A method and device for determining a design model of a power battery box

Abstract

The application provides a method and device for determining a design model of a power battery box, the method comprising: obtaining design parameters of a power battery box to be designed; and determining at least one power battery box design model corresponding to the design parameters from a power battery box model library based on the design parameters, wherein the power battery box model library comprises a plurality of pre-constructed power battery box original models, and the design parameter characteristic values of each power battery box original model are determined by a pre-trained characteristic value determination model. Through the method and device, a plurality of battery box design models can be quickly obtained by inputting the design parameters of different power battery boxes to be designed, so as to accelerate the development speed of the power battery box, realize agile design of the power battery box, and shorten the development cycle of the power battery.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery, in particular to a method and device for determining a design model of a power battery box. BACKGROUND

[0002] New energy vehicles have the advantages of green environmental protection, and power batteries are developing rapidly. It is a key problem to quickly design power batteries with high strength, light weight, good safety, low cost and high reliability. The power battery box, as an important component of the power battery, plays multiple roles such as protecting the battery cell, fixing high and low voltage electrical components, ensuring sealing, and connecting the vehicle. Therefore, promoting the agile design of the power battery box is of great significance to speed up the production of the power battery.

[0003] Currently, in the power battery industry, the development cycle of the power battery box is long, and a large amount of manpower and resources need to be invested. Therefore, how to quickly determine the design model of the power battery box to speed up the development of the power battery box has become a technical problem that cannot be ignored. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a method and device for determining a design model of a power battery box. By inputting different design parameters of the power battery box to be designed, multiple battery box design models can be quickly obtained to speed up the development of the power battery box, realize the agile design of the power battery box, and shorten the development cycle of the power battery.

[0005] In a first aspect, the embodiments of the present application provide a method for determining a design model of a power battery box, which comprises:

[0006] obtaining design parameters of a power battery box to be designed;

[0007] determining at least one power battery box design model corresponding to the design parameters from a power battery box model library based on the design parameters; wherein the power battery box model library comprises a plurality of pre-constructed power battery box original models, and the design parameter characteristic values of each power battery box original model are determined by a pre-trained characteristic value determination model.

[0008] Further, the design parameters include the outer envelope space parameters, the inner envelope space parameters, the box structure form parameters, the product design rule parameters, the product function performance parameters and the box manufacturing feasibility parameters of the power battery box to be designed.

[0009] Further, the determining at least one power battery box design model corresponding to the design parameters from the power battery box model library based on the design parameters comprises:

[0010] determine an initial structure of the to-be-designed power battery box based on the outer envelope space parameter and the inner envelope space parameter, and screen a first candidate model from a plurality of power battery box original models in the power battery box model library based on the initial structure; wherein a box structure of the first candidate model is the initial structure;

[0011] determine a second candidate model corresponding to the box structure form parameter from the first candidate model based on the box structure form parameter;

[0012] determine a third candidate model corresponding to the product design rule parameter from the second candidate model based on the product design rule parameter;

[0013] determine a fourth candidate model corresponding to the product function performance parameter from the third candidate model based on the product function performance parameter;

[0014] determine at least one power battery box design model from the fourth candidate model based on the box manufacturing feasibility parameter.

[0015] Further, each power battery box original model in the power battery box model library is constructed by the following steps:

[0016] obtain a plurality of power battery box product design data;

[0017] For each power battery box product design data, input the power battery box product design data into the characteristic value determination model, determine the corresponding design parameter characteristic value, and generate the power battery box original model corresponding to the power battery box product design data based on the design parameter characteristic value.

[0018] Further, the characteristic value determination model is trained by the following steps:

[0019] obtain a plurality of product design sample data and a design parameter sample characteristic value corresponding to each product design sample data;

[0020] For each product design sample data, input the product design sample data into the characteristic value original determination model to determine the design parameter preset characteristic value corresponding to the product design sample data;

[0021] Compare the design parameter sample characteristic value corresponding to each product design sample data with the design parameter preset characteristic value, and calculate the loss function of the characteristic value original determination model under the current state;

[0022] Based on the loss function of the characteristic value original determination model, the model parameters of the characteristic value original determination model are continuously adjusted until the characteristic value original determination model reaches a convergence state, and the characteristic value determination model is obtained.

[0023] Further, after the at least one power battery case design model corresponding to the design parameters is determined from the power battery case model library based on the design parameters, the determination method further comprises:

[0024] For each power battery case design model, an evaluation score after evaluation analysis of the power battery case design model is obtained.

[0025] Based on the evaluation score corresponding to each power battery case design model, a power battery case target model with the highest evaluation score is determined from the at least one power battery case design model.

[0026] In a second aspect, the embodiments of the present application further provide a determination device of a power battery case design model, the determination device comprising:

[0027] A design parameter acquisition module is configured to acquire design parameters of a power battery case to be designed.

[0028] A design model determination module is configured to determine at least one power battery case design model corresponding to the design parameters from a power battery case model library based on the design parameters, wherein the power battery case model library comprises a plurality of pre-constructed power battery case original models, and the design parameter characteristic value of each power battery case original model is determined by a pre-trained characteristic value determination model.

[0029] Further, the design parameters include an outer envelope space parameter, an inner envelope space parameter, a case structure form parameter, a product design rule parameter, a product function performance parameter, and a case manufacturing feasibility parameter of the power battery case to be designed.

[0030] In a third aspect, the embodiments of the present application further provide an electronic device, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the determination method of the power battery case design model as described above.

[0031] In a fourth aspect, the embodiments of the present application further provide a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to perform the steps of the determination method of the power battery case design model as described above.

[0032] The embodiment of the present application provides a kind of power battery box design model determination method and determination device, first, the design parameter of the power battery box to be designed is acquired;Then, at least one power battery box design model corresponding to the design parameter is determined from the power battery box model library based on the design parameter;Wherein, the power battery box model library includes a plurality of pre-constructed power battery box original model, and the design parameter characteristic value of each power battery box original model is determined by the characteristic value determination model determined by pre-training.

[0033] The embodiment of the present application can quickly obtain a plurality of battery box design models by inputting different design parameters of the power battery box to be designed, so that the user can determine the design scheme of the power battery box to be designed according to the power battery box design model, and develop the power battery box to be designed according to the power battery box design model. The design model of the power battery box is quickly determined to speed up the development speed of the power battery box, to realize the agile design of the power battery box, and shorten the development cycle of the power battery.

[0034] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0036] Figure 1 The flow chart of the power battery box design model determination method provided by the embodiment of the present application is shown in the figure.

[0037] Figure 2 The structure schematic diagram of the power battery box design model determination device provided by the embodiment of the present application is shown in the figure.

[0038] Figure 3 The structure schematic diagram of the power battery box design model determination device provided by the embodiment of the present application is shown in the figure.

[0039] Figure 4 The structure schematic diagram of the electronic device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0040] To make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the accompanying drawings of the embodiments of the present application to make a clear and complete description of the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. The components of the embodiments of the present application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without creative work falls within the scope of protection of the present application.

[0041] Firstly, the application scenarios applicable to the present application are introduced. The present application can be applied to the field of battery technology.

[0042] New energy vehicles have the advantages of green environmental protection, and power batteries develop rapidly. It is a key problem to quickly design power batteries with high strength, light weight, good safety, low cost and high reliability. The power battery box, as an important component of the power battery, undertakes the protection of the power battery, the fixation of high and low voltage electrical components, the guarantee of sealing, the connection of the whole vehicle and other functions. Therefore, promoting the agile design of the power battery box is of great significance to speed up the production speed of the power battery.

[0043] It is found through research that at present in the power battery industry, the development cycle of the power battery box is long, and a large amount of manpower and material resources need to be invested. Therefore, how to quickly determine the design model of the power battery box to speed up the development speed of the power battery box has become a technical problem that cannot be underestimated.

[0044] Based on this, the embodiments of the present application provide a method for determining the design model of the power battery box, which quickly determines the design model of the power battery box to speed up the development speed of the power battery box, so as to realize the agile design of the power battery box and shorten the development cycle of the power battery.

[0045] Please refer to Figure 1 , Figure 1 The flowchart of the method for determining the design model of the power battery box provided by the embodiments of the present application is shown in FIG. 1. As shown in FIG. 1, the determining method provided by the embodiments of the present application comprises the following steps. Figure 1

[0046] S101, obtaining the design parameters of the power battery box to be designed.

[0047] ​For the above step S101, in specific implementation, the design parameters of the to-be-designed power battery case are acquired. Specifically, according to the embodiments provided in the present application, the design parameters of the to-be-designed power battery case include an outer envelope space parameter, an inner envelope space parameter, a case structure form parameter, a product design rule parameter, a product function performance parameter and a case manufacturing feasibility parameter of the to-be-designed power battery case.

[0048] S102, at least one power battery case design model corresponding to the design parameters is determined from the power battery case model library based on the design parameters.

[0049] Wherein, the power battery case model library includes a plurality of pre-constructed power battery case original models, and the design parameter characteristic values of each power battery case original model are determined by a pre-trained characteristic value determination model. Here, the design parameter characteristic values include the outer envelope space X, the inner envelope space Y, the product design rule M, the function performance requirement N and the manufacturing feasibility requirement K of the power battery case.

[0050] For the above step S102, in specific implementation, at least one power battery case design model corresponding to the design parameters is determined from the power battery case model library based on the design parameters acquired in step S101. In this way, according to the product development design input, the design parameters of the to-be-designed power battery case are confirmed, the trained power battery case model library is used to complete the product design of the to-be-designed power battery case, and at least one power battery case design model is output. In this way, the user can determine the design scheme of the to-be-designed power battery case according to the power battery case design model, and develop the to-be-designed power battery case according to the power battery case design model.

[0051] As an optional embodiment, each power battery case original model in the power battery case model library is constructed by the following steps:

[0052] A: Acquire a plurality of power battery case product design data.

[0053] B: For each power battery case product design data, input the power battery case product design data into the characteristic value determination model, determine the corresponding design parameter characteristic value, and generate the power battery case original model corresponding to the power battery case product design data based on the design parameter characteristic value.

[0054] For the above steps A-step B, in the specific implementation, a plurality of power battery box product design data are acquired. For each power battery box product design data, the power battery box product design data is input into the characteristic value determination model, the corresponding design parameter characteristic value is determined, and the power battery box original model corresponding to the power battery box product design data is generated based on the design parameter characteristic value.

[0055] Specifically, according to the embodiments provided in the present application, first, the outer envelope space X of the power battery box to be designed and the inner envelope space Y of the power battery are confirmed according to external input; the box structure form Z is confirmed according to past project experience and design scheme accumulation; the product design rule M is accumulated into product design rule M according to project experience, design specification, technical condition, DFMEA, problem avoidance, etc. knowledge; the product scheme designed by the power battery box design model also needs to meet the requirements of battery pack mechanical reliability, thermal safety, electrical safety, sealing, environmental resistance, etc., as well as manufacturing feasibility requirements. Therefore, the functional performance requirement N and the manufacturing feasibility requirement K are introduced to generate the power battery box model, which is expressed as follows:

[0056] F{X, Y, Z, M, N}

[0057] F={f1,f2,f3...}

[0058] X={x1,x2,x3…}

[0059] Y={y1,y2,y3…}

[0060] Z={z1,z2,z3…}

[0061] M={m1,m2,m3…}

[0062] N={n1,n2,n3…}

[0063] K={k1,k2,k3…}

[0064] Wherein, F is the power battery box model.

[0065] Wherein, f1, f2, f3... are different power battery box models; x1, x2, x3... are different outer envelope spaces, y1, y2, y3... are different inner envelope spaces; z1, z2, z3... are different box structure forms; m1, m2, m3... are different product design rules.

[0066] The outer envelope space includes but is not limited to the maximum outer envelope size x 11 The hanging point x matched with the vehicle floor, the threshold, etc. 12 The connection point x matched with the vehicle bottom guard plate, the outer trim plate, the wheel cover, the wire harness, etc. 13High voltage connector, low voltage connector, water inlet / outlet pipe interface mounting point x 14 Partially fixed on the box body, explosion-proof valve, breather valve, etc. Functional parts of the fixed point x 15 .

[0067] The inner envelope space includes but is not limited to module (battery cell) envelope and mounting point y 11 Battery master / slave control unit envelope and mounting point y 12 Envelope and mounting point y of safety protection components 13 Envelope and mounting point y of low-voltage wire harness 14 Envelope and mounting point y of connection row 15 Envelope and mounting point y of high-voltage electrical cut-off unit 16 .

[0068] The box body structure form includes but is not limited to steel plate stamping box body z 11 Aluminum plate stamping box body z 12 Aluminum profile box body z 13 Steel roller pressing box body z 14 Non-metallic box body z 15 Die-cast aluminum box body z 16 .

[0069] The product design rules include but are not limited to whole vehicle development check gap check m 11 Power battery development check internal gap check m 12 Hoisting and transfer tool checking m 13 Assembly space checking m 14 Standard part selection checking m 15 Dimension chain checking m 16 .

[0070] The product functional performance requirements include but are not limited to whole package modal requirements n 11 Whole package bottom protection requirements n 12 Whole package mechanical impact requirements n 13 Whole package extrusion requirements n 14 Whole package random vibration requirements n 15 Battery cell expansion force requirements n 16 Whole package sealing requirements n 17 .

[0071] The lower box body manufacturing feasibility includes but is not limited to 3D data interference (repetition, missing parts) checking k 11 Connection (welding, riveting, screwing, etc.) relationship checking k 12 Forming process (stamping, machining, casting) rationality checking k 13 Product special performance (airtightness, flame retardant, insulation, etc.) requirements k14 .

[0072] Here, a characteristic value determination model is established by using a deep learning technology. As an example, the characteristic value determination model can be a deep neural network algorithm model, and the present application does not make specific limitations thereto. A plurality of power battery box product design data are input, the parameter characteristic value of each design parameter is determined through the characteristic value determination model, and the original model of the power battery box corresponding to each power battery box product design data is generated based on the design parameter characteristic value, so as to finally obtain a mature, stable and reliable power battery box model library.

[0073] Specifically, the characteristic value determination model is trained through the following steps:

[0074] a: Obtain a plurality of product design sample data and the design parameter sample characteristic value corresponding to each product design sample data.

[0075] b: For each product design sample data, the product design sample data is input into the characteristic value original determination model to determine the design parameter preset characteristic value corresponding to the product design sample data.

[0076] Here, the design parameter sample characteristic value also includes the above-mentioned various design parameters, which will not be repeated here.

[0077] For steps a-b above, in specific implementation, a plurality of product design sample data and the design parameter sample characteristic value corresponding to each product design sample data are obtained. For each product design sample data, the product design sample data is input into the characteristic value original determination model to determine the design parameter preset characteristic value corresponding to the product design sample data predicted by the characteristic value original determination model.

[0078] c: Compare the design parameter sample characteristic value corresponding to each product design sample data with the design parameter preset characteristic value, and calculate the loss function of the characteristic value original determination model under the current state.

[0079] d: Based on the loss function of the characteristic value original determination model, the model parameters of the characteristic value original determination model are constantly adjusted until the characteristic value original determination model reaches a convergence state, and the characteristic value determination model is obtained.

[0080] For the above steps c-step d, in specific implementation, for each product design sample data, the design parameter sample characteristic value of the product design sample data is compared with the design parameter preset characteristic value, and whether the prediction of the characteristic value original determination model is accurate is judged by comparing the design parameter sample characteristic value of the product design sample data with the design parameter preset characteristic value. When the design parameter sample characteristic value of the product design sample data is different from the design parameter preset characteristic value, it is considered that the prediction of the characteristic value original determination model is not accurate. At this time, the loss function of the characteristic value original determination model under the current state needs to be calculated. The way of calculating the loss function is explained in detail in the prior art, and will not be described in detail here. Then the model parameters of the characteristic value original determination model are continuously adjusted, and the characteristic value original determination model will continuously minimize the loss through iteration. At each step of iteration, the loss value of the characteristic value original determination model is calculated. When the loss value of the characteristic value original determination model cannot reach the loss threshold, the model parameters of the characteristic value original determination model are continuously updated, and the new parameters will calculate a new loss value, so that the loss value in the iteration process presents a fluctuating downward trend. Finally, when the loss value reaches a smooth state, that is, the loss value of the trained characteristic value original determination model is not greater than the loss threshold, that is, the loss value compared with the loss value calculated last time does not decrease obviously, it is considered that the characteristic value original determination model reaches a convergence state, and the prediction of the characteristic value original determination model at this time is relatively accurate. At this time, the training is ended, and the characteristic value determination model is obtained.

[0081] Specifically, for the above step S102, the at least one power battery case design model corresponding to the design parameter is determined from the power battery case model library based on the design parameter, which comprises:

[0082] Step 1021, determine the initial structure of the power battery case to be designed based on the outer envelope space parameter and the inner envelope space parameter, and select the first candidate model from the plurality of power battery case original models in the power battery case model library based on the initial structure.

[0083] Among them, the box structure of the first candidate model is the initial structure.

[0084] For the above step 1021, in specific implementation, the basic size and structure of the power battery case to be designed, that is, the initial structure, are determined based on the externally input outer envelope space parameter and inner envelope space parameter, and the first candidate model with the initial structure is selected from the plurality of power battery case original models in the power battery case model library based on the initial structure.

[0085] Step 1022, determine the second candidate model corresponding to the box structure form parameter from the first candidate model based on the box structure form parameter.

[0086] For the above step 1022, in specific implementation, the second candidate model corresponding to the box structure form parameter is determined from the first candidate model based on the box structure form parameter. Here, as an example, considering the project platformization demand and the supplier resource, the box structure form parameter selects the aluminum profile box z 13 , the fourth candidate model f1~f 13 is determined from the third candidate model f1~f 100 according to the product functional performance parameter.

[0087] Step 1023, the third candidate model corresponding to the product design rule parameter is determined from the second candidate model based on the product design rule parameter.

[0088] For the above step 1023, in specific implementation, the third candidate model corresponding to the product design rule parameter is determined from the second candidate model based on the product design rule parameter. Here, as an example, when the product design rule parameter is the whole vehicle development check gap check m 11 ≥10mm, the power battery development check internal gap check m 12 ≥5mm, the third candidate model f1~f 100 with the same product design rule parameter is determined from the second candidate model f1~f 30 according to the product design rule parameter.

[0089] Step 1024, the fourth candidate model corresponding to the product functional performance parameter is determined from the third candidate model based on the product functional performance parameter.

[0090] For the above step 1024, in specific implementation, the fourth candidate model corresponding to the product functional performance parameter is determined from the third candidate model based on the product functional performance parameter. Here, as an example, when the product functional performance parameter is the whole package modal requirement n 11 ≥35Hz, preferably ≥45Hz, the whole package bottom protection requirement n 12 ≥300J, the whole package mechanical impact requirement n 13 , the whole package extrusion requirement n 14 , the whole package random vibration requirement n 15 are all executed according to GB 38031 standard, the cell swelling force requirement n 16 ≥50KN, the whole package sealing requirement n 17 is IPX7, the fourth candidate model f1~f 30 is determined from the third candidate model f1~f 10 according to the product functional performance parameter.

[0091] Step 1025, determining at least one power battery case design model from the fourth candidate model based on the case manufacturing feasibility parameters.

[0092] For the above step 1025, in specific implementation, at least one power battery case design model is determined from the fourth candidate model based on the case manufacturing feasibility parameters. Here, as an example, when the case manufacturing feasibility parameters are 3D data without interference, repetition, missing parts, whether each part is beveled, whether the welding gun is accessible, whether the welding is continuous, whether the key parts of the lower case have insulation protection, etc., the power battery case design model f1-f5 is determined from the fourth candidate model f1-f4 according to the case manufacturing feasibility parameters. 10

[0093] As an optional embodiment, after the at least one power battery case design model corresponding to the design parameters is determined from the power battery case model library based on the design parameters in the above step S102, the determination method further comprises:

[0094] I: For each power battery case design model, the review score after the review analysis of the power battery case design model is obtained.

[0095] II: Based on the review score corresponding to each power battery case design model, the power battery case target model with the highest review score is determined from the at least one power battery case design model.

[0096] Here, the review analysis includes cost analysis, mass production feasibility analysis, modular development demand analysis, supplier resource analysis, etc. of the power battery case design model. The review score after the review analysis is determined by manual review analysis.

[0097] For the above step I-step II, in specific implementation, for each power battery case design model, the review score after the manual review analysis of the power battery case design model is obtained. Based on the review score corresponding to each power battery case design model, the power battery case target model with the highest review score is determined from the at least one power battery case design model. In this way, the optimal power battery case target model is determined from the at least one power battery case design model through the review score, so as to determine the design scheme of the power battery case to be designed according to the power battery case target model.

[0098] ​The method for determining a power battery box design model provided in the embodiments of the present application first acquires design parameters of a power battery box to be designed; then, at least one power battery box design model corresponding to the design parameters is determined from a power battery box model library based on the design parameters; and the power battery box model library comprises a plurality of pre-constructed power battery box original models, and a design parameter characteristic value of each power battery box original model is determined by a pre-trained characteristic value determination model.

[0099] The present application can quickly obtain a plurality of battery box design models by inputting different design parameters of power battery boxes to be designed, so that a user can determine a design scheme of the power battery box to be designed according to the power battery box design model, develop the power battery box to be designed according to the power battery box design model, and accelerate the development speed of the power battery box by quickly determining the design model of the power battery box to realize agile design of the power battery box and shorten the development cycle of the power battery.

[0100] Please refer to Figure 2 、 Figure 3 , Figure 2 FIG. 1 is a structural schematic diagram of a determination device of a power battery box design model provided in the embodiments of the present application, Figure 3 FIG. 2 is another structural schematic diagram of the determination device of the power battery box design model provided in the embodiments of the present application. As shown in FIG. 2, the determination device 200 comprises: Figure 2

[0101] a design parameter acquisition module 201 configured to acquire design parameters of a power battery box to be designed;

[0102] a design model determination module 202 configured to determine at least one power battery box design model corresponding to the design parameters from a power battery box model library based on the design parameters; and the power battery box model library comprises a plurality of pre-constructed power battery box original models, and a design parameter characteristic value of each power battery box original model is determined by a pre-trained characteristic value determination model.

[0103] Further, the design parameters comprise an outer envelope space parameter, an inner envelope space parameter, a box structure form parameter, a product design rule parameter, a product function performance parameter and a box manufacturing feasibility parameter of the power battery box to be designed.

[0104] Further, when the design model determination module 202 is configured to determine at least one power battery box design model corresponding to the design parameters from a power battery box model library based on the design parameters, the design model determination module 202 is further configured to: ​

[0105] determine an initial structure of the to-be-designed power battery box based on the outer envelope space parameter and the inner envelope space parameter, and screen a first candidate model from a plurality of power battery box original models in the power battery box model library based on the initial structure; wherein a box structure of the first candidate model is the initial structure;

[0106] determine a second candidate model corresponding to the box structure form parameter from the first candidate model based on the box structure form parameter;

[0107] determine a third candidate model corresponding to the product design rule parameter from the second candidate model based on the product design rule parameter;

[0108] determine a fourth candidate model corresponding to the product function performance parameter from the third candidate model based on the product function performance parameter;

[0109] determine at least one power battery box design model from the fourth candidate model based on the box manufacturing feasibility parameter.

[0110] Referring to Figure 3 , the determination device 200 further comprises a design model construction module 203, which is configured to construct each power battery box original model in the power battery box model library by the following steps:

[0111] obtain a plurality of power battery box product design data;

[0112] For each power battery box product design data, input the power battery box product design data into the characteristic value determination model, determine the corresponding design parameter characteristic value, and generate the power battery box original model corresponding to the power battery box product design data based on the design parameter characteristic value.

[0113] Referring to Figure 3 , the determination device 200 further comprises a model training module 204, which is configured to train the characteristic value determination model by the following steps:

[0114] obtain a plurality of product design sample data and a design parameter sample characteristic value corresponding to each product design sample data;

[0115] For each product design sample data, input the product design sample data into the characteristic value original determination model, and determine the design parameter preset characteristic value corresponding to the product design sample data;

[0116] The design parameter sample feature value corresponding to each product design sample data is compared with the design parameter preset feature value, and a loss function of the feature value original determination model in the current state is calculated;

[0117] Based on the loss function of the feature value original determination model, the model parameters of the feature value original determination model are continuously adjusted until the feature value original determination model reaches a convergence state, and the feature value determination model is obtained.

[0118] Referring to Figure 3 , the determination device 200 further includes a design model screening module 205, after determining at least one power battery box design model corresponding to the design parameters from the power battery box model library based on the design parameters, the design model screening module 205 is used for:

[0119] For each power battery box design model, an evaluation score after evaluation analysis of the power battery box design model is obtained;

[0120] Based on the evaluation score corresponding to each power battery box design model, a power battery box target model with the highest evaluation score is determined from at least one of the power battery box design models.

[0121] Referring to Figure 4 , Figure 4 A structural schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 4. Figure 4 As shown in FIG. 4, the electronic device 400 includes a processor 410, a memory 420 and a bus 430.

[0122] The memory 420 stores machine readable instructions executable by the processor 410, when the electronic device 400 is running, the processor 410 and the memory 420 communicate through the bus 430, and the machine readable instructions are executed by the processor 410, which can execute the steps of the determination method of the power battery box design model in the method embodiment as shown in the above Figure 1 The specific implementation can be referred to the method embodiment, which will not be repeated here.

[0123] The embodiment of the present application further provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is run by the processor, which can execute the steps of the determination method of the power battery box design model in the method embodiment as shown in the above Figure 1 The specific implementation can be referred to the method embodiment, which will not be repeated here.

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0125] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some communication interfaces, devices or units, and can be electrical, mechanical or other forms.

[0126] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0127] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0128] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solutions of the present application or the essential part or part of the technical solutions that make contributions to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and various program code storage media.

[0129] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the same. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that any skilled person in the art can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features, within the technical scope disclosed by the present application. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for determining a design model for a power battery housing, characterized in that, The determination method includes: Obtain the design parameters of the power battery box to be designed; Based on the design parameters, at least one power battery box design model corresponding to the design parameters is determined from the power battery box model library; wherein, the power battery box model library includes multiple pre-built original power battery box models, and the design parameter feature values ​​of each original power battery box model are determined by a pre-trained feature value determination model; The original model of each power battery box in the power battery box model library is constructed by following these steps: Obtain design data for multiple power battery enclosure products; For each power battery box product design data, the power battery box product design data is input into the feature value determination model to determine the corresponding design parameter feature values, and the original power battery box model corresponding to the power battery box product design data is generated based on the design parameter feature values. The model is determined by training the eigenvalues ​​using the following steps: Acquire multiple product design sample data and the corresponding design parameter sample feature values ​​for each product design sample data; For each product design sample data, the product design sample data is input into the feature value original determination model to determine the preset feature value of the design parameter corresponding to the product design sample data; Compare the sample feature values ​​of the design parameters corresponding to each product design sample data with the preset feature values ​​of the design parameters, and calculate the loss function of the original model for determining the feature values ​​in the current state; Based on the loss function of the original feature value determination model, the model parameters of the original feature value determination model are continuously adjusted until the original feature value determination model reaches a convergent state, thus obtaining the feature value determination model.

2. The determination method according to claim 1, characterized in that, The design parameters include the outer envelope space parameters, inner envelope space parameters, box structure parameters, product design rule parameters, product functional performance parameters, and box manufacturing feasibility parameters of the power battery box to be designed.

3. The determination method according to claim 2, characterized in that, The step of determining at least one power battery box design model corresponding to the design parameters from the power battery box model library based on the design parameters includes: The initial structure of the power battery box to be designed is determined based on the outer envelope space parameters and the inner envelope space parameters, and a first candidate model is selected from multiple original power battery box models in the power battery box model library based on the initial structure; wherein, the box structure of the first candidate model is the initial structure; Based on the box structure form parameters, a second candidate model corresponding to the box structure form parameters is determined from the first candidate model; Based on the product design rule parameters, a third candidate model corresponding to the product design rule parameters is determined from the second candidate model; Based on the product functional performance parameters, a fourth candidate model corresponding to the product functional performance parameters is determined from the third candidate model; Based on the feasibility parameters for battery box manufacturing, at least one design model for the power battery box is determined from the fourth candidate models.

4. The determination method according to claim 1, characterized in that, After determining at least one power battery housing design model corresponding to the design parameters from the power battery housing model library based on the design parameters, the determination method further includes: For each power battery box design model, obtain the review score after review and analysis of that power battery box design model; Based on the review score corresponding to each power battery housing design model, the target power battery housing model with the highest review score is determined from at least one of the power battery housing design models.

5. A device for determining the design model of a power battery housing, characterized in that, The determining device includes: The design parameter acquisition module is used to acquire the design parameters of the power battery box to be designed. The design model determination module is used to determine at least one power battery box design model corresponding to the design parameters from the power battery box model library based on the design parameters; wherein, the power battery box model library includes multiple pre-built original power battery box models, and the design parameter feature values ​​of each original power battery box model are determined by a pre-trained feature value determination model; The determining device further includes a design model building module, which is used to build an original model of each power battery box in the power battery box model library through the following steps: Obtain design data for multiple power battery enclosure products; For each power battery box product design data, the power battery box product design data is input into the feature value determination model to determine the corresponding design parameter feature values, and the original power battery box model corresponding to the power battery box product design data is generated based on the design parameter feature values. The determining device further includes a model training module, which is used to train the feature value determining model through the following steps: Acquire multiple product design sample data and the corresponding design parameter sample feature values ​​for each product design sample data; For each product design sample data, the product design sample data is input into the feature value original determination model to determine the preset feature value of the design parameter corresponding to the product design sample data; Compare the sample feature values ​​of the design parameters corresponding to each product design sample data with the preset feature values ​​of the design parameters, and calculate the loss function of the original model for determining the feature values ​​in the current state; Based on the loss function of the original feature value determination model, the model parameters of the original feature value determination model are continuously adjusted until the original feature value determination model reaches a convergent state, thus obtaining the feature value determination model.

6. The determining device according to claim 5, characterized in that, The design parameters include the outer envelope space parameters, inner envelope space parameters, box structure parameters, product design rule parameters, product functional performance parameters, and box manufacturing feasibility parameters of the power battery box to be designed.

7. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. The machine-readable instructions are executed by the processor to perform the steps of the method for determining the design model of the power battery housing as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, performs the steps of the method for determining the design model of the power battery housing as described in any one of claims 1 to 4.

Images