WO2023040400A1 - Procédé et appareil de prédiction de défaut d'excavatrice, dispositif électronique et support de stockage - Google Patents

Procédé et appareil de prédiction de défaut d'excavatrice, dispositif électronique et support de stockage Download PDF

Info

Publication number
WO2023040400A1
WO2023040400A1 PCT/CN2022/100752 CN2022100752W WO2023040400A1 WO 2023040400 A1 WO2023040400 A1 WO 2023040400A1 CN 2022100752 W CN2022100752 W CN 2022100752W WO 2023040400 A1 WO2023040400 A1 WO 2023040400A1
Authority
WO
WIPO (PCT)
Prior art keywords
excavator
detected
working condition
condition data
tested
Prior art date
Application number
PCT/CN2022/100752
Other languages
English (en)
Chinese (zh)
Inventor
刘乐星
Original Assignee
树根互联股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 树根互联股份有限公司 filed Critical 树根互联股份有限公司
Publication of WO2023040400A1 publication Critical patent/WO2023040400A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/15—Vehicle, aircraft or watercraft design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/04—Ageing analysis or optimisation against ageing

Definitions

  • the present disclosure relates to the technical field of fault detection of excavators, in particular to a method, system, electronic equipment and storage medium for predicting faults of excavators.
  • Excavator is a kind of engineering machinery widely used in earthwork construction. It is widely used in road construction, mining, water conservancy construction and farmland development. It can reduce the labor intensity of construction personnel, improve the efficiency of overall construction and It has played an irreplaceable role in ensuring the quality of construction operations.
  • the present disclosure provides an excavator failure prediction method, system, electronic equipment, and storage medium, through regular detection and inspection of the excavator within a preset period, according to the excavation data collected when the excavator performs a specified action
  • the operating data of the excavator is used to predict the failure of each component of the excavator in the future, so that when the excavator does not fail, the failure of each component of the excavator can be judged in a timely and effective manner, which is helpful to improve the detection of excavators. timeliness of failure.
  • An embodiment of the present disclosure provides a method for predicting a failure of an excavator, and the method for predicting may include:
  • the fault information of the faulty detection component among the multiple components to be detected of the excavator to be detected is output.
  • the forecasting method may also include:
  • each of the multiple components to be detected If it is detected that each of the multiple components to be detected is qualified, analyze the remaining service life of each component to be detected of the excavator to be detected according to the multiple working condition data, and output the excavator to be detected The remaining service life corresponding to each component to be tested and the corresponding maintenance strategy.
  • the detecting whether a plurality of components to be detected of the excavator to be detected is qualified based on the plurality of working condition data may include:
  • the analyzing the remaining service life of each component to be tested of the excavator to be tested according to the plurality of working condition data may include:
  • a health characteristic value is determined based on each working condition data of each component to be detected of the excavator to be detected within the preset detection cycle time, and a corresponding health characteristic value is determined. the corresponding running time;
  • the predicted value of the end of life is determined, and the predicted value of the predicted end of life is determined.
  • the runtime corresponding to the value
  • the remaining service life of the component to be tested of the excavator to be tested is determined based on the difference between the running time corresponding to the end-of-life prediction value and the running time corresponding to the health characteristic value .
  • the predictive maintenance decision method may further include:
  • the prediction method may include: inputting the plurality of working condition data into a pre-trained predictive analysis model, and detecting a plurality of excavators to be detected based on the plurality of working condition data. Whether the parts to be tested are qualified include:
  • the predictive method may further include: training, testing and deploying the predictive analysis model according to the factory commissioning data of the excavator to be tested, so as to obtain the predictive analysis model, wherein the predictive analysis model is used to treat Detect multiple detection parts of the excavator to detect and judge whether there are faults in the multiple components to be detected of the excavator to be detected.
  • An embodiment of the present disclosure also provides an excavator failure prediction system, the prediction system may include:
  • the physical examination module is configured to control the excavator to be detected to perform a specified detection action within a preset detection period, and to acquire the time when the excavator to be detected performs a specified detection action during the excavator to be detected. Multiple working condition data during action;
  • the detection module is configured to input the multiple working condition data into a pre-trained predictive analysis model, and detect whether the multiple components to be tested of the excavator to be tested are qualified based on the multiple working condition data ;
  • the determination module is configured to output the faulty detection component among the plurality of components to be detected of the excavator to be detected if it is detected that any component to be detected is unqualified among the plurality of components to be detected. accident details.
  • the determining module may also be configured to:
  • each of the multiple components to be detected If it is detected that each of the multiple components to be detected is qualified, analyze the remaining service life of each component to be detected of the excavator to be detected according to the multiple working condition data, and output the excavator to be detected The remaining service life corresponding to each component to be tested and the corresponding maintenance strategy.
  • the detection module can also be configured to:
  • the detection module may also be configured to: when the detection module analyzes the remaining service life of each component to be detected of the excavator to be detected according to the plurality of working condition data , also used in:
  • a health characteristic value is determined based on each working condition data of each component to be detected of the excavator to be detected within the preset detection cycle time, and a corresponding health characteristic value is determined. the corresponding running time;
  • the predicted value of the end of life is determined, and the predicted value of the predicted end of life is determined.
  • the runtime corresponding to the value
  • the remaining service life of the component to be tested of the excavator to be tested is determined based on the difference between the running time corresponding to the end-of-life prediction value and the running time corresponding to the health characteristic value .
  • the prediction system also includes an optimization module, which can be configured to:
  • the detection module can also be configured to:
  • the predictive analysis model is obtained by training, testing and deploying the predictive analysis model according to the factory commissioning data of the excavator to be detected, wherein the predictive analysis model is used for multiple detection parts of the excavator to be detected Detecting is performed to determine whether a plurality of components to be detected of the excavator to be detected have faults.
  • an embodiment of the present disclosure also provides an electronic device, which may include: a processor, a memory, and a bus, the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the The processor communicates with the memory through the bus, and the machine-readable instructions are executed by the processor to perform the mining described in the above-mentioned first aspect or any possible implementation manner of the first aspect.
  • the steps of the machine failure prediction method may include: a processor, a memory, and a bus, the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the The processor communicates with the memory through the bus, and the machine-readable instructions are executed by the processor to perform the mining described in the above-mentioned first aspect or any possible implementation manner of the first aspect.
  • an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, the above-mentioned first aspect or the first aspect is executed.
  • the present disclosure provides an excavator fault prediction method, system, electronic device and storage medium, which controls the excavator to be detected to perform a specified detection action within a preset detection period, and performs the specified detection action when the excavator to be detected performs the specified detection action
  • a plurality of working condition data of the excavator to be detected is obtained when the specified detection action is completed; the plurality of working condition data is input into the pre-trained predictive analysis model, and detection is performed based on the plurality of working condition data Whether the plurality of components to be detected of the excavator to be detected is qualified; if it is detected that any component to be detected in the plurality of components to be detected is unqualified, then output the plurality of components to be detected of the excavator to be detected Fault information of the faulty detection component in .
  • FIG. 1 is a flow chart of a method for predicting an excavator failure provided by an embodiment of the present disclosure
  • FIG. 2 is a flow chart of another excavator fault prediction method provided by an embodiment of the present disclosure
  • FIG. 3 is a graph of remaining life prediction results in an excavator failure prediction method provided by an embodiment of the present disclosure
  • FIG. 4 is a business flow chart of speed drop analysis in an excavator fault prediction method provided by an embodiment of the present disclosure
  • FIG. 5 is one of the structural schematic diagrams of an excavator failure prediction system provided by an embodiment of the present disclosure
  • FIG. 6 is the second structural schematic diagram of an excavator failure prediction system provided by an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the first aspect of the present disclosure proposes a method for predicting excavator faults, by regularly testing the excavator within a preset period, and predicting its health status for a period of time in the future based on the collected operating data of the excavator. In order to make a reasonable maintenance plan and realize the health management of the excavator's life cycle based on predictive maintenance decisions.
  • FIG. 1 is a flow chart of a method for predicting an excavator failure provided by an embodiment of the present disclosure. As shown in Figure 1, the forecasting method may include:
  • S101 Control the excavator to be detected to perform a specified detection action within a preset detection period, and acquire multiple working hours of the excavator to be detected when the excavator to be detected completes the specified detection action during the process of performing the specified detection action by the excavator to be detected status data.
  • a preset detection cycle is set, and the excavator to be detected is controlled to perform a specified detection action within the preset detection cycle, and the time when the excavator performs the specified detection action is obtained during the process of the excavator performing the specified detection action.
  • the plurality of working condition data wherein there are multiple specified detection actions, are used to make each detection component of the excavator perform a specified detection action check.
  • the preset detection cycle may be preset according to other factors such as wear cycle or service cycle of multiple components to be detected of the excavator to be detected during operation.
  • the specified detection action of the excavator provided by the embodiment of the present disclosure may be:
  • the slewing system of the excavator performs the following detection actions in sequence: Detect the left-swing speed: cancel the automatic idle speed, turn the gear to the 11th gear, pull the handle to the bottom, perform the left-swing action, and turn 6 times continuously; Check the speed of turning right: cancel the automatic idle speed, turn the gear to the 11th gear, click start, pull the handle to the bottom, perform the action of turning right, and turn 6 times continuously.
  • the walking system of the excavator performs the following inspection actions in sequence: walking pressure suppression: cancel the automatic idle speed, turn the gear to the 11th gear, and use the bucket to hold the track, so that the excavator cannot walk.
  • walking pressure suppression cancel the automatic idle speed, turn the gear to the 11th gear, and use the bucket to hold the track, so that the excavator cannot walk.
  • Click start pull the handle to the bottom, perform the action of holding pressure while walking, and hold the pressure for about 10s
  • Swing pressure cancel the automatic idle speed, turn the gear to the 11th gear, and grab the bucket to prevent the excavator from turning.
  • Click to start pull the handle to the bottom, perform the rotary pressure holding action, and hold the pressure for about 10s.
  • Engine-dual pump overflow cancel the automatic idle speed, turn the gear to the 11th gear, click start, pull the two handles to the bottom, the boom, The three actions of the stick and bucket hold the pressure at the same time, and hold the pressure for about 10s;
  • engine-P11 gear cancel the automatic idle speed, turn the gear to the 11th gear, and do not perform any action for 10 seconds without load;
  • engine-H10 gear cancel the automatic idle speed, Turn the gear to the 10th gear, and do not perform any action for 10 seconds without load;
  • engine-automatic idle speed turn on the automatic idle speed, turn the gear position to the 11th gear, and perform no action for 10 seconds without load;
  • engine-first gear idle speed enable automatic idle speed , turn the gear to 1st gear, and do not perform any action for 10s with no load.
  • the working system, slewing system, walking system and engine of the excavator contain multiple detection components. This inspection is completed after each system of the excavator completes the above detection actions.
  • the detection of the working system, slewing system, and walking system The operating speed, pilot pressure, main pump pressure and other performance indicators can detect the engine speed under different gear conditions, and detect the engine speed drop under the dual-pump overflow condition.
  • multiple working condition data of the excavator are obtained in the following ways: install other sensors such as pressure, speed, and temperature on the excavator, and connect the data signal to the excavator controller, install the on-board data acquisition IoT gateway, and pass CAN
  • the bus connects the IoT gateway to the excavator controller.
  • the operation and maintenance personnel operate the excavator to perform all the physical examination actions in sequence according to the specified process.
  • Multiple working condition data upload multiple working condition data to the data cloud platform for storage through the 4G network based on the MQTT communication protocol.
  • the identity information of the excavator needs to be verified.
  • the ID information of the excavator input by the operator matches the registration information of the excavator in the data cloud platform, the Multiple operating condition data of the excavator are sent to the operator.
  • the preset physical examination cycle can be 50 hours, 250 hours, 500 hours, 1000 hours, 1500 hours, 2000 hours, 2500 hours, 3000 hours, 3500 hours, 4000 hours and so on.
  • the working condition data includes core working condition data such as accelerator position, engine speed, pilot pressure, main pump pressure, hydraulic oil temperature, etc.
  • S102 Input the plurality of working condition data into a pre-trained predictive analysis model, and detect whether the plurality of components to be tested of the excavator to be tested are qualified based on the multiple working condition data.
  • the multiple working condition data of the excavator to be detected obtained from the data cloud platform are input into the pre-trained predictive analysis model, and the predictive analysis model performs analysis based on multiple working condition data to detect multiple working conditions of the excavator. Whether a component to be tested is qualified.
  • the predictive analysis model is based on the factory commissioning data of the excavator to be tested for training, testing and deployment of the predictive analysis model, wherein the predictive analysis model is used to detect and judge multiple detection parts of the excavator to be tested. Whether there is a fault in a component to be detected, for example, when a fault is detected in a component to be detected, it means that the component to be detected is unqualified.
  • the detecting whether a plurality of components to be detected of the excavator to be detected is qualified based on the plurality of working condition data includes:
  • A Calculate the performance index corresponding to each working condition data based on the input multiple working condition data of the excavator to be tested.
  • the performance index of each working condition data is calculated according to the multiple working condition data of the excavator to be tested.
  • the performance index is the walking speed
  • the working condition data is the climbing height
  • the corresponding performance index is the climbing ability, which is not limited in this part.
  • each working condition data corresponds to a performance index
  • the performance index of each working condition data is calculated.
  • the performance index of the working condition data is compared with the corresponding standard performance of the parts to be tested in the excavator to be tested. Indexes are compared, if the performance index corresponding to the working condition data is consistent with the standard performance index, it means that the component to be tested corresponding to the working condition data is qualified.
  • the performance index of the condition data corresponds to a component to be tested.
  • the performance index corresponding to the working condition data is inconsistent with the standard performance index, it means that the component to be tested corresponding to the working condition data is unqualified.
  • the fault information is that there is a fault in a certain component to be detected in the excavator to be detected.
  • the predictive analysis model After the predictive analysis model outputs the fault information, the operator performs fault maintenance on the component to be detected.
  • the start time and end time of each detection action in each detection process are recorded.
  • a plurality of working condition data of the detection process of the excavator to be detected is obtained from the data cloud platform, and the Multiple working condition data are input into the pre-analysis model to calculate the performance index of each working condition, and the performance index of each working condition data is compared with the standard performance to judge whether the multiple parts to be tested of the excavator to be tested are qualified, If it is unqualified, a maintenance work order is generated to repair the fault of the detected component.
  • the present disclosure provides an excavator failure prediction method system, which controls the excavator to be detected to perform a specified detection action within a preset detection period, and obtains the excavator to be detected during the process of performing a specified detection action by the excavator to be detected.
  • a plurality of working condition data of the excavator when the specified detection action is completed input the plurality of working condition data into the pre-trained predictive analysis model, and detect the excavator to be detected based on the plurality of working condition data Whether a plurality of parts to be detected is qualified; if it is detected that there is any unqualified situation in any part to be detected in the plurality of parts to be detected, then output the detection part of the faulty detection part in the plurality of parts to be detected of the excavator to be detected accident details.
  • FIG. 2 is a flow chart of another excavator fault prediction method provided by an embodiment of the present disclosure.
  • the prediction method provided by the embodiment of the present disclosure may include:
  • S201 Control the excavator to be detected to perform a specified detection action within a preset detection period, and obtain multiple working hours of the excavator to be detected when the excavator to be detected completes the specified detection action during the process of performing the specified detection action by the excavator to be detected. status data.
  • S202 Input the multiple working condition data into a pre-trained predictive analysis model, and check whether the multiple components to be tested of the excavator to be tested are qualified based on the multiple working condition data.
  • S201 to S202 can refer to the description of S102 to S102, and can achieve the same technical effect, so it will not be repeated here.
  • each component to be detected is qualified, then in the predictive analysis model, multiple The remaining service life of the components to be detected is analyzed, and the remaining service life corresponding to each component to be detected of the excavator to be detected and the corresponding maintenance strategy are output.
  • the remaining service life is the difference between the expected service life and the used service life
  • the maintenance strategy is an operation and maintenance strategy that matches the remaining service life of each component to be tested.
  • the analysis of the remaining service life of each component to be tested of the excavator to be tested according to the plurality of working condition data may include:
  • a For each working condition data, determine the health characteristic value based on each working condition data of each component to be detected of the excavator to be detected within the preset detection cycle time, and determine the health characteristic The value corresponds to the running time.
  • the start time and end time of each detection action in each detection process are recorded, and for each working condition data, according to each working condition data of each component to be detected of the excavator to be detected within the preset detection cycle time Calculate the health characteristic value and the running time corresponding to the health characteristic value.
  • b For each working condition data, determine the health characteristic value based on each working condition data of each component to be detected of the excavator to be detected within the preset detection cycle time, and determine the health characteristic The value corresponds to the running time.
  • the predicted value of the end of life is calculated and the corresponding operation of the predicted value of the end of life is determined. time.
  • the operating time corresponding to the predicted value of the end of life calculated according to each working condition data of each component to be detected of the excavator to be detected within the preset detection cycle time is related to the health characteristic value
  • the corresponding running time determines the remaining service life of the component to be tested of the excavator to be tested.
  • Fig. 3 is a prediction method for excavator failure provided by an embodiment of the disclosure
  • the abscissa represents the operating time of the component to be detected
  • the ordinate represents the characteristic value of the health state of the component to be detected
  • Df represents the fault threshold corresponding to the characteristic value of the health state (over This threshold means that the performance degradation of the component to be detected is very serious, and the specified function cannot be completed, that is, the component to be detected is invalid)
  • the actual monitoring value of the health characteristic value of the component to be detected at time t i is D i
  • the end of life of the component to be detected is
  • the predicted value D f time is t f
  • the predicted (estimated) value of the remaining life of the component to be tested is shown in formula 1, and the corresponding standard deviation is ⁇ i .
  • the key component performance indicators are obtained from the excavator detection process data obtained from the platform, and the long-short-term memory network (LSTM, LongShort-TermMemory) algorithm is used to predict the remaining service life and change trend of each performance indicator.
  • LSTM LongShort-TermMemory
  • the output of the remaining service life is the expectation of the remaining service life.
  • the remaining service life of the component to be detected indicates the remaining service time before the actual failure time of the component to be detected under the given current operating time, operating conditions and historical operating state observations of the component to be detected.
  • X represents the estimated value of the remaining life of the component to be tested
  • T is the actual system state of the component to be tested.
  • the standard deviation of the estimated remaining life of the inspected component is:
  • the predictive maintenance decision-making method further includes:
  • the operator performs maintenance processing on multiple parts to be detected of the excavator to be detected according to the maintenance strategy, and after the excavator to be detected has completed the maintenance processing, controls the excavator to be detected to continue to perform the specified detection action of the next preset detection cycle, and Obtain a plurality of maintenance working condition data when the specified detection action is completed in the next preset detection cycle.
  • a plurality of maintenance working condition data is input into the predictive analysis model, if the remaining service life of the plurality of detection components of the excavator to be detected does not increase if the predictive analysis model outputs, the predictive analysis model is optimized, here the prediction
  • the analysis model is optimized as any optimization scheme in related technologies.
  • FIG. 4 is a flow chart of the speed drop analysis business in an excavator fault prediction method provided by an embodiment of the present disclosure.
  • the throttle gear of the excavator is The 11th gear
  • the boom, stick, and bucket perform the pressure-holding action at the same time, collect the engine speed and target speed data during the whole action process, calculate the maximum speed drop value according to the engine speed and target speed, and judge whether the maximum speed drop value exceeds 200rpm , if the maximum speed drop value is greater than 200rpm, issue a fault work order directly; if the maximum speed drop value is less than 200rpm, use the engine speed drop value trend prediction algorithm to predict the remaining service life of the engine with a speed drop value greater than 200rpm, according to the remaining service life time Determine whether to deliver the maintenance policy.
  • the present disclosure provides a method for predicting faults of an excavator, which controls the excavator to be detected to perform a specified detection action within a preset detection period, and obtains the excavator to be detected Multiple working condition data of the excavator when the specified detection action is completed; input the multiple working condition data into the pre-trained predictive analysis model, and detect multiple working condition data of the excavator to be detected based on the multiple working condition data Whether each component to be detected is qualified; if it is detected that each component to be detected in a plurality of components to be detected is qualified, analyze the remaining service life of each component to be detected of the excavator to be detected according to the multiple working condition data, and The remaining service life corresponding to each component to be detected of the excavator to be detected and the corresponding maintenance strategy are output.
  • Fig. 5 is one of the structural schematic diagrams of an excavator fault prediction system provided by an embodiment of the present disclosure
  • Fig. 6 is a kind of excavator fault prediction system provided by an embodiment of the present disclosure
  • the prediction system 500 may include:
  • the physical examination module 501 may be configured to control the excavator to be detected to perform a specified detection action within a preset detection period, and obtain the time when the excavator to be detected performs a specified detection action. Specify multiple working condition data when detecting actions;
  • the detection module 502 may be configured to input the plurality of working condition data into a pre-trained predictive analysis model, and detect a plurality of components to be detected of the excavator to be detected based on the plurality of working condition data Eligibility;
  • the determining module 503 may be configured to output a detection that there is a fault among the plurality of components to be detected of the excavator to be detected if it is detected that any component to be detected is unqualified in the plurality of components to be detected Fault information for the component.
  • the determining module 503 may also be configured to:
  • each of the multiple components to be detected If it is detected that each of the multiple components to be detected is qualified, analyze the remaining service life of each component to be detected of the excavator to be detected according to the multiple working condition data, and output the excavator to be detected The remaining service life corresponding to each component to be tested and the corresponding maintenance strategy.
  • the detection module 502 may also be configured to:
  • the detection module 502 when used for analyzing the remaining service life of each component to be detected of the excavator to be detected according to the plurality of working condition data, it may also be configured as Used for:
  • a health characteristic value is determined based on each working condition data of each component to be detected of the excavator to be detected within the preset detection cycle time, and a corresponding health characteristic value is determined. the corresponding running time;
  • the predicted value of the end of life is determined, and the predicted value of the predicted end of life is determined.
  • the runtime corresponding to the value
  • the remaining service life of the component to be tested of the excavator to be tested is determined based on the difference between the running time corresponding to the end-of-life prediction value and the running time corresponding to the health characteristic value .
  • the forecasting system also includes that the optimization module 504 may be configured to:
  • An embodiment of the present disclosure provides an excavator failure prediction system, the prediction system includes: a detection module, which can be configured to control the excavator to be detected to perform a specified detection action within a preset detection period, and When the excavator to be detected performs the specified detection action, a plurality of working condition data of the excavator to be detected is obtained when the specified detection action is completed; the detection module can be configured to input the plurality of working condition data to the In the pre-trained predictive analysis model, it is detected whether the plurality of parts to be inspected of the excavator to be inspected is qualified based on the plurality of working condition data; the determination module can be configured to If any component to be detected is unqualified, output the fault information of the faulty detection component among the plurality of components to be detected of the excavator to be detected.
  • a detection module which can be configured to control the excavator to be detected to perform a specified detection action within a preset detection period, and When the excavator to be detected perform
  • FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.
  • the electronic device 700 includes a processor 710 , a memory 720 and a bus 730 .
  • the memory 720 stores machine-readable instructions executable by the processor 710.
  • the processor 710 communicates with the memory 720 through the bus 730, and the machine-readable instructions are executed by When the processor 710 is executed, it can execute the steps of the excavator failure prediction method in the above method embodiments shown in FIG. 1 and FIG.
  • An embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is run by a processor, it can execute the method in the above-mentioned embodiments shown in FIG. 1 and FIG. 2 .
  • the specific implementation may refer to the method embodiments, and will not be repeated here.
  • the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or may be distributed to multiple network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional module in each embodiment of the present disclosure may be integrated into one processing module, each module may exist separately physically, or two or more modules may be integrated into one module.
  • the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor.
  • the computer software product is stored in a storage medium, including several
  • the 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 various embodiments of the present disclosure.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-OnlyMemory, ROM), random-access memory (RandomAccessMemory, RAM), magnetic disk or optical disk, and various media capable of storing program codes.
  • the present disclosure provides an excavator failure prediction method, system, electronic device and storage medium, which controls the excavator to be detected to perform a specified detection action within a preset detection period, and in the process of performing a specified detection action by the excavator to be detected Acquiring a plurality of working condition data of the excavator to be detected when the specified detection action is completed; inputting the plurality of working condition data into a pre-trained predictive analysis model, and detecting the excavator to be detected based on the plurality of working condition data Whether the plurality of components to be detected is qualified; if it is detected that any of the components to be detected in the plurality of components to be detected is unqualified, then output the fault of the faulty detection component among the multiple components to be detected of the excavator to be detected information.
  • the failure of each component of the excavator in the future is predicted based on the operating data of the excavator collected when the excavator
  • the excavator fault prediction method, device, electronic device and storage medium disclosed in the present disclosure are reproducible and can be used in various industrial applications.
  • the excavator failure prediction method, device, electronic equipment and storage medium disclosed in the present disclosure may be used in the technical field of excavator failure detection.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
  • Component Parts Of Construction Machinery (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

La présente divulgation concerne un procédé et un système de prédiction de défaut d'excavatrice, un dispositif électronique et un support de stockage. Le procédé consiste : à commander, pendant une période de détection prédéfinie, à une excavatrice devant être détectée d'exécuter une action de détection spécifiée, et à obtenir une pluralité de données de condition de travail de ladite excavatrice lorsque ladite excavatrice achève l'action de détection spécifiée dans le processus d'exécution de l'action de détection spécifiée par ladite excavatrice ; à entrer la pluralité de données d'état de travail dans un modèle d'analyse de prédiction pré-formé, et à détecter, sur la base de la pluralité de données de conditions de travail, si une pluralité d'éléments de ladite excavatrice à détecter sont qualifiés ; et s'il est détecté qu'un quelconque élément parmi ladite pluralité d'éléments n'est pas qualifié, à délivrer des informations de défaut de l'élément détecté parmi ladite pluralité d'éléments de ladite excavatrice dans lequel il existe un défaut. L'excavatrice est périodiquement détectée et inspectée pendant la période prédéfinie, et une condition de défaillance de chaque élément de l'excavatrice dans une future période de temps est prédite en fonction des données de fonctionnement de l'excavatrice acquises lorsque l'excavatrice exécute l'action spécifiée.
PCT/CN2022/100752 2021-09-14 2022-06-23 Procédé et appareil de prédiction de défaut d'excavatrice, dispositif électronique et support de stockage WO2023040400A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111071993.8 2021-09-14
CN202111071993.8A CN113779699A (zh) 2021-09-14 2021-09-14 一种挖掘机故障的预测方法、系统、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023040400A1 true WO2023040400A1 (fr) 2023-03-23

Family

ID=78843318

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/100752 WO2023040400A1 (fr) 2021-09-14 2022-06-23 Procédé et appareil de prédiction de défaut d'excavatrice, dispositif électronique et support de stockage

Country Status (2)

Country Link
CN (1) CN113779699A (fr)
WO (1) WO2023040400A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116155964A (zh) * 2023-04-18 2023-05-23 北京徐工汉云技术有限公司 挖掘机工作装置的异常监控系统、方法与装置
CN116991149A (zh) * 2023-09-28 2023-11-03 山西磊源电器有限责任公司 一种费控产品检验方法、装置、电子设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113779699A (zh) * 2021-09-14 2021-12-10 树根互联股份有限公司 一种挖掘机故障的预测方法、系统、电子设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170286854A1 (en) * 2016-03-30 2017-10-05 General Electric Company Automatic revision of a predictive damage model
CN108196985A (zh) * 2017-12-29 2018-06-22 中国电子科技集团公司信息科学研究院 一种基于智能预测的存储系统故障预测方法与装置
CN111178674A (zh) * 2019-12-04 2020-05-19 中国特种设备检测研究院 一种工业大数据驱动的起重机械健康管控服务系统
CN111472410A (zh) * 2020-05-13 2020-07-31 雷沃工程机械集团有限公司 一种挖掘机电气元件故障预报警方法及系统
CN113779699A (zh) * 2021-09-14 2021-12-10 树根互联股份有限公司 一种挖掘机故障的预测方法、系统、电子设备及存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6363332B1 (en) * 1998-12-22 2002-03-26 Caterpillar Inc. Method and apparatus for predicting a fault condition using non-linear curve fitting techniques
US7751955B2 (en) * 2006-06-30 2010-07-06 Spx Corporation Diagnostics data collection and analysis method and apparatus to diagnose vehicle component failures
CN106934126B (zh) * 2017-02-28 2020-03-31 西安交通大学 基于循环神经网络融合的机械零部件健康指标构造方法
KR102045263B1 (ko) * 2018-04-05 2019-11-18 동국대학교 산학협력단 굴삭기 고장 예측 장치 및 이의 동작 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170286854A1 (en) * 2016-03-30 2017-10-05 General Electric Company Automatic revision of a predictive damage model
CN108196985A (zh) * 2017-12-29 2018-06-22 中国电子科技集团公司信息科学研究院 一种基于智能预测的存储系统故障预测方法与装置
CN111178674A (zh) * 2019-12-04 2020-05-19 中国特种设备检测研究院 一种工业大数据驱动的起重机械健康管控服务系统
CN111472410A (zh) * 2020-05-13 2020-07-31 雷沃工程机械集团有限公司 一种挖掘机电气元件故障预报警方法及系统
CN113779699A (zh) * 2021-09-14 2021-12-10 树根互联股份有限公司 一种挖掘机故障的预测方法、系统、电子设备及存储介质

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116155964A (zh) * 2023-04-18 2023-05-23 北京徐工汉云技术有限公司 挖掘机工作装置的异常监控系统、方法与装置
CN116155964B (zh) * 2023-04-18 2023-06-13 北京徐工汉云技术有限公司 挖掘机工作装置的异常监控系统、方法与装置
CN116991149A (zh) * 2023-09-28 2023-11-03 山西磊源电器有限责任公司 一种费控产品检验方法、装置、电子设备及存储介质
CN116991149B (zh) * 2023-09-28 2023-12-08 山西磊源电器有限责任公司 一种费控产品检验方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN113779699A (zh) 2021-12-10

Similar Documents

Publication Publication Date Title
WO2023040400A1 (fr) Procédé et appareil de prédiction de défaut d'excavatrice, dispositif électronique et support de stockage
CN113447290B (zh) 一种工程机械故障预警方法、装置及工程机械
CN111435557B (zh) 用于检测机器部件问题的故障检测装置
US10929820B2 (en) Predictive replacement for heavy machinery
AU2011252963B2 (en) Predictive analysis for remote machine monitoring
JP2018014092A (ja) 機械部品の期待耐用年数の推定方法
US20200401744A1 (en) Rig systems self diagnostics
CN112727965B (zh) 采煤机制动器的故障监测方法及装置
US11222202B2 (en) Targeted testing and machine-learning systems for detecting and identifying machine behavior
WO2016044249A1 (fr) Classificateur de fonctionnement de machine
CN112328703B (zh) 一种基于增量学习的数控设备健康状态诊断装置及方法
CN117176560B (zh) 一种基于物联网的监测设备监管系统及其方法
CN116670608A (zh) 用于物联网预测建模的混合系综方法
CN114139297B (zh) 基于机泵设备状态监测和大数据分析的专家诊断系统
CN110765633A (zh) 一种动力装置的智能管理方法和装置
CN112801199B (zh) 挖掘机动臂寿命预测方法、装置、电子设备及存储介质
WO2023160300A1 (fr) Procédé et dispositif de prédiction de durée de vie restante de pièce structurale, et machine d'exploitation
Petroutsatou et al. Integrated prescriptive maintenance system (PREMSYS) for construction equipment based on productivity
CN109783832A (zh) 一种基于贝叶斯修正的液压泵性能退化建模方法
Kumar et al. An expert system for predictive maintenance of mining excavators and its various forms in open cast mining
US11680591B2 (en) Determining remaining life of a hose assembly based on sensor data
Neelamkavil Condition-based maintenance in facilities management
CN115906938A (zh) 一种矿井齿轮箱油液检测及分析方法、系统机存储介质
KR20230122269A (ko) Ai 기술을 활용한 산업설비 진단 예측 시스템
CN117236511A (zh) 绞吸式挖泥船水下泵真空度的大数据预测方法及装置

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: 22868777

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE