WO2023284443A1 - 挖掘机工况判定方法及装置 - Google Patents
挖掘机工况判定方法及装置 Download PDFInfo
- Publication number
- WO2023284443A1 WO2023284443A1 PCT/CN2022/097336 CN2022097336W WO2023284443A1 WO 2023284443 A1 WO2023284443 A1 WO 2023284443A1 CN 2022097336 W CN2022097336 W CN 2022097336W WO 2023284443 A1 WO2023284443 A1 WO 2023284443A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- excavator
- working condition
- time period
- parameter data
- state parameter
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000004590 computer program Methods 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 238000010295 mobile communication Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000009412 basement excavation Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
- E02F—DREDGING; SOIL-SHIFTING
- E02F9/00—Component parts of dredgers or soil-shifting machines, not restricted to one of the kinds covered by groups E02F3/00 - E02F7/00
- E02F9/20—Drives; Control devices
Definitions
- the present application relates to the technical field of engineering machinery, in particular to a method and device for judging the working condition of an excavator.
- the working conditions of the excavator are very complicated. 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 affected. Therefore, it is very important to judge the working conditions of the excavator.
- This application provides a method and device for judging the working condition of an excavator, which is used to solve the defects in the prior art that the data required for judging the working condition of the excavator are not easy to obtain and the generality of the judgment model is not high, so as to realize the use of easily obtained data and universal
- the highly reliable model realizes the judgment of the working condition of the excavator.
- the present application provides a method for judging the working condition of an excavator, including:
- the excavator working condition judgment model is trained based on state parameter data samples carrying working condition type labels.
- the acquiring the real-time state parameter data of the excavator specifically includes: acquiring the real-time state parameter data of the excavator within each preset time period in the target time period;
- the inputting the real-time state parameter data into the excavator working condition judgment model to obtain the working condition type of the excavator output by the excavator working condition judging model specifically includes:
- the real-time state parameter data of the excavator within each preset time period are respectively input into the working condition judging model of the excavator to obtain the excavator
- the corresponding working condition type of the excavator output by the working condition determination model in each preset time period and then also include:
- the proportion of the working condition type corresponding to each preset time period is determined.
- the real-time state parameter data of the excavator in each preset time period are respectively input into the judging model of the working condition of the excavator, and the working condition of the excavator is obtained.
- the corresponding working condition type of the excavator output by the condition determination model in each preset time period and then also include:
- the type of working condition corresponding to the excavator within each preset time period and the real-time state parameter data of the excavator within each preset time period Upload to the cloud data platform, and then include:
- the second training is performed on the excavator working condition judgment model to obtain The excavator operating condition judgment model after the second training;
- the excavator operating condition determination model is updated.
- the real-time state parameter data includes at least one of engine speed, pilot pressure, current, pump pressure and service time.
- the present application also provides a device for judging the working condition of an excavator, including:
- the parameter data obtaining module is used to obtain the real-time state parameter data of the excavator
- An excavator working condition judgment module configured to input the real-time state parameter data into an excavator working condition judging model, and obtain the working condition type of the excavator output by the excavator working condition judging model;
- the excavator working condition judgment model is trained based on state parameter data samples carrying working condition type labels.
- the present application also provides an excavator, including: the device for determining the working condition of the excavator as described above, configured to determine the type of the working condition of the excavator.
- the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. The steps of the situation determination method.
- the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any method for determining the working condition of the excavator described above are implemented.
- the excavator operating condition determination method and device provided in this application obtain the excavator operating condition determination model output by obtaining the real-time state parameter data of the excavator and inputting the real-time state parameter data into the excavator operating condition determination model.
- the type of working conditions, the data required by this method is easy to obtain, and a large amount of data is used when training the excavator working condition judgment model, so the universality of the excavator working condition judgment model is strong, making it easy to determine the excavator working condition easy to accomplish.
- Fig. 1 is a schematic flow chart of the method for judging the working condition of the excavator provided by the present application
- Fig. 2 is the specific flow diagram of the method for judging the working condition of the excavator provided by the present application
- Fig. 3 is a structural schematic diagram of an excavator working condition judging device provided by the present application.
- FIG. 4 is a schematic structural diagram of an electronic device provided by the present application.
- the present application provides a method for judging the working condition of an excavator.
- Fig. 1 is a schematic flow chart of the method for judging the working condition of the excavator provided by the present application. As shown in Fig. 1, the method includes:
- the excavator working condition judgment model is trained based on state parameter data samples with working condition type labels.
- the method for judging the working condition of an excavator provided in the embodiment of the present application is executed by a server.
- the server may be a local server or a cloud server.
- the local server may specifically be a computer, a tablet computer, or a smart phone. This is not specifically limited in the example.
- step S1 is executed to obtain the real-time state parameter data of the excavator.
- the real-time state parameter data of the excavator can be collected through the CAN bus.
- CAN Controller Area Network, CAN
- controller area network which is a multi-host serial bus standard used to connect electronic control units.
- the data communication between each node of the CAN bus network has strong real-time performance, so various real-time state parameter data of the excavator can be collected directly through the CAN bus.
- step S2 is executed to input the obtained real-time state parameter data into the excavator working condition judgment model to obtain the excavator working condition type output by the excavator working condition judgment model.
- the excavator working condition judgment model is trained based on state parameter data samples with working condition type labels.
- the excavator working condition judgment model can be obtained by training in the following way: First, collect a large number of state parameter data samples of the excavator and mark them on the state parameter data samples, that is, make the state parameter data samples carry the working condition type label. Then, the initial model is trained based on the state parameter data samples carrying the working condition type label, so as to obtain the excavator working condition judgment model.
- the real-time state parameter data is input into the trained excavator working condition judgment model, and the output of the excavator working condition judgment model can be obtained.
- Condition type the types of working conditions of the excavator include excavation, leveling, loading, slope repair and crushing.
- a time period corresponding to this working condition type can also be generated, and two timestamps can be used for this time period to represent its start time and end time respectively.
- the working condition type in this time period, the start 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 end time can be represented by 2021.06.30.12.35 This timestamp represents.
- the representation of the timestamp can be a unix timestamp.
- 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.
- the method for judging the working condition of the excavator in the embodiment of the present application obtains the real-time state parameter data of the excavator and inputs the real-time state parameter data into the working condition judging model of the excavator to obtain the output of the working condition judging model of the excavator.
- the type of working conditions, the data required by this method are easy to obtain, and a large number of state parameter data samples are used when training the excavator working condition judgment model, so the generality of the excavator working condition judgment model is strong, which makes it possible to determine the excavator working condition. becomes easy to implement.
- the inputting the real-time state parameter data into the excavator working condition judgment model to obtain the working condition type of the excavator output by the excavator working condition judging model specifically includes:
- the target time period may be the working time period of the excavator, for example, if the excavator works 8 hours a day, then the target time period may be the 8 working hours of the excavator.
- Each preset time period can be set according to actual needs, for example, the preset time period can be set to 5 minutes.
- the real-time state parameter data is input into the excavator working condition judgment model, and the excavator working condition type output by the excavator working condition judgment model is obtained by inputting the real-time state parameter data of the excavator in each preset time period respectively To the excavator working condition determination model, the corresponding working condition types of the excavator in each preset time period output by the excavator working condition determination model are obtained.
- the real-time state parameter data of the excavator in each preset time period are respectively input into the working condition judging model of the excavator, and the output of the working condition judging model of the excavator is obtained.
- the type of working condition corresponding to each preset time period can continuously judge the working condition type of the excavator within the working time range of the excavator, so that the determination of the working condition type of the excavator is more accurate.
- the method for judging the working condition of the excavator includes inputting the real-time state parameter data of the excavator in each preset time period into the judging working condition of the excavator respectively. model to obtain the corresponding working condition type of the excavator in each preset time period output by the excavator working condition determination model, and then further include:
- the proportion of the working condition type corresponding to each preset time period is determined.
- each preset time period is set to 10 minutes
- it is necessary to obtain the working condition types corresponding to each 10 minutes within 8 hours that is to say, a total of 48 working condition types will be obtained.
- calculate the proportion of working condition types corresponding to each preset time period For example, among the 48 working condition types, 24 working condition types are excavation, and the proportion of the working condition type of excavation is 50%.
- the proportion of the working condition type corresponding to each preset time period is determined, so that the user can understand the working conditions of the excavator in the target time period, It also provides more data references for users.
- the real-time state parameter data of the excavator within each preset time period are respectively input into the working condition judging model of the excavator , to obtain the corresponding working condition type of the excavator output by the excavator working condition determination model in each preset time period, and then include:
- the excavator working condition determination model After obtaining the corresponding working condition types of the excavator in each preset time period output by the excavator working condition determination model, it is also necessary to classify the corresponding working condition types of the excavator in each preset time period.
- the type of condition and the real-time status parameter data of the excavator within each preset time period are uploaded to the cloud data platform.
- the type of working condition corresponding to the excavator in each preset time period and the real-time state parameter data of the excavator in each preset time period can be transmitted through the fourth-generation mobile communication technology or the fifth-generation mobile communication technology. Upload to the cloud data platform.
- the fourth generation mobile communication technology (4th Generation Mobile Communication Technology, 4G) is an upgrade on the third generation mobile communication technology, through Orthogonal Frequency Division Multiplexing (OFDM), multiple input multiple output ( Multi Input Multi Output, MIMO), smart antenna and other technologies make the data transmission rate faster than 3G.
- OFDM Orthogonal Frequency Division Multiplexing
- MIMO multiple input multiple output
- smart antenna smart antenna and other technologies make the data transmission rate faster than 3G.
- the fifth generation mobile communication technology (5th Generation Mobile Communication Technology, 5G) is a new generation of broadband mobile communication technology with the characteristics of high speed, low delay and large connection.
- 5G technology has three major application scenarios, 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 Connectivity.
- the cloud data platform After uploading the corresponding working condition type of the excavator in each preset time period and the real-time state parameter data of the excavator in each preset time period to the cloud data platform, the cloud data platform can also make the excavator in each preset time period
- the real-time state parameter data in the preset time period is aggregated and calculated to obtain the target state parameter data of the excavator in each preset time period.
- each preset time period Since the real-time state parameter data in each preset time period is collected through the CAN bus, each preset time period will contain a lot of real-time state parameter data. Through aggregation calculation, the data in each preset time period can be Multiple pieces of real-time state parameter data are aggregated into one piece of state parameter data, that is, target state parameter data within each preset time period.
- the cloud data warehouse may be a cloud database, and the type of the cloud database may be selected according to actual needs, which is not specifically limited in this embodiment of the present application.
- the corresponding working condition type of the excavator in each preset time period and the real-time state parameter data of the excavator in each preset time period are uploaded to the cloud data platform, and then The real-time state parameter data of the excavator in each preset time period is aggregated and calculated to obtain the target state parameter data of the excavator in each preset time period, and the corresponding The type of working condition and the target state parameter data of the excavator in each preset time period are stored in the cloud data warehouse, which facilitates the staff to query the working condition type and real-time state parameter data of the excavator online, and also provides the staff with analysis and mining
- the data support for the relationship between the real-time state parameter data and the type of working conditions within the life cycle of the machine, and the cloud data platform is highly scalable, can store more data, and reduce data storage costs.
- the method for judging the working condition of the excavator provided in the embodiments of the present application further includes:
- the type of working condition, the real-time state parameter data and the preset time period corresponding to the type of working condition are stored in a local storage module.
- the working condition of the excavator after obtaining the working condition type of the excavator output by the working condition determination model of the excavator, the real-time state parameter data and the preset time period corresponding to the working condition type, the working condition of the excavator can also be type, real-time state parameter data, and the preset time period corresponding to the type of working condition to the local storage module.
- the local storage module may be a local database.
- Local databases can be relational databases, non-relational databases, and key-value databases.
- relational databases can be MySQL, MariaDB, etc.
- non-relational databases can be BigTable, Cassandra, etc.
- key-value databases can be Apache Cassandra.
- the storage format of the preset time period corresponding to the type, real-time state parameter data, and working condition type needs to correspond to the database used.
- the embodiment of the present application does not specifically limit the type of the database.
- the working condition type, real-time state parameter data, and the preset time period corresponding to the working condition type in the local storage module when storing the working condition type, real-time state parameter data, and the preset time period corresponding to the working condition type in the local storage module, the working condition type, real-time state parameter data can be sorted according to the order of each preset time period And the preset time period corresponding to the working condition type is stored, and the data in the local storage module can be overwritten according to the preset cycle, that is, the storage time of the data in the local storage module is the preset cycle.
- the preset period may be set according to actual needs, which is not specifically limited in this embodiment of the present application.
- the preset period is 30 days
- the working condition type, real-time state parameter data and the preset time period corresponding to the working condition type are stored in the local storage module on date A, then after 30 days, the data stored in date A
- the working condition type, real-time state parameter data and the preset time period corresponding to the working condition type will be overwritten by the newly stored working condition type, real-time state parameter data and the preset time period corresponding to the working condition type.
- the working condition type, the real-time state parameter data, and the preset time period corresponding to the working condition type are stored in the local storage module in sequence according to each preset time period, and the newly stored working condition is used according to the preset cycle type, real-time state parameter data and the preset time period corresponding to the working condition type will cover the working condition type, real-time state parameter data and the preset time period corresponding to the working condition type in the local storage module, so that the staff can view the excavator locally Working conditions, and when there is a problem with the transmission of the working condition type, real-time state parameter data, and the preset time period corresponding to the working condition type to the cloud data platform, data support can be provided, which strengthens the data security.
- Periodically overwrite the working condition type, real-time state parameter data and the preset time period corresponding to the working condition type in the local storage module which reduces the difficulty of data maintenance and memory requirements of the local storage module.
- the method for judging the working condition of the excavator provided by the embodiment of the present application, the type of working condition corresponding to the excavator within each preset time period and the type of working condition of the excavator within each preset time period
- the real-time status parameter data in the segment is uploaded to the cloud data platform, and then includes:
- the second training is performed on the excavator working condition judgment model to obtain The excavator operating condition judgment model after the second training;
- the excavator operating condition determination model is updated.
- the mining In order to make the excavator working condition judgment model more in line with the actual situation of the excavator, the mining The type of working condition corresponding to the excavator in each preset time period and the target state parameter data of the excavator in each preset time period perform secondary training on the excavator working condition determination model.
- the excavator working condition judgment model after the second training can be obtained. Based on the excavator working condition judgment model after the secondary training, the excavator working condition judgment model is updated, and the excavator working condition judgment model that is more in line with the actual situation of the excavator is obtained.
- the excavator operating condition determination model can be trained twice according to the target frequency, and the target frequency can be set according to actual needs, for example, 90 days, etc., which is not specifically limited in this embodiment of the present application.
- the corresponding working condition type of the excavator in each preset time period and the target state parameter data of the excavator in each preset time period are as follows:
- the type of working condition corresponding to the excavator in each preset time period and the target state parameter data of the excavator in each preset time period are accumulated and stored in the cloud data warehouse in the first 90 days.
- the method for judging the working condition of the excavator in the embodiment of the present application determines the working condition of the excavator based on the corresponding working condition type of the excavator in each preset time period and the target state parameter data of the excavator in each preset time period
- the model is trained and updated twice, which avoids the instability of the excavator's working condition judgment model caused by the excavator's aging or performance degradation, and improves the judgment accuracy of the excavator's working condition judgment model.
- Fig. 2 is the specific flowchart diagram of the method for judging the working conditions of excavators provided by the present application.
- the rectangular frame with solid line represents the edge computing device for judging the working conditions
- the computing device for judging the working conditions includes a CAN data acquisition module, an excavator Machine working condition judgment module, data local storage module and data remote transmission module.
- the excavator operating condition judgment module is represented by the content in the dashed box in Fig. 2 .
- CAN data acquisition module uses the CAN data acquisition module to collect the real-time state parameter data of the excavator through the CAN bus, such as real-time state parameter data such as engine speed, pilot pressure, current, pump pressure and service time;
- the real-time state parameter data of the excavator in each preset time period is aggregated and calculated to obtain the target state parameter data, and the target state parameter data is corresponding to the excavator in each preset time period
- the working condition type of the excavator is stored in the cloud data warehouse, and the excavator working condition judgment model is trained based on the target state parameter data and the corresponding working condition type of the excavator in each preset time period, and the excavator working condition is determined based on the training results.
- the condition judgment model is continuously updated to make the excavator working condition judgment model more in line with the actual situation of the excavator.
- Fig. 3 is a schematic structural diagram of the device for judging the working condition of the excavator provided by the present application. As shown in Figure 3, the device includes:
- Parameter data obtaining module 301 is used for obtaining the real-time state parameter data of excavator
- Excavator operating condition determination module 302 configured to input the real-time state parameter data into the excavator operating condition determination model, and obtain the excavator operating condition type output by the excavator operating condition determination model;
- the excavator working condition judgment model is trained based on state parameter data samples carrying working condition type labels.
- the parameter data acquisition module specifically includes:
- the state parameter data acquisition sub-module is used to obtain the real-time state parameter data of the excavator in each preset time period in the target time period;
- the said excavator operating condition determination module specifically includes:
- the excavator working condition judgment sub-module is used to input the real-time state parameter data of the excavator in each preset time period into the excavator working condition judgment model to obtain the output of the excavator working condition judgment model The type of working condition corresponding to the excavator in each preset time period.
- the device for judging the working condition of the excavator provided in the embodiments of the present application further includes:
- the proportion calculation module is used to determine the proportion of the working condition type corresponding to each preset time period based on the corresponding working condition type of the excavator in each preset time period.
- the device for judging the working condition of the excavator provided in the embodiments of the present application further includes:
- the cloud module is used to upload the corresponding working condition type of the excavator in each preset time period and the real-time state parameter data of the excavator in each preset time period to the cloud data platform, so that the cloud
- the data platform aggregates and calculates the real-time state parameter data of the excavator in each preset time period, obtains the target state parameter data of the excavator in each preset time period, and calculates the excavator in each preset time period.
- the corresponding working condition type in each preset time period and the target state parameter data of the excavator in each preset time period are stored in the cloud data warehouse.
- the device for judging the working condition of the excavator provided in the embodiments of the present application further includes:
- a model update module configured to determine the working condition model of the excavator based on the corresponding working condition type of the excavator in each preset time period and the target state parameter data of the excavator in each preset time period Carry out secondary training to obtain the excavator working condition judgment model after the secondary training;
- the excavator operating condition determination model is updated.
- the embodiment of the present application provides an excavator operating condition determination device, wherein the real-time state parameter data includes at least one of engine speed, pilot pressure, current, pump pressure, and service time.
- each module in the excavator operating condition determination device provided in the embodiment of the present application is in one-to-one correspondence with the operation process of each step in the above-mentioned method embodiment, and the achieved effect is also consistent.
- this will not be repeated in this embodiment of the application.
- the present application also provides an excavator, including the above-mentioned device for judging the working condition of the excavator, for judging the type of the working condition of the excavator.
- FIG. 4 illustrates a schematic diagram of the physical structure of an electronic device.
- the electronic device may include: a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440, Wherein, the processor 410 , the communication interface 420 , and the memory 430 communicate with each other through the communication bus 440 .
- the processor 410 can call the logic instructions in the memory 430 to execute the method for judging the working condition of the excavator.
- the method includes: acquiring real-time state parameter data of the excavator; inputting the real-time state parameter data into the model for judging the working condition of the excavator, The working condition type of the excavator output by the excavator working condition determination model is obtained; wherein, the excavator working condition determination model is trained based on state parameter data samples carrying a working condition type label.
- the above logic instructions in the memory 430 may be implemented in the form of software function units and be stored in a computer-readable storage medium when sold or used as an independent product.
- the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
- the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .
- the present application also provides a computer program product
- the computer program product includes a computer program stored on a non-transitory computer-readable storage medium
- the computer program includes program instructions, and when the program instructions are executed by a computer During execution, the computer can execute the method for judging the working condition of the excavator provided by the above methods.
- the method includes: obtaining the real-time state parameter data of the excavator; inputting the real-time state parameter data into the working condition judgment model of the excavator to obtain the The working condition type of the excavator output by the working condition determination model of the excavator; wherein, the working condition determination model of the excavator is obtained by training based on the state parameter data samples carrying the working condition type label.
- the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it is implemented to perform the methods for determining the working conditions of excavators provided above, the method Including: obtaining real-time state parameter data of the excavator; inputting the real-time state parameter data into the excavator working condition judgment model, and obtaining the working condition type of the excavator output by the excavator working condition judgment model; wherein, the The above excavator working condition judgment model is trained based on state parameter data samples with working condition type labels.
- the device embodiments described above are only illustrative, and 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 in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative effort.
- each implementation can be implemented by means of software plus a necessary general hardware platform, and of course also by hardware.
- the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.
Abstract
一种挖掘机工况判定方法及装置，获取挖掘机的实时状态参数数据；将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到，该方法所需的数据易于获取，且在训练挖掘机工况判定模型时，使用了大量的数据，因此挖掘机工况判定模型的通用性强，使得判定挖掘机工况变得容易实现。
Description
相关申请的交叉引用
本申请要求于2021年7月15日提交的申请号为202110802807.7，发明名称为“挖掘机工况判定方法及装置”的中国专利申请的优先权，其通过引用方式全部并入本文。
本申请涉及工程机械技术领域，尤其涉及一种挖掘机工况判定方法及装置。
挖掘机在工程机械行业扮演着非常重要的角色，被广泛应用于建筑、交通、军工等行业，随着基建行业的不断发展，各行各业对挖掘机的需求也进一步扩大。
但是由于挖掘机的作业内容包括挖掘、破碎、平地等，所以挖掘机工况十分复杂。挖掘机不同的工况对应着不同的目标参数，如果目标参数与挖掘机的实际工况不匹配会严重影响挖掘机的工作效率，因此，对挖掘机的工况进行判定十分重要。
目前在对挖掘机进行工况判定时，通常是获取挖掘机的实际工作流量，生成流量检测数据，然后将流量检测数据与专家库信息比较，确定挖掘机的实际工况，但这种方法中的流量数据不易获取，并且专家库构建的模型通用性也不高。
发明内容
本申请提供一种挖掘机工况判定方法及装置，用以解决现有技术中挖掘机工况判定所需的数据不易获取并且判定模型的通用性不高缺陷，实现使用容易获取的数据和通用性高的模型实现挖掘机工况的判定。
本申请提供一种挖掘机工况判定方法，包括：
获取挖掘机的实时状态参数数据；
将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；
其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
根据本申请提供的一种挖掘机工况判定方法，所述获取挖掘机的实时状态参数数据，具体包括：获取所述挖掘机在目标时间段中各预设时间段内的实时状态参数数据；
相应地，所述将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型，具体包括：
将所述挖掘机在各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型。
根据本申请提供的一种挖掘机工况判定方法，所述将所述挖掘机在各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型，之后还包括：
基于所述挖掘机在各预设时间段内对应的工况类型，确定各预设时间段对应的工况类型占比。
根据本申请提供的一种挖掘机工况判定方法，所述将所述挖掘机各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型，之后还包括：
将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台，以使所述云端数据平台对所述挖掘机在每一预设时间段内的实时状态参数数据进行聚合计算，得到所述挖掘机在每一预设时间段内的目标状态参数数据，并将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据存储至云端数据仓库。
根据本申请提供的一种挖掘机工况判定方法，所述将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的实时 状态参数数据上传至云端数据平台，之后还包括：
基于所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据，对所述挖掘机工况判定模型进行二次训练，得到二次训练后的挖掘机工况判定模型；
基于二次训练后的挖掘机工况判定模型，对所述挖掘机工况判定模型进行更新。
根据本申请提供的一种挖掘机工况判定方法，所述实时状态参数数据包括发动机转速、先导压力、电流、泵压以及使用时长中的至少一个。
本申请还提供一种挖掘机工况判定装置，包括：
参数数据获取模块，用于获取挖掘机的实时状态参数数据；
挖掘机工况判定模块，用于将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；
其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
本申请还提供一种挖掘机，包括：如上所述的挖掘机工况判定装置，用于对挖掘机工况类型进行判定。
本申请还提供一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如上述任一种所述挖掘机工况判定方法的步骤。
本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如上述任一种所述挖掘机工况判定方法的步骤。
本申请提供的挖掘机工况判定方法及装置，通过获取挖掘机的实时状态参数数据，并将实时状态参数数据输入至挖掘机工况判定模型，得到挖掘机工况判定模型输出的挖掘机的工况类型，该方法所需的数据易于获取，且在训练挖掘机工况判定模型时，使用了大量的数据，因此挖掘机工况判定模型的通用性强，使判定挖掘机工况变得容易实现。
为了更清楚地说明本申请或现有技术中的技术方案，下面将对实施例 或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请提供的挖掘机工况判定方法的流程示意图；
图2是本申请提供的挖掘机工况判定方法的具体流程示意图；
图3是本申请提供的挖掘机工况判定装置的结构示意图；
图4是本申请提供的电子设备的结构示意图。
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请中的附图，对本申请中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
由于目前在识别挖掘机工况时，使用的流量数据不易获取，并且所使用的专家库构建的模型通用性不高，因此，本申请提供一种挖掘机工况判定方法。
图1是本申请提供的挖掘机工况判定方法的流程示意图，如图1所示，该方法包括：
S1，获取挖掘机的实时状态参数数据；
S2，将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；
其中，所述挖掘机工况判定模型基于带有工况类型标签的状态参数数据样本训练得到。
本申请实施例中提供的挖掘机工况判定方法，其执行主体为服务器，该服务器可以是本地服务器，也可以是云端服务器，本地服务器具体可以是计算机、平板电脑以及智能手机等，本申请实施例中对此不作具体限定。
首先执行步骤S1，获取挖掘机的实时状态参数数据。
其中，挖掘机的实时状态参数数据可以包括发动机转速、先导压力、电流、泵压、使用时长等实时状态参数数据。
在本申请实施例中，可以通过CAN总线采集挖掘机的实时状态参数数据。CAN(Controller Area Network，CAN)总线是指控制器局域网络，是一个用于连接电子控制单元的多主机串行总线标准。CAN总线的网络各节点之间的数据通信实时性强，因此可以直接通过CAN总线采集到挖掘机的各项实时状态参数数据。
通过CAN总线采集挖掘机的实时状态参数数据，无需在挖掘机的主阀或控制器加装传感器，降低了获取状态参数数据的成本，也能够更方便的获取到挖掘机工况识别模型所需要的输入数据。
然后执行步骤S2，将获取到的实时状态参数数据输入至挖掘机工况判定模型，得到挖掘机工况判定模型输出的挖掘机的工况类型。
其中，挖掘机工况判定模型可以是现有的开源神经网络模型，例如卷积神经网络模型、残差神经网络模型或循环神经网络模型等，本申请实施例对此不作具体限定。
所述挖掘机工况判定模型基于带有工况类型标签的状态参数数据样本训练得到。具体可以通过如下方式训练得到挖掘机工况判定模型：首先，收集大量挖掘机的状态参数数据样本，并在状态参数数据样本上进行标注，也即是使状态参数数据样本携带工况类型标签。随即，基于携带有工况类型标签的状态参数数据样本训练初始模型，从而得到挖掘机工况判定模型。
由于挖掘机不同的工况类型对应着不同的状态参数数据，因此，将实时状态参数数据输入至训练好的挖掘机工况判定模型中，就可以得到挖掘机工况判定模型输出的挖掘机的工况类型。其中，挖掘机的工况类型包括挖掘、平地、装车、修坡和破碎等。
在挖掘机工况判定模型输出挖掘机的工况类型时，还可以生成这个工况类型对应的时间段，这个时间段可以用两个时间戳分别表示其起始时间和终止时间。例如，将2021年06月29日12时30分至2021年06月29日12时35分这个时间段内的实时状态参数数据输入至挖掘机工况判定模型，得到挖掘机工况判定模型输出的这个时间段内的工况类型，则这个时间段内的工况类型对应的时间段的起始时刻就可以用2021.06.30.12.30这个时间戳表示，终止时刻就可以用2021.06.30.12.35这个时间戳表示。时间戳的表示形式可以是unix时间戳。时间戳可以用于验证实时状态参数数 据是否发生了篡改，也就是说，时间戳代表一个可信赖的时间。
本申请实施例中的挖掘机工况判定方法，通过获取挖掘机的实时状态参数数据，并将实时状态参数数据输入至挖掘机工况判定模型，得到挖掘机工况判定模型输出的挖掘机的工况类型，该方法所需的数据易于获取，且在训练挖掘机工况判定模型时，使用了大量的状态参数数据样本，因此挖掘机工况判定模型的通用性强，使判定挖掘机工况变得容易实现。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定方法，所述获取挖掘机的实时状态参数数据，具体包括：获取所述挖掘机在目标时间段中各预设时间段内的实时状态参数数据；
相应地，所述将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型，具体包括：
将所述挖掘机在各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型。
具体地，本申请实施例中，需要获取挖掘机在目标时间段中各预设时间段内的实时状态参数数据。其中，目标时间段可以是挖掘机的工作时间段，例如，挖掘机一天工作8个小时，则目标时间段可以是挖掘机工作的这8个小时。各预设时间段可以根据实际需要进行设置，例如，可以将预设时间段设置为5分钟。
相应地，将实时状态参数数据输入至挖掘机工况判定模型，得到挖掘机工况判定模型输出的挖掘机的工况类型就是将挖掘机在各预设时间段内的实时状态参数数据分别输入至挖掘机工况判定模型，得到挖掘机工况判定模型输出的挖掘机在各预设时间段内对应的工况类型。
例如，在上述例子中，目标时间段是挖掘机的工作时间段，预设时间段是5分钟，如果挖掘机的工作时间段是从早上8点到下午6点，则目标时间段是10个小时，将这10个小时内的各个5分钟内的实时状态参数数据分别输入至挖掘机工况判定模型，就可以得到挖掘机工况判定模型输出的挖掘机在各预设时间段内对应的工况类型。例如，将9点至9：05这个时间段内的实时状态参数数据输入至挖掘机工况判定模型，就可以得到9点至9：05这个时间段对应的工况类型。
本申请实施例中的挖掘机工况判定方法，将挖掘机在各预设时间段内的实时状态参数数据分别输入至挖掘机工况判定模型，得到挖掘机工况判定模型输出的挖掘机在各预设时间段内对应的工况类型，能够在挖掘机的工作时间范围内对挖掘机的工况类型进行持续的判断，使挖掘机的工况类型的判定更加准确。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定方法，所述将所述挖掘机在各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型，之后还包括：
基于所述挖掘机在各预设时间段内对应的工况类型，确定各预设时间段对应的工况类型占比。
具体地，本申请实施例中，在得到挖掘机工况判定模型输出的挖掘机在各预设时间段内对应的工况类型之后，还可以基于各预设时间段内对应的工况类型，确定各预设时间段对应的工况类型占比。
例如，目标时间段是8小时，各预设时间段设置为10分钟，则需要获取8个小时内的各个10分钟对应的工况类型，也就是说，一共会获取到48个工况类型。再基于这48个工况类型，计算各预设时间段对应的工况类型占比。例如，在这48个工况类型中，有24个工况类型是挖掘，则挖掘这一工况类型的占比就是50％。
本申请实施例中，基于挖掘机在各预设时间段内对应的工况类型，确定各预设时间段对应的工况类型占比，便于用户了解挖掘机在目标时间段内的工作情况，也为用户提供了更多的数据参考。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定方法，所述将所述挖掘机各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型，之后还包括：
将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台，以使所述云端数据平台对所述挖掘机在每一预设时间段内的实时状态参数数据进行聚合计算，得到所述挖掘机在每一预设时间段内的目标状态参数数据，并将 所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据存储至云端数据仓库。
具体地，本申请实施例中，在得到挖掘机工况判定模型输出的挖掘机在各预设时间段内对应的工况类型之后，还需要将挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台。
其中，可以通过第四代移动通信技术或第五代移动通信技术的传输方式将挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台。
第四代移动通信技术(4th Generation Mobile Communication Technology，4G)，是在第三代移动通信技术上的一次升级，通过正交频分复用(Orthogonal Frequency Division Multiplexing，OFDM)、多输入多输出(Multi Input Multi Output，MIMO)、智能天线等技术，使数据传输的速率比3G更快。
第五代移动通信技术(5th Generation Mobile Communication Technology，5G)，是具有高速率、低时延和大连接特点的新一代宽带移动通信技术，是实现人机物互联的网络基础设施。5G技术具有三大类应用场景，即增强移动宽带、超高可靠低时延通信和海量机器类通信，使用5G技术进行数据传输会使数据传输的速率变得更快，并且具有更高的设备连接能力。
在将挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台之后，还可以使云端数据平台对挖掘机在每一预设时间段内的实时状态参数数据进行聚合计算，得到挖掘机在每一预设时间段内的目标状态参数数据。
由于各预设时间段内的实时状态参数数据是通过CAN总线采集的，因此每个预设时间段内都会包含很多条实时状态参数数据，通过聚合计算，可以将每个预设时间段内的多条实时状态参数数据聚合成一条状态参数数据，也就是每一预设时间段内的目标状态参数数据。
在得到目标状态参数数据后，就可以将挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据存储至云 端数据仓库。其中，云端数据仓库可以是云端数据库，云端数据库的类型可以根据实际需要进行选择，本申请实施例对此不作具体限定。
本申请实施例中的挖掘机工况判定方法，将挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台，再对挖掘机在每一预设时间段内的实时状态参数数据进行聚合计算，得到挖掘机在每一预设时间段内的目标状态参数数据，并将挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据存储至云端数据仓库，方便了工作人员在线查询挖掘机的工况类型和实时状态参数数据，也为工作人员提供了分析挖掘机的生命周期内的实时状态参数数据与工况类型之间关系的数据支持，且云端数据平台可扩展性强，可以存储更多的数据，降低数据的存储成本。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定方法，还包括：
将所述工况类型、所述实时状态参数数据以及所述工况类型对应的预设时间段存储至本地存储模块。
具体地，本申请实施例中，在得到挖掘机工况判定模型输出的挖掘机的工况类型、实时状态参数数据以及工况类型对应的预设时间段之后，还可以将挖掘机的工况类型、实时状态参数数据以及工况类型对应的预设时间段至本地存储模块。
其中，本地存储模块可以是本地数据库。本地数据库可以是关系数据库、非关系型数据库和键值数据库，例如，关系数据库可以是MySQL、MariaDB等，非关系型数据库可以是BigTable、Cassandra等，键值数据库可以是Apache Cassandra等，则工况类型、实时状态参数数据和工况类型对应的预设时间段的存储格式需要和使用的数据库对应。本申请实施例对数据库的类型不作具体限定。
本申请实施例中，将工况类型、实时状态参数数据以及工况类型对应的预设时间段存储至本地存储模块时，可以按照各预设时间段的顺序对工况类型、实时状态参数数据以及工况类型对应的预设时间段进行存储，并且可以按照预设的周期对本地存储模块中的数据进行覆盖，即本地存储模块中的数据的存储时间是预设的周期。其中，预设的周期可以根据实际需 要进行设置，本申请实施例对此不作具体限定。
例如，当预设的周期是30天时，如果在日期A将工况类型、实时状态参数数据以及工况类型对应的预设时间段存储至本地存储模块，则在30天之后，日期A存储的工况类型、实时状态参数数据以及工况类型对应的预设时间段将被新存储进来的工况类型、实时状态参数数据以及工况类型对应的预设时间段覆盖。
本申请实施例中，将工况类型、实时状态参数数据以及工况类型对应的预设时间段按照各预设时间段顺序存储至本地存储模块，并按照预设的周期用新存储的工况类型、实时状态参数数据以及工况类型对应的预设时间段将本地存储模块中的工况类型、实时状态参数数据以及工况类型对应的预设时间段覆盖，便于工作人员在本地查看挖掘机的工况情况，并且当工况类型、实时状态参数数据以及工况类型对应的预设时间段传输至云端数据平台出现问题时，可以提供数据支持，加强了数据的保障性，按照预设的周期对本地存储模块中的工况类型、实时状态参数数据以及工况类型对应的预设时间段进行覆盖，降低了本地存储模块的数据维护难度和内存要求。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定方法，所述将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台，之后还包括：
基于所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据，对所述挖掘机工况判定模型进行二次训练，得到二次训练后的挖掘机工况判定模型；
基于二次训练后的挖掘机工况判定模型，对所述挖掘机工况判定模型进行更新。
具体地，本申请实施例中，由于挖掘机在达到一定的使用时间后，性能会发生下降，此时挖掘机在相同工况下的各项实时状态参数数据会发生改变，即会引起实时状态参数数据漂移。由于挖掘机实时状态参数数据的漂移，原有的挖掘机工况判定模型的判定结果的准确率就会下降，因此，为了使挖掘机工况判定模型更符合挖掘机的实际情况，可以使用挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目 标状态参数数据对挖掘机工况判定模型进行二次训练。
在训练完成后，可以得到二次训练后的挖掘机工况判定模型。基于二次训练后的挖掘机工况判定模型对挖掘机工况判定模型进行更新，得到更符合挖掘机实际情况的挖掘机工况判定模型。其中，可以按照目标频率对挖掘机工况判定模型进行二次训练，目标频率可以根据实际需要进行设置，例如设置为90天等，本申请实施例对此不作具体限定。
在使用挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据对挖掘机工况判定模型进行二次训练时，使用的是累积得到的挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据，例如，当每隔90天对挖掘机工况判定模型进行二次训练时，在第一次对挖掘机工况判定模型进行二次训练时，使用的挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据结果就是前90天内累积存储在云端数据仓库中的挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据。同样的，在第二次对挖掘机工况判定模型进行更新时，就会使用前180天内累积存储在云端存储数据仓库中的挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据。
本申请实施例中的挖掘机工况判定方法，基于挖掘机在各预设时间段内对应的工况类型以及挖掘机在各预设时间段内的目标状态参数数据，对挖掘机工况判定模型进行二次训练和更新，避免了因挖掘机老化或性能下降等导致的挖掘机工况判定模型的不稳定，提高了挖掘机工况判定模型的判定准确率。
图2是本申请提供的挖掘机工况判定方法的具体流程示意图，如图2所示，实线矩形框表示工况判定边缘计算装置，该工况判定边缘计算装置包括CAN数据采集模块、挖掘机工况判定模块、数据本地存储模块以及数据远程传输模块。其中，挖掘机工况判定模块在图2中用虚线框中的内容表示。
当进行挖掘机的工况判定时，需要执行以下步骤：
1)使用CAN数据采集模块，通过CAN总线采集挖掘机的实时状态 参数数据，例如发动机转速、先导压力、电流、泵压和使用时长等实时状态参数数据；
2)将这些实时状态参数数据输入至训练好的工况判定模型中，使用工况判定模型计算挖掘机在各预设时间段内对应的工况类型，在得到挖掘机在各预设时间段内对应的工况类型之后，还可以确定各预设时间段对应的工况类型占比，其中，占比最大的工况类型就是挖掘机在目标时间段内所处时长最长的工况类型；还可以得到模型判定工况，也就是挖掘机在目标时间段内的各个工况类型；
3)将CAN数据采集模块采集到的实时状态参数数据、挖掘机在各预设时间段内对应的工况类型以及各预设时间段存储至数据本地存储模块；对于数据本地存储模块中的数据，还可以通过人工定期取出的方式对数据本地存储模块中的数据进行维护保养，培训工况判定模型；
4)通过数据远程传输模块，使用4G或5G的方式，将CAN数据采集模块采集到的实时状态参数数据、挖掘机在各预设时间段内对应的工况类型以及各预设时间段上传至云端大数据平台；
5)基于云端大数据平台，对挖掘机在每一预设时间段内的实时状态参数数据进行聚合计算，得到目标状态参数数据，将目标状态参数数据和挖掘机在各预设时间段内对应的工况类型存储至云端数据仓库，并基于目标状态参数数据和挖掘机在各预设时间段内对应的工况类型对挖掘机工况判定模型进行训练，并基于训练的结果对挖掘机工况判定模型进行持续的更新，使挖掘机工况判定模型更符合挖掘机的实际情况。
图3是本申请提供的挖掘机工况判定装置的结构示意图。如图3所示，该装置包括：
参数数据获取模块301，用于获取挖掘机的实时状态参数数据；
挖掘机工况判定模块302，用于将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；
其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定装置， 所述参数数据获取模块，具体包括：
状态参数数据获取子模块，用于获取所述挖掘机在目标时间段中各预设时间段内的实时状态参数数据；
相应地，所述挖掘机工况判定模块，具体包括：
挖掘机工况判定子模块，用于将所述挖掘机在各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定装置，还包括：
占比计算模块，用于基于所述挖掘机在各预设时间段内对应的工况类型，确定各预设时间段对应的工况类型占比。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定装置，还包括：
云端模块，用于将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台，以使所述云端数据平台对所述挖掘机在每一预设时间段内的实时状态参数数据进行聚合计算，得到所述挖掘机在每一预设时间段内的目标状态参数数据，并将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据存储至云端数据仓库。在上述实施例的基础上，本申请实施例提供的挖掘机工况判定装置，还包括：
模型更新模块，用于基于所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据，对所述挖掘机工况判定模型进行二次训练，得到二次训练后的挖掘机工况判定模型；
基于二次训练后的挖掘机工况判定模型，对所述挖掘机工况判定模型进行更新。
在上述实施例的基础上，本申请实施例提供的挖掘机工况判定装置，所述实时状态参数数据包括发动机转速、先导压力、电流、泵压以及使用时长中的至少一个。
具体地，本申请实施例中提供的挖掘机工况判定装置中各模块的作用与上述方法类实施例中各步骤的操作流程是一一对应的，实现的效果也是 一致的，具体参见上述实施例，本申请实施例中对此不再赘述。
本申请还提供一种挖掘机，包括上述的挖掘机工况判定装置，用于对挖掘机工况类型进行判定。
图4示例了一种电子设备的实体结构示意图，如图4所示，该电子设备可以包括：处理器(processor)410、通信接口(Communications Interface)420、存储器(memory)430和通信总线440，其中，处理器410，通信接口420，存储器430通过通信总线440完成相互间的通信。处理器410可以调用存储器430中的逻辑指令，以执行挖掘机工况判定方法，该方法包括：获取挖掘机的实时状态参数数据；将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
此外，上述的存储器430中的逻辑指令可以通过软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
另一方面，本申请还提供一种计算机程序产品，所述计算机程序产品包括存储在非暂态计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被计算机执行时，计算机能够执行上述各方法所提供的挖掘机工况判定方法，该方法包括：获取挖掘机的实时状态参数数据；将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
又一方面，本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现以执行上述各提供的挖 掘机工况判定方法，该方法包括：获取挖掘机的实时状态参数数据；将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。
Claims (10)
- 一种挖掘机工况判定方法，包括：获取挖掘机的实时状态参数数据；将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
- 根据权利要求1所述的挖掘机工况判定方法，其中，所述获取挖掘机的实时状态参数数据，具体包括：获取所述挖掘机在目标时间段中各预设时间段内的实时状态参数数据；相应地，所述将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型，具体包括：将所述挖掘机在各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型。
- 根据权利要求2所述的挖掘机工况判定方法，其中，所述将所述挖掘机在各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型，之后还包括：基于所述挖掘机在各预设时间段内对应的工况类型，确定各预设时间段对应的工况类型占比。
- 根据权利要求2所述的挖掘机工况判定方法，其中，所述将所述挖掘机各预设时间段内的实时状态参数数据分别输入至所述挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机在各预设时间段内对应的工况类型，之后还包括：将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台，以使所述云端数据平台对所述挖掘机在每一预设时间段内的实时状态参数数据进行 聚合计算，得到所述挖掘机在每一预设时间段内的目标状态参数数据，并将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据存储至云端数据仓库。
- 根据权利要求4所述的挖掘机工况判定方法，其中，所述将所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的实时状态参数数据上传至云端数据平台，之后还包括：基于所述挖掘机在各预设时间段内对应的工况类型以及所述挖掘机在各预设时间段内的目标状态参数数据，对所述挖掘机工况判定模型进行二次训练，得到二次训练后的挖掘机工况判定模型；基于二次训练后的挖掘机工况判定模型，对所述挖掘机工况判定模型进行更新。
- 根据权利要求1-5中任一项所述的挖掘机工况判定方法，其中，所述实时状态参数数据包括发动机转速、先导压力、电流、泵压以及使用时长中的至少一个。
- 一种挖掘机工况判定装置，包括：参数数据获取模块，用于获取挖掘机的实时状态参数数据；挖掘机工况判定模块，用于将所述实时状态参数数据输入至挖掘机工况判定模型，得到所述挖掘机工况判定模型输出的所述挖掘机的工况类型；其中，所述挖掘机工况判定模型基于携带有工况类型标签的状态参数数据样本训练得到。
- 一种挖掘机，包括：如权利要求7所述的挖掘机工况判定装置，用于对所述挖掘机的工况类型进行判定。
- 一种电子设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求1至6任一项所述挖掘机工况判定方法的步骤。
- 一种非暂态计算机可读存储介质，其上存储有计算机程序，其中，所述计算机程序被处理器执行时实现如权利要求1至6任一项所述挖掘机工况判定方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110802807.7 | 2021-07-15 | ||
| CN202110802807.7A CN113502870B (zh) | 2021-07-15 | 2021-07-15 | 挖掘机工况判定方法及装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023284443A1 true WO2023284443A1 (zh) | 2023-01-19 |
Family
ID=78012902
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2022/097336 WO2023284443A1 (zh) | 2021-07-15 | 2022-06-07 | 挖掘机工况判定方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113502870B (zh) |
| WO (1) | WO2023284443A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451809A (zh) * | 2023-06-16 | 2023-07-18 | 北谷电子股份有限公司 | 基于dagsvm算法的挖掘机工况识别方法及系统 |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113502870B (zh) * | 2021-07-15 | 2023-02-07 | 上海三一重机股份有限公司 | 挖掘机工况判定方法及装置 |
| CN113774985B (zh) * | 2021-10-28 | 2023-03-24 | 三一重机有限公司 | 作业机械的控制方法、装置、介质及作业机械 |
| CN115982541B (zh) * | 2023-01-16 | 2023-09-29 | 徐州徐工挖掘机械有限公司 | 一种基于大数据的挖掘机工况占比统计方法 |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908874A (zh) * | 2017-11-15 | 2018-04-13 | 上海华兴数字科技有限公司 | 工况识别方法和装置及工程机械设备 |
| JP2018138751A (ja) * | 2017-02-24 | 2018-09-06 | 住友重機械工業株式会社 | 建設機械及びその管理装置 |
| CN109359524A (zh) * | 2018-09-07 | 2019-02-19 | 长安大学 | 一种装载机工况识别模型构建及识别方法 |
| CN109636951A (zh) * | 2018-11-21 | 2019-04-16 | 中南大学 | 一种基于工作阶段识别的挖掘机能耗分析方法 |
| CN110258709A (zh) * | 2019-07-08 | 2019-09-20 | 山重建机有限公司 | 一种挖掘机自动匹配不同工况的方法 |
| CN113029571A (zh) * | 2021-03-31 | 2021-06-25 | 徐州徐工挖掘机械有限公司 | 一种液压挖掘机排放污染物测试系统与方法 |
| CN113502870A (zh) * | 2021-07-15 | 2021-10-15 | 上海三一重机股份有限公司 | 挖掘机工况判定方法及装置 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109358549B (zh) * | 2018-11-01 | 2020-11-03 | 三一重机有限公司 | 一种挖掘机的智能控制方法及装置 |
| CN112734246A (zh) * | 2021-01-14 | 2021-04-30 | 上海华兴数字科技有限公司 | 挖掘机工况识别方法及其装置、存储介质及电子设备 |
| CN113006188B (zh) * | 2021-03-22 | 2022-02-18 | 大连理工大学 | 一种基于lstm神经网络的挖掘机分阶段功率匹配方法 |
-
2021
- 2021-07-15 CN CN202110802807.7A patent/CN113502870B/zh active Active
-
2022
- 2022-06-07 WO PCT/CN2022/097336 patent/WO2023284443A1/zh unknown
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018138751A (ja) * | 2017-02-24 | 2018-09-06 | 住友重機械工業株式会社 | 建設機械及びその管理装置 |
| CN107908874A (zh) * | 2017-11-15 | 2018-04-13 | 上海华兴数字科技有限公司 | 工况识别方法和装置及工程机械设备 |
| CN109359524A (zh) * | 2018-09-07 | 2019-02-19 | 长安大学 | 一种装载机工况识别模型构建及识别方法 |
| CN109636951A (zh) * | 2018-11-21 | 2019-04-16 | 中南大学 | 一种基于工作阶段识别的挖掘机能耗分析方法 |
| CN110258709A (zh) * | 2019-07-08 | 2019-09-20 | 山重建机有限公司 | 一种挖掘机自动匹配不同工况的方法 |
| CN113029571A (zh) * | 2021-03-31 | 2021-06-25 | 徐州徐工挖掘机械有限公司 | 一种液压挖掘机排放污染物测试系统与方法 |
| CN113502870A (zh) * | 2021-07-15 | 2021-10-15 | 上海三一重机股份有限公司 | 挖掘机工况判定方法及装置 |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116451809A (zh) * | 2023-06-16 | 2023-07-18 | 北谷电子股份有限公司 | 基于dagsvm算法的挖掘机工况识别方法及系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113502870A (zh) | 2021-10-15 |
| CN113502870B (zh) | 2023-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023284443A1 (zh) | 挖掘机工况判定方法及装置 | |
| CN110659173B (zh) | 一种运维系统及方法 | |
| CN108628929B (zh) | 用于智能存档和分析的方法和装置 | |
| WO2021000556A1 (zh) | 一种工业设备剩余有效寿命预测方法、系统及电子设备 | |
| WO2022257423A1 (zh) | 告警信息关联方法、装置、电子设备和可读存储介质 | |
| CN110750650A (zh) | 企业知识图谱的构建方法及装置 | |
| US20190079965A1 (en) | Apparatus and method for real time analysis, predicting and reporting of anomalous database transaction log activity | |
| EP2466495B1 (en) | Systems and/or methods for event stream deviation detection | |
| CN104636241A (zh) | 基于需求建模的车载控制器日志数据自动分析方法 | |
| CN113535831A (zh) | 一种基于大数据的报表分析方法、装置、设备和介质 | |
| CN114416703A (zh) | 数据完整性自动监控方法、装置、设备及介质 | |
| CN112416918A (zh) | 数据治理系统及其工作方法 | |
| CN107590747A (zh) | 基于综合能源大数据分析的电网资产周转率计算方法 | |
| CN109116818B (zh) | 一种scada系统升级时的实时数据转储方法和装置 | |
| US20190340540A1 (en) | Adaptive continuous log model learning | |
| CN109800271A (zh) | 一种基于大数据的信息采集方法 | |
| CN114312930B (zh) | 基于日志数据的列车运行异常诊断方法和装置 | |
| US11164349B2 (en) | Visualizing a time series relation | |
| WO2019055329A1 (en) | METHOD FOR DRIVING ROBUST REGRESSION MODELS FROM LIMITED TRAINING DATA | |
| CN114661571A (zh) | 模型评测方法、装置、电子设备和存储介质 | |
| US9459939B2 (en) | In-memory approach to extend semantic event processing with domain insights | |
| CN114095390B (zh) | 区域内对象流量的预测方法、装置、设备及存储介质 | |
| CN115356949B (zh) | 一种数字孪生模型一致性保持系统及方法 | |
| US11985048B2 (en) | Computerized system and method for an improved self organizing network | |
| US20230231778A1 (en) | Computerized system and method for an improved self organizing network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22841083 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |