Energy storage cell heat convection intensity detection method based on optical flow algorithm

Abstract

The invention relates to the technical field of heat flow intensity detection, and particularly discloses an energy storage cell heat convection intensity detection method based on an optical flow algorithm, and the method comprises the steps: generating a reference light spot based on a preset laser; capturing light spot deformation in real time based on a preset camera; calculating a displacement field according to the captured light spot deformation; the precision of the displacement field is a pixel level; mapping the displacement field into a temperature field; and comparing the temperature field with a preset dynamic threshold value to generate an early warning signal. According to the method, a correlation model of the hot air refraction effect and the optical flow field is established, specifically, the quantitative mapping relation of the displacement field, the refractive index gradient and the temperature gradient is established, the calculation efficiency is improved by adopting the weighted least square method according to the high contrast characteristic of laser spots, and the early warning accuracy is improved by combining the local optical flow displacement and the global temperature trend.

Description

Technical Field

[0001] This invention relates to the field of heat flow intensity detection technology, specifically a method for detecting the heat convection intensity of energy storage cells based on optical flow algorithms. Background Technology

[0002] Before thermal runaway occurs in an energy storage power station, the heating of the battery cells causes hot air to be ejected from small holes (which need to be drilled in advance) above the battery module. There are three traditional thermal runaway early warning technologies, each with its own drawbacks: 1. Temperature sensor: Deployed on the battery surface, with a slow response speed (lag of 5-10 seconds) and unable to detect internal heat accumulation; 2. Gas sensor: Requires gas to diffuse to the detector, and by the time an early warning is issued, the thermal runaway has already entered an irreversible stage; 3. Infrared thermal imaging: High cost, easily affected by environmental thermal radiation, and insufficient resolution (unable to capture minute airflows).

[0003] In summary, the existing technology has the following problems: 1. Lag: The sensor needs to be in direct contact with the high-temperature area or after the gas diffuses before it can trigger an alarm, and it cannot provide early warning in the initial stage of hot air ejection; 2. Poor anti-interference ability: The false alarm rate is high in complex environments (such as interference from other heat sources); 3. Coverage blind spots: It cannot monitor local small hot air flows in real time.

[0004] Therefore, how to provide a more accurate and rapid method for detecting thermal convection is a preferred embodiment of the technical solution of the present invention. Summary of the Invention

[0005] The purpose of this invention is to provide a method for detecting the thermal convection intensity of energy storage cells based on optical flow algorithms, so as to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for detecting the thermal convection intensity of an energy storage cell based on an optical flow algorithm, the method comprising:

[0008] A reference spot is generated based on a preset laser.

[0009] The camera captures light spot deformation in real time based on preset parameters;

[0010] The displacement field is calculated based on the captured light spot deformation; the accuracy of the displacement field is at the pixel level.

[0011] Map the displacement field to a temperature field;

[0012] The temperature field is compared with a preset dynamic threshold to generate an early warning signal.

[0013] As a further aspect of the present invention: the laser is a 650nm semiconductor laser with a power ≤5mW.

[0014] As a further aspect of the present invention: the camera is a CMOS camera with a resolution of 1280×1024 and a frame rate of 200fps.

[0015] As a further aspect of the present invention: the step of real-time capture of light spot deformation based on a preset camera includes:

[0016] The captured image is subjected to Gaussian filtering; the parameter σ of the Gaussian filter is set to 1.5 pixels.

[0017] SIFT feature matching is performed on the Gaussian filtered image to eliminate camera shake error.

[0018] As a further aspect of the present invention: the step of calculating the displacement field based on the captured light spot deformation includes:

[0019] Construct sparse optical flow equations;

[0020] Weighted least squares method is used in the sparse optical flow equation;

[0021] The spot displacement is determined based on the sparse optical flow equation using the weighted least squares method;

[0022] The rarefied optical flow equation is:

[0023]

[0024] The weight matrix for weighted least squares is:

[0025] W = diag(|I t |);

[0026] Among them, I x and I y These are the spatial gradients of the image in two directions, I and I. t The temporal gradient of the image. Indicates optical flow; diag(|I t |) indicates that it is based on I t The diagonal matrix of absolute values.

[0027] As a further aspect of the present invention: the step of mapping the displacement field to a temperature field includes:

[0028] Calculate the refractive index gradient based on the spot displacement;

[0029] Solving the temperature field based on the refractive index gradient;

[0030] The calculation process for the refractive index gradient is as follows:

[0031]

[0032] In the formula, Δx is the spot displacement calculated based on the optical flow algorithm, and the independent variable is... n0 is the reference refractive index of air, and L is the preset optical path length, which is 0.3 meters. This represents the refractive index gradient at various locations;

[0033] The solution process for the temperature field is as follows:

[0034]

[0035] T0 is the preset ambient reference temperature, k is the Gladstone-Dale constant, P is the atmospheric pressure, and T(x,y) is the temperature at position (x,y).

[0036] As a further aspect of the present invention: the step of comparing the temperature field with a preset dynamic threshold to generate a warning signal includes:

[0037] In solving the temperature field, a sliding window is used to statistically analyze the extreme values ​​of the temperature gradient; the window size of the sliding window is 10 frames.

[0038] The statistically obtained extreme values ​​of the temperature gradient are compared with the preset dynamic threshold, and an early warning signal is generated based on the comparison results.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention creates a correlation model between the hot air refraction effect and the optical flow field. Specifically, it establishes a quantitative mapping relationship between the displacement field, the refractive index gradient, and the temperature gradient. For the high contrast characteristics of the laser spot, the weighted least squares method is used to improve the calculation efficiency. Combined with the local optical flow displacement and the global temperature trend, the accuracy of the early warning is improved. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention.

[0041] Figure 1 This is a flowchart of a method for detecting the thermal convection intensity of energy storage cells based on optical flow algorithms. Detailed Implementation

[0042] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0043] Figure 1A flowchart of a method for detecting the thermal convection intensity of an energy storage cell based on an optical flow algorithm is shown. In this embodiment of the invention, a method for detecting the thermal convection intensity of an energy storage cell based on an optical flow algorithm includes:

[0044] Step S100: Generate a reference spot based on a preset laser;

[0045] Step S200: Real-time capture of light spot deformation based on preset camera settings;

[0046] Step S300: Calculate the displacement field based on the captured light spot deformation; the accuracy of the displacement field is at the pixel level;

[0047] Step S400: Map the displacement field to a temperature field;

[0048] Step S500: Compare the temperature field with the preset dynamic threshold to generate an early warning signal.

[0049] Specifically, regarding the parameters of the laser, one possible approach is:

[0050] The laser is a 650nm semiconductor laser with a power of ≤5mW.

[0051] Regarding camera parameters, one possible approach is:

[0052] The camera uses a CMOS sensor with a resolution of 1280×1024 and a frame rate of 200fps.

[0053] As a preferred embodiment of the technical solution of the present invention, the step of real-time capture of light spot deformation based on a preset camera includes:

[0054] The captured image is subjected to Gaussian filtering; the parameter σ of the Gaussian filter is set to 1.5 pixels.

[0055] SIFT feature matching is performed on the Gaussian filtered image to eliminate camera shake error.

[0056] In one example of the technical solution of the present invention, the processing procedure of the image acquired by the camera is described. The above content is the preprocessing stage before image processing. Gaussian filtering is used to eliminate CMOS image noise (σ is 1.5 pixels), and then SIFT feature matching is used to eliminate camera shake error and register the image.

[0057] As a preferred embodiment of the technical solution of the present invention, the step of calculating the displacement field based on the captured light spot deformation includes:

[0058] Construct sparse optical flow equations;

[0059] Weighted least squares method is used in the sparse optical flow equation;

[0060] The spot displacement is determined based on the sparse optical flow equation using the weighted least squares method.

[0061] The rarefied optical flow equation is:

[0062]

[0063] The weight matrix for weighted least squares is:

[0064] W = diag(|I t |);

[0065] Among them, I x and I y These are the spatial gradients of the image in two directions, I and I. t The temporal gradient of the image. Indicates optical flow; diag(|I t |) indicates that it is based on I t The diagonal matrix of absolute values.

[0066] After the displacement field calculation is completed, the temperature field is calculated based on the displacement field. The step of mapping the displacement field to the temperature field includes:

[0067] Calculate the refractive index gradient based on the spot displacement;

[0068] Solving the temperature field based on the refractive index gradient;

[0069] The calculation process for the refractive index gradient is as follows:

[0070]

[0071] In the formula, Δx is the spot displacement calculated based on the optical flow algorithm, and the independent variable is... n0 is the reference refractive index of air, and L is the preset optical path length, which is 0.3 meters. This represents the refractive index gradient at various locations;

[0072] The solution process for the temperature field is as follows:

[0073]

[0074] T0 is the preset ambient reference temperature, k is the Gladstone-Dale constant, P is the atmospheric pressure, and T(x,y) is the temperature at position (x,y).

[0075] As a preferred embodiment of the technical solution of the present invention, the step of comparing the temperature field with a preset dynamic threshold to generate a warning signal includes:

[0076] In solving the temperature field, a sliding window is used to statistically analyze the extreme values ​​of the temperature gradient; the window size of the sliding window is 10 frames.

[0077] The statistically obtained extreme values ​​of the temperature gradient are compared with the preset dynamic threshold, and an early warning signal is generated based on the comparison results.

[0078] In one embodiment of the technical solution of the present invention, an early warning logic is provided, as follows:

[0079] A sliding window (window size 10 frames) is used to count the extreme values ​​of the temperature gradient to avoid instantaneous noise interference.

[0080] Multi-level alarm strategy:

[0081] 1. Primary alarm (ΔT>50℃ / m): Notify maintenance personnel to check.

[0082] 2. Emergency alarm (ΔT>100℃ / m): Disconnect the power supply link of the battery cluster.

[0083] Here, ΔT is the statistically observed extreme value of the temperature gradient.

[0084] The above describes a detection process based on an optical flow constraint algorithm, with the following constraints:

[0085] 1. Assuming constant brightness, then I(x+u, y+v, t+1) = I(x, y, t);

[0086] 2. Temperature-Refractive Index Relationship:

[0087] Where T0 is 293K and P is 101325Pa.

[0088] 3. Early warning threshold model:

[0089] Where α is the dynamic adjustment coefficient, T base The ambient reference temperature.

[0090] The functions of the energy storage cell thermal convection intensity detection method based on optical flow algorithm are all performed by computer equipment. The computer equipment includes one or more processors and one or more memories. The one or more memories store at least one piece of program code. The program code is loaded and executed by the one or more processors to realize the functions of the energy storage cell thermal convection intensity detection method based on optical flow algorithm.

[0091] The processor fetches instructions from memory one by one, analyzes the instructions, and then performs the corresponding operations according to the instructions, generating a series of control commands to enable the various parts of the computer to act automatically, continuously, and in a coordinated manner, forming an organic whole. This enables the input of programs and data, as well as the calculation and output of results. The arithmetic or logical operations generated in this process are all performed by the arithmetic unit. The memory includes a read-only memory (ROM), which is used to store computer programs. The memory is protected by an external protection device.

[0092] For example, a computer program can be divided into one or more modules, one or more of which are stored in memory and executed by a processor to perform the present invention. The one or more modules can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a terminal device.

[0093] Those skilled in the art will understand that the above description of the service equipment is merely an example and does not constitute a limitation on the terminal equipment. It may include more or fewer components than described above, or a combination of certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0094] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the terminal device, connecting various parts of the user terminal via various interfaces and lines.

[0095] The aforementioned memory can be used to store computer programs and / or modules. The aforementioned processor implements various functions of the aforementioned terminal device by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as information collection template display function, product information publishing function, etc.); the data storage area may store data created based on the use of the berth status display system (such as product information collection templates corresponding to different product types, product information that different product providers need to publish, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0096] If the modules / units integrated into the terminal device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the modules / units in the systems of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the functions of the various system embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0097] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0098] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for detecting the thermal convection intensity of an energy storage cell based on an optical flow algorithm, characterized in that, The method includes: A reference spot is generated based on a preset laser. The camera captures light spot deformation in real time based on preset parameters; The displacement field is calculated based on the captured light spot deformation; the accuracy of the displacement field is at the pixel level. Map the displacement field to a temperature field; The temperature field is compared with a preset dynamic threshold to generate an early warning signal.

2. The method for detecting thermal convection intensity of energy storage cells based on optical flow algorithm according to claim 1, characterized in that, The laser is a 650nm semiconductor laser with a power of ≤5mW.

3. The method for detecting thermal convection intensity of energy storage cells based on optical flow algorithm according to claim 1, characterized in that, The camera uses a CMOS sensor with a resolution of 1280×1024 and a frame rate of 200fps.

4. The method for detecting thermal convection intensity of energy storage cells based on optical flow algorithm according to claim 1, characterized in that, The step of capturing light spot deformation in real time based on a preset camera includes: The captured image is subjected to Gaussian filtering; the parameter σ of the Gaussian filter is set to 1.5 pixels. SIFT feature matching is performed on the Gaussian filtered image to eliminate camera shake error.

5. The method for detecting thermal convection intensity of energy storage cells based on optical flow algorithm according to claim 1, characterized in that, The step of calculating the displacement field based on the captured light spot deformation includes: Construct sparse optical flow equations; Weighted least squares method is used in the sparse optical flow equation; The spot displacement is determined based on the sparse optical flow equation using the weighted least squares method; The rarefied optical flow equation is: The weight matrix for weighted least squares is: W=diag(|I t |); Among them, I x and I y These are the spatial gradients of the image in two directions, I and I. t The temporal gradient of the image. Indicates optical flow; diag(|I t |) indicates that it is based on I t The diagonal matrix of absolute values.

6. The method for detecting thermal convection intensity of energy storage cells based on optical flow algorithm according to claim 5, characterized in that, The step of mapping the displacement field to a temperature field includes: Calculate the refractive index gradient based on the spot displacement; Solving the temperature field based on the refractive index gradient; The calculation process for the refractive index gradient is as follows: In the formula, Δx is the spot displacement calculated based on the optical flow algorithm, and the independent variable is... n0 is the reference refractive index of air, and L is the preset optical path length, which is 0.3 meters. This represents the refractive index gradient at various locations; The solution process for the temperature field is as follows: T0 is the preset ambient reference temperature, k is the Gladstone-Dale constant, P is the atmospheric pressure, and T(x,y) is the temperature at position (x,y).

7. The method for detecting thermal convection intensity of energy storage cells based on optical flow algorithm according to claim 1, characterized in that, The step of comparing the temperature field with a preset dynamic threshold to generate a warning signal includes: In solving the temperature field, a sliding window is used to statistically analyze the extreme values ​​of the temperature gradient; the window size of the sliding window is 10 frames. The statistically obtained extreme values ​​of the temperature gradient are compared with the preset dynamic threshold, and an early warning signal is generated based on the comparison results.

Images