WO2022267879A1 - 一种工程机械故障预警方法、装置及工程机械 - Google Patents

一种工程机械故障预警方法、装置及工程机械 Download PDF

Info

Publication number
WO2022267879A1
WO2022267879A1 PCT/CN2022/097334 CN2022097334W WO2022267879A1 WO 2022267879 A1 WO2022267879 A1 WO 2022267879A1 CN 2022097334 W CN2022097334 W CN 2022097334W WO 2022267879 A1 WO2022267879 A1 WO 2022267879A1
Authority
WO
WIPO (PCT)
Prior art keywords
fault
data
occurrence
preset
construction machinery
Prior art date
Application number
PCT/CN2022/097334
Other languages
English (en)
French (fr)
Inventor
李曾
王佳宇
Original Assignee
上海三一重机股份有限公司
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 上海三一重机股份有限公司 filed Critical 上海三一重机股份有限公司
Publication of WO2022267879A1 publication Critical patent/WO2022267879A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01MTESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00Subject matter not provided for in other groups of this subclass
    • G01M99/005Testing of complete machines, e.g. washing-machines or mobile phones
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/205Parsing
    • G06F40/216Parsing using statistical methods

Definitions

  • the present application relates to the technical field of construction machinery, in particular to a method and device for early warning of construction machinery faults, and construction machinery.
  • Construction machinery such as excavators plays a very important role in engineering construction.
  • the fault detection and fault warning of construction machinery not only affect the service life of construction machinery, but also have an important impact on the completion progress of construction projects.
  • the existing technology is to upload the operation log data of construction machinery to the cloud platform and use big data analysis to determine whether the construction machinery has failed.
  • Early warning because many working states of construction machinery cannot be detected by sensors, the accuracy of failure early warning based on operation log data is low.
  • the embodiment of the present application provides a construction machinery fault early warning method, device and construction machinery to overcome the problem of low accuracy of construction machinery fault early warning in the prior art.
  • an embodiment of the present application provides a construction machinery failure early warning method, including:
  • the frequency of occurrence and the time of occurrence of the preset fault keywords are counted, and the preset fault keywords are used to characterize the abnormal state of the target construction machinery;
  • Fault pre-warning is performed based on the fault prediction data.
  • the prediction of the failure prediction data of the target engineering machinery in the next operation cycle based on the occurrence frequency, occurrence time and corresponding abnormal operation parameters of preset failure keywords includes:
  • the parameter value of the abnormal operation parameter in the next operation cycle is predicted.
  • a filter smoothing algorithm and a time series model are used to predict the occurrence frequency of the preset fault keyword in the next operation cycle and the parameter value of the abnormal operation parameter in the next operation cycle.
  • the performing fault early warning based on the fault prediction data includes:
  • Fault pre-warning is performed based on the current fault level.
  • the method also includes:
  • a maintenance plan is generated based on the fault prediction data.
  • the method also includes:
  • an embodiment of the present application provides a construction machinery failure early warning device, including: an acquisition module, configured to acquire historical usage data and historical operation data of the target engineering machinery, wherein the historical usage data is used to represent Subjective evaluation data of the usage status of the target construction machinery, the historical operation data is parameter data used to characterize the operation state of the target construction machinery;
  • the first processing module is configured to, based on the historical usage data, count the occurrence frequency and occurrence time of preset fault keywords, the preset fault keywords are used to characterize the abnormal state of the target construction machine;
  • the second processing module is configured to perform collaborative filtering on the historical operation data based on the occurrence time of preset fault keywords in the historical usage data to determine abnormal operation parameters;
  • the third processing module is used to predict the failure prediction data of the target construction machine in the next operation cycle based on the frequency of occurrence, occurrence time and abnormal operation parameters of the preset failure keywords;
  • a fourth processing module configured to perform fault warning based on the fault prediction data.
  • an embodiment of the present application provides a construction machine, including: a memory and a processor, the memory and the processor are connected to each other in communication, the memory stores computer instructions, and the processor By executing the computer instructions, the first aspect or the method described in any optional implementation manner of the first aspect is executed.
  • the construction machine is an excavator.
  • the embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to make the computer execute the first aspect, or any of the first aspects A method described in an alternative embodiment.
  • the construction machinery failure early warning method, device and construction machinery use the historical usage data and historical operation data of the target construction machinery; based on the historical usage data, the frequency of occurrence and the time of occurrence of the preset failure keywords are counted; based on The occurrence time of the preset fault keywords in the historical usage data is used to perform collaborative filtering on the historical operation data to determine the abnormal operation parameters; based on the occurrence frequency, occurrence time and abnormal operation parameters of the preset fault keywords, predict the next operation cycle of the target construction machinery Fault prediction data; fault warning based on fault prediction data. Therefore, by using sparse data such as the use of construction machinery and subjective evaluations fed back by construction machinery users, the status of construction machinery that cannot be monitored is analyzed. The fusion of frequency data can accurately locate abnormalities or faults that have a risk of failure, and then carry out timely fault warnings, thereby improving the accuracy of fault warnings and facilitating timely maintenance of construction machinery to extend the service life.
  • Fig. 1 is the flow chart of the engineering machinery failure early warning method of the embodiment of the present application
  • Fig. 2 is the schematic diagram of the working process of engineering machinery failure early warning of the embodiment of the present application
  • FIG. 3 is a schematic structural diagram of a construction machinery fault early warning device according to an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a construction machine according to an embodiment of the present application.
  • Construction machinery such as excavators plays a very important role in engineering construction.
  • the fault detection and fault warning of construction machinery not only affect the service life of construction machinery, but also have an important impact on the completion progress of construction projects.
  • the existing technology is to upload the operation log data of construction machinery to the cloud platform and use big data analysis to determine whether the construction machinery has failed.
  • Early warning because many working states of construction machinery cannot be detected by sensors, the accuracy of failure early warning based on operation log data is low.
  • the embodiment of the present application provides a construction machinery fault early warning method, as shown in Figure 1, the construction machinery fault method provided in the embodiment of the present application specifically includes the following steps:
  • Step S101 Obtain historical usage data and historical operation data of the target construction machine.
  • the historical use data is the subjective evaluation data used to characterize the usage status of the target construction machinery
  • the historical operation data is the parameter data used to characterize the operating state of the target construction machinery.
  • the target construction machine is an excavator as an example.
  • the target construction machine can also be concrete transport vehicles, cranes, forklifts and other projects. Machinery, the present application is not limited thereto.
  • the historical use data is the use log fed back by the user of the target construction machine, and the use log includes the user's regular feedback on the use of the excavator, occasional fault reporting, and the operator's subjective evaluation of the excavator.
  • These data can be used to analyze the monitoring equipment installed on the excavator, such as the operating status of the excavator that cannot be directly sensed by the sensor, and can reflect the operating status of the excavator and possible hidden troubles from the user's intuitive perspective;
  • the historical operating data is The operation data collected by the operation monitoring equipment installed on the excavator, such as: engine speed, fuel consumption, cooling water temperature and other parameters.
  • Step S102 Based on the historical usage data, count the occurrence frequency and occurrence time of the preset failure keywords.
  • the preset fault keywords are used to characterize the abnormal state of the target construction machinery. Specifically, there can be one or more preset failure keywords, and the frequency of occurrence of preset failure keywords can be counted separately, or the travel frequency of all preset keywords can be comprehensively counted. It should be noted that, In the embodiment of the present application, the separate statistics of different preset fault keywords is used as an example for illustration, and the present application is not limited thereto.
  • the preset fault keywords include but are not limited to: engine tremor, black smoke, weak movement, arm drop, etc.
  • words that appear in historical usage data can be determined through big data analysis
  • the default fault keywords can be flexibly set based on the association relationship with construction machinery faults, and this application is not limited thereto.
  • Step S103 Perform collaborative filtering on the historical operating data based on the occurrence time of preset fault keywords in the historical usage data to determine abnormal operating parameters.
  • the preset fault keywords such as "black smoke” appear in the historical usage data
  • the time when "black smoke” appears according to the time when "black smoke” appears Using the collaborative filtering algorithm, it can be analyzed from the historical operating data that it is related to "black smoke” and some abnormal operating parameters of the excavator.
  • the abnormal operation parameters include: the engine speed is too high, the cooling water temperature is too high, etc., and this is only an example, and the present application is not limited thereto.
  • Step S104 Predict the failure prediction data of the target construction machinery in the next operation cycle based on the occurrence frequency, occurrence time and abnormal operation parameters of the preset failure keywords.
  • the failure prediction data is the prediction situation used to characterize the failure situation that may occur in the next operation cycle of the target construction machine.
  • the fault prediction data includes: the occurrence frequency of preset fault keywords in the next operating cycle, specific parameter values of abnormal operating parameters, and the like.
  • Step S105 Carry out fault warning based on the fault prediction data.
  • the construction machinery fault warning method analyzes the state of construction machinery that cannot be monitored by using sparse data such as the use of construction machinery and subjective evaluations fed back by users of construction machinery, and at the same time combines High-frequency data such as the corresponding operating data of construction machinery, through the fusion of low-frequency data and high-frequency data, can accurately locate abnormalities or faults that have a risk of failure, and then provide timely fault warnings, thereby improving the accuracy of fault warnings, which is beneficial to Construction machinery should be maintained in time to prolong its service life.
  • step S104 specifically includes the following steps:
  • Step S201 Predict the frequency of occurrence of the preset fault keywords in the next operation cycle based on the frequency and time of occurrence of the preset fault keywords.
  • the operation cycle can be flexibly set according to the actual maintenance requirements of the excavator and the requirements of the early warning response speed.
  • the operation cycle is 1 month as an example for illustration.
  • the operation period can also be three months, 10 days, half a month, etc., and this application is not limited thereto.
  • the frequency of the preset fault keywords in each historical operation cycle can be determined, so that the excavator can continue to operate in the current state according to the historical operation cycle.
  • the frequency of occurrence in the next operation cycle can be inferred.
  • Step S202 Predict the parameter value of the abnormal operation parameter in the next operation cycle based on the abnormal operation parameter.
  • the abnormal operation parameter is a situation that does not meet the requirements of the normal operation of the excavator.
  • the normal operation of the excavator requires that the cooling water temperature should not be higher than 25°C. If the current cooling water temperature is 30°C, it means that the cooling water The water temperature is an abnormal operation parameter.
  • the change trend of the abnormal operation parameters when the excavator continues to operate according to the current state can be obtained, so as to speculate Output the parameter value corresponding to the abnormal operation parameter in the next operation cycle.
  • a filter smoothing algorithm and a time series model may be used to predict the occurrence frequency of preset fault keywords in the next operation cycle and the parameter values of the abnormal operation parameters in the next operation cycle.
  • the filter smoothing algorithm can eliminate a small amount of data with extremely drastic changes, weaken the irregular fluctuations of the unstable and continuously changing time series data, and then use the time series forecast to obtain the change trend of key parameters, so as to estimate the key parameters more accurately. Next direction of change. For specific working principles and execution processes of related algorithms, reference may be made to related descriptions in the prior art, and details are not repeated here.
  • step S105 specifically includes the following steps:
  • Step S301 Determine the current fault level of the target construction machine based on the relationship between the predicted parameter value of the abnormal operation parameter and the preset parameter threshold, and the predicted occurrence frequency of the fault keyword and the preset frequency threshold.
  • the preset parameter threshold is the parameter peak value of the abnormal operation parameter during normal operation
  • the preset frequency threshold is the frequency peak value of the preset fault keyword when the excavator is running normally.
  • the more the parameter value exceeds the preset parameter threshold the more serious the abnormality of the excavator is, and the greater the probability of its possible failure is.
  • the more the frequency of the preset failure keyword is higher than the frequency peak value it also indicates that the excavator The more serious the abnormality of the excavator, the greater the probability of failure.
  • the abnormal situation reflected by the two can determine the current failure level of the excavator.
  • Step S301 Carry out fault warning based on the current fault level.
  • the fault level of the excavator can be divided into multiple levels according to the actual early warning requirements.
  • three levels are taken as an example.
  • the first level indicates that the excavator has no failure, and the second level indicates that the excavator has a slight failure.
  • the third level indicates that the excavator has a serious fault, etc., and an early warning is given when the current fault level is greater than the first level, so as to remind the maintenance personnel to perform maintenance in time to avoid the expansion of the fault and prolong the service life of the excavator.
  • the fault level can be divided into more levels, and the fault warning is set after the fault reaches a certain fault level. For example, the early warning is only performed when the fault reaches the highest level. This application is not limited to this .
  • the computer program that realizes the above-mentioned construction machinery failure early warning method can be packaged and compiled into a model file, and the corresponding cloud model can be generated. Scanning the QR code on the mobile phone to log in to the system can realize one-key download and refresh of the cloud. model, you can also add the model file for the excavator with a mobile phone.
  • the model file can be automatically updated at regular intervals, such as one month or three months, to include the latest historical data into the model file. In this way, automatic early warning of construction machinery can be realized on the construction machinery side without the participation of external cloud servers. It solves the problem of difficult updating of excavator models under special working conditions such as tunnels and mines.
  • the above-mentioned construction machinery failure early warning method specifically further includes the following steps:
  • Step S106 Generate a maintenance plan based on the fault prediction data.
  • the abnormal operating parameters contained in the fault prediction data such as the engine speed is too high, etc.
  • the engine may be faulty, and a maintenance plan for the engine overhaul can be generated correspondingly, so that the maintenance personnel can carry out more targeted excavation Machine maintenance, improve maintenance efficiency.
  • Step S107 Obtain the first location of the target construction machine and the second location of the maintenance terminal.
  • the maintenance terminal is a user terminal carried by the maintenance personnel, which can be a terminal device such as a mobile phone.
  • the current location of the maintenance personnel can be obtained by using the positioning function of the maintenance terminal.
  • the location of the excavator can be obtained by setting a positioning device on the excavator current location.
  • Step S108 Generate a maintenance route based on the first location and the second location.
  • the existing path planning algorithm can be combined with the map of the construction site to obtain the nearest maintenance route for the maintenance personnel to move to the target excavator, so as to shorten the time-consuming and further improve the maintenance efficiency of the excavator.
  • Step S109 Send the maintenance route and maintenance plan to the maintenance terminal.
  • the optimal maintenance plan can be arranged according to the severity of the corresponding faults and the time-consuming maintenance routes, so as to further improve the maintenance efficiency of construction machinery.
  • FIG. 2 The working process of construction machinery failure early warning is shown in Figure 2.
  • the operator can record the usage data during the daily use of the excavator to form sparse data. matrix; and real-time collection of parameter values of various key parameters during the operation of the excavator to form a high-frequency data matrix. Then, through the data fusion processing of the sparse data matrix and high-frequency data, the decision-making suggestions of the maintenance plan are obtained, and the fault warning function of construction machinery is realized.
  • the above scheme has high flexibility based on the high-frequency historical operation data and the subjective log of operator feedback. It can not only cover the complete working conditions of the excavator, accurately find the deviation of functional parameters, but also dig out the status that the sensor cannot directly monitor; Use the fusion analysis of high and low frequency data to dig out the relationship between faults and operator logs; based on the word frequency of keywords in the operation logs, establish smoothing filtering and collaborative filtering algorithms to find the most risky abnormalities or faults; use mobile phone to log in Control the model update, and you can also use the mobile phone to add the model to the excavator, which solves the problem of difficult model update of excavators under special working conditions such as tunnels and mines. Based on the severity of the abnormality and the spatio-temporal distribution of the excavator, the most time-saving maintenance route is calculated, and the optimal maintenance suggestion is automatically sent to the maintenance engineer.
  • the construction machinery fault warning method analyzes the state of construction machinery that cannot be monitored by using sparse data such as the use of construction machinery and subjective evaluations fed back by users of construction machinery, and at the same time combines High-frequency data such as the corresponding operating data of construction machinery, through the fusion of low-frequency data and high-frequency data, can accurately locate abnormalities or faults that have a risk of failure, and then provide timely fault warnings, thereby improving the accuracy of fault warnings, which is beneficial to Construction machinery should be maintained in time to prolong its service life.
  • the most time-saving maintenance route and maintenance plan are calculated, and optimal maintenance suggestions are automatically sent to maintenance engineers to improve maintenance efficiency.
  • the embodiment of the present application also provides a construction machinery fault early warning device, as shown in Figure 3, the construction machinery fault early warning device specifically includes:
  • the acquisition module 101 is used to acquire historical usage data and historical operation data of the target construction machinery, wherein the historical usage data is subjective evaluation data used to characterize the usage status of the target construction machinery, and the historical operation data is used to characterize the operating state of the target construction machinery parameter data.
  • the historical usage data is subjective evaluation data used to characterize the usage status of the target construction machinery
  • the historical operation data is used to characterize the operating state of the target construction machinery parameter data.
  • the first processing module 102 is configured to count the occurrence frequency and occurrence time of preset fault keywords based on historical usage data.
  • the preset fault keywords are used to characterize the abnormal state of the target construction machine. For details, refer to the relevant description of step S102 in the above method embodiment, and details are not repeated here.
  • the second processing module 103 is configured to perform collaborative filtering on the historical operation data based on the occurrence time of preset fault keywords in the historical usage data to determine abnormal operation parameters. For details, refer to the relevant description of step S103 in the above method embodiment, and details are not repeated here.
  • the third processing module 104 is configured to predict the failure prediction data of the target construction machine in the next operation cycle based on the frequency of occurrence, occurrence time and abnormal operation parameters of preset failure keywords. For details, refer to the relevant description of step S104 in the above method embodiment, and details are not repeated here.
  • the fourth processing module 105 is configured to perform fault warning based on the fault prediction data. For details, refer to the relevant description of step S105 in the above method embodiment, and details are not repeated here.
  • the construction machinery fault early warning device provided in the embodiment of the present application is used to implement the construction machinery fault early warning method provided in the above embodiment, and its implementation method is the same as the principle. For details, please refer to the relevant description of the above method embodiment, and will not repeat them here.
  • the construction machinery fault warning device provided in the embodiment of the present application can monitor the status of construction machinery that cannot be monitored by using sparse data such as the use of construction machinery and subjective evaluations fed back by users of construction machinery. Analysis, combined with high-frequency data such as corresponding operating data of construction machinery, through the fusion of low-frequency data and high-frequency data, it is possible to accurately locate abnormalities or faults with a risk of failure, and then carry out timely fault warnings, thereby improving the accuracy of fault warnings , which is conducive to timely maintenance of construction machinery to prolong the service life.
  • the embodiment of the present application also provides a construction machine.
  • the construction machine includes: a processor 901 and a memory 902, wherein the processor 901 and the memory 902 can be connected through a bus or in other ways.
  • the Take connection via bus as an example.
  • the processor 901 may be a central processing unit (Central Processing Unit, CPU).
  • the processor 901 can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application-specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate array (Field-Programmable Gate Array, FPGA) or Other chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • Other chips such as programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.
  • the memory 902 as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the methods in the above method embodiments.
  • the processor 901 executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the memory 902, that is, implements the methods in the above method embodiments.
  • the memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created by the processor 901 and the like.
  • the memory 902 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices.
  • the storage 902 may optionally include storages that are remotely located relative to the processor 901, and these remote storages may be connected to the processor 901 through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • One or more modules are stored in the memory 902, and when executed by the processor 901, the methods in the foregoing method embodiments are executed.
  • the storage medium can be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive) , abbreviation: HDD) or solid-state drive (Solid-State Drive, SSD), etc.; the storage medium may also include a combination of the above-mentioned types of memory.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请提供了一种工程机械故障预警方法、装置及工程机械,该方法包括:获取目标工程机械的历史使用数据及历史运行数据;基于历史使用数据,统计预设故障关键词的出现频率及其出现时间;基于历史使用数据中预设故障关键词的出现时间对历史运行数据进行协同滤波,确定异常运行参数;基于预设故障关键词的出现频率、出现时间及异常运行参数,预测目标工程机械在下一运行周期的故障预测数据;基于故障预测数据进行故障预警。通过利用工程机械的使用者反馈的工程机械的使用情况及主观评价结合工程机械相应的运行数据,精准定位存在故障风险的异常或故障,进而及时进行故障预警,提高故障预警的精确性,有利于对工程机械进行及时维护、延长使用寿命。

Description

一种工程机械故障预警方法、装置及工程机械
相关申请的交叉引用
本申请要求于2021年6月25日提交的申请号为202110716054.8,发明名称为“一种工程机械故障预警方法、装置及工程机械”的中国专利申请的优先权,其通过引用方式全部并入本文。
技术领域
本申请涉及工程机械技术领域,具体涉及一种工程机械故障预警方法、装置及工程机械。
背景技术
挖掘机等工程机械在工程建设中有着非常重要的作用。工程机械的故障检测和故障预警不仅影响工程机械的使用寿命,也对工程建设项目的完成进度有着重要的影响。
为了解决工程机械的故障预警问题,现有技术是通过将工程机械的运行日志数据上传至云平台,通过利用大数据分析确定工程机械是否发生故障,这种方式虽然能够在一定程度上实现工程机械预警,但是,由于工程机械的很多工作状态无法通过传感器进行检测,造成仅依靠运行日志数据进行故障预警的准确性较低。
发明内容
有鉴于此,本申请实施例提供了一种工程机械故障预警方法、装置及工程机械以克服现有技术中工程机械故障预警准确性低的问题。
根据第一方面,本申请实施例提供了一种工程机械故障预警方法,包括:
获取目标工程机械的历史使用数据及历史运行数据,其中,所述历史使用数据为用于表征所述目标工程机械使用状况的主观评价数据,所述历史运行数据为用于表征所述目标工程机械运行状态的参数数据;
基于所述历史使用数据,统计预设故障关键词的出现频率及其出现时 间,所述预设故障关键词用于表征所述目标工程机械的异常状态;
基于所述历史使用数据中预设故障关键词的出现时间对所述历史运行数据进行协同滤波,确定异常运行参数;
基于预设故障关键词的出现频率、出现时间及异常运行参数,预测所述目标工程机械在下一运行周期的故障预测数据;
基于所述故障预测数据进行故障预警。
可选地,所述基于预设故障关键词的出现频率、出现时间及对应的异常运行参数,预测所述目标工程机械在下一运行周期的故障预测数据,包括:
基于预设故障关键词的出现频率及出现时间,预测所述预设故障关键词在下一运行周期的出现频率;
基于异常运行参数,预测所述异常运行参数在下一运行周期的参数值。
可选地,采用滤波平滑算法和时间序列模型预测所述预设故障关键词在下一运行周期的出现频率以及所述异常运行参数在下一运行周期的参数值。
可选地,所述基于所述故障预测数据进行故障预警,包括:
基于所述异常运行参数的预测参数值与预设参数阈值以及所述故障关键词的预测出现频率与预设频率阈值的关系,确定所述目标工程机械的当前故障等级;
基于所述当前故障等级进行故障预警。
可选地,所述方法还包括:
基于所述故障预测数据及生成维保方案。
可选地,所述方法还包括:
获取所述目标工程机械的第一位置及维保终端的第二位置;
基于所述第一位置和所述第二位置生成维保路线;
将所述维保路线和所述维保方案发送至所述维保终端。
根据第二方面,本申请实施例提供了一种工程机械故障预警装置,包括:获取模块,用于获取目标工程机械的历史使用数据及历史运行数据,其中,所述历史使用数据为用于表征所述目标工程机械使用状况的主观评价数据,所述历史运行数据为用于表征所述目标工程机械运行状态的参数数据;
第一处理模块,用于基于所述历史使用数据,统计预设故障关键词的出现频率及其出现时间,所述预设故障关键词用于表征所述目标工程机械的异常状态;
第二处理模块,用于基于所述历史使用数据中预设故障关键词的出现时间对所述历史运行数据进行协同滤波,确定异常运行参数;
第三处理模块,用于基于预设故障关键词的出现频率、出现时间及异常运行参数,预测所述目标工程机械在下一运行周期的故障预测数据;
第四处理模块,用于基于所述故障预测数据进行故障预警。
根据第三方面,本申请实施例提供了一种工程机械,包括:存储器和处理器,所述存储器和所述处理器之间互相通信连接,所述存储器中存储有计算机指令,所述处理器通过执行所述计算机指令,从而执行第一方面,或者第一方面任意一种可选实施方式中所述的方法。
可选地,所述工程机械为挖掘机。
根据第四方面,本申请实施例提供了一种计算机可读存储介质,所述计算机可读存储介质存储计算机指令,所述计算机指令用于使所述计算机执行第一方面,或者第一方面任意一种可选实施方式中所述的方法。
本申请技术方案,具有如下优点:
本申请实施例提供的工程机械故障预警方法、装置及工程机械,通过目标工程机械的历史使用数据及历史运行数据;基于历史使用数据,统计预设故障关键词的出现频率及其出现时间;基于历史使用数据中预设故障关键词的出现时间对历史运行数据进行协同滤波,确定异常运行参数;基于预设故障关键词的出现频率、出现时间及异常运行参数,预测目标工程机械在下一运行周期的故障预测数据;基于故障预测数据进行故障预警。从而通过利用工程机械的使用者反馈的工程机械的使用情况及主观评价等稀疏数据对无法进行监测的工程机械状态进行分析,同时结合工程机械相应的运行数据等高频数据,通过低频数据与高频数据的融合,可以精准定位存在故障风险的异常或故障,进而及时进行故障预警,从而提高了故障预警的精确性,有利于对工程机械进行及时维护以延长使用寿命。
附图说明
为了更清楚地说明本申请具体实施方式或现有技术中的技术方案,下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图是本申请的一些实施方式,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为本申请实施例的工程机械故障预警方法的流程图;
图2为本申请实施例的工程机械故障预警工作过程的示意图;
图3为本申请实施例的工程机械故障预警装置的结构示意图;
图4为本申请实施例的工程机械的结构示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚,下面将结合本申请实施例中的附图,对本申请实施例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。
下面所描述的本申请不同实施方式中所涉及的技术特征只要彼此之间未构成冲突就可以相互结合。
挖掘机等工程机械在工程建设中有着非常重要的作用。工程机械的故障检测和故障预警不仅影响工程机械的使用寿命,也对工程建设项目的完成进度有着重要的影响。
为了解决工程机械的故障预警问题,现有技术是通过将工程机械的运行日志数据上传至云平台,通过利用大数据分析确定工程机械是否发生故障,这种方式虽然能够在一定程度上实现工程机械预警,但是,由于工程机械的很多工作状态无法通过传感器进行检测,造成仅依靠运行日志数据进行故障预警的准确性较低。
基于上述问题,本申请实施例提供了一种工程机械故障预警方法,如图1所示,本申请实施例提供的工程机械故障方法具体包括如下步骤:
步骤S101:获取目标工程机械的历史使用数据及历史运行数据。
其中,历史使用数据为用于表征目标工程机械使用状况的主观评价数 据,历史运行数据为用于表征目标工程机械运行状态的参数数据。需要说明的是,在本申请实施例中,是以该目标工程机械为挖掘机为例进行的说明,在实际应用中,该目标工程机械还可以是混凝土运输车辆、吊车、铲车等其他工程机械,本申请并不以此为限。
示例性地,该历史使用数据为目标工程机械的用户反馈的使用日志,该使用日志包括用户定时回馈挖掘机使用情况、不定时的故障上报情况及操作手对挖掘机的主观评价等。这些数据可用于对挖掘机上设置的监测设备如传感器不可直接感知的挖掘机运行状态进行分析,可以从用户使用的直观角度反映挖掘机的运行状态及可能发生的故障隐患等;该历史运行数据为挖掘机上设置的运行监测设备所采集的运行数据,如:发动机转速、油耗、冷却水温度等参数。
步骤S102:基于历史使用数据,统计预设故障关键词的出现频率及其出现时间。
其中,预设故障关键词用于表征目标工程机械的异常状态。具体地,该预设故障关键词可以是一个也可以是多个,预设故障关键词的出现频率可以单独统计,也可以将所有预设关键词的出行频率进行综合统计,需要说明的是,在本申请实施例中是以不同预设故障关键词单独统计为例进行的说明,本申请并不以此为限。
示例性地,对于挖掘机而言,该预设故障关键词包括但不限于:发动机颤抖、冒黑烟、动作无力、掉臂等,具体可通过大数据分析来确定历史使用数据中出现的词语与工程机械故障间的关联关系,来灵活设置预设故障关键词,本申请并不以此为限。
步骤S103:基于历史使用数据中预设故障关键词的出现时间对历史运行数据进行协同滤波,确定异常运行参数。
其中,在历史使用数据中出现预设故障关键词如:“冒黑烟”时,则说明此时挖掘机可能存在异常,为了进一步确认挖掘机的工作状态,根据出现“冒黑烟”的时间利用协同滤波算法,可以从历史运行数据中分析出与“冒黑烟”与挖掘机某些异常运行参数有关。示例性地,该异常运行参数包括:发动机转速过高、冷却水温度过高等,仅以此为例,本申请并不以此为限。
步骤S104:基于预设故障关键词的出现频率、出现时间及异常运行参数,预测目标工程机械在下一运行周期的故障预测数据。
其中,该故障预测数据为用于表征目标工程机械在下一运行周期中可能出现故障情况的预测情况。示例性地,该故障预测数据包括:下一运行周期预设故障关键词的出现频率、异常运行参数的具体参数值等。
步骤S105:基于故障预测数据进行故障预警。
通过执行上述步骤,本申请实施例提供的工程机械故障预警方法,通过利用工程机械的使用者反馈的工程机械的使用情况及主观评价等稀疏数据对无法进行监测的工程机械状态进行分析,同时结合工程机械相应的运行数据等高频数据,通过低频数据与高频数据的融合,可以精准定位存在故障风险的异常或故障,进而及时进行故障预警,从而提高了故障预警的精确性,有利于对工程机械进行及时维护以延长使用寿命。
具体地,在一实施例中,上述的步骤S104,具体包括如下步骤:
步骤S201:基于预设故障关键词的出现频率及出现时间,预测预设故障关键词在下一运行周期的出现频率。
具体地,该运行周期可根据挖掘机的实际检修需求及预警响应速度的要求进行灵活的设置,在本申请实施例中以该运行周期为1个月为例进行说明,在实际应用中,该运行周期还可以是三个月、10天、半个月等,本申请并不以此为限。具体地,基于预设故障关键词的出现频率及出现时间,可以确定预设故障关键词在各个历史运行周期中出现的频率,从而可以根据历史运行周期的情况得出挖掘机继续按当前状态运行时预设关键词出现的规律性趋势,从而推测出下一运行周期的出现频率。
步骤S202:基于异常运行参数,预测异常运行参数在下一运行周期的参数值。
具体地,该异常运行参数为不符合挖掘机正常运行是参数要求的情况,示例性地,挖掘机正常运行要求冷却水温度不得高于25℃,如果当前冷却水温度为30℃,则说明冷却水温度为异常运行参数,类似地,基于历史运行数据中在各个历史运行周期中异常运行参数的参数值,可以得出挖掘机继续按当前状态运行时异常运行参数的参数值变化趋势,从而推测出下一运行周期异常运行参数对应的参数值。
示例性地,可以采用滤波平滑算法和时间序列模型预测预设故障关键词在下一运行周期的出现频率以及异常运行参数在下一运行周期的参数值。滤波平滑算法可剔除少量变化极为剧烈的数据,将不稳定的持续变化的时间序列数据的不规则波动予以削弱,然后用时间序列预测得出关键参数的变化趋势,从而更加准确估计关键参数接下来的变化方向。相关算法的具体工作原理及执行过程可参照现有技术中的相关描述,在此不再进行赘述。
具体地,在一实施例中,上述的步骤S105,具体包括如下步骤:
步骤S301:基于异常运行参数的预测参数值与预设参数阈值以及故障关键词的预测出现频率与预设频率阈值的关系,确定目标工程机械的当前故障等级。
其中,该预设参数阈值为异常运行参数正常运行时的参数峰值,类似地,预设频率阈值为挖掘机正常运行时预设故障关键词的频率峰值。参数值超过预设参数阈值越多则说明挖掘机的异常越严重,其可能出现故障的概率越大,类似地,预设故障关键词的出现频率高出频率峰值越多,则也同样说明挖掘机的异常越严重,其可以出现故障的概率越大,综合二者反映的异常情况可确定挖掘机当前的故障等级。
步骤S301:基于当前故障等级进行故障预警。其中,挖掘机的故障等级可根据实际预警需求划分为多个等级,在本申请实施例中以三个等级为例,第一等级表示挖掘机没有故障,第二等级表示挖掘机存在轻微故障,第三等级表示挖掘机存在严重故障等,并在当前故障等级大于第一等级时进行预警,以提醒检修人员及时进行检修,避免故障扩大化,延长挖掘机的使用寿命。此外,在实际应用中,故障等级还可以划分为更多等级,并设置在故障达到某一故障等级后进行故障预警,如只有在达到最高等级时进行预警等,本申请并不以此为限。
具体地,在实际应用中,可以将实现上述工程机械故障预警方法的计算机程序打包编译为一个模型文件,生成对应的云端模型,通过手机二维码扫描登陆***,可以实现一键下载和刷新云端模型,也可以用手机为挖掘机加注该模型文件。模型文件每间隔一定时间如一个月或三个月等可自动实施更新,将最新的历史数据包括进模型文件里。从而实现在不需要外 部云服务器参与的情况下,在工程机械侧即可实现工程机械的自动预警。解决了特殊工况下如隧道和矿井下挖掘机模型更新难的问题。
具体地,在一实施例中,上述的工程机械故障预警方法,具体还包括如下步骤:
步骤S106:基于故障预测数据及生成维保方案。
具体地,可以根据故障预测数据所包含的异常运行参数,如发动机转速过高等,推测发动机可能出现故障,则对应生成对发动机进行检修的维保方案,便于维保人员更有针对性的进行挖掘机的维修,提高维修效率。
步骤S107:获取目标工程机械的第一位置及维保终端的第二位置。
其中,维保终端为维保人员携带的用户终端,可以是手机等终端设备,利用维保终端的定位功能可以获取维保人员当前所在位置,类似地,通过挖掘机上设置定位装置获得挖掘机的当前位置。
步骤S108:基于第一位置和第二位置生成维保路线。
具体地,可以采用现有的路径规划算法结合施工现场的地图,得到维保人员移动至目标挖掘机最近的维保路线,以缩短耗时,进一步提高挖掘机维修效率。
步骤S109:将维保路线和维保方案发送至维保终端。
具体地,通过将维保路线和维保方案发送至维保人员对应的维保终端,便于维保人员对挖掘机的及时维修,并且在实际工况中,维保人员在面对多个待维修工程机械时,可根据各自当前对应的故障严重程度及维保路线的耗时等,排布最优的维保方案,进一步提高工程机械的维修效率。
下面将结合具体应用示例,对本申请实施例提供的工程机械故障预警方法进行详细的说明。
工程机械故障预警的工作过程如图2所示,通过在挖掘机上创建用户端问题快速上报手段和通用化故障记录模板,以供操作手在日常使用挖掘机的过程中记录使用数据,构成稀疏数据矩阵;并实时采集挖掘机运行过程中的各个关键参数的参数值,构成高频数据矩阵。然后通过对稀疏数据矩阵和高频数据就在的数据融合处理后,得到维保计划的决策建议,实现工程机械的故障预警功能。
工作原理:通过用户定时回馈挖掘机使用情况和不定时的上报故障, 获取操作手对挖掘机工况的主观评价,对传感器不可直接感知的状态都能进行分析;利用高频数据监控挖掘机动力***和液压***的核心参数,诊断常见的明显故障,利用低频数据感知传感器不能监控的状态,如发动机颤抖、冒黑烟或者动作无力、掉臂等;统计操作手上传的日志里的关键词的词频,基于滤波平滑算法和时间序列,剔除少量变化极为剧烈的数据,将不稳定的持续变化的时间序列数据的不规则波动予以削弱,然后用时间序列预测得出关键参数的变化趋势;同时基于协同过滤算法处理相同时间范围内的运行数据,利用这段时间内的用户反馈,例如机器无力,与采集的表征挖掘机工况的高频数据做协同过滤,从而分析最具有风险的参数异常或者故障状态,例如发动机掉速,液压泵输出功率低等,从而估计关键参数接下来的变化方向;根据统计分析结果,计算异常上报的频率和异常值偏离正常阈值,判断异常的严重程度,得到维保方案,然后根据操作手的时空分布,以及维保工程师现在的位置,统计维保工程师到达所有挖掘机现场的所有可行的路线和耗费的时间,加上根据工程师既往经验估算的维修所需要的时间,从而计算出总耗时最短的维保路线,自动为维保工程师推荐维保计划。
上述方案通过基于高频历史运行数据和操作手反馈的主观日志,灵活性高,既可以覆盖挖掘机的完整工况,准确的发现功能参数的偏移,还可以挖掘传感器不能直接监控的状态;利用高低频数据的融合分析,挖掘出故障和操作手日志间的关系;基于操作日志里的关键词的词频,建立起平滑滤波和协同过滤算法,找到最有风险的异常或者故障;利用手机登录控制模型更新,也可以用手机为挖掘机加注模型,解决了特殊工况下如隧道和矿井下挖掘机模型更新难的问题。以异常严重程度和挖掘机的时空分布作为决策依据,计算出最省时的维保路线,自动为维保工程师推送最优维护建议。
通过执行上述步骤,本申请实施例提供的工程机械故障预警方法,通过利用工程机械的使用者反馈的工程机械的使用情况及主观评价等稀疏数据对无法进行监测的工程机械状态进行分析,同时结合工程机械相应的运行数据等高频数据,通过低频数据与高频数据的融合,可以精准定位存在故障风险的异常或故障,进而及时进行故障预警,从而提高了故障预警 的精确性,有利于对工程机械进行及时维护以延长使用寿命。以异常严重程度和工程机械的时空分布作为决策依据,计算出最省时的维保路线和维保方案,自动为维保工程师推送最优维护建议,提高维保效率。
本申请实施例还提供了一种工程机械故障预警装置,如图3所示,该工程机械故障预警装置具体包括:
获取模块101,用于获取目标工程机械的历史使用数据及历史运行数据,其中,历史使用数据为用于表征目标工程机械使用状况的主观评价数据,历史运行数据为用于表征目标工程机械运行状态的参数数据。详细内容参见上述方法实施例中步骤S101的相关描述,在此不再进行赘述。
第一处理模块102,用于基于历史使用数据,统计预设故障关键词的出现频率及其出现时间,预设故障关键词用于表征目标工程机械的异常状态。详细内容参见上述方法实施例中步骤S102的相关描述,在此不再进行赘述。
第二处理模块103,用于基于历史使用数据中预设故障关键词的出现时间对历史运行数据进行协同滤波,确定异常运行参数。详细内容参见上述方法实施例中步骤S103的相关描述,在此不再进行赘述。
第三处理模块104,用于基于预设故障关键词的出现频率、出现时间及异常运行参数,预测目标工程机械在下一运行周期的故障预测数据。详细内容参见上述方法实施例中步骤S104的相关描述,在此不再进行赘述。
第四处理模块105,用于基于故障预测数据进行故障预警。详细内容参见上述方法实施例中步骤S105的相关描述,在此不再进行赘述。
本申请实施例提供的工程机械故障预警装置,用于执行上述实施例提供的工程机械故障预警方法,其实现方式与原理相同,详细内容参见上述方法实施例的相关描述,不再赘述。
通过上述各个组成部分的协同合作,本申请实施例提供的工程机械故障预警装置,通过利用工程机械的使用者反馈的工程机械的使用情况及主观评价等稀疏数据对无法进行监测的工程机械状态进行分析,同时结合工程机械相应的运行数据等高频数据,通过低频数据与高频数据的融合,可以精准定位存在故障风险的异常或故障,进而及时进行故障预警,从而提高了故障预警的精确性,有利于对工程机械进行及时维护以延长使用寿命。
本申请实施例还提供了一种工程机械,如图4所示,该工程机械包括:处理器901和存储器902,其中,处理器901和存储器902可以通过总线或者其他方式连接,图4中以通过总线连接为例。
处理器901可以为中央处理器(Central Processing Unit,CPU)。处理器901还可以为其他通用处理器、数字信号处理器(Digital Signal Processor,DSP)、专用集成电路(Application Specific Integrated Circuit,ASIC)、现场可编程门阵列(Field-Programmable Gate Array,FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等芯片,或者上述各类芯片的组合。
存储器902作为一种非暂态计算机可读存储介质,可用于存储非暂态软件程序、非暂态计算机可执行程序以及模块,如上述方法实施例中的方法所对应的程序指令/模块。处理器901通过运行存储在存储器902中的非暂态软件程序、指令以及模块,从而执行处理器的各种功能应用以及数据处理,即实现上述方法实施例中的方法。
存储器902可以包括存储程序区和存储数据区,其中,存储程序区可存储操作***、至少一个功能所需要的应用程序;存储数据区可存储处理器901所创建的数据等。此外,存储器902可以包括高速随机存取存储器,还可以包括非暂态存储器,例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施例中,存储器902可选包括相对于处理器901远程设置的存储器,这些远程存储器可以通过网络连接至处理器901。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
一个或者多个模块存储在存储器902中,当被处理器901执行时,执行上述方法实施例中的方法。
上述控制器具体细节可以对应参阅上述方法实施例中对应的相关描述和效果进行理解,此处不再赘述。
本领域技术人员可以理解,实现上述实施例方法中的全部或部分流程,是可以通过计算机程序来指令相关的硬件来完成,实现的程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,存储介质可为磁碟、光盘、只读存储记忆体(Read-Only  Memory,ROM)、随机存储记忆体(Random Access Memory,RAM)、快闪存储器(Flash Memory)、硬盘(Hard Disk Drive,缩写:HDD)或固态硬盘(Solid-State Drive,SSD)等;存储介质还可以包括上述种类的存储器的组合。
虽然结合附图描述了本申请的实施例,但是本领域技术人员可以在不脱离本申请的精神和范围的情况下作出各种修改和变型,这样的修改和变型均落入由所附权利要求所限定的范围之内。

Claims (10)

  1. 一种工程机械故障预警方法,包括:
    获取目标工程机械的历史使用数据及历史运行数据,其中,所述历史使用数据为用于表征所述目标工程机械使用状况的主观评价数据,所述历史运行数据为用于表征所述目标工程机械运行状态的参数数据;
    基于所述历史使用数据,统计预设故障关键词的出现频率及其出现时间,所述预设故障关键词用于表征所述目标工程机械的异常状态;
    基于所述历史使用数据中预设故障关键词的出现时间对所述历史运行数据进行协同滤波,确定异常运行参数;
    基于预设故障关键词的出现频率、出现时间及异常运行参数,预测所述目标工程机械在下一运行周期的故障预测数据;
    基于所述故障预测数据进行故障预警。
  2. 根据权利要求1所述的方法,其中,所述基于预设故障关键词的出现频率、出现时间及对应的异常运行参数,预测所述目标工程机械在下一运行周期的故障预测数据,包括:
    基于预设故障关键词的出现频率及出现时间,预测所述预设故障关键词在下一运行周期的出现频率;
    基于异常运行参数,预测所述异常运行参数在下一运行周期的参数值。
  3. 根据权利要求2所述的方法,其中,所述基于所述故障预测数据进行故障预警,包括:
    基于所述异常运行参数的预测参数值与预设参数阈值以及所述故障关键词的预测出现频率与预设频率阈值的关系,确定所述目标工程机械的当前故障等级;
    基于所述当前故障等级进行故障预警。
  4. 根据权利要求1所述的方法,还包括:
    基于所述故障预测数据及生成维保方案。
  5. 根据权利要求4所述的方法,还包括:
    获取所述目标工程机械的第一位置及维保终端的第二位置;
    基于所述第一位置和所述第二位置生成维保路线;
    将所述维保路线和所述维保方案发送至所述维保终端。
  6. 根据权利要求2所述的方法,其中,
    采用滤波平滑算法和时间序列模型预测所述预设故障关键词在下一运行周期的出现频率以及所述异常运行参数在下一运行周期的参数值。
  7. 一种工程机械故障预警装置,包括:
    获取模块,用于获取目标工程机械的历史使用数据及历史运行数据,其中,所述历史使用数据为用于表征所述目标工程机械使用状况的主观评价数据,所述历史运行数据为用于表征所述目标工程机械运行状态的参数数据;
    第一处理模块,用于基于所述历史使用数据,统计预设故障关键词的出现频率及其出现时间,所述预设故障关键词用于表征所述目标工程机械的异常状态;第二处理模块,用于基于所述历史使用数据中预设故障关键词的出现时间对所述历史运行数据进行协同滤波,确定异常运行参数;
    第三处理模块,用于基于预设故障关键词的出现频率、出现时间及异常运行参数,预测所述目标工程机械在下一运行周期的故障预测数据;
    第四处理模块,用于基于所述故障预测数据进行故障预警。
  8. 一种工程机械,包括:
    存储器和处理器,所述存储器和所述处理器之间互相通信连接,所述存储器中存储有计算机指令,所述处理器通过执行所述计算机指令,从而执行权利要求1-6任一项所述的方法。
  9. 根据权利要求8所述的工程机械,其中,所述工程机械为挖掘机。
  10. 一种计算机可读存储介质,其中,所述计算机可读存储介质存储有计算机指令,所述计算机指令用于使所述计算机执行如权利要求1-6任一项所述的方法。
PCT/CN2022/097334 2021-06-25 2022-06-07 一种工程机械故障预警方法、装置及工程机械 WO2022267879A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110716054.8 2021-06-25
CN202110716054.8A CN113447290B (zh) 2021-06-25 2021-06-25 一种工程机械故障预警方法、装置及工程机械

Publications (1)

Publication Number Publication Date
WO2022267879A1 true WO2022267879A1 (zh) 2022-12-29

Family

ID=77813379

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/097334 WO2022267879A1 (zh) 2021-06-25 2022-06-07 一种工程机械故障预警方法、装置及工程机械

Country Status (2)

Country Link
CN (1) CN113447290B (zh)
WO (1) WO2022267879A1 (zh)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115689534A (zh) * 2022-12-30 2023-02-03 北京飞利信信息安全技术有限公司 基于大数据的设备寿命管理的方法、装置、设备及介质
CN115935243A (zh) * 2023-03-01 2023-04-07 武汉同创万智数字科技有限公司 一种基于数据处理的故障分析方法
CN116030422A (zh) * 2023-03-28 2023-04-28 深圳市海威恒泰智能科技有限公司 一种可视化视频监控智能运维管理***
CN116105885A (zh) * 2023-02-28 2023-05-12 镇江默勒电器有限公司 一种核电用电气设备状态监测方法及***
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***、方法与装置
CN116260235A (zh) * 2023-03-11 2023-06-13 傲视恒安科技(北京)有限公司 电源切换的方法、装置、电子设备及可读存储介质
CN116383606A (zh) * 2023-03-17 2023-07-04 无锡市第五人民医院 一种分布式医疗设备的恒流温度采集方法及***
CN116796261A (zh) * 2023-08-16 2023-09-22 宁波天安菁华电力科技有限公司 一种基于人工智能的封闭开关设备机械特性预测方法
CN116882639A (zh) * 2023-09-08 2023-10-13 山东立鑫石油机械制造有限公司 基于大数据分析的石油钻采设备管理方法及***
CN116956076A (zh) * 2023-09-20 2023-10-27 奇点数联(北京)科技有限公司 一种用户数量异常状态的提示***
CN117092974A (zh) * 2023-09-12 2023-11-21 温州天瑞化纤有限公司 一种纺粘无纺布车间智能开关控制***
CN117131425A (zh) * 2023-10-25 2023-11-28 广东德力宏展智能装备有限公司 一种基于反馈数据的数控机床加工状态监测方法及***
CN117145752A (zh) * 2023-10-26 2023-12-01 意朗智能科技(南通)有限公司 用于空压机的过滤故障识别方法及***
CN117496445A (zh) * 2023-12-12 2024-02-02 山东德才建设有限公司 一种建筑施工设备故障预测方法、设备及介质
CN117494027A (zh) * 2023-12-29 2024-02-02 宁德时代新能源科技股份有限公司 搅拌设备的故障监测方法、设备、***和存储介质
CN117514885A (zh) * 2023-11-23 2024-02-06 德州隆达空调设备集团有限公司 一种轴流风机的故障检测方法及装置
CN117706402A (zh) * 2023-12-13 2024-03-15 石家庄开发区天远科技有限公司 工程机械电瓶的健康状态评价方法、装置及***
CN117742303A (zh) * 2024-02-07 2024-03-22 珠海市运泰利电子有限公司 一种生产自动化设备检测方法、***和介质
CN117786385A (zh) * 2023-12-26 2024-03-29 嘉兴欣晟电机股份有限公司 基于孪生网络的三相异步电动机故障监测方法及***

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113447290B (zh) * 2021-06-25 2022-11-29 上海三一重机股份有限公司 一种工程机械故障预警方法、装置及工程机械
CN113985834A (zh) * 2021-12-30 2022-01-28 柳工常州机械有限公司 工程车及其自动优化控制***
CN115115116A (zh) * 2022-04-06 2022-09-27 深圳市玄羽科技有限公司 应用于工业互联网的故障预测方法及相关设备
CN116027724B (zh) * 2022-09-23 2024-01-12 河北东来工程技术服务有限公司 一种船舶设备风险监控方法和***
CN115817178A (zh) * 2022-11-14 2023-03-21 宁德时代新能源科技股份有限公司 故障预警方法、装置、电池、车辆及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160161375A1 (en) * 2014-12-05 2016-06-09 General Electric Company Text-mining approach for diagnostics and prognostics using temporal multidimensional sensor observations
CN108170581A (zh) * 2017-12-27 2018-06-15 北京奇艺世纪科技有限公司 一种故障预警方法、装置及电子设备
CN109815096A (zh) * 2017-11-20 2019-05-28 北京绪水互联科技有限公司 设备故障的分类统计方法和***及基于关键词统计的设备实时质控方法和***
CN110727531A (zh) * 2019-09-18 2020-01-24 上海麦克风文化传媒有限公司 一种线上***的故障预测及处理方法及***
CN113447290A (zh) * 2021-06-25 2021-09-28 上海三一重机股份有限公司 一种工程机械故障预警方法、装置及工程机械

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2566554C (en) * 2006-10-31 2010-07-20 2012244 Ontario Inc. Handheld electronic device with text disambiguation and selective disabling of frequency learning
JP2009217770A (ja) * 2008-03-13 2009-09-24 Nec Corp 故障予測通知システム、故障予測通知方法、故障予測通知プログラムおよびプログラム記録媒体
CN105589795A (zh) * 2014-12-31 2016-05-18 ***股份有限公司 基于预测模型的磁盘故障预测方法及装置
EP3151131A1 (en) * 2015-09-30 2017-04-05 Hitachi, Ltd. Apparatus and method for executing an automated analysis of data, in particular social media data, for product failure detection
US10127125B2 (en) * 2016-10-21 2018-11-13 Accenture Global Solutions Limited Application monitoring and failure prediction
GB201621631D0 (en) * 2016-12-19 2017-02-01 Palantir Technologies Inc Predictive modelling
CN109902153B (zh) * 2019-04-02 2020-11-06 杭州安脉盛智能技术有限公司 基于自然语言处理和案例推理的设备故障诊断方法及***

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160161375A1 (en) * 2014-12-05 2016-06-09 General Electric Company Text-mining approach for diagnostics and prognostics using temporal multidimensional sensor observations
CN109815096A (zh) * 2017-11-20 2019-05-28 北京绪水互联科技有限公司 设备故障的分类统计方法和***及基于关键词统计的设备实时质控方法和***
CN108170581A (zh) * 2017-12-27 2018-06-15 北京奇艺世纪科技有限公司 一种故障预警方法、装置及电子设备
CN110727531A (zh) * 2019-09-18 2020-01-24 上海麦克风文化传媒有限公司 一种线上***的故障预测及处理方法及***
CN113447290A (zh) * 2021-06-25 2021-09-28 上海三一重机股份有限公司 一种工程机械故障预警方法、装置及工程机械

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115689534A (zh) * 2022-12-30 2023-02-03 北京飞利信信息安全技术有限公司 基于大数据的设备寿命管理的方法、装置、设备及介质
CN116105885A (zh) * 2023-02-28 2023-05-12 镇江默勒电器有限公司 一种核电用电气设备状态监测方法及***
CN116105885B (zh) * 2023-02-28 2023-12-12 镇江默勒电器有限公司 一种核电用电气设备状态监测方法及***
CN115935243A (zh) * 2023-03-01 2023-04-07 武汉同创万智数字科技有限公司 一种基于数据处理的故障分析方法
CN115935243B (zh) * 2023-03-01 2023-09-15 华谋咨询技术(深圳)有限公司 一种基于数据处理的故障分析方法
CN116260235A (zh) * 2023-03-11 2023-06-13 傲视恒安科技(北京)有限公司 电源切换的方法、装置、电子设备及可读存储介质
CN116260235B (zh) * 2023-03-11 2023-08-22 傲视恒安科技(北京)有限公司 电源切换的方法、装置、电子设备及可读存储介质
CN116383606B (zh) * 2023-03-17 2023-10-20 无锡市第五人民医院 一种分布式医疗设备的恒流温度采集方法及***
CN116383606A (zh) * 2023-03-17 2023-07-04 无锡市第五人民医院 一种分布式医疗设备的恒流温度采集方法及***
CN116030422A (zh) * 2023-03-28 2023-04-28 深圳市海威恒泰智能科技有限公司 一种可视化视频监控智能运维管理***
CN116030422B (zh) * 2023-03-28 2023-05-30 深圳市海威恒泰智能科技有限公司 一种可视化视频监控智能运维管理***
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***、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***、方法与装置
CN116796261A (zh) * 2023-08-16 2023-09-22 宁波天安菁华电力科技有限公司 一种基于人工智能的封闭开关设备机械特性预测方法
CN116796261B (zh) * 2023-08-16 2023-11-07 宁波天安菁华电力科技有限公司 一种基于人工智能的封闭开关设备机械特性预测方法
CN116882639A (zh) * 2023-09-08 2023-10-13 山东立鑫石油机械制造有限公司 基于大数据分析的石油钻采设备管理方法及***
CN116882639B (zh) * 2023-09-08 2023-12-08 山东立鑫石油机械制造有限公司 基于大数据分析的石油钻采设备管理方法及***
CN117092974A (zh) * 2023-09-12 2023-11-21 温州天瑞化纤有限公司 一种纺粘无纺布车间智能开关控制***
CN116956076A (zh) * 2023-09-20 2023-10-27 奇点数联(北京)科技有限公司 一种用户数量异常状态的提示***
CN116956076B (zh) * 2023-09-20 2024-01-05 奇点数联(北京)科技有限公司 一种用户数量异常状态的提示***
CN117131425B (zh) * 2023-10-25 2024-02-27 广东德力宏展智能装备有限公司 一种基于反馈数据的数控机床加工状态监测方法及***
CN117131425A (zh) * 2023-10-25 2023-11-28 广东德力宏展智能装备有限公司 一种基于反馈数据的数控机床加工状态监测方法及***
CN117145752B (zh) * 2023-10-26 2024-01-30 意朗智能科技(南通)有限公司 用于空压机的过滤故障识别方法及***
CN117145752A (zh) * 2023-10-26 2023-12-01 意朗智能科技(南通)有限公司 用于空压机的过滤故障识别方法及***
CN117514885A (zh) * 2023-11-23 2024-02-06 德州隆达空调设备集团有限公司 一种轴流风机的故障检测方法及装置
CN117514885B (zh) * 2023-11-23 2024-05-10 德州隆达空调设备集团有限公司 一种轴流风机的故障检测方法及装置
CN117496445A (zh) * 2023-12-12 2024-02-02 山东德才建设有限公司 一种建筑施工设备故障预测方法、设备及介质
CN117496445B (zh) * 2023-12-12 2024-04-09 山东德才建设有限公司 一种建筑施工设备故障预测方法、设备及介质
CN117706402A (zh) * 2023-12-13 2024-03-15 石家庄开发区天远科技有限公司 工程机械电瓶的健康状态评价方法、装置及***
CN117786385A (zh) * 2023-12-26 2024-03-29 嘉兴欣晟电机股份有限公司 基于孪生网络的三相异步电动机故障监测方法及***
CN117786385B (zh) * 2023-12-26 2024-05-17 嘉兴欣晟电机股份有限公司 基于孪生网络的三相异步电动机故障监测方法及***
CN117494027A (zh) * 2023-12-29 2024-02-02 宁德时代新能源科技股份有限公司 搅拌设备的故障监测方法、设备、***和存储介质
CN117494027B (zh) * 2023-12-29 2024-05-17 宁德时代新能源科技股份有限公司 搅拌设备的故障监测方法、设备、***和存储介质
CN117742303A (zh) * 2024-02-07 2024-03-22 珠海市运泰利电子有限公司 一种生产自动化设备检测方法、***和介质
CN117742303B (zh) * 2024-02-07 2024-05-14 珠海市运泰利电子有限公司 一种生产自动化设备检测方法、***和介质

Also Published As

Publication number Publication date
CN113447290A (zh) 2021-09-28
CN113447290B (zh) 2022-11-29

Similar Documents

Publication Publication Date Title
WO2022267879A1 (zh) 一种工程机械故障预警方法、装置及工程机械
CN112152830B (zh) 一种智能的故障根因分析方法及***
CA2799402C (en) Cycle decomposition analysis for remote machine monitoring
US10657450B2 (en) Systems and methods for machine diagnostics based on stored machine data and available machine telematic data
CN116880412B (zh) 一种基于云的可视化生产管理平台
CN113112086A (zh) 一种基于边缘计算和标识解析的智能生产***
CN102323505B (zh) 一种支持光器件寿命预测和失效原因分析的装置和方法
CN113708493B (zh) 基于云边协同的配电终端运维方法、装置和计算机设备
CN105512812A (zh) 基于动态仿真模型的核电厂设备故障预警分析方法及***
CN104238491B (zh) 用于基于工业自动化流的数据处理的信息平台
CN116645010B (zh) 一种化工安全生产巡控***
CN104639368A (zh) 通信网络设备的故障处理方法及装置
WO2023040400A1 (zh) 一种挖掘机故障的预测方法、装置、电子设备及存储介质
CN114862275B (zh) 基于数字孪生模型的仓储物流***可靠性评估方法及***
CN104407959A (zh) 基于应用的监控方法及监控装置
CN110879151B (zh) 基于运行大数据的燃气轮机远程监测和诊断***及方法
CN116755964A (zh) 一种加固服务器的故障预测与健康管理***
CN110765633A (zh) 一种动力装置的智能管理方法和装置
CN111476381A (zh) 基于国产化信息技术创新应用***运维服务的方法和***
CN111160598A (zh) 一种基于动态能耗基准的能源预测与能耗管控方法及***
CN114726708A (zh) 一种基于人工智能的网元设备故障预测方法及***
CN117435883A (zh) 一种基于数字孪生的设备故障预测的方法和***
CN102158521A (zh) 基于以太网的电脑横机在线测控***
EP3885854B1 (en) Data analysis method, device and system
CN104699597A (zh) 基于unix操作***的计算软件监控***

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: 22827375

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22827375

Country of ref document: EP

Kind code of ref document: A1