Method, device, controller and excavator for determining working condition type of excavator

Abstract

An embodiment of the present application provides a method, a device, a controller, and an excavator for determining the working condition type of an excavator. The method includes: obtaining data characteristics of the excavator during excavation operations in a preset operation time period, where the data characteristics include working condition data characteristics corresponding to multiple working condition parameters of each excavation cycle within the preset operation time period; respectively inputting the working condition data characteristics of each excavation cycle into a first working condition recognition model and a second working condition recognition model; obtaining a first working condition type corresponding to each excavation cycle output by the first working condition recognition model and a second working condition type corresponding to each excavation cycle output by the second working condition recognition model; counting all the first working condition types and second working condition types of multiple cycles; and determining the working condition type with the largest quantity as the actual working condition type of the excavator during excavation operations in the preset operation time period, so as to improve the accuracy of identifying the working condition type, avoid faults of the excavator, and extend the service life of the excavator.

Description

Technical Field

[0001] The present application relates to the technical field of construction machinery, and particularly relates to a method, a device, a controller and an excavator for determining the working condition type of an excavator. Background Art

[0002] Excavators play a very important role in the construction machinery industry, especially in earthwork construction, and are mainly used in engineering construction such as mining, construction, and water conservancy infrastructure. As a multi-functional machine, the main operation contents of an excavator are excavation, landfill, transportation, loading soil, etc. In different operating environments and operating objects, the operating conditions of the excavator are very complex.

[0003] In the current existing technologies, most of them determine the working condition of the excavator by collecting a large number of pilot signals and setting a preset threshold to judge whether the pilot signal is within the preset threshold. This kind of identification method needs to rely on human experience to find the threshold rule from the data, and the accuracy and reliability are relatively low. And many excavators do not have a device for collecting pilot signals. Timely and accurately determining the operating condition of the excavator is of great significance for the whole machine maintenance, fault detection, targeted sales, etc. of the excavator. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method, a device, a controller and an excavator for determining the working condition type of an excavator.

[0005] To achieve the above purpose, the first aspect of the present application provides a method for determining the working condition type of an excavator, including:

[0006] Obtain the data features of the excavator during the excavation operation in a preset operation time period, where the data features include the working condition data features corresponding to multiple working condition parameters of each excavation cycle in the preset operation time period;

[0007] Input the working condition data features of each excavation cycle into the first working condition recognition model and the second working condition recognition model respectively;

[0008] Obtain the first working condition type corresponding to each excavation cycle output by the first working condition recognition model and the second working condition type corresponding to each excavation cycle output by the second working condition recognition model;

[0009] Count all the first working condition types and the second working condition types of multiple cycles;

[0010] Determine the actual working condition type of the excavator during the excavation operation in the preset operation time period as the working condition type with the largest quantity.

[0011] In an embodiment of the present application, the method further includes a training step for the first working condition recognition model. The training step of the first working condition recognition model includes: obtaining historical working condition data corresponding to the excavator under multiple working condition types. Among them, the excavator includes at least a first pressure pump and a second pressure pump, and the historical working condition data includes first historical working condition data of the first pressure pump and / or second historical working condition data of the second pressure pump; determining the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data; determining first working condition data features corresponding to multiple historical working condition parameters included in each excavation cycle; sequentially inputting the first working condition data features corresponding to each excavation cycle into the first working condition recognition model to train the first working condition recognition model.

[0012] In an embodiment of the present application, the historical working condition data includes historical working condition parameters corresponding to each time point. Determining the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data includes: filtering the historical working condition data; traversing the historical working condition parameters included in the filtered historical working condition data according to a sliding window with a preset duration, and determining the excavation break point of the excavator as the time point corresponding to the minimum value of the historical working condition parameters within the sliding window; dividing the filtered historical working condition data according to multiple excavation break points to determine the excavation cycle of the excavator.

[0013] In an embodiment of the present application, the first historical working condition data includes first historical working condition parameters corresponding to each time point, and the second historical working condition data includes second historical working condition parameters corresponding to each time point. The method further includes a training step for the second working condition recognition model. The training step of the second working condition recognition model includes: for the same time point, determining the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to the time point; sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator; screening out the parameter differences greater than or equal to a preset parameter threshold, and determining second working condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold; inputting the second working condition data features into the second working condition recognition model to train the second working condition recognition model.

[0014] In an embodiment of the present application, sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator includes: sorting the parameter differences in the order of the time points; filtering the parameter signals corresponding to each parameter difference; traversing the parameter differences included in the filtered parameter signals according to a sliding window with a preset duration, and determining the excavation break point of the excavator as the time point corresponding to the minimum value of the parameter differences within the sliding window; according to the sorting of the time points, determining the time period between two adjacent excavation break points as the excavation cycle of the excavator.

[0015] In the embodiments of the present application, before screening out the parameter differences greater than or equal to the preset parameter threshold and determining the second working condition data features included in each mining cycle based on the parameter differences greater than or equal to the preset parameter threshold, it includes: determining the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to each time point, and determining the parameter mean of the parameter difference; determining a preset multiple of the parameter mean as the preset parameter threshold.

[0016] In the embodiments of the present application, the preset multiple is 0.1 or 0.05.

[0017] In the embodiments of the present application, the working condition types include the soil excavation working condition and the stone excavation working condition, where the soil excavation working condition includes any one of the backfill soil excavation working condition and the original soil excavation working condition.

[0018] In the embodiments of the present application, the working condition parameters include the pressure value of the excavator pressure signal and / or the current value of the current signal.

[0019] The second aspect of the present application provides a controller configured to execute the above method for determining the working condition type of an excavator.

[0020] The third aspect of the present application provides a device for determining the working condition type of an excavator, including: a data acquisition device for acquiring the working condition data generated by the excavator during operation; and the above-mentioned controller.

[0021] The fourth aspect of the present application provides an excavator including the above-mentioned device for determining the working condition type of an excavator.

[0022] In the embodiments of the present application, the excavator includes at least a first pressure pump and a second pressure pump.

[0023] Through the above technical solutions, it is possible to timely and accurately determine the current working condition type of the excavator, avoid failures of the excavator due to different working conditions during operation, improve the safety of the excavator operation, and further extend the service life of the excavator. At the same time, the method of multi-model and multi-cycle fusion can greatly improve the accuracy and stability of identifying the working condition type of the excavator.

[0024] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation part. Description of the Drawings

[0025] The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. They are used to explain the embodiments of the present application together with the following specific implementation, but do not constitute a limitation to the embodiments of the present application. In the drawings:

[0026] Figure 1Schematically shows a flowchart of a method for determining the working condition type of an excavator according to an embodiment of the present application;

[0027] Figure 2 Schematically shows a flowchart of a method for determining the working condition type of an excavator according to another embodiment of the present application;

[0028] Figure 3 Schematically shows a structural block diagram of a device for determining the working condition type of an excavator according to an embodiment of the present application;

[0029] Figure 4 Schematically shows the internal structure diagram of a computer device according to an embodiment of the present application. Detailed implementation manners

[0030] To make the objectives, 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 with reference to the accompanying drawings in the embodiments of the present application. It should be understood that the specific implementation manners 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 those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.

[0031] Figure 1 Schematically shows a flowchart of a method for determining the working condition type of an excavator according to an embodiment of the present application. As Figure 1 shown, in an embodiment of the present application, a method for determining the working condition type of an excavator is provided, including the following steps:

[0032] Step 101, obtain the data characteristics of the excavator during the excavation operation in a preset operation time period, where the data characteristics include the working condition data characteristics corresponding to multiple working condition parameters of each excavation cycle in the preset operation time period.

[0033] Step 102, input the working condition data characteristics of each excavation cycle into the first working condition recognition model and the second working condition recognition model respectively.

[0034] Step 103, obtain the first working condition type corresponding to each excavation cycle output by the first working condition recognition model and the second working condition type corresponding to each excavation cycle output by the second working condition recognition model.

[0035] Step 104, count all the first working condition types and the second working condition types of multiple cycles.

[0036] Step 105, determine the actual working condition type of the excavator during the excavation operation in the preset operation time period as the working condition type with the largest quantity.

[0037] The working conditions of an excavator during excavation operations can include soil excavation conditions and stone excavation conditions. Among them, the soil excavation conditions can include backfill soil excavation conditions and virgin soil excavation conditions. For different working conditions, the excavator can adopt different excavation operation methods. Therefore, by determining the working condition type of the excavator during excavation operations, it is possible to avoid malfunctions caused by improper selection of operation methods.

[0038] To identify the working condition type of the excavator during excavation operations, the controller can first obtain the data characteristics of the excavator during excavation operations in a preset operation time period. Among them, the data characteristics can include the working condition data characteristics corresponding to multiple working condition parameters in each excavation cycle within the preset operation time period. The preset time period can include multiple excavation cycles during the excavation operation of the excavator.

[0039] Among them, each excavation cycle of the excavator can refer to the pressure signal or current signal generated after the excavator sequentially completes four excavation actions: excavation, loading and slewing, unloading, and returning with an empty bucket. Each excavation cycle can contain multiple time points, and each time point has corresponding working condition parameters. Therefore, for each excavation cycle, there can be multiple working condition parameters. Among them, the working condition parameters can be pressure values and / or current values. After determining the multiple working condition parameters included in each excavation cycle, the working condition data characteristics of each excavation cycle can be further determined based on the multiple working condition parameters corresponding to each excavation cycle. The working condition data characteristics can be parameter means, parameter variances, parameter medians, and parameter quantiles, etc.

[0040] Taking the example that each excavation cycle contains three working condition parameters, each excavation cycle can contain the working condition parameter 1 corresponding to the time point t1, the working condition parameter 2 corresponding to the time point t2, and the working condition parameter 3 corresponding to the time point t3. If the average of the working condition parameter 1, the working condition parameter 2, and the working condition parameter 3 is calculated, the working condition data characteristics corresponding to the three working condition parameters of each excavation cycle can refer to the parameter mean.

[0041] After determining the working condition data characteristics of each excavation cycle, the working condition type of each excavation cycle can be determined through the first working condition identification model and the second working condition identification model. Among them, the first working condition identification model and the second working condition identification model can refer to different classification models. The XG-Boost can be selected for the first working condition identification model, and the extreme vector machine can be selected for the second working condition identification model.

[0042] The controller can input the working condition data features into the first working condition recognition model and the second working condition recognition model respectively to obtain the first working condition type corresponding to each excavation cycle output by the first working condition recognition model and the second working condition type corresponding to each excavation cycle output by the second working condition type. Among them, the first working condition type and the second working condition type can refer to the working condition types of the excavator. The working condition types of the excavator can include the soil excavation working condition and the stone excavation working condition. The soil excavation working condition can include any one of the backfill soil excavation working condition and the native soil excavation working condition.

[0043] For each excavation cycle, since the training methods adopted by the first working condition recognition model and the second working condition recognition model are different, the first working condition type output by the first working condition recognition model and the second working condition type output by the second working condition recognition model can be different working condition types or the same working condition types. In order to further determine the working condition type of the excavator during the preset operation time period, the controller can count all the first working condition types and the second working condition types of multiple cycles. Then, the controller can determine the working condition type with the largest quantity as the actual working condition type of the excavator during the excavation operation in the preset operation time period.

[0044] Taking 10 excavation cycles as an example, the controller can count that the working condition types of the excavator during the preset operation time period are 20. Among them, the first working condition type can be 10, and the second working condition type can be 10. Specifically, if the first working condition type is A, A, A, A, A, B, B, B, C, and C, and if the second working condition type is A, A, A, A, B, B, B, C, C, and C, then the controller can determine the working condition type A with the largest quantity as the actual working condition type of the excavator during the excavation operation in the preset operation time period.

[0045] Through the above technical solution, it is possible to timely and accurately determine the current working condition type of the excavator, avoid the occurrence of failures due to different working conditions during the operation of the excavator, improve the safety of the excavator operation, and further extend the service life of the excavator. At the same time, the method of fusing multiple models and multiple cycles can greatly improve the accuracy and stability of identifying the working condition type of the excavator.

[0046] In one embodiment, the method further includes a training step for the first working condition recognition model, and the training step of the first working condition recognition model includes: obtaining historical working condition data corresponding to the excavator under multiple working condition types, where the excavator includes at least a first pressure pump and a second pressure pump, and the historical working condition data includes first historical working condition data of the first pressure pump and / or second historical working condition data of the second pressure pump; determining the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data; determining first working condition data features corresponding to multiple historical working condition parameters included in each excavation cycle; and sequentially inputting the first working condition data features corresponding to each excavation cycle into the first working condition recognition model to train the first working condition recognition model.

[0047] The excavator can at least include a first pressure pump and a second pressure pump. The working condition types of the excavator can refer to the working conditions of excavating soil and excavating stone. The working condition of excavating soil can include any one of the working conditions of excavating backfill soil and excavating virgin soil. After determining the working condition type, the controller can obtain the historical working condition data corresponding to the excavator under multiple working condition types.

[0048] Among them, the historical working condition data can include first historical working condition data of the first pressure pump and / or second historical working condition data of the second pressure pump. The historical working condition data can refer to historical pressure signals or historical current signals. Among them, the first historical working condition data and the second historical working condition data can correspond to the historical working condition data of the excavator. For example, if the historical working condition data refers to a historical pressure signal, the first historical working condition data can be the first historical pressure signal, and the second historical working condition data can be the second historical pressure signal.

[0049] The controller can determine the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data included in the historical working condition data. That is, the controller can determine the excavation cycle of the excavator according to the first historical working condition data or the second historical working condition data, or can also determine the excavation cycle of the excavator according to the first historical working condition data and the second historical working condition data. Among them, each excavation cycle of the excavator can refer to the pressure signal or current signal generated after the excavator sequentially completes four excavation actions of excavation, loading and slewing, unloading, and returning with an empty bucket.

[0050] Each excavation cycle may include multiple time points, and each time point has corresponding historical operating condition parameters. Therefore, for each excavation cycle, there can be multiple historical operating condition parameters. Among them, the historical operating condition parameters can be historical pressure values and / or historical current values. After determining the multiple historical operating condition parameters included in each excavation cycle, the first operating condition data feature of each excavation cycle can be further determined according to the multiple historical operating condition parameters corresponding to each excavation cycle. The first operating condition data feature can refer to historical parameter means, historical parameter variances, historical parameter medians, historical parameter quantiles, etc. corresponding to the multiple historical operating condition parameters.

[0051] The controller can sequentially input the first operating condition data feature corresponding to each excavation cycle into the first operating condition recognition model to train the first operating condition recognition model. Among them, the first operating condition recognition model can select a classification model, and the classification model can be XGBoost.

[0052] In one embodiment, after determining the first operating condition data feature corresponding to the multiple historical operating condition parameters included in each excavation cycle, the controller can screen out important features according to the Pearson correlation coefficient and the feature importance of the first operating condition data feature. Screening out important features can prevent overfitting in the subsequent model training process, ensure the stability of the model, and at the same time reduce the operation complexity of the subsequent model.

[0053] In one embodiment, the historical operating condition data includes historical operating condition parameters corresponding to each time point. Determining the excavation cycle of the excavator according to the first historical operating condition data and / or the second historical operating condition data includes: filtering the historical operating condition data; traversing the historical operating condition parameters included in the filtered historical operating condition data according to a sliding window with a preset duration, so as to determine the time point corresponding to the minimum value of the historical operating condition parameters within the sliding window as the excavation break point of the excavator; dividing the filtered historical operating condition data according to multiple excavation break points to determine the excavation cycle of the excavator.

[0054] Among them, the historical operating condition data can include historical operating condition parameters corresponding to each time point. The historical operating condition data can refer to a historical pressure signal or a historical current signal. The historical operating condition parameters can refer to a historical pressure value or a historical current value. After obtaining the historical operating condition data, the controller can filter the historical operating condition data. The controller can filter the historical operating condition parameters included in the historical operating condition data by means of Savitzky–Golay smoothing filtering. By means of Savitzky–Golay smoothing filtering, the noise in the historical operating condition data can be filtered out, the shape and width of the historical operating condition data can be ensured to remain unchanged, and the periodicity of the filtered historical operating condition data can be made obvious.

[0055] The controller can traverse the historical working condition parameters included in the filtered historical working condition data according to a sliding window with a preset duration, so as to determine the excavation break point of the excavator as the time point corresponding to the minimum value of the historical working condition parameters within the sliding window. Specifically, the controller can arrange the historical working condition parameters included in the filtered historical working condition data in chronological order. Then, the controller can select a sliding window with a preset duration and traverse the historical working condition parameters included in the filtered historical working condition data according to the sliding window with the preset duration. If the historical working condition parameter corresponding to the time point where the center line of the sliding window is located is the minimum value of the historical working condition parameters within the sliding window, the controller can determine the time point corresponding to the minimum value of the historical working condition parameters within the sliding window as the excavation break point of the excavator. Then, the controller can divide the filtered historical working condition data according to multiple excavation break points to determine the excavation cycle of the excavator.

[0056] Among them, the preset duration of the sliding window can be selected according to the duration used for the excavator to complete four actions of excavation, loading and slewing, unloading, and returning with an empty bucket. The preset duration of the sliding window can be slightly longer than the preset duration used for the excavator to complete one excavation cycle. Generally, the duration used for the excavator to complete the four actions of excavation, loading and slewing, unloading, and returning with an empty bucket can be 15s - 20s. Therefore, the preset duration of the sliding window can be correspondingly set to a sliding window greater than 15s - 20s. For example, it can be correspondingly set to a sliding window of 20s - 30s. The sliding step of the sliding window can be 1 data sampling period (if the data sampling period is 100ms, the step is 100ms).

[0057] Taking the sliding window A with a preset duration of 20s as an example, the sliding window A can include the pressure values corresponding to each time point. For example, the sliding window A can include the pressure value p1 corresponding to the time point t1, the pressure value p2 corresponding to the time point t2, the pressure value p3 corresponding to the time point t3, and the pressure value p4 corresponding to the time point t4. Among them, the magnitudes of the pressure values within the sliding window can be p1 > p2 > p3 > p4. If the pressure value corresponding to the time point where the center line of the sliding window is located, that is, the 10th second, is p4, the controller can use the t4 time point corresponding to the pressure value p4 as an excavation break point of the excavator. Then, the controller can sequentially determine multiple excavation break points and divide the historical pressure signal according to the multiple excavation break points to determine the excavation cycle of the excavator.

[0058] In one embodiment, the first historical operating condition data includes first historical operating condition parameters corresponding to each time point, and the second historical operating condition data includes second historical operating condition parameters corresponding to each time point. The method further includes a training step for the second operating condition recognition model. The training step of the second operating condition recognition model includes: for the same time point, determining the parameter difference between the first historical operating condition parameter and the second historical operating condition parameter corresponding to the time point; sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator; screening out the parameter differences greater than or equal to the preset parameter threshold, and determining the second operating condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold; inputting the second operating condition data features into the second operating condition recognition model to train the second operating condition recognition model.

[0059] Among them, the first historical operating condition data includes first historical operating condition parameters corresponding to each time point, and the second historical operating condition data includes second historical operating condition parameters corresponding to each time point. The first historical operating condition data can be the first historical voltage signal or the first historical current signal. The second historical operating condition data can be the second historical voltage signal or the second historical current signal.

[0060] Since the pressure difference between the first pressure pump and the second pressure pump of the excavator is mainly reflected in the excavation action of the excavator, therefore, using the parameter difference between the first historical operating condition parameter and the second historical operating condition parameter can highlight the excavation action of the excavator and can indirectly magnify the excavation cycle of the excavator. For the same time point, the controller can determine the parameter difference between the first historical operating condition parameter and the second historical operating condition parameter corresponding to each time point. Among them, the first historical operating condition parameter can be the first historical pressure value or the first historical current value. The second historical operating condition parameter can be the second historical pressure value or the second historical current value. The parameter difference can be the pressure difference between the first historical pressure value and the second historical pressure value.

[0061] The controller can sort the parameter differences in the order of the time points to determine the excavation cycle of the excavator. Then, the controller can screen out the parameter differences greater than or equal to the preset parameter threshold included in the excavation cycle, and determine the second operating condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold. Among them, the second operating condition data features can refer to the parameter mean, historical parameter variance, historical parameter median, and historical parameter quantile corresponding to multiple parameter differences, etc. The controller can input the second operating condition data features into the second operating condition recognition model to train the second operating condition recognition model. Among them, the second operating condition recognition model can select the extreme vector machine.

[0062] In one embodiment, after the controller determines the second working condition data features included in each excavation cycle based on a parameter difference greater than or equal to a preset parameter threshold, the controller can screen out important features according to the Pearson correlation coefficient and the feature importance of the second working condition data features. Screening out important features can prevent overfitting during the subsequent model training, ensure the stability of the model, and at the same time reduce the operation complexity of the subsequent model.

[0063] In one embodiment, the parameter differences are sorted in the order of time points to determine the excavation cycle of the excavator, including: sorting the parameter differences in the order of time points; filtering the parameter signals corresponding to each parameter difference; traversing the parameter differences included in the filtered parameter signals according to a sliding window with a preset duration, and determining the time point corresponding to the minimum value of the parameter differences within the sliding window as the excavation break point of the excavator; according to the time point sorting, determining the time period between two adjacent excavation break points as the excavation cycle of the excavator.

[0064] The controller can sort the parameter differences in the order of time points and filter the parameter signals corresponding to each parameter difference. Then, the controller can select a sliding window with a preset duration and traverse the parameter differences included in the filtered parameter signals according to the sliding window with the preset duration. If the parameter difference corresponding to the time point where the center line of the sliding window is located is the minimum value of the parameter differences within the sliding window, the controller can determine the time point corresponding to the minimum value of the parameter differences within the sliding window as the excavation break point of the excavator. Then, the controller can, according to the order of time points, determine the time period between two adjacent excavation break points as the excavation cycle of the excavator.

[0065] Among them, the parameter difference can be a pressure difference or a current difference. The parameter signal can be a pressure difference signal or a current difference signal. Among them, the preset duration of the sliding window can be selected according to the duration used for the excavator to complete four actions of excavation, load rotation, unloading, and empty bucket return. The preset duration of the sliding window can be slightly greater than the preset duration used for the excavator to complete one excavation cycle. Generally, the duration used for the excavator to complete four actions of excavation, load rotation, unloading, and empty bucket return can be 15s - 20s. Therefore, the preset duration of the sliding window can be correspondingly set to a sliding window greater than 15s - 20s. For example, it can be correspondingly set to a sliding window of 20s - 30s. The sliding step of the sliding window can be 1 data sampling period (if the data sampling period is 100ms, the step is 100ms).

[0066] In one embodiment, parameter differences greater than or equal to a preset parameter threshold are screened out, and before determining the second working condition data features included in each excavation cycle based on the parameter differences greater than or equal to the preset parameter threshold, it includes: determining the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to each time point, and determining the parameter mean of the parameter differences; determining a preset multiple of the parameter mean as the preset parameter threshold.

[0067] In one embodiment, the preset multiple is 0.1 or 0.05.

[0068] Wherein, each time point corresponds to a parameter difference. The controller can determine the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to each time point. Then, the controller can determine the corresponding parameter mean according to multiple parameter differences. The controller can determine a preset multiple of the parameter mean as the preset parameter threshold. Among them, the parameter mean can refer to the mean pressure difference or the mean current difference. The preset multiple can be 0.1 or 0.05.

[0069] In one embodiment, the working condition types include the soil excavation working condition and the stone excavation working condition, wherein the soil excavation working condition includes any one of the backfill soil excavation working condition and the native soil excavation working condition.

[0070] The working condition types of the excavator can include the soil excavation working condition and the stone excavation working condition. Among them, the soil excavation working condition can include any one of the backfill soil excavation working condition and the native soil excavation working condition.

[0071] In one embodiment, the working condition parameters include the pressure value of the excavator pressure signal and / or the current value of the current signal.

[0072] The working condition parameters can include the pressure value of the excavator pressure signal and / or the current value of the current signal.

[0073] In one embodiment, as Figure 2 shown, another method for determining the working condition type of an excavator is provided. The method includes:

[0074] Step 201, obtaining the working condition data features corresponding to multiple working condition parameters included in each excavation cycle of the excavator.

[0075] Step 202, inputting the working condition data features into the first working condition recognition model and the second working condition recognition model respectively.

[0076] Step 203, obtaining the first working condition type corresponding to each excavation cycle output by the first working condition recognition model and the second working condition type corresponding to each excavation cycle output by the second working condition recognition model.

[0077] Step 204: Determine the working condition type of the excavator in each excavation cycle according to the first working condition type and the second working condition type.

[0078] Step 205: Determine the most frequent working condition type corresponding to each excavation cycle as the final working condition type.

[0079] The controller can obtain the working condition data characteristics corresponding to multiple working condition parameters included in each excavation cycle of the excavator. Among them, each excavation cycle can include multiple pressure values and can include multiple current values. That is, the working condition parameters can refer to pressure values or can refer to current values. The working condition data characteristics can refer to parameter means, parameter variances, parameter medians, and parameter quantiles, etc. corresponding to multiple working condition parameters.

[0080] The controller can input the working condition data characteristics into the first working condition recognition model and the second working condition recognition model respectively. Among them, the first working condition recognition model can select XGBoost, and the second working condition recognition model can select the extreme vector machine. The controller can obtain the first working condition type corresponding to each excavation cycle output by the first working condition recognition model and the second working condition type corresponding to each excavation cycle output by the second working condition recognition model. Among them, the first working condition type can include the soil excavation working condition and the stone excavation working condition, and the soil excavation working condition can include any one of the backfill soil excavation working condition and the original soil excavation working condition. The second working condition type can include the soil excavation working condition and the stone excavation working condition, and the soil excavation working condition can include any one of the backfill soil excavation working condition and the original soil excavation working condition.

[0081] The controller can determine the working condition type of the excavator in each excavation cycle according to the first working condition type and the second working condition type. That is, for each excavation cycle, the controller can determine one of the first working condition type and the second working condition type as the working condition type corresponding to each excavation cycle. The controller can determine the most frequent working condition type corresponding to each excavation cycle as the final working condition type. Taking 10 excavation cycles as an example, the controller can obtain 10 working condition types. If the 10 working condition types are A, A, A, A, A, B, B, B, C, and C, then the controller can determine the most frequent working condition type A as the final working condition type.

[0082] Through the above technical solution, it is possible to determine the current working condition type of the excavator in a timely and accurate manner, avoid failures of the excavator due to different working conditions during operation, improve the safety of the excavator operation, and further extend the service life of the excavator. At the same time, the method of integrating multiple models and multiple cycles can greatly improve the accuracy and stability of identifying the working condition type of the excavator. Moreover, the above technical solution can better capture the working condition signals of the excavator with the excavation cycle, quickly obtain the working conditions of the current working condition of the excavator, and provide a large number of high-quality training samples for subsequent model training.

[0083] Figure 1-2 This is a flowchart showing the method for determining the working condition type of an excavator in an embodiment of the present application. It should be understood that although Figure 1-2 the steps in the flowchart are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, Figure 1-2 at least a part of the steps in

[0084] In one embodiment, as Figure 3 shown, a device for determining the working condition type of an excavator is provided. The device includes a data acquisition device 301 and the above-mentioned controller 302. Among them, the data acquisition device 301 is used to acquire the working condition data generated by the excavator during operation.

[0085] An embodiment of the present application provides a storage medium, on which a program is stored. When the program is executed by the controller, the method for determining the working condition type of the excavator as described above is implemented.

[0086] An embodiment of the present application provides a controller, which is used to run a program. When the program runs, the method for determining the working condition type of the excavator as described above is executed.

[0087] In one embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure), and a database (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data such as working condition data and working condition parameters. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for determining the working condition type of an excavator is implemented.

[0088] Those skilled in the art can understand that Figure 4 the structure shown in Figure 4 is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0089] An embodiment of this application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining data characteristics during the excavation operation of the excavator in a preset operation time period, where the data characteristics include the working condition data characteristics corresponding to multiple working condition parameters of each excavation cycle within the preset operation time period; respectively inputting the working condition data characteristics of each excavation cycle into a first working condition recognition model and a second working condition recognition model; obtaining the first working condition type corresponding to each excavation cycle output by the first working condition recognition model and the second working condition type corresponding to each excavation cycle output by the second working condition recognition model; counting all the first working condition types and second working condition types of multiple cycles; and determining the actual working condition type of the excavator during the excavation operation in the preset operation time period as the working condition type with the largest quantity.

[0090] In one embodiment, the method further includes a training step for the first working condition recognition model. The training step of the first working condition recognition model includes: obtaining historical working condition data corresponding to the excavator under multiple working condition types, where the excavator includes at least a first pressure pump and a second pressure pump, and the historical working condition data includes the first historical working condition data of the first pressure pump and / or the second historical working condition data of the second pressure pump; determining the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data; determining the first working condition data characteristics corresponding to multiple historical working condition parameters included in each excavation cycle; and sequentially inputting the first working condition data characteristics corresponding to each excavation cycle into the first working condition recognition model to train the first working condition recognition model.

[0091] In one embodiment, the historical working condition data includes historical working condition parameters corresponding to each time point. Determining the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data includes: filtering the historical working condition data; traversing the historical working condition parameters included in the filtered historical working condition data according to a sliding window with a preset duration, so as to determine the time point corresponding to the minimum value of the historical working condition parameters within the sliding window as the excavation break point of the excavator; and dividing the filtered historical working condition data according to multiple excavation break points to determine the excavation cycle of the excavator.

[0092] In one embodiment, the first historical working condition data includes first historical working condition parameters corresponding to each time point, and the second historical working condition data includes second historical working condition parameters corresponding to each time point. The method further includes a training step for the second working condition recognition model. The training step of the second working condition recognition model includes: for the same time point, determining the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to the time point; sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator; screening out the parameter differences greater than or equal to a preset parameter threshold, and determining the second working condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold; inputting the second working condition data features into the second working condition recognition model to train the second working condition recognition model.

[0093] In one embodiment, sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator includes: sorting the parameter differences in the order of the time points; filtering the parameter signals corresponding to each parameter difference; traversing the parameter differences included in the filtered parameter signals according to a sliding window with a preset duration to determine the excavation break point of the excavator as the time point corresponding to the minimum value of the parameter differences within the sliding window; according to the sorting of the time points, determining the time period between two adjacent excavation break points as the excavation cycle of the excavator.

[0094] In one embodiment, before screening out the parameter differences greater than or equal to the preset parameter threshold and determining the second working condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold, it includes: determining the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to each time point, and determining the parameter mean of the parameter differences; determining a preset multiple of the parameter mean as the preset parameter threshold.

[0095] In one embodiment, the preset multiple is 0.1 or 0.05.

[0096] In one embodiment, the working condition types include the soil excavation working condition and the stone excavation working condition, where the soil excavation working condition includes any one of the backfill soil excavation working condition and the original soil excavation working condition.

[0097] In one embodiment, the working condition parameters include the pressure value of the excavator pressure signal and / or the current value of the current signal.

[0098] The present application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program initialized with the following method steps: obtaining data characteristics of an excavator during excavation operations in a preset operation time period, where the data characteristics include data characteristics of working conditions corresponding to multiple working condition parameters of each excavation cycle in the preset operation time period; respectively inputting the data characteristics of the working conditions of each excavation cycle into a first working condition recognition model and a second working condition recognition model; obtaining a first working condition type corresponding to each excavation cycle output by the first working condition recognition model and a second working condition type corresponding to each excavation cycle output by the second working condition recognition model; counting all the first working condition types and second working condition types of multiple cycles; and determining the actual working condition type of the excavator during excavation operations in the preset operation time period as the working condition type with the largest quantity.

[0099] In one embodiment, the method further includes a training step for the first working condition recognition model, and the training step of the first working condition recognition model includes: obtaining historical working condition data corresponding to the excavator under multiple working condition types, where the excavator at least includes a first pressure pump and a second pressure pump, and the historical working condition data includes first historical working condition data of the first pressure pump and / or second historical working condition data of the second pressure pump; determining the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data; determining first working condition data characteristics corresponding to multiple historical working condition parameters included in each excavation cycle; and sequentially inputting the first working condition data characteristics corresponding to each excavation cycle into the first working condition recognition model to train the first working condition recognition model.

[0100] In one embodiment, the historical working condition data includes historical working condition parameters corresponding to each time point, and determining the excavation cycle of the excavator according to the first historical working condition data and / or the second historical working condition data includes: filtering the historical working condition data; traversing the historical working condition parameters included in the filtered historical working condition data according to a sliding window with a preset duration to determine the time point corresponding to the minimum value of the historical working condition parameters within the sliding window as the excavation break point of the excavator; and dividing the filtered historical working condition data according to multiple excavation break points to determine the excavation cycle of the excavator.

[0101] In one embodiment, the first historical working condition data includes first historical working condition parameters corresponding to each time point, and the second historical working condition data includes second historical working condition parameters corresponding to each time point. The method further includes a training step for the second working condition recognition model. The training step of the second working condition recognition model includes: for the same time point, determining the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to the time point; sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator; screening out the parameter differences greater than or equal to the preset parameter threshold, and determining the second working condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold; inputting the second working condition data features into the second working condition recognition model to train the second working condition recognition model.

[0102] In one embodiment, sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator includes: sorting the parameter differences in the order of the time points; filtering the parameter signals corresponding to each parameter difference; traversing the parameter differences included in the filtered parameter signals according to a sliding window with a preset duration to determine the time point corresponding to the minimum value of the parameter differences within the sliding window as the excavation break point of the excavator; according to the sorting of the time points, determining the time period between two adjacent excavation break points as the excavation cycle of the excavator.

[0103] In one embodiment, before screening out the parameter differences greater than or equal to the preset parameter threshold and determining the second working condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold, it includes: determining the parameter difference between the first historical working condition parameter and the second historical working condition parameter corresponding to each time point, and determining the parameter mean of the parameter differences; determining a preset multiple of the parameter mean as the preset parameter threshold.

[0104] In one embodiment, the preset multiple is 0.1 or 0.05.

[0105] In one embodiment, the working condition types include the soil excavation working condition and the stone excavation working condition, where the soil excavation working condition includes any one of the backfill soil excavation working condition and the native soil excavation working condition.

[0106] In one embodiment, the working condition parameters include the pressure value of the excavator pressure signal and / or the current value of the current signal.

[0107] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0108] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0109] These computer program instructions can 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, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0111] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0112] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0113] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape 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 temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0114] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0115] The above are only 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 modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining the working condition type of an excavator, characterized in that, The method includes: Obtaining data characteristics of an excavator during excavation operations in a preset operation time period, where the data characteristics include operation data characteristics corresponding to multiple operation condition parameters in each excavation cycle within the preset operation time period. Among them, the operation data characteristics include parameter mean, parameter variance, parameter median, and parameter quantile; Inputting the operation data characteristics of each excavation cycle into a first operation condition recognition model and a second operation condition recognition model respectively; Obtaining a first operation condition type corresponding to each excavation cycle output by the first operation condition recognition model and a second operation condition type corresponding to each excavation cycle output by the second operation condition recognition model; Counting all the first operation condition types and second operation condition types of multiple cycles; Determining the actual operation condition type of the excavator during excavation operations in the preset operation time period as the operation condition type with the largest quantity; Among them, the method further includes a training step for the first operation condition recognition model, and the training step of the first operation condition recognition model includes: Obtaining historical operation condition data corresponding to multiple operation condition types of the excavator. Among them, the excavator includes at least a first pressure pump and a second pressure pump, and the historical operation condition data includes first historical operation condition data of the first pressure pump and / or second historical operation condition data of the second pressure pump; Determining the excavation cycle of the excavator according to the first historical operation condition data and / or the second historical operation condition data; Determining first operation data characteristics corresponding to multiple historical operation condition parameters included in each excavation cycle; Sequentially inputting the first operation data characteristics corresponding to each excavation cycle into the first operation condition recognition model to train the first operation condition recognition model.

2. The method for determining the working condition type of an excavator according to claim 1, characterized in that, The historical operation condition data includes historical operation condition parameters corresponding to each time point, and determining the excavation cycle of the excavator according to the first historical operation condition data and / or the second historical operation condition data includes: Filtering the historical operation condition data; Traversing the historical operation condition parameters included in the filtered historical operation condition data according to a sliding window with a preset duration, and determining the excavation break point of the excavator as the time point corresponding to the minimum value of the historical operation condition parameters within the sliding window; Dividing the filtered historical operation condition data according to multiple excavation break points to determine the excavation cycle of the excavator.

3. The method for determining the working condition type of an excavator according to claim 1, wherein The first historical operation condition data includes first historical operation condition parameters corresponding to each time point, the second historical operation condition data includes second historical operation condition parameters corresponding to each time point, and the method further includes a training step for the second operation condition recognition model. The training step of the second operation condition recognition model includes: Determining the parameter difference between the first historical operation condition parameters and the second historical operation condition parameters corresponding to the same time point; Sorting the parameter differences in the order of the time points to determine the excavation cycle of the excavator; Selecting parameter differences greater than or equal to a preset parameter threshold, and determining second operation data characteristics included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold; Input the second operating condition data features into the second operating condition recognition model to train the second operating condition recognition model.

4. The method for determining the working condition type of an excavator according to claim 3, characterized in that, The steps of sorting the parameter differences in chronological order to determine the excavation cycle of the excavator include: Sort the parameter differences in chronological order; Filter the parameter signals corresponding to each parameter difference; Traverse the parameter differences included in the filtered parameter signals according to a sliding window with a preset duration, and determine the time point corresponding to the minimum value of the parameter differences within the sliding window as the excavation break point of the excavator; According to the sorting of the time points, determine the time period between two adjacent excavation break points as the excavation cycle of the excavator.

5. The method for determining the working condition type of an excavator according to claim 3, characterized in that, Before screening out the parameter differences greater than or equal to the preset parameter threshold and determining the second operating condition data features included in each excavation cycle according to the parameter differences greater than or equal to the preset parameter threshold, it includes: Determine the parameter difference between the first historical operating condition parameter and the second historical operating condition parameter corresponding to each time point, and determine the parameter mean of the parameter difference; Determine the preset multiple of the parameter mean as the preset parameter threshold.

6. The method for determining the working condition type of an excavator according to claim 5, characterized in that, The preset multiple is 0.1 or 0.

05.

7. The method for determining the working condition type of an excavator according to any one of claims 1 to 6, characterized in that, The operating condition types include the excavation soil condition and the excavation stone condition, where the excavation soil condition includes any one of the excavation backfill soil condition and the excavation native soil condition.

8. The method for determining the working condition type of an excavator according to any one of claims 1 to 6, characterized in that, The operating condition parameters include the pressure value of the pressure signal and / or the current value of the current signal of the excavator.

9. A controller, characterized in that, Configured to execute the method for determining the operating condition type of an excavator according to any one of claims 1 to 8.

10. A device for determining the working condition type of an excavator, characterized in that, The device includes: A data acquisition device for collecting the operating condition data generated by the excavator during operation; and The controller according to claim 9.

11. An excavator, characterized in that, Including the device for determining the operating condition type of an excavator according to claim 10.

12. The excavator according to claim 11, characterized in that, The excavator includes at least a first pressure pump and a second pressure pump.

Images