Battery assembly method and system

Abstract

The present invention discloses a battery grouping method and system, which relates to the field of battery technology. The method obtains the number of battery groups and the total number of batteries, and constructs an initial quantum group based on the number of battery groups and the total number of batteries. Each quantum bit in the initial quantum group corresponds to a battery. When the quantum bit corresponding to a battery is a preset reference bit, the battery is determined as a target battery. The state of each target battery is evaluated to obtain the state parameters corresponding to each target battery. Based on a quantum optimization algorithm, the initial quantum group is optimized according to a preset grouping evaluation function and each state parameter to obtain the corresponding grouping result. This solves the problem that the existing technology mainly relies on the factory static parameters of the battery for battery grouping. However, the static parameters cannot reflect the dynamic characteristics of the battery and the environmental adaptability during the grouping process, making it difficult to predict the performance of the battery under actual working conditions, thereby reducing the reliability of the battery grouping.

Description

Technical Field

[0001] The present invention relates to the technical field of storage batteries, and in particular to a storage battery assembly method and system. Background Art

[0002] As the sole backup power source for DC systems, the performance of battery packs directly impacts the reliability of the power system's safety net. In the event of an AC power outage, the battery pack must immediately assume the entire DC load, providing continuous, stable power to protection and control equipment until AC power is restored or the system safely shuts down. Currently, existing battery packs typically consist of multiple batteries connected in series or parallel. However, batteries inevitably vary during transportation, manufacturing, initial performance, and operational aging. Therefore, selecting the right battery from a variety of batteries for assembly is crucial.

[0003] At present, existing technologies mainly rely on the factory static parameters of batteries (such as open circuit voltage and nominal capacity) for battery matching. However, static parameters cannot reflect the dynamic characteristics of batteries and the environmental adaptability during the matching process. It is difficult to predict the performance of batteries under actual working conditions, which reduces the reliability of battery matching. Summary of the Invention

[0004] The present invention provides a battery grouping method and system, which solves the technical problem that the existing technology mainly relies on the factory static parameters of the battery for battery grouping, but the static parameters cannot reflect the dynamic characteristics of the battery and the environmental adaptability during the grouping process, making it difficult to predict the performance of the battery under actual working conditions, thereby reducing the reliability of the battery grouping.

[0005] A first aspect of the present invention provides a method for assembling batteries, comprising:

[0006] Obtaining the number of battery groups and the total number of batteries, and constructing an initial quantum group based on the number of battery groups and the total number of batteries, wherein each quantum bit of the initial quantum group corresponds to a battery;

[0007] When the quantum bit corresponding to the battery is a preset reference bit, the battery is determined as a target battery;

[0008] Performing a status evaluation on each of the target batteries to obtain a status parameter corresponding to each of the target batteries;

[0009] Based on the quantum optimization algorithm, the initial quantum group is optimized according to the preset grouping evaluation function and each of the state parameters to obtain the corresponding grouping result.

[0010] Optionally, the step of performing status evaluation on each of the target batteries to obtain status parameters corresponding to each of the target batteries includes:

[0011] Ratio processing is performed on the battery capacity corresponding to each target battery to the rated capacity to obtain multiple battery health values;

[0012] Inputting the operating condition parameters of each target battery into a pre-trained remaining power detection model to obtain multiple remaining power values;

[0013] performing ratio processing on the output power and input power of each target battery to obtain a plurality of charge and discharge efficiency values;

[0014] Performing path safety assessment on the transport parameters of each target battery to obtain multiple path safety assessment values;

[0015] The transport parameter, path safety assessment value, battery health value, remaining power value and charge / discharge efficiency value corresponding to each target battery are respectively determined as the state parameters corresponding to each target battery.

[0016] Optionally, the step of optimizing the initial quantum group based on a quantum optimization algorithm according to a preset grouping evaluation function and each of the state parameters to obtain a corresponding grouping result includes:

[0017] Inputting each of the state parameters into a preset grouping evaluation function to obtain a corresponding grouping evaluation value;

[0018] Updating the initial quantum group according to the pairing evaluation value to obtain an updated quantum group;

[0019] Determining whether the update number of the updated quantum group is greater than or equal to a preset iteration threshold;

[0020] If the update number is less than the iteration threshold, the updated quantum group is used as a new initial quantum group, and the step of determining the battery as a target battery when the quantum bit corresponding to the battery is a preset reference bit is skipped and executed;

[0021] If the number of updates is greater than or equal to the iteration threshold, the updated quantum group corresponding to the maximum value of each pairing evaluation value is selected as the target quantum group;

[0022] The battery grouping corresponding to the target quantum group is taken as the corresponding grouping result.

[0023] Optionally, the transport parameters include path complexity, multiple angle change values, path length, and the number of obstacles. The step of performing path safety assessment on the transport parameters of each target battery to obtain multiple path safety assessment values ​​includes:

[0024] respectively summing up the absolute values ​​of the angle change values ​​corresponding to the target batteries to obtain a plurality of first sum values;

[0025] Based on a preset transfer weight, weighted operations are performed on the path complexity and the first sum value corresponding to each target battery to obtain multiple transfer difficulty values;

[0026] Multiplying the path length, the number of obstacles, and the transport difficulty value corresponding to each target battery respectively to obtain a plurality of first multiplied values;

[0027] The preset transfer reference value is respectively compared with each of the first multiplication values ​​to obtain a plurality of path safety assessment values.

[0028] Optionally, the training process of the remaining power detection model is specifically as follows:

[0029] Acquire multiple training battery operating condition parameters, perform data preprocessing on each of the training battery operating condition parameters, and generate a battery feature set;

[0030] Using the battery feature set to input a preset initial remaining power detection model for training, and outputting training remaining power data;

[0031] Calculating a training loss function value of the battery feature set based on the training remaining power data based on a mean square error function;

[0032] When the training loss function value is greater than or equal to a preset standard loss function value, the network parameters of the initial remaining power detection model are adjusted, and the process jumps to executing the step of using the battery feature set to input the preset initial remaining power detection model for training and outputting training remaining power data, until the training loss function value is less than the standard loss function value;

[0033] When the training loss function value is less than the standard loss function value, a remaining power detection model is generated.

[0034] Optionally, the pairing evaluation function is specifically:

[0035] ;

[0036] in, is the group evaluation value, is the evaluation value of the i-th target battery, is the battery health value of the i-th target battery, is the remaining power value of the i-th target battery, is the charge and discharge efficiency value of the i-th target battery, is the path safety assessment value of the i-th target battery, is the collision safety value, is the first evaluation weight coefficient, is the second evaluation weight coefficient, is the third evaluation weight coefficient, is the fourth evaluation weight coefficient, is the fifth evaluation weight coefficient, is the first collision safety factor, is the second collision safety factor, is the third collision safety factor, is the degree of path intersection, is the path complexity between the i-th target battery and the j-th target battery, is the operating speed of the i-th target battery and the j-th target battery, is the length of the overlap between the i-th target battery and the j-th target battery, is the total path length between the i-th target battery and the j-th target battery, i is the first index of the target battery, j is the second index of the target battery, and M is the total number of target batteries.

[0037] A second aspect of the present invention provides a battery assembly system, comprising:

[0038] a construction module, configured to obtain the number of battery groups and the total number of batteries, and construct an initial quantum group according to the number of battery groups and the total number of batteries, wherein each quantum bit of the initial quantum group corresponds to a battery;

[0039] a detection module, configured to determine the battery as a target battery when the quantum bit corresponding to the battery is a preset reference bit;

[0040] An evaluation module, configured to perform a status evaluation on each of the target batteries to obtain a status parameter corresponding to each of the target batteries;

[0041] The optimization module is used to optimize the initial quantum group based on the quantum optimization algorithm according to the preset grouping evaluation function and each state parameter to obtain the corresponding grouping result.

[0042] A third aspect of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the battery pairing method as described in any one of the above items.

[0043] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the battery grouping method as described in any one of the above items.

[0044] A fifth aspect of the present invention provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the battery pairing method as described in any one of the above items.

[0045] It can be seen from the above technical solutions that the present invention has the following advantages:

[0046] The present invention obtains the number of battery groups and the total number of batteries and constructs an initial quantum group based on the number of battery groups and the total number of batteries. Each qubit in the initial quantum group corresponds to a battery. When the qubit corresponding to a battery is a preset reference bit, the battery is identified as a target battery. A state assessment is performed on each target battery to obtain state parameters corresponding to each target battery. Based on a quantum optimization algorithm, the initial quantum group is optimized according to a preset grouping evaluation function and each state parameter to obtain the corresponding grouping result. This overcomes the existing practice of relying primarily on factory static parameters for battery grouping. However, these static parameters fail to reflect the dynamic characteristics of the battery and its environmental adaptability during the grouping process, making it difficult to predict the battery's performance under actual operating conditions and reducing the reliability of the battery grouping. Compared to traditional battery grouping methods, the present invention performs a state assessment on each target battery to obtain state parameters reflecting the battery's dynamic characteristics and environmental adaptability. Based on a quantum optimization algorithm, the initial quantum group is optimized according to a preset grouping evaluation function and each state parameter to obtain the optimal grouping result, thereby improving the reliability of the battery grouping. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 A flowchart of the steps of a battery packing method provided in Example 1 of the present invention;

[0049] Figure 2 A flowchart of the steps of a battery packing method provided in the second embodiment of the present invention;

[0050] Figure 3 This is a structural block diagram of a battery packing system provided in Example 3 of the present invention;

[0051] Figure 4This is a structural block diagram of an electronic device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0052] Embodiments of the present invention provide a battery grouping method and system for resolving the technical problem that the prior art mainly relies on the factory static parameters of the battery for battery grouping, but the static parameters cannot reflect the dynamic characteristics of the battery and the environmental adaptability during the grouping process, making it difficult to predict the performance of the battery under actual working conditions, thereby reducing the reliability of the battery grouping.

[0053] In order to make the purpose, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 , Figure 1 This is a flowchart of the steps of a battery assembly method provided in Example 1 of the present invention.

[0055] The present invention provides a battery assembly method, comprising:

[0056] Step 101: Obtain the number of battery groups and the total number of batteries, and construct an initial quantum group based on the number of battery groups and the total number of batteries, wherein each quantum bit of the initial quantum group corresponds to a battery.

[0057] The number of battery packs refers to the total number of batteries in the battery pack that needs to be assembled.

[0058] In this embodiment of the present invention, when the number of battery groups and the total number of batteries are received, an initial quantum group is constructed based on the number of battery groups and the total number of batteries, where each qubit in the initial quantum group corresponds to a battery. For example, if the total number of batteries is 20 and the number of battery groups is 3, then the total number of qubits in the constructed initial quantum group is 20, of which 3 qubits have a quantum state of 1.

[0059] Step 102: When the quantum bit corresponding to the battery is a preset reference bit, the battery is determined as a target battery.

[0060] The reference bit refers to the quantum bit whose quantum state is 1.

[0061] The target battery refers to a battery selected from multiple batteries.

[0062] In an embodiment of the present invention, when the quantum state of the quantum bit corresponding to the battery is 1, the battery is determined as the target battery.

[0063] Step 103: Perform status evaluation on each target battery to obtain status parameters corresponding to each target battery.

[0064] Status parameters refer to quantitative indicators used to evaluate the reliability of battery packs, including but not limited to transportation parameters, path safety assessment values, battery health values, remaining power values, and charge and discharge efficiency values.

[0065] In an embodiment of the present invention, the battery capacity and rated capacity corresponding to each target battery are input into a preset battery health function to obtain multiple battery health values. The operating condition parameters of each target battery are input into a pre-trained remaining capacity detection model to obtain multiple remaining capacity values. The output power and input power of each target battery are input into a preset charge-discharge efficiency function to obtain multiple charge-discharge efficiency values. The transport parameters of each target battery are input into a preset route safety assessment function to obtain multiple route safety assessment values. The transport parameters, route safety assessment value, battery health value, remaining capacity value, and charge-discharge efficiency value corresponding to each target battery are determined as the state parameters corresponding to each target battery.

[0066] It should be noted that the battery health function is specifically:

[0067] ;

[0068] in, is the battery capacity of the i-th target battery, is the rated capacity of the i-th target battery, is the battery health value of the i-th target battery.

[0069] The specific charge and discharge efficiency function is:

[0070] ;

[0071] in, is the charge and discharge efficiency value of the i-th target battery, is the output power of the i-th target battery, is the input power of the i-th target battery.

[0072] The path safety evaluation function is specifically:

[0073] ;

[0074] in, is the path length of the i-th target battery, is the number of obstacles of the i-th target battery, is the difficulty value of transporting the i-th target battery, is the path complexity of the i-th target battery, is the kth angle change value in the i-th target battery, is the first transport weight coefficient, is the second transport weight coefficient, n is the total number of angle change values, k is the index of the angle change value, is the path safety assessment value of the i-th target battery.

[0075] It should be noted that the path safety assessment function and battery health function are dimensionless calculations.

[0076] Step 104: Based on the quantum optimization algorithm, the initial quantum group is optimized according to the preset grouping evaluation function and various state parameters to obtain the corresponding grouping result.

[0077] In an embodiment of the present invention, each state parameter is input into a preset grouping evaluation function to obtain a corresponding grouping evaluation value. The initial quantum group is updated based on the grouping evaluation value to obtain an updated quantum group. A determination is made as to whether the number of updates to the updated quantum group is greater than or equal to a preset iteration threshold. If the number of updates is less than the iteration threshold, the updated quantum group is used as the new initial quantum group, and the process jumps to the step of determining the battery as a target battery when the quantum bit corresponding to the battery is a preset reference bit. If the number of updates is greater than or equal to the iteration threshold, the updated quantum group corresponding to the maximum value among the grouping evaluation values ​​is selected as the target quantum group. The battery group corresponding to the target quantum group is used as the corresponding grouping result.

[0078] It is worth noting that, as shown in Tables 1 and 2, the computation time and storage space occupied by the exhaustive algorithm in the present invention, under the same group evaluation function, increase exponentially with the number of battery groups, demonstrating the high complexity and low efficiency of the exhaustive algorithm. The A* algorithm is faster, but its complexity continues to increase: compared to the exhaustive algorithm, the A* algorithm is more efficient, but its computation time and storage space usage also increase rapidly with the number of battery groups. In contrast, the computation time and storage space occupied by the quantum optimization algorithm show a slow but steady increase with the number of battery groups. The quantum optimization algorithm is more reliable than both the A* and exhaustive algorithms.

[0079] Table 1

[0080]

[0081] Table 2

[0082]

[0083] In an embodiment of the present invention, an initial quantum group is constructed based on the number of battery groups and the total number of batteries. Each qubit in the initial quantum group corresponds to a battery. When the qubit corresponding to a battery is a preset reference bit, the battery is identified as a target battery. A state assessment is performed on each target battery to obtain state parameters corresponding to each target battery. Based on a quantum optimization algorithm, the initial quantum group is optimized according to a preset grouping evaluation function and each state parameter to obtain the corresponding grouping result. This overcomes the existing practice of relying primarily on the factory static parameters of batteries for battery grouping. However, these static parameters cannot reflect the dynamic characteristics of the batteries or the environmental adaptability during the grouping process, making it difficult to predict the battery's performance under actual operating conditions and reducing the reliability of battery grouping. Compared to traditional battery grouping methods, the present invention performs a state assessment on each target battery to obtain state parameters reflecting the battery's dynamic characteristics and environmental adaptability. Based on a quantum optimization algorithm, the initial quantum group is optimized according to the preset grouping evaluation function and each state parameter to obtain the optimal grouping result, thereby improving the reliability of battery grouping.

[0084] See also Figure 2 , Figure 2 This is a flowchart of the steps of a battery assembly method provided in Example 2 of the present invention.

[0085] The present invention provides a battery assembly method, comprising:

[0086] Step 201: Obtain the number of battery groups and the total number of batteries, and construct an initial quantum group based on the number of battery groups and the total number of batteries, wherein each quantum bit of the initial quantum group corresponds to a battery.

[0087] In this embodiment of the present invention, the number of battery groups and the total number of batteries are obtained, and an initial quantum group is constructed based on the total number of batteries and the number of battery groups, where each qubit in the initial quantum group corresponds to a battery. For example, if the total number of batteries is 40 and the number of battery groups is 4, the total number of qubits in the constructed initial quantum group is 40, of which 4 have a quantum state of 1.

[0088] Step 202: When the quantum bit corresponding to the battery is a preset reference bit, the battery is determined as a target battery.

[0089] In an embodiment of the present invention, the quantum state of the quantum bit corresponding to the battery is measured, and when the quantum state is 1, the battery is determined to be a target battery.

[0090] It is worth mentioning that when the quantum state of the qubit corresponding to the battery is 1, it means that the battery is selected as the paired battery. When the quantum state of the qubit corresponding to the battery is 0, it means that the battery is not selected as the paired battery.

[0091] Step 203: Perform status evaluation on each target battery to obtain status parameters corresponding to each target battery.

[0092] Furthermore, step 203 includes the following sub-steps:

[0093] S11. Ratio processing is performed on the battery capacity corresponding to each target battery and the rated capacity to obtain multiple battery health values.

[0094] Battery health value refers to the value used to quantify the degree of attenuation of the battery's current performance relative to its initial performance, reflecting the battery's aging state and remaining life.

[0095] Battery capacity refers to the actual capacity of the battery.

[0096] In the embodiment of the present invention, the ratio between the battery capacity corresponding to each target battery and the rated capacity is calculated to obtain multiple battery health values.

[0097] It is worth mentioning that the battery capacity can be calculated using the constant current discharge method by monitoring the current and time integral during the discharge process. The specific expression of battery capacity is:

[0098] ;

[0099] in, is the discharge current at the jth moment, is the j-1th moment, is the jth moment, j is the time index, is the battery capacity, t max is the maximum discharge moment.

[0100] S12. Input the operating condition parameters of each target battery into a pre-trained remaining power detection model to obtain multiple remaining power values.

[0101] The operating parameters refer to the voltage data, current data and temperature data of the target battery.

[0102] In an embodiment of the present invention, the operating parameters of each target battery are respectively input into a pre-trained remaining power detection model to obtain multiple remaining power values, wherein the operating parameters include voltage data, current data and temperature data.

[0103] It should be noted that the training process of the remaining power detection model is as follows:

[0104] A1. Obtain multiple training battery operating condition parameters, perform data preprocessing on each training battery operating condition parameter, and generate a battery feature set.

[0105] The training battery operating condition parameters refer to the historical operating condition parameters of the battery, including but not limited to historical voltage, historical current value, historical temperature value and historical remaining power value.

[0106] Data preprocessing refers to cleaning and smoothing the training battery operating condition parameters and using the battery feature set composed of the corrected training battery operating condition parameters.

[0107] In an embodiment of the present invention, a plurality of training battery operating condition parameters are obtained, cleaning and smoothing operations are performed on each training battery operating condition parameter, and a battery feature set composed of the corrected training battery operating condition parameters is adopted.

[0108] A2. Use the battery feature set to input the preset initial remaining power detection model for training, and output the training remaining power data.

[0109] In an embodiment of the present invention, the battery feature set is input into a preset initial remaining power detection model for training to obtain corresponding training remaining power data.

[0110] It should be noted that the initial remaining power detection model is a feedforward neural network. The feedforward neural network includes an input layer, a hidden layer, and an output layer. The input layer is used to receive battery operating parameters including voltage, current, and temperature.

[0111] The expression of the working condition parameters is: .

[0112] The hidden layer contains multiple neurons, each of which performs linear transformations and nonlinear activation functions. Activation functions include but are not limited to Sigmoid function (i.e., S-shaped function) and ReLU (i.e., Rectifier Linear Unit). The output of a neuron is specifically:

[0113]

[0114] in, is the output of the j1th neuron, is the weight between the i1th neuron in the input layer and the j1th neuron in the hidden layer, is the working condition parameter, is the bias of the hidden layer of the j1th neuron, i1 is the index of the input layer neuron, j1 is the index of the hidden layer neuron, is a non-linear activation function.

[0115] Output layer: used to output the predicted value. The expression of the predicted value is:

[0116]

[0117] in, is the predicted value, is the weight between the j1th neuron in the hidden layer and the k1th neuron in the output layer, is the bias of the output layer of the k1th neuron, and k1 is the index of the output layer neuron.

[0118] A3. Based on the mean square error function, calculate the training loss function value of the battery feature set according to the training remaining power data.

[0119] In an embodiment of the present invention, the training remaining power data and the battery feature set are input into a preset mean square error function to obtain a corresponding training loss function value.

[0120] It should be noted that the mean square error function is specifically:

[0121] ;

[0122] in, is the training loss function value, is the predicted value of the qth sample, is the actual value of the qth sample, is the number of samples in the battery feature set, and q is the index of the sample.

[0123] A4. When the training loss function value is greater than or equal to the preset standard loss function value, the network parameters of the initial remaining power detection model are adjusted, and the execution jumps to the step of using the battery feature set to input the preset initial remaining power detection model for training and outputting the training remaining power data until the training loss function value is less than the standard loss function value.

[0124] In an embodiment of the present invention, when the training loss function value is greater than or equal to the preset standard loss function value, the network parameters of the initial remaining power detection model are adjusted through the back propagation algorithm, and the execution of A2-A4 is jumped until the training loss function value is less than the standard loss function value.

[0125] It should be noted that the backpropagation algorithm updates the network weights by calculating the gap between the predicted results of the neural network and the actual values.

[0126] A5. When the training loss function value is less than the standard loss function value, a remaining power detection model is generated.

[0127] In an embodiment of the present invention, if the training loss function value is less than the standard loss function value, a remaining power detection model is generated.

[0128] S13. Ratio processing is performed on the output power and input power of each target battery to obtain multiple charge and discharge efficiency values.

[0129] Output power refers to the actual power output when the target battery is discharged.

[0130] Input power refers to the power input when the target battery is charged.

[0131] The charge and discharge efficiency value refers to the ratio of the actual available energy of the target battery to the input / output energy during the charge and discharge cycle.

[0132] In the embodiment of the present invention, the ratio between the output power and the input power of each target battery is calculated respectively to obtain a plurality of charge and discharge efficiency values.

[0133] S14: Perform path safety assessment on the transport parameters of each target battery to obtain multiple path safety assessment values.

[0134] Furthermore, the transfer parameters include path complexity, multiple angle change values, path length, and number of obstacles. S14 includes the following sub-steps:

[0135] S141 , summing up the absolute values ​​of the angle change values ​​corresponding to the target batteries to obtain a plurality of first sum values.

[0136] The angle change value refers to the angular change of the target battery along the transport path. For example, obtain the coordinate point sequence corresponding to the transport path of the target battery {first path point, second path point, third path point, pi-th path point, ..., pn-th path point} (e.g., one point every 0.5 meters), where pn is the total number of path points and pi is the index of the path point. The angle change value = atan²(the vector from the pi-1th path point to the pi-th path point) - atan²(the vector from the pi-th path point to the pi+1th path point).

[0137] In the embodiment of the present invention, the sum of the absolute values ​​of the angle change values ​​corresponding to the target batteries is calculated respectively to obtain a plurality of first sum values.

[0138] S142. Based on the preset transfer weight, perform weighted calculation on the path complexity and the first sum value corresponding to each target battery to obtain multiple transfer difficulty values.

[0139] Path complexity refers to the complexity of the target battery's transport path, which is usually related to path length, obstacle density, and number of turns. For example, the path length, obstacle density, and number of turns corresponding to the target battery's transport path are obtained. Path complexity is calculated by weighting the path length, obstacle density, and number of turns according to the preset path complexity weight. (Obstacle density can be obtained through lidar or image recognition.)

[0140] The transport difficulty value refers to the difficulty of controlling the passage of the target battery on the transport route, which is generally determined by factors such as path complexity and angle changes (the simpler the path, the safer it is).

[0141] In the embodiment of the present invention, according to the preset transfer weight, a weighted operation is performed on the path complexity and the first sum value corresponding to each target battery to obtain a plurality of transfer difficulty values.

[0142] S143. Multiply the path length, the number of obstacles, and the transport difficulty value corresponding to each target battery respectively to obtain a plurality of first multiplied values.

[0143] Path length refers to the length of the transport path of the target battery.

[0144] The number of obstacles refers to the number of obstacles that may exist on the transport path of the target battery (the fewer obstacles, the safer the path). For example, the number of obstacles on the transport path corresponding to the target battery is obtained through lidar or image recognition.

[0145] In the embodiment of the present invention, the multiplication values ​​among the path length, the number of obstacles and the transportation difficulty value corresponding to each target battery are calculated respectively to obtain a plurality of first multiplication values.

[0146] S144: Perform ratio processing on the preset transfer reference value and each first multiplication value to obtain multiple path safety assessment values.

[0147] The transfer benchmark value refers to the standard value for quantifying the safety of batteries during transfer, and its value is 1.

[0148] The path safety assessment value refers to an indicator that quantitatively assesses the safety risk of target battery transportation.

[0149] In the embodiment of the present invention, the ratios between the preset transfer reference value and each first multiplication value are calculated respectively to obtain a plurality of path safety assessment values.

[0150] S15. Determine the transport parameter, route safety assessment value, battery health value, remaining power value, and charge / discharge efficiency value corresponding to each target battery as the state parameter corresponding to each target battery.

[0151] In the embodiment of the present invention, the transport parameter, route safety assessment value, battery health value, remaining power value and charge / discharge efficiency value corresponding to each target battery are respectively used as the state parameters corresponding to each target battery.

[0152] Step 204: Input each state parameter into a preset grouping evaluation function to obtain a corresponding grouping evaluation value.

[0153] In the embodiment of the present invention, each state parameter is evaluated based on a preset group evaluation function to obtain a corresponding group evaluation value.

[0154] It should be noted that the group evaluation function is specifically:

[0155] ;

[0156] in, is the group evaluation value, is the evaluation value of the i-th target battery, is the battery health value of the i-th target battery, is the remaining power value of the i-th target battery, is the charge and discharge efficiency value of the i-th target battery, is the path safety assessment value of the i-th target battery, is the collision safety value, is the first evaluation weight coefficient, is the second evaluation weight coefficient, is the third evaluation weight coefficient, is the fourth evaluation weight coefficient, is the fifth evaluation weight coefficient, is the first collision safety factor, is the second collision safety factor, is the third collision safety factor, is the degree of path intersection, is the path complexity between the i-th target battery and the j-th target battery, is the operating speed of the i-th target battery and the j-th target battery, is the length of the overlap between the i-th target battery and the j-th target battery, is the total path length between the i-th target battery and the j-th target battery, i is the first index of the target battery, and j is the second index of the target battery.

[0157] It should be noted that the group evaluation function is a dimensionless calculation.

[0158] It is worth mentioning that the complexity of the path between the i-th target battery and the j-th target battery can be calculated by counting the number of intersections between the transfer path corresponding to the i-th target battery and the transfer path corresponding to the j-th target battery, and taking the number of intersections between the transfer path corresponding to the i-th target battery and the transfer path corresponding to the j-th target battery as the complexity of the path between the i-th target battery and the j-th target battery.

[0159] Step 205: Update the initial quantum group according to the group matching evaluation value to obtain an updated quantum group.

[0160] In an embodiment of the present invention, based on the grouping evaluation value, a rotating gate is used to update the quantum state of each quantum bit in the initial quantum group to obtain an updated quantum group.

[0161] It should be noted that the update process of the initial quantum group is specifically as follows: B1, the matching evaluation value is compared with the preset reference matching evaluation value to obtain a first ratio. B2, the first ratio is multiplied by the preset reference rotation angle to obtain Rotation angle (i.e. =reference rotation angle*(matching evaluation value / reference matching evaluation value). B3. Input the revolving door function according to the rotation angle to obtain the corresponding revolving door, wherein the revolving door function is specifically:

[0162] ;

[0163] in, For revolving door.

[0164] B4, obtain the first probability amplitude (referring to the probability of the quantum state becoming 1) and the second probability amplitude (referring to the probability of the quantum state becoming 0) of each quantum bit in the initial quantum group (and the first probability amplitude 2 +Second Probability Amplitude 2 =1). B5. Based on a preset probability amplitude update function, update each first probability amplitude and each second probability amplitude according to the revolving door to obtain updated first probability amplitudes and each second probability amplitude. The probability amplitude update function is specifically:

[0165] ;

[0166] in, is the first probability amplitude after update, is the updated second probability amplitude, is the first probability amplitude, is the second probability amplitude. B6. Construct an initial updated quantum group based on the updated first probability amplitudes and the updated second probability amplitudes. B7. Determine whether the number of quantum states of 1 in the initial updated quantum group is consistent with the number of quantum states of 1 in the initial quantum group. B8. If the number of quantum states of 1 in the initial updated quantum group is inconsistent with the number of quantum states of 1 in the initial quantum group, re-execute B6-B7. B9. If the number of quantum states of 1 in the initial updated quantum group is consistent with the number of quantum states of 1 in the initial quantum group, generate an updated quantum group.

[0167] Step 206: Determine whether the update times of the updated quantum group is greater than or equal to a preset iteration threshold.

[0168] In an embodiment of the present invention, it is determined whether the number of updates of the quantum group is greater than or equal to a preset iteration threshold, wherein the iteration threshold can be dynamically adjusted according to the number of battery groups.

[0169] Step 207: If the number of updates is less than the iteration threshold, the updated quantum group is used as the new initial quantum group, and the execution jumps to the step of determining the battery as the target battery when the quantum bit corresponding to the battery is a preset reference bit.

[0170] In the embodiment of the present invention, if the number of updates is less than the iteration threshold, the updated quantum group is used as a new initial quantum group, and the process jumps to step 202 to step 207.

[0171] Step 208: If the number of updates is greater than or equal to the iteration threshold, the updated quantum group corresponding to the maximum value of each pairing evaluation value is selected as the target quantum group.

[0172] In the embodiment of the present invention, if the number of updates is greater than or equal to the iteration threshold, the updated quantum group corresponding to the maximum value of each pairing evaluation value is used as the target quantum group.

[0173] Step 209: The battery group corresponding to the target quantum group is used as the corresponding grouping result.

[0174] Battery grouping refers to the quantum state of each quantum bit in the target quantum group.

[0175] In an embodiment of the present invention, the quantum state of each quantum bit in the target quantum group is measured, the battery grouping is determined according to the value of each quantum state, and the battery grouping is used as the corresponding grouping result.

[0176] For example, when the battery group corresponding to the target quantum group is: , then the first battery, the fifth battery and the eighth battery are selected as the corresponding grouping results. When the battery group corresponding to the target quantum group is: , then select the fourth battery, the fifth battery and the eighth battery as the corresponding matching results.

[0177] In an embodiment of the present invention, an initial quantum group is constructed based on the number of battery groups and the total number of batteries. Each qubit in the initial quantum group corresponds to a battery. When the qubit corresponding to a battery is a preset reference bit, the battery is identified as a target battery. A state assessment is performed on each target battery to obtain state parameters corresponding to each target battery. Based on a quantum optimization algorithm, the initial quantum group is optimized according to a preset grouping evaluation function and each state parameter to obtain the corresponding grouping result. This overcomes the existing practice of relying primarily on the factory static parameters of batteries for battery grouping. However, these static parameters cannot reflect the dynamic characteristics of the batteries or the environmental adaptability during the grouping process, making it difficult to predict the battery's performance under actual operating conditions and reducing the reliability of battery grouping. Compared to traditional battery grouping methods, the present invention performs a state assessment on each target battery to obtain state parameters reflecting the battery's dynamic characteristics and environmental adaptability. Based on a quantum optimization algorithm, the initial quantum group is optimized according to the preset grouping evaluation function and each state parameter to obtain the optimal grouping result, thereby improving the reliability of battery grouping.

[0178] See also Figure 3 , Figure 3 This is a structural block diagram of a battery packing system provided in Example 3 of the present invention.

[0179] The present invention provides a battery assembly system, comprising:

[0180] A construction module 301 is used to obtain the number of battery groups and the total number of batteries, and construct an initial quantum group based on the number of battery groups and the total number of batteries, wherein each quantum bit of the initial quantum group corresponds to a battery;

[0181] A detection module 302 is configured to determine the battery as a target battery when the qubit corresponding to the battery is a preset reference bit;

[0182] An evaluation module 303 is configured to evaluate the status of each target battery and obtain a status parameter corresponding to each target battery;

[0183] The optimization module 304 is used to optimize the initial quantum group based on the quantum optimization algorithm according to the preset grouping evaluation function and various state parameters to obtain the corresponding grouping result.

[0184] Furthermore, the evaluation module 303 includes:

[0185] The health assessment submodule is used to perform ratio processing on the battery capacity corresponding to each target battery and the rated capacity to obtain multiple battery health values;

[0186] The remaining power evaluation submodule is used to input the operating condition parameters of each target battery into a pre-trained remaining power detection model to obtain multiple remaining power values;

[0187] The charge and discharge efficiency submodule is used to perform ratio processing on the output power and input power of each target battery to obtain multiple charge and discharge efficiency values;

[0188] The path safety assessment submodule is used to perform path safety assessment on the transport parameters of each target battery to obtain multiple path safety assessment values;

[0189] The evaluation submodule is used to determine the transport parameters, path safety evaluation value, battery health value, remaining power value and charge-discharge efficiency value corresponding to each target battery as the state parameters corresponding to each target battery.

[0190] Furthermore, the optimization module 304 includes:

[0191] The first analysis submodule is used to input each state parameter into a preset group evaluation function to obtain a corresponding group evaluation value;

[0192] The update submodule is used to update the initial quantum group according to the group evaluation value to obtain an updated quantum group;

[0193] The second analysis submodule is used to determine whether the update number of the updated quantum group is greater than or equal to a preset iteration threshold;

[0194] If the number of updates is less than the iteration threshold, the updated quantum group is used as the new initial quantum group, and the execution jumps to the step of determining the battery as the target battery when the quantum bit corresponding to the battery is a preset reference bit;

[0195] If the number of updates is greater than or equal to the iteration threshold, the updated quantum group corresponding to the maximum value of each matching group evaluation value is selected as the target quantum group;

[0196] The measurement submodule is used to take the battery grouping corresponding to the target quantum group as the corresponding grouping result.

[0197] Furthermore, the transfer parameters include path complexity, multiple angle change values, path length and number of obstacles. The path safety assessment submodule includes:

[0198] a summing unit, configured to sum the absolute values ​​of the angle change values ​​corresponding to the target batteries to obtain a plurality of first sum values;

[0199] a weighting unit, configured to perform a weighted operation on the path complexity and the first sum value corresponding to each target battery based on a preset transfer weight, to obtain a plurality of transfer difficulty values;

[0200] a multiplication unit, configured to multiply the path length, the number of obstacles, and the transport difficulty value corresponding to each target battery to obtain a plurality of first multiplication values;

[0201] The safety assessment unit is used to perform ratio processing on the preset transfer reference value and each first multiplication value respectively to obtain multiple path safety assessment values.

[0202] Furthermore, the training process of the remaining power detection model is as follows:

[0203] Acquire multiple training battery operating condition parameters, perform data preprocessing on each training battery operating condition parameter, and generate a battery feature set;

[0204] Use the battery feature set to input the preset initial remaining power detection model for training, and output the training remaining power data;

[0205] Based on the mean square error function, the training loss function value of the battery feature set is calculated according to the training remaining power data;

[0206] When the training loss function value is greater than or equal to the preset standard loss function value, the network parameters of the initial remaining power detection model are adjusted, and the execution jumps to the step of using the battery feature set to input the preset initial remaining power detection model for training and outputting the training remaining power data until the training loss function value is less than the standard loss function value;

[0207] When the training loss function value is less than the standard loss function value, a remaining power detection model is generated.

[0208] Furthermore, the group evaluation function is specifically:

[0209] ;

[0210] in, is the group evaluation value, is the evaluation value of the i-th target battery, is the battery health value of the i-th target battery, is the remaining power value of the i-th target battery, is the charge and discharge efficiency value of the i-th target battery, is the path safety assessment value of the i-th target battery, is the collision safety value, is the first evaluation weight coefficient, is the second evaluation weight coefficient, is the third evaluation weight coefficient, is the fourth evaluation weight coefficient, is the fifth evaluation weight coefficient, is the first collision safety factor, is the second collision safety factor, is the third collision safety factor, is the degree of path intersection, is the path complexity between the i-th target battery and the j-th target battery, is the operating speed of the i-th target battery and the j-th target battery, is the length of the overlap between the i-th target battery and the j-th target battery, is the total path length between the i-th target battery and the j-th target battery, i is the first index of the target battery, and j is the second index of the target battery.

[0211] See also Figure 4 , Figure 4 This is a structural block diagram of an electronic device provided in Example 4 of the present invention.

[0212] An electronic device according to an embodiment of the present invention includes: a memory 401 and a processor 402, wherein the memory 401 stores a computer program; when the computer program is executed by the processor 402, the processor 402 executes the battery grouping method according to any of the above embodiments.

[0213] Memory 401 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 401 has storage space 403 for program code 413 for executing any of the method steps described above. For example, storage space 403 for program code may include individual program codes 413 for implementing various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. The program codes may be compressed, for example, in a suitable format. When executed by a processing device, these codes cause the processing device to execute the various steps in the method described above. These program codes may be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, compact disks (CDs), memory cards, or floppy disks. The program codes may be compressed, for example, in a suitable format. When these codes are executed by a processing device, they cause the processing device to execute the various steps of the battery grouping method described above.

[0214] The fifth embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the battery grouping method according to any of the above embodiments is implemented.

[0215] Embodiment 6 of the present invention further provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer executes the battery grouping method as described in any of the above embodiments.

[0216] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0217] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0218] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0219] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0220] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0221] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A battery assembly method, characterized in that: include: Obtaining the number of battery groups and the total number of batteries, and constructing an initial quantum group based on the number of battery groups and the total number of batteries, wherein each quantum bit of the initial quantum group corresponds to a battery; When the quantum bit corresponding to the battery is a preset reference bit, the battery is determined as a target battery; Performing a status evaluation on each of the target batteries to obtain a status parameter corresponding to each of the target batteries; Based on the quantum optimization algorithm, the initial quantum group is optimized according to the preset grouping evaluation function and each of the state parameters to obtain the corresponding grouping result; The group evaluation function is specifically: ； in, is the group evaluation value, is the evaluation value of the i-th target battery, is the battery health value of the i-th target battery, is the remaining power value of the i-th target battery, is the charge and discharge efficiency value of the i-th target battery, is the path safety assessment value of the i-th target battery, is the collision safety value, is the first evaluation weight coefficient, is the second evaluation weight coefficient, is the third evaluation weight coefficient, is the fourth evaluation weight coefficient, is the fifth evaluation weight coefficient, is the first collision safety factor, is the second collision safety factor, is the third collision safety factor, is the degree of path intersection, is the path complexity between the i-th target battery and the j-th target battery, is the operating speed of the i-th target battery and the j-th target battery, is the length of the overlap between the i-th target battery and the j-th target battery, is the total path length between the i-th target battery and the j-th target battery, i is the first index of the target battery, j is the second index of the target battery, M is the total number of target batteries, The target battery set.

2. The battery assembly method according to claim 1, characterized in that: The step of performing status evaluation on each of the target batteries to obtain status parameters corresponding to each of the target batteries includes: Ratio processing is performed on the battery capacity corresponding to each target battery to the rated capacity to obtain multiple battery health values; Inputting the operating condition parameters of each target battery into a pre-trained remaining power detection model to obtain multiple remaining power values; performing ratio processing on the output power and input power of each target battery to obtain a plurality of charge and discharge efficiency values; Performing path safety assessment on the transport parameters of each target battery to obtain multiple path safety assessment values; The transport parameter, path safety assessment value, battery health value, remaining power value and charge / discharge efficiency value corresponding to each target battery are respectively determined as the state parameters corresponding to each target battery.

3. The battery assembly method according to claim 1, characterized in that: The step of optimizing the initial quantum group based on the quantum optimization algorithm according to the preset grouping evaluation function and each of the state parameters to obtain the corresponding grouping result includes: Inputting each of the state parameters into a preset grouping evaluation function to obtain a corresponding grouping evaluation value; Updating the initial quantum group according to the pairing evaluation value to obtain an updated quantum group; Determining whether the update number of the updated quantum group is greater than or equal to a preset iteration threshold; If the update number is less than the iteration threshold, the updated quantum group is used as a new initial quantum group, and the step of determining the battery as a target battery when the quantum bit corresponding to the battery is a preset reference bit is skipped and executed; If the number of updates is greater than or equal to the iteration threshold, the updated quantum group corresponding to the maximum value of each pairing evaluation value is selected as the target quantum group; The battery grouping corresponding to the target quantum group is taken as the corresponding grouping result.

4. The battery assembly method according to claim 2, characterized in that: The transport parameters include path complexity, multiple angle change values, path length, and the number of obstacles. The step of performing path safety assessment on the transport parameters of each target battery to obtain multiple path safety assessment values ​​includes: respectively summing up the absolute values ​​of the angle change values ​​corresponding to the target batteries to obtain a plurality of first sum values; Based on a preset transfer weight, weighted operations are performed on the path complexity and the first sum value corresponding to each target battery to obtain multiple transfer difficulty values; Multiplying the path length, the number of obstacles, and the transport difficulty value corresponding to each target battery respectively to obtain a plurality of first multiplied values; The preset transfer reference value is respectively compared with each of the first multiplication values ​​to obtain a plurality of path safety assessment values.

5. The battery assembly method according to claim 2, characterized in that: The training process of the remaining power detection model is specifically as follows: Acquire multiple training battery operating condition parameters, perform data preprocessing on each of the training battery operating condition parameters, and generate a battery feature set; Using the battery feature set to input a preset initial remaining power detection model for training, and outputting training remaining power data; Calculating a training loss function value of the battery feature set based on the training remaining power data based on a mean square error function; When the training loss function value is greater than or equal to a preset standard loss function value, the network parameters of the initial remaining power detection model are adjusted, and the process jumps to executing the step of using the battery feature set to input the preset initial remaining power detection model for training and outputting training remaining power data, until the training loss function value is less than the standard loss function value; When the training loss function value is less than the standard loss function value, a remaining power detection model is generated.

6. A battery packing system, characterized in that: include: a construction module, configured to obtain the number of battery groups and the total number of batteries, and construct an initial quantum group according to the number of battery groups and the total number of batteries, wherein each quantum bit of the initial quantum group corresponds to a battery; a detection module, configured to determine the battery as a target battery when the quantum bit corresponding to the battery is a preset reference bit; An evaluation module, configured to perform a status evaluation on each of the target batteries to obtain a status parameter corresponding to each of the target batteries; An optimization module is used to optimize the initial quantum group based on a quantum optimization algorithm according to a preset grouping evaluation function and each of the state parameters to obtain a corresponding grouping result; The group evaluation function is specifically: ； in, is the group evaluation value, is the evaluation value of the i-th target battery, is the battery health value of the i-th target battery, is the remaining power value of the i-th target battery, is the charge and discharge efficiency value of the i-th target battery, is the path safety assessment value of the i-th target battery, is the collision safety value, is the first evaluation weight coefficient, is the second evaluation weight coefficient, is the third evaluation weight coefficient, is the fourth evaluation weight coefficient, is the fifth evaluation weight coefficient, is the first collision safety factor, is the second collision safety factor, is the third collision safety factor, is the degree of path intersection, is the path complexity between the i-th target battery and the j-th target battery, is the operating speed of the i-th target battery and the j-th target battery, is the length of the overlap between the i-th target battery and the j-th target battery, is the total path length between the i-th target battery and the j-th target battery, i is the first index of the target battery, j is the second index of the target battery, M is the total number of target batteries, The target battery set.

7. An electronic device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the battery grouping method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the battery grouping method according to any one of claims 1 to 5 is implemented.

9. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer is caused to execute the battery pairing method according to any one of claims 1 to 5.

Images