Electric motor truck power system energy efficiency optimization method based on deep learning

Abstract

The application relates to the field of computer technology application, in particular to a power system energy efficiency optimization method for an electric mine truck based on deep learning, which comprises the following steps: obtaining to-be-processed information; obtaining corresponding driving resource estimated value as the initial driving resource estimated value of a mobile object based on the driving resource influence parameter information and the driving resource prediction model of the mobile object; correcting the initial driving resource estimated value based on the user information of the mobile object and the target driving resource estimated value to obtain the corresponding correction result as the target driving resource estimated value; generating the driving resource mapping relationship diagram of the mobile object and performing visual display based on the target driving resource estimated value; and generating the control instruction for the power system of the mobile object based on the driving resource mapping relationship diagram and outputting the generated control instruction in response to receiving the control instruction generation information. The application can optimize the energy efficiency of the power system of the electric mine truck.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computer technology application, and particularly relates to a power system energy efficiency optimization method for electric mine truck based on deep learning. BACKGROUND

[0002] With the accelerated penetration of electrification in the field of transportation, special transport equipment with fixed operation path characteristics is undergoing systematic power transformation, and the electrification of mine trucks (mine trucks) has become a core measure for mine green upgrading. However, electric mine trucks face severe energy consumption management challenges in complex working conditions in open-pit mines: unstructured terrain leads to dynamic changes in slope (-15% to +25%), and heavy load transportation causes continuous high power demand (peak value >800kW). In this context, developing intelligent energy distribution strategies based on working condition perception to achieve spatial-time two-dimensional optimization scheduling of limited power of power batteries has become a decisive factor for improving transportation efficiency. SUMMARY

[0003] To solve the above technical problems, the technical scheme adopted by the present application is as follows:

[0004] The embodiment of the present application provides a power system energy efficiency optimization method for electric mine truck based on deep learning, which is executed by a computer program, and the method comprises the following steps:

[0005] S100, obtaining to-be-processed information; the to-be-processed information includes driving resource influence parameter information of a mobile object and user information, and the driving resource influence parameter information includes terrain data of a target path and attribute parameters of the mobile object.

[0006] S200, obtaining a corresponding driving resource estimated value based on the driving resource influence parameter information of the mobile object and a driving resource prediction model, as an initial driving resource estimated value of the mobile object.

[0007] S300, correcting the initial driving resource estimated value based on the user information of the mobile object to obtain a corresponding correction result as a target driving resource estimated value.

[0008] S400, generating a driving resource mapping relationship diagram of the mobile object based on the target driving resource estimated value and a mapping relationship diagram, and performing visual display; wherein the driving resource mapping relationship diagram contains a mapping relationship between the terrain data and the driving resource.

[0009] S500, the mapping relationship diagram generates a control instruction for the power system of the mobile object based on the driving resource mapping relationship diagram in response to receiving control instruction generation information, and outputs the generated control instruction.

[0010] The present application has at least the following advantages:

[0011] The power system energy efficiency optimization method based on deep learning provided by the embodiment of the present application can obtain the initial driving resource estimation value required by the mobile object to drive the target path based on the terrain data of the target path and the attribute parameters of the mobile object based on deep learning, correct the initial driving resource estimation value based on user information, and generate the control instruction of the power system acting on the mobile object based on the driving resource estimation value and the received control instruction generation information. In actual application scenarios, the prediction accuracy can be improved, and the energy consumption deviation caused by the operation difference of different people can be eliminated, thereby effectively optimizing the energy efficiency of the power system of the electric mine truck.

[0012] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0014] Figure 1 The flowchart of the power system energy efficiency optimization method based on deep learning provided by the embodiment of the present application. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0017] It is to be understood that some of the example embodiments are described in terms of a process or method depicted as a flowchart. Although each step in a flowchart can be identified with a reference number and can describe an operation, which can be implemented, for example, in hardware, software or a combination of hardware and software, many of these steps require no operation, but can simply be a reordering of existing operations already performed. These references are merely aids to better illustrate the example embodiments; they are not intended to limit the example embodiments in any way. Further, one or more steps can be carried out in parallel, concurrently or by means of a cloud computing resource or service provided by a service-oriented architecture. In addition, the order of the steps can be re-arranged. A process is terminated when its operations are completed, but could also terminate without having completed its steps. A process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0018] The embodiment of the present application provides a deep learning-based electric mine truck power system energy efficiency optimization method, which is executed by a computer program. Figure 1 As shown in the figure, the method comprises the following steps:

[0019] S100, acquiring to-be-processed information; the to-be-processed information comprises driving resource influence parameter information of a mobile object and user information, and the driving resource influence parameter information comprises topographic data of a target path and attribute parameters of the mobile object.

[0020] In the embodiment of the present application, the mobile object is an electric mine truck. The driving resource refers to an energy consumption value, i.e. power consumption. The target path is a road that needs to be passed through by the mobile object.

[0021] In the embodiment of the present application, the topographic data of the target path can comprise path length, road surface damage information, uphill information and road surface material. In an illustrative embodiment, the topographic data can be data obtained by field measurement. In a preferred embodiment, the topographic data can be obtained based on vibration sensor monitoring data and a high-precision map. The vibration sensor monitoring data can obtain pit information of the target path, and the high-precision map can obtain other topographic data of the target path.

[0022] In the embodiment of the present application, the attribute parameters of the mobile object can comprise load, residual power and battery residual life.

[0023] In the embodiment of the present application, the uphill is a slope that needs to be climbed by the mobile object. The road surface material of the target path can be the same or can be different, which can be determined based on actual conditions.

[0024] S200, acquiring a corresponding driving resource estimation value based on the driving resource influence parameter information of the mobile object and a driving resource prediction model.

[0025] S200, acquiring a corresponding driving resource estimation value based on the driving resource influence parameter information of the mobile object and a driving resource prediction model.

[0026] In the embodiments of the present application, the travel resource prediction model can be a trained deep learning model, and the deep learning model can be an existing deep learning model, for example, a hybrid network model of a convolutional neural network and a long short-term memory artificial neural network.

[0027] In the embodiments of the present application, the travel resource prediction model can be trained based on a training data set, and the training data set can be a historical data set collected and an enhanced data set obtained by data enhancement on the historical data set. Each data includes travel resource impact parameter information and an actual energy consumption value of a corresponding mobile object. In the training process, the original deep learning model is trained by taking the encoded features corresponding to the travel resource impact parameter information as input information and taking the actual energy consumption value as a label.

[0028] As known by those skilled in the art, any method for training the original deep learning model based on the training data set to obtain the trained deep learning model falls within the protection scope of the present application. The data enhancement method can be an existing data enhancement method, for example, generating terrain data based on a GAN network.

[0029] Further, S200 can specifically include:

[0030] S201, generating a path state feature vector and an attribute state feature vector of the mobile object based on the travel resource impact parameter information.

[0031] S202, inputting the path state feature vector and the attribute state feature vector into the travel resource prediction model to obtain a corresponding travel resource estimation value.

[0032] The path state feature vector includes a path length feature, a road surface damage feature, an uphill feature, and a road surface material feature, wherein the path length feature is determined based on path length and set path length level determination information, the road surface damage feature is determined based on road surface damage representation value and set road surface damage level determination information, the uphill feature is determined based on slope feature index and set uphill level determination information, and the road surface material feature is determined based on road surface material representation value and set road surface material level determination information.

[0033] In an embodiment of the present application, the set path length level determination information can be obtained based on existing data; for example, it can be obtained based on path length information in the training data set, and specifically, the path length can be divided into different levels based on the path length information in the training data set, each level corresponding to a path length range, and the specific division method can be realized by using an existing method.

[0034] The setting road surface damage level determination information can be obtained based on the road surface damage information in the training data set, and specifically, the road surface damage degree can be divided into different levels based on the road surface damage information in the training data set, and each level corresponds to a road surface damage representation value range, and the specific division method can be realized by using an existing method.

[0035] The setting uphill lane level determination information can be obtained based on the uphill lane information in the training data set, and specifically, the uphill lane can be divided into different levels based on the uphill lane information in the training data set, and each level corresponds to a slope feature index range, and the specific division method can be realized by using an existing method.

[0036] The setting road surface material level determination information can be obtained based on the road surface material information in the training data set, and specifically, the uphill road surface material can be divided into different levels based on the road surface material information in the training data set, and each level corresponds to a road surface material representation value range.

[0037] In the embodiment of the application, the attribute state feature vector can include a load feature, a remaining power feature, and a battery remaining life feature, wherein the load feature is determined based on the load and the setting load level determination information, the remaining power feature is determined based on the remaining power and the setting remaining power level determination information, and the battery remaining life feature is determined based on the battery remaining life and the setting battery remaining life level determination information.

[0038] In the embodiment of the application, the setting load level determination information, the setting remaining power level determination information, and the setting battery remaining life level determination information can all be determined based on the load information, the remaining power information, and the battery remaining life information in the training data set. Specifically, the load can be divided into different levels based on the load information in the training data set, and each level corresponds to a load range. The load can be divided into different levels based on the remaining power information in the training data set, and each level corresponds to a remaining power range. The load can be divided into different levels based on the battery remaining life information in the training data set, and each level corresponds to a battery remaining life range.

[0039] In the embodiment of the application, the levels of different features can be distinguished by using different identification values.

[0040] Further, in the embodiment of the application, the road surface damage information can include pit information, and the pit information includes pit depth and edge angle; the road surface damage representation value of the moving object includes a first pit representation value and a second pit representation value, wherein the first representation value is used to represent the edge steepness of the pit, and the second representation value is used to represent the roughness of the road surface.

[0041] Specifically, the first pit representation value satisfies the following condition: .

[0042] wherein CV1 is the first pit characterization value, d i is the depth of the ith pit, θ i is the edge angle of the ith pit, f1() is a first function expression, i is an integer from 1 to m1, and m1 is the number of pits; f1(d i , θ i ) = d i x tan θ i .

[0043] In the embodiments of the present application, the edge angle of the pit is equal to the included angle between the edge of the pit and the vertical direction.

[0044] Further, the second pit characterization value satisfies the following condition: .

[0045] wherein CV2 is the second pit characterization value, f2() is a second function expression, N j is the number of pits in the jth unit path length in the target path, j is an integer from 1 to n, n is the number of unit path lengths, Avgd j is the average depth of the pits in the jth unit path length, wp j is the pit weight corresponding to the jth unit path length, f2(N j , Avgd j ) = N j x Avgd j .

[0046] In the embodiments of the present application, the unit path length can be set based on actual needs, for example, it can be 100 meters.

[0047] Further, in the embodiments of the present application, , N b is the number of pits in the bth unit path length in the target path, b is an integer from 1 to n, and Avgd b is the average depth of the pits in the bth unit path length.

[0048] Further, in the embodiments of the present application, the uphill information can include the uphill length and the slope angle.

[0049] As known by those skilled in the art, the road surface damage feature can include two feature values, i.e., two feature values determined based on the first pit characterization value and the second pit characterization value, respectively.

[0050] wherein the slope feature index of the moving object includes a first slope feature index and a second slope feature index, wherein the first slope feature index represents the degree of elevation change of the road surface, and the second slope feature index represents the flatness of the road surface.

[0051] Further, the first slope feature index satisfies the following condition: .

[0052] wherein, RV1 is the first slope feature index, f3() is a third function expression, L r is a length of an rth uphill in the uphill information, r is an integer from 1 to m2, m2 is a number of the uphill in the uphill information, a r is a slope angle of the rth uphill; f3(L r , a r ) = L r × Sin a r .

[0053] Further, the second slope feature index satisfies the following condition: .

[0054] wherein, f4() is a fourth function expression, Avg a is an average slope angle based on the uphill information, Max a is a maximum slope angle in the uphill information.

[0055] In the embodiment of the present application, f4(Avg a, Max a) = w1×Avg a + w2×Max a, wherein, w1 is a weight corresponding to the average slope angle, w2 is a weight corresponding to the maximum slope angle, w1 and w2 can be test values, and w1 + w2 = 1. In one illustrative embodiment, w1 can be greater than w2.

[0056] As known by those skilled in the art, the uphill feature can include two feature values, i.e., two feature values determined based on the first slope feature index and the second slope feature index respectively.

[0057] Further, in the embodiment of the present application, the road surface material representation value can satisfy the following condition: .

[0058] wherein, MV is the road surface material representation value, L s is a resistance coefficient of an sth road surface material in the target path, s is an integer from 1 to q, q is a number of types of road surface materials included in the target path, W s is a weight of the sth road surface material, which can be a test value, and generally, the greater the resistance coefficient of the road surface material, the greater the weight.

[0059] S300, based on user information of the mobile object, correcting the initial driving resource estimation value to obtain a corresponding correction result as a target driving resource estimation value.

[0060] In the embodiment of the present application, the user information corresponding to the mobile object is the ID of the user who controls the mobile object, i.e., the ID of the driver. The ID of the user can be the identity of the user, for example, the driver's license number.

[0061] Further, S300 can specifically include:

[0062] Based on the user information, a correction coefficient corresponding to the user information is obtained.

[0063] The initial driving resource estimation value of the mobile object is corrected by using the correction coefficient, and the target driving resource estimation value is obtained.

[0064] Further, the obtaining of the correction coefficient based on the user information specifically includes:

[0065] If the user information does not exist in the preset correction coefficient reference information table, the correction coefficient corresponding to the user information is determined as a reference correction coefficient; if the user information exists in the preset correction coefficient reference information table, the correction coefficient of the user information in the preset correction coefficient reference information table is taken as the correction coefficient corresponding to the user information.

[0066] In the embodiment of the present application, the preset correction coefficient reference information stores the correction coefficient corresponding to each user. The correction coefficient of each user is determined based on the driving behavior habit of the user. Users with different driving behavior habits have different correction coefficients. The correction coefficient of each user can be determined based on actual conditions or historical operation behaviors.

[0067] In the embodiment of the present application, the reference correction coefficient can be a coefficient greater than 1, which can be an empirical value.

[0068] In the embodiment of the present application, the target driving resource estimation value can be equal to the product of the correction coefficient and the initial driving resource estimation value.

[0069] In the embodiment of the present application, the initial driving resource estimation value is predicted based on the driving behavior habit of the user, which can eliminate the energy consumption deviation caused by the operation difference of different people, so that the obtained driving resource estimation value is more accurate.

[0070] S400, based on the target driving resource estimation value, a driving resource mapping relationship diagram of the mobile object is generated and visually displayed; wherein the driving resource mapping relationship diagram contains the mapping relationship between the terrain data and the driving resource.

[0071] In the embodiment of the present application, the driving resource mapping relationship diagram can be obtained based on the existing method, as long as the available driving resource corresponding to each feature section on the target path can be displayed.

[0072] In the embodiments of the present application, the characteristic road segments include flat road segments, uphill ramps, downhill ramps and potholes. The available driving resources corresponding to each flat road segment, uphill ramp, downhill ramp and pothole are displayed in the driving resource mapping relationship diagram.

[0073] As known by those skilled in the art, the present application knows that the pothole should belong to a region, but for the convenience of description, the present application approximates the pothole as a micro road segment, but this does not affect the essential scheme of the present application.

[0074] In an illustrative embodiment of the present application, the available driving resources of each characteristic road segment can be obtained based on the trained driving resource allocation model, and specifically can be obtained by the following steps:

[0075] S401, input the path state feature vector, attribute state feature vector and target driving resource estimate value of the mobile object into the trained driving resource allocation model to obtain the available driving resources of the uphill road segment and the available driving resources of the pothole road segment.

[0076] The trained driving resource allocation model can be a deep learning model, which can be trained based on a historical data set. In the training process, the input of the model is the path state feature vector, attribute state feature vector and actual driving resource added with noise of the mobile object, and the output is the available driving resources of the uphill road segment and the available driving resources of the pothole road segment. The added noise can be subject to a prediction error distribution, such as a Gaussian distribution N(0, σ²).

[0077] As known by those skilled in the art, the specific training method of the driving resource allocation model can belong to the prior art.

[0078] S402, the remaining driving resources obtained by subtracting the available driving resources of the uphill road segment and the available driving resources of the pothole road segment from the target driving resource estimate value are used as the available driving resources of the flat road segment and the downhill ramp.

[0079] S403, based on the available driving resources of the uphill road segment, the available driving resources corresponding to each uphill ramp in the target path are determined; based on the available driving resources of the pothole road segment, the available driving resources corresponding to each pothole in the target path are determined; and based on the available driving resources of the flat road segment and the downhill ramp, the available driving resources of each flat road segment and each uphill ramp in the target path are determined.

[0080] Specifically, the available driving resources corresponding to each uphill ramp can satisfy the following condition: UR r = (f3(L r , α r ) / RV1) × TUR.

[0081] Wherein, UR rTUR is the available driving resource of the uphill road section.

[0082] The available driving resource corresponding to each pit can satisfy the following condition: PR i = (f1(d i , θ i ) / CV1) x TPR.

[0083] wherein PR i is the available driving resource of the i-th pit in the target path, and TPR is the available driving resource of the pit section.

[0084] In the embodiments of the present application, to simplify the calculation, the resource saving or braking demand information of the downhill is not considered, and the flat section and the downhill are regarded as the same section. Specifically, the available driving resource of each flat section or downhill can satisfy the following condition:

[0085] FR = WF x (LF / TLF) x TFR.

[0086] wherein FR is the available driving resource of each flat section or each downhill, LF is the path length of each flat section or each downhill, TLF is the sum of the path lengths of all flat sections and the downhills in the target path, TFR is the available driving resource of the flat section and the downhill, WF is the weight corresponding to each flat section or each downhill, all flat sections have the same weight, and all downhills have the same weight, and the specific weight can be determined based on the actual situation, for example, the weight of the flat section can be greater than the weight of the downhill.

[0087] S500, in response to receiving the control instruction generation information, generating a control instruction for the power system of the mobile object based on the driving resource mapping relationship diagram, and outputting the generated control instruction.

[0088] In the embodiments of the present application, the control instruction for controlling the power system of the mobile object can be generated based on the available driving resource of each feature section. The control instruction can be set based on actual needs, as long as the energy consumption of each feature section is less than or equal to the corresponding available driving resource, for example, it can include torque distribution instructions, power limiting instructions, shift strategy instructions, etc. acting on each feature section.

[0089] In the embodiment of the present application, the control instruction generation information can be generated by user input, or automatically triggered based on the control system setting of the mobile object, that is, once the travel resource mapping relationship graph is detected to be generated, the control instruction generation information is automatically triggered. The control instruction is sent to the power system of the mobile object to guide the power output of the power system. It should be noted that in the embodiment of the present application, the control instruction indicates a reference information, and is not an instruction for forcibly limiting the power system to output according to the control instruction. In actual application scenarios, the user can change the output of the power system based on the driving behavior habit of the user, that is, the final decision right of the driver is reserved.

[0090] Further, the embodiment of the present application further includes the following steps:

[0091] S600, when receiving the monitoring data obtained by monitoring the travel resource of the mobile object in the travel process, updating the current travel resource mapping relationship graph based on the received monitoring data, and generating the control instruction for the power system of the mobile object based on the updated travel resource mapping relationship graph, the initial value of the current travel resource mapping relationship graph is the initial travel resource mapping relationship graph.

[0092] In the embodiment of the present application, the monitoring data can be obtained by the energy consumption monitoring system on the mobile object.

[0093] Further, S600 specifically includes:

[0094] S601, based on the received monitoring data, judging whether the current characteristic road section currently passed by the mobile object is the last road section of the target path, if yes, calculating the travel resource actually used by the mobile object passing through the target path, and executing S606; if not, executing S602.

[0095] S602, obtaining the used travel resource used by the mobile object passing through the current characteristic road section as the current used travel resource, and comparing the current used travel resource with the current available travel resource corresponding to the current characteristic road section, if the used travel resource is greater than the corresponding current available travel resource, executing S603, otherwise, executing S601.

[0096] S603, updating the current available travel resource based on the current used travel resource, that is, subtracting the current used travel resource from the current available travel resource to obtain the updated available travel resource, and executing S604; wherein the initial value of the current available travel resource is the target travel resource estimation value.

[0097] ​S604, taking the updated available driving resource as the current available driving resource, determining a current feature vector of the mobile object based on the terrain data and attribute parameters of the current remaining driving path of the mobile object, and updating the current driving resource mapping relationship graph based on the current feature vector and the current available driving resource, and performing S605.

[0098] In the embodiment of the present application, the current feature vector includes a current path state feature vector and a current attribute state feature vector, and the current feature vector can be obtained in the manner as described in the implementation of S200, i.e., the current path state feature vector is obtained based on the terrain data contained in the current remaining driving path, and the current attribute state feature vector is obtained based on the current attribute parameters of the mobile object. The current available driving resource can be obtained in the manner as described in the implementation of S400, and the specific implementation of updating the current driving resource mapping relationship graph also refers to the specific implementation of S400. The initial value of the current driving resource mapping relationship graph is the driving resource mapping relationship graph generated in S400.

[0099] In the embodiment of the present application, the updating of the driving resource mapping relationship graph can be performed in the manner of edge computing plus cloud cooperation.

[0100] S605, based on the current driving resource mapping relationship graph, generating a control instruction for the power system of the mobile object, and performing S601.

[0101] S606, if the difference between the actual driving resource used by the mobile object through the target path and the corresponding target driving resource estimation value is greater than 0, and the difference is greater than a set value, setting the current operation identifier of the user corresponding to the mobile object as a first identifier, otherwise, i.e., if the actual driving resource used by the mobile object through the target path is less than or equal to the corresponding target driving resource estimation value, or if the actual driving resource used by the mobile object through the target path is greater than the corresponding target driving resource estimation value, but the difference is less than or equal to the set value, setting the current operation identifier of the user corresponding to the mobile object as a second identifier, storing the current operation identifier in the corresponding operation identifier record set, and exiting the current control program, i.e., ending the power system energy consumption optimization process of the target path this time.

[0102] In the embodiment of the present application, the set value can be set based on actual needs. The initial value of the operation identifier record set of each user can be empty. The first identifier and the second identifier can be represented by different numbers. It is known to those skilled in the art that the operation identifier record set is used to record the difference information between the actual driving resource used by the user each time through a certain target path and the corresponding target driving resource estimation value.

[0103] Further, in the embodiment of the present application, the correction factor of each user in the preset correction factor reference information table can be updated based on the corresponding operation identifier record set, and specifically can be updated based on the last Q operation identifiers in the operation identifier record set. Further, the correction factor of each user can be updated through the following steps:

[0104] S1, obtaining the number of first identifiers in the last Q operation identifiers in the operation identifier record corresponding to the user, if the number of first identifiers is greater than a set number, it indicates that the operation behavior habit of the user has changed, and the current correction factor needs to be updated, and S2 is executed; otherwise, the current correction factor of the user is not updated.

[0105] In the embodiment of the present application, Q can be an empirical value. The initial value of the current correction factor of the user is the reference correction factor. The set number can be an empirical value, for example, can be equal to c×Q, and c can be a number greater than 0.5, for example, can be set to 0.8.

[0106] S2, updating the current correction factor of the user in the following manner: k=kc+△k.

[0107] Wherein, k is the updated correction factor of the user, kc is the current correction factor of the user, and △k is a preset correction factor change value, which can be an empirical value.

[0108] In theory, the driving behavior habit of the user is generally fixed, but it is not excluded that the driving behavior habit of the user changes, for example, the target path of the mobile object operated by the user changes, so that the terrain data changes greatly, and / or the attribute of the mobile object changes, resulting in a certain change in the driving behavior habit of the user.

[0109] In the embodiment of the present application, the correction factor of each user can be updated based on the corresponding current operation identifier record set, so that the correction factor of the user is more accurate.

[0110] As known by those skilled in the art, all data that need to be processed in the embodiment of the present application can be obtained from the corresponding device through the computer interface of the computer device.

[0111] The embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are arranged to execute the method described in the embodiment of the present application.

[0112] The embodiment of the present application also provides a computer readable storage medium, which stores computer executable instructions, and the computer instructions are used to execute the method described in the embodiment of the present application.

[0113] It should be understood that the various forms of flow shown above can be used to reorder, add, or delete steps. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present application can be achieved, which is not limited herein.

[0114] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A deep learning-based electric mine truck power system energy efficiency optimization method, characterized in that, The method is executed by a computer program, and the method comprises the following steps: S100, obtaining to-be-processed information; the to-be-processed information comprises travel resource influence parameter information of a mobile object and user information, the travel resource influence parameter information comprises terrain data of a target path and attribute parameters of the mobile object; the terrain data of the target path comprises path length, road damage information, uphill information and road surface material; the attribute parameters of the mobile object comprise load, residual power and battery residual life; S200, obtaining corresponding travel resource estimated values based on the travel resource influence parameter information of the mobile object and a travel resource prediction model, as initial travel resource estimated values of the mobile object; S300, correcting the initial travel resource estimated values based on the user information of the mobile object to obtain corresponding correction results, as target travel resource estimated values; S400, generating a travel resource mapping relationship diagram of the mobile object based on the target travel resource estimated values and performing visual display; wherein the travel resource mapping relationship diagram comprises a mapping relationship between terrain data and travel resources; S500, in response to receiving control instruction generation information, generating a control instruction for a power system of the mobile object based on the travel resource mapping relationship diagram, and outputting the generated control instruction.

2. The method of claim 1, wherein, S200 specifically comprises: S201, generating a path state feature vector and an attribute state feature vector of the mobile object based on the travel resource influence parameter information; S202, inputting the path state feature vector and the attribute state feature vector into the travel resource prediction model to obtain corresponding travel resource estimated values; The path state feature vector comprises a path length feature, a road damage feature, an uphill feature and a road surface material feature, wherein the path length feature is determined based on the path length and set path length level determination information, the road damage feature is determined based on a road damage representation value and set road damage level determination information, the uphill feature is determined based on a slope feature index and set uphill level determination information, and the road surface material feature is determined based on a road surface material representation value and set road surface material level determination information; The attribute state feature vector comprises a load feature, a residual power feature and a battery residual life feature, wherein the load feature is determined based on the load and set load level determination information, the residual power feature is determined based on the residual power and set residual power level determination information, and the battery residual life feature is determined based on the battery residual life and set battery residual life level determination information.

3. The method of claim 1, wherein, The road damage information comprises pit information, and the pit information comprises pit depth and edge angle; the road damage representation value of the mobile object comprises a first pit representation value and a second pit representation value; The first pit characterization value satisfies the following condition: ; wherein CV1 is a first pit characterization value, d i is a depth of the i-th pit, θ i is an edge angle of the i-th pit, f1() is a first function expression, i has a value of 1 to m1, and m1 is a number of pits; The second pit representation value satisfies the following condition: ； wherein CV2 is a second pit characterization value, f2() is a second function expression, N j is a number of pits within the jth unit path length in the target path, j has a value of 1 to n, n is a number of unit path lengths, Avgd j is an average depth of pits within the jth unit path length, wp j is a pit weight corresponding to the jth unit path length.

4. The method of claim 3, wherein, f1(d i , θ i ) = d i × tan θ i .

5. The method of claim 3, wherein, f2(N j , Avgd j ) = N j × Avgd j .

6. The method of claim 1, wherein, The uphill information comprises uphill length and slope angle; the slope feature index of the mobile object comprises a first slope feature index and a second slope feature index; The first slope characteristic index satisfies the following condition: ; Wherein, RV1 is the first slope characteristic index, f3( ) is the third function expression, L r is the length of the rth ramp in the ramp information, r is valued from 1 to m2, m2 is the number of ramps in the ramp information, α r is the slope angle of the rth ramp. The second slope feature index satisfies the following condition: ; Wherein f4() is a fourth function expression, Avgα is an average slope angle based on the uphill information, and Maxα is a maximum slope angle in the uphill information.

7. The method of claim 6, wherein, f3(L r , a r ) = L r x Sin a r .

8. The method of claim 6, wherein, f4 (Avg a, Max a) = w1 x Avg a + w2 x Max a, wherein w1 is a weight corresponding to the average slope angle, and w2 is a weight corresponding to the maximum slope angle.

9. The method of claim 1, wherein, S300 specifically comprises: Based on the user information, a correction coefficient corresponding to the user information is obtained. The initial driving resource estimation value of the mobile object is corrected by using the correction coefficient to obtain the target driving resource estimation value.

10. The method of claim 1, wherein, Further comprising the following steps: S600, when receiving monitoring data obtained by monitoring the driving resource of the mobile object in the driving process, updating the current driving resource mapping relationship graph based on the received monitoring data, and generating a control instruction of the power system acting on the mobile object based on the updated driving resource mapping relationship graph, the initial value of the current driving resource mapping relationship graph is the initial driving resource mapping relationship graph.

Images