promote the commercialization of hydrogen electricity.
Patent Information
- Application Number
- CN202411129398.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-16
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-16
AI Technical Summary
How to effectively and accurately control and optimize hydrogen-electric conversion efficiency and promote the commercialization process of hydrogen energy.
By screening the test vehicle, testing the range and road condition data, using machine learning models to train and verify the hydrogen source and range of the target vehicle, combined with the road condition collection process, the hydrogen and electricity operation efficiency of the vehicle is monitored in real time, and the problem of degradation of performance is timely discovered.
Accurate monitoring and optimization of hydrogen-electric conversion efficiency is achieved, ensuring that vehicles use hydrogen-electricity efficiently for a long time and promoting the commercialization of hydrogen-electricity.
Smart Images

Figure CN118643754B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of hydrogen-electricity technology, and in particular to a method for managing hydrogen-electricity conversion efficiency. Background Art
[0002] At present, hydrogen-electric (hydrogen fuel cell) power technology is gradually improving, and the application research of hydrogen-electric vehicles has also received more and more attention. In the actual application process, the hydrogen-electric conversion efficiency is directly related to the effective utilization rate and application cost of hydrogen energy. How to effectively and accurately control and optimize the hydrogen-electric conversion efficiency is a problem that needs to be solved at present.
[0003] In view of this, this application is hereby filed. Summary of the invention
[0004] The purpose of the present invention is to provide a hydrogen-to-electricity conversion efficiency management method, which can effectively and accurately control the hydrogen-to-electricity conversion efficiency, help to optimize and improve the hydrogen-to-electricity conversion efficiency in actual application scenarios, and promote the commercialization of hydrogen-to-electricity.
[0005] The embodiment of the present invention is achieved as follows:
[0006] A method for managing hydrogen-to-electricity conversion efficiency comprises the following steps:
[0007] S1. Screen the test vehicle and equip it with a hydrogen storage device and a hydrogen fuel cell power system.
[0008] S2. Test the cruising range of the test vehicle, and record the corresponding hydrogen source amount and road condition data, and determine the "road condition type-length" data based on the road condition data.
[0009] S3. Obtain several endurance test results, and use the hydrogen source amount, endurance mileage, and “road condition type-length” data in the endurance test results as a training set to complete the training of the machine learning model.
[0010] S4. Obtain the endurance test results of the target vehicle, and use the machine learning model to determine whether the hydrogen source amount, cruising range and "road condition type-length" data of the target vehicle match. If the cruising range of the target vehicle is lower than the theoretical value, it is prompted to check the system conversion efficiency of the target vehicle. If the cruising range of the target vehicle is higher than the theoretical value, it is prompted that the system conversion efficiency of the target vehicle is excellent, and the hydrogen source amount, cruising range and "road condition type-length" data of the target vehicle are used as a backup training set.
[0011] Furthermore, the backup training set is specified by the administrator at the execution time for training the machine learning model.
[0012] Furthermore, the traffic data is obtained through a traffic collection process, which includes the following steps:
[0013] Sa. A first lens is arranged under the vehicle, the first lens is arranged toward the front wheel, and the field of view of the first lens extends from the wheel surface of the front wheel to the road surface on the side of the front wheel close to the rear wheel. The first image data is collected by using the first lens.
[0014] Sb. Determine the size information of the road surface according to the width of the wheel in the first image data. Determine the vehicle speed according to the rotation speed of the wheel in the first image data. Determine the undulation of the road surface according to the distance change of the road surface in the first image data during the change process.
[0015] Further, in Sb, when determining the undulation of the road surface according to the distance change of the road surface in the first image data during the change process, it includes:
[0016] Sb1. Taking the distance change of the road surface in the first image data when the vehicle is traveling on a horizontal and flat road surface as a reference.
[0017] Sb2. If the distance change of the road surface in the first image data of the target vehicle is farther than the reference reference, it indicates that the road surface at the front wheel is lifted.
[0018] Sb3. If the distance change of the road surface in the first image data of the target vehicle is closer than the reference reference, it indicates that the road surface at the front wheel is sinking.
[0019] Furthermore, in Sb, when the distance change of the road surface in the first image data of the target vehicle becomes farther or closer than the reference datum, it indicates that the contact part between the front wheel and the ground undergoes corresponding fluctuation changes.
[0020] Furthermore, the traffic condition collection process also includes the following steps:
[0021] Sc. A second lens is arranged under the vehicle. The second lens is arranged toward the rear wheel, and the field of view of the second lens extends from the wheel surface of the rear wheel to the road surface on the side of the rear wheel close to the front wheel. The second image data is collected by the second lens.
[0022] Sd, construct a first reference plane and a second reference plane, when the vehicle is stationary on a horizontal and flat road, the rotation axis of the front wheel and the rear wheel are both located in the first reference plane, the second reference plane is perpendicular to the first reference plane, and the distances from the rotation axis of the front wheel and the rear wheel to the second reference plane are equal. The first lens and the second lens are symmetrically arranged relative to the second reference plane.
[0023] Se. When it is detected that the distance change of the road surface in the first image data of the target vehicle is farther than the reference base, the distance from the road surface position point closest to the rear wheel in the field of view of the first lens to the first lens is the first reference distance, and the distance from the road surface position point closest to the front wheel in the field of view of the second lens to the second lens is the second reference distance. If the first reference distance is greater than the second reference distance, it indicates that the road surface at the front wheel is lifted.
[0024] Sf. When it is detected that the distance change of the road surface in the first image data of the target vehicle is closer than the reference reference, if the first reference distance is less than the second reference distance, it indicates that the road surface at the front wheel is sinking.
[0025] Furthermore, the traffic condition collection process also includes the following steps:
[0026] Sg. Confirming a first undulation of the road surface at the front wheel based on a change in the distance of the road surface in the first image data compared to a change in a reference datum.
[0027] Sh. confirming a second undulation of the road surface at the front wheel based on the up and down movement amplitude of the front wheel compared to the vehicle body in the first image data.
[0028] Si. Determine the actual undulation of the road surface at the front wheel based on the first undulation and the second undulation, where the actual undulation = the first undulation + the second undulation.
[0029] The beneficial effects of the technical solution of the embodiment of the present invention include:
[0030] The hydrogen-to-electricity conversion efficiency management method provided in the embodiment of the present invention can accurately monitor the actual hydrogen-to-electricity operating efficiency of the "target vehicle" during the use of the target vehicle, so as to grasp the changes in the actual hydrogen-to-electricity operating efficiency of the target vehicle during use at any time, and can promptly discover the problem of a decrease in the actual hydrogen-to-electricity operating efficiency of the target vehicle, so as to maintain the long-term efficient use of hydrogen and electricity by the target vehicle.
[0031] In general, the hydrogen-to-electricity conversion efficiency management method provided in the embodiment of the present invention can effectively and accurately control the hydrogen-to-electricity conversion efficiency, help to optimize and improve the hydrogen-to-electricity conversion efficiency in actual application scenarios, and promote the process of hydrogen-to-electricity commercialization. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0033] Figure 1It is a schematic diagram of the position of area D when the vehicle is traveling on a horizontal and flat road;
[0034] Figure 2 The relative position of area D when the vehicle is traveling on a level and flat road Figure 1 Schematic diagram of the position after the position in continues to move;
[0035] Figure 3 It is a schematic diagram of the distance relationship of the road surface when the road surface ahead is lifted;
[0036] Figure 4 It is a schematic diagram of the distance relationship of the road surface when the road surface ahead sinks;
[0037] Figure 5 A schematic diagram of a first reference distance and a second reference distance when the road surface ahead is lifted;
[0038] Figure 6 It is a schematic diagram of the first reference distance and the second reference distance when the road surface ahead sinks.
[0039] Description of reference numerals:
[0040] A first lens 100 ; a second lens 200 . DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.
[0042] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0044] The terms “first”, “second”, etc. are only used for distinguishing descriptions and should not be understood as indicating or implying relative importance.
[0045] As shown in this specification and claims, unless the context clearly provides an example, the words "a", "an", "the", etc. do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.
[0046] The flowcharts used in this specification are used to illustrate the operations performed by the system according to the embodiments of this specification. It is understood that the operations of each step are not necessarily performed precisely in order. On the contrary, the steps can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.
[0047] In order to solve the deficiencies in the prior art, this embodiment provides a hydrogen-to-electricity conversion efficiency management method, which includes the following steps:
[0048] S1. Select the test vehicle and equip it with a hydrogen storage device and a hydrogen fuel cell power system. That is, select a vehicle powered by hydrogen and electricity as the test vehicle.
[0049] S2. Test the cruising range of the test vehicle under the corresponding amount of hydrogen source, and record the corresponding amount of hydrogen source and road condition data, and determine the "road condition type-length" data based on the road condition data. The "road condition type-length" data refers to the length of each type of road condition during the entire driving process.
[0050] S3. Obtain several endurance test results, and use the hydrogen source amount, endurance mileage and "road condition type-length" data in these endurance test results as training sets to complete the training of the machine learning model.
[0051] S4. Obtain the endurance test results of the target vehicle, and use the machine learning model to determine whether the hydrogen source amount, endurance mileage and "road condition type-length" data of the target vehicle match. That is, use the machine learning model to calculate its theoretical endurance mileage (i.e., theoretical value) based on the hydrogen source amount and "road condition type-length" data of the target vehicle, and then check whether the theoretical value is the same as the actual endurance mileage of the target vehicle.
[0052] If the cruising range of the target vehicle is lower than the theoretical value, that is, the hydrogen source consumption determined by the machine learning model based on the "road condition type-length" data of the target vehicle and the actual cruising range (i.e. the actual walking distance) is less than the hydrogen source consumption actually consumed by the target vehicle, it means that under the same hydrogen source amount and road conditions, the actual cruising range of the target vehicle will be shorter than the cruising range calculated by the machine learning model based on the same hydrogen source amount and road conditions. This means that the actual hydrogen-electricity efficiency of the target vehicle during driving is lower than that of the test vehicle, then it is prompted to check the system conversion efficiency of the target vehicle in order to troubleshoot the problem of low actual hydrogen-electricity efficiency of the "target vehicle".
[0053] If the cruising range of the target vehicle is higher than the theoretical value, which is exactly the opposite of the above situation, it indicates that the system conversion efficiency of the target vehicle is excellent, and the hydrogen source amount, cruising range and "road condition type-length" data of the target vehicle are used as a backup training set.
[0054] It should be noted that the test vehicle can be a vehicle specially selected for training the machine learning model, or it can be a brand new target vehicle. When a brand new target vehicle is selected as the test vehicle, the results of its previous range tests can be used as a training set.
[0055] Through the above design, the actual operating efficiency of hydrogen and electricity of the "target vehicle" can be accurately monitored during the use of the target vehicle, so as to grasp the changes in the actual operating efficiency of hydrogen and electricity of the target vehicle during use at any time, and timely discover the problem of reduced actual operating efficiency of hydrogen and electricity of the target vehicle, so as to maintain the long-term efficient use of hydrogen and electricity by the target vehicle.
[0056] In general, the hydrogen-to-electricity conversion efficiency management method provided in this embodiment can effectively and accurately control the hydrogen-to-electricity conversion efficiency, help to optimize and improve the hydrogen-to-electricity conversion efficiency in actual application scenarios, and promote the commercialization of hydrogen-to-electricity.
[0057] In this embodiment, the spare training set is specified by the management personnel for the execution time of training the machine learning model. If the cruising range of the target vehicle is higher than the theoretical value, it means that the hydrogen energy conversion efficiency of the target vehicle is higher, that is, the hydrogen energy utilization rate is higher, and the target vehicle can be used as a reference object for further optimizing the hydrogen energy conversion efficiency. The spare training set can be used to train a machine learning model with a higher conversion efficiency standard.
[0058] The traffic data is obtained through the traffic collection process, which specifically includes the following steps:
[0059] Sa. A first lens 100 is arranged under the vehicle, the first lens 100 is arranged toward the front wheel, and the field of view of the first lens 100 extends from the wheel surface of the front wheel to the road surface on the side of the front wheel close to the rear wheel. The first image data is collected by using the first lens 100.
[0060] Sb. Determine the size information of the road surface according to the width of the wheel in the first image data, that is, we can determine the actual size of the ground through the actual width of the wheel according to the proportional relationship between the wheel width and the ground in the first image data. Determine the vehicle speed according to the rotation speed of the wheel in the first image data, that is, we can determine the linear speed of the wheel according to the rotation speed of the wheel and the circumference of the wheel in the first image data. If the rotation speed of the wheel in the first image data matches the speed of change of the road surface, the linear speed of the wheel is the vehicle speed. If the wheel slips, resulting in a mismatch between the rotation speed of the wheel in the first image data and the speed of change of the road surface, the degree of slip can be confirmed according to the linear speed of the wheel and the speed of change of the road surface. Determine the undulation of the road surface according to the distance change of the road surface in the first image data during the change process.
[0061] Specifically, in Sb, determining the undulation of the road surface according to the distance change of the road surface in the first image data during the change process includes:
[0062] Sb1, taking the distance change of the road surface in the first image data when the vehicle is traveling on a horizontal and flat road as a reference. Figure 1 As shown, when the vehicle is moving, the area D of the road surface will gradually move to the rear of the vehicle in the first image data collected by the first lens 100, such as Figure 2 As shown, during the movement of area D, the distance of area D relative to the first lens 100 changes, and the distance in the field of view (in the first image data) also changes.
[0063] Sb2. If the distance change of the road surface in the first image data of the target vehicle is farther than the reference reference, it indicates that the road surface at the front wheel is lifted. Figure 3 As shown, when the road surface in front rises, the front wheel will be raised relative to the rear wheel when it just moves to the raised part. Since the first lens 100 is fixed to the vehicle body, at this time, if it is assumed that the vehicle is still driving on a flat road, then the flat road surface corresponding to the vehicle in this posture should be road surface S1, but the current actual road surface is road surface S2, that is, road surface S2 is "farther" than road surface S1. The situation of the road surface rising in front includes but is not limited to: uphill, partial bulge of the road surface, etc.
[0064] Sb3. If the distance change of the road surface in the first image data of the target vehicle is closer than the reference reference, it indicates that the road surface at the front wheel is sinking. Figure 4As shown, when the road surface in front sinks, the front wheel will sink relative to the rear wheel just as it moves to the sinking part. Since the first lens 100 is fixed to the vehicle body, at this time, if it is assumed that the vehicle is still driving on a flat road, then the flat road surface corresponding to the vehicle in this posture should be road surface S1, but the current actual road surface is road surface S2, that is, road surface S2 is "closer" to road surface S1. The situation of the road surface sinking in front includes but is not limited to: downhill, partial depression of the road surface, etc.
[0065] If the vehicle passes through a local protrusion, it will appear to be "lifted" first and then "sunk"; if the vehicle passes through a local depression, it will appear to be "sunk" first and then "lifted".
[0066] It should be noted that in Sb, when the distance change of the road surface in the first image data of the object vehicle "just" appears farther or closer than the reference benchmark, it means that the contact part of the front wheel with the ground "just" has a corresponding ups and downs change.
[0067] Furthermore, the traffic condition collection process also includes the following steps:
[0068] Sc. A second lens 200 is arranged under the vehicle. The second lens 200 is arranged toward the rear wheel, and the field of view of the second lens 200 extends from the wheel surface of the rear wheel to the road surface on the side of the rear wheel close to the front wheel. The second image data is collected by the second lens 200.
[0069] Sd, construct a first reference plane (not shown in the figure) and a second reference plane (not shown in the figure), when the vehicle is stationary on a horizontal and flat road, the rotation axis of the front wheel and the rear wheel are both located in the first reference plane, the second reference plane is perpendicular to the first reference plane, and the distances from the rotation axis of the front wheel and the rear wheel to the second reference plane are equal. The first lens 100 and the second lens 200 are symmetrically arranged relative to the second reference plane, and the fields of view of the first lens 100 and the second lens 200 are also symmetrically arranged relative to the second reference plane. The field of view of the first lens 100 and the second lens 200 are both angles α (such as Figure 1 shown)
[0070] Se, when it is detected that the distance change of the road surface in the first image data of the target vehicle is farther than the reference reference, the road surface position point closest to the rear wheel in the field of view of the first lens 100 (such as Figure 5 The distance from the point a1 shown in FIG. 1 to the first lens 100 is a first reference distance (eg Figure 5 ), with the road surface position point closest to the front wheel in the field of view of the second lens 200 (such as Figure 5 The distance from the point b1 shown in FIG. 2 to the second lens 200 is the second reference distance (eg Figure 5If the first reference distance is greater than the second reference distance, it indicates that the road surface at the front wheel is lifted. This can be used as a check on the road surface lift at the front wheel.
[0071] Sf, when it is detected that the distance change of the road surface in the first image data of the target vehicle is closer than the reference reference, such as Figure 6 As shown, if the first reference distance (such as Figure 6 The line segment a2-A shown in FIG. 1 is smaller than the second reference distance (such as Figure 6 The line segment b2-B shown in FIG. 1 shows that the road surface at the front wheel is sinking. This can be used as a check on the road surface sinking at the front wheel.
[0072] Furthermore, the traffic condition collection process also includes the following steps:
[0073] Sg. Confirming a first undulation of the road surface at the front wheel based on a change in the distance of the road surface in the first image data compared to a change in a reference datum.
[0074] Sh. confirming a second undulation of the road surface at the front wheel based on the up and down movement amplitude of the front wheel compared to the vehicle body in the first image data.
[0075] Si. Determine the actual undulation of the road surface at the front wheel based on the first undulation and the second undulation, where the actual undulation = the first undulation + the second undulation.
[0076] This design takes into account the actual performance of the front wheel suspension system during driving, which helps to further improve the accuracy of confirming road conditions, thereby more objectively and accurately evaluating the vehicle's actual hydrogen-to-electricity conversion efficiency.
[0077] In summary, the hydrogen-to-electricity conversion efficiency management method provided in the embodiment of the present invention can effectively and accurately control the hydrogen-to-electricity conversion efficiency, help to optimize and improve the hydrogen-to-electricity conversion efficiency in actual application scenarios, and promote the commercialization of hydrogen-to-electricity.
[0078] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. A method for managing hydrogen-to-electricity conversion efficiency, It is characterized in that The steps include: S1. Screen the test vehicle and equip it with a hydrogen storage device and a hydrogen fuel cell power system; S2. Testing the cruising range of the test vehicle, and recording the corresponding hydrogen source amount and road condition data, and determining "road condition type-length" data according to the road condition data; S3. Obtain several endurance test results, and use the hydrogen source amount, endurance mileage, and "road condition type-length" data in the endurance test results as a training set to complete the training of the machine learning model; S4. Obtain the endurance test result of the target vehicle, and use the machine learning model to determine whether the hydrogen source amount, cruising range and "road condition type-length" data of the target vehicle match; if the cruising range of the target vehicle is lower than the theoretical value, it is prompted to check the system conversion efficiency of the target vehicle; if the cruising range of the target vehicle is higher than the theoretical value, it is prompted that the system conversion efficiency of the target vehicle is excellent, and the hydrogen source amount, cruising range and "road condition type-length" data of the target vehicle are used as a backup training set; The road condition data is obtained through a road condition collection process, which includes: Sa, setting a first lens under the vehicle, the first lens is set toward the front wheel, and the field of view of the first lens extends from the wheel surface of the front wheel to the road surface on the side of the front wheel close to the rear wheel; using the first lens to collect first image data; Sb, determining the size information of the road surface according to the width of the wheel in the first image data; determining the vehicle speed according to the rotation speed of the wheel in the first image data; taking the distance change of the road surface in the first image data when the vehicle is traveling on a horizontal and flat road as a reference; if the distance change of the road surface in the first image data of the target vehicle is greater than that of the target vehicle, the vehicle speed is determined. If the distance variation of the road surface in the first image data of the target vehicle is closer than the reference reference, it indicates that the road surface at the front wheel has risen; if the distance variation of the road surface in the first image data of the target vehicle is closer than the reference reference, it indicates that the road surface at the front wheel has sunk; Sg, confirming the first undulation of the road surface at the front wheel according to the variation amplitude of the distance variation of the road surface in the first image data compared with the reference reference; Sh, confirming the second undulation of the road surface at the front wheel according to the up and down movement amplitude of the front wheel compared with the vehicle body in the first image data; Si, confirming the actual undulation of the road surface at the front wheel according to the first undulation and the second undulation, wherein the actual undulation=the first undulation+the second undulation.
2. The hydrogen-to-electricity conversion efficiency management method according to claim 1, It is characterized in that The backup training set is specified by the administrator at the execution time for training the machine learning model.
3. The hydrogen-to-electricity conversion efficiency management method according to claim 1, It is characterized in that In Sb, when the distance change of the road surface in the first image data of the target vehicle just becomes farther or closer than the reference datum, it indicates that the contact part between the front wheel and the ground has corresponding fluctuation changes.
4. The hydrogen-to-electricity conversion efficiency management method according to claim 3, It is characterized in that The traffic condition collection process also includes the following steps: Sc, a second lens is arranged under the vehicle; the second lens is arranged toward the rear wheel, and the field of view of the second lens extends from the wheel surface of the rear wheel to the road surface on the side of the rear wheel close to the front wheel; collecting second image data using the second lens; Sd, constructing a first reference plane and a second reference plane, when the vehicle is stationary on a horizontal and flat road, the rotation axis lines of the front wheels and the rear wheels are both located in the first reference plane, the second reference plane is perpendicular to the first reference plane, and the distances from the rotation axis lines of the front wheels and the rear wheels to the second reference plane are equal; the first lens and the second lens are symmetrically arranged relative to the second reference plane; Se, when it is detected that the distance change of the road surface in the first image data of the target vehicle is farther than the reference datum, the distance from the road surface position point closest to the rear wheel in the field of view of the first lens to the first lens is taken as the first reference distance, and the distance from the road surface position point closest to the front wheel in the field of view of the second lens to the second lens is taken as the second reference distance. If the first reference distance is greater than the second reference distance, it indicates that the road surface at the front wheel is lifted; Sf. When it is detected that the distance change of the road surface in the first image data of the target vehicle is closer than the reference reference, if the first reference distance is smaller than the second reference distance, it indicates that the road surface at the front wheel is sinking.
