Battery device, battery temperature monitoring method, electronic equipment, medium and product

Abstract

The invention discloses a battery device, a battery temperature monitoring method, electronic equipment, a medium and a product, the battery device comprises a packaging shell, the packaging shell internally comprises at least one battery cell module and at least one thermal stress monitoring module, the battery cell module and the thermal stress monitoring module are in one-to-one correspondence, and the battery cell module and the thermal stress monitoring module are in one-to-one correspondence. Each battery cell module is located below the corresponding thermal stress monitoring module, each battery cell module comprises x battery cells, each thermal stress monitoring module comprises two elastic connecting plates and a strain gauge sensor, the strain gauge sensor is adhered to the joint of the two elastic connecting plates, and x is an integer greater than or equal to 2. Each elastic connecting plate is adhered with one battery cell, and x is an integer greater than or equal to 2.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of battery, in particular to a battery device, a battery temperature monitoring method, an electronic device, a medium and a product. BACKGROUND

[0002] At present, battery temperature early warning usually relies on temperature sensors to monitor the temperature of the surface of the battery. For a temperature sensor, each sensor can only monitor one point and can only reflect the temperature of the contact point. Under normal working conditions, there is a large temperature difference between the inside and the surface of the battery cell, so the temperature sensor cannot truly reflect the temperature of the heating point of the battery cell, and there is a problem of low temperature monitoring accuracy in the inside of the battery cell. SUMMARY

[0003] Embodiments of the present application provide a battery device, a battery temperature monitoring method, an electronic device, a medium and a product, which can solve the problem of low temperature monitoring accuracy in the inside of the battery cell.

[0004] In order to solve the above technical problems, the present application is implemented as follows: In a first aspect, a battery device is provided, comprising: a packaging shell, the inside of the packaging shell comprising at least one battery cell module and at least one thermal stress monitoring module, wherein the battery cell module and the thermal stress monitoring module correspond one by one, each battery cell module is located below the corresponding thermal stress monitoring module, each battery cell module comprises x battery cells, each thermal stress monitoring module comprises two elastic connecting plates and one strain gauge sensor, the strain gauge sensor is attached at the joint of the two elastic connecting plates, each elastic connecting plate is attached to x battery cells, and x is an integer greater than or equal to 2. In a first aspect, a battery device is provided, comprising: a packaging shell, the inside of the packaging shell comprising at least one battery cell module and at least one thermal stress monitoring module, wherein the battery cell module and the thermal stress monitoring module correspond one by one, each battery cell module is located below the corresponding thermal stress monitoring module, each battery cell module comprises x battery cells, each thermal stress monitoring module comprises two elastic connecting plates and one strain gauge sensor, the strain gauge sensor is attached at the joint of the two elastic connecting plates, each elastic connecting plate is attached to x battery cells, and x is an integer greater than or equal to 2.

[0005] In a second aspect, a battery temperature monitoring method is provided, applied to the battery device of the first aspect, the method comprising: acquiring thermal stress data collected by a strain gauge sensor in each thermal stress monitoring module; for the thermal stress data corresponding to each thermal stress monitoring module, inputting the thermal stress data into a temperature monitoring model through a first input channel to obtain a first temperature value of the battery cell module corresponding to the thermal stress monitoring module output by the temperature monitoring model; and in response to any first temperature value being greater than a high temperature alarm threshold, determining that the temperature of the battery device is abnormal.

[0006] In a third aspect, an electronic device is provided, comprising a processor, a memory and a program or instructions stored on the memory and executable on the processor, the program or instructions being executed by the processor to implement the steps of the method of the second aspect.

[0007] In a fourth aspect, a readable storage medium is provided, and the readable storage medium has stored thereon a program or instructions, which, when executed by a processor, implement the steps of the method according to the second aspect.

[0008] In a fifth aspect, a computer program product is provided, and the computer program product includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, which, when executed by a computer, cause the computer to implement the steps of the method according to the second aspect.

[0009] In the embodiments of the present application, a battery device is provided, which comprises a packaging shell, and the packaging shell internally comprises at least one battery cell module and at least one thermal stress monitoring module, wherein the battery cell module and the thermal stress monitoring module correspond to each other, each battery cell module is located below the corresponding thermal stress monitoring module, each battery cell module comprises x battery cells, each thermal stress monitoring module comprises two elastic connecting plates and one strain gauge sensor, the strain gauge sensor is attached at the joint of the two elastic connecting plates, each elastic connecting plate is attached to x battery cells, and x is an integer greater than or equal to 2. By connecting the battery cells and the strain gauge sensor through the elastic connecting plates, the thermal expansion deformation of the battery cells can be effectively amplified, the internal temperature of the battery cells can be derived based on the thermal stress, the detection accuracy of the internal temperature of the battery is improved, and the thermal expansion phenomenon of at least two battery cells can be simultaneously detected by one strain gauge sensor, thereby breaking through the limitation of single-point monitoring.

[0010] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0011] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present application and, together with the specification, serve to explain the principles of the present application.

[0012] Figure 1 FIG. 1 shows a structural schematic diagram of a battery temperature monitoring device according to an exemplary embodiment of the present application; Figure 2 FIG. 2 shows a structural schematic diagram of a battery temperature monitoring device according to an exemplary embodiment of the present application; Figure 3 FIG. 3 shows a structural schematic diagram of a battery temperature monitoring device according to an exemplary embodiment of the present application; Figure 4 FIG. 4 shows a structural schematic diagram of a battery temperature monitoring device according to an exemplary embodiment of the present application; Figure 5Fig. 1 shows a structural schematic diagram of a battery temperature monitoring device according to an example embodiment of the present application; Figure 6 Fig. 1 shows a structural schematic diagram of a battery temperature monitoring device according to an example embodiment of the present application; Figure 7 Fig. 1 shows a structural schematic diagram of a battery temperature monitoring device according to an example embodiment of the present application; Figure 8 Fig. 1 shows a structural schematic diagram of a battery temperature monitoring device according to an example embodiment of the present application; Figure 9 Fig. 1 shows a structural schematic diagram of a battery temperature monitoring device according to an example embodiment of the present application; Figure 10 Fig. 2 shows a flow schematic diagram of a battery temperature monitoring method according to an example embodiment of the present application; Figure 11 Fig. 3 shows a training schematic diagram of a temperature monitoring model according to an example embodiment of the present application; Figure 12 Fig. 4 shows another training schematic diagram of a temperature monitoring model according to an example embodiment of the present application; Figure 13 Fig. 5 shows another flow schematic diagram of a battery temperature monitoring method according to an example embodiment of the present application; Figure 14 Fig. 6 shows another training schematic diagram of a temperature monitoring model according to an example embodiment of the present application; Figure 15 Fig. 7 shows another training schematic diagram of a temperature monitoring model according to an example embodiment of the present application; Figure 16 Fig. 8 shows another flow schematic diagram of a battery temperature monitoring method according to an example embodiment of the present application; Figure 17 Fig. 9 shows a structural schematic diagram of an electronic device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0013] The example embodiments will be described in detail herein with reference to the attached drawings. When the description refers to accompanying drawings, the same numbers in different drawings refer to the same or similar elements unless otherwise described. The following example embodiments described in the following detailed description are not meant to represent all embodiments in accordance with the present application. Rather, they are merely examples of apparatus and methods in accordance with aspects of the present application as detailed in the appended claims.

[0014] Figure 1 Fig. 1 shows a structural schematic diagram of a battery temperature monitoring device according to an example embodiment of the present application.Figure 2 This application shows a top view schematic diagram of a battery device provided in an exemplary embodiment, such as... Figure 1 and Figure 2 As shown, the battery device includes: a packaging shell 110, which contains at least one battery cell module 120 and at least one thermal stress monitoring module 130. The battery cell module 120 and the thermal stress monitoring module 130 are in one-to-one correspondence. Each battery cell module 120 is located below its corresponding thermal stress monitoring module 130. Each battery cell module 120 includes x batteries 121. Each thermal stress monitoring module 130 includes two elastic connecting plates 131 and a strain gauge sensor 132. The strain gauge sensor 132 is bonded to the joint of the two elastic connecting plates 131. Each elastic connecting plate 131 is bonded to... The battery cell 121, where x is an integer greater than or equal to 2.

[0015] The elastic connecting plate 131 is used to receive thermal stress generated by the heating of the battery cell 121, thereby causing deformation. The strain gauge sensor 132 is used to capture the deformation of the elastic connecting plate 131 and convert it into stress data, which is output in the form of an electrical signal.

[0016] It is understandable that battery cells generate heat during operation due to various reasons. Based on the principle of thermal expansion, the increase in cell temperature will generate thermal expansion stress. Since each elastic connecting plate 131 is bonded... The thermal expansion stress generated by the battery cell 121 is transmitted to the elastic connecting plate 131, causing the elastic connecting plate 131 to deform accordingly. Since the strain gauge sensor 132 is bonded to the elastic connecting plate 131, the strain gauge sensor 132 captures the deformation of the elastic connecting plate 131 and converts it into stress data, outputting it as an electrical signal. Therefore, by connecting the battery cell and the integrated strain gauge sensor through the elastic connecting plate, the thermal expansion deformation of the battery cell can be effectively amplified, improving detection accuracy and enabling the simultaneous detection of the thermal expansion of multiple battery cells using a single strain gauge sensor. Furthermore, compared to the physical delay of heat conduction, the speed of stress transmission is consistent with the speed of sound; by inferring internal temperature changes through stress changes, the efficiency of temperature detection can be rapidly improved.

[0017] In one exemplary embodiment, the strain gauge sensor is an integrated strain gauge sensor with a built-in integrated circuit for converting the detected deformation of the elastic connecting plate into stress data and outputting it.

[0018] In an example embodiment, the elastic connecting plate 131 can be made of polycarbonate plate. Since the Young's modulus of polycarbonate is small, it can produce a larger deformation under the same force, thereby effectively amplifying the thermal expansion deformation of the battery cell 121, and further improving the detection accuracy of the strain gauge sensor 132.

[0019] In an example embodiment, each battery cell 121 is connected to the corresponding elastic connecting plate 131 by an adhesive.

[0020] In an example embodiment, each strain gauge sensor 132 is adhered at the center of the joint between two elastic connecting plates 131.

[0021] In an example embodiment, two adjacent thermal stress monitoring modules 130 can be connected or separated. For example, the battery device includes two thermal stress monitoring modules 130: a first thermal stress monitoring module 1301 and a second thermal stress monitoring module 1302. As shown in FIG. 1A, the first thermal stress monitoring module 1301 and the second thermal stress monitoring module 1302 are separated. As shown in FIG. 1B, the first thermal stress monitoring module 1301 and the second thermal stress monitoring module 1302 are connected. Figure 3 Figure 4

[0022] In an example embodiment, at least one battery cell 121 is adhered to each elastic connecting plate 131. For example, as shown in FIG. 2A, one battery cell 121 is adhered to each elastic connecting plate 131. As shown in FIG. 2B, two battery cells 121 are adhered to each elastic connecting plate 131. The two battery cells include a first battery cell 1211 and a second battery cell 1212. Figure 1 Figure 5

[0023] The battery device is described below. For example, as shown in FIG. 3A, the battery device includes two thermal stress monitoring modules 130: a first thermal stress monitoring module 1301 and a second thermal stress monitoring module 1302. The first thermal stress monitoring module 1301 and the second thermal stress monitoring module 1302 are separated. As shown in FIG. 3B, the first thermal stress monitoring module 1301 and the second thermal stress monitoring module 1302 are connected. Figure 6 ​​​​As shown, the battery device comprises: a packaging shell 110, which internally comprises two cell modules 120 and two thermal stress monitoring modules 130, wherein the two cell modules 120 comprise a first cell module 1201 and a second cell module 1202, the two thermal stress monitoring modules 130 comprise a first thermal stress monitoring module 1301 and a second thermal stress monitoring module 1302, the first cell module 1201 is arranged below and corresponds to the first thermal stress monitoring module 1301, and the second cell module 1202 is arranged below and corresponds to the second thermal stress monitoring module 1302. The first cell module 1201 and the second cell module 1202 each comprise four cells 121. The first thermal stress monitoring module 1301 comprises two elastic connecting plates 131 and a first strain gauge sensor 1321, wherein the two elastic connecting plates 131 comprise a first elastic connecting plate 1311 and a second elastic connecting plate 1312, the first elastic connecting plate 1311 is adhered to the four cells 121, the second elastic connecting plate 1312 is adhered to the four cells 121, and the first strain gauge sensor 1321 is arranged at the joint of the first elastic connecting plate 1311 and the second elastic connecting plate 1312. The second thermal stress monitoring module 1302 comprises two elastic connecting plates 131 and a second strain gauge sensor 1322, wherein the two elastic connecting plates 131 comprise a third elastic connecting plate 1313 and a fourth elastic connecting plate 1314, the third elastic connecting plate 1313 is adhered to the four cells 121, the fourth elastic connecting plate 1314 is adhered to the four cells 121, and the second strain gauge sensor 1322 is arranged at the joint of the third elastic connecting plate 1313 and the fourth elastic connecting plate 1314.

[0024] In the first cell module 1201, if the temperature of any cell 121 adhered to the first elastic connecting plate 1311 rises, the cell with the rising temperature will generate thermal expansion stress, which will be transmitted to the first elastic connecting plate 1311, and the first elastic connecting plate 1311 will generate corresponding deformation. The first strain gauge sensor 1321 will capture the deformation of the first elastic connecting plate 1311 and convert it into stress data in the form of an electrical signal. Similarly, in the first cell module 1201, if the temperature of any cell 121 adhered to the second elastic connecting plate 1312 rises, the cell with the rising temperature will generate thermal expansion stress, which will be transmitted to the second elastic connecting plate 1312, and the second elastic connecting plate 1312 will generate corresponding deformation. The first strain gauge sensor 1321 will capture the deformation of the second elastic connecting plate 1312 and convert it into stress data in the form of an electrical signal. Similarly, the second cell module 1202 and the second thermal stress monitoring module 1302 will also implement the above process, which will not be described here.

[0025] In the embodiments of the present application, a battery device is provided, which comprises: a packaging shell, the inside of the packaging shell comprising at least one battery cell module and at least one thermal stress monitoring module, wherein the battery cell module and the thermal stress monitoring module correspond to each other, each battery cell module is located below the corresponding thermal stress monitoring module, each battery cell module comprises x battery cells, each thermal stress monitoring module comprises two elastic connecting plates and a strain gauge sensor, the strain gauge sensor is attached at the joint of the two elastic connecting plates, each elastic connecting plate is attached to x battery cells, and x is an integer greater than or equal to 2. In this way, the battery cell and the strain gauge sensor are connected by the elastic connecting plate, which can effectively amplify the thermal expansion deformation of the battery cell, thereby improving the detection accuracy of the internal temperature of the battery, and at least two battery cells can be simultaneously detected by one strain gauge sensor, thereby breaking through the limitation of single-point monitoring.

[0026] Further, in another exemplary embodiment, as shown in Figure 7 the battery device further comprises: at least one set of temperature monitoring modules 140, wherein the temperature monitoring modules 140 and the battery cell modules 120 correspond to each other, and each temperature monitoring module 140 comprises at least one temperature sensor 141. Exemplarily, Figure 8 another top view of the battery device provided by an exemplary embodiment of the present application is shown. As shown in Figure 7 and Figure 8 the temperature sensor 141 in the temperature monitoring module 140 is arranged on the surface of any battery cell in the corresponding battery cell module 120. In this way, when the strain gauge sensor is damaged, the surface temperature data of the battery cell can be used to derive the internal temperature of the battery cell, thereby realizing efficient, high-precision and high-reliability battery temperature detection.

[0027] The battery device is exemplarily described as follows, as shown in Figure 9 the battery device is used in Figure 6 ​The embodiment shown further includes two temperature monitoring modules 140, wherein the two temperature monitoring modules 140 include a first temperature monitoring module 1401 and a second temperature monitoring module 1402. The first temperature monitoring module 1401 includes two temperature sensors 141, which include a first temperature sensor 1411 and a second temperature sensor 1412. The second temperature monitoring module 1402 includes two temperature sensors 141, which include a third temperature sensor 1413 and a fourth temperature sensor 1414. The first temperature monitoring module 1401 corresponds to the first cell module 1201, and the first temperature sensor 1411 and the second temperature sensor 1412 are arranged on the surface of any cell 121 included in the first cell module 1201. The second temperature monitoring module 1402 corresponds to the second cell module 1202, and the third temperature sensor 1413 and the fourth temperature sensor 1414 are arranged on the surface of any cell 121 included in the second cell module 1202.

[0028] Figure 10 A flowchart of a battery temperature monitoring method provided by an example embodiment of the present application is shown, which is applied to Figures 1-10 The battery device, the method comprises the following steps: S1010: Obtain thermal stress data collected by a strain gauge sensor in at least one thermal stress monitoring module.

[0029] S1020: For the thermal stress data corresponding to each thermal stress monitoring module, input the thermal stress data into a temperature monitoring model through a first input channel to obtain a first temperature value of a cell module corresponding to the thermal stress monitoring module output by the temperature monitoring model.

[0030] S1030: In response to any first temperature value being greater than a high temperature alarm threshold, determine that the battery device has a temperature anomaly.

[0031] It can be understood that the thermal stress data is the deformation of the elastic connecting plate captured by the strain gauge sensor and converted into thermal stress data output in the form of an electrical signal. The thermal stress data is input to the temperature monitoring model through the first input channel to obtain the first temperature value of the battery module corresponding to the thermal stress monitoring module output by the temperature monitoring model. That is, the thermal stress data is deduced by the temperature monitoring model, so that the internal temperature change of the battery can be obtained. As long as any first temperature value is greater than the high temperature alarm threshold, it is determined that the battery device temperature is abnormal. For example, assuming that the high temperature alarm threshold is Tmax, the first temperature value corresponding to the thermal stress data collected by the first thermal stress monitoring module is Tu1, and the first temperature value corresponding to the thermal stress data collected by the second thermal stress monitoring module is Tu2, when Tu1 > Tmax and Tu2 > Tmax, it is determined that the battery device temperature is abnormal; when Tu1 < Tmax and Tu2 > Tmax, it is determined that the battery device temperature is abnormal; when Tu1 > Tmax and Tu2 < Tmax, it is determined that the battery device temperature is abnormal; when Tu1 < Tmax and Tu2 < Tmax, it is determined that the battery device temperature is normal.

[0032] In an example embodiment, the temperature monitoring model can be a Physics-Informed Neural Networks (PINN) model.

[0033] In the embodiments of the present application, by acquiring the thermal stress data collected by the strain gauge sensor in at least one thermal stress monitoring module, for the thermal stress data corresponding to each thermal stress monitoring module, the thermal stress data is input to the temperature monitoring model through the first input channel to obtain the first temperature value of the battery module corresponding to the thermal stress monitoring module output by the temperature monitoring model, in response to any first temperature value greater than the high temperature alarm threshold, it is determined that the battery device temperature is abnormal, which effectively improves the temperature detection precision and detection efficiency.

[0034] In an example embodiment, the temperature monitoring model includes an input layer, a hidden layer, and an output layer; the thermal stress data is input to the temperature monitoring model through the first input channel to obtain the first temperature value of the battery module corresponding to the thermal stress monitoring module output by the temperature monitoring model, including: based on the first weight matrix and the first threshold matrix corresponding to the input layer, the second weight matrix corresponding to the hidden layer, the thermal stress data is converted and processed to obtain the first temperature value output by the output layer.

[0035] It can be understood that, as Figure 11As shown, the temperature monitoring model includes an input layer, a hidden layer, and an output layer. The input layer comprises three neurons, corresponding to the acquired data, time t, and the coordinates x of the cell's heating point, respectively. In this embodiment, the acquired data is thermal stress data σ1, time t is the current time, and the coordinates x of the cell's heating point can be half the cell's height or the coordinates of other locations on the cell. The input layer receives the thermal stress data σ1 and obtains the time t and the cell's heating point coordinates x, then processes them through the corresponding first weight matrix: w j1 =[w 1-1 w 1-2 w 1-3 ] h and the first threshold matrix: b k1 =[b 1-1 b 1-2 ] h The thermal stress data σ1, acquisition time t, and cell heating point coordinates x are initially transformed by multiplying them with the first weight matrix. Then, a fixed offset value is added to each input data point using the first threshold matrix to obtain the output of the input layer. This output is used as the input data for the hidden layer. The hidden layer consists of four layers, each with 32 neurons. The hidden layers are used based on the corresponding second weight matrix: c g1 =[c 1-1 c 1-2 ...c 1-32 ] h The first temperature value is derived from the received data and then output through an output layer containing one neuron.

[0036] In one exemplary embodiment, before inputting the thermal stress data into the temperature monitoring model through the first input channel to obtain the first temperature value of the cell module corresponding to the thermal stress monitoring module output by the temperature monitoring model, the method further includes: training the temperature monitoring model based on a first loss function to obtain a first weight matrix, a first threshold matrix, and a second weight matrix, wherein the first loss function consists of a first loss, a second loss, and a third loss, the first loss consists of the thermal conduction parameter in the thermal strain residual and a first weight, the second loss consists of the thermal strain parameter in the thermal strain residual and a second weight, and the third loss consists of a data matching term and a third weight, wherein the data matching term is used to clean the sample data.

[0037] In this embodiment, by introducing thermal strain residuals, prior physical knowledge of the battery cell module can be injected into the temperature monitoring model. Simultaneously, the thermal strain of the battery cell module can be physically constrained based on the thermal strain residuals, ensuring it conforms to physical laws. The thermal strain residuals of the battery cell module can be expressed by the following formula:

[0038] wherein, , ) is the time-space point coordinate, T is the temperature of the heat point of the battery cell, is the partial derivative of the temperature of the heat point of the battery cell with respect to time, i.e., the temperature change rate, and a is the thermal diffusivity, is the Laplace of the temperature field of the battery cell module, i.e., the spatial second-order derivative, is the divergence of the thermal stress tensor, and f is the body force. The parameters , , , a, T, , and f can be obtained through a public data set.

[0039] The first loss function can be represented by the following formula:

[0040] wherein, is the first weight, represents the heat conduction parameter in the thermal strain residual, is the second threshold, represents the thermal strain parameter in the thermal strain residual, is the third weight, represents the data matching item.

[0041] In the training process, as shown in FIG. 1, the parameters Figure 12 = 1, = 1, = 1 are set, and the parameters , , , a, T, , , f, , and are brought into the first loss function to calculate the gradient of the loss function with respect to the network parameters ， ， ， . Wherein, represents the first weight matrix, represents the first threshold matrix, represents the second weight matrix. In an exemplary embodiment, the Adam optimizer can be used to update the parameters in the negative gradient direction: W( ， ， ) ← W( ， ， ) - η *

[0042] wherein, η is a learning rate, η = 0.5.

[0043] When the loss Loss1 of the model is reduced and stagnates after multiple iterations, the pre-training is completed, and the temperature monitoring model is obtained as [w 1-1 w 1-2 w 1-3 ] h 、 [b 1-1 b 1-2 ] h 、 [c 1-1 c 1-2 … c 1-32 ] h The optimal solution is obtained, so as to realize the mapping of the temperature in the battery cell derived from the thermal stress. The pre-trained model inputs the thermal stress data obtained by sampling into the temperature monitoring model in use, and respectively multiplies the first weight matrix [w 1-1 w 1-2 w 1-3 ] h , the first threshold matrix [b 1-1 b 1-2 ] h , and the weight matrix [c 1- 1c 1-2 … c 1-32 ] h of the hidden layer to obtain the temperature of the heating point of the battery cell.

[0044] In an exemplary embodiment, after obtaining the thermal stress data collected by the strain gauge sensor in each thermal stress monitoring module, as shown in Figure 13 , the method further comprises the following steps: S1310: In response to the thermal stress data collected by the strain gauge sensor in each thermal stress monitoring module being invalid data, obtaining the battery surface temperature value collected by the temperature sensor in each temperature monitoring module.

[0045] It can be understood that when the strain gauge sensor is in a normal working state, the collected thermal stress data is valid data, and the temperature inside the battery cell can be accurately derived based on the collected thermal stress data. When the strain gauge sensor is in an abnormal state, the collected thermal stress data is invalid data, and then the temperature inside the battery cell can be derived based on the battery surface temperature value collected by the temperature sensor.

[0046] In an exemplary embodiment, the invalid data can include null values or other abnormal values.

[0047] In an exemplary embodiment, when the temperature monitoring module corresponding to the thermal stress monitoring module includes a plurality of temperature sensors, the battery surface temperature value can be the average of the temperatures collected by the plurality of temperature sensors.

[0048] S1320: For each battery surface temperature value corresponding to a temperature monitoring module, input the battery surface temperature value through a second input channel to the temperature monitoring model to obtain a second temperature value of the battery module corresponding to the temperature monitoring module output by the temperature monitoring model.

[0049] It can be understood that the temperature monitoring model of the present application is a double-input channel model, each input channel corresponding to a monitoring mode. The first monitoring mode is that when the strain gauge sensor is in a normal working state, the corresponding thermal stress data is input to the temperature monitoring model through the first channel to obtain the temperature monitoring model output of the battery internal heating point temperature, so as to make a temperature high judgment. The second monitoring mode is that when the strain gauge sensor is abnormal, the battery internal temperature is derived based on the battery surface temperature obtained by the temperature sensor, that is, the corresponding surface temperature information is input to the temperature monitoring model through the second channel to obtain the battery heating point temperature output by the temperature monitoring model, so as to make a temperature high judgment, realizing the unified analysis of single network to multi-physical field coupling relationship.

[0050] S1330: In response to any second temperature value being greater than the temperature high alarm threshold, determining that the battery device temperature is abnormal.

[0051] That is, as long as there is any second temperature value greater than the temperature high alarm threshold, it is determined that the battery device temperature is abnormal.

[0052] In this embodiment, the internal temperature of the battery cell is monitored by the thermal stress data in the normal working state, and the internal temperature of the battery cell is automatically switched to the battery surface temperature when the fault occurs, realizing the multi-physical quantity fusion analysis and derivation, and guaranteeing the accuracy and timeliness of the internal temperature monitoring of the battery cell.

[0053] In an example embodiment, the temperature monitoring model comprises an input layer, a hidden layer and an output layer; the inputting of the cell surface temperature value through the second input channel into the temperature monitoring model to obtain the second temperature value of the cell module corresponding to the temperature monitoring module output by the temperature monitoring model comprises: based on the third weight matrix and the second threshold matrix corresponding to the output layer, the fourth weight matrix corresponding to the hidden layer, the cell surface temperature value is converted to obtain the second temperature value output by the output layer.

[0054] Exemplarily, referring to Figure 14 , the temperature monitoring model comprises an input layer, a hidden layer and an output layer, wherein the input layer comprises three neurons, and the three neurons correspond to collected data, time t and cell heat point coordinates x respectively, wherein in this embodiment, the collected data is the cell surface temperature value σ2, the time t is the current time, and the cell heat point coordinates x is the coordinate of one half of the cell height or other positions of the cell. The input layer is used to receive the cell surface temperature value and obtain the time t and the cell heat point coordinates x, and then multiply the cell surface temperature value σ2, the obtained time t and the cell heat point coordinates x by the corresponding third weight matrix W j2 = [W 2-1 W 2-2 W 2-3 ] h and the second threshold matrix b k2 = [b 2-1 b 2-2 ] h The cell surface temperature value σ2, the obtained time t and the cell heat point coordinates x are preliminarily converted, i.e. the cell surface temperature value σ2, the obtained time t and the cell heat point coordinates x are multiplied by the third weight matrix, and then a fixed offset value is added to each input data through the second threshold matrix to obtain the output result of the input layer. The output result is used as the input data of the hidden layer and is input into the hidden layer. The hidden layer comprises 4 layers, and each layer comprises 32 neurons. The hidden layer is used to derive the received data to obtain the first temperature value, and then output the second temperature value through the output layer comprising 1 neuron. g2 2-1 2-2 2-32 h

[0055] ​​​​​In an example embodiment, before the cell surface temperature value is input into the temperature monitoring model through the second input channel to obtain the second temperature value of the cell module corresponding to the temperature monitoring module output by the temperature monitoring model, the method further comprises: training the temperature monitoring model based on a second loss function to obtain the third weight matrix, the second threshold matrix and the fourth weight matrix, wherein the second loss function is composed of a first loss and a third loss, the first loss is composed of a heat conduction parameter in a thermal strain residual and a first weight value, and the third loss is composed of a data matching item and a third weight value, and the data matching item is used to clean sample data.

[0056] It can be understood that in the monitoring mode corresponding to the first input channel, the first loss function is composed of a first loss, a second loss and a third loss, the first loss is composed of a heat conduction parameter in a thermal strain residual and a first weight value, the second loss is composed of a thermal strain parameter in the thermal strain residual and a second weight value, and the third loss is composed of a data matching item and a third weight value, and the data matching item is used to clean sample data. In this embodiment, the second loss function is composed of the first loss and the third loss. That is, the thermal strain parameter in the thermal strain residual is not involved in the second loss function. The second loss function can be represented by the following formula:

[0057] wherein, is the first weight value, represents the heat conduction parameter in the thermal strain residual, is the third weight value, represents the data matching item.

[0058] In the training process, as shown in Figure 15 , the parameters = 1, = 1, , , , , α, , , f, and are brought into the second loss function to calculate the gradient of the loss function with respect to the network parameters ， ， . Wherein, represents the third weight matrix, represents the second threshold matrix, represents the fourth weight matrix. In an example embodiment, the Adam optimizer can be used to update the parameters along the negative gradient direction: W( ， ， ) ← W( ， ， )- η *

[0059] wherein, η is a learning rate, η = 0.5.

[0060] When the loss Loss2 of the model decreases stagnantly after multiple iterations, the pre-training is completed, and the temperature monitoring model is obtained. [w 2-1 w 2-2 w 2-3 ] h 、 [b 2-1 b 2-2 ] h 、 [c 2-1 c 2-2 ……c 2-32 ] h The optimal solution of the temperature monitoring model is obtained, so as to realize the mapping of the thermal stress to the temperature in the battery cell. When the pre-trained model is used, the thermal stress data obtained by sampling is input into the temperature monitoring model, and is multiplied with the third weight matrix [w 2-1 w 2-2 w 2-3 ] h , the second threshold matrix [b 2-1 b 2-2 ] h , and the fourth weight matrix [c 2-1 c 2-2 ……c 2-32 ] h of the hidden layer to obtain the temperature of the heating point of the battery cell.

[0061] In this embodiment, when the temperature in the battery cell-temperature on the surface of the battery cell data is analyzed, the data matching item and the heat conduction equation are used as the loss function, the battery cell surface temperature data collected by the temperature sensor is used as the training sample, and the battery cell internal temperature derived by the temperature monitoring model is used as the label to input the temperature monitoring model again, and the physical information and data characteristics of the battery cell surface temperature and the battery cell internal temperature represented by the third weight matrix, the second threshold matrix and the fourth weight matrix are trained.

[0062] The followingFigure 16 Another flowchart of the battery temperature monitoring method provided by the exemplary embodiments of the present application is shown, which is used to illustrate the above-mentioned embodiments. As shown in Figure 16 The method can include the following steps: S1610: collecting the thermal stress data of the battery cell in response to the strain gauge sensor being in the normal working state.

[0063] S1620: inputting the thermal stress data of the battery cell into the temperature monitoring model.

[0064] In an exemplary embodiment, the data input into the temperature monitoring model further includes the time and the coordinates of the heat point of the battery cell.

[0065] S1630: obtaining the first heat point temperature of the battery cell output by the temperature monitoring model.

[0066] S1640: determining whether the first heat point temperature of the battery cell is greater than the temperature alarm threshold of the battery cell.

[0067] If yes, go to S1650.

[0068] S1650: sending the high-temperature warning of the battery cell.

[0069] S1660: collecting the surface temperature of the battery cell by using the temperature sensor in response to the strain gauge sensor being in the abnormal state.

[0070] S1670: inputting the surface temperature of the battery cell into the temperature monitoring model.

[0071] In an exemplary embodiment, the data input into the temperature monitoring model further includes the time and the coordinates of the heat point of the battery cell.

[0072] S1680: obtaining the second heat point temperature of the battery cell output by the temperature monitoring model.

[0073] S1690: determining whether the first heat point temperature of the battery cell is greater than the temperature alarm threshold of the battery cell.

[0074] If yes, go to S1695.

[0075] S1695: sending the high-temperature warning of the battery cell.

[0076] As shown in Figure 17 The embodiments of the present application further provide an electronic device 1700, which includes a processor 1710 and a memory 1720, and the memory 1720 stores programs or instructions which can be run on the processor 1710, and the programs or instructions are executed by the processor 1710 to implement the above-mentioned Figures 10 to 16 The processes of the above-mentioned embodiments are implemented, and the same technical effects can be achieved. To avoid repetition, details are not described here.

[0077] The embodiment of the present application further provides a readable storage medium, wherein a program or instructions are stored on the readable storage medium, and the program or instructions are executed by a processor to implement the above-mentioned Figures 10 to 16 The various processes of the embodiments shown above can achieve the same technical effects, and thus, details are not described herein again.

[0078] The processor is the processor in the terminal in the above-mentioned embodiments. The readable storage medium can include a computer readable only memory (ROM), a random access memory (RAM), a magnetic disc or an optical disc, etc. In some examples, the readable storage medium can be a non-transitory computer readable storage medium.

[0079] The embodiment of the present application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used to run a program or instructions to implement the above-mentioned Figures 10 to 16 The various processes of the embodiments shown above can achieve the same technical effects, and thus, details are not described herein again.

[0080] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system chip, a system chip, a chip system or a system on chip, etc.

[0081] The embodiment of the present application further provides a computer program / program product, which comprises a computer program stored on a non-transitory computer readable storage medium, and the computer program comprises program instructions, and when the program instructions are executed by a computer, the computer is caused to implement the above-mentioned Figures 1 to 16 The various processes of the embodiments shown above can achieve the same technical effects, and thus, details are not described herein again.

[0082] It should be understood that, in this document, the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "comprises a" does not exclude the presence of additional identical elements in the process, method, article or device including the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to the order of performing the functions shown or discussed, and can also include performing the functions in a substantially simultaneous manner or in a reverse order, for example, the described method can be performed in an order different from the described order, and various steps can also be added, omitted or combined. In addition, the features described with reference to certain examples can be combined in other examples.

[0083] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of a computer software product and a general hardware platform as necessary, and of course can also be realized by hardware. The computer software product is stored in a storage medium (such as a ROM, a RAM, a magnetic disk, an optical disk, etc.), and includes a plurality of instructions for enabling a terminal or a network side device to execute the method described in each embodiment of the present application.

[0084] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the specific embodiments described above, and the specific embodiments described above are only illustrative but not restrictive. Those skilled in the art can make many forms of embodiments under the inspiration of the present application without departing from the scope of the present application and the scope protected by the claims.

Claims

1. A battery device, characterized in that, include: The encapsulation shell includes at least one battery cell module and at least one thermal stress monitoring module, wherein the battery cell module and the thermal stress monitoring module correspond one-to-one, with each battery cell module located below its corresponding thermal stress monitoring module. Each battery cell module includes x battery cells, and each thermal stress monitoring module includes two elastic connecting plates and a strain gauge sensor. The strain gauge sensor is bonded to the joint of the two elastic connecting plates, and each elastic connecting plate is bonded... The cell in question, where x is an integer greater than or equal to 2.

2. The battery device according to claim 1, characterized in that, The battery device further includes at least one set of temperature monitoring modules, wherein the temperature monitoring modules correspond one-to-one with the cell modules, and each temperature monitoring module includes at least one temperature sensor.

3. A battery temperature monitoring method, characterized in that, Applied to the battery device according to any one of claims 1-2, the method comprises: Acquire thermal stress data collected by strain gauge sensors in at least one thermal stress monitoring module; For the thermal stress data corresponding to each thermal stress monitoring module, the thermal stress data is input into the temperature monitoring model through the first input channel to obtain the first temperature value of the cell module corresponding to the thermal stress monitoring module output by the temperature monitoring model. In response to any of the first temperature values ​​being greater than the high temperature alarm threshold, the temperature of the battery device is determined to be abnormal.

4. The method according to claim 3, characterized in that, The temperature monitoring model includes an input layer, a hidden layer, and an output layer; the step of inputting the thermal stress data into the temperature monitoring model through the first input channel to obtain the first temperature value of the cell module corresponding to the thermal stress monitoring module output by the temperature monitoring model includes: The thermal stress data is transformed based on the first weight matrix and first threshold matrix corresponding to the input layer and the second weight matrix corresponding to the hidden layer to obtain the first temperature value output by the output layer.

5. The method according to claim 4, characterized in that, Before inputting the thermal stress data into the temperature monitoring model through the first input channel to obtain the first temperature value of the cell module corresponding to the thermal stress monitoring module output by the temperature monitoring model, the method further includes: The temperature monitoring model is trained based on the first loss function to obtain the first weight matrix, the first threshold matrix, and the second weight matrix. The first loss function consists of a first loss, a second loss, and a third loss. The first loss consists of the thermal conduction parameter in the thermal strain residual and the first weight. The second loss consists of the thermal strain parameter in the thermal strain residual and the second weight. The third loss consists of a data matching term and a third weight. The data matching term is used to clean the sample data.

6. The method according to claim 3, characterized in that, After acquiring the thermal stress data collected by the strain gauge sensors in each of the thermal stress monitoring modules, the method further includes: In response to invalid thermal stress data collected by the strain gauge sensor in each thermal stress monitoring module, the cell surface temperature value collected by the temperature sensor in each temperature monitoring module is obtained. For each temperature monitoring module, the cell surface temperature value is input into the temperature monitoring model through the second input channel to obtain the second temperature value of the cell module corresponding to the temperature monitoring module output by the temperature monitoring model. In response to any of the second temperature values ​​being greater than the high temperature alarm threshold, the temperature of the battery device is determined to be abnormal.

7. The method according to claim 6, characterized in that, The temperature monitoring model includes an input layer, a hidden layer, and an output layer; the step of inputting the cell surface temperature value into the temperature monitoring model through a second input channel to obtain the second temperature value of the cell module corresponding to the temperature monitoring module output by the temperature monitoring model includes: The surface temperature value of the battery cell is converted based on the third weight matrix and the second threshold matrix corresponding to the output layer and the fourth weight matrix corresponding to the hidden layer to obtain the second temperature value output by the output layer.

8. The method according to claim 7, characterized in that, Before inputting the cell surface temperature value into the temperature monitoring model through the second input channel to obtain the second temperature value of the cell module corresponding to the temperature monitoring module output by the temperature monitoring model, the method further includes: The temperature monitoring model is trained based on the second loss function to obtain the third weight matrix, the second threshold matrix, and the fourth weight matrix. The second loss function consists of the first loss and the third loss. The first loss consists of the thermal conduction parameter in the thermal strain residual and the first weight. The third loss consists of the data matching term and the third weight. The data matching term is used to clean the sample data.

9. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the battery temperature monitoring method as described in any one of claims 3-8.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the battery temperature monitoring method as described in any one of claims 3-8.

11. A computer program product, characterized in that, The computer program product includes program instructions that, when executed by a computer, cause the computer to perform the steps of the battery temperature monitoring method as described in any one of claims 3-8.

Images