Electric heavy truck lithium battery temperature control detection method and device based on multi-scale feature fusion and medium

Abstract

The invention discloses an electric heavy truck lithium battery temperature control detection method and device based on multi-scale feature fusion and a medium. The method comprises the following steps: carrying out multi-scale feature extraction and feature fusion on an infrared light image and a structured light image of a target lithium battery at each moment; performing temperature detection on the multi-scale fusion features at different moments by using a target detection network to obtain temperature measurement results of the target lithium battery at different moments; based on the temperature measurement results of the target lithium battery at different moments, regional temperature measurement maps of the target lithium battery at multiple moments are drawn according to preset point locations; risk point identification is carried out based on the regional temperature measurement maps of the target lithium battery at the multiple moments; performing risk analysis and evaluation on the target lithium battery based on each risk point to obtain a risk analysis and evaluation result; and determining the temperature control level of the target lithium battery according to a risk analysis and evaluation result. The accuracy and convenience of temperature control level detection of the lithium battery of the electric heavy truck are improved, and the safety of the lithium battery of the electric heavy truck is further improved.

Description

Technical Field

[0001] The present invention relates to the field of lithium battery temperature detection, and particularly to a temperature control detection method, device and medium for lithium batteries of electric heavy trucks based on multi-scale feature fusion. Background Art

[0002] With the acceleration of the electrification process of heavy trucks, lithium batteries, as the core power source, have attracted much attention for their safety and reliability. Among them, temperature is a key factor affecting the performance and safety of lithium batteries. Too high or too low temperature will lead to a decline in battery performance, shortened lifespan, and even serious safety accidents such as thermal runaway. Therefore, it is crucial to accurately monitor the temperature and issue risk warnings for lithium batteries of electric heavy trucks.

[0003] Currently, the daily maintenance of lithium batteries of electric heavy trucks usually involves power-on detection after disassembly. However, due to the large volume and weight of lithium batteries of electric heavy trucks, it is not easy to disassemble and assemble them. Therefore, the daily maintenance and detection of their state performance, especially the detection of the temperature control level, become extremely inconvenient. Moreover, power-on detection requires analyzing a large amount of battery-related data, the detection process is complex, and the detection results are not intuitive and accurate, resulting in the safety of lithium batteries of electric heavy trucks not being guaranteed. Summary of the Invention

[0004] In view of this, the present invention provides a temperature control detection method, device and medium for lithium batteries of electric heavy trucks based on multi-scale feature fusion, which can improve the accuracy and convenience of the temperature control level detection of lithium batteries of electric heavy trucks, and further improve the safety of lithium batteries of electric heavy trucks.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] In a first aspect, the present invention provides a temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion includes: acquiring infrared light images and structured light images of a target lithium battery at multiple moments; the target lithium battery is a lithium battery of an electric heavy truck; performing multi-scale feature extraction and feature fusion on the infrared light images and structured light images of the target lithium battery at each moment to obtain multi-scale fusion features at each moment; using a target detection network to perform temperature detection on the multi-scale fusion features at different moments to obtain temperature measurement results of the target lithium battery at different moments; drawing regional temperature measurement maps of the target lithium battery at multiple moments according to the temperature measurement results of the target lithium battery at different moments at preset points; identifying risk points based on the regional temperature measurement maps of the target lithium battery at multiple moments; performing risk analysis and evaluation on the target lithium battery based on each risk point to obtain a risk analysis and evaluation result; and determining the temperature control level of the target lithium battery according to the risk analysis and evaluation result.

[0007] In a second aspect, the present invention provides a computer device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the above-mentioned temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion.

[0008] In a third aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the above-mentioned temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion.

[0009] According to the specific embodiments provided by the present invention, the following technical effects are disclosed by the present invention:

[0010] As can be seen from the above technical solutions, the present invention obtains the infrared light image and the structured light image of the target lithium battery, uses the infrared light image to characterize the temperature of the lithium battery, uses the structured light image to characterize the structural form change of the lithium battery caused by temperature change, performs feature fusion between scales on the two, and obtains a multi-scale fusion feature with stronger characterization ability, improving the accuracy of lithium battery temperature detection; in addition, the process of obtaining the infrared light image and the structured light image of the target lithium battery does not involve circuit connection and lithium battery parameter analysis, the detection result is more direct, and the detection process is also more convenient; afterwards, the temperature measurement results of the target lithium battery at different times are used to draw a regional temperature measurement map, so as to identify risk points and detect the mutual influence between each risk point, and judge whether there is room for optimization in the temperature control ability of the target lithium battery, so as to process the lithium battery that needs temperature control optimization in time, improving the safety of lithium batteries of electric heavy trucks. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0012] Figure 1 It is a schematic flow chart of a temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion provided by an embodiment of the present invention;

[0013] Figure 2 It is a schematic layout diagram of an equally spaced array provided by an embodiment of the present invention.

[0014] Figure 3 It is a schematic layout diagram of a staggered spaced array provided by an embodiment of the present invention.

[0015] Figure 4 A schematic structural diagram of a computer device provided by an embodiment of the present invention. Specific implementation manner

[0016] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment 1, as Figure 1 shown, this embodiment provides a temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion includes:

[0018] S1. Obtain infrared light images and structured light images of the target lithium battery at multiple moments; the target lithium battery is a lithium battery of an electric heavy truck.

[0019] Further, the infrared light image of the target lithium battery is collected by an infrared camera.

[0020] Further, the structured light image of the target lithium battery is collected by a depth camera.

[0021] S2. Perform multi-scale feature extraction and feature fusion on the infrared light image and the structured light image of the target lithium battery at each moment to obtain multi-scale fusion features at each moment.

[0022] In some implementation manners, step S2 specifically includes:

[0023] S21. Perform multi-scale feature extraction on the infrared light image and the structured light image of the target lithium battery at each moment respectively to obtain infrared features at multiple scales at each moment and structural features at multiple scales at each moment.

[0024] S22. Align the infrared features and the corresponding structural features at each scale at each moment in terms of spatial position to obtain the aligned infrared features and the aligned structural features at each scale at each moment.

[0025] S23. Perform feature fusion on the aligned infrared features and the aligned structural features at each scale at each moment to obtain infrared-structural fusion features at each scale at each moment.

[0026] S24. Perform feature fusion across scales on the infrared-structure fusion features at each scale for each moment to obtain the multi-scale fusion features for each moment.

[0027] S3. Use an object detection network to perform temperature detection on the multi-scale fusion features at different moments to obtain the temperature measurement results of the target lithium battery at different moments.

[0028] In some embodiments, the object detection network includes at least any one of the R-CNN network model and the YOLO network model.

[0029] S4. Based on the temperature measurement results of the target lithium battery at different moments, draw the regional temperature measurement maps of the target lithium battery at multiple moments according to the preset points.

[0030] Optionally, as Figure 2 shown, the preset points are points arranged in an equally spaced array.

[0031] Optionally, the points arranged in the array are 500×500 array points.

[0032] Optionally, as Figure 3 shown, the preset points are points arranged in a staggered spaced array.

[0033] S5. Perform risk point identification based on the regional temperature measurement maps of the target lithium battery at multiple moments.

[0034] In some embodiments, step S5 specifically includes:

[0035] S51. Mark the temperature change amounts of each point in the regional temperature measurement maps of the target lithium battery at multiple moments.

[0036] S52. Mark the points with temperature change amounts exceeding the threshold as risk points.

[0037] Optionally, the threshold is 65°C.

[0038] S53. Normalize the temperature change amounts of each risk point to obtain the temperature change coefficients of each risk point after normalization.

[0039] S6. Perform risk analysis and evaluation on the target lithium battery based on each risk point to obtain the risk analysis and evaluation results;

[0040] In some embodiments, step S6 specifically includes: According to the positions of each risk point and the temperature change coefficients of each risk point after normalization, use a dynamic thermal coupling model to perform risk analysis and evaluation based on the mutual influence of risk points to obtain the risk analysis and evaluation results.

[0041] S7. Determine the temperature control level of the target lithium battery according to the risk analysis and evaluation results.

[0042] In some embodiments, step S7 specifically includes: when the risk analysis and assessment result exceeds the threshold, the temperature control level of the target lithium battery is that temperature control optimization is required; otherwise, the temperature control level of the target lithium battery is that temperature control optimization is not required.

[0043] The technical effects of the present invention are as follows:

[0044] The present invention obtains the infrared light image and the structured light image of the target lithium battery, uses the infrared light image to characterize the temperature of the lithium battery, uses the structured light image to characterize the structural form change of the lithium battery caused by temperature change, performs feature fusion between the two at different scales, obtains a multi-scale fusion feature with stronger characterization ability, and improves the accuracy of lithium battery temperature detection; in addition, the process of obtaining the infrared light image and the structured light image of the target lithium battery does not involve circuit connection and lithium battery parameter analysis, the detection result is more direct, and the detection process is more convenient; afterwards, a regional temperature measurement map is drawn using the temperature measurement results of the target lithium battery at different times, risk points are identified based on this, and the mutual influence between each risk point is detected to determine whether there is room for optimization in the temperature control ability of the target lithium battery, so as to process the lithium battery that requires temperature control optimization in a timely manner, improving the safety of the lithium battery of the electric heavy truck.

[0045] Embodiment 2, as Figure 4 shown, the present invention also provides a computer device, which can be a server or a terminal. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store and process data. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements the above-mentioned method.

[0046] Those skilled in the art can understand that Figure 4 the structure shown in

[0047] Example 3. The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned various methods.

[0048] In several embodiments provided by the present invention, it can be understood that each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, the program segment, or the part of code includes one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.

[0049] In several embodiments provided by the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other may be through some interfaces, and the indirect coupling or communication connection of the apparatus or unit may be in an electrical, mechanical, or other form.

[0050] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion, characterized in that: The electric heavy-duty truck lithium battery temperature control detection method based on multi-scale feature fusion includes: Acquire infrared light images and structured light images of a target lithium battery at multiple moments; the target lithium battery is a lithium battery for an electric heavy truck; Perform multi-scale feature extraction and feature fusion on the infrared light image and structured light image of the target lithium battery at each moment to obtain the multi-scale fusion features at each moment; The target detection network is used to detect the temperature of the multi-scale fusion features at different times, and the temperature measurement results of the target lithium battery at different times are obtained; Based on the temperature measurement results of the target lithium battery at different times, a regional temperature measurement map of the target lithium battery at multiple times is drawn according to preset points; Identify risk points based on regional temperature measurement maps of target lithium batteries at multiple times; Perform risk analysis and assessment on the target lithium battery based on each risk point to obtain risk analysis and assessment results; Determine the temperature control level of the target lithium battery based on the risk analysis and assessment results.

2. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion according to claim 1 is characterized in that: Multi-scale feature extraction and feature fusion are performed on the infrared light image and structured light image of the target lithium battery at each moment to obtain the multi-scale fusion features at each moment, including: Perform multi-scale feature extraction on the infrared light image and structured light image of the target lithium battery at each moment, respectively, to obtain infrared features at multiple scales at each moment and structural features at multiple scales at each moment; Align the infrared features at each scale at each moment with the corresponding structural features in terms of spatial position, and obtain the aligned infrared features and aligned structural features at each scale at each moment; The aligned infrared features and aligned structural features at each scale at each moment are fused to obtain the infrared-structural fusion features at each scale at each moment; The infrared-structure fusion features at each scale at each moment are fused between scales to obtain multi-scale fusion features at each moment.

3. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion according to claim 1 is characterized in that: Risk point identification is performed based on the regional temperature measurement map of the target lithium battery at multiple times, including: Mark the temperature change of each point in the regional temperature measurement map of the target lithium battery at multiple times; Mark the points where the temperature change exceeds the threshold as risk points; The temperature variation of each risk point is normalized to obtain the normalized temperature variation coefficient of each risk point.

4. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion according to claim 3 is characterized in that: Based on each risk point, the target lithium battery is subjected to risk analysis and assessment, and the risk analysis and assessment results are obtained, including: According to the position of each risk point and the normalized temperature variation coefficient of each risk point, the dynamic thermal coupling model is used to perform risk analysis and evaluation according to the mutual influence of risk points to obtain the risk analysis and evaluation results.

5. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion according to claim 1 is characterized in that: Determine the temperature control level of the target lithium battery based on the risk analysis and assessment results, including: When the risk analysis assessment result exceeds the threshold, the temperature control level of the target lithium battery is that temperature control optimization is required, otherwise the temperature control level of the target lithium battery is that temperature control optimization is not required.

6. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion according to claim 1 is characterized in that: The infrared light image of the target lithium battery is acquired by collecting it with an infrared camera.

7. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion according to claim 1 is characterized in that: The structured light image of the target lithium battery is acquired by a depth camera.

8. The temperature control detection method for lithium batteries of electric heavy trucks based on multi-scale feature fusion according to claim 1 is characterized in that: The target detection network includes at least one of an R-CNN network model and a YOLO network model.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the temperature control detection method for lithium batteries of electric heavy-duty trucks based on multi-scale feature fusion as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the temperature control detection method for lithium batteries of electric heavy-duty trucks based on multi-scale feature fusion described in any one of claims 1 to 8 is implemented.

Images