Construction method and device of residual operation mileage prediction model and electric operation machine

Abstract

The invention discloses a construction method and device of a residual operation mileage prediction model and an electric operation machine, and belongs to the technical field of new energy, the construction method is applied to the electric operation machine, and the construction method comprises the following steps: obtaining a plurality of historical working condition parameters of the electric operation machine, the historical working condition parameters comprise a first historical working condition parameter and a second historical working condition parameter; determining a correlation value of each first historical working condition parameter relative to the second historical working condition parameter based on a preset correlation coefficient algorithm; screening the plurality of first historical working condition parameters according to the correlation value to obtain a target working condition parameter; and based on a regression prediction algorithm, according to the target working condition parameters and the second historical working condition parameters, determining an importance coefficient of each target working condition parameter so as to obtain a residual operation mileage prediction model. According to the invention, the prediction accuracy of the remaining operation mileage can be improved.

Description

Technical Field

[0001] The present application relates to the field of new energy technology, and specifically to a method and device for constructing a remaining operating mileage prediction model and an electric operating machine. Background Art

[0002] With the continuous development of new energy technologies, construction transport options are no longer limited to fuel-powered machinery, with a growing focus on electric machinery. Given the lack of a robust charging infrastructure, the remaining operating range of electric machinery has become a key concern to prevent it from running out of energy during construction transport.

[0003] Existing technologies predict the remaining operating range by estimating the battery status of electric working machinery, determining the average battery power consumption over a specific time period, and thus determining the remaining operating range corresponding to the current remaining power. However, in engineering transportation, the operating conditions of electric working machinery are relatively complex, and different operating conditions correspond to different power consumption. For example, different load conditions on electric working machinery will also result in different battery power consumption. Therefore, existing technologies use the average battery power consumption to determine the remaining operating range under different operating conditions, resulting in low accuracy in predicting the remaining operating range. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method, device and electric working machine for constructing a remaining operating mileage prediction model to solve the problem of low accuracy in predicting the remaining operating mileage in the prior art.

[0005] To achieve the above objectives, the present application provides, in a first aspect, a method for constructing a remaining operating range prediction model, which is applied to electric operating machinery. The method comprises:

[0006] Acquire multiple historical operating condition parameters of the electric operating machine, wherein the historical operating condition parameters include a first historical operating condition parameter and a second historical operating condition parameter, the first historical operating condition parameter including a historical state parameter before a preset prediction point in each historical operating process and a historical predicted full-charge operating mileage corresponding to each historical operating process, and the second historical operating condition parameter including a historical remaining operating mileage after the preset prediction point in each historical operating process;

[0007] Determining, based on a preset correlation coefficient algorithm, a correlation value of each first historical operating condition parameter relative to the second historical operating condition parameter;

[0008] Screening the plurality of first historical operating condition parameters according to the correlation value to obtain the target operating condition parameter;

[0009] Based on the regression prediction algorithm, the importance coefficient of each target operating condition parameter is determined according to the target operating condition parameter and the second historical operating condition parameter to obtain the remaining operating mileage prediction model.

[0010] In an embodiment of the present application, obtaining the historical predicted full-charge operating mileage includes: obtaining the first actual operating mileage and the actual power consumption percentage of the electric operating machinery in each historical operating process; determining the ratio of the first actual operating mileage to the actual power consumption percentage to obtain the single estimated full-charge operating mileage corresponding to each historical operating process; comparing the average of multiple single estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities most recently before each historical operating process with the single estimated full-charge operating mileage corresponding to each historical operating process to determine the target cumulative quantity among the multiple preset cumulative quantities, wherein the target cumulative quantity is the preset cumulative quantity corresponding to the minimum of the difference between the average of multiple single estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities and the single estimated full-charge operating mileage corresponding to each historical operating process; determining the average of multiple single estimated full-charge operating mileages of the target cumulative quantity most recently before each historical operating process as the historical predicted full-charge operating mileage corresponding to the historical operating process.

[0011] In an embodiment of the present application, the acquisition of historical remaining operating mileage includes: acquiring the second actual operating mileage from the preset prediction point to the end of the operation in each historical operation process and the remaining power percentage corresponding to the end of the operation; determining the product value of the single estimated full-charge operating mileage and the remaining power percentage to obtain the estimated operating mileage with remaining power; determining the sum of the second actual operating mileage and the estimated operating mileage with remaining power to obtain the historical remaining operating mileage.

[0012] In an embodiment of the present application, multiple first historical operating condition parameters are screened according to correlation values ​​to obtain target operating condition parameters, including: determining the first historical operating condition parameter among the multiple first historical operating condition parameters whose correlation value is greater than a preset correlation threshold as the target operating condition parameter.

[0013] In an embodiment of the present application, the historical status parameters include parameters related to the operating time, parameters related to the driving speed, parameters related to the operating mileage, parameters related to the power consumption, parameters related to the upper motor speed, parameters related to the upper motor torque, parameters related to the chassis motor speed, parameters related to the chassis motor torque, and parameters related to the ambient temperature of the environment in which the electric operating machinery is located.

[0014] The second aspect of the present application provides a method for predicting the remaining operating mileage, which is applied to an electric working machine. The method includes: constructing a remaining operating mileage prediction model according to the construction method of the remaining operating mileage prediction model; obtaining the target operating condition parameter value of the target operating condition parameter of the electric working machine at the current moment; based on the remaining operating mileage prediction model, predicting the remaining operating mileage of the electric working machine according to the target operating condition parameter value.

[0015] The third aspect of the present application provides a device for constructing a remaining operating mileage prediction model, the construction device including: a memory configured to store instructions; and a processor configured to call instructions from the memory and to implement the above-mentioned method for constructing a remaining operating mileage prediction model when executing the instructions.

[0016] The fourth aspect of the present application provides a device for predicting the remaining operating mileage, comprising: a memory configured to store instructions; and a processor configured to call instructions from the memory and to implement the above-mentioned method for predicting the remaining operating mileage when executing the instructions.

[0017] The fifth aspect of the present application provides an electric working machine, comprising: a device for constructing the above-mentioned remaining operating mileage prediction model, or a device for predicting the remaining operating mileage according to the above-mentioned device.

[0018] In a sixth aspect, the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the method for constructing the remaining operating mileage prediction model described above, or the method for predicting the remaining operating mileage described above.

[0019] The above technical solution obtains multiple historical operating condition parameters of the electric working machine, wherein the historical operating condition parameters include a first historical operating condition parameter and a second historical operating condition parameter, wherein the first historical operating condition parameter includes the historical state parameter before a preset prediction point in each historical operating process and the historical predicted fully charged operating mileage corresponding to each historical operating process, and the second historical operating condition parameter includes the historical remaining operating mileage after the preset prediction point in each historical operating process. Based on a preset correlation coefficient algorithm, the correlation value between each first historical operating condition parameter and the second historical operating condition parameter is determined. The first historical operating condition parameter is then filtered based on the correlation value to obtain a target operating condition parameter. Based on the target operating condition parameter and the second historical operating condition parameter, the importance coefficient of each target operating condition parameter is determined based on the regression prediction algorithm to obtain a remaining operating mileage prediction model. Thus, compared to the prior art remaining operating mileage prediction method, the technical solution of the present application does not simply consider the energy consumption of the battery of the electric working machine, but instead comprehensively considers the impact of each target operating condition parameter on the remaining operating mileage of the electric working machine to construct a remaining operating mileage prediction model, thereby achieving accurate prediction of the remaining operating mileage of the electric working machine.

[0020] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0022] Figure 1 A flowchart of a method for constructing a remaining operating mileage prediction model according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0023] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0024] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. In the embodiments of this application, certain software, components, models, and other existing solutions in the industry may be mentioned. These should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use such solutions.

[0025] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0026] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0027] Figure 1 The following schematically shows a flow chart of a method for constructing a remaining operating mileage prediction model according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for constructing a remaining operating range prediction model, which is applied to an electric operating machine. Taking the construction method applied to a processor as an example, the method may include the following steps:

[0028] Step S101, obtain multiple historical operating condition parameters of the electric operating machinery, wherein the historical operating condition parameters include a first historical operating condition parameter and a second historical operating condition parameter, the first historical operating condition parameter includes the historical state parameter before the preset prediction point in each historical operating process and the historical predicted full-charge operating mileage corresponding to each historical operating process, and the second historical operating condition parameter includes the historical remaining operating mileage after the preset prediction point in each historical operating process.

[0029] Step S102 : determining the correlation value of each first historical operating condition parameter relative to the second historical operating condition parameter based on a preset correlation coefficient algorithm.

[0030] Step S103 : screening the plurality of first historical operating condition parameters according to the correlation value to obtain the target operating condition parameters.

[0031] Step S104 , based on a regression prediction algorithm, the importance coefficient of each target operating condition parameter is determined according to the target operating condition parameter and the second historical operating condition parameter to obtain a remaining operating mileage prediction model.

[0032] It is understood that an electric working machine is a machine that consumes electrical energy to perform operations. Historical operating condition parameters are parameters used to measure the operating conditions of the electric working machine during historical operating processes. These parameters may include, but are not limited to, a first historical operating condition parameter and a second historical operating condition parameter. The first historical operating condition parameter may include the historical state parameters of each historical operating process before a preset prediction point and the historical predicted fully charged operating range corresponding to each historical operating process. The second historical operating condition parameter includes the historical remaining operating range after the preset prediction point in each historical operating process. The historical predicted fully charged operating range is the predicted operating range that can be traveled after a full charge in each historical operating process. The historical remaining operating range is the operating range that can be traveled after the preset prediction point in each historical operating process. A historical operating process is the operating process from the end of the previous charge to the start of the next charge. The preset prediction point is a preset prediction point. The preset correlation coefficient algorithm is a preset correlation coefficient algorithm, such as the Pearson correlation coefficient algorithm or the Spearman rank correlation coefficient. The target operating condition parameter is a number of items in the first historical operating condition parameter. A regression prediction algorithm is a prediction algorithm used to characterize the linear or nonlinear relationship between an independent variable (target operating condition parameter) and a dependent variable (second historical operating condition parameter). Regression prediction algorithms may include linear regression prediction algorithms, neural networks, support vector machine (SVM) supervision algorithms, tree regression prediction algorithms, and Bayesian regression prediction algorithms. The importance coefficient is a coefficient used to characterize the importance of the target operating condition parameter relative to the second historical operating condition parameter. The larger the importance coefficient, the greater the importance of the target operating condition parameter relative to the second historical operating condition parameter. The remaining operating mileage prediction model is a model used to predict the remaining operating mileage.

[0033] Specifically, the processor can obtain multiple historical operating condition parameters of the electric operating machine from the stored historical operating condition parameter database, wherein the historical operating condition parameters may include but are not limited to the first historical operating condition parameter and the second historical operating condition parameter, the first historical operating condition parameter may include but are not limited to the historical state parameter before the preset prediction point in each historical operating process and the historical predicted full-charge operating mileage corresponding to each historical operating process, the second historical operating condition parameter may include but are not limited to the historical remaining operating mileage after the preset prediction point in each historical operating process, so that the processor can determine the correlation value of each first historical operating condition parameter with respect to the second historical operating condition parameter based on a preset correlation coefficient algorithm, and then can calculate the correlation value of each first historical operating condition parameter with respect to the second historical operating condition parameter based on the preset correlation coefficient algorithm. The correlation value filters multiple first historical operating condition parameters to obtain the target operating condition parameters in the first historical operating condition parameters. Furthermore, based on the regression prediction algorithm, the linear regression prediction algorithm is fitted according to the target operating condition parameters and the second historical operating condition parameters, and the importance coefficient corresponding to each target operating condition parameter is continuously adjusted until the importance coefficient makes the error value between the predicted second historical operating condition parameter output by the remaining operating mileage prediction model and the second historical operating condition parameter less than the preset error threshold. In this way, the processor can obtain the remaining operating mileage prediction model, wherein the error value can be calculated using the mean absolute error algorithm, the mean square error algorithm, the mean absolute percentage error algorithm or other error algorithms, which are not limited here.

[0034] The above-mentioned method for constructing the remaining operating mileage prediction model obtains multiple historical operating condition parameters of the electric operating machinery, wherein the historical operating condition parameters include a first historical operating condition parameter and a second historical operating condition parameter, and the first historical operating condition parameter includes the historical state parameter before the preset prediction point in each historical operating process and the historical predicted full-charge operating mileage corresponding to each historical operating process, and the second historical operating condition parameter includes the historical remaining operating mileage after the preset prediction point in each historical operating process, so that based on the preset correlation coefficient algorithm, the correlation value of each first historical operating condition parameter and the second historical operating condition parameter can be determined, and then the first historical operating condition parameter can be screened according to the correlation value to obtain the target operating condition parameter, and based on the linear regression prediction algorithm, the importance coefficient of each target operating condition parameter is determined according to the target operating condition parameter and the second historical operating condition parameter, and the remaining operating mileage prediction model can be obtained. In this way, compared with the remaining operating mileage prediction method of the prior art, the technical solution of the present application does not simply consider the power and energy consumption of the battery of the electric working machinery, but comprehensively considers the impact of various target operating parameters on the remaining operating mileage of the electric working machinery, and constructs a remaining operating mileage prediction model, thereby realizing accurate prediction of the remaining operating mileage of the electric working machinery.

[0035] In one embodiment, obtaining the historical predicted full-charge operating mileage includes: obtaining the first actual operating mileage and the actual power consumption percentage of the electric operating machinery in each historical operating process; determining the ratio of the first actual operating mileage to the actual power consumption percentage to obtain the single estimated full-charge operating mileage corresponding to each historical operating process; comparing the average of multiple single estimated full-charge operating mileages corresponding to the multiple most recent preset cumulative quantities before each historical operating process with the single estimated full-charge operating mileage corresponding to each historical operating process to determine the target cumulative quantity among the multiple preset cumulative quantities, wherein the target cumulative quantity is the preset cumulative quantity corresponding to the minimum of the difference between the average of multiple single estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities and the single estimated full-charge operating mileage corresponding to each historical operating process; and determining the average of multiple single estimated full-charge operating mileages of the target cumulative quantity most recent before each historical operating process as the historical predicted full-charge operating mileage corresponding to the historical operating process.

[0036] It can be understood that the first actual operating mileage is the mileage traveled during each historical operating process. The actual percentage of power consumption is the percentage of power consumed during each historical operating process. The single estimated full-charge operating mileage is the operating mileage that the electric operating machine can travel when fully charged during a single operating process. The preset cumulative number is a preset cumulative number of operations. The target cumulative number is one of the preset cumulative numbers, and the target cumulative number is the preset cumulative number corresponding to the minimum difference between the average of multiple single estimated full-charge operating mileages corresponding to the multiple preset cumulative numbers and the single estimated full-charge operating mileage corresponding to each historical operating process.

[0037] Specifically, the processor can obtain the first actual operating mileage and the actual power consumption percentage of the electric machinery in each historical operating process from another storage database, so that the processor can determine the ratio of the first actual operating mileage to the actual power consumption percentage, and obtain multiple single estimated full-charge operating mileages corresponding to each historical operating process. The average of the multiple single estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities before each historical operating process is compared with the single estimated full-charge operating mileage corresponding to each historical operating process, so as to determine the target cumulative quantity among the multiple preset cumulative quantities. In the event that the difference between the average of the multiple single-time estimated full-charge operating mileages and the single-time estimated full-charge operating mileages corresponding to each historical operation process is negative, the target cumulative quantity is the preset cumulative quantity corresponding to the minimum absolute value of the difference between the average of the multiple single-time estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities and the single-time estimated full-charge operating mileages corresponding to each historical operation process. In the event that the difference between the average of the multiple single-time estimated full-charge operating mileages and the single-time estimated full-charge operating mileages corresponding to each historical operation process is not negative, the target cumulative quantity is the preset cumulative quantity corresponding to the minimum absolute value of the difference between the average of the multiple single-time estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities and the single-time estimated full-charge operating mileages corresponding to each historical operation process. That is, the target cumulative quantity among the multiple preset cumulative quantities is determined with the single-time estimated full-charge operating mileage closest to the historical operation process as the target. In this way, the processor may determine the average of the single-time estimated full-charge operating mileages of the target cumulative quantities that precede each historical operation process and are closest to the historical operation process as the historical predicted full-charge operating mileage corresponding to the historical operation process.

[0038] In a specific embodiment, when the electric operating machine operates a total of 100 times, the first actual operating mileage and the actual power consumption percentage of the electric operating machine in the first 99 historical operating processes are determined, so that 99 single estimated full-charge operating mileages corresponding to the first 99 historical operating processes can be determined, and the preset cumulative number range can be set to 1 to 30 based on expert experience, and then the average of the multiple single estimated full-charge operating mileages corresponding to the preset cumulative numbers (1 to 30) is taken and compared with the single estimated full-charge operating mileage corresponding to each historical operating process. The specific comparison process is: determine the difference between the average of the multiple single estimated full-charge operating mileages corresponding to the preset cumulative numbers (1 to 30) and the corresponding single estimated full-charge operating mileage, and determine the preset cumulative number (5) corresponding to the smallest absolute value of the difference, that is, the average of the single estimated full-charge operating mileages corresponding to the 95th to 99th (target cumulative number) historical operating processes closest to the 100th historical operating process can be used as the historical predicted full-charge operating mileage corresponding to the 100th historical operating process.

[0039] Since the number of samples of the operating mileage that the electric operating machinery can travel in a fully charged state during each historical operating process is small and the operating conditions are different, the ratio of the first actual operating mileage in each historical operating process to the actual power consumption percentage can be used as the single estimated full-charge operating mileage corresponding to each historical operating process, and the average of the multiple single estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities before each historical operating process can be compared with the single estimated full-charge operating mileage corresponding to each historical operating process, so as to determine the target cumulative quantity among the multiple preset cumulative quantities, and the single estimated full-charge operating mileage of the target cumulative quantity closest to the target cumulative quantity before each historical operating process can be used as the average of the multiple single estimated full-charge operating mileages corresponding to the multiple preset cumulative quantities before each historical operating process. The average of the estimated full-charge operating mileage is determined as the historical predicted full-charge operating mileage corresponding to the historical operating process, wherein the target cumulative quantity is the preset cumulative quantity corresponding to the minimum of the average of multiple single estimated full-charge operating mileages corresponding to multiple preset cumulative quantities and the single estimated full-charge operating mileage corresponding to each historical operating process. That is to say, the average of multiple single estimated full-charge operating mileages of the target cumulative quantity is the single estimated full-charge operating mileage corresponding to the historical operating process that is closest to the historical operating process. The historical predicted full-charge operating mileage corresponding to the historical operating process is determined as much as possible through historical data, which greatly improves the accuracy of estimating the historical predicted full-charge operating mileage using historical data.

[0040] In one embodiment, in the embodiment of the present application, the acquisition of historical remaining operating mileage includes: acquiring the second actual operating mileage from the preset prediction point to the end of the operation in each historical operation process and the remaining power percentage corresponding to the end of the operation; determining the product value of the single estimated full-charge operating mileage and the remaining power percentage to obtain the estimated operating mileage with remaining power; determining the sum of the second actual operating mileage and the estimated operating mileage with remaining power to obtain the historical remaining operating mileage.

[0041] It can be understood that the second actual operating mileage is the actual mileage traveled by the electric working machine from the preset prediction point to the end of each historical operation. The remaining battery percentage is the remaining battery power at the end of the operation, expressed as a percentage. The estimated operating mileage based on remaining battery power is the estimated mileage that the electric working machine could travel based on the remaining battery power at the end of the operation.

[0042] Specifically, the processor can obtain from the database the second actual operating mileage of the electric operating machinery from the preset prediction point to the end of the operation in each historical operation process and the remaining power percentage corresponding to the end of the operation, so as to determine the product value of the single estimated full-charge operating mileage and the remaining power percentage, and thus obtain the estimated mileage that the electric operating machinery can travel based on the remaining power percentage (estimated operating mileage with remaining power), and then determine the sum of the second actual operating mileage and the estimated operating mileage with remaining power, and thus obtain the remaining operating mileage that the electric operating machinery can travel at the preset prediction point (historical remaining operating mileage).

[0043] Since the remaining power percentage of the electric operating machinery is not 0% at the end of the operation in most cases, in order to calculate the historical remaining operating mileage, in addition to determining the actual driving distance of the electric operating machinery from the preset prediction point to the end of the operation in each historical operation process (the second actual operating mileage), it is also necessary to determine the remaining power percentage of the electric operating machinery at the preset prediction point in each historical operation process, and then estimate the mileage that the electric operating machinery can travel based on the remaining power (the estimated remaining power operating mileage) based on the remaining power percentage. By determining the sum of the second actual operating mileage and the estimated remaining power operating mileage, the historical remaining operating mileage of the electric operating machinery at the preset prediction point in each historical operation process can be predicted. The historical remaining operating mileage of the electric operating machinery at the preset prediction point in each historical operation process can be determined more accurately, providing an accurate data basis for the subsequent determination of the correlation value between the first historical operating condition parameter and the historical remaining operating mileage.

[0044] In one embodiment, screening multiple first historical operating condition parameters according to correlation values ​​to obtain target operating condition parameters includes: determining the first historical operating condition parameter among the multiple first historical operating condition parameters whose correlation value is greater than a preset correlation threshold as the target operating condition parameter.

[0045] It can be understood that the preset correlation threshold is a pre-set correlation threshold.

[0046] Specifically, based on a preset correlation threshold, the processor can determine the first historical operating condition parameter among multiple first historical operating condition parameters whose correlation value is greater than the preset correlation threshold as the target operating condition parameter, indicating that the degree of correlation between the target operating condition parameter and the second historical operating condition parameter is relatively high, and filter out the first historical operating condition parameter among multiple first historical operating condition parameters whose correlation value is less than or equal to the preset correlation threshold, indicating that the degree of correlation between the first historical operating condition parameter whose correlation value is less than or equal to the preset correlation threshold is relatively low.

[0047] The above technical solution filters the first historical operating condition parameters through a preset correlation threshold, thereby retaining the first historical operating condition parameters (target operating condition parameters) whose correlation values ​​with the second historical operating condition parameters are greater than the preset correlation threshold. Conversely, the remaining first historical operating condition parameters are filtered out and the target operating condition parameters are retained, which can avoid data redundancy and improve the prediction of the remaining operating mileage.

[0048] In one embodiment, the historical status parameters include parameters related to operation duration, parameters related to driving speed, parameters related to driving operation mileage, parameters related to power consumption, parameters related to upper motor speed, parameters related to upper motor torque, parameters related to chassis motor speed, parameters related to chassis motor torque, and parameters related to the ambient temperature of the environment in which the electric operating machine is located.

[0049] It is understood that the operation duration-related parameters may include, but are not limited to, natural duration parameters and operation duration parameters. The natural duration parameter is the duration from the last charging end time of the electric operating machine to the next charging start time, and the operation duration parameter is the operation duration of the electric operating machine from the last charging end time to the next charging start time. The driving speed-related parameters may include, but are not limited to, a maximum driving speed parameter, an upper quartile driving speed parameter, a median driving speed parameter, a lower quartile driving speed parameter, and a mean driving speed parameter. The maximum driving speed parameter is the maximum driving speed parameter, the upper quartile driving speed parameter is the driving speed parameter at the 75th percentile after the driving speed parameters are sorted in ascending order, the median driving speed parameter is the driving speed parameter at the median after the driving speed parameters are sorted in ascending order, the lower quartile driving speed parameter is the driving speed parameter at the 25th percentile after the driving speed parameters are sorted in ascending order, and the mean driving speed parameter is the mean of the driving speed parameters. Parameters related to operating mileage may include, but are not limited to, a factory cumulative operating mileage parameter and a traveled mileage condition parameter. The factory cumulative operating mileage parameter is the total mileage the electric working machine has traveled since leaving the factory and before a preset prediction point, and the traveled mileage condition parameter is the mileage the electric working machine has traveled at a preset prediction point during the current historical operating process. Parameters related to power consumption may include, but are not limited to, a cumulative power consumption condition parameter and a consumed power condition parameter. The cumulative power consumption condition parameter is the total power consumed by the electric working machine since leaving the factory and before a preset prediction point, and the consumed power condition parameter is the power consumed at a preset prediction point during the current historical operating process. The upper motor is a motor that drives the components on the electric working machinery to operate. The parameters related to the upper motor speed may include but are not limited to the maximum upper motor speed parameter, the upper motor speed upper quartile parameter, the upper motor speed median parameter, the upper motor speed mean parameter, the upper motor speed lower quartile parameter and the upper motor speed absolute value cumulative parameter. The upper motor speed maximum parameter is the largest upper motor speed parameter, the upper motor speed upper quartile parameter is the upper motor speed parameter at the 75% position after the upper motor speed parameters are arranged in ascending order, the upper motor speed median parameter is the upper motor speed parameter at the median after the upper motor speed parameters are arranged in ascending order, the upper motor speed mean parameter is the mean of the upper motor speed parameters, the upper motor speed lower quartile parameter is the upper motor speed parameter at the 25% position after the upper motor speed parameters are arranged in ascending order, and the upper motor speed absolute value cumulative parameter is the sum of the absolute values ​​of each upper motor speed.The parameters related to the upper motor torque may include but are not limited to the upper motor torque maximum parameter, the upper motor torque upper quartile parameter, the upper motor torque median parameter, the upper motor torque mean parameter, the upper motor torque lower quartile parameter, and the upper motor torque absolute value cumulative parameter. The upper motor torque is related to the load corresponding to the components of the electric working machinery borne by the upper motor. The greater the load, the greater the upper motor torque. The parameters related to the chassis motor speed may include but are not limited to the chassis motor speed maximum parameter, the chassis motor speed upper quartile parameter, the chassis motor speed median parameter, the chassis motor speed mean parameter, the chassis motor speed lower quartile parameter, and the current chassis motor speed absolute value cumulative parameter. The chassis motor is the motor that drives the electric working machinery. The parameters related to the chassis motor torque may include but are not limited to the chassis motor torque maximum parameter, the chassis motor torque upper quartile parameter, the chassis motor torque median parameter, the chassis motor torque mean parameter, the chassis motor torque lower quartile parameter, and the current chassis motor torque absolute value cumulative parameter. The ambient temperature related parameters may include but are not limited to the maximum ambient temperature parameter, the upper quartile parameter, the median parameter, the mean parameter, the quartile parameter, the absolute value cumulative parameter and the minimum ambient temperature parameter of the environment in which the electric working machine is located.

[0050] The processor takes into account multiple historical status parameters and can more accurately determine the current operating condition of the electric working machine, thereby accurately predicting the remaining operating mileage of the working machine based on the current operating condition.

[0051] An embodiment of the present application also provides a method for predicting the remaining operating mileage, which is applied to an electric operating machine. The method includes: constructing a remaining operating mileage prediction model according to the method for constructing the remaining operating mileage prediction model; obtaining the target operating condition parameter value of the target operating condition parameter of the electric operating machine at the current moment; and predicting the remaining operating mileage of the electric operating machine according to the target operating condition parameter value based on the remaining operating mileage prediction model.

[0052] It can be understood that the target operating condition parameter value is the parameter value presented by the target operating condition parameter at the current moment, and the remaining operating mileage is the predicted mileage that the electric operating machine can travel at the current moment.

[0053] Specifically, the processor can construct a remaining operating mileage prediction model through the construction method of the remaining operating mileage prediction model, and can obtain the target operating condition parameter values ​​corresponding to the target operating condition parameters of the electric operating machinery at the current moment through various types of sensors, and then input the target operating condition parameter values ​​into the remaining operating mileage prediction model to predict the remaining operating mileage of the electric operating machinery at the current moment.

[0054] By obtaining the target operating condition parameter value corresponding to the target operating condition parameter of the electric operating machinery at the current moment, the processor can roughly determine the current operating condition of the electric operating machinery at the current moment. Based on the remaining operating mileage prediction model, according to the target operating condition parameter, the remaining operating mileage of the electric operating machinery under the current operating condition can be accurately predicted, thereby improving the prediction accuracy of the remaining operating mileage.

[0055] In one specific embodiment, since the operation of an electric working machine includes both charging and discharging processes, the remaining operating range of the electric working machine is precisely determined during the discharging process. To reduce computational complexity during the discharging process, the first and second historical operating condition parameters corresponding to each historical operating process can be divided into five equal parts based on expert experience, with the four middle data points serving as the four preset prediction points. Based on this, the processor can collect the historical state parameters (pumping condition data) before each preset prediction point in each historical operation process through the industrial Internet of Things edge computing box installed on the electric operating machinery (such as a pump truck). The processor can also determine the historical predicted full-charge operating mileage and the second historical condition parameter corresponding to each historical operation process through other data acquisition methods, wherein the first historical condition parameter may include the historical state parameter (pumping condition data) and the historical predicted full-charge operating mileage corresponding to each historical operation process, and the second historical condition parameter includes the historical remaining operating mileage after each preset prediction point in each historical operation process. The historical state parameters may include but are not limited to parameters related to the operation time, parameters related to the driving speed, parameters related to the driving operating mileage, parameters related to the power consumption, parameters related to the upper motor speed, parameters related to the upper motor torque, parameters related to the chassis motor speed, parameters related to the chassis motor torque, and parameters related to the ambient temperature of the environment in which the electric operating machinery is located. Therefore, if each electric operating machinery has 1000 operations, 4000 (1000*4) sample data can be generated.

[0056] The processor can obtain the historical predicted full-charge operating mileage by the following method. Specifically, when the electric operating machine operates 100 times in total, the first actual operating mileage and the actual power consumption percentage of the electric operating machine in the first 99 historical operating processes are obtained, so that the 99 single estimated full-charge operating mileages corresponding to the first 99 historical operating processes can be determined, and the preset cumulative number range can be set to 1 to 30 through expert experience. The average of multiple single estimated full-charge operating mileages corresponding to the preset cumulative number (1 to 30) is taken and the average of each historical operating process is obtained. The specific comparison process is as follows: determine the difference between the average of multiple single estimated full-charge operation mileages corresponding to the preset cumulative number (1 to 30) and the corresponding single estimated full-charge operation mileage, and determine the preset cumulative number (5) corresponding to the smallest absolute value of the difference. That is to say, the average of the single estimated full-charge operation mileages corresponding to the 95th to 99th (target cumulative number) historical operation processes closest to the 100th historical operation process can be used as the historical predicted full-charge operation mileage corresponding to the 100th historical operation process.

[0057] The processor can also obtain the historical remaining operating mileage through the following method. Specifically, 4000 (4*1000) second actual operating mileages from the 4 preset prediction points to the end of the operation in the 1000 historical operation processes and the 4 remaining power percentages corresponding to the end of the operation are obtained, and the product value of the single estimated full-charge operating mileage corresponding to the 1000 historical operation processes and the 4 remaining power percentages is determined. 4000 (4*1000) remaining power estimated operating mileages corresponding to the 4 preset prediction points can be obtained. Further, the sum of the 4000 (4*1000) second actual operating mileages and the corresponding 4000 (4*1000) remaining power estimated operating mileages can be determined to obtain 4000 (4*1000) historical remaining operating mileages.

[0058] Based on a preset correlation coefficient algorithm, a correlation value of each first historical operating condition parameter relative to the second historical operating condition parameter is determined. The preset correlation coefficient algorithm may be a Pearson correlation coefficient algorithm or a Spearman correlation coefficient. The Pearson correlation coefficient algorithm is determined by the following formula:

[0059]

[0060] Among them, r is the correlation value of each first historical operating condition parameter relative to the second historical operating condition parameter, x i is the first historical operating condition parameter of the i-th period, is the mean value of each first historical operating condition parameter, y i is the second historical operating condition parameter of the i-th period, is the mean value of each second historical operating condition parameter.

[0061] In this way, the target operating condition parameters can be obtained by screening multiple first historical operating condition parameters according to the correlation value. Specifically, the first historical operating condition parameters with correlation values ​​greater than the preset correlation threshold are determined among the multiple first historical operating condition parameters to obtain the target operating condition parameters.

[0062] Based on the linear regression prediction algorithm, the target operating condition parameters and the corresponding second historical operating condition parameters can be fitted until the error value between the historical remaining operating mileage and the predicted remaining operating mileage output by the algorithm is less than a preset threshold. The importance coefficient of each target operating condition parameter can be determined, or the importance coefficient of each standard operating condition parameter can be directly obtained using L1 regularization to obtain the remaining operating mileage prediction model. In addition, the processor can also obtain the remaining operating mileage prediction model by fitting algorithms such as neural networks, SVM algorithms, tree regression prediction algorithms, and Bayesian regression prediction algorithms. Specifically, the linear regression prediction algorithm can be determined by the following formula:

[0063] y0=a1×x1+a2×x2+...+a n ×x n

[0064] Among them, y0 is the second historical operating condition parameter, a1 is the importance coefficient corresponding to the first target operating condition parameter, a2 is the importance coefficient corresponding to the second target operating condition parameter, and a n is the importance coefficient corresponding to the nth target operating condition parameter, x1 is the first target operating condition parameter, x2 is the second target operating condition parameter, and x n is the nth target operating condition parameter.

[0065] The processor can obtain the target operating parameter value corresponding to the target operating parameter of the electric operating machinery at the current moment through sensors or other data acquisition methods, and input the target operating parameter value into the model based on the remaining operating mileage prediction model, so as to obtain the output of the remaining operating mileage of the electric operating machinery.

[0066] The above technical solution uses a variety of historical operating condition data, taking into account the battery health status and the impact of different operating conditions on the battery power. It can accurately predict the remaining operating mileage of electric operating machinery, thereby providing accurate and effective guidance for the production scheduling of electric operating machinery.

[0067] An embodiment of the present application also provides a device for constructing a remaining operating mileage prediction model, the construction device including: a memory configured to store instructions; and a processor configured to call instructions from the memory and to implement the above-mentioned method for constructing a remaining operating mileage prediction model when executing the instructions.

[0068] An embodiment of the present application also provides a device for predicting the remaining operating mileage, comprising: a memory configured to store instructions; and a processor configured to call instructions from the memory and to implement the above-mentioned method for predicting the remaining operating mileage when executing the instructions.

[0069] An embodiment of the present application also provides an electric working machine, including: a device for constructing the above-mentioned remaining operating mileage prediction model, or a device for predicting the remaining operating mileage according to the above-mentioned device.

[0070] An embodiment of the present application also provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the method for constructing the remaining operating mileage prediction model described above, or the method for predicting the remaining operating mileage described above.

[0071] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0072] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0073] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0074] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0075] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0076] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0077] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0078] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0079] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for constructing a remaining operating range prediction model, applied to electric operating machinery, characterized in that: The construction method comprises: Acquiring a plurality of historical operating condition parameters of the electric operating machine, wherein the historical operating condition parameters include a first historical operating condition parameter and a second historical operating condition parameter, the first historical operating condition parameter including a historical state parameter located before a preset prediction point in each historical operating process and a historical predicted full-charge operating mileage corresponding to each historical operating process, and the second historical operating condition parameter including a historical remaining operating mileage located after the preset prediction point in each historical operating process; Determining, based on a preset correlation coefficient algorithm, a correlation value of each of the first historical operating condition parameters relative to the second historical operating condition parameter; screening the plurality of first historical operating condition parameters according to the correlation value to obtain a target operating condition parameter; Based on the regression prediction algorithm, the importance coefficient of each target operating condition parameter is determined according to the target operating condition parameter and the second historical operating condition parameter to obtain a remaining operating mileage prediction model.

2. The construction method according to claim 1, characterized in that The acquisition of the historical predicted full-charge operating mileage includes: Obtaining a first actual operating mileage and an actual percentage of power consumption of the electric operating machine during each historical operating process; Determining a ratio of the first actual operating mileage to the actual percentage of power consumption to obtain a single estimated full-charge operating mileage corresponding to each of the historical operating processes; Comparing the average of the multiple single estimated full-charge operation mileages corresponding to the multiple most recent preset cumulative quantities before each of the historical operation processes with the single estimated full-charge operation mileage corresponding to each of the historical operation processes to determine a target cumulative quantity among the multiple preset cumulative quantities, wherein the target cumulative quantity is the preset cumulative quantity corresponding to the minimum difference between the average of the multiple single estimated full-charge operation mileages corresponding to the multiple preset cumulative quantities and the single estimated full-charge operation mileage corresponding to each of the historical operation processes; The average of multiple single estimated full-charge operation mileages of the target cumulative number most recently before each of the historical operation processes is determined as the historical predicted full-charge operation mileage corresponding to the historical operation process.

3. The construction method according to claim 2, characterized in that The acquisition of the historical remaining operating mileage includes: Obtaining the second actual operation mileage from the preset prediction point to the end of the operation in each historical operation process and the remaining power percentage corresponding to the end of the operation; Determine the product of the single estimated full-charge operating mileage and the remaining power percentage to obtain the remaining power estimated operating mileage; The sum of the second actual operating mileage and the estimated operating mileage with respect to the remaining power is determined to obtain the historical remaining operating mileage.

4. The construction method according to claim 1, characterized in that The screening of the plurality of first historical operating condition parameters according to the correlation value to obtain a target operating condition parameter includes: A first historical operating condition parameter among the plurality of first historical operating condition parameters, the first historical operating condition parameter of which the correlation value is greater than a preset correlation threshold, is determined as the target operating condition parameter.

5. The construction method according to claim 1, characterized in that The historical status parameters include parameters related to operation time, driving speed, driving operation mileage, power consumption, upper motor speed, upper motor torque, chassis motor speed, chassis motor torque, and ambient temperature of the environment in which the electric operating machine is located.

6. A method for predicting remaining operating mileage, applied to an electric operating machine, characterized in that: The method comprises: Constructing a remaining operating mileage prediction model according to the method for constructing a remaining operating mileage prediction model according to any one of claims 1 to 5; Obtaining a target operating parameter value of a target operating parameter of the electric operating machine at a current moment; Based on the remaining operating mileage prediction model, the remaining operating mileage of the electric working machine is predicted according to the target operating condition parameter value.

7. A device for constructing a remaining operating mileage prediction model, characterized in that: The construction device comprises: a memory configured to store instructions; and A processor is configured to call the stored instructions from the memory and implement the method for constructing a remaining operating mileage prediction model according to any one of claims 1 to 5 when executing the stored instructions.

8. A device for predicting remaining operating mileage, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instructions from the memory and implement the method for predicting remaining operating mileage according to claim 6 when executing the instructions.

9. An electric working machine, characterized in that: include: The device for constructing a remaining operating mileage prediction model according to claim 7, or the device for predicting remaining operating mileage according to claim 8.

10. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for causing the machine to execute the method for constructing a remaining operating mileage prediction model according to any one of claims 1 to 5, or the method for predicting remaining operating mileage according to claim 6.

Images