Method and device for evaluating manipulation performance of working machine, and electronic equipment

Abstract

The invention provides a control performance evaluation method and device for an operation machine and electronic equipment, and the method comprises the steps: determining respective corresponding target curves according to respective corresponding continuous target signals of the operation machine during multiple times of cyclic actions; for each target curve in the plurality of target curves, slicing the target curves based on a plurality of unloading points in the target curves, and determining a plurality of first sub-curves; for adjacent unloading points in the plurality of unloading points, determining second sub-curves corresponding to the adjacent unloading points from the plurality of first sub-curves; clustering the plurality of second sub-curves based on the target clustering number corresponding to the plurality of second sub-curves, and determining third sub-curves corresponding to adjacent unloading points; according to the third sub-curves corresponding to all the adjacent unloading points, an action regression curve corresponding to the operation machine is determined, the action regression curve is used for determining a control performance evaluation result corresponding to the operation machine, and subjectivity and uncertainty of manual judgment can be effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of operating machine controllability evaluation, and in particular to an operating machine controllability evaluation method, device and electronic equipment. Background Art

[0002] With the rapid development of the engineering construction field, operating machinery (such as excavators) is a key equipment in infrastructure construction, mining and earthmoving operations. The control performance of operating machinery directly affects the operating efficiency, safety, and the comfort and satisfaction of operators.

[0003] In the existing technology, customers and testers mainly rely on manual evaluation to evaluate the controllability of operating machinery, that is, manually operating the operating machinery to perform a series of predetermined actions and tasks. During the operation, testers will evaluate the controllability of the operating machinery based on their own experience, skills and feelings. However, manual evaluation often has strong subjectivity and uncertainty, and it is difficult to fully and truly reflect the controllability of the operating machinery. Summary of the invention

[0004] The present invention provides a method, device and electronic equipment for evaluating the controllability performance of a working machine, so as to solve the problem that the evaluation of the controllability performance of a working machine in the prior art mainly relies on human evaluation, which is often highly subjective and uncertain, and is difficult to fully and truly reflect the controllability performance of the working machine. The method analyzes and processes the continuous target signals corresponding to each of the working machines when the working machine performs cyclic actions for multiple times, and obtains the action regression curve corresponding to the working machine. The action regression curve can accurately reflect the action trend of the working machine when the working machine performs cyclic actions for multiple times, and lays an objective foundation for determining the evaluation result of the controllability performance corresponding to the working machine, thereby effectively avoiding the subjectivity and uncertainty of human judgment.

[0005] The present invention provides a method for evaluating the controllability of a working machine, comprising the following steps.

[0006] According to the continuous target signals corresponding to each other when the working machine performs cyclic actions for multiple times, the corresponding target curves are determined; for each target curve in the multiple target curves, based on the multiple unloading points in the target curve, the target curve is sliced ​​to determine multiple first sub-curves; for adjacent unloading points in the multiple unloading points, the second sub-curves corresponding to the adjacent unloading points are determined from the multiple first sub-curves; based on the target cluster numbers corresponding to the multiple second sub-curves, the multiple second sub-curves are clustered to determine the third sub-curves corresponding to the adjacent unloading points; according to the third sub-curves corresponding to all the adjacent unloading points, the action regression curve corresponding to the working machine is determined, and the action regression curve is used to determine the control performance evaluation result corresponding to the working machine.

[0007] According to a method for evaluating the control performance of a working machine provided by the present invention, the continuous target signal includes: a continuous input signal and a continuous output signal; the target cluster number is obtained based on the following steps: determining the target cluster number according to a first target cluster number corresponding to a plurality of second sub-curves corresponding to the continuous input signal and a second target cluster number corresponding to a plurality of second sub-curves corresponding to the continuous output signal.

[0008] According to a method for evaluating the control performance of a working machine provided by the present invention, the first target clustering number is obtained based on the following steps: S1. Based on the first clustering number corresponding to the continuous input signal, multiple second sub-curves corresponding to the continuous input signal are clustered to obtain a clustering result of the first clustering number; S2. The first target clustering number is determined according to the root mean square error corresponding to the clustering result of the first clustering number.

[0009] According to a method for evaluating the controllability performance of a working machinery provided by the present invention, the S2, determining the first target clustering number according to the root mean square error corresponding to the clustering result of the first clustering number, includes: S21, when the mean square error is less than or equal to a preset threshold, determining the first clustering number as the first target clustering number; S22, when the mean square error is greater than the preset threshold, increasing the first clustering number to obtain a second clustering number; and determining the second clustering number as the new first clustering number; S23, repeating the above steps S1, S21-S22 until the finally determined root mean square error is less than or equal to the preset threshold, and determining the clustering number corresponding to the finally determined root mean square error as the first target clustering number.

[0010] According to a method for evaluating the controllability of a working machine provided by the present invention, the target cluster number is determined based on a first target cluster number corresponding to a plurality of second sub-curves corresponding to the continuous input signal and a second target cluster number corresponding to a plurality of second sub-curves corresponding to the continuous output signal, including: determining the minimum value of the first target cluster number and the second target cluster number as the target cluster number.

[0011] According to a method for evaluating the controllability performance of a working machine provided by the present invention, the method also includes: determining a standard input signal based on an action regression curve corresponding to the continuous input signal; and determining a standard output signal based on an action regression curve corresponding to the continuous output signal; determining a target scoring index based on the continuous input signal, the standard input signal, the continuous output signal and the standard output signal; and determining a controllability evaluation result corresponding to the working machine based on the target scoring index.

[0012] According to a method for evaluating the controllability of a working machine provided by the present invention, the target scoring index is determined based on the continuous input signal, the standard input signal, the continuous output signal and the standard output signal, including: determining a first correlation and a first Euclidean distance between the continuous input signal and the standard input signal; and determining a second correlation and a second Euclidean distance between the continuous output signal and the standard output signal; and determining the target scoring index based on the first correlation, the first Euclidean distance, the second correlation and the second Euclidean distance.

[0013] According to a method for evaluating the control performance of a working machine provided by the present invention, the action regression curve corresponding to the working machine is determined based on the third sub-curves corresponding to all adjacent unloading points, including: smoothing the third sub-curves corresponding to all adjacent unloading points to obtain the action regression curve corresponding to the working machine.

[0014] The present invention also provides a device for evaluating the control performance of a working machine, comprising the following modules.

[0015] A processing module is used to determine the corresponding target curves according to the continuous target signals corresponding to each of the operating machinery when the operating machinery performs cyclic actions for multiple times; for each target curve in the multiple target curves, based on the multiple unloading points in the target curve, the target curve is sliced ​​to determine multiple first sub-curves; for adjacent unloading points in the multiple unloading points, the second sub-curve corresponding to the adjacent unloading point is determined from the multiple first sub-curves; based on the target cluster numbers corresponding to the multiple second sub-curves, the multiple second sub-curves are clustered to determine the third sub-curve corresponding to the adjacent unloading point; based on the third sub-curves corresponding to all the adjacent unloading points, the action regression curve corresponding to the operating machinery is determined, and the action regression curve is used to determine the control performance evaluation result corresponding to the operating machinery.

[0016] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for evaluating the control performance of the working machine as described above is implemented.

[0017] The control performance evaluation method, device and electronic device of the operating machine provided by the present invention determine the corresponding target curves according to the continuous target signals corresponding to each of the operating machines when performing cyclic actions for multiple times; for each target curve in the multiple target curves, slice the target curve based on the multiple unloading points in the target curve to determine multiple first sub-curves; for adjacent unloading points in the multiple unloading points, determine the second sub-curves corresponding to the adjacent unloading points from the multiple first sub-curves; based on the target clustering numbers corresponding to the multiple second sub-curves, cluster the multiple second sub-curves to determine the third sub-curves corresponding to the adjacent unloading points; and determine the action regression curve corresponding to the operating machine according to the third sub-curves corresponding to all adjacent unloading points, and the action regression curve is used to determine the control performance evaluation result corresponding to the operating machine. The method analyzes and processes the continuous target signals corresponding to each of the operating machines when performing cyclic actions for multiple times, and obtains the action regression curve corresponding to the operating machine. The action regression curve can accurately reflect the action trend of the operating machine when performing cyclic actions for multiple times, and lays an objective foundation for determining the control performance evaluation result corresponding to the operating machine, thereby effectively avoiding the subjectivity and uncertainty of human judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of the method for evaluating the controllability of a working machine provided by the present invention.

[0020] Figure 2 It is a schematic diagram of multiple target curves and action regression curves provided by the present invention.

[0021] Figure 3 is a schematic diagram of multiple second sub-curves provided by the present invention.

[0022] Figure 4 It is a schematic diagram of the third sub-curve provided by the present invention.

[0023] Figure 5 It is a schematic diagram of the smoothing process provided by the present invention.

[0024] Figure 6 It is a schematic structural diagram of the operating machine control performance evaluation device provided by the present invention.

[0025] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] It should be noted that the execution subject involved in the embodiment of the present invention may be a control performance evaluation device of an operating machine, or may be an electronic device. Optionally, the electronic device may include: a computer and a mobile terminal, etc.

[0028] The embodiment of the present invention is further described below by taking an electronic device as an example.

[0029] Figure 1 is a flow chart of the method for evaluating the controllability of a working machine provided by the present invention, such as Figure 1 As shown, the method includes the following steps 101 to 104.

[0030] Step 101: Determine the corresponding target curves according to the continuous target signals corresponding to the working machine when the working machine performs cyclic actions for multiple times.

[0031] Exemplarily, the work machine may be an excavator.

[0032] It should be noted that a displacement sensor is provided in the oil cylinder of the excavator for collecting the displacement signal of the oil cylinder; a speed sensor is also provided in the oil cylinder of the excavator for collecting the speed signal of the oil cylinder.

[0033] Optionally, the above-mentioned cylinder displacement signal may include: boom cylinder displacement signal, arm cylinder displacement signal, bucket cylinder displacement signal and slewing cylinder displacement signal, etc. The above-mentioned cylinder speed signal may include: boom cylinder speed signal, arm cylinder speed signal, bucket cylinder speed signal and slewing cylinder speed signal, etc.

[0034] Optionally, the continuous target signal may include: a continuous input signal and a continuous output signal.

[0035] Among them, the continuous input signal can be an electric control handle signal or a pilot pressure signal of a hydraulic control handle; the continuous output signal can be the above-mentioned cylinder displacement signal or the above-mentioned cylinder speed signal, which is not specifically limited here.

[0036] It should be noted that the target curve is used to characterize the trajectory of the continuous target signal.

[0037] Exemplarily, the relevant actions of the operating machine are shown in Table 1.

[0038] Table 1:

[0039] As can be seen from Table 1, since most actions of the operating machinery include actions in the opposite direction when they are restored, they can be classified into one type of action for subsequent analysis and processing.

[0040] For any type of action of the operating machine, the operating machine needs to execute this type of action in a cycle for multiple times in order to perform subsequent analysis and processing.

[0041] The electronic device can obtain in real time the continuous target signals corresponding to each of the operating machines when they perform cyclic actions for multiple times. Each time the operating machine performs any type of action, the electronic device can obtain a continuous target signal. The electronic device will obtain as many continuous target signals as the operating machine performs this type of action cyclically. In this way, the electronic device can determine the target curves corresponding to each of the multiple continuous target signals based on the multiple continuous target signals.

[0042] For example, Figure 2 It is a schematic diagram of multiple target curves and action regression curves provided by the present invention. Figure 2 In the figure, the red curve is the action regression curve, and the other colored curves except the red curve are multiple target curves. Figure 2 It can be seen that the operating machinery performs any type of action in multiple cycles and will be affected by factors such as the driver's operating habits, attention state, reaction speed, and changes in the external environment. Therefore, the continuous target signals obtained by the electronic equipment are different. In this way, there will be differences between multiple target curves, but the differences will not be large.

[0043] Optionally, the continuous target signal is obtained based on the following steps: the electronic device obtains the initial continuous target signal corresponding to each of the operating machinery when the operating machinery performs a cyclic action multiple times; the electronic device normalizes the initial continuous target signal to obtain the continuous target signal.

[0044] Among them, the above normalization processing can unify the initial continuous target signal to the maximum range, which is convenient for subsequent analysis and processing.

[0045] The above-mentioned initial target signal may include: an initial continuous input signal and an initial continuous output signal.

[0046] Take the initial continuous input signal as an example. At this time, the continuous target signal is the continuous input signal. Assuming that the initial continuous input signal is the initial electric control handle signal f0, the continuous input signal (the electric control handle signal f at this time) can be expressed as: f=(f0-f min ) / (fmax -f min ), where f min Indicates the minimum value of the electric control handle range; f max Indicates the maximum value of the electric control handle range.

[0047] Step 102: for each target curve among the multiple target curves, based on the multiple unloading points in the target curve, slice the target curve to determine multiple first sub-curves; for adjacent unloading points among the multiple unloading points, determine the second sub-curve corresponding to the adjacent unloading point from the multiple first sub-curves.

[0048] For example, it is assumed that the number of multiple unloading points is k (k ≥ 2), and the k unloading points are t1, t2, ..., t i ,…,t k , where t i represents the i-th (1≤i≤k) unloading point.

[0049] Taking k=5 as an example, adjacent unloading points can be t1 and t2, t2 and t3, t3 and t4, t4 and t5, t5 and t1.

[0050] The following operations are performed for each target curve in the multiple target curves: the electronic device first determines multiple unloading points in the target curve, and then slices the target curve according to the multiple unloading points to obtain multiple sub-curves. Since the length of each sub-curve may be different, the electronic device performs an equidistant stretching operation on the multiple sub-curves to obtain multiple first sub-curves of equal length; for adjacent unloading points (such as t2 and t3) in the multiple unloading points, the electronic device determines the sub-curve corresponding to the adjacent unloading points (such as t2 and t3) from the multiple first sub-curves, that is, the second sub-curve.

[0051] It can be understood that, for each target curve, there are as many second sub-curves as there are pairs of adjacent unloading points.

[0052] Optionally, the electronic device determines a plurality of unloading points in the target curve, which may include: the electronic device randomly selects an initial excavation point and an unloading completion point from the target curve; the electronic device selects a midpoint between the initial excavation point and the unloading completion point from the target curve (or a point near the midpoint on the target curve), and uses the midpoint as the initial point (assuming it is (x0, y0)); the electronic device determines a plurality of target points that meet a preset condition (x>x0 and y>y0) from the target curve, and based on the infinite norm (max{|x-x0|,|y-y0|}) and the binary norm ([(x-x0) 2 +(y-y0) 2 ] 1 / 2), determine multiple unloading points from multiple target points.

[0053] Step 103: cluster the plurality of second sub-curves based on the target number of clusters corresponding to the plurality of second sub-curves, and determine third sub-curves corresponding to adjacent unloading points.

[0054] Taking adjacent unloading points t2 and t3 as an example, for each target curve in the plurality of target curves, there are adjacent unloading points t2 and t3. Figure 3 is a schematic diagram of multiple second sub-curves provided by the present invention. Figure 3 It can be seen that, assuming there are 5 target curves, there are adjacent unloading points t2 and t3 on these 5 target curves. After slicing, the section of the subcurve between the adjacent unloading points t2 and t3, that is, the second subcurve corresponding to the adjacent unloading points (t2 and t3), exists on these 5 target curves. Similarly, there are adjacent unloading points t1 and t2 on these 5 target curves. After slicing, the section of the subcurve between the adjacent unloading points t1 and t2, that is, the second subcurve corresponding to the adjacent unloading points (t1 and t2). Other adjacent unloading points Figure 3 Not shown in FIG.

[0055] Exemplary, combined Figure 3 , the electronic device can cluster the five second sub-curves based on the target clustering numbers corresponding to the five second sub-curves, and determine the optimal sub-curve corresponding to the adjacent unloading points (t2 and t3), that is, the third sub-curve. Specifically, assuming that the target clustering number corresponding to the five second sub-curves is 2, the electronic device can determine the clustering centers of the two clusters after clustering (which can be the most representative second sub-curve in the cluster, or the second sub-curve that can best reflect the overall trend or characteristics of all the second sub-curves in the cluster), and then take the average of the two clustering centers to obtain the third sub-curve.

[0056] It can be understood that there are as many third sub-curves as there are pairs of adjacent unloading points.

[0057] In some embodiments, the continuous target signal may include: a continuous input signal and a continuous output signal; the target cluster number is obtained based on the following steps: the electronic device determines the target cluster number based on the first target cluster number corresponding to the multiple second sub-curves corresponding to the continuous input signal and the second target cluster number corresponding to the multiple second sub-curves corresponding to the continuous output signal.

[0058] The electronic device first determines the first target cluster number corresponding to multiple second sub-curves corresponding to the continuous input signal and the second target cluster number corresponding to multiple second sub-curves corresponding to the continuous output signal, and then determines the optimal cluster number, that is, the target cluster number, based on the first target cluster number and the second target cluster number.

[0059] In this way, based on the target clustering number, the electronic device can effectively cluster the multiple second sub-curves corresponding to the continuous input signals, and determine the third sub-curves corresponding to the adjacent unloading points corresponding to the continuous input signals. At the same time, the electronic device can effectively cluster the multiple second sub-curves corresponding to the continuous output signals, and determine the third sub-curves corresponding to the adjacent unloading points corresponding to the continuous output signals.

[0060] In some embodiments, the first target cluster number is obtained based on the following steps: S1. The electronic device clusters multiple second sub-curves corresponding to the continuous input signal based on the first cluster number corresponding to the continuous input signal to obtain a clustering result of the first cluster number; S2. The electronic device determines the first target cluster number based on the root mean square error (RMSE) corresponding to the clustering result of the first cluster number.

[0061] The first cluster number refers to a preset initial cluster number, which is generally set to 1. The first cluster number can be represented by p1.

[0062] Example 1: S1. The electronic device may use a preset K-means (Kmeans) clustering algorithm to cluster multiple second sub-curves corresponding to the continuous input signal based on the first cluster number (p1=1 at this time) corresponding to the continuous input signal, and obtain a clustering result of the first cluster number. Specifically, a second sub-curve sample of the first cluster number is selected as the cluster center of the first cluster number, and for any second sub-curve among the multiple second sub-curves, the Euclidean distance between the second sub-curve and each cluster center is calculated, and the second sub-curve is classified into the cluster where the cluster center corresponding to the minimum Euclidean distance is located.

[0063] Next, for each clustering result in the clustering result of the first clustering number, the electronic device can determine an initial root mean square error between the clustering result and the corresponding cluster center. It can be understood that there are as many initial root mean square errors as there are clustering results. The electronic device averages the initial root mean square errors of the first clustering number to obtain the root mean square error corresponding to the clustering result of the first clustering number.

[0064] Then, S2, the electronic device may determine the first target cluster number according to the above root mean square error, so as to subsequently determine the target cluster number in combination with the second target cluster number.

[0065] In some embodiments, S2, the electronic device determines the first target cluster number based on the root mean square error corresponding to the clustering result of the first cluster number, which may include: S21, when the mean square error is less than or equal to a preset threshold, the electronic device determines the first cluster number as the first target cluster number; S22, when the mean square error is greater than the preset threshold, the electronic device increases the first cluster number to obtain a second cluster number; and determines the second cluster number as the new first cluster number; S23, the electronic device repeats the above steps S1, S21-S22 until the finally determined root mean square error is less than or equal to the preset threshold, and determines the cluster number corresponding to the finally determined root mean square error as the first target cluster number.

[0066] Optionally, the preset threshold value may be set before the electronic device leaves the factory, or may be obtained through user debugging.

[0067] In combination with Example 1, Example 2: After determining the root mean square error corresponding to the clustering result of the first clustering number, S21, if the root mean square error is less than or equal to the preset threshold, it means that the convergence condition is met at this time, and the electronic device directly determines the first clustering number (p1=1 at this time) as the first target clustering number; S22, if the root mean square error is greater than the preset threshold, it means that the convergence condition has not been met at this time, then the electronic device increases the first clustering number (such as p1+1=2), obtains the second clustering number p2 (p2=2), and determines the second clustering number p2 as the new first clustering number (p1=2 at this time); S23, the electronic device repeats the above steps S1, S21-S22 until the finally determined root mean square error is less than or equal to the preset threshold, and determines the clustering number corresponding to the finally determined root mean square error as the first target clustering number.

[0068] Optionally, the second target cluster number is obtained based on the following steps: S1. The electronic device clusters multiple second sub-curves corresponding to the continuous output signal based on the third cluster number corresponding to the continuous output signal to obtain a clustering result of the third cluster number; S2. The electronic device determines the second target cluster number based on the root mean square error corresponding to the clustering result of the third cluster number.

[0069] The third cluster number refers to a preset initial cluster number, which is generally set to 1.

[0070] Optionally, S2, the electronic device determines the second target cluster number based on the root mean square error corresponding to the clustering result of the third cluster number, which may include: S21, when the mean square error is less than or equal to a preset threshold, the electronic device determines the third cluster number as the second target cluster number; S22, when the mean square error is greater than the preset threshold, the electronic device increases the third cluster number to obtain a fourth cluster number; and determines the fourth cluster number as the new third cluster number; S23, the electronic device repeats the above steps S1, S21-S22 until the finally determined root mean square error is less than or equal to the preset threshold, and determines the cluster number corresponding to the finally determined root mean square error as the second target cluster number.

[0071] It should be noted that the process of the electronic device determining the second target cluster number is the same as the process of the electronic device determining the first target cluster number, which will not be described in detail here.

[0072] In some embodiments, the electronic device determines the target cluster number based on the first target cluster number corresponding to multiple second sub-curves corresponding to continuous input signals and the second target cluster number corresponding to multiple second sub-curves corresponding to continuous output signals, which may include: the electronic device determines the minimum value of the first target cluster number and the second target cluster number as the target cluster number.

[0073] For example, assuming that the first target cluster number is p in , the second target cluster number is p out , the target cluster number can be expressed as: p=min{p in , p out}.

[0074] In this way, the electronic device can cluster the multiple second sub-curves based on the optimal clustering number (ie, the target clustering number p) to determine the third sub-curves corresponding to the adjacent unloading points.

[0075] Taking adjacent unloading points t2 and t3 as an example, combined with Figure 3 , Figure 4 It is a schematic diagram of the third sub-curve provided by the present invention. Figure 4 In the figure, the red curve segment is the third sub-curve corresponding to the adjacent unloading points (t2 and t3).

[0076] Step 104: Determine the motion regression curve corresponding to the working machine according to the third sub-curves corresponding to all adjacent unloading points. The motion regression curve is used to determine the control performance evaluation result corresponding to the working machine.

[0077] The electronic device can determine the motion regression curve corresponding to the operating machinery based on the third sub-curves corresponding to all adjacent unloading points. The motion regression curve can accurately reflect the motion trend of the operating machinery when it performs multiple cyclic actions, laying an objective foundation for determining the corresponding control performance evaluation results of the operating machinery, thereby effectively avoiding the subjectivity and uncertainty of human judgment.

[0078] In some embodiments, the electronic device determines the motion regression curve corresponding to the operating machinery based on the third sub-curves corresponding to all adjacent unloading points, which may include: the electronic device smoothes the third sub-curves corresponding to all adjacent unloading points to obtain the motion regression curve corresponding to the operating machinery.

[0079] For example, Figure 5 Schematic diagram of the smoothing process provided by the present invention. Figure 5 As can be seen from the figure, since the third sub-curves corresponding to all adjacent unloading points cannot form a continuous and smooth trajectory, the electronic device calculates the third sub-curves corresponding to all adjacent unloading points ( Figure 5 The multiple red curve segments shown in (a) in the figure are smoothed to obtain the corresponding motion regression curve of the operating machine ( Figure 5 The red curve shown in (b)).

[0080] It should be noted that, when the continuous target signal includes a continuous input signal, the electronic device executes the above steps 101 to 104 to obtain an action regression curve corresponding to the continuous input signal; when the continuous target signal includes a continuous output signal, the electronic device executes the above steps 101 to 104 to obtain an action regression curve corresponding to the continuous output signal.

[0081] In some embodiments, after step 104, the method may further include: the electronic device determines a standard input signal based on an action regression curve corresponding to the continuous input signal; and determines a standard output signal based on an action regression curve corresponding to the continuous output signal; the electronic device determines a target scoring index based on the continuous input signal, the standard input signal, the continuous output signal and the standard output signal; the electronic device determines a control performance evaluation result corresponding to the operating machinery based on the target scoring index.

[0082] The electronic device can determine the standard input signal according to the action regression curve corresponding to the continuous input signal, and the electronic device can determine the standard output signal according to the action regression curve corresponding to the continuous output signal. In this way, the electronic device can determine the target scoring index, and then compare the target scoring index with the preset index threshold to determine the control performance evaluation result corresponding to the operating machine. Specifically, if the target scoring index is greater than or equal to the preset index threshold, it means that the control performance of the operating machine meets the expected standard or requirement, and the control performance reaching the standard is determined as the control performance evaluation result corresponding to the operating machine; if the target scoring index is less than the preset index threshold, it means that the control performance of the operating machine does not meet the expected standard or requirement, and the control performance not meeting the standard is determined as the control performance evaluation result corresponding to the operating machine. In the whole process, the control performance of the operating machine can be objectively evaluated, which effectively avoids the subjectivity and uncertainty of human judgment, so that the test personnel can find problems in time and take corresponding measures.

[0083] In some embodiments, the electronic device determines the target scoring indicator based on the continuous input signal, the standard input signal, the continuous output signal and the standard output signal, which may include: the electronic device determines a first correlation and a first Euclidean distance between the continuous input signal and the standard input signal; and determines a second correlation and a second Euclidean distance between the continuous output signal and the standard output signal; the electronic device determines the target scoring indicator based on the first correlation, the first Euclidean distance, the second correlation and the second Euclidean distance.

[0084] For example, the calculation formula of the target scoring index is: r=[r in (E in -E out )] / (r out E out ), where r represents the target scoring index; r in Indicates the first correlation; E in represents the first Euclidean distance; r out Indicates the second correlation; E out Represents the second Euclidean distance.

[0085] In an embodiment of the present invention, according to the continuous target signals corresponding to each of the operating machinery when performing cyclic actions for multiple times, the corresponding target curves are determined; for each of the multiple target curves, based on the multiple unloading points in the target curve, the target curve is sliced ​​to determine multiple first sub-curves; for the adjacent unloading points in the multiple unloading points, the second sub-curves corresponding to the adjacent unloading points are determined from the multiple first sub-curves; based on the target clustering numbers corresponding to the multiple second sub-curves, the multiple second sub-curves are clustered to determine the third sub-curves corresponding to the adjacent unloading points; according to the third sub-curves corresponding to all the adjacent unloading points, the action regression curve corresponding to the operating machinery is determined, and the action regression curve is used to determine the control performance evaluation result corresponding to the operating machinery. The method analyzes and processes the continuous target signals corresponding to each of the operating machinery when performing cyclic actions for multiple times, and obtains the action regression curve corresponding to the operating machinery. The action regression curve can accurately reflect the action trend of the operating machinery when performing cyclic actions for multiple times, and lays an objective foundation for determining the control performance evaluation result corresponding to the operating machinery, thereby effectively avoiding the subjectivity and uncertainty of human judgment.

[0086] The controllability evaluation device for a working machine provided by the present invention is described below. The controllability evaluation device for a working machine described below and the controllability evaluation method for a working machine described above can be referred to each other.

[0087] Figure 6 Schematic diagram of the structure of the operating machine control performance evaluation device provided by the present invention, such as Figure 6 As shown, the device includes the following processing module 601.

[0088] The processing module 601 is used to determine the corresponding target curves according to the continuous target signals corresponding to each of the operating machinery when the operating machinery performs cyclic actions for multiple times; for each target curve in the multiple target curves, based on the multiple unloading points in the target curve, slice the target curve to determine multiple first sub-curves; for adjacent unloading points in the multiple unloading points, determine the second sub-curve corresponding to the adjacent unloading point from the multiple first sub-curves; based on the target cluster numbers corresponding to the multiple second sub-curves, cluster the multiple second sub-curves to determine the third sub-curve corresponding to the adjacent unloading point; and determine the action regression curve corresponding to the operating machinery according to the third sub-curves corresponding to all the adjacent unloading points, and the action regression curve is used to determine the control performance evaluation result corresponding to the operating machinery.

[0089] Optionally, the continuous target signal may include: a continuous input signal and a continuous output signal; the target cluster number is obtained based on the following steps: determining the target cluster number according to the first target cluster number corresponding to the multiple second sub-curves corresponding to the continuous input signal and the second target cluster number corresponding to the multiple second sub-curves corresponding to the continuous output signal.

[0090] Optionally, the first target cluster number is obtained based on the following steps: S1. Based on the first cluster number corresponding to the continuous input signal, clustering multiple second sub-curves corresponding to the continuous input signal to obtain a clustering result of the first cluster number; S2. Determine the first target cluster number based on the root mean square error corresponding to the clustering result of the first cluster number.

[0091] Optionally, the processing module 601 is specifically used for S21, when the mean square error is less than or equal to a preset threshold, determining the first cluster number as the first target cluster number; S22, when the mean square error is greater than the preset threshold, increasing the first cluster number to obtain a second cluster number; and determining the second cluster number as the new first cluster number; S23, repeating the above steps S1, S21-S22 until the finally determined root mean square error is less than or equal to the preset threshold, and determining the cluster number corresponding to the finally determined root mean square error as the first target cluster number.

[0092] Optionally, the processing module 601 is specifically configured to determine a minimum value between the first target cluster number and the second target cluster number as the target cluster number.

[0093] Optionally, the processing module 601 is also used to determine a standard input signal based on an action regression curve corresponding to the continuous input signal; and to determine a standard output signal based on an action regression curve corresponding to the continuous output signal; to determine a target scoring index based on the continuous input signal, the standard input signal, the continuous output signal and the standard output signal; and to determine a control performance evaluation result corresponding to the operating machinery based on the target scoring index.

[0094] Optionally, the processing module 601 is specifically used to determine a first correlation and a first Euclidean distance between the continuous input signal and the standard input signal; and determine a second correlation and a second Euclidean distance between the continuous output signal and the standard output signal; and determine the target scoring index based on the first correlation, the first Euclidean distance, the second correlation and the second Euclidean distance.

[0095] Optionally, the processing module 601 is specifically used to smooth the third sub-curves corresponding to all the adjacent unloading points to obtain the motion regression curve corresponding to the operating machine.

[0096] Figure 7 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 7As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the control performance evaluation method of the working machine, the method comprising: determining the corresponding target curves according to the continuous target signals corresponding to the working machine when the working machine performs the cyclic action for multiple times; for each target curve in the multiple target curves, based on the multiple unloading points in the target curve, slicing the target curve to determine multiple first sub-curves; for adjacent unloading points in the multiple unloading points, determining the second sub-curve corresponding to the adjacent unloading point from the multiple first sub-curves; based on the target clustering numbers corresponding to the multiple second sub-curves, clustering the multiple second sub-curves to determine the third sub-curve corresponding to the adjacent unloading point; determining the action regression curve corresponding to the working machine according to the third sub-curves corresponding to all the adjacent unloading points, the action regression curve is used to determine the control performance evaluation result corresponding to the working machine.

[0097] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0098] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the control performance evaluation method of the working machine provided by the above-mentioned methods, which method includes: determining the corresponding target curves according to the continuous target signals corresponding to each of the working machines when the working machines perform cyclic actions multiple times; for each target curve in the multiple target curves, slicing the target curve based on the multiple unloading points in the target curve to determine multiple first sub-curves; for adjacent unloading points in the multiple unloading points, determining the second sub-curve corresponding to the adjacent unloading point from the multiple first sub-curves; based on the target cluster numbers corresponding to the multiple second sub-curves, clustering the multiple second sub-curves to determine the third sub-curve corresponding to the adjacent unloading point; determining the action regression curve corresponding to the working machine according to the third sub-curves corresponding to all the adjacent unloading points, and the action regression curve is used to determine the control performance evaluation result corresponding to the working machine.

[0099] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the control performance evaluation method of the working machine provided by the above-mentioned methods, the method comprising: determining the corresponding target curves according to the continuous target signals corresponding to each of the working machines when the working machine performs cyclic actions multiple times; for each target curve in the multiple target curves, slicing the target curve based on the multiple unloading points in the target curve to determine multiple first sub-curves; for adjacent unloading points in the multiple unloading points, determining the second sub-curve corresponding to the adjacent unloading point from the multiple first sub-curves; clustering the multiple second sub-curves based on the target cluster numbers corresponding to the multiple second sub-curves to determine the third sub-curve corresponding to the adjacent unloading point; determining the action regression curve corresponding to the working machine according to the third sub-curves corresponding to all the adjacent unloading points, and the action regression curve is used to determine the control performance evaluation result corresponding to the working machine.

[0100] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0101] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the controllability of a working machine, characterized in that: include: Determine the respective corresponding target curves according to the respective corresponding continuous target signals when the operating machine performs the cyclic actions for multiple times; For each target curve among the multiple target curves, based on multiple unloading points in the target curve, the target curve is sliced ​​to determine multiple first sub-curves; for adjacent unloading points among the multiple unloading points, a second sub-curve corresponding to the adjacent unloading point is determined from the multiple first sub-curves; Clustering the plurality of second sub-curves based on target cluster numbers corresponding to the plurality of second sub-curves to determine a third sub-curve corresponding to the adjacent unloading point; According to the third sub-curves corresponding to all adjacent unloading points, a motion regression curve corresponding to the working machine is determined, and the motion regression curve is used to determine the control performance evaluation result corresponding to the working machine.

2. The method for evaluating the controllability of a working machine according to claim 1, characterized in that: The continuous target signal includes: a continuous input signal and a continuous output signal; the target cluster number is obtained based on the following steps: The target cluster number is determined according to the first target cluster number corresponding to the plurality of second sub-curves corresponding to the continuous input signal and the second target cluster number corresponding to the plurality of second sub-curves corresponding to the continuous output signal.

3. The method for evaluating the controllability of a working machine according to claim 2, characterized in that: The first target cluster number is obtained based on the following steps: S1. Clustering a plurality of second sub-curves corresponding to the continuous input signal based on a first cluster number corresponding to the continuous input signal to obtain a clustering result of the first cluster number; S2. Determine the first target number of clusters according to the root mean square error corresponding to the clustering result of the first number of clusters.

4. The method for evaluating the controllability of a working machine according to claim 3, characterized in that: The step S2, determining the first target number of clusters according to a root mean square error corresponding to the clustering result of the first number of clusters, comprises: S21. When the mean square error is less than or equal to a preset threshold, determining the first cluster number as the first target cluster number; S22. When the mean square error is greater than the preset threshold, increase the first cluster number to obtain a second cluster number; and determine the second cluster number as the new first cluster number; S23, repeatedly executing the above steps S1, S21-S22 until the finally determined root mean square error is less than or equal to the preset threshold, and determining the number of clusters corresponding to the finally determined root mean square error as the first target number of clusters.

5. The method for evaluating the controllability of a working machine according to claim 2, wherein: The determining the target cluster number according to the first target cluster number corresponding to the plurality of second sub-curves corresponding to the continuous input signal and the second target cluster number corresponding to the plurality of second sub-curves corresponding to the continuous output signal comprises: The minimum value between the first target cluster number and the second target cluster number is determined as the target cluster number.

6. The method for evaluating the controllability of a working machine according to any one of claims 2 to 5, characterized in that: The method further comprises: Determine a standard input signal according to the action regression curve corresponding to the continuous input signal; and determine a standard output signal according to the action regression curve corresponding to the continuous output signal; Determining a target scoring index according to the continuous input signal, the standard input signal, the continuous output signal, and the standard output signal; According to the target scoring index, a controllability evaluation result corresponding to the working machine is determined.

7. The method for evaluating the controllability of a working machine according to claim 6, characterized in that: The step of determining a target scoring index according to the continuous input signal, the standard input signal, the continuous output signal, and the standard output signal comprises: Determine a first correlation and a first Euclidean distance between the continuous input signal and the standard input signal; and determine a second correlation and a second Euclidean distance between the continuous output signal and the standard output signal; The target scoring index is determined according to the first correlation, the first Euclidean distance, the second correlation, and the second Euclidean distance.

8. The method for evaluating the controllability of a working machine according to any one of claims 1 to 5, characterized in that: The step of determining the motion regression curve corresponding to the working machine according to the third sub-curves corresponding to all adjacent unloading points includes: The third sub-curves corresponding to all the adjacent unloading points are smoothed to obtain the motion regression curve corresponding to the working machine.

9. A device for evaluating the control performance of a working machine, characterized in that: include: A processing module, used for determining the respective corresponding target curves according to the respective corresponding continuous target signals when the operating machine performs the cyclic actions for multiple times; For each target curve among the multiple target curves, based on the multiple unloading points in the target curve, the target curve is sliced ​​to determine a plurality of first sub-curves; for adjacent unloading points among the multiple unloading points, the second sub-curve corresponding to the adjacent unloading point is determined from the multiple first sub-curves; based on the target cluster numbers corresponding to the multiple second sub-curves, the multiple second sub-curves are clustered to determine the third sub-curve corresponding to the adjacent unloading point; based on the third sub-curves corresponding to all the adjacent unloading points, the motion regression curve corresponding to the operating machine is determined, and the motion regression curve is used to determine the control performance evaluation result corresponding to the operating machine.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for evaluating the maneuverability of the working machine according to any one of claims 1 to 8 is implemented.

Images