WO2022219997A1 - 故障予測システム - Google Patents
故障予測システム Download PDFInfo
- Publication number
- WO2022219997A1 WO2022219997A1 PCT/JP2022/011789 JP2022011789W WO2022219997A1 WO 2022219997 A1 WO2022219997 A1 WO 2022219997A1 JP 2022011789 W JP2022011789 W JP 2022011789W WO 2022219997 A1 WO2022219997 A1 WO 2022219997A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- inspection
- unit
- failure
- acquisition unit
- data
- Prior art date
Links
- 230000007257 malfunction Effects 0.000 title abstract 4
- 238000007689 inspection Methods 0.000 claims abstract description 132
- 230000008439 repair process Effects 0.000 claims abstract description 59
- 238000013500 data storage Methods 0.000 description 21
- 238000012545 processing Methods 0.000 description 21
- 238000012423 maintenance Methods 0.000 description 19
- 238000000034 method Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 230000032683 aging Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0267—Fault communication, e.g. human machine interface [HMI]
- G05B23/0272—Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user
Definitions
- the present invention relates to a failure prediction system that predicts failures of working machines such as hydraulic excavators.
- Patent Literature 1 discloses a failure prediction system that improves prediction accuracy by learning while comparing failure prediction values and results (whether or not an event has occurred) for a predetermined period of time.
- the present invention was made to solve such technical problems, and aims to provide a failure prediction system capable of improving the accuracy of failure prediction.
- a failure prediction system is a failure prediction system that predicts a failure of a working machine, and includes an operation information acquisition unit that acquires operation information of the work machine, and an inspection information acquisition unit that acquires inspection information of the work machine.
- a part replacement/repair information acquisition unit that acquires part replacement/repair information of the work machine; the operation information acquired by the operation information acquisition unit; the inspection information acquired by the inspection information acquisition unit; For each part of the work machine based on the parts replacement/repair information acquired by the information acquisition unit and the discrepancy information between the failure probability for each part of the work machine and the inspection results of the work machine stored in the storage unit It is characterized by comprising a failure prediction unit that predicts the failure probability of
- the failure prediction unit includes operation information acquired by the operation information acquisition unit, inspection information acquired by the inspection information acquisition unit, and parts replacement/repair information acquired by the parts replacement/repair information acquisition unit. , and the failure probability for each part of the work machine is predicted based on the deviation information between the failure probability for each part of the work machine and the inspection results of the work machine stored in the storage unit. In this way, the accuracy of failure prediction can be improved by adding inspection information, parts replacement/repair information, and discrepancy information between the failure probability and inspection results to the operating information of the work machine to predict the failure probability. .
- FIG. 1 is a schematic configuration diagram showing a failure prediction system according to an embodiment
- FIG. 1 is a block diagram showing a failure prediction system according to an embodiment
- FIG. It is a figure which shows an example of failure probability data. It is a figure which shows an example of inspection item data. It is a figure which shows an example of main component data.
- 4 is a flowchart showing control processing of a server; 4 is a flowchart showing control processing regarding an inspection item screen of a mobile terminal; 4 is a flow chart showing control processing related to the main component screen of the mobile terminal; 7 is a flow chart showing control processing relating to a failure probability screen of a mobile terminal; It is a figure which shows an example of the inspection item screen of a portable terminal.
- FIG. 11 is a schematic configuration diagram showing a modification of the failure prediction system
- FIG. 11 is a schematic configuration diagram showing a modification of the failure prediction system
- Part basically has a larger range than “part”.
- the part “front” is composed of parts such as a boom, an arm and a bucket.
- parts such as a boom, an arm and a bucket.
- an “engine” it may be a part or a part. Therefore, depending on the contents, there are cases where the same part is referred to as a part and a part.
- FIG. 1 is a schematic configuration diagram showing the failure prediction system according to the embodiment
- FIG. 2 is a block diagram showing the failure prediction system according to the embodiment.
- a failure prediction system 1 according to the present embodiment includes a plurality of hydraulic excavators 10, a server 20 configured to be able to communicate with each of these hydraulic excavators 10 via a network 40, and a server 20 and hydraulic excavators via the network 40. 10 and mobile terminals 30 capable of communicating with each other.
- the hydraulic excavator 10 is shipped from the manufacturer's factory and used by a predetermined user (for example, the owner or user of the hydraulic excavator) at a work site where civil engineering work, construction work, demolition work, dredging work, or the like is performed. .
- the hydraulic excavator 10 is provided with an operation data collection unit 101 .
- the operation data collection unit 101 is, for example, a part of the control unit that controls the entire hydraulic excavator 10, and transmits the operation data of the hydraulic excavator 10 to the server 20 or the mobile terminal 30 together with its own identification number. Note that transmission to the server 20 and the mobile terminal 30 is performed periodically (for example, once a day).
- the mobile terminal 30 is, for example, a smart phone, a tablet terminal, a mobile phone, a PDA (Personal Data Assistant), or the like, and is carried by a maintenance worker or user of the hydraulic excavator 10 .
- a maintenance worker or a user can request information such as inspection items related to a specific hydraulic excavator 10 via the mobile terminal 30, for example.
- the identification number of the specific hydraulic excavator 10 is directly input into the input unit 304 of the mobile terminal 30, By selecting the identification number of the specific hydraulic excavator 10 displayed on the input unit 304 , a request is made to the server 20 via the mobile terminal 30 .
- the mobile terminal 30 has an inspection item screen 301 , a main parts screen 302 , a failure probability screen (display section) 303 and an input section 304 .
- the inspection item screen 301, the main parts screen 302, and the failure probability screen 303 can be switched by selection by maintenance personnel or the user. A detailed description of these screens will be given later.
- the input unit 304 is for receiving input from maintenance personnel or users, and is composed of, for example, a touch panel displayed on the display of the mobile terminal 30, a keyboard, and the like. As described above, when maintenance personnel or users desire information such as inspection items for a particular hydraulic excavator 10 , they can request the server 20 by inputting an identification number into the input unit 304 .
- inspection information for example, inspection results
- identification number of the hydraulic excavator 10 is sent to the server. 20.
- a maintenance worker replaces or repairs a part of the hydraulic excavator 10
- he/she can use the input unit 304 to obtain a work-related number as a management number along with the replacement or repair of the part.
- data relating to the work-related number is transmitted to the server 20 as part replacement/repair information.
- the operator when an operator performs inspection work based on a failure probability predicted by a failure prediction unit 205, which will be described later, the operator inputs the actual inspection results into the input unit 304 together with the identification number of the hydraulic excavator 10, and sends it to the server 20. can be sent.
- the server 20 learns the results by comparing actual values and predicted values based on actual inspection results based on the input results.
- the server 20 is a main computer that constitutes the failure prediction system 1, and is installed in the head office, branch office, factory, or management center of the manufacturer of the hydraulic excavator 10. , and these hydraulic excavators 10 are centrally managed.
- the server 20 includes, for example, a CPU (Central Processing Unit) that executes calculations, a ROM (Read Only Memory) as a secondary storage device that stores programs for calculations, and storage of calculation progress and temporary control variables. It is composed of a microcomputer combined with a RAM (Random Access Memory) as a temporary storage device, and performs processing such as calculation and judgment by executing a stored program.
- a CPU Central Processing Unit
- ROM Read Only Memory
- RAM Random Access Memory
- the server 20 predicts the failure probability of each part of the hydraulic excavator 10 based on the operation data of the hydraulic excavator 10 to be managed, and transmits the predicted result to the mobile terminal 30 .
- the server 20 of the present embodiment includes an operation data acquisition unit (operation information acquisition unit) 201, an inspection data acquisition unit (inspection information acquisition unit) 202, a parts replacement/repair data acquisition unit (parts replacement/repair information acquisition section) 203 , a learning section 204 , a failure prediction section 205 , an inspection item acquisition section 206 , a main part acquisition section 207 and a data storage section 210 .
- the operation data acquisition unit 201 acquires the operation data transmitted from the hydraulic excavator 10 and stores and accumulates the acquired operation data together with the identification number of the hydraulic excavator 10 in the data storage unit 210 .
- the operation data history 211 in FIG. 2 is operation data of the hydraulic excavator 10 accumulated for a predetermined period (for example, the period from factory shipment to the present), and is stored in the data storage unit 210 .
- This operation data is data related to operation information, and includes, for example, operation start time, operation end time, position information, and information detected by each sensor of the hydraulic excavator 10 .
- the inspection data acquisition unit 202 acquires inspection information of the hydraulic excavator 10 and stores the acquired result as inspection data 212 in the data storage unit 210 together with the identification number of the hydraulic excavator 10 .
- the inspection information of the hydraulic excavator 10 is the information transmitted by inputting to the input unit 304 by the maintenance personnel as described above.
- the inspection data 212 includes inspection date and time, inspection items, inspection work details, inspection results, and the like.
- the parts replacement/repair data acquisition unit 203 acquires information on parts repairs and parts replacements related to the above-described "work-related number", and stores the acquired parts repair and/or parts replacement results as parts replacement/repair data 213 for the hydraulic excavator 10. is stored in the data storage unit 210 together with the identification number of the .
- the parts replacement/repair data 213 includes parts repair details, parts replacement details, repair date and time, replacement date and time, and the like.
- the learning unit 204 performs machine learning using well-known methods such as decision trees and gradient boosting, which is an advanced version of decision trees.
- Machine learning uses the operating data history of other hydraulic excavators collected and accumulated at the time of the desired prediction as an explanatory variable to determine which of the inspection/repair history and parts replacement history of those hydraulic excavators has been performed.
- a failure model that derives the failure probability is created by using business data including Note that the inspection/repair history and parts replacement history are objective variables and indicate the fact of failure. Therefore, if the operation data history includes the failure history, inspection/repair history and parts replacement history are unnecessary. On the other hand, if the operation data history does not include the failure history, the inspection/repair history and parts replacement history are necessary. In other words, data relating to inspection/repair history and part replacement history are referenced depending on whether or not the operation data history includes generating a failure model, which will be described later.
- the failure prediction unit 205 has an operation data history 211 that is constantly collected from the hydraulic excavator 10, and inspection data 212 and parts replacement/repair data 213 that are fed back from the mobile terminal when an inspection or repair is performed on any hydraulic excavator 10.
- the failure probability for each part of the hydraulic excavator 10 is predicted based on , and the prediction result is stored in the data storage unit 210 together with the identification number of the hydraulic excavator 10 as failure probability data 215 . Further, the failure probability data is provided to the learning unit 204, and machine learning is performed.
- the predicted failure probability is expressed as a percentage, the higher the number, the higher the probability of failure (in other words, the more urgent the inspection).
- the types here are divided into “aging”, “sudden”, and “general”. "aging” indicates the possibility of time-related failures such as aging deterioration and wear, and “sudden” indicates recent operating conditions. indicates the possibility that signs of failure have appeared, and “total” indicates the failure probability that takes into account both "aging” and "sudden”.
- the inspection item acquisition unit 206 acquires the inspection item data 216 of the hydraulic excavator 10 stored in the data storage unit 210 in response to a request from the mobile terminal 30 and transmits the inspection item data 216 to the mobile terminal 30 .
- inspection item data 216 include an exhaust pipe, a supercharger, a fuel filter, a boom, etc., as shown in FIG. 4, and these inspection items are classified by model.
- the main parts acquisition unit 207 acquires the main parts data 217 of the hydraulic excavator 10 stored in the data storage unit 210 in response to a request from the mobile terminal 30 and transmits it to the mobile terminal 30 .
- the main parts data 217 for example, as shown in FIG. 5, it is divided by model and inspection item.
- step S101 at least one of the operation data history of the hydraulic excavator 10, the inspection data history, or the parts replacement/repair data history is acquired.
- the reason why the term "history" is used is that the prediction is made based not only on the time when the data is acquired, but also on the history up to that point.
- the operation data acquisition unit 201 acquires the operation data transmitted from the hydraulic excavator 10 together with the identification number of the hydraulic excavator 10 and stores the acquired result in the data storage unit 210 .
- the inspection data acquisition unit 202 acquires the inspection data transmitted from the mobile terminal 30 when an arbitrary hydraulic excavator 10 is inspected, together with the identification number of the hydraulic excavator 10, and stores the acquired result in the data storage unit 210.
- both the inspection data history and the parts replacement/repair data history are information related to failures. Since these variables are essential for failure prediction, they are not referred to when they are included in the operating data history, and are referred to when they are not included.
- the parts replacement/repair data acquisition unit 203 acquires the parts replacement/repair data transmitted from the portable terminal 30 when repairing the hydraulic excavator 10 is performed, together with the identification number of the hydraulic excavator 10, and stores the acquired result as data. Stored in unit 210 .
- the learning unit 204 stores the operation data history and the data storage unit 210.
- a failure model generated based on at least one of inspection data history and parts replacement/repair data history stored in is "updated” and compared with failure probability data stored in failure prediction unit 205 .
- Deviation data 214 is generated based on the “difference” between the failure probability data (predicted value) and the actual inspection result (actual value), and is stored in the data storage unit 210 together with the identification number of the hydraulic excavator 10 .
- the divergence data 214 includes deviation details, divergence analysis results, correction values reflecting the analysis results, and the like, and is utilized in machine learning for predicting failure probability.
- step S102 following step S101 the failure probability is predicted.
- the failure prediction unit 205 acquires the operation data history, the inspection data acquired by the inspection data acquisition unit 202, the parts replacement/repair data acquired by the parts replacement/repair data acquisition unit 203, and the failure model generated by the learning unit 204. predicts the failure probability for each part of the hydraulic excavator 10 by .
- a failure model at the time when failure prediction is desired is extracted from the data storage unit 210, and by substituting the operation data history of the hydraulic excavator for which failure prediction is desired into the model, past failures can be determined.
- the probability of failure is predicted based on how close it is to the actual value (operation data history) of the hydraulic excavator that occurred, and failure probability data is generated.
- step S103 the failure prediction unit 205 causes the data storage unit 210 to store the prediction result together with the identification number of the hydraulic excavator 10. This completes the series of control processes.
- FIG. 7 is a flow chart showing control processing relating to the inspection item screen of the portable terminal.
- the control process shown in FIG. 7 is executed by cooperation between the mobile terminal 30 and the server 20. More specifically, part of step S201 and steps S204 to S209 are executed by the server 20. , and other steps are processes executed by the mobile terminal 30 .
- the control process shown in FIG. 7 is started by, for example, maintenance personnel or the user selecting the inspection item screen 301 displayed on the mobile terminal 30 .
- an inspection item list is obtained.
- the maintenance staff or the user requests the inspection item list of the excavator 10 from the server 20 by selecting (eg, tapping) the inspection item screen 301 .
- the inspection item acquisition unit 206 of the server 20 acquires an inspection item list from the inspection item data 216 in response to the request, and transmits the inspection item list to the mobile terminal 30 .
- the mobile terminal 30 then receives the inspection item list transmitted from the server 20 and displays the received contents on the inspection item screen 301 .
- inspection items such as "engine”, “upper rotating body”, and “lower traveling body” are listed.
- loop processing relating to inspection items shown in steps S202 to S210 is performed. Specifically, for example, when maintenance personnel or a user selects one of a plurality of inspection item lists displayed on the inspection item screen 301 (for example, "undercarriage" shown in FIG. 10), the portable terminal 30 The selected inspection items are sent to the server 20, and a main parts list is requested from the server 20 (see step S203).
- step S204 the main parts acquisition unit 207 of the server 20 acquires a main parts list from the main parts data 217 in response to the request. For example, when "undercarriage" is selected as shown in FIG. 10, the main parts acquisition unit 207 acquires main parts related to "undercarriage” such as sprockets, center joints, track frames, side frames, and track links. Get list.
- main parts related to "undercarriage” such as sprockets, center joints, track frames, side frames, and track links. Get list.
- loop processing of failure probability acquisition shown in steps S205 to S207 is performed for these acquired main parts. That is, the acquisition of the failure probabilities of the main components acquired in step S205 is performed sequentially (see step S206).
- the failure probability of the main component is predicted by the failure prediction unit 205 and stored in the data storage unit 210 as failure probability data 215 .
- step S208 the failure prediction unit 205 calculates the failure probability of the selected inspection item based on the failure probabilities of the main components acquired in steps S205-S207.
- step S209 the server 20 returns (in other words, transmits) the failure probability of the inspection item predicted in step S208 to the mobile terminal 30.
- Such a loop process regarding inspection items shown in steps S202 to S210 is performed for each selected inspection item. For example, when “upper rotating body” and “engine” are selected in order after “lower traveling body”, steps S203 to S209 are repeated in the order of "upper rotating body” and "engine”.
- step S211 following step S210 the mobile terminal 30 displays the received inspection item list on the inspection item screen 301 together with the failure probability of each inspection item. This completes a series of control processes relating to the inspection item screen.
- FIG. 8 is a flow chart showing control processing relating to the main component screen of the portable terminal.
- the control process shown in FIG. 8 is executed by cooperation between the mobile terminal 30 and the server 20. More specifically, steps S303 to S307 are processes executed by the server 20, and the other steps are This processing is executed by the mobile terminal 30 .
- step S301 inspection items are selected. For example, when a maintenance person or user selects an inspection item such as "front” as shown in FIG. (See step S302).
- the main parts acquisition unit 207 of the server 20 acquires a main parts list related to the inspection item from the main parts data 217 in response to the request. Since "front" is selected here, the main parts acquisition unit 207 acquires a list of main parts such as buckets and links related to "front".
- loop processing for obtaining the failure probability of the main parts shown in steps S304 to S306 is performed for these main parts that have been obtained. That is, the acquisition of the failure probabilities of the main components acquired in step S303 is performed sequentially (see step S305).
- the failure probability of the main component is predicted by the failure prediction unit 205 and stored in the data storage unit 210 as failure probability data 215 .
- step S308 following step S307, the mobile terminal 30 displays the received main parts list on the main parts screen 302 together with the failure probability of each part. At this time, for example, as shown in FIG. 11, the failure probability is displayed for each target link. Then, when step S308 ends, a series of control processing relating to the main parts screen ends.
- FIG. 9 is a flow chart showing control processing relating to the failure probability screen of the portable terminal.
- the control processing shown in FIG. 9 is executed by cooperation between the mobile terminal 30 and the server 20. More specifically, steps S402 to S404 and steps S407 to S408 are executed by the server 20. , and other steps are processes executed by the mobile terminal 30 .
- step S401 information about the target hydraulic excavator is transmitted.
- the maintenance staff or the user inputs the identification number of the hydraulic excavator 10 whose failure probability is to be checked into the input unit 304 of the mobile terminal 30 to request the server 20 .
- step S402 it is determined whether or not the specified target hydraulic excavator is included in the management target.
- the server 20 determines whether there is a hydraulic excavator corresponding to the identification number among the plurality of hydraulic excavators under management, based on the transmitted hydraulic excavator identification number. If it is determined that there is no target hydraulic excavator, the control process ends. On the other hand, if it is determined that there is a target hydraulic excavator, the control process proceeds to step S403.
- the server 20 determines whether or not there is inspection data for the target hydraulic excavator. If it is determined that there is no inspection data, the control process ends. On the other hand, if it is determined that there is inspection data, the control process proceeds to step S404.
- step S404 the server 20 determines whether or not there is parts replacement/repair data for the target hydraulic excavator. If it is determined that there is no part replacement/repair data for the target hydraulic excavator, the control process ends. On the other hand, if it is determined that there is part replacement/repair data, the control process proceeds to step S405.
- step S405 main parts are selected.
- the mobile terminal 30 transmits the selected main parts to the server 20 and requests the related main parts list from the server 20 ( See step S406).
- the maintenance personnel or the user selects 'buckets, links' related to 'front' as shown in FIG.
- step S407 the server 20 acquires the failure probability list of main parts from the failure probability data 215 in response to the request.
- step S ⁇ b>408 the server 20 returns (in other words, transmits) the acquired failure probability list of the main components to the mobile terminal 30 .
- step S409 following step S408, the mobile terminal 30 displays the received failure probability list of the main parts on the failure probability screen 303.
- the failure probability screen 303 for example, as shown in FIG. 11, among a plurality of bucket links, each link is classified as "A link” or "B link” and given a model number. .
- An icon representing the degree of inspection recommendation is displayed on each target link.
- a bell mark is used, but the bell may not be used as long as the degree of inspection recommendation can be visually recognized.
- the "inspection recommendation level” is used instead of the failure probability (see Fig. 12).
- the inspection recommendation level has the same meaning as the failure probability, and is an expression that has been replaced for easier understanding by the user.
- the bell icon is preferably color-coded according to the range of inspection recommendations. For example, if the inspection recommendation level is 90% or more, the bell icon is red, if the inspection recommendation level is 60% or more and less than 90%, the bell icon is yellow, if the inspection recommendation level is 40% or more and less than 60%, the bell icon is blue.
- the inspection recommendation level for each configured part will be displayed as a bell icon. Furthermore, when the bell icon of each part is selected, the degree of inspection recommendation for each type (that is, "general”, “aging”, and “unexpected") is displayed as a specific numerical value, as shown in FIG.
- step S409 ends, a series of control processing relating to the failure probability screen ends.
- the failure prediction unit 205 obtains the operation data acquired by the operation data acquisition unit 201, the inspection data acquired by the inspection data acquisition unit 202, and the parts replacement/repair data acquisition unit 203. predicts the failure probability for each part of the hydraulic excavator 10 based on the parts replacement/repair data acquired by . By adding inspection data and parts replacement/repair data to the operation data of the hydraulic excavator 10 in this manner to predict the failure probability, the accuracy of failure prediction can be improved.
- the deviation data 214 learned by the learning unit 204 is added to the operation data, inspection data, and parts replacement/repair data of the hydraulic excavator 10, and the failure probability for each part of the hydraulic excavator 10 is predicted based on these data. Therefore, the accuracy of failure prediction can be further improved.
- the operation data acquisition unit 201, the inspection data acquisition unit 202, the parts replacement/repair data acquisition unit 203, the learning unit 204, and the failure prediction unit 205 are provided in the server 20.
- the inspection data acquisition unit 202, the parts replacement/repair data acquisition unit 203, the learning unit 204, and the failure prediction unit 205 are data storage units that store inspection data 212, parts replacement/repair data 213, deviation data 214, and failure probability data 215. 218 may be provided in the control unit of the hydraulic excavator 10 .
- the operation data collection unit 101 functions as an operation data acquisition unit.
- the hydraulic excavator 10 is provided with a display section 102 for displaying the failure probability. In this way, the failure probability can be grasped not only on the portable terminal 30 side but also on the hydraulic excavator 10 side.
- the operation data acquisition unit (operation information acquisition unit) 220, the learning unit 204, and the failure prediction unit 205 may be provided in the portable terminal 30 together with the data storage unit 219.
- the operation data acquisition unit 220 acquires the operation data transmitted from the hydraulic excavator 10 and stores the acquired operation data together with the identification number of the hydraulic excavator 10 in the data storage unit 219. stored and accumulated in The data storage unit 219 stores operation data history 211, inspection data 212, parts replacement/repair data 213, divergence data 214, and failure probability data 215.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
Description
油圧ショベル10は、メーカーの工場から出荷され、土木作業、建設作業、解体作業、浚渫作業などが行われる作業現場において所定のユーザ(例えば、油圧ショベルの所有者または使用者)に使用されている。油圧ショベル10には、稼働データ収集部101が設けられている。稼働データ収集部101は、例えば油圧ショベル10全体の制御を行う制御部の一部からなり、油圧ショベル10の稼働データを自分の識別番号とともにサーバ20や携帯端末30に送信する。なお、サーバ20や携帯端末30への送信は、定期的に(例えば1日1回の頻度で)行われている。
携帯端末30は、例えばスマートフォン、タブレット端末、携帯電話、PDA(Personal Data Assistant)などからなり、油圧ショベル10の保守員又はユーザに携帯されている。保守員又はユーザは、例えば携帯端末30を介して特定の油圧ショベル10に関する点検項目などの情報を求めることができる。具体的には、保守員又はユーザが特定の油圧ショベル10の点検項目などの情報を希望した場合、例えばその特定の油圧ショベル10の識別番号を携帯端末30の入力部304に直接入力したり、入力部304に表示された該特定の油圧ショベル10の識別番号を選択したりすることで、携帯端末30を介してサーバ20に要求する。
サーバ20は、故障予測システム1を構成するメインのコンピュータであり、油圧ショベル10のメーカーの本社、支社、工場或いは管理センタに設置され、複数の油圧ショベル10から送信された稼働データなどを定期的に収集し、これらの油圧ショベル10を集中管理している。サーバ20は、例えば演算を実行するCPU(Central Processing Unit)と、演算のためのプログラムを記憶した二次記憶装置としてのROM(Read Only Memory)と、演算経過の保存や一時的な制御変数を保存する一時記憶装置としてのRAM(Random Access Memory)とを組み合わせてなるマイクロコンピュータにより構成されており、記憶されたプログラムの実行によって算出や判断などの処理を行う。
以下、図6を参照してサーバ20の制御処理を説明する。図6に示す制御処理は、例えば所定の周期で繰り返し実行されている。
まず、図7を基に携帯端末30の点検項目画面301について説明する。図7は携帯端末の点検項目画面に関する制御処理を示すフローチャートである。図7に示す制御処理は、携帯端末30とサーバ20との協働によって実行されるものであり、より詳細には、ステップS201の一部及びステップS204~S209はサーバ20により実行される処理であり、その他のステップは携帯端末30により実行される処理である。
次に、図8を基に携帯端末の主要部品画面について説明する。図8は携帯端末の主要部品画面に関する制御処理を示すフローチャートである。図8に示す制御処理は、携帯端末30とサーバ20との協働によって実行されるものであり、より詳細には、ステップS303~S307はサーバ20により実行される処理であり、その他のステップは携帯端末30により実行される処理である。
次に、図9を基に携帯端末の故障確率画面について説明する。図9は携帯端末の故障確率画面に関する制御処理を示すフローチャートである。図9に示す制御処理は、携帯端末30とサーバ20との協働によって実行されるものであり、より詳細には、ステップS402~S404、ステップS407~S408はサーバ20により実行される処理であり、その他のステップは携帯端末30により実行される処理である。
Claims (8)
- 作業機械の故障を予測する故障予測システムであって、
前記作業機械の稼働情報を取得する稼働情報取得部と、
前記作業機械の点検情報を取得する点検情報取得部と、
前記作業機械の部品交換修理情報を取得する部品交換修理情報取得部と、
前記稼働情報取得部により取得された稼働情報、前記点検情報取得部により取得された点検情報、前記部品交換修理情報取得部により取得された部品交換修理情報、及び、記憶部に記憶された前記作業機械の部位ごとの故障確率と前記作業機械の点検実績との乖離情報に基づいて、前記作業機械の部位ごとの故障確率を予測する故障予測部と、
を備えることを特徴とする故障予測システム。 - 前記故障予測部によって予測された故障確率と前記作業機械の点検実績との前記乖離情報を学習する学習部を更に備え、
前記故障予測部は、前記学習部により学習された前記乖離情報に基づいて、前記作業機械の部位ごとの故障確率を予測する請求項1に記載の故障予測システム。 - 前記作業機械と通信可能なサーバを更に備え、
前記稼働情報取得部、前記点検情報取得部、前記部品交換修理情報取得部、前記故障予測部、及び前記学習部は、前記サーバに設けられている請求項2に記載の故障予測システム。 - 前記サーバと通信可能な携帯端末を更に備え、
前記携帯端末には、前記故障予測部により予測された故障確率を表示する表示部が設けられている請求項3に記載の故障予測システム。 - 前記作業機械と通信可能な携帯端末を更に備え、
前記稼働情報取得部、前記点検情報取得部、前記部品交換修理情報取得部、前記故障予測部、及び前記学習部は、前記携帯端末に設けられている請求項2に記載の故障予測システム。 - 前記携帯端末には、前記故障予測部により予測された故障確率を表示する表示部が設けられている請求項5に記載の故障予測システム。
- 前記稼働情報取得部、前記点検情報取得部、前記部品交換修理情報取得部、前記故障予測部、及び前記学習部は、前記作業機械に設けられている請求項2に記載の故障予測システム。
- 前記作業機械には、前記故障予測部により予測された故障確率を表示する表示部が設けられている請求項7に記載の故障予測システム。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2023514528A JPWO2022219997A1 (ja) | 2021-04-14 | 2022-03-16 | |
EP22787923.6A EP4325313A1 (en) | 2021-04-14 | 2022-03-16 | Malfunction prediction system |
KR1020237028320A KR20230133365A (ko) | 2021-04-14 | 2022-03-16 | 고장 예측 시스템 |
CN202280016993.4A CN116917824A (zh) | 2021-04-14 | 2022-03-16 | 故障预测系统 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021-068549 | 2021-04-14 | ||
JP2021068549 | 2021-04-14 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022219997A1 true WO2022219997A1 (ja) | 2022-10-20 |
Family
ID=83640544
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/011789 WO2022219997A1 (ja) | 2021-04-14 | 2022-03-16 | 故障予測システム |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP4325313A1 (ja) |
JP (1) | JPWO2022219997A1 (ja) |
KR (1) | KR20230133365A (ja) |
CN (1) | CN116917824A (ja) |
WO (1) | WO2022219997A1 (ja) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005182558A (ja) * | 2003-12-22 | 2005-07-07 | Hitachi Ltd | コスト予測・評価方式 |
JP2008165352A (ja) * | 2006-12-27 | 2008-07-17 | Toshiba Corp | 定期点検データ分析装置およびその方法 |
JP2009087235A (ja) * | 2007-10-02 | 2009-04-23 | Toshiba Corp | モデル構築装置並びにモデル構築のための方法およびプログラム |
JP2016157280A (ja) | 2015-02-25 | 2016-09-01 | 三菱重工業株式会社 | 事象予測システム、事象予測方法及びプログラム |
JP2020102097A (ja) * | 2018-12-25 | 2020-07-02 | 株式会社日立製作所 | 劣化度合予測システムおよび劣化度合予測方法 |
JP2020135133A (ja) * | 2019-02-14 | 2020-08-31 | 三菱重工サーマルシステムズ株式会社 | 故障防止システム、故障防止方法及びプログラム |
-
2022
- 2022-03-16 JP JP2023514528A patent/JPWO2022219997A1/ja active Pending
- 2022-03-16 CN CN202280016993.4A patent/CN116917824A/zh active Pending
- 2022-03-16 WO PCT/JP2022/011789 patent/WO2022219997A1/ja active Application Filing
- 2022-03-16 KR KR1020237028320A patent/KR20230133365A/ko unknown
- 2022-03-16 EP EP22787923.6A patent/EP4325313A1/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005182558A (ja) * | 2003-12-22 | 2005-07-07 | Hitachi Ltd | コスト予測・評価方式 |
JP2008165352A (ja) * | 2006-12-27 | 2008-07-17 | Toshiba Corp | 定期点検データ分析装置およびその方法 |
JP2009087235A (ja) * | 2007-10-02 | 2009-04-23 | Toshiba Corp | モデル構築装置並びにモデル構築のための方法およびプログラム |
JP2016157280A (ja) | 2015-02-25 | 2016-09-01 | 三菱重工業株式会社 | 事象予測システム、事象予測方法及びプログラム |
JP2020102097A (ja) * | 2018-12-25 | 2020-07-02 | 株式会社日立製作所 | 劣化度合予測システムおよび劣化度合予測方法 |
JP2020135133A (ja) * | 2019-02-14 | 2020-08-31 | 三菱重工サーマルシステムズ株式会社 | 故障防止システム、故障防止方法及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
KR20230133365A (ko) | 2023-09-19 |
JPWO2022219997A1 (ja) | 2022-10-20 |
EP4325313A1 (en) | 2024-02-21 |
CN116917824A (zh) | 2023-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102184182B1 (ko) | Super Tree 기반의 Project/Task 지능 목표관리 방법 및 플랫폼 | |
JP4884214B2 (ja) | 建設機械のメンテナンス支援システム | |
JP2019061614A (ja) | 設計支援装置および設計支援方法 | |
WO2010073771A1 (ja) | 建設機械の診断情報提供装置 | |
US20140032169A1 (en) | Systems and methods for improving control system reliability | |
CN1761919A (zh) | 过程工厂中的资产优化报告 | |
EP3767563B1 (en) | Work order placement/receiving system, server, and work order placement/receiving method | |
JP6906209B2 (ja) | 建設機械稼働状況管理システム及び管理方法 | |
Hasegan et al. | Predicting performance–a dynamic capability view | |
JP2011065626A (ja) | プラントの建設計画支援装置及び方法 | |
JP2015522895A (ja) | 制御の信頼性動作ためのシステムおよび方法 | |
Prasad et al. | A software prototype for material handling equipment selection for construction sites | |
JP2012160085A (ja) | 建設機械のメンテナンス方法およびメンテナンスシステム | |
WO2020203170A1 (ja) | スキル情報提示システム及びスキル情報提示方法 | |
JP2017199128A (ja) | 復旧計画管理装置、復旧計画プログラム及び復旧計画方法 | |
JP2011170496A (ja) | プラントの工事計画支援装置及び方法 | |
Sobotka et al. | Decision support system in management of concrete demolition waste | |
EP1571570A1 (en) | Construction device information processing system and construction device information processing method | |
Zarghami | Forecasting project duration in the face of disruptive events: A resource-based approach | |
JP4990877B2 (ja) | 設備のリスク評価システムおよびリスク評価方法 | |
WO2022219997A1 (ja) | 故障予測システム | |
JP2022161342A (ja) | デジタルツイン管理システムおよび方法 | |
Alarcón et al. | Impact of machine-failure costs on equipment replacement policies: tunneling company case study | |
JP2018085013A (ja) | 企業情報システムおよび企業情報提供方法 | |
JP2022164024A (ja) | 点検支援システム |
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: 22787923 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20237028320 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020237028320 Country of ref document: KR |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280016993.4 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18279430 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023514528 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022787923 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022787923 Country of ref document: EP Effective date: 20231114 |