CN116383641A

CN116383641A - Earthwork mechanical working condition identification method and device, storage medium and processor

Info

Publication number: CN116383641A
Application number: CN202310172176.4A
Authority: CN
Inventors: 史余鹏; 付玲; 刘延斌; 王维; 张军花; 刘洋
Original assignee: Zoomlion Heavy Industry Science and Technology Co Ltd
Current assignee: Zoomlion Heavy Industry Science and Technology Co Ltd
Priority date: 2023-02-27
Filing date: 2023-02-27
Publication date: 2023-07-04

Abstract

The invention relates to the technical field of engineering machinery, and discloses a method and a device for identifying working conditions of earthwork machinery, a storage medium and a processor. The identification method of the invention comprises the following steps: acquiring basic data of earthmoving machinery; according to the basic data, a preset working condition stage identification model is adopted to identify working condition stages of the earthmoving machine, and a working condition stage identification result is obtained; and according to the working condition stage identification result, a preset working condition type identification model is adopted to identify the working condition type of the earthmoving machine, and a working condition type identification result is obtained. The multi-level working condition recognition method is realized, the complexity and calculation force requirements of the working condition recognition model are reduced, the real vehicle carrying is facilitated, and the accuracy and stability of the recognition result are improved. Meanwhile, the working condition stage recognition model and the working condition type recognition model can cover all working condition stages and working condition types, so that the coverage of the recognition model is widened, the recognition model can be used for various scenes, and the environmental adaptability of the working condition recognition method is improved.

Description

Earthwork mechanical working condition identification method and device, storage medium and processor

Technical Field

The invention relates to the technical field of engineering machinery, in particular to an earthmoving machine working condition identification method, an earthmoving machine working condition identification device, a machine-readable storage medium and a processor.

Background

Along with the improvement of manpower and material cost and the improvement of quality and progress requirements in the project construction process, intelligent construction with project decision driven based on field equipment and personnel operation information is a typical feature and becomes a future development direction. In the construction process, the excavator is responsible for completing 65-70% of earthwork tasks, and working condition change, earthwork workload, fuel consumption and other operation information statistics in the construction process are important contents of intelligent construction.

The most direct way to implement the statistics of the working information of the earthmoving machine is to dispatch the staff for on-site monitoring, but the method has high cost and poor reliability. Therefore, host manufacturers develop various operation information statistical methods based on the internet of things technology to realize remote and accurate monitoring of the operation efficiency of the excavator through the mounted multi-source sensing information system, however, the operation information statistical methods all need to identify the working conditions.

At present, for working condition identification, a working condition identification method based on visual information is often adopted in the prior art, and the working condition identification method has the defects of narrow working condition type coverage and poor environmental adaptability.

Disclosure of Invention

The invention aims to provide an earthmoving machine working condition identification method, an earthmoving machine working condition identification device, a machine-readable storage medium and a processor. The earth machinery working condition recognition method can realize multi-level working condition recognition, cover more working condition stages and working condition types, widen the coverage of a recognition model and improve the environmental adaptability of the working condition recognition method.

In order to achieve the above object, a first aspect of the present application provides a method for identifying working conditions of an earthmoving machine, including:

acquiring basic data of earthmoving machinery;

according to the basic data, a preset working condition stage identification model is adopted to identify the working condition stage of the earthmoving machine, and a working condition stage identification result is obtained;

according to the working condition stage identification result, a preset working condition type identification model is adopted to identify the working condition type of the earthmoving machine, and a working condition type identification result is obtained;

the data type of the basic data at least comprises one of a main pump pressure signal, data acquired by adopting machine vision, an operation handle pilot control signal and an actuating mechanism displacement signal.

In this embodiment of the present application, the process for constructing the preset working condition stage identification model includes:

Acquiring first sample data, wherein the first sample data comprises main pump pressure data of each working condition stage under each working condition type and a working condition stage label corresponding to the main pump pressure data;

the method comprises the steps of respectively inputting main pump pressure data of each working condition stage to a first neural network to obtain a predicted working condition stage;

and adjusting parameters of the first neural network according to the predicted working condition stage and the working condition stage label corresponding to the main pump pressure data in the first sample data to obtain a working condition stage identification model.

In this embodiment of the present application, the process for constructing the preset operating mode type recognition model includes:

acquiring second sample data, wherein the second sample data comprises characteristic data of each working condition stage under each working condition type and a working condition type label corresponding to the characteristic data;

respectively inputting the characteristic data of each working condition stage into a second neural network to obtain a predicted working condition type;

and adjusting parameters of the second neural network according to the predicted working condition type and the working condition type label corresponding to the characteristic data in the second sample data to obtain a working condition type identification model.

In this embodiment of the present application, the basic data is a main pump pressure signal, where the main pump pressure signal includes a plurality of main pump pressure data within a first preset time range from the current time;

The working condition stage of the earthmoving machine is identified by adopting a preset working condition stage identification model according to the basic data, and a working condition stage identification result is obtained, and the method comprises the following steps:

a1: extracting features of the main pump pressure signal to obtain a feature vector;

a2: normalizing the feature vector to obtain a normalized feature vector;

a3: inputting the normalized feature vector into a preset working condition stage identification model to perform working condition stage identification, and obtaining a working condition stage identification result;

a4: judging whether the working condition stage identification process is finished;

a5: outputting a working condition stage identification result under the condition that the working condition stage identification process is finished;

a6: and under the condition that the working condition stage identification process is not finished, rejecting the main pump pressure data farthest from the current moment in the main pump pressure signal, and acquiring the main pump pressure data at the next moment to update the main pump pressure signal to obtain a new main pump pressure signal, and returning to the execution A1.

In this embodiment of the present application, according to the result of the working condition stage identification, a preset working condition type identification model is used to identify the working condition type of the earthmoving machine, so as to obtain a result of identifying the working condition type, including:

B1: acquiring a plurality of working condition stage identification results within a second preset time range from the current moment, and forming a working condition stage vector from the plurality of working condition stage identification results;

b2: inputting the working condition stage vector into a preset working condition type recognition model to recognize the working condition type, and obtaining a working condition type recognition result;

b3: judging whether the working condition type identification process is finished;

b4: outputting a working condition type identification result under the condition that the working condition type identification process is finished;

b5: and under the condition that the working condition type identification process is not finished, eliminating the working condition stage identification result farthest from the current moment in the working condition stage identification results, acquiring the working condition stage identification result at the next moment, updating the working condition stage vector to obtain a new working condition stage vector, and returning to the execution of B2.

In this embodiment of the present application, after obtaining the recognition result of the working condition type, the method further includes:

according to the working condition stage identification result and the working condition type identification result, counting according to preset working condition information counting conditions to obtain a working condition information counting result;

acquiring fuel consumption rate information;

and according to the working condition stage identification result, the working condition type identification result, the working condition information statistical result and the fuel consumption rate information, the working information of the earthmoving machine is counted in the time dimension, and a first working information statistical result is obtained.

In an embodiment of the present application, further includes:

the method comprises the steps of obtaining terrain information of a to-be-operated range of the earth machinery, and forming an operation environment electronic map according to the terrain information;

acquiring positioning signals of the earthmoving machine and motion information of an actuating mechanism in real time;

determining the position of the earthmoving machine in the operation environment electronic map according to the positioning signal of the earthmoving machine, and obtaining the track of a working device of the earthmoving machine according to the motion information of an actuating mechanism of the earthmoving machine;

determining the amount of the earth which is already worked based on the working environment electronic map and the working device track of the earth machinery;

the track of the working device is formed by the change of the motion information of the actuating mechanism of the earthmoving machine along with the time.

In an embodiment of the present application, the determining the amount of the worked earthwork based on the working environment electronic map and the working device trajectory of the earthwork machine includes:

dividing a range to be operated in the operation environment electronic map into a plurality of uniform cubes;

determining the intersection states of each cube and the track of the working device respectively to obtain a plurality of cube states;

and obtaining the worked earthwork according to the states of the cubes and the volumes of the cubes.

In an embodiment of the present application, at least one of the following steps is further included:

according to the operated earthwork quantity and the total operation duration of earthwork excavation, calculating to obtain earthwork operation efficiency, wherein the first operation information statistical result at least comprises the total operation duration of earthwork excavation;

and calculating to obtain single earthwork excavation working capacity according to the worked earthwork capacity and the earthwork excavation cycle times, wherein the working condition information statistical result at least comprises the earthwork excavation cycle times.

The second aspect of the present application provides an earthmoving machine operating condition recognition device, comprising:

the acquisition module is used for acquiring basic data of the earthmoving machine; the data type of the basic data at least comprises one of a main pump pressure signal, data acquired by adopting machine vision, an operation handle pilot control signal and an actuating mechanism displacement signal;

the first recognition module is used for recognizing the working condition stage of the earthmoving machine by adopting a preset working condition stage recognition model according to the basic data to obtain a working condition stage recognition result;

and the second recognition module is used for recognizing the working condition type of the earthmoving machine by adopting a preset working condition type recognition model according to the working condition stage recognition result to obtain a working condition type recognition result.

A third aspect of the present application provides a processor configured to perform the above-described method of identifying an earth moving machine condition.

A fourth aspect of the present application provides a machine-readable storage medium having stored thereon instructions that, when executed by a processor, cause the processor to be configured to perform the earthmoving machine condition identification method described above.

According to the technical scheme, based on basic data of the earthmoving machine, the working condition stage identification model and the working condition type identification model are utilized to sequentially perform working condition stage identification and working condition type identification, so that a working condition stage identification result and a working condition type identification result are obtained. Based on basic data of the earthmoving machine, the working condition identification of the earthmoving machine is completed according to a working condition stage-working condition type multi-step mode, so that a multi-level working condition identification method is realized, the complexity and calculation force requirements of a working condition identification model can be reduced compared with a single-step working condition identification method, the real vehicle carrying is facilitated, and the accuracy and stability of an identification result are improved. Meanwhile, the working condition stage recognition model and the working condition type recognition model can cover more working condition stages and working condition types, so that the coverage of the recognition model is widened, the method can be used in various scenes, and the environmental adaptability of the working condition recognition method is improved.

Additional features and advantages of the invention will be set forth in the detailed description which follows.

Drawings

The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate the invention and together with the description serve to explain, without limitation, the invention. In the drawings:

FIG. 1 schematically illustrates a flow chart of a method for identifying working conditions of an earthmoving machine according to an embodiment of the present application;

FIG. 2 schematically illustrates a multi-level, multi-dimensional hydraulic excavator work information statistical flow diagram in accordance with an embodiment of the present application;

FIG. 3 schematically illustrates a simplified diagram of a backhoe structure according to an embodiment of the present application;

FIG. 4 schematically illustrates an excavator work device D-H coordinate system in accordance with an embodiment of the present application;

FIG. 5 schematically illustrates a block diagram of an earthmoving machine condition identification apparatus in accordance with an embodiment of the present application;

fig. 6 schematically shows an internal structural diagram of a computer device according to an embodiment of the present application.

Description of the reference numerals

1-getting off; 2-getting on; 3-a movable arm; 4-a movable arm hydraulic cylinder; 5-a bucket rod hydraulic cylinder; 6, a bucket rod; 7-a bucket hydraulic cylinder; 8-rocker arms; 9-connecting rod; 10-a bucket; 410-an acquisition module; 420-a first identification module; 430-a second identification module; a01-a processor; a02-a network interface; a03-an internal memory; a04-a display screen; a05-an input device; a06—a nonvolatile storage medium; b01-operating system; b02-computer program.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in 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 implementations described herein are only for illustrating and explaining the embodiments of the present application, and are not intended to limit the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.

It should be noted that, in the embodiment of the present application, directional indications (such as up, down, left, right, front, and rear … …) are referred to, and the directional indications are merely used to explain the relative positional relationship, movement conditions, and the like between the components in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indications are correspondingly changed.

In addition, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.

Referring to fig. 1 and 2, fig. 1 schematically illustrates a flow chart of a method for identifying working conditions of an earthmoving machine according to an embodiment of the present application, and fig. 2 schematically illustrates a multi-level and multi-dimensional statistical flow chart of operation information of a hydraulic excavator according to an embodiment of the present application.

As shown in fig. 1, in an embodiment of the present application, an earth moving machine working condition identifying method is provided, and it should be noted that, the earth moving machine working condition identifying method provided in this embodiment may be applied to an earth moving machine such as digging, shoveling, pushing or leveling soil and sand. For convenience of explanation, in this embodiment, an earth moving machine is mainly used as an excavator. The earth machinery working condition identification method comprises the following steps:

step 210: acquiring basic data of earthmoving machinery; the data type of the basic data at least comprises one of a main pump pressure signal, data acquired by adopting machine vision, an operation handle pilot control signal and an actuating mechanism displacement signal;

step 220: according to the basic data, a preset working condition stage identification model is adopted to identify the working condition stage of the earthmoving machine, and a working condition stage identification result is obtained;

Step 230: and according to the working condition stage identification result, a preset working condition type identification model is adopted to identify the working condition type of the earthmoving machine, and a working condition type identification result is obtained.

According to the technical scheme, basic data of the earthmoving machine are firstly obtained, and then the working condition stage recognition and the working condition type recognition are sequentially carried out by utilizing the working condition stage recognition model and the working condition type recognition model based on the basic data, so that a working condition stage recognition result and a working condition type recognition result are obtained. Based on basic data of the earthmoving machine, the working condition identification of the earthmoving machine is completed according to a working condition stage-working condition type multi-step mode, so that a multi-level working condition identification method is realized, the complexity and calculation force requirements of a working condition identification model are reduced compared with a single-step working condition identification method, the real vehicle carrying is facilitated, and the accuracy and stability of an identification result are improved. Meanwhile, the working condition stage recognition model and the working condition type recognition model can cover more working condition stages and working condition types, so that the coverage of the recognition model is widened, the method can be used in various scenes, and the environmental adaptability of the working condition recognition method is improved.

In the implementation process, the working condition stage recognition result and the working condition type recognition result are respectively recognized by adopting the working condition stage recognition model and the working condition type recognition model, and the output of the working condition stage recognition model is used as the input of the working condition type recognition model, so that a multi-level working condition recognition method is realized, the calculated amount is reduced, and the working condition recognition result is facilitated to be obtained quickly.

In this embodiment, the basic data of the earthmoving machine is a data source for performing working condition recognition, and may be at least one of a main pump pressure signal, data acquired by machine vision, a pilot control signal of an operating handle, a displacement signal of an actuating mechanism, and other types of data as the data source for performing working condition recognition.

In order to facilitate explanation of the scheme, the embodiment mainly uses the main pump pressure signal as a data source for identifying the working condition, that is, the basic data is the main pump pressure signal. The main pump pressure signal of the earthmoving machine can be acquired by a pressure sensor on the earthmoving machine. The main pump pressure signal may be main pump pressure data acquired at the current time or main pump pressure data within a certain time range. Such as: and under the condition that the earth machinery is an excavator, collecting a main pump pressure signal within 0.5s from the current moment of the excavator by adopting a pressure sensor. For different types of earthmoving machines, the main pump pressure signals may be one or more sets, such as: for mini-excavators, only one set of main pump pressure signals is included; for large and medium-sized excavators, two sets of main pump pressure signals are included.

Accordingly, step 220 may identify the working condition stage of the earthmoving machine according to the main pump pressure signal by using a preset working condition stage identification model, so as to obtain a working condition stage identification result.

In the case where the earth moving machine is an excavator, the excavator working types may include earth moving, land leveling, slope repairing, crushing, whole vehicle walking and machine idling; the method comprises the following working condition types of the earthwork excavation of the excavator, wherein the working condition types comprise five working condition stages of excavation preparation, excavation, lifting and turning, unloading and returning of an empty bucket; the land leveling working condition type comprises two working condition stages of bucket and bucket rod outward swinging and bucket rod inward folding; the slope repairing working condition type comprises two working condition stages of the inward retraction of the movable arm lifting bucket rod and the outward swinging of the movable arm descending bucket rod; the crushing working condition type comprises two working condition stages of crushing impact and crushing point adjustment; the running and idle of the whole vehicle are not only independent working condition types but also working condition stages, and are not subdivided. The working condition types and working condition stages of other earthmoving machines can be determined according to actual conditions, and are not described herein.

The construction of the working condition stage identification model may be implemented by building and training a neural network in advance before step 220, and the working condition stage identification model of the component may be preset in the earthmoving machine. In some embodiments, the construction process of the preset working condition stage identification model includes the following steps:

Firstly, acquiring first sample data, wherein the first sample data comprises main pump pressure data of each working condition stage under each working condition type and a working condition stage label corresponding to the main pump pressure data; in this embodiment, the first sample data includes a plurality of sets of data, and each set of data includes a main pump pressure data and a working condition stage label corresponding to the main pump pressure data. The dividing of each working condition stage may be to use the pressure waveform of the main pump corresponding to each working condition stage as a working condition stage dividing mark. For example: under the condition that the earthmoving machine is an excavator, because the pressure signals of the main pump in different working condition stages are different, the pressure waveform of the main pump corresponding to each working condition stage in different working condition types can be used as a working condition stage division mark, the working cycle of the excavator is segmented, and the segmentation result is the corresponding working condition stage. Taking the type of the working condition of earth excavation as an example, after working circulation is segmented, five working condition stages of excavation preparation, excavation, lifting and rotation, unloading and bucket returning are shared. The main pump pressure waveform herein refers to a main pump pressure signal.

Then, respectively inputting the pressure data of the main pump in each working condition stage into a first neural network to obtain a predicted working condition stage;

Then, comparing the predicted working condition stage with a working condition stage label corresponding to the main pump pressure data in the first sample data to obtain a working condition stage comparison result;

and finally, adjusting parameters of the first neural network according to the comparison result of the working condition phases to obtain a working condition phase identification model.

In this embodiment, the first neural network may be a linear neural network, a feedback neural network, a multi-layer feedforward neural network (BP neural network), or the like, where the BP neural network has a network structure with strong nonlinear mapping capability and flexibility. The number of middle layers of the network and the number of neurons of each layer can be set arbitrarily according to specific situations, and the network has strong generalization capability and fault tolerance capability. The BP neural network can be used for obtaining a more stable and reliable working condition stage identification model. When the earthmoving machine is an excavator, an excavator working condition stage identification model can be established based on the BP neural network, main pump pressure data of each working condition stage under each working condition type is used as model input to obtain a predicted working condition stage, working condition stage labels corresponding to the predicted working condition stage and the main pump pressure data are input to a preset loss function to obtain corresponding loss values, model parameters are adjusted according to the loss values, the predicted working condition stage labels corresponding to the main pump pressure data are the same, so that the model has enough identification accuracy, and finally the working condition stage identification model is obtained through training.

Accordingly, the working condition type recognition model can also be pre-constructed, and the construction process of the preset working condition type recognition model comprises the following steps:

firstly, obtaining second sample data, wherein the second sample data comprises characteristic data of each working condition stage under each working condition type and a working condition type label corresponding to the characteristic data; in this embodiment, the second sample data includes a plurality of sets of data, where each set of data includes feature data of one working condition stage and a working condition type tag corresponding to the feature data. The dividing of each working condition type can be to use waveform characteristics corresponding to each working condition stage as a working condition type dividing mark. For example: under the condition that the earthmoving machine is an excavator, the working type of the excavator is divided by taking the waveform characteristic of the corresponding working condition stage under the working condition type as the identification mark of the working condition type, and the division result is the working condition type corresponding to the current moment. Taking the earthwork excavation working condition type as an example, when the working condition stage at the current moment is any stage of excavation preparation, excavation, lifting and turning, unloading and bucket returning, the working condition type at the current moment is earthwork excavation.

Then, respectively inputting the characteristic data of each working condition stage into a second neural network to obtain a predicted working condition type;

then, comparing the predicted working condition type with a working condition type label corresponding to the characteristic data in the second sample data to obtain a working condition type comparison result;

and finally, adjusting parameters of the second neural network according to the comparison result of the working condition types to obtain a working condition type identification model.

In this embodiment, the second neural network may be a linear neural network, a feedback neural network, a multi-layer feedforward neural network (BP neural network), or the like, where the BP neural network has a network structure with strong nonlinear mapping capability and flexibility. The number of middle layers of the network and the number of neurons of each layer can be set arbitrarily according to specific situations, and the network has strong generalization capability and fault tolerance capability. The BP neural network can be used for obtaining a more stable and reliable working condition type identification model. Under the condition that the earthmoving machine is an excavator, an excavator working condition type identification model can be established based on a BP neural network, waveform characteristics of working condition stages under all working condition types are used as model input to obtain a predicted working condition type, a working condition type label corresponding to the predicted working condition type and characteristic data is input to a preset loss function to obtain a corresponding loss value, model parameters are adjusted according to the loss value, the predicted working condition type label corresponding to the characteristic data is the same, the model has enough identification accuracy, and finally the working condition type identification model is obtained through training.

In the implementation process, the working condition stage recognition model and the working condition type recognition model are obtained through training by adopting the neural network, so that the reliability of the working condition recognition result is improved. The BP neural network model is selected, so that the cost of working condition identification can be reduced, and the BP neural network model is more convenient to carry on engineering machinery.

When the preset working condition stage identification model is adopted to identify the working condition stage of the earthmoving machine, the main pump pressure signal can be input into the preset working condition stage identification model to obtain a working condition stage identification result. In order to enable the obtained working condition stage identification result to be more accurate, main pump pressure data in a certain time range can be used as a data source to identify the working condition stage, namely, the main pump pressure signal comprises a plurality of main pump pressure data in a first preset time range from the current moment; such as the main pump pressure signal within 0.5s from the current time in the example described above.

In one embodiment, a working condition class stage result may be obtained in real time, and according to the basic data, a preset working condition stage recognition model is adopted to recognize a working condition stage of the earthmoving machine, so as to obtain a working condition stage recognition result, including the following steps:

Step A1: extracting features of the main pump pressure signal to obtain a feature vector; in this embodiment, the feature extraction includes reducing noise and transient disturbances of the main pump pressure signal using mean filtering; then reducing the frequency of the pressure signal of the main pump in a system sampling mode according to the calculation force of the host controller; and finally extracting the time domain characteristic value of the main pump pressure signal after frequency reduction to obtain a characteristic vector. The time domain characteristic value of the main pump pressure signal after the extraction and the frequency reduction can be obtained by calculating the mean value and the variance of the main pump pressure signal. The system sampling is adopted to reduce the data sampling frequency, so that the low cost and low calculation force requirements of working condition identification are ensured, and the system is more convenient to carry to earthwork machinery.

Taking an earthmoving machine as an excavator as an example, for a small excavator with only one main pump, a feature vector is composed of a mean value and a variance of a main pump pressure signal with a feature value of No. 1, and can be expressed as: x= [ X ] ₁ ,x ₂ ]Wherein X is a feature vector constructed by the time domain feature values; x is x ₁ The mean value of the pressure signals of the No. 1 main pump; x is x ₂ The variance of the pressure signal of the main pump No. 1; for a large and medium-sized excavator with two main pumps, the characteristic vector is composed of a mean value and a variance of a pressure signal of a main pump No. 1, a mean value and a variance of a pressure signal of a main pump No. 2 and a mean value and a variance of a pressure signal difference of the main pumps No. 1 and No. 2, and can be expressed as follows: x= [ X ] ₁ ,x ₂ ,x ₃ ,x ₄ ,x ₅ ,x ₆ ]Wherein X is a feature vector constructed by the time domain feature values; x is x ₁ The mean value of the pressure signals of the No. 1 main pump; x is x ₂ The variance of the pressure signal of the main pump No. 1; x is x ₃ The mean value of the pressure signal of the No. 2 main pump; x is x ₄ The variance of the pressure signal of the No. 2 main pump; x is x ₅ Is the average value of the difference values of the main pump pressure signals of No. 1 and No. 2; x is x ₆ Is the variance of the difference between the main pump pressure signals No. 1 and No. 2.

Step A2: normalizing the feature vector to obtain a normalized feature vector; in this embodiment, the normalization processing may be to substitute the feature values in the feature vectors into normalization formulas to calculate normalized feature values, so as to obtain normalized feature vectors. Wherein, the normalization formula can be:

wherein x is _new The normalized characteristic value; x is a characteristic value before normalization; x is x _max The maximum value of the corresponding type characteristic value of x in the characteristic vector is obtained; x is x _min Is the minimum value of the corresponding category characteristic value of x in the characteristic vector. In practical application, other normalization modes such as nonlinear normalization can be adopted.

Step A3: inputting the normalized feature vector into a preset working condition stage identification model to perform working condition stage identification, and obtaining a working condition stage identification result;

Under the condition that the earthmoving machine is an excavator, the normalized feature vector is input into the working condition stage identification model, and the working condition stage where the excavator is located can be judged according to the sequence number with the largest output probability value in the output result of the working condition stage identification model. Such as: when the sequence number of the maximum probability value is 1-5, working condition stages of the excavator at the current moment are respectively excavating preparation, excavating, lifting and turning, unloading and empty bucket returning stages under the earthwork excavating working condition type; when the serial number of the maximum probability value is 6-7, working condition stages of the excavator at the current moment are respectively bucket and bucket rod outward swinging and bucket rod inward folding stages under the flat ground working condition type; when the sequence number of the maximum probability value is 8-9, working condition stages of the excavator at the current moment are respectively a movable arm lifting arm adduction and a movable arm descending arm outward swinging stage under the slope repairing working condition type; when the sequence number of the maximum probability value is 10-11, the working condition stage of the excavator at the current moment is respectively a crushing impact stage and a crushing point adjustment stage under the type of crushing working condition; when the serial number of the maximum probability value is 12-13, working condition stages of the excavator at the current moment are the whole vehicle walking and idle stages respectively. It should be noted that, the sequence number may be set when the model is identified in the pre-training working condition stage, and the sequence number with the largest output probability value is set as the output result.

In one embodiment, the obtained recognition result of the working condition stage may be stored in a hardware device such as a processor, a cache, or the like.

In one embodiment, the obtained recognition result of the working condition stage may be output from the hardware device to an output device in real time, where the output device may be a memory, a display device, a terminal, a communication module, etc., so that the user may obtain the recognition result of the working condition stage in time. For example, the recognition result of the working condition stage stored in the processor can be output to the display device.

In one embodiment, in order to further improve accuracy of the working condition stage identification, the working condition stage identification may be performed in a circulating manner until the end signal is received, and the working condition stage identification result is output, and specifically, step A4 may be continuously performed after step A3 is performed: judging whether the working condition stage identification process is finished; in this embodiment, whether the working condition stage identifying process is ended may be determined whether there is an ending signal, and the ending signal may be a switch that is set, and a worker starts the switch according to the actual situation, so as to obtain the ending signal. It is also possible to judge whether the condition stage recognition process is ended by judging whether to power off.

Step A5: outputting a working condition stage identification result under the condition that the working condition stage identification process is finished;

in this real-time example, the obtained recognition result of the working condition stage may be output from the above hardware device to an output device, where the output device may be a memory, a display device, a terminal, a communication module, etc., so that the user may obtain the recognition result of the working condition stage in time. For example, the recognition result of the working condition stage stored in the processor can be output to the display device.

Step A6: and under the condition that the working condition stage identification process is not finished, rejecting the main pump pressure data farthest from the current moment in the main pump pressure signal, acquiring the main pump pressure data at the next moment, updating the main pump pressure signal to obtain a new main pump pressure signal, and executing A1-A4.

In this embodiment, since the main pump pressure signal includes main pump pressure data within a certain time range, when the working condition stage identification process is not finished, the main pump pressure data farthest from the current moment can be removed along with the change of time, then the main pump pressure data at the next moment is added, so as to form a new main pump pressure signal, and then the steps A1-A4 are repeated until the identification is finished, so that the accuracy and the instantaneity of the working condition stage identification result are ensured.

Correspondingly, in order to make the obtained recognition result of the working condition type more accurate, the recognition result of the working condition stage within a certain time range can be adopted as a data source to recognize the working condition type,

in one embodiment, the condition type recognition result is a real-time output condition type recognition result. And according to the working condition stage identification result, identifying the working condition type of the earthmoving machine by adopting a preset working condition type identification model to obtain a working condition type identification result, wherein the working condition type identification result comprises the following steps:

step B1: acquiring a plurality of working condition stage identification results within a second preset time range from the current moment, and forming a working condition stage vector from the plurality of working condition stage identification results; such as: taking an earthmoving machine as an excavator, receiving recognition results which are output by an excavator working condition stage recognition model and are within 0.5s from the current moment, and combining the working condition stage recognition results into a vector to obtain a working condition stage vector.

It should be noted that, in this embodiment, the first preset time and the second preset time may be the same or different, and specifically set according to actual needs.

Step B2: inputting the working condition stage vector into a preset working condition type recognition model to recognize the working condition type, and obtaining a working condition type recognition result;

Under the condition that the earthwork machine is an excavator, the working condition stage vector is input into a working condition type identification model, and the working condition type of the excavator is judged according to the sequence number with the maximum output probability value in the model output result. Such as: when the sequence number of the maximum probability value is 1, the working condition type of the excavator at the current moment is earth excavation; when the serial number of the maximum probability value is 2, the working condition type of the excavator at the current moment is a land leveling working condition; when the serial number of the maximum probability value is 3, the working condition type of the excavator at the current moment is slope repairing; when the serial number of the maximum probability value is 4, the working condition type of the excavator at the current moment is broken; when the serial number of the maximum probability value is 5-6, the working condition types of the excavator at the current moment are the running and idle of the whole excavator respectively. It should be noted that, the sequence number may be set when the model is identified in the pre-training working condition stage, and the sequence number with the largest output probability value is set as the output result.

In one embodiment, the obtained condition type recognition result may be stored in a hardware device such as a processor, a cache, or the like.

In one embodiment, the obtained condition type recognition result may be output from the hardware device to an output device in real time, where the output device may be a memory, a display device, a terminal, a communication module, etc., so that a user may obtain the condition type recognition result in time. For example, the result of identifying the type of the working condition stored in the processor may be output to the display device.

In one embodiment, in order to further improve accuracy of the working condition type identification, the working condition type identification may be performed in a circulating manner until the end signal is received, and the working condition type identification result is output, and specifically, the step B3 may be continuously performed after the step B2 is performed: judging whether the working condition type identification process is finished; in this embodiment, whether the operation mode type recognition process is ended is similar to whether the operation mode stage recognition process is ended in the step A4 is determined by judging whether an ending signal is present, and detailed description thereof is omitted.

Step B4: outputting a working condition type identification result under the condition that the working condition type identification process is finished;

in this real-time example, the obtained condition type recognition result may be output from the hardware device to an output device, where the output device may be a memory, a display device, a terminal, a communication module, etc., so that a user may obtain the condition type recognition result in time. For example, the result of identifying the type of the working condition stored in the processor may be output to the display device.

Step B5: and under the condition that the working condition type identification process is not finished, eliminating the working condition stage identification result farthest from the current moment in the plurality of working condition stage identification results, acquiring the working condition stage identification result at the next moment, updating the working condition stage vector to obtain a new working condition stage vector, and executing the B2-B3.

In this embodiment, since the working condition stage vector is composed of working condition stage recognition results of multiple time points, when the working condition type recognition process is not finished, the working condition stage recognition result farthest from the current moment can be removed along with time change, then the working condition stage recognition result at the next moment is added, so as to form a new working condition stage vector, and then steps B2-B3 are repeated until the recognition is finished, so that accuracy and instantaneity of the working condition type recognition result are ensured.

In the implementation process, a main pump pressure signal of the earthmoving machine is obtained; then, according to the main pump pressure signal, a preset working condition stage identification model is adopted to identify the working condition stage of the earthmoving machine, and a working condition stage identification result is obtained; and according to the working condition stage identification result, a preset working condition type identification model is adopted to identify the working condition type of the earthmoving machine, and a working condition type identification result is obtained. Based on the main pump pressure signal, the working condition stage identification model and the working condition type identification model are utilized to sequentially identify, so that a working condition stage identification result and a working condition type identification result are obtained. The main pump pressure generated by the basic action of the executing mechanism is used as a data source, and the working condition identification of the earthmoving machine is completed according to a working condition stage-working condition type multi-step mode, so that a multi-level working condition identification method is realized, the complexity and calculation force requirements of a working condition identification model are reduced compared with a single-step working condition identification method, the carrying of a real vehicle is facilitated, and the accuracy and stability of an identification result are improved. Meanwhile, the working condition stage recognition model and the working condition type recognition model can cover more working condition stages and working condition types, so that the coverage of the recognition model is widened, the method can be used in various scenes, and the environmental adaptability of the working condition recognition method is improved.

The working process of the excavator is divided into 6 working condition types of earth excavation, land leveling, slope repairing, crushing, whole vehicle walking and idle machine, working condition stages covered by the working condition types are further defined, the basic action of an executing mechanism and the pressure waveform of a main pump in the working condition stages are mapped, the working condition stages and the working condition types are identified sequentially from bottom to top, and the multi-level identification mode can effectively improve the reliability of the model; and moreover, the main pump pressure signal is used as an original signal source, and the BP neural network is used for establishing an identification model, so that the cost is low, the calculation force requirement is low, and the method is more suitable for the configuration of a host machine of engineering machinery.

After the working condition type identification result is obtained, working condition information statistics and time dimension operation information statistics can be performed, and the method specifically comprises the following steps:

firstly, according to the working condition stage identification result and the working condition type identification result, counting according to preset working condition information counting conditions to obtain a working condition information counting result; in this embodiment, the operating condition information statistics includes statistics of complete cycle times for each operating condition stage and each operating condition type. The statistical process can be that statistical conditions of working condition information are adopted for statistics, AND when the statistical process is implemented specifically, the statistical process can be completed in the form of conditions of IF-AND-THEN, the working condition stage AND the working condition type identification result are matched with the IF part one by one, IF the IF part of a certain condition is met, the THEN part is executed, AND the statistical result is changed; otherwise, the original statistical result is maintained unchanged.

In the case where the earth moving machine is an excavator, the conditions of the IF-AND-THEN may include:

condition one: the working condition stage result at the current moment of the IF is different from the working condition stage result at the last moment, and the cycle number of the working condition stage result corresponding to the last moment of the THEN is increased by 1 time;

condition II: the result of the working condition stage at the moment of IF is any working condition stage of empty bucket return, bucket AND bucket rod adduction, movable arm descending bucket rod outward swing, crushing point adjustment, whole vehicle walking AND idle machine, the result of the working condition stage at the moment of AND is different from the result of the working condition stage at the moment of last moment, AND the cycle number of the working condition type result corresponding to the working condition stage structure at the moment of THEN is increased by 1 time. It should be noted that the above conditions may be set according to different working condition types.

According to the working condition stage identification result and the working condition type identification result, the working condition information statistics conditions are adopted for statistics, so that the working condition information can be rapidly and effectively counted, and reasonable project decisions can be made by project managers.

Then, acquiring fuel consumption rate information; in this embodiment, the fuel consumption rate information may be CAN bus fuel consumption rate information, and may be obtained from a control module of the earthmoving machine.

And finally, according to the working condition stage identification result, the working condition type identification result, the working condition information statistics result and the fuel consumption rate information, counting the working information of the earthmoving machine in the time dimension to obtain a first working information statistics result. In this embodiment, the job information statistics for the time dimension include a total duration and time duty cycle for each operating condition phase, an average fuel consumption rate and fuel consumption rate duty cycle for each operating condition phase, a total duration for each operating condition type, a single cycle duration and time duty cycle, an average fuel consumption rate and fuel consumption rate duty cycle for each operating condition type.

In the case where the earth moving machine is an excavator, the job information statistics in the above-described time dimension can be calculated by the following equation:

wherein deltat is the working condition stage identification time interval; m1 _i The number of times of occurrence of each working condition stage in the working condition stage identification result is calculated; t1 _i The duration of each working condition stage is the total time; η1 _i The time duty ratio of each working condition stage is; o1 _i The instantaneous fuel consumption rate of each working condition stage; o1 _i Average fuel consumption rate for each working condition stage; η2 _i Average fuel consumption rate ratio for each working condition stage; m1 _i 、T1 _i 、η1 _i 、o1 _i 、O1 _i 、η2 _i I in (i)=1, 2..13, respectively representing the excavation preparation, excavation, lifting swing, unloading, empty bucket return, bucket and arm outward swing, bucket and arm adduction, boom lifting arm adduction, boom lowering arm outward swing, crushing impact, crushing point adjustment, whole vehicle walking, and idle working condition phases; m2 _i The number of times of occurrence of each working condition type in the working condition type identification result is set; n (N) _i The circulation times of each working condition type are multi-level working condition information statistical results; t2 _i The duration time is the total time of each working condition type; t is t _i Single cycle duration for each operating mode type; η3 _i Single cycle duration duty cycle for each operating mode type; o2 _i Instantaneous fuel consumption rate for each operating mode type; o2 _i Average fuel consumption rate for each operating mode type; η4 (eta 4) _i Average fuel consumption rate for each operating mode type; m2 _i 、N _i 、T2 _i 、t _i 、η3 _i 、o2 _i 、O2 _i 、η4 _i I=1, 2,..6, respectively represent earthmoving preparation, land leveling, slope repair, crushing, whole car walking and idle work types.

In the implementation process, multi-level working condition information statistics and time dimension working information statistics of the excavator are completed according to the working condition stage, the working condition type identification result and the CAN bus fuel consumption rate information, the information in the aspects of working condition and energy consumption is covered by statistics, the detailed information of the working condition type and the working condition stage in the working process of the excavator is revealed, and reasonable project decision making by project managers is facilitated.

The whole construction site work load is measured in the current construction process, so that the whole progress of the project is determined. The method is to send people to see, or to measure the working amount of the whole construction site by using simple equipment, or to regularly cruise through an unmanned aerial vehicle, compare the difference of electronic maps in a period of time and determine the construction earthwork amount of the whole project. However, in these methods, the work soil amount of each earth moving machine cannot be measured, and the work efficiency of each earth moving machine cannot be measured.

In this embodiment, the operation information statistics may also be performed from a spatial dimension, including statistics of the operated earthwork amounts of the individual earthworks machine, including the following steps:

firstly, obtaining the topographic information of the to-be-operated range of the earth machinery, and forming an operation environment electronic map according to the topographic information; in this embodiment, the terrain information may be 3D terrain information, taking an earthmoving machine as an excavator as an example, and the manner of acquiring the 3D terrain information of the excavator working range includes a single manual survey, an unmanned airborne laser radar technology, a machine vision technology, a millimeter wave radar technology, or a combination of multiple manners. The unmanned plane laser radar completes a terrain point cloud model in the working range of the excavator through the flight of the aircraft and the scanning of laser pulses; the visual sensors are arranged at the front part and the rear part of the top of the cab of the excavator, and at the left side and the right side of the vehicle body; millimeter wave radar is installed at the front, rear, left and right parts of the lower car body. All the technologies are finally used for acquiring the terrain elevation and gradient information in the working range of the excavator to form an electronic map of the working environment.

Then, positioning signals of the earthmoving machine and motion information of an actuating mechanism are obtained in real time; in this embodiment, taking an earth moving machine as an excavator, the excavator positioning signal refers to an absolute position of a center of rotation of an upper vehicle, and the acquiring mode includes a single differential GPS high-precision positioning system, an inertial navigation unit or a combination of multiple modes. The acquisition of the motion information of the actuating mechanism refers to the acquisition of the space coordinate of the driving space or the joint space of the actuating mechanism by installing a displacement sensor, an inclination sensor or a position sensor on the actuating structure, and finally, the space coordinate of the tooth tip pose of the bucket is converted by utilizing an excavator kinematics model. The method specifically comprises the following steps:

Firstly, acquiring initial space coordinates of an executing mechanism in real time; in this embodiment, the initial spatial coordinates may be actuator drive space or joint spatial coordinates.

The second step, based on the excavator kinematics model, converting the initial space coordinate into the pose space coordinate of the executing mechanism;

and thirdly, obtaining the motion information of the actuating mechanism according to the pose space coordinates of the actuating mechanism.

Please refer toFig. 3 and 4, fig. 3 schematically illustrates a simplified view of a backhoe structure according to an embodiment of the present application, and fig. 4 schematically illustrates an excavator work device D-H coordinate system according to an embodiment of the present application. In the case where the earth moving machine is an excavator, the excavator includes a lower carriage 1, an upper carriage 2, a boom 3, a boom cylinder 4, an arm cylinder 5, an arm 6, a bucket cylinder 7, a swing arm 8, a link 9, and a bucket 10. Coordinate systems are respectively established in the lower carriage 1, the upper carriage 2, the movable arm 3, the bucket arm 6 and the bucket 10 and are denoted by O ₀ 、O ₁ 、O ₂ 、O ₃ 、O ₄ Wherein O is ₀ Is a base coordinate system, O ₁ For getting on the car coordinate system, O ₂ Is a movable arm coordinate system, O ₃ Is the arm coordinate system, O ₄ Is a bucket coordinate system. The position relation between adjacent coordinate systems is described by adopting offset, rotation angle, rod length and torsion angle, and is defined as follows:

Offset distance s _i : along z _i Axis from x _i Axis to x _j Distance of axis, regulation and z _i The positive direction of the axes is consistent to be positive;

angle of rotation theta _i : along z _i Axis from x _i Axis to x _j The rotation angle of the shaft is positive in the anticlockwise direction and corresponds to the joint space;

length h of rod _i : along x _j Axis from z _i Axis to z _j Distance of axis, prescribed from x _j The positive direction of the axes is consistent to be positive;

torsion angle alpha _i : along x _j Axis from z _i Axis to z _j The rotation angle of the shaft is positive in the counterclockwise direction.

Excavator drive space: from rotary motor angle L ₀ Length L of movable arm hydraulic cylinder ₁ Length L of hydraulic cylinder of bucket rod ₂ And bucket cylinder length L ₃ Composition, denoted by [ L ] ₀ ,L ₁ ,L ₂ ,L ₃ ] ^T ；

Excavator joint space: from the included angle theta between the lower car 1 and the upper car 2 ₀ Included angle theta between upper vehicle 2 and movable arm 3 ₁ Angle theta between boom 3 and arm 6 ₂ Angle theta between arm 6 and bucket 10 ₃ Composition, expressed as [ theta ] ₀ ,θ ₁ ,θ ₂ ,θ ₃ ] ^T ；

Excavator pose space: the position and attitude angle of the bucket 10 in the base coordinate system (the angle at which the stop surface reaches the point where the bucket 10 hinges and the tip of the bucket 10 are joined) is expressed as [ x, y, z, ζ] ^T 。

The joint space coordinates of the excavator can be obtained through a formula for converting a driving space into a joint space, and then the pose space coordinates are obtained through a formula for converting the joint space into a pose space.

The formula for converting the driving space into the joint space is as follows:

the joint space is converted into a pose space formula:

wherein, XYZ represents the included angle between the straight line XY and the straight line YZ, L _XY As the distance between the hinge points X, Y, similar variables are the included angle between two straight lines or the distance between two hinge points, and can be identified with reference to fig. 2; alpha is the included angle between the connecting line of the hinge point A, F and the horizontal plane; θ ₀ Is the included angle between the lower vehicle 1 and the upper vehicle 2; θ ₁ Is the included angle between the upper vehicle 2 and the movable arm 3; θ ₂ Is the included angle between the movable arm 3 and the bucket rod 6; θ ₃ Is the included angle between the bucket arm 6 and the bucket 10; h is a ₁ Is the length of the boom 3 AB; h is a ₂ The length of the bucket rod 6 BG; h is a ₃ Is the length of bucket 10 GJ; the pose space coordinates are expressed as: [ x, y, z, ζ ]] ^T Where x, y, z are the positions of the actuators in the base coordinate system (e.g., the position of bucket 10 in the base coordinate system); ζ is the pose angle, namely the angle between the hinge point of the stopping surface to the bucket 10 and the connecting line of the tooth tip of the bucket 10.

Then, determining the position of the earthmoving machine in the electronic map of the working environment according to the positioning signal of the earthmoving machine, and obtaining the track of a working device of the earthmoving machine according to the motion information of an actuating mechanism of the earthmoving machine; the track of the working device is formed by the change of the motion information of the actuating mechanism of the earthmoving machine along with the time. In this embodiment, since the actuator movement information also changes with time, for example, the position of the tooth tip of the bucket 10 changes with time, a locus is obtained as the work implement locus of the earth moving machine. Each point on the work implement trajectory is the pose space coordinates of the bucket 10 tip at each point in time.

And finally, determining the amount of the worked earthwork based on the electronic map of the working environment and the track of the working device of the earthwork machine. In this embodiment, the amount of the worked earth may be obtained by calculating an intersection of the working device trajectory based on the working environment electronic map and the earth machine, specifically, may be obtained by:

dividing a to-be-operated range in the operation environment electronic map into a plurality of uniform cubes;

step two, determining the intersecting states of each cube and the track of the working device respectively to obtain a plurality of cube states; in this embodiment, each cube state may be respectively determined according to the track of the working device and a preset cube state determination formula; in this embodiment, pose space coordinates in the working device track are substituted into a cube state judgment formula to obtain each cube state. Wherein, the cube state judgment formula is:

wherein: m is M _j In a certain cube state, M _j =1 represents mined, M _j =0 represents non-excavated; v (V) _i A spatial extent defined for the cube; [ x, y, z, ζ ]]Is the pose space coordinate in the track of the working device, j is the number of the cube.

Thirdly, obtaining the worked earthwork according to the state of each cube and the volume of each cube. In this embodiment, each cube state and each cube volume may be substituted into the following formula:

V＝V ₀ ×ΣM _j ；

wherein: v (V) ₀ For the volume of the cubes, M _j V is the amount of earth worked for each cube state.

In the implementation process, the terrain information of the to-be-operated range of the earth machinery is obtained, and an operation environment electronic map is formed according to the terrain information; acquiring positioning signals of the earthmoving machine and motion information of an actuating mechanism in real time; then determining the position of the earthmoving machine in the electronic map of the working environment according to the positioning signal of the earthmoving machine, and obtaining the track of a working device of the earthmoving machine according to the motion information of an actuating mechanism of the earthmoving machine; and finally, obtaining the worked earthwork according to the state of each cube and the volume of each cube. And counting the operated earthwork quantity of the earthwork machine in the space dimension, and determining the earthwork quantity based on the intersection of the electronic map and the motion trail, so that the earthwork quantity of a single earthwork machine can be more conveniently obtained, and the efficiency of the single earthwork machine can be conveniently evaluated.

After the working earthwork quantity is obtained, the earthwork working efficiency of the space dimension can be further counted, specifically: according to the operated earthwork quantity and the total operation duration of earthwork excavation in the first operation information statistical result, calculating to obtain earthwork operation efficiency; in this embodiment, the amount of the earth that has been worked and the total working time length of the earth excavation in the first working information statistical result may be substituted into the following formula:

wherein eta is the earth work efficiency, V is the amount of earth worked, T2 ₁ Is the total working time of the earthwork excavation.

Correspondingly, after the worked earthwork volume is obtained, the single earthwork excavation work volume with space dimension can be further counted, and the method specifically comprises the following steps: and calculating to obtain single earthwork excavation work capacity according to the worked earthwork capacity and the earthwork excavation cycle times in the working condition information statistical result. In this embodiment, the amount of the earth that has been worked and the number of earth excavation cycles in the statistical result of the working condition information may be substituted into the following formula:

wherein V is the amount of earth volume already worked,

n is the single earth excavation work load ₁ The times of digging and circulating for earthwork; wherein, the earthwork excavation has five working condition stages, and the five working condition stages do one cycle of calculation at a time.

In the implementation process, the working information of the earthmoving machine is counted in the space dimension according to the track of the working device, the working condition information counting result and the first working information counting result, so that the working efficiency evaluation of a single machine of the earthmoving machine is realized. Therefore, operation information statistics is carried out from space dimension, a data basis is provided for host health evaluation and intelligent construction, information statistics in the aspect of earthwork workload and single-machine operation efficiency can be obtained, and reasonable project decision making by project managers is further facilitated.

The working earthwork quantity, the earthwork working efficiency and the single earthwork excavation working quantity can be used as second working information statistical results, multi-level multi-dimensional working information statistics can be realized after the first working information statistical results and the second working information statistical results are obtained, the working information statistics covers three aspects of working conditions, energy consumption and the earthwork working quantity, so that more comprehensive host working process information is provided, and project managers can be supported to make reasonable project decisions. And then the first operation information statistical result and the second operation information statistical result can be uploaded to the Internet of things platform through the external controller, so that the remote monitoring of the operation information of the host is realized.

Fig. 1 is a flow chart of a method for identifying working conditions of an earthmoving machine in an embodiment. It should be understood that, although the steps in the flowchart of fig. 1 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or sub-steps of other steps.

In one embodiment, as shown in fig. 5, fig. 5 schematically illustrates a block diagram of an earthmoving machine condition recognition device according to an embodiment of the present application. An earthmoving machine working condition recognition device is provided, which comprises an acquisition module 410, a first recognition module 420 and a second recognition module 430, wherein:

An acquisition module 410, configured to acquire basic data of an earthmoving machine; the data type of the basic data at least comprises one of a main pump pressure signal, data acquired by adopting machine vision, an operation handle pilot control signal and an actuating mechanism displacement signal;

the first identifying module 420 is configured to identify, according to the basic data, a working condition stage of the earth machine by using a preset working condition stage identifying model, so as to obtain a working condition stage identifying result;

and the second identifying module 430 is configured to identify the working condition type of the earthmoving machine by using a preset working condition type identifying model according to the working condition stage identifying result, so as to obtain a working condition type identifying result.

The working condition recognition device for earthmoving machinery comprises a processor and a memory, wherein the acquisition module 410, the first recognition module 420, the second recognition module 430 and the like are stored in the memory as program units, and the processor executes the program modules stored in the memory to realize corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and multi-level working condition identification is realized by adjusting kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the application provides a storage medium, and a program is stored on the storage medium, and the program realizes the method for identifying the working condition of the earthmoving machine when being executed by a processor.

In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 6. The computer apparatus includes a processor a01, a network interface a02, a display screen a04, an input device a05, and a memory (not shown in the figure) which are connected through a system bus. Wherein the processor a01 of the computer device is adapted to provide computing and control capabilities. The memory of the computer device includes an internal memory a03 and a nonvolatile storage medium a06. The nonvolatile storage medium a06 stores an operating system B01 and a computer program B02. The internal memory a03 provides an environment for the operation of the operating system B01 and the computer program B02 in the nonvolatile storage medium a06. The network interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program, when executed by the processor a01, implements a method for identifying the working conditions of an earthmoving machine. The display screen a04 of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device a05 of the computer device may be a touch layer covered on the display screen, or may be a key, a track ball or a touch pad arranged on a casing of the computer device, or may be an external keyboard, a touch pad or a mouse.

It will be appreciated by those skilled in the art that the structure shown in fig. 6 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, the earthmoving machine condition identification apparatus provided herein may be implemented in the form of a computer program that is executable on a computer device as shown in fig. 6. The memory of the computer device may store various program modules that make up the earthmoving machine condition identification apparatus, such as the acquisition module 410, the first identification module 420, and the second identification module 430 shown in fig. 5. The computer program comprising the respective program modules causes the processor to execute the steps in the method for identifying an earthmoving machine condition according to the respective embodiments of the present application described in the present specification.

The computer device shown in fig. 6 may perform step 210 through the acquisition module 410 in the earthmoving machine condition identification apparatus as shown in fig. 5. The computer device may perform step 220 by means of the first recognition module 420 and step 230 by means of the second recognition module 430.

The embodiment of the application provides equipment, which comprises a processor, a memory and a program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the following steps:

acquiring basic data of earthmoving machinery;

In one embodiment, the construction process of the preset working condition stage identification model includes:

acquiring first sample data, wherein the first sample data comprises main pump pressure data of all working condition stages under all working condition types and working condition stage labels corresponding to the main pump pressure data;

In one embodiment, the construction process of the preset working condition type identification model includes:

acquiring second sample data, wherein the second sample data comprises characteristic data of each working condition stage under all working condition types and a working condition type label corresponding to the characteristic data;

In one embodiment, the base data is a main pump pressure signal comprising a plurality of main pump pressure data within a first predetermined time range from a current time;

a2: normalizing the feature vector to obtain a normalized feature vector;

a6: and under the condition that the working condition stage identification process is not finished, rejecting the main pump pressure data farthest from the current moment in the main pump pressure signal, acquiring the main pump pressure data at the next moment to update the main pump pressure signal, obtaining a new main pump pressure signal, and returning to the execution A1.

In one embodiment, the identifying the working condition type of the earthmoving machine according to the working condition stage identification result by using a preset working condition type identification model to obtain a working condition type identification result includes:

b5: and under the condition that the working condition type identification process is not finished, eliminating the working condition stage identification result farthest from the current moment in the working condition stage identification results, acquiring the working condition stage identification result at the next moment to update the working condition stage vector, obtaining a new working condition stage vector, and returning to the execution of B2.

In one embodiment, after obtaining the condition type identification result, the method further includes:

acquiring fuel consumption rate information;

In one embodiment, further comprising:

In one embodiment, the determining the amount of worked earth based on the work environment electronic map and the working device trajectory of the earth moving machine includes:

In one embodiment, at least one of the following steps is further included:

It will be appreciated by those skilled in the art that 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 one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer-readable media include both permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer 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, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

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 one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. The method for identifying the working condition of the earthmoving machine is characterized by comprising the following steps:

acquiring basic data of earthmoving machinery;

2. The method for identifying working conditions of an earthmoving machine according to claim 1, wherein the construction process of the working condition stage identification model comprises the following steps:

3. The method for identifying working conditions of an earthmoving machine according to claim 1, wherein the construction process of the working condition type identification model comprises the following steps:

4. The earth moving machine condition identification method of claim 1, wherein the base data is a main pump pressure signal comprising a plurality of main pump pressure data within a first preset time range from a current time;

a2: normalizing the feature vector to obtain a normalized feature vector;

5. The method for identifying the working condition of the earthmoving machine according to claim 1, wherein the identifying the working condition type of the earthmoving machine by using a preset working condition type identification model according to the working condition stage identification result, to obtain a working condition type identification result, comprises:

6. The method for recognizing the working condition of the earth moving machine according to claim 1, further comprising, after the result of recognizing the type of working condition is obtained:

acquiring fuel consumption rate information;

7. The method of claim 6, further comprising:

8. The method of claim 7, wherein determining the amount of earth worked based on the electronic map of the work environment and the trajectory of the working device of the earth working machine comprises:

and obtaining the worked earthwork according to the state of each cube and the volume of each cube.

9. The method of claim 7, further comprising at least one of the following steps:

and calculating to obtain single earthwork excavation working quantity according to the worked earthwork quantity and the earthwork excavation cycle times, wherein the working condition information statistical result at least comprises the earthwork excavation cycle times.

10. An earthmoving machine operating condition recognition device, comprising:

11. A processor configured to perform the earthmoving machine condition identification method of any one of claims 1 to 9.

12. A machine-readable storage medium having instructions stored thereon, which when executed by a processor cause the processor to be configured to perform the earthmoving machine condition identification method of any one of claims 1 to 9.