Power battery module for new energy electric vehicle and cooling control method of power battery module

Abstract

The invention discloses a power battery module for a new energy electric vehicle and a cooling control method of the power battery module. The plurality of battery cell fixing positions are respectively arranged on the battery cell lower pressing plate at equal intervals in an array manner along the transverse direction and the longitudinal direction; one end of each battery cell is arranged on the corresponding battery cell fixing position in a matched manner; the water channel mechanism is arranged in a hole between two adjacent rows of battery cells and is in close contact with the battery cells, and the water channel is distributed in an S shape among the plurality of battery cells; the two connecting ports are respectively arranged at the two ends of the water channel in a communicating manner; and the battery cell upper pressing plate is arranged at the tops of the plurality of battery cells in a matching manner. The plurality of battery cells are integrated together, and the temperature of the battery cells is adjusted through the water channel mechanism, so that the problem of non-uniform local heat dissipation of the battery module is solved. The invention further discloses a cooling control method for the power battery module of the new energy electric vehicle.

Description

Technical Field

[0001] This invention relates to a power battery module for new energy electric vehicles and its cooling control method, belonging to the field of new energy electric vehicle technology. Background Technology

[0002] The power batteries used in electric vehicles are composed of multiple individual cells connected in series and parallel to form a battery pack, with the individual cells arranged closely together. During charging and discharging, the heat generated by each individual cell affects the others. If heat dissipation is uneven, the local temperature of the battery pack will rise rapidly, which will greatly affect the consistency of the batteries. In severe cases, it can cause thermal runaway of some individual cells, resulting in serious accidents.

[0003] Existing power battery cooling control methods are generally based on a limited number of temperature sensors, and only begin to adjust after the temperature reaches or exceeds a set threshold. When the local temperature suddenly rises abnormally, it cannot respond immediately. Summary of the Invention

[0004] This invention designs and develops a power battery module for new energy electric vehicles, which integrates multiple battery cells together and uses a water channel mechanism to regulate their temperature, thus overcoming the problem of uneven heat dissipation in local areas of the battery module.

[0005] This invention also designs and develops a cooling control method for power battery modules of new energy electric vehicles. Based on graph attention network, a coupling relationship between cells and water channels is established to control the temperature of the battery module and improve the stability and safety performance of the power battery module.

[0006] The technical solution provided by this invention is as follows: A power battery module for new energy electric vehicles and its cooling control method, comprising: Cell lower pressure plate; Multiple cell fixing positions are arranged in an array at equal intervals along the horizontal and vertical directions on the cell lower pressure plate; Multiple battery cells, one end of which is respectively matched and disposed at the battery cell fixing position; The water channel mechanism is set in the gap between two adjacent rows of battery cells and is in close contact with the battery cells. The water channel is distributed in an S-shape among multiple battery cells. Two connection ports are respectively connected to the two ends of the waterway; A cell pressure plate is matched and disposed on top of the plurality of cells.

[0007] Preferably, it also includes: A copper busbar lower pressure plate is disposed on the upper pressure plate of the battery cell; A copper busbar, which is mounted on the lower pressure plate of the copper busbar; A pressure plate is installed on the copper busbar.

[0008] Preferably, it also includes: The upper cover plate is disposed on the upper pressure plate of the copper busbar; The lower tray is located at the bottom of the cell lower pressure plate; The outer frame is a cuboid structure, including four sides connected in sequence; the outer frame is disposed outside the plurality of battery cells and matches the upper cover plate and the lower tray to form a cuboid outer shell.

[0009] Preferably, the waterway mechanism includes: waterway; Water channel rubber, which is disposed outside the water channel, the water channel rubber has a continuous S-shaped structure and is matched with the plurality of battery cells; Two water pipe heads are respectively matched and installed at both ends of the waterway.

[0010] A cooling control method for a power battery module for new energy electric vehicles, characterized in that the power battery module for new energy electric vehicles includes: Step 1: Establish a graph model of the battery module, with each cell as a graph node and the heat conduction and water channel coupling relationships between cells as graph edges; Step 2: Collect the temperature of the battery cells according to the sampling period, extract the temporal features of each battery cell based on the temporal convolutional network, and use the graph attention network to aggregate the spatial thermal correlation features between the battery cells; based on the fused spatiotemporal features, predict the temperature change sequence of each battery cell in the next period. Step 3: Based on the predicted changes in cell temperature, construct a cooling control optimization model; ; In the formula, For the first The predicted average temperature The target temperature is set to 25℃. For the first The maximum temperature difference predicted in the step. This is for controlling the coolant flow rate. , , These are the weighting coefficients; Step 4: Based on the cooling control optimization model, obtain the optimal coolant flow rate sequence; Execute the first control variable in the optimal cooling flow sequence and perform rolling optimization control; Step 5: When the temperature of any cell is detected to be higher than the set safe temperature, the maximum cooling flow rate is used.

[0011] Preferably, the temporal convolutional network in step two employs multi-scale dilated causal convolution, and its first... Layer output features The calculation formula is: ; In the formula, It is a linear rectified activation function. For weighted indexes, For the first kernel size of each layer For the first The first layer of convolution kernel Each weight represents a convolution operation. for Layered networks in The output features calculated at each time step, For the first The expansion factor of the layer For the first The layer bias term is the current time index.

[0012] Preferably, in step two, the formula for calculating the attention coefficient of the graph attention network is: ; In the formula, It is a linear rectifier unit with leakage. For attention weight vectors, For transpose, The feature transformation weight matrix, , , For node feature vectors, For structural prior fusion coefficients, For structural prior weights, For nodes The set of neighbors.

[0013] Preferably, the constraint condition in step three is: ; ; ; In the formula, In time step For the Predicted temperature value for each battery cell For the current moment, To predict the number of steps, , For cell numbering, , The maximum safe temperature is set at 50℃. The maximum allowable temperature difference is set at 10℃. As the minimum allowable quantity, This is the maximum allowed amount.

[0014] The beneficial effects of the present invention are as follows: The power battery module for new energy electric vehicles provided by the present invention integrates multiple battery cells on the lower pressure plate through cooperation between the lower pressure plate and the battery cell fixing position, and cooperates with the water channel mechanism through the multiple battery cells to regulate the temperature of the battery cells during charging and discharging, so as to prevent safety accidents caused by excessive local temperature of the battery cells and improve battery life.

[0015] The cooling control method for the power battery module of new energy electric vehicles provided by this invention establishes the coupling relationship between the cells and the water channel based on the graph attention network. It can obtain the temperature of individual cells in a timely manner and obtain the temperature change trend over time by the charging and discharging heating rate. It can promptly investigate local temperature anomalies in the power battery module, realize timely heat dissipation of local abnormal temperature areas, prevent accidents caused by untimely heat dissipation, and improve the safety performance and service life of the power battery module. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of the power battery module for new energy electric vehicles according to the present invention.

[0017] Figure 2 This is a front view of the power battery module for new energy electric vehicles according to the present invention.

[0018] Figure 3 This is a rear view of the power battery module for new energy electric vehicles according to the present invention.

[0019] Figure 4 This is a top view of the power battery module for new energy electric vehicles described in this invention.

[0020] Figure 5 This is a left view of the power battery module for new energy electric vehicles according to the present invention.

[0021] Figure 6 This is a right view of the power battery module for new energy electric vehicles described in this invention.

[0022] Figure 7 for Figure 1 A magnified view of a section at point I.

[0023] Figure 8 for Figure 3 A magnified view of section II in the middle.

[0024] Figure 9 for Figure 4 A magnified view of section III in the middle.

[0025] Figure 10 for Figure 6 A magnified view of section IV in the middle.

[0026] Figure 11 This is a schematic diagram of the cell pressure plate structure for the power battery module used in new energy electric vehicles according to the present invention.

[0027] Figure 12 for Figure 11 A magnified view of the middle V section.

[0028] Figure 13 This is a schematic diagram of the cooling pipes for the power battery module used in new energy electric vehicles according to the present invention. Detailed Implementation

[0029] The present invention will now be described in further detail with reference to the accompanying drawings, so that those skilled in the art can implement it based on the description.

[0030] like Figure 1-13 As shown, the present invention provides a power battery module for new energy electric vehicles, including: an upper cover plate 1, a copper busbar upper pressure plate 2, a water channel 3, a water channel pipe head 4, a copper busbar 5, an outer frame 6, a water channel outer rubber 7, a battery cell 8, a battery cell empty space 9, a lower tray 10, a copper busbar lower pressure plate 11, a welding column 12, a battery cell upper pressure plate 13, and a battery cell lower pressure plate 14.

[0031] A lower pressure plate 14 for the battery cells is placed horizontally. Multiple battery cell fixing positions are evenly spaced along the horizontal and vertical directions on the lower pressure plate 14, arranged in an array to fix each battery cell of the battery module. There are gaps between adjacent battery cells 8, and elongated gaps are formed between adjacent rows of battery cells 8 to accommodate a water channel mechanism. The water channel mechanism can make close contact with the battery cells 8. Between the elongated gaps formed by multiple rows of battery cells 8, the water channel mechanism is distributed in a continuous S-shape, including horizontally or vertically. A higher pressure plate 13 for the battery cells 8 is fitted on top of each battery cell 8.

[0032] A copper busbar lower pressure plate 11, a copper busbar 5, and a copper busbar upper pressure plate 2 are sequentially arranged on the upper pressure plate 13 of the battery cell. The upper cover plate 1 is arranged on the upper pressure plate 2 of the copper busbar. The lower tray 10 is arranged at the bottom of the lower pressure plate 14 of the battery cell and is arranged opposite to the upper cover plate 1. The outer frame 6 is a cuboid structure, including four sides connected in sequence. The outer frame 6 is arranged outside the multiple battery cells 8 and matches the upper cover plate and the lower tray to form a cuboid outer shell.

[0033] The water channel mechanism includes a water channel 3 and an outer rubber 7 that surrounds the water channel. Two connecting pipes 4 are respectively connected to the two ends of the water channel 3 for connecting components such as coolant and flow valve. The flow valve controls the flow rate of the coolant, thereby adjusting the temperature of the battery cell.

[0034] During installation, the lower pressure plate 14 of the battery cell is fixed on the lower tray 0 with the battery cell fixing position 9 facing upwards. One end of the battery cell 8 is placed in the battery cell fixing position 9 in sequence, ensuring that the battery cell 8 is vertically positioned. The water channel mechanism is set along the long gap between two adjacent rows of battery cells 8, so that it is in close contact with the battery cell 8, and is distributed in a continuous S-shaped structure. The upper pressure plate 13 of the battery cell is set on top of the battery cell 8 and matched with the lower pressure plate 14 of the battery cell to axially press the battery cell 8. The lower pressure plate 11 of the copper busbar, the copper busbar 5, and the upper pressure plate 13 of the copper busbar are placed on top of the upper pressure plate 13 of the battery cell in sequence and fixed with multiple bolts to form a copper busbar mechanism, ensuring that the copper busbar 5 is in contact with the terminal post of the battery cell 8. At the same time, the outer frame 6 is set on the outside of multiple battery cells 8, and the bottom of the outer frame 6 is aligned with the lower tray 10 and fixed by welding through welding posts. The upper cover plate 1 set on top is fixed to the outer frame with multiple bolts, completing the assembly of the entire battery module.

[0035] This invention also provides a cooling control method for a power battery module for new energy electric vehicles, using the power battery module for new energy electric vehicles provided by this invention, comprising: Step 1: Establish a graph model of the battery module, with each cell as a graph node and the heat conduction and water channel coupling relationships between cells as graph edges; Step 2: Collect the temperature of the battery cells according to the sampling period, extract the temporal features of each battery cell based on the temporal convolutional network, and use the graph attention network to aggregate the spatial thermal correlation features between the battery cells; based on the fused spatiotemporal features, predict the temperature change sequence of each battery cell in the next period. The temporal convolutional network employs multi-scale dilated causal convolution, and the formula for calculating the output features of its i-th layer is as follows: ; In the formula, It is a linear rectified activation function. For weighted indexes, For the first kernel size of each layer For the first The first layer of convolution kernel Each weight represents a convolution operation. for Layered networks in The output features calculated at each time step, For the first The expansion factor of the layer For the first The layer bias term is the current time index.

[0036] The formula for calculating the attention coefficient of a graph attention network is: ; In the formula, It is a linear rectifier unit with leakage. For attention weight vectors, For transpose, The feature transformation weight matrix, , , For node feature vectors, For structural prior fusion coefficients, For structural prior weights, For nodes The set of neighbors.

[0037] Step 3: Based on the predicted changes in cell temperature, construct a cooling control optimization model; ; In the formula, For the first The predicted average temperature The target temperature is set to 25℃. For the first The maximum temperature difference predicted in the step. This is for controlling the coolant flow rate. , , These are the weighting coefficients; The calculation formula is:

[0038] For temperature tracking weights, Temperature difference control weight, As energy consumption penalty weight, ; The constraints are: ; ; ; In the formula, In time step For the Predicted temperature value for each battery cell For the current moment, To predict the number of steps, , For cell numbering, , The maximum safe temperature is set at 50℃. The maximum allowable temperature difference is set at 10℃. As the minimum allowable quantity, This is the maximum allowed amount.

[0039] Step 4: Based on the cooling control optimization model, obtain the optimal coolant flow rate sequence; Execute the first control variable in the optimal cooling flow sequence and perform rolling optimization control; Step 5: When the temperature of any cell is detected to be higher than the set safe temperature, the maximum cooling flow rate is used.

[0040] Example

[0041] The battery consists of 36 ternary lithium battery cells, each with a capacity of 2.5Ah and a voltage of 3.7V. One end of each cell is interference-fitted with the cell fixing position, and the cell lower pressure plate 14 is integrally formed from flame-retardant material.

[0042] The 36 battery cells are numbered from 1 to 36 and used as 36 nodes in the graph model. The thermal conduction relationship between any two adjacent battery cells is used as an undirected graph edge, and the coupling relationship between each battery cell and the adjacent water channel is used as a directed graph edge.

[0043] The edge weights of the graph are: Weight of thermal conduction sides between battery cells: ; In the formula, The thermal conductivity of the battery cell is taken as 385 W / (mK). For the first The first cell and the first The center-to-center spacing of each cell is 0.025m. Calculations show that... =15400; Cell and water channel coupling side weight ; In the formula, is the thermal conductivity of the rubber outside the waterway, which is taken as 0.4 W / (mK). For the first The contact area between each battery cell and the waterway is taken as 0.012m². 2 Calculated =0.0048.

[0044] The weights of the graph edges are updated according to the working status of the battery cell, with an update cycle of 5 seconds.

[0045] The sampling period is set to 5 seconds. The actual temperature of each cell is collected by the temperature sensor corresponding to each cell. The data is collected continuously for 20 cycles and used as training samples. After collecting 20 cycles, the temperature data is updated every 5 seconds.

[0046] Based on a temporal convolutional network and employing a multi-scale dilated causal convolutional structure, the number of network layers is set to 4. The features extracted by the temporal convolutional network are input into the graph attention network to aggregate the thermal impact features of adjacent cells. Output the temperature prediction sequence of each cell for the next 10 cycles.

[0047] Construct a cooling control optimization model; ; In the formula, For the first The predicted average temperature The target temperature is set to 25℃. For the first The maximum temperature difference predicted in the step. For coolant flow control, set =0.6, =0.3, =0.1; The constraints are: ; ; ; The gradient descent method was used to solve the cooling control optimization model, with a learning rate of 0.001, 1000 iterations, and a solution accuracy controlled within ±0.1 L / min. The optimal coolant flow rate sequence for the next 10 sampling periods was obtained. ; Execute the first control variable in the optimal flow sequence. The system controls the operation of the cooling system water pump. After each sampling cycle, it updates the actual temperature data of the previous cycle, re-executes the previous steps (steps two to four), generates a new optimal flow sequence, and executes the first control variable of the new sequence to achieve rolling optimization control.

[0048] When the temperature sensor detects that the actual temperature of any cell is greater than or equal to 50°C, the water channel mechanism immediately switches to maximum cooling flow until the temperature of all cells is less than 50°C.

[0049] The following tests were conducted at an ambient temperature of 25℃:

[0050] As shown in Table 1, the cooling control method provided by this invention can maintain the average temperature of the battery cells close to the target value and reduce the temperature difference within the module, ensuring continuous temperature consistency. Simultaneously, while maintaining temperature consistency, the coolant flow rate is reduced by approximately 26%, thus reducing system energy consumption.

[0051] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

Claims

1. A power battery module for new energy electric vehicles, characterized in that, include: Cell lower pressure plate; Multiple cell fixing positions are arranged in an array at equal intervals along the horizontal and vertical directions on the cell lower pressure plate; Multiple battery cells, one end of which is respectively matched and disposed at the battery cell fixing position; The water channel mechanism is set in the gap between two adjacent rows of battery cells and is in close contact with the battery cells. The water channel is distributed in an S-shape among multiple battery cells. Two connection ports are respectively connected to the two ends of the waterway; A cell pressure plate is matched and disposed on top of the plurality of cells.

2. The power battery module for new energy electric vehicles according to claim 1, characterized in that, Also includes: A copper busbar lower pressure plate is disposed on the upper pressure plate of the battery cell; A copper busbar, which is mounted on the lower pressure plate of the copper busbar; A pressure plate is installed on the copper busbar.

3. The power battery module for new energy electric vehicles according to claim 2, characterized in that, Also includes: The upper cover plate is disposed on the upper pressure plate of the copper busbar; The lower tray is located at the bottom of the cell lower pressure plate; The outer frame is a cuboid structure, including four sides connected in sequence; the outer frame is disposed outside the plurality of battery cells and matches the upper cover plate and the lower tray to form a cuboid outer shell.

4. The power battery module for new energy electric vehicles according to claim 3, characterized in that, The waterway mechanism includes: waterway; Water channel rubber, which is disposed outside the water channel, the water channel rubber has a continuous S-shaped structure and is matched with the plurality of battery cells; Two water pipe heads are respectively matched and installed at both ends of the waterway.

5. A cooling control method for a power battery module in a new energy electric vehicle, characterized in that, The power battery module for new energy electric vehicles according to any one of claims 1-4 includes: Step 1: Establish a graph model of the battery module, with each cell as a graph node and the heat conduction and water channel coupling relationships between cells as graph edges; Step 2: Collect the temperature of the battery cells according to the sampling period, extract the temporal features of each battery cell based on the temporal convolutional network, and use the graph attention network to aggregate the spatial thermal correlation features between the battery cells; based on the fused spatiotemporal features, predict the temperature change sequence of each battery cell in the next period. Step 3: Based on the predicted changes in cell temperature, construct a cooling control optimization model; ； In the formula, For the first The predicted average temperature The target temperature is set to 25℃. For the first The maximum temperature difference predicted in the step. This is for controlling the coolant flow rate. , , These are the weighting coefficients; Step 4: Based on the cooling control optimization model, obtain the optimal coolant flow rate sequence; Execute the first control variable in the optimal cooling flow sequence and perform rolling optimization control; Step 5: When the temperature of any cell is detected to be higher than the set safe temperature, the maximum cooling flow rate is used.

6. The cooling control method for a power battery module in a new energy electric vehicle according to claim 5, characterized in that, In step two, the temporal convolutional network employs multi-scale dilated causal convolution, the first of which... Layer output features The calculation formula is: ； In the formula, It is a linear rectified activation function. For weighted indexes, For the first kernel size of each layer For the first The first layer of convolution kernel Each weight represents a convolution operation. for Layered networks in The output features calculated at each time step, For the first The expansion factor of the layer For the first The layer bias term is the current time index.

7. The cooling control method for a power battery module in a new energy electric vehicle according to claim 6, characterized in that, In step two, the formula for calculating the attention coefficient of the graph attention network is: ； In the formula, It is a linear rectifier unit with leakage. For attention weight vectors, For transpose, The feature transformation weight matrix, , , For node feature vectors, For structural prior fusion coefficients, For structural prior weights, For nodes The set of neighbors.

8. The cooling control method for a power battery module in a new energy electric vehicle according to claim 5, characterized in that, The constraints in step three are as follows: ； ； ； In the formula, In time step For the Predicted temperature value for each battery cell For the current moment, To predict the number of steps, , For cell numbering, , The maximum safe temperature is set at 50℃. The maximum allowable temperature difference is set at 10℃. As the minimum allowable quantity, This is the maximum allowed amount.

Images