CN115169412A - Method and device for determining operation mode, controller and engineering vehicle - Google Patents

Method and device for determining operation mode, controller and engineering vehicle Download PDF

Info

Publication number
CN115169412A
CN115169412A CN202210871593.3A CN202210871593A CN115169412A CN 115169412 A CN115169412 A CN 115169412A CN 202210871593 A CN202210871593 A CN 202210871593A CN 115169412 A CN115169412 A CN 115169412A
Authority
CN
China
Prior art keywords
signal
value
job
historical
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210871593.3A
Other languages
Chinese (zh)
Inventor
吴凡
叶舟
刘向阳
童兴
魏学平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhongke Yungu Technology Co Ltd
Original Assignee
Zhongke Yungu Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhongke Yungu Technology Co Ltd filed Critical Zhongke Yungu Technology Co Ltd
Priority to CN202210871593.3A priority Critical patent/CN115169412A/en
Publication of CN115169412A publication Critical patent/CN115169412A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02F—DREDGING; SOIL-SHIFTING
    • E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
    • E02F9/20—Drives; Control devices
    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02F—DREDGING; SOIL-SHIFTING
    • E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
    • E02F9/20—Drives; Control devices
    • E02F9/2058—Electric or electro-mechanical or mechanical control devices of vehicle sub-units
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Mining & Mineral Resources (AREA)
  • Structural Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Civil Engineering (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Feedback Control In General (AREA)

Abstract

The embodiment of the application provides a method and a device for determining an operation mode, a controller and an engineering vehicle. The method comprises the following steps: acquiring an operation signal of an engineering vehicle during operation in a preset time period, wherein the preset time period comprises a plurality of preset time windows; determining the peak value number of the envelope peak value corresponding to each preset time window and the characteristic value corresponding to each preset time window according to the operation signal; and inputting the peak value quantity and the characteristic value of all the preset time windows into the operation identification model so as to output the corresponding operation mode of the engineering vehicle during operation within the preset time period through the operation identification model. Through the technical scheme, the operation mode of the engineering vehicle is predicted from the local fluctuation frequency and the integral discrete degree of the operation signal, the accuracy and the reliability of determining the operation mode are greatly improved, the labor cost and the time cost which need to be consumed are lower, and the operation identification efficiency of the engineering vehicle is effectively improved.

Description

Method and device for determining operation mode, controller and engineering vehicle
Technical Field
The application relates to the field of engineering machinery, in particular to a method, a device, a controller and an engineering vehicle for determining an operation mode.
Background
In the current prior art, the working mode of the engineering vehicle is determined by acquiring the pressure difference of the main pump when the engineering vehicle actually works and comparing the pressure difference with a preset threshold value. However, when the work pattern of the excavator is predicted by using the threshold comparison, it is necessary to ensure a high difference between the pressure data of the work vehicle in each work pattern, and thus the accuracy of the prediction can be ensured.
Taking a working vehicle as an excavator as an example, the operation modes of the excavator may include an excavation operation, a leveling operation, and a crushing operation mode. In general, since an excavator has a high randomness when performing leveling work, the distribution range of the corresponding pressure data is wide. Meanwhile, when the excavator carries out excavation operation and crushing operation, the corresponding pressure data distribution is highly overlapped. Therefore, if the operation mode of the excavator is predicted by using the threshold comparison, the operation mode of the excavator cannot be accurately determined, and the operation quality and the operation efficiency of the excavator are greatly reduced.
Disclosure of Invention
The embodiment of the application aims to provide a method, a device, a controller and an engineering vehicle for determining a work mode.
In order to achieve the above object, a first aspect of the present application provides a method for determining a work mode, applied to a work vehicle, the method including:
acquiring an operation signal of an engineering vehicle during operation in a preset time period, wherein the preset time period comprises a plurality of preset time windows;
determining the peak value number of the envelope peak value corresponding to each preset time window and the characteristic value corresponding to each preset time window according to the operation signal;
and inputting the peak value quantity and the characteristic value of all the preset time windows into the operation identification model so as to output the corresponding operation mode of the engineering vehicle during operation within the preset time period through the operation identification model.
In an embodiment of the present application, a work vehicle includes a first main pump and a second main pump, and a work signal includes a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump; determining the number of peak values of the envelope peak value corresponding to each preset time window from the job signal comprises: filtering the first and second operation signals, respectively; respectively carrying out differential processing on the filtered first operation signal and the filtered second operation signal to respectively determine a first envelope peak value corresponding to the filtered first operation signal and a second envelope peak value corresponding to the filtered second operation signal; and determining the peak number of the first envelope peak and the peak number of the second envelope peak in each preset time window.
In an embodiment of the present application, the preset time period includes a plurality of time points, the job signal includes a job parameter value corresponding to each time point, and performing differential processing on the filtered first job signal and the filtered second job signal to determine a first envelope peak value corresponding to the filtered first job signal and a second envelope peak value corresponding to the filtered second job signal respectively includes: acquiring an operation parameter value corresponding to any time point in the filtered first operation signal or the filtered second operation signal; determining a first parameter difference value between the operation parameter value at the current time point and the operation parameter value at the previous time point, and a second parameter difference value between the operation parameter value at the current time point and the operation parameter value at the next time point; and under the condition that the first parameter difference value is larger than a preset threshold value and the second parameter difference value is smaller than the preset threshold value, determining the operation parameter value corresponding to the current time point as an envelope peak value corresponding to the operation signal.
In an embodiment of the application, the engineering vehicle comprises a first main pump and a second main pump, the operation signals comprise a first operation signal corresponding to the first main pump and a second operation signal corresponding to the second main pump, the preset time period comprises a plurality of preset time windows, each preset time window comprises a plurality of time points, the operation signals comprise operation parameter values corresponding to each time point, and the characteristic values comprise a variation coefficient and a variance; determining a characteristic value corresponding to each preset time window from the job signal includes: determining a parameter mean value of an operation parameter value corresponding to each time point in the operation signal aiming at the first operation signal or the second operation signal; determining the variance and standard deviation of the operation parameter value of each preset time window according to the parameter mean value and the operation parameter value corresponding to each time point; and determining the variation coefficient corresponding to each preset time window according to the parameter mean value and the standard deviation corresponding to each preset time window.
In an embodiment of the application, the method further comprises a training step of the job recognition model, the training step comprising: acquiring sample signals under a plurality of historical operation modes corresponding to the engineering vehicle in the historical operation process, and taking the sample signal under each historical operation as a training sample, wherein the engineering vehicle at least comprises a first main pump and a second main pump, the sample signals comprise a first sample signal corresponding to the first main pump and a second sample signal corresponding to the second main pump, and the label of the training sample is the corresponding historical operation mode; respectively determining the number of first history peak values and first history characteristic values corresponding to the history time window in each history work mode according to the first sample signal; respectively determining the number of second historical peak values and second historical characteristic values corresponding to the historical time windows in each historical operation mode according to the second sample signals; and inputting the number of the first historical peak values, the number of the second historical peak values, the first historical characteristic values and the second historical characteristic values of all the historical time windows into a job recognition model so as to train the job recognition model.
In an embodiment of the application, the method further comprises: outputting a plurality of prediction operation modes corresponding to sample signals through the operation recognition model aiming at each training of the operation recognition model; comparing each predicted job mode with an actual job mode to determine a plurality of predicted deviation values for the job identification model; determining that the operation recognition model is trained under the condition that the error between the prediction deviation values of the adjacent quantity is less than or equal to a preset value; and under the condition that the error between the prediction deviation values of the adjacent quantities is larger than a preset value, inputting the quantity of the first historical peak values, the quantity of the second historical peak values, the first historical characteristic value and the second historical characteristic value of all historical time windows into the operation recognition model again to train the operation recognition model until the training times of the operation recognition model reach the preset training times or the error between the prediction deviation values of the adjacent quantities is smaller than or equal to the preset value.
In an embodiment of the present application, the work vehicle is an excavator, and the work mode of the work vehicle includes any one of excavation work, leveling work, and crushing work.
A second aspect of the present application provides a controller configured to perform the above-described method for determining a job mode.
A third aspect of the present application provides an apparatus for determining a job mode, comprising: the data acquisition equipment is used for acquiring an operation signal generated by the engineering vehicle during operation; and the controller described above.
The present application fourth aspect provides an engineering vehicle, the engineering vehicle comprising: at least one main pump; and the above-mentioned means for determining the operation mode.
Through the technical scheme, the peak value quantity and the characteristic value of all the preset time windows are input into the operation identification model, the operation mode of the engineering vehicle is predicted from the local fluctuation frequency and the integral discrete degree of the operation signal, the accuracy and the reliability of determining the operation mode are greatly improved, the labor cost and the time cost which need to be consumed are low, and the operation identification efficiency of the engineering vehicle is effectively improved.
Additional features and advantages of embodiments of the present application will be described in detail in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the embodiments of the disclosure, but are not intended to limit the embodiments of the disclosure. In the drawings:
FIG. 1 schematically illustrates a flow diagram of a method for determining a job mode according to an embodiment of the present application;
FIG. 2 schematically illustrates a flow diagram of a method for determining a job mode according to yet another embodiment of the present application;
FIG. 3 schematically illustrates a flow diagram of model training according to an embodiment of the present application;
fig. 4 is a block diagram schematically showing the configuration of an apparatus for determining a job mode according to an embodiment of the present application;
fig. 5 schematically shows an internal structure diagram of a computer device according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the specific embodiments described herein are only used for illustrating and explaining the embodiments of the present application and are not used for limiting the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 schematically shows a flow diagram of a method for determining a job mode according to an embodiment of the present application. As shown in fig. 1, in an embodiment of the present application, there is provided a method for determining a work mode, applied to a work vehicle, the method including the steps of:
step 101, acquiring an operation signal of the engineering vehicle during operation in a preset time period, wherein the preset time period comprises a plurality of preset time windows.
And 102, determining the peak number of the envelope peak corresponding to each preset time window and the characteristic value corresponding to each preset time window according to the operation signal.
And 103, inputting the peak value quantity and the characteristic value of all the preset time windows into the operation identification model so as to output the operation mode corresponding to the operation of the engineering vehicle within the preset time period through the operation identification model.
The work vehicle may refer to a vehicle capable of performing mechanical work. The work mode of the working vehicle may include an excavating work, a leveling work, and a crushing work. The work vehicle may have at least one main pump. In order to be able to accurately determine the work mode of the work vehicle, the controller may acquire a work signal when the work vehicle performs work for a preset time period. The preset time period may include a plurality of preset time windows. The work signal may refer to a signal corresponding to a main pump of the work vehicle. The operation signal may be a pressure signal or a current signal.
In the case where the job signal is acquired, the controller may determine the number of peak values of the envelope peak value corresponding to each preset time window from the job signal. Further, the controller may first determine an envelope peak value corresponding to the job signal from the job signal. The controller may then further determine a peak number of envelope peaks corresponding to each preset time window. By determining the number of peaks corresponding to each preset time window, the degree of fluctuation of the job signal can be quantified from a local angle. In the case where the job signal is acquired, the controller may determine a feature value corresponding to each preset time window according to the job signal. Wherein the feature value may refer to a statistical feature value. Specifically, the feature values may include a variance and a coefficient of variation. The integral discrete degree of the operation signal can be effectively reflected by determining the characteristic value, and a reference basis can be provided for accurately determining the operation mode of the engineering vehicle.
Under the condition that the peak value quantity and the characteristic value of the envelope peak value corresponding to each preset time window are determined, the controller can input the peak value quantity and the characteristic value of all the preset time windows into the operation identification model, so that the operation mode corresponding to the engineering vehicle in operation within the preset time period can be output through the operation identification model. Wherein the job identification model may be a classification model. In particular, the classification model may be a random forest.
According to the technical scheme, the peak value quantity and the characteristic value of all the preset time windows are input into the operation identification model, the operation mode of the engineering vehicle is predicted from the local change trend and the overall change trend of the operation signal, the accuracy and the reliability of determining the operation mode are greatly improved, the labor cost and the time cost which need to be consumed are low, and the operation quality and the operation efficiency of the engineering vehicle are effectively improved.
In one embodiment, the working vehicle is an excavator, and the work mode of the working vehicle includes any one of excavation work, leveling work, and crushing work.
The work vehicle may refer to a vehicle capable of performing mechanical construction. The work vehicle may be referred to as an excavator. The work mode of the working vehicle may include any one of excavation work, leveling work, and crushing work.
In one embodiment, the engineering vehicle comprises a first main pump and a second main pump, and the work signals comprise a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump; determining the number of peak values of the envelope peak value corresponding to each preset time window from the job signal comprises: filtering the first and second job signals, respectively; respectively carrying out differential processing on the filtered first operation signal and the filtered second operation signal to respectively determine a first envelope peak value corresponding to the filtered first operation signal and a second envelope peak value corresponding to the filtered second operation signal; and determining the peak number of the first envelope peak and the peak number of the second envelope peak in each preset time window.
The engineering vehicle comprises a first main pump and a second main pump. The work signal when the work vehicle performs work for a preset time period may include a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump. The operation signal may be a pressure signal or a current signal. In the case where the operation signal is a pressure signal, the first operation signal corresponding to the first main pump may refer to a first pressure signal, and the second operation signal corresponding to the second main pump may refer to a second pressure signal.
The controller may filter the first and second job signals, respectively, upon acquisition of the first and second job signals. The filtering may be an S-G envelope filter. The shape and the width of the working signal can be ensured to be unchanged while the working signal is fitted and the waveform envelope is obtained through S-G envelope filtering. And after S-G envelope filtering, the signal noise of the operation signal can be reduced, and the variation trend of the operation signal is extracted, so that the envelope peak value can be determined quickly and accurately in the following process.
The controller may perform differential processing on the filtered first and second job signals to determine a first envelope peak corresponding to the filtered first job signal and a second envelope peak corresponding to the filtered second job signal, respectively. In the case where all envelope peak values corresponding to the operation signal are determined, the controller may further determine the number of peak values of the first envelope peak value and the number of peak values of the second envelope peak value within each preset time window. The preset time window can be determined according to actual conditions, or can be determined after comprehensively considering the recognition robustness and the sensitivity of the operation recognition model. For example, the preset time window may be a 30s time window. That is, the preset time period may be divided into a plurality of time windows of 30 s. The controller may determine the number of peaks of the first envelope peak and the number of peaks of the second envelope peak for each 30s time window. The number of peaks of the first envelope peak and the number of peaks of the second envelope peak may then be input to the job identification model when a job mode is subsequently determined.
In one embodiment, the predetermined time period includes a plurality of time points, the job signal includes a job parameter value corresponding to each time point, and the differential processing of the first and second filtered job signals to determine a first envelope peak corresponding to the first filtered job signal and a second envelope peak corresponding to the second filtered job signal respectively includes: acquiring an operation parameter value corresponding to any time point in the filtered first operation signal or the filtered second operation signal; determining a first parameter difference value between the operation parameter value at the current time point and the operation parameter value at the previous time point, and a second parameter difference value between the operation parameter value at the current time point and the operation parameter value at the next time point; and under the condition that the first parameter difference value is larger than a preset threshold value and the second parameter difference value is smaller than the preset threshold value, determining the operation parameter value corresponding to the current time point as an envelope peak value corresponding to the operation signal.
Wherein, a plurality of time points can be included in the preset time period. The job signal may include a job parameter value corresponding to each time point. The operation signal may be a pressure signal or a current signal. In case the operation signal is a pressure signal, then the operation parameter value of each time point corresponding thereto may refer to a pressure value. In the case where the operation signal is a current signal, the operation parameter value at each time point corresponding thereto may refer to a current value.
After filtering the first job signal and the second job signal respectively, the controller may obtain an operation parameter value corresponding to any one time point of the filtered first job signal or the filtered second job signal. For example, the controller may obtain an operation parameter value at a current time point, an operation parameter value at a previous time point, and an operation parameter value at a next time point in the filtered first or second operation signal. The controller may then determine a first parameter difference between the value of the job parameter at the current point in time and the value of the job parameter at the previous point in time, and a second parameter difference between the value of the job parameter at the current point in time and the value of the job parameter at the next point in time.
In case that the first parameter difference value and the second parameter difference value are determined, the controller may compare the first parameter difference value with a preset threshold value, and may compare the second parameter difference value with the preset threshold value. The preset threshold may be 0. If the first parameter difference is greater than the preset threshold and the second parameter difference is less than the preset threshold, it may be determined that the change trend of the pressure signal from the previous time point to the next time point is up-down, and at this time, the controller may further determine the operation parameter value corresponding to the current time point as the envelope peak value corresponding to the operation signal. In the case where all the envelope peaks corresponding to the work signal within the preset time period are determined, the controller may determine the number of peaks of the envelope peaks within the preset time window, thereby determining the work mode of the work vehicle through the work recognition model.
For example, the controller may obtain that the pressure value at the time point t-1 in the filtered first pressure signal is y0, the pressure value at the time point t is y1, and the pressure value at the time point t +1 is y2, so that the first pressure difference value is y1-y0, and the second pressure difference value is y2-y1. In the case where y1-y0 > 0 and y2-y1 < 0, the controller may determine the pressure value at the time point t as y1 as the envelope peak corresponding to the first pressure signal. Under the conditions that y1-y0 is greater than 0, y2-y1 is greater than 0 (the variation trend of the first pressure signal is rising within t-1 to t + 1), y1-y0 is less than 0, y2-y1 is less than 0 (the variation trend of the first pressure signal is falling within t-1 to t + 1), and y1-y0 is less than 0, and y2-y1 is greater than 0 (the variation trend of the first pressure signal is falling-rising within t-1 to t + 1), the controller can further acquire the pressure value at the time point of t +2 as y3 to determine the envelope peak value corresponding to the first pressure signal.
In one embodiment, the engineering vehicle comprises a first main pump and a second main pump, the operation signals comprise a first operation signal corresponding to the first main pump and a second operation signal corresponding to the second main pump, the preset time period comprises a plurality of preset time windows, each preset time window comprises a plurality of time points, the operation signals comprise operation parameter values corresponding to each time point, and the characteristic values comprise coefficient of variation and variance; determining a feature value corresponding to each preset time window according to the job signal includes: determining a parameter mean value of an operation parameter value corresponding to each time point in the operation signal aiming at the first operation signal or the second operation signal; determining the variance and standard deviation of the operation parameter value of each preset time window according to the parameter mean value and the operation parameter value corresponding to each time point; and determining the variation coefficient corresponding to each preset time window according to the parameter mean value and the standard deviation corresponding to each preset time window.
The engineering vehicle comprises a first main pump and a second main pump. The work signal when the work vehicle performs work for a preset time period may include a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump. The operation signal may be a pressure signal or a current signal. In the case where the operation signal is a pressure signal, the first operation signal corresponding to the first main pump may refer to a first pressure signal, and the second operation signal corresponding to the second main pump may refer to a second pressure signal. In a case where the operation signal is a current signal, the first operation signal corresponding to the first main pump may refer to a first current signal, and the second operation signal corresponding to the second main pump may refer to a second current signal. The preset time period may include a plurality of preset time windows. Each preset time window may include a plurality of time points. The job signal may include a job parameter value corresponding to each time point. If the operation signal is a pressure signal, the operation parameter value corresponding to each time point refers to a pressure value. If the operation signal is a current signal, the operation parameter value corresponding to each time point is referred to as a current value.
For the first operation signal or the second operation signal, the controller may determine an operation parameter value corresponding to each time point in the operation signal, and average the operation parameter values corresponding to all the time points to determine a parameter average value. In the case of determining the parameter mean, the controller may further determine a variance and a standard deviation of the operation parameter value of each preset time window according to the parameter mean and the operation parameter value corresponding to each time point. Then, the controller may determine the coefficient of variation corresponding to each preset time window according to the parameter mean and the standard deviation corresponding to each preset time window. The overall variation degree of the operation signal can be effectively reflected through the variation coefficient and the variance.
In one embodiment, as shown in FIG. 2, a flow diagram of another method for determining a job mode is provided.
The controller may acquire a pressure signal P1 of the main pump 1 and a pressure signal P2 of the main pump 2 when the work vehicle is performing work in a time zone. The pressure signal P1 and the pressure signal P2 may then be envelope filtered, respectively. The controller may differentially process the filtered pressure signal P1 and the pressure signal P2, respectively, to determine a local peak corresponding to the filtered pressure signal P1 and a local peak corresponding to the filtered pressure signal P2. In the case of determining the local peak, the controller may divide the time period into a plurality of time windows and determine an envelope peak amount of the local peak within each time window. In the case of acquiring the pressure signal P1 of the main pump 1 and the pressure signal P2 of the main pump 2 when the work vehicle performs work in a time zone, the controller may divide the time zone into a plurality of time windows, and determine a coefficient of variation and a variance corresponding to each time window.
In the case of determining the variation coefficient, the variance, and the envelope peak amount corresponding to the pressure signal P1, and the variation coefficient, the variance, and the envelope peak amount corresponding to the pressure signal P2, the controller may train the job identification model through the above parameters. Under the condition that the training of the operation recognition model is completed, the controller can acquire a real-time operation signal of the engineering vehicle during operation within a preset time period, and determine a corresponding variation coefficient, variance and envelope peak value according to the real-time operation signal, so that an operation mode of the engineering vehicle during operation within the preset time period is output through the trained operation recognition model. The work mode may include, among others, an excavation work, a leveling work, and a crushing work.
In one embodiment, the method further comprises a training step of the job recognition model, the training step comprising: the method comprises the steps of obtaining sample signals under a plurality of historical operation modes corresponding to an engineering vehicle in the process of historical operation, and taking the sample signals under each historical operation mode as training samples, wherein the engineering vehicle at least comprises a first main pump and a second main pump, the sample signals comprise a first sample signal corresponding to the first main pump and a second sample signal corresponding to the second main pump, and labels of the training samples are the corresponding historical operation modes; respectively determining the number of first history peak values and first history characteristic values corresponding to the history time window in each history work mode according to the first sample signal; respectively determining the number of second historical peak values and second historical characteristic values corresponding to the historical time windows in each historical operation mode according to the second sample signals; and inputting the number of the first historical peak values, the number of the second historical peak values, the first historical characteristic values and the second historical characteristic values of all historical time windows into a job recognition model so as to train the job recognition model.
The controller can obtain sample signals under a plurality of historical modes corresponding to the engineering vehicle in the historical operation process, and the sample signals under each historical operation mode are used as training samples. The engineering vehicle at least comprises a first main pump and a second main pump. The sample signals may include a first sample signal corresponding to the first main pump and a second sample signal corresponding to the second main pump. The training samples may refer to historical pressure signals or historical current signals for each historical job mode. The training samples carry labels. The labels of the training samples may be the corresponding historical job patterns. For example, for training sample 1, the corresponding historical job pattern is a leveling job. For training sample 2, the corresponding historical job pattern is a mining job. In the case where the training samples are historical pressure signals in each historical working mode, the historical pressure signals may include a first historical pressure signal corresponding to the first main pump and a second historical pressure signal corresponding to the second main pump. In the case where the training samples are historical current signals in each historical operating mode, the historical pressure signals may include a first historical current signal corresponding to the first main pump and a second historical current signal corresponding to the second main pump. The historical work pattern may include digging work, leveling work, and crushing work.
The controller may determine a number of first history peaks corresponding to the history time window in each history job mode according to the first sample signal. In particular, the controller may filter the first sample signal. The controller may then perform a differential processing on the filtered first sample signal to determine a first historical peak corresponding to the filtered first sample signal. In the case where the first historical peak is determined, the controller may determine a number of first historical peaks corresponding to the historical time window.
The controller may determine a first history feature value corresponding to the history time window in each history job mode according to the first sample signal. Wherein the first sample signal may comprise a first sample value corresponding to each historical time point. The historical time window includes a plurality of historical time points. The first historical eigenvalue may refer to the coefficient of variation and variance corresponding to the historical time window determined from the first sample signal. In particular, the controller may determine a mean of the first sample values corresponding to each historical time point in the first sample signal. In the case of determining the mean of the first sample values, the controller may determine the variance and standard deviation of the first sample values of the historical time window according to the mean of the first sample values and the first sample values corresponding to each historical time point. Then, the controller may further determine a variation coefficient corresponding to the historical time window according to a mean and a standard deviation of the first sample value corresponding to the historical time window.
The controller may determine a peak number of the second history peaks corresponding to the history time window in each history job mode according to the second sample signal. In particular, the controller may filter the second sample signal. The controller may then differentially process the filtered second sample signal to determine a second historical peak corresponding to the filtered second sample signal. In the case where the second historical peak is determined, the controller may determine a number of second historical peaks corresponding to the historical time window.
The controller may determine a second history feature value corresponding to the history time window in each history job mode according to the second sample signal. Wherein the second sample signal may comprise second sample values corresponding to each historical time point. The second historical eigenvalue may refer to the coefficient of variation and variance corresponding to the historical time window determined from the second sample signal. In particular, the controller may determine a mean value of the second sample values corresponding to each historical time point in the second sample signal. In the case of determining the mean value of the second sample values, the controller may determine the variance and standard deviation of the second sample values of the historical time window according to the mean value of the second sample values and the second sample value corresponding to each historical time point. Then, the controller may further determine a variation coefficient corresponding to the historical time window according to a mean value and a standard deviation of the second sample values corresponding to the historical time window.
The controller may input the number of first history peaks, the number of second history peaks, the first history feature value, and the second history feature value of all the history time windows to the job recognition model to train the job recognition model. Wherein the job recognition model may refer to a classification model. The classification model may be a random forest.
In one embodiment, the method further comprises: outputting a plurality of prediction operation modes corresponding to sample signals through the operation recognition model aiming at each training of the operation recognition model; comparing each predicted job mode with an actual job mode to determine a plurality of predicted deviation values for the job identification model; determining that the training of the operation recognition model is finished under the condition that the error between the prediction deviation values of the adjacent quantity is less than or equal to a preset value; and inputting the number of the first historical peak values, the number of the second historical peak values, the first historical characteristic values and the second historical characteristic values of all historical time windows into the operation recognition model again under the condition that the error between the prediction deviation values of the adjacent numbers is larger than a preset value, so as to train the operation recognition model until the training times of the operation recognition model reach the preset training times or the error between the prediction deviation values of the adjacent numbers is smaller than or equal to the preset value.
Wherein the job recognition model may refer to a classification model. The classification model may be a random forest. The sample signal may be a historical pressure signal or a historical current signal. The job identification model can be trained for multiple times through the number of the first historical peaks, the number of the second historical peaks, the first historical characteristic value and the second historical characteristic value of all historical time windows. The controller may output a plurality of predicted job patterns corresponding to the sample signal through the job recognition model for each training of the job recognition model. In the case where the actual operation mode corresponding to the sample signal is acquired, the controller may compare the predicted operation mode with the actual operation to determine a plurality of prediction deviation values of the operation recognition model, so that the training effect of the model may be evaluated according to the plurality of prediction deviation values.
The controller may determine that the job recognition mode training is completed in a case where an error between the prediction deviation values of the adjacent numbers is less than or equal to a preset value. That is, after a plurality of consecutive trainings, the error of the prediction deviation value corresponding to each training does not exceed the preset value, and at this time, the prediction accuracy of the job recognition model may have reached the maximum value, and the processor may determine that the training of the job recognition model is completed. When the error between the prediction deviation values of the adjacent numbers is greater than the preset value, the processor may input the number of the first history peak values, the number of the second history peak values, the first history feature value, and the second history feature value of all the history time windows to the job recognition model again to train the job recognition model. That is, after a plurality of consecutive trainings, the error of the prediction deviation value corresponding to each training exceeds the preset value, and at this time, the prediction accuracy of the job recognition model may not reach the maximum value yet, the processor may train the job recognition model again until the training frequency of the job recognition model reaches the preset training frequency or the error between the prediction deviation values of adjacent numbers is less than or equal to the preset value, so as to improve the training accuracy of the job recognition model. The preset training times can be customized according to actual conditions.
In one embodiment, the loss value in the model is identified to represent the difference between the label value of the training sample and the output value of the model, and when the loss value is not reduced any more or the iteration number is greater than a preset value, the model training is completed. And carrying out parameter optimization by using grid search, sequentially adjusting parameters according to step length, and finding out the parameter with the highest precision on the verification set from all the parameters through circular traversal, wherein the model corresponding to the group of parameters is the final operation identification model.
In one embodiment, as shown in FIG. 3, a flow diagram for training a job recognition model is provided. The controller may input the feature X to the mining action recognition model to output the prediction Z through the mining action recognition model. Wherein the feature X may include a number of first historical peaks, a number of second historical peaks, a first historical feature value, and a second historical feature value. The mining action recognition model may refer to a job recognition model. The prediction Z may refer to a predicted work mode of the work vehicle. The label Y may refer to the actual job mode corresponding to the feature X. Under the condition that the prediction Z is output through the mining action recognition model, the controller can compare the label Y with the prediction Z to determine the prediction deviation value of the operation mining action recognition model until the prediction deviation value is not obviously reduced in continuous multiple times of training or the model training reaches the preset iteration times.
In one embodiment, the method further comprises: acquiring an operation signal of the engineering vehicle in an actual operation process as a prediction signal, wherein the prediction signal comprises a first operation signal corresponding to the first main pump and a second operation signal corresponding to the second main pump; respectively determining the number of first operation peak values and a first operation characteristic value according to the first operation signal; respectively determining the number of second operation peak values and second operation characteristic values according to the second operation signals; and inputting the number of the first operation peak values, the number of the second operation peak values, the first operation characteristic value and the second operation characteristic value into the operation identification model so as to predict the operation mode of the engineering vehicle in the actual operation process.
The controller may acquire a work signal of the engineering vehicle during an actual work process as the prediction signal. The prediction signal may be a voltage signal or a current signal. The prediction signal may include a first work signal corresponding to a first main pump of the work vehicle and a second work signal corresponding to a second main pump. The controller may determine the number of first job peaks and the first job eigenvalue from the first job signal, respectively. The controller may determine the number of second job peaks and the second job eigenvalue from the second job signal, respectively. The job characteristic value may include a coefficient of variation and a variance, among others. The operation peak may refer to an envelope peak. The controller may input the number of the first work peaks, the number of the second work peaks, the first work characteristic value, and the second work characteristic value to the work recognition model to predict the work pattern of the work vehicle during the actual work through the work recognition model. The work mode of the working vehicle may include an excavating work, a leveling work, and a crushing work. According to the technical scheme, the peak value quantity and the characteristic value of all the preset time windows are input into the operation identification model, the operation mode of the engineering vehicle is predicted from the local change trend and the overall change trend of the operation signal, the accuracy and the reliability of determining the operation mode are greatly improved, the labor cost and the time cost which need to be consumed are low, and the operation quality and the operation efficiency of the engineering vehicle are effectively improved.
1-2 are flow diagrams of a method for determining a job mode in one embodiment. It should be understood that although the various steps in the flow charts of fig. 1-2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, the controller is configured to run a program, wherein the program when running performs the above-described method for determining a job mode.
In one embodiment, as shown in fig. 4, an apparatus for determining a work mode is provided, comprising a data acquisition device 401 and the controller 402 described above. The data acquisition device 401 may be used to acquire an operation signal generated by the engineering vehicle during operation.
In one embodiment, a work vehicle is provided comprising at least one main pump and the above-described apparatus for determining a work mode.
In one embodiment, a storage medium is provided, having a program stored thereon, which when executed by a controller implements the above-described method for determining a job mode.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer apparatus 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. Wherein the processor a01 of the computer device is arranged to provide computing and control capabilities. The memory of the computer apparatus includes an internal memory a03 and a nonvolatile storage medium a04. The nonvolatile storage medium a04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory a03 provides an environment for running the operating system B01 and the computer program B02 in the nonvolatile storage medium a04. The database of the computer device is used for storing data such as job signals. The network interface a02 of the computer apparatus is used for communicating with an external terminal through a network connection. The computer program B02 is executed by the processor a01 to implement a method for determining a job mode.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
The embodiment of the application provides equipment, the equipment comprises a processor, a memory and a program which is stored on the memory and can run on the processor, and the following steps are realized when the processor executes the program: acquiring an operation signal of an engineering vehicle during operation in a preset time period, wherein the preset time period comprises a plurality of preset time windows; determining the peak value number of the envelope peak value corresponding to each preset time window and the characteristic value corresponding to each preset time window according to the operation signal; and inputting the peak value quantity and the characteristic value of all the preset time windows into the operation identification model so as to output the corresponding operation mode of the engineering vehicle during operation within the preset time period through the operation identification model.
In one embodiment, the work vehicle comprises a first main pump and a second main pump, and the work signals comprise a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump; determining the number of peak values of the envelope peak value corresponding to each preset time window from the job signal comprises: filtering the first and second operation signals, respectively; respectively carrying out differential processing on the filtered first operation signal and the filtered second operation signal to respectively determine a first envelope peak value corresponding to the filtered first operation signal and a second envelope peak value corresponding to the filtered second operation signal; and determining the peak number of the first envelope peak and the peak number of the second envelope peak in each preset time window.
In one embodiment, the preset time period includes a plurality of time points, the job signal includes a job parameter value corresponding to each time point, and the differential processing of the first and second filtered job signals to determine a first envelope peak value corresponding to the first filtered job signal and a second envelope peak value corresponding to the second filtered job signal includes: acquiring an operation parameter value corresponding to any time point in the filtered first operation signal or the filtered second operation signal; determining a first parameter difference value between the operation parameter value at the current time point and the operation parameter value at the previous time point, and a second parameter difference value between the operation parameter value at the current time point and the operation parameter value at the next time point; and under the condition that the first parameter difference value is larger than a preset threshold value and the second parameter difference value is smaller than the preset threshold value, determining the operation parameter value corresponding to the current time point as an envelope peak value corresponding to the operation signal.
In one embodiment, the engineering vehicle comprises a first main pump and a second main pump, the operation signals comprise a first operation signal corresponding to the first main pump and a second operation signal corresponding to the second main pump, the preset time period comprises a plurality of preset time windows, each preset time window comprises a plurality of time points, the operation signals comprise operation parameter values corresponding to each time point, and the characteristic values comprise a coefficient of variation and a variance; determining a characteristic value corresponding to each preset time window from the job signal includes: determining a parameter mean value of an operation parameter value corresponding to each time point in the operation signal aiming at the first operation signal or the second operation signal; determining the variance and standard deviation of the operation parameter value of each preset time window according to the parameter mean value and the operation parameter value corresponding to each time point; and determining the variation coefficient corresponding to each preset time window according to the parameter mean value and the standard deviation corresponding to each preset time window.
In one embodiment, the method further comprises a training step of the job recognition model, the training step comprising: the method comprises the steps of obtaining sample signals under a plurality of historical operation modes corresponding to an engineering vehicle in the process of historical operation, and taking the sample signals under each historical operation mode as training samples, wherein the engineering vehicle at least comprises a first main pump and a second main pump, the sample signals comprise a first sample signal corresponding to the first main pump and a second sample signal corresponding to the second main pump, and labels of the training samples are corresponding historical operation modes; respectively determining the number of first history peak values and first history characteristic values corresponding to the history time window in each history work mode according to the first sample signal; respectively determining the number of second historical peak values and second historical characteristic values corresponding to the historical time windows in each historical operation mode according to the second sample signals; and inputting the number of the first historical peak values, the number of the second historical peak values, the first historical characteristic values and the second historical characteristic values of all the historical time windows into a job recognition model so as to train the job recognition model.
In one embodiment, the method further comprises: outputting a plurality of prediction operation modes corresponding to sample signals through the operation recognition model aiming at each training of the operation recognition model; comparing each predicted job mode with an actual job mode to determine a plurality of predicted deviation values for the job identification model; determining that the training of the operation recognition model is finished under the condition that the error between the prediction deviation values of the adjacent quantity is less than or equal to a preset value; and inputting the number of the first historical peak values, the number of the second historical peak values, the first historical characteristic values and the second historical characteristic values of all historical time windows into the operation recognition model again under the condition that the error between the prediction deviation values of the adjacent numbers is larger than a preset value, so as to train the operation recognition model until the training times of the operation recognition model reach the preset training times or the error between the prediction deviation values of the adjacent numbers is smaller than or equal to the preset value.
In one embodiment, the work vehicle is an excavator, and the work mode of the work vehicle includes any one of excavation work, leveling work, and crushing work.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: acquiring an operation signal of an engineering vehicle during operation in a preset time period, wherein the preset time period comprises a plurality of preset time windows; determining the peak value number of the envelope peak value corresponding to each preset time window and the characteristic value corresponding to each preset time window according to the operation signal; and inputting the peak value quantity and the characteristic value of all the preset time windows into the operation identification model so as to output the corresponding operation mode of the engineering vehicle during operation within the preset time period through the operation identification model.
In one embodiment, the engineering vehicle comprises a first main pump and a second main pump, and the work signals comprise a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump; determining the number of peak values of the envelope peak value corresponding to each preset time window from the job signal comprises: filtering the first and second operation signals, respectively; respectively carrying out differential processing on the filtered first operation signal and the filtered second operation signal to respectively determine a first envelope peak value corresponding to the filtered first operation signal and a second envelope peak value corresponding to the filtered second operation signal; and determining the peak number of the first envelope peak and the peak number of the second envelope peak in each preset time window.
In one embodiment, the predetermined time period includes a plurality of time points, the job signal includes a job parameter value corresponding to each time point, and the differential processing of the first and second filtered job signals to determine a first envelope peak corresponding to the first filtered job signal and a second envelope peak corresponding to the second filtered job signal respectively includes: acquiring an operation parameter value corresponding to any time point in the filtered first operation signal or the filtered second operation signal; determining a first parameter difference value between the operation parameter value at the current time point and the operation parameter value at the previous time point, and a second parameter difference value between the operation parameter value at the current time point and the operation parameter value at the next time point; and under the condition that the first parameter difference value is larger than a preset threshold value and the second parameter difference value is smaller than the preset threshold value, determining the operation parameter value corresponding to the current time point as an envelope peak value corresponding to the operation signal.
In one embodiment, the engineering vehicle comprises a first main pump and a second main pump, the operation signals comprise a first operation signal corresponding to the first main pump and a second operation signal corresponding to the second main pump, the preset time period comprises a plurality of preset time windows, each preset time window comprises a plurality of time points, the operation signals comprise operation parameter values corresponding to each time point, and the characteristic values comprise a coefficient of variation and a variance; determining a characteristic value corresponding to each preset time window from the job signal includes: determining a parameter mean value of an operation parameter value corresponding to each time point in the operation signal aiming at the first operation signal or the second operation signal; determining the variance and standard deviation of the operation parameter value of each preset time window according to the parameter mean value and the operation parameter value corresponding to each time point; and determining the variation coefficient corresponding to each preset time window according to the parameter mean value and the standard deviation corresponding to each preset time window.
In one embodiment, the method further comprises a training step of the job recognition model, the training step comprising: the method comprises the steps of obtaining sample signals under a plurality of historical operation modes corresponding to an engineering vehicle in the process of historical operation, and taking the sample signals under each historical operation mode as training samples, wherein the engineering vehicle at least comprises a first main pump and a second main pump, the sample signals comprise a first sample signal corresponding to the first main pump and a second sample signal corresponding to the second main pump, and labels of the training samples are corresponding historical operation modes; respectively determining the number of first history peak values and first history characteristic values corresponding to the history time window in each history work mode according to the first sample signal; respectively determining the number of second historical peak values and second historical characteristic values corresponding to the historical time windows in each historical operation mode according to the second sample signals; and inputting the number of the first historical peak values, the number of the second historical peak values, the first historical characteristic values and the second historical characteristic values of all historical time windows into a job recognition model so as to train the job recognition model.
In one embodiment, the method further comprises: outputting a plurality of prediction operation modes corresponding to sample signals through the operation recognition model aiming at each training of the operation recognition model; comparing each predicted job mode with an actual job mode to determine a plurality of predicted deviation values for the job identification model; determining that the training of the operation recognition model is finished under the condition that the error between the prediction deviation values of the adjacent quantity is less than or equal to a preset value; and under the condition that the error between the prediction deviation values of the adjacent quantities is larger than a preset value, inputting the quantity of the first historical peak values, the quantity of the second historical peak values, the first historical characteristic value and the second historical characteristic value of all historical time windows into the operation recognition model again to train the operation recognition model until the training times of the operation recognition model reach the preset training times or the error between the prediction deviation values of the adjacent quantities is smaller than or equal to the preset value.
In one embodiment, the working vehicle is an excavator, and the work mode of the working vehicle includes any one of excavation work, leveling work, and crushing work.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, 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.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (10)

1. A method for determining a work mode, applied to a work vehicle, the method comprising:
acquiring an operation signal of the engineering vehicle during operation in a preset time period, wherein the preset time period comprises a plurality of preset time windows;
determining the peak value number of the envelope peak value corresponding to each preset time window and the characteristic value corresponding to each preset time window according to the operation signal;
and inputting the peak value number and the characteristic value of all the preset time windows into an operation identification model so as to output an operation mode corresponding to the engineering vehicle in operation within the preset time period through the operation identification model.
2. The method for determining a work mode of claim 1, wherein the work vehicle comprises a first main pump and a second main pump, the work signals comprising a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump;
determining the number of peak values of the envelope peak corresponding to each preset time window according to the job signal comprises:
filtering the first and second operation signals, respectively;
respectively carrying out differential processing on the filtered first operation signal and the filtered second operation signal to respectively determine a first envelope peak value corresponding to the filtered first operation signal and a second envelope peak value corresponding to the filtered second operation signal;
and determining the peak number of the first envelope peak and the peak number of the second envelope peak in each preset time window.
3. The method of claim 2, wherein the predetermined time period comprises a plurality of time points, wherein the job signal comprises a job parameter value corresponding to each time point, and wherein the differencing the first and second filtered job signals to determine a first envelope peak corresponding to the first filtered job signal and a second envelope peak corresponding to the second filtered job signal comprises:
acquiring an operation parameter value corresponding to any time point in the filtered first operation signal or the filtered second operation signal;
determining a first parameter difference value between an operation parameter value at a current time point and an operation parameter value at a previous time point, and a second parameter difference value between the operation parameter value at the current time point and an operation parameter value at a next time point;
and under the condition that the first parameter difference value is larger than a preset threshold value and the second parameter difference value is smaller than the preset threshold value, determining the operation parameter value corresponding to the current time point as an envelope peak value corresponding to an operation signal.
4. The method for determining the work mode of claim 1, wherein the work vehicle comprises a first main pump and a second main pump, the work signals comprise a first work signal corresponding to the first main pump and a second work signal corresponding to the second main pump, the preset time period comprises a plurality of preset time windows, each preset time window comprises a plurality of time points, the work signals comprise work parameter values corresponding to each time point, and the characteristic values comprise a coefficient of variation and a variance;
determining a feature value corresponding to each preset time window according to the job signal comprises:
determining a parameter average value of an operation parameter value corresponding to each time point in the operation signal aiming at the first operation signal or the second operation signal;
determining the variance and standard deviation of the operation parameter value of each preset time window according to the parameter mean value and the operation parameter value corresponding to each time point;
and determining the variation coefficient corresponding to each preset time window according to the parameter mean value and the standard deviation corresponding to each preset time window.
5. The method for determining job patterns according to claim 1, further comprising a training step of the job recognition model, the training step comprising:
acquiring sample signals under a plurality of historical operation modes corresponding to an engineering vehicle in a historical operation process, and taking the sample signals under each historical operation mode as training samples, wherein the engineering vehicle at least comprises a first main pump and a second main pump, the sample signals comprise a first sample signal corresponding to the first main pump and a second sample signal corresponding to the second main pump, and the labels of the training samples are corresponding historical operation modes;
respectively determining the number of first history peak values and first history characteristic values corresponding to a history time window in each history job mode according to the first sample signal;
respectively determining the number of second historical peak values and second historical characteristic values corresponding to the historical time windows in each historical operation mode according to the second sample signals;
inputting the number of first historical peaks, the number of second historical peaks, a first historical characteristic value and a second historical characteristic value of all historical time windows into the job recognition model so as to train the job recognition model.
6. The method for determining a job mode according to claim 5, further comprising:
outputting a plurality of prediction operation modes corresponding to sample signals through the operation recognition model aiming at each training of the operation recognition model;
comparing each predicted job mode with an actual job mode to determine a plurality of predicted deviation values for the job identification model;
determining that the training of the operation recognition model is finished under the condition that the error between the prediction deviation values of the adjacent quantity is less than or equal to a preset value;
and under the condition that the error between the prediction deviation values of the adjacent quantities is larger than a preset value, inputting the quantity of the first historical peak values, the quantity of the second historical peak values, the first historical characteristic value and the second historical characteristic value of all historical time windows into the operation recognition model again to train the operation recognition model until the training times of the operation recognition model reach the preset training times or the error between the prediction deviation values of the adjacent quantities is smaller than or equal to the preset value.
7. The method for determining a work mode according to any one of claims 1 to 6, wherein the work vehicle is an excavator, and the work mode of the work vehicle includes any one of an excavating work, a leveling work, and a crushing work.
8. A controller configured to perform a method for determining a job mode according to any one of claims 1 to 7.
9. An apparatus for determining a mode of operation, the apparatus comprising:
the data acquisition equipment is used for acquiring an operation signal generated by the engineering vehicle during operation; and
the controller of claim 8.
10. A work vehicle, characterized in that the work vehicle comprises:
at least one main pump; and
the apparatus for determining a job mode according to claim 9.
CN202210871593.3A 2022-07-22 2022-07-22 Method and device for determining operation mode, controller and engineering vehicle Pending CN115169412A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210871593.3A CN115169412A (en) 2022-07-22 2022-07-22 Method and device for determining operation mode, controller and engineering vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210871593.3A CN115169412A (en) 2022-07-22 2022-07-22 Method and device for determining operation mode, controller and engineering vehicle

Publications (1)

Publication Number Publication Date
CN115169412A true CN115169412A (en) 2022-10-11

Family

ID=83497882

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210871593.3A Pending CN115169412A (en) 2022-07-22 2022-07-22 Method and device for determining operation mode, controller and engineering vehicle

Country Status (1)

Country Link
CN (1) CN115169412A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116341281A (en) * 2023-05-12 2023-06-27 中国恩菲工程技术有限公司 Method and system for determining work rate, storage medium and terminal

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116341281A (en) * 2023-05-12 2023-06-27 中国恩菲工程技术有限公司 Method and system for determining work rate, storage medium and terminal
CN116341281B (en) * 2023-05-12 2023-08-15 中国恩菲工程技术有限公司 Method and system for determining work rate, storage medium and terminal

Similar Documents

Publication Publication Date Title
CN111081010B (en) Method and device for predicting traffic flow or travel time
KR102097953B1 (en) Failure risk index estimation device and failure risk index estimation method
CN110909306B (en) Business abnormality detection method and device, electronic equipment and storage equipment
CN110426634B (en) Method and equipment for predicting abnormity of driving system
CN112365070B (en) Power load prediction method, device, equipment and readable storage medium
US20220042952A1 (en) State estimation device and state estimation method
CN115169412A (en) Method and device for determining operation mode, controller and engineering vehicle
CN111177485A (en) Method, device and medium for predicting device failure based on parameter rule matching
CN115081760B (en) Processing resource management optimization method, device, terminal and storage medium
CN103646670A (en) Method and device for evaluating performances of storage system
CN117501288A (en) System and method for monitoring an industrial environment
CN112684402B (en) Method and system for monitoring electric energy running error data of stable electric consumption
CN113886237A (en) Analysis report generation method and device, electronic equipment and storage medium
CN117593464A (en) Construction method and system of electric power digital twin model library
CN116186479A (en) Processing method, processor, device and storage medium for pump truck working condition data
Baier et al. Identifying failure root causes by visualizing parameter interdependencies with spectrograms
CN116894213A (en) Method for identifying working condition of excavator and working condition identifying device of excavator
CN114756990A (en) Method and device for determining working condition type of excavator, controller and excavator
CN116482460A (en) Fault diagnosis method for power grid equipment and related equipment
US20230297095A1 (en) Monitoring device and method for detecting anomalies
CN114817209A (en) Monitoring rule processing method and device, processor and electronic equipment
CN114021112A (en) Cryptographic algorithm energy analysis method and device, storage medium and electronic equipment
CN111783486A (en) Maintenance early warning method and device for card reader equipment
CN112580827A (en) Work order generation method and device
CN115718878A (en) Method for detecting working condition data, storage medium and processor

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination