This application relates to the technical field of construction machinery, in particular relates to a method and an apparatus for determining a working condition of an excavator.
Excavators play a very important role in the construction machinery industry and are widely used in construction, transportation, military industry and other industries. With the continuous development of infrastructure industry, the demand for excavators in all walks of life is further expanded.
However, the working conditions of an excavator are very complicated because the working contents of an excavator include excavation, crushing, leveling, etc. Different working conditions of the excavator correspond to different target parameters. If the target parameters do not match the actual working conditions of the excavator, the working efficiency of the excavator will be seriously adversely affected. Therefore, it is very important to determine the working conditions of an excavator.
At present, when determining the working condition of an excavator, it is usually done by obtaining an actual working flow rate of an excavator, generating flow rate detection data, and then comparing the flow rate detection data with the information of an expert database to determine the actual working condition of the excavator. However, the flow rate data in this method is not easy to acquire, and a model constructed by using an expert database does not have high universality.
This application provides a method and an apparatus for determining a working condition of an excavator, which are used for overcoming the defects that the data required for determining a working condition of an excavator is not easy to acquire and the universality of a determination model thereof is not high in the prior art, so as to realize the determination of the working condition of the excavator by using data that is easy to acquire and a model with high universality.
This application provides a method for determining a working condition of an excavator, which comprises the following steps:
According to the method for determining a working condition of an excavator provided by this application, the step of acquiring the real-time state parameter data of the excavator comprises:
According to the method for determining a working condition of an excavator provided by this application, after respectively inputting the real-time state parameter data of the excavator in each preset time segment into the excavator working condition determination model to obtain the corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model, the method further comprises:
According to the method for determining a working condition of an excavator provided by this application, after respectively inputting the real-time state parameter data of the excavator in each preset time segment into the excavator working condition determination model to obtain the corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model, the method further comprises:
According to the method for determining a working condition of an excavator provided by this application, after uploading the corresponding working condition type of the excavator in each preset time segment and the real-time state parameter data of the excavator in each preset time segment onto the cloud data platform, the method further comprises:
According to the method for determining a working condition of an excavator provided by this application, the real-time state parameter data comprises at least one of engine speed, pilot pressure, electric current, pump pressure and service time.
This application also provides an apparatus for determining a working condition of an excavator that comprises:
This application also provides an excavator that comprises the aforementioned apparatus for determining a working condition of an excavator, which is configured to determine the working condition type of the excavator.
This application also provides an electronic device that comprises a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the computer program, when executed by the processor, causes the processor to perform the steps of any one of the above-mentioned method for determining a working condition of an excavator.
This application also provides a non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, causes the processor to perform the steps of any one of the above-mentioned method for determining a working condition of an excavator.
The method and apparatus for determining a working condition of an excavator are provided in this application, wherein, acquiring real-time state parameter data of an excavator; inputting the real-time state parameter data into an excavator working condition determination model to obtain a working condition type of the excavator output by the excavator working condition determination model, and in the method and apparatus, the required data is easy to acquire, and a large amount of data is used when the excavator working condition determination model is being trained, so that the excavator working condition determination model has strong universality and makes it easy to realize the determination of the working condition of an excavator.
In order to explain the technical scheme in this application or in the prior art more clearly, the drawings needed in the description of the embodiments or the prior art will be briefly introduced below. Apparently, the drawings described below only represent some embodiments of this application. For a person with ordinary skill in the art, other drawings can be obtained according to these drawings without expenditure of creative labor.
In order to make the purpose, technical scheme and advantages of this application more clearly understood, the technical scheme in this application will be described clearly and completely with reference to the appended drawings in this application. Apparently, the described embodiments only represent part of the embodiments of this application, but not all of them. Based on the embodiments described in this application, all other embodiments obtainable by a person with ordinary skill in the art without expenditure of creative labor belong to the protection scope of this application.
At present, when identifying the working condition of an excavator, the flow rate data to be used is not easy to acquire, and a model constructed by using an expert database does not have high universality, therefore, this application provides a method for determining a working condition of an excavator.
Wherein, the excavator working condition determination model is obtained by performing training based on state parameter data samples carrying working condition type labels.
The execution host of the method for determining a working condition of an excavator provided in the embodiments of this application is a server, which can be a local server or a cloud server, and the local server can be a computer, a tablet computer, a smart phone, etc., which is not specifically limited in the embodiments of this application.
Firstly, step S1 is executed to acquire the real-time state parameter data of the excavator.
Wherein, the real-time state parameter data of excavator can comprise real-time state parameter data such as engine speed, pilot pressure, electric current, pump pressure and service time, etc.
In the embodiments of this application, the real-time state parameter data of the excavator can be collected through a CAN bus CAN (Controller Area Network) bus refers to a controller area network bus, which is a multi-host serial bus standard for connecting electronic control units. The data communication between the nodes of the CAN bus network is highly real-time, so various items of real-time state parameter data of the excavator can be collected directly through a CAN bus.
Since the real-time state parameter data of the excavator is collected through a CAN bus, there is no need to install sensors on the main valve or on the controller of the excavator, which reduces the cost for acquiring state parameter data and can also acquire the input data required by the excavator working condition determination model more conveniently.
Then step S2 is executed, wherein the acquired real-time state parameter data is input into the excavator working condition determination model to obtain the working condition type of the excavator output by the excavator working condition determination model.
Wherein, the excavator working condition determination model can be an existing open-source neural network model, such as a convolutional neural network model, a residual neural network model or a cyclic neural network model, etc., which is not specifically limited in the embodiments of this application.
The excavator working condition determination model is obtained by performing training based on state parameter data samples carrying working condition type labels. Specifically, the excavator working condition determination model can be obtained by performing training in the following way firstly, a large amount of excavator state parameter data samples are collected and labels are assigned to the state parameter data samples, that is, the state parameter data samples are made to carry working condition type labels. Then, the initial model is trained based on the state parameter data samples carrying the working condition type labels, so as to obtain the excavator working condition determination model.
Because different working condition types of the excavator correspond to different state parameter data, thus, by inputting the real-time state parameter data into the trained excavator working condition determination model, the working condition type of the excavator output by the excavator working condition determination model can be obtained. Wherein, the working condition types of the excavator include excavation, leveling, loading, slope trimming, and crushing.
When the excavator working condition determination model outputs the working condition type of the excavator, it can also generate a time period corresponding to this working condition type, and this time period can be represented by two timestamps indicating its starting time and ending time respectively. For example, the real-time state parameter data in a time period from 12:30 on Jun. 29, 2021 to 12:35 on Jun. 29, 2021 is input into the excavator working condition determination model, and the working condition type in this time period output by the excavator working condition determination model is obtained, then the starting time of the time period corresponding to the working condition type in this time period can be represented by the timestamp of 2021.06.30.12.30, and the ending time thereof can be represented by 2021.06.30.12.35. Timestamps can be represented in the form of unix timestamps. The timestamp can be used to verify whether the real-time state parameter data has been tampered with, that is, the timestamp represents a reliable time.
According to the method for determining a working condition of an excavator in the embodiments of this application, the working condition type of the excavator output by the excavator working condition determination model is obtained by acquiring the real-time state parameter data of the excavator and inputting the real-time state parameter data into the excavator working condition determination model, and in the method, the required data is easy to acquire, and a large amount of state parameter data samples are used when the excavator working condition determination model is being trained, so that the excavator working condition determination model has strong universality and makes it easy to realize the determination of the working condition of an excavator.
On the basis of the above-mentioned embodiments, in the method for determining the working condition of an excavator provided by the embodiments of this application, the step of acquiring the real-time state parameter data of the excavator specifically comprises: acquiring the real-time state parameter data of the excavator in each preset time segment in a target time period;
Correspondingly, the step of inputting the real-time state parameter data into the excavator working condition determination model to obtain the working condition type of the excavator output by the excavator working condition determination model specifically comprises:
Respectively inputting the real-time state parameter data of the excavator in each preset time segment into the excavator working condition determination model to obtain a corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model.
Specifically, in the embodiments of this application, it is needed to acquire the real-time state parameter data of the excavator in each preset time segment in a target time period. The target time period can be a working time period of the excavator. For example, if the excavator works 8 hours a day, the target time period can be these 8 hours when the excavator is working. Each preset time segment can be set according to actual needs, for example, the preset time segment can each be set to 5 minutes.
Accordingly, when the real-time state parameter data is input into the excavator working condition determination model to obtain the working condition type of the excavator output by the excavator working condition determination model, the real-time state parameter data of the excavator in each preset time segment is input into the excavator working condition determination model respectively to obtain the working condition type of the excavator corresponding to each preset time segment output by the excavator working condition determination model.
For example, in the above example, the target time period is the working time period of the excavator, and each preset time segment is 5 minutes. If the working time period of the excavator is from 8:00 am to 6:00 pm, the target time period is 10 hours. Inputting the real-time state parameter data in each 5 minutes within these 10 hours into the excavator working condition determination model respectively, and the corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model can be obtained. For example, the real-time state parameter data in a time segment from 9:00 to 9:05 can be input into the excavator working condition determination model, and the corresponding working condition type in this time segment from 9:00 to 9:05 can be obtained.
According to the method for determining a working condition of an excavator in the embodiments of this application, the real-time state parameter data of the excavator in each preset time segment is respectively input into the excavator working condition determination model, and the corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model is obtained, so that the working condition type of the excavator can be continuously determined during the working time range of the excavator, and therefore the determination of the working condition type of the excavator is made more accurate.
On the basis of the above embodiments, in the method for determining a working condition of an excavator provided by the embodiments of this application, after respectively inputting the real-time state parameter data of the excavator in each preset time segment into the excavator working condition determination model to obtain the corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model, the method further comprises:
Specifically, in the embodiments of this application, after obtaining the corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model, a ratio of working condition type corresponding to each preset time segment can be determined based on the corresponding working condition type in each preset time segment.
For example, if the target time period is 8 hours and each preset time segment is set to 10 minutes, it is needed to obtain the working condition type corresponding to each 10 minutes within the 8 hours, that is to say, a total of 48 working condition types will be obtained. Then, based on these 48 working condition types, the ratio of working condition type corresponding to each preset time segment is calculated. For example, among these 48 working condition types, 24 working condition types are excavation, so the ratio of working condition type for excavation is 50%.
In the embodiments of this application, based on the working condition type of the excavator corresponding to each preset time segment, the ratio of working condition type corresponding to each preset time segment is determined, which makes it convenient for a user to know the working conditions of the excavator during the target time period and also provides more reference data for the user.
On the basis of the above-mentioned embodiments, in the method for determining a working condition of an excavator provided by the embodiment of this application, after respectively inputting the real-time state parameter data of the excavator in each preset time segment into the excavator working condition determination model to obtain the corresponding working condition type of the excavator in each preset time segment output by the excavator working condition determination model, the method further comprises:
Specifically, in the embodiments of this application, after obtaining the working condition type of the excavator corresponding to each preset time segment output by the excavator working condition determination model, it is also needed to upload the working condition type of the excavator corresponding to each preset time segment and the real-time state parameter data of the excavator in each preset time segment onto a cloud data platform.
Wherein, the working condition type of the excavator corresponding to each preset time segment and the real-time state parameter data of the excavator in each preset time segment can be uploaded onto the cloud data platform by means of a transmission mode of the Fourth-Generation Mobile Communication Technology or the Fifth-Generation Mobile Communication Technology.
The Fourth-Generation Mobile Communication Technology (4G) is an upgrade based on the Third-Generation Mobile Communication Technology. By means of orthogonal frequency division multiplexing (OFDM), Multi Input Multi Output (MIMO), smart antenna and other technologies, the data transmission rate is faster than that of 3G.
The Fifth-Generation Mobile Communication Technology (5G) is a new generation broadband mobile communication technology with the characteristics of high speed, low latency and broad connection, and it is the network infrastructure to realize the interconnection among human, machine, and objects. There are three application scenarios of 5G technology, namely, enhanced mobile broadband, ultra-high reliability and low latency communication, and massive machine-type communication. Using 5G technology for data transmission will make the data transmission rate faster and have higher equipment connection capability.
After uploading the working condition type of the excavator corresponding to each preset time segment and the real-time state parameter data of the excavator in each preset time segment onto the cloud data platform, the cloud data platform can also be made to perform aggregate calculation on the real-time state parameter data of the excavator in each preset time segment to obtain a target state parameter dataset of the excavator in each preset time segment.
Because the real-time state parameter data in each preset time segment is collected through a CAN bus, each preset time segment would contain many pieces of real-time state parameter data. By means of aggregate calculation, multiple pieces of real-time state parameter data within each preset time segment can be aggregated into one set of state parameter data, that is, the target state parameter dataset in each preset time segment.
After obtaining the target state parameter dataset, the working condition type of the excavator corresponding to each preset time segment and the target state parameter dataset of the excavator in each preset time segment can be stored into a cloud data warehouse. Wherein, the cloud data warehouse can be a cloud database, and the type of the cloud database can be selected according to actual needs, which is not specifically limited in the embodiments of this application.
The method for determining a working condition of an excavator in the embodiments of this application uploads the working condition type of the excavator corresponding to each preset time segment and the real-time state parameter data of the excavator in each preset time segment onto the cloud data platform, and then performs aggregate calculation on the real-time state parameter data of the excavator in each preset time segment to obtain the target state parameter dataset of the excavator in each preset time segment. And the working condition type of the excavator corresponding to each preset time segment and the target state parameter dataset of the excavator in each preset time segment are stored into the cloud data warehouse, so it is made convenient for working personnel to query the working condition type and real-time state parameter data of the excavator online, and also provides data support for working personnel to analyze the relationship between the real-time state parameter data and the working condition types during the life cycle of the excavator Moreover, the cloud data platform has strong scalability, and can store more data, thereby reducing the storage cost for data.
On the basis of the above embodiments, the method for determining a working condition of an excavator provided by the embodiments of this application further comprises:
Specifically, in the embodiment of this application, after obtaining the working condition type, real-time state parameter data of the excavator and the preset time segment corresponding to the working condition type output by the excavator working condition determination model, the working condition type, real-time state parameter data of the excavator and the preset time segment corresponding to the working condition type can also be stored into a local storage module.
Wherein, the local storage module can be a local database. The local database can be relational database, non-relational database and key-value database. For example, the relational database can be MySQL. MariaDB, etc., the non-relational database can be BigTable, Cassandra, etc., and the key-value database can be Apache Cassandra etc. Accordingly, the storage format of the working condition type, real-time state parameter data and the preset time segment corresponding to the working condition type need to correspond to the database that is being used. The embodiments of the present application do not specifically limit the type of the database.
In the embodiments of this application, when the working condition type, the real-time state parameter data and the preset time segment corresponding to the working condition type are being stored into the local storage module, the working condition type, the real-time state parameter data and the preset time segment corresponding to the working condition type can be stored in accordance with the sequence of each preset time segment, and the data in the local storage module can be overwritten according to a preset cyclic period, that is, the storage-keeping time of the data in the local storage module is the preset cyclic period. Wherein, the preset cyclic period can be set according to actual needs, and the embodiments of this application do not specifically limit this.
For example, when the preset cyclic period is 30 days, if a working condition type, real-time state parameter data and a preset time segment corresponding to the working condition type are stored into the local storage module on date A, then, after 30 days, the working condition type, real-time state parameter data and the preset time segment corresponding to the working condition type that were stored on date A would be overwritten by the newly stored working condition type, real-time state parameter data and a preset time segment corresponding to the newly stored working condition type.
In the embodiments of this application, the working condition type, the real-time state parameter data and the preset time segment corresponding to the working condition type are stored into the local storage module in accordance with the sequence of each preset time segment, and the working condition type, the real-time state parameter data and the preset time segment corresponding to the working condition type in the local storage module are overwritten by the newly stored working condition type, the real-time state parameter data and the preset time segment corresponding to the newly stored working condition type according to the preset cyclic period. Therefore, it is convenient for working personnel to check the working condition of the excavator locally, and when there is a problem in transmitting the working condition type, real-time state parameter data and the preset time segment corresponding to the working condition type onto the cloud data platform, the local storage module can provide data support and strengthen the data security, and by overwriting the working condition type, real-time state parameter data and the preset time segment corresponding to the working condition type in the local storage module according to the preset cyclic period, the data maintenance difficulty and memory requirements are reduced for the local storage module.
On the basis of the above-mentioned embodiments, in the method for determining a working condition of an excavator provided by the embodiments of this application, after uploading the corresponding working condition type of the excavator in each preset time segment and the real-time state parameter data of the excavator in each preset time segment onto the cloud data platform, the method further comprises:
Specifically, in the embodiments of this application, the performance of the excavator will degrade after reaching a certain service time, and at this time, all the real-time state parameter data of the excavator under the same working condition will change, which will cause the real-time state parameter data to drift. Due to the drift of the real-time state parameter data of the excavator, the accuracy of the determination result of the original excavator working condition determination model will decrease. Therefore, in order to make the excavator working condition determination model be more in line with the actual situation of the excavator, the excavator working condition determination model can be retrained for a second time by using the corresponding working condition types of the excavator in each preset time segment and the target state parameter dataset of the excavator in each preset time segment.
After the retraining is completed, a secondarily retrained excavator working condition determination model can be obtained. Based on the secondarily retrained excavator working condition determination model, the excavator working condition determination model is updated, so as to obtain an excavator working condition determination model that is more in line with the actual situation of the excavator. Wherein, the excavator working condition determination model can be retrained according to a target frequency, and the target frequency can be set according to actual needs, for example, it may be once every 90 days, etc., which is not specifically limited in the embodiments of this application.
When the working condition type of the excavator corresponding to each preset time segment and the target state parameter dataset of the excavator in each preset time segment are used for secondary retraining of the excavator working condition determination model, the accumulated working condition types of the excavator corresponding to the respective preset time segments and the accumulated target state parameter datasets of the excavator in the respective preset time segments are used. For example, if the excavator working condition determination model is retrained once every 90 days, when the excavator working condition determination model is retrained for the first time, the working condition types of the excavator corresponding to the respective preset time segments and the target state parameter datasets of the excavator in the respective preset time segments that would be used are the working condition types of the excavator corresponding to the respective preset time segments and the target state parameter datasets of the excavator in the respective preset time segments that have been accumulated and stored in the cloud data warehouse during the first 90 days. Similarly, when the excavator working condition determination model is updated by retraining for the second time, the working condition types of the excavator corresponding to the respective preset time segments and the target state parameter datasets of the excavator in the respective preset time segments that have been accumulated and stored in the cloud data warehouse during the first 180 days would be used.
According to the method for determining a working condition of an excavator in the embodiments of this application, the excavator working condition determination model is retrained and updated based on the working condition types of the excavator corresponding to the respective preset time segments and the target state parameter datasets of the excavator in the respective preset time segments, so that the instability of the excavator working condition determination model caused by the aging or performance degradation of the excavator is avoided, and the determining accuracy of the excavator working condition determination model is improved.
When determining a working condition of an excavator, the following steps need to be performed:
On the basis of the above embodiments, in the apparatus for determining a working condition of an excavator provided by the embodiments of this application, the parameter data acquisition module specifically comprises:
Correspondingly, the excavator working condition determining module specifically comprises:
On the basis of the above embodiments, the apparatus for determining a working condition of an excavator provided by the embodiments of this application further comprises:
On the basis of the above embodiments, the apparatus for determining a working condition of an excavator provided by the embodiments of this application further comprises:
On the basis of the above embodiments, the apparatus for determining a working condition of an excavator provided by the embodiments of this application further comprises:
On the basis of the above embodiments, as acquired by the apparatus for determining a working condition of an excavator provided by the embodiments of this application, the real-time state parameter data comprises at least one of engine speed, pilot pressure, electric current, pump pressure and service time.
Specifically, the functions of the respective modules in the apparatus for determining a working condition of an excavator provided by the embodiments of this application are in one-to-one correspondence with the operation flow of the respective steps in the above-mentioned method embodiments, and the achieved effects are also consistent. Referring to the above-mentioned embodiments for details, and the details thereof will not be repeated in the embodiments of this application.
This application also provides an excavator that comprises the aforementioned apparatus for determining a working condition of an excavator, which is configured to determine the working condition type of the excavator.
In addition, the above-mentioned logical instructions in the memory 430 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical scheme of this application in its essence, or those aspects thereof that make a contribution to the prior art, or part of such a technical scheme, can be embodied in the form of a software product, which is stored in a storage medium and comprises a plurality of instructions to cause a computer apparatus (which can be a personal computer, a server, a network apparatus, etc.) to execute all or part of the steps of the method described in various embodiments of this application. The aforementioned storage medium comprises U disk (flash drive), mobile hard disk, Read-Only Memory (ROM). Random Access Memory (RAM), magnetic disk or optical disk and other media that can store program codes.
In another aspect, this application also provides a computer program product, which comprises a computer program stored on a non-transitory computer-readable storage medium, and the computer program comprises program instructions, and when the program instructions are executed by a computer, the computer is enabled to execute the method for determining a working condition of an excavator provided by the above method embodiments, and the method comprises the following steps: acquiring real-time state parameter data of an excavator; inputting the real-time state parameter data into an excavator working condition determination model to obtain a working condition type of the excavator output by the excavator working condition determination model; wherein, the excavator working condition determination model is obtained by performing training based on state parameter data samples carrying working condition type labels.
In another aspect, this application also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, causes the processor to execute the method for determining a working condition of an excavator provided by the above method embodiments, and the method comprises the following steps: acquiring real-time state parameter data of an excavator; inputting the real-time state parameter data into an excavator working condition determination model to obtain a working condition type of the excavator output by the excavator working condition determination model; wherein, the excavator working condition determination model is obtained by performing training based on state parameter data samples carrying working condition type labels.
The apparatus embodiments described above are only illustrative, in which the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located all in one place or may be distributed at multiple network units. Some or all of the modules thereof may be selected according to actual needs to achieve the purpose of the technical solutions of the embodiments. A person with ordinary skill in the art can understand and implement these technical solutions without expenditure of creative labor.
From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a necessary general-purpose hardware platform, and of course, it can also be realized by hardware. Based on this understanding, the essence of the above technical schemes or the part thereof that has contributed to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and comprises a plurality of instructions for causing a computer apparatus (which can be a personal computer, a server, or a network apparatus, etc.) to execute the methods described in various embodiments or some parts of the embodiments.
Finally, it should be noted that, the above embodiments are only used to illustrate the technical scheme of this application, but not intended to limit it; Although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that they can still modify the technical solutions described in the foregoing embodiments or replace some technical features thereof with equivalents; Nevertheless, these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of this application.
Number | Date | Country | Kind |
---|---|---|---|
202110802807.7 | Jul 2021 | CN | national |
This application is the U.S. National Stage of PCT/CN2022/097336 filed on Jun. 7, 2022, which claims the priority of Chinese Patent Application No. 202110802807.7, filed on Jul. 15, 2021, entitled “Method and apparatus for determining working condition of excavator”, which is incorporated herein by reference in its entirety.
Filing Document | Filing Date | Country | Kind |
---|---|---|---|
PCT/CN2022/097336 | 6/7/2022 | WO |