WO2015114792A1 - Maintenance and operation assist system, maintenance and operation assist method, and maintenance and operation assist program - Google Patents

Maintenance and operation assist system, maintenance and operation assist method, and maintenance and operation assist program Download PDF

Info

Publication number
WO2015114792A1
WO2015114792A1 PCT/JP2014/052203 JP2014052203W WO2015114792A1 WO 2015114792 A1 WO2015114792 A1 WO 2015114792A1 JP 2014052203 W JP2014052203 W JP 2014052203W WO 2015114792 A1 WO2015114792 A1 WO 2015114792A1
Authority
WO
WIPO (PCT)
Prior art keywords
factor
maintenance
work machine
operating
operation support
Prior art date
Application number
PCT/JP2014/052203
Other languages
French (fr)
Japanese (ja)
Inventor
峻行 羽渕
巌 田沼
裕 吉川
Original Assignee
株式会社日立製作所
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 株式会社日立製作所 filed Critical 株式会社日立製作所
Priority to PCT/JP2014/052203 priority Critical patent/WO2015114792A1/en
Priority to JP2015559687A priority patent/JP6285467B2/en
Publication of WO2015114792A1 publication Critical patent/WO2015114792A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00—Registering or indicating the working of vehicles
    • G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station

Definitions

  • the present invention relates to a maintenance operation support system for a work machine, a maintenance operation support method, and a maintenance operation support program.
  • Patent Document 1 JP-A-2002-181668
  • the life of a machine is estimated from the roughness of the road surface on which the mining machine travels, the traveling speed, and the load amount of the mining machine operated in the mine.
  • the sensor data is analyzed to estimate the life and the superiority of the surrounding environment.
  • Maintenance factors such as the implementation status of maintenance work on the machine can be cited as factors that affect the operating rate that are not described in Patent Document 1.
  • analysis of maintenance work logs input by maintenance workers can be mentioned.
  • the maintenance work log input by the maintenance worker at the site is inaccurate and may cause an input omission. Therefore, in order to analyze the maintenance work log and estimate the maintenance factor, a technique for complementing inaccuracy and input omission is required.
  • the present invention estimates and visualizes the status of maintenance work, which has conventionally been difficult to acquire information with sensors, without relying on maintenance work logs, and comprehensively evaluates factors that affect the operating rate. Objective.
  • a maintenance operation support apparatus that supports maintenance operation of a work machine is provided from one aspect of the present invention.
  • the maintenance operation support apparatus a communication unit that receives operation result data including operation time information of the work machine and sensor data measured by a sensor attached to the work machine, and a standard operation rate with respect to the accumulated operation time of the work machine
  • a storage unit that stores rated operating rate information including information regarding the sensor and sensor threshold information including information regarding a threshold with respect to a value indicated by the sensor data.
  • the processing unit calculates a rated operating rate achievement degree, which is information related to a ratio between the operating rate and the standard operating rate of the work machine, based on the operation result data and the rated operating rate information.
  • a maintenance factor that is a factor that affects the operating rate of a work machine and that is related to maintenance work on the work machine, based on the calculation of a certain environmental factor and based on the achievement rate of the rated operation rate, the operating factor, and the environmental factor Is calculated.
  • a maintenance operation support method in a maintenance operation support system that supports maintenance operation of a work machine by communicating with a sensor attached to the work machine via a network.
  • the maintenance operation support method receives operation result data including operation time information of the work machine and sensor data measured by the sensor, and includes information on the operation result data and the standard operation rate with respect to the accumulated operation time of the work machine.
  • sensor threshold information that calculates the rated availability achievement level, which is information related to the ratio between the availability and standard availability of the work machine, and includes sensor data and information on the threshold for the value indicated by the sensor data.
  • the feature amount is calculated based on the above, and based on the feature amount, the operating factor of the work machine is related to the operating factor and the operating environment of the working machine, which are factors affecting the operation rate of the work machine.
  • the environmental factors that are the factors are calculated, and the factors affecting the operating rate of the work machine based on the achievement rate of the rated operating rate, the operating factor, and the environmental factor.
  • To calculate the maintenance factor is a factor related to that maintenance work.
  • a maintenance operation support system including a sensor attached to a work machine, a work machine operation management system, a maintenance operation support device that supports maintenance operation of the work machine, and a terminal device.
  • the operation management system manages the operation result data including the operation time information of the work machine, and transmits the operation result data to the maintenance operation support device via the network.
  • the sensor transmits the measured sensor data to the maintenance operation support apparatus via the network.
  • the maintenance operation support apparatus includes rated operation rate information including information on a standard operation rate with respect to the cumulative operation time of the work machine, and sensor threshold information including information on a threshold value with respect to a value indicated by the sensor data.
  • the rated operating rate achievement level which is information on the operating rate and standard operating rate of the work machine, is calculated, and based on the sensor data and the sensor threshold information This is a factor that affects the operating rate of the work machine based on the feature value and that is related to the operation of the work machine and the operating environment of the work machine.
  • the environmental factors are calculated, and the factors affecting the operating rate of the work machine based on the degree of rated operating rate achievement, operating factors, and environmental factors.
  • Calculating the maintenance factor is a factor that, transmits information on maintenance factors, to the terminal apparatus via the network.
  • the terminal device displays the received information regarding the maintenance factor on the display unit.
  • maintenance factors can be analyzed and visualized based on existing sensor data. Therefore, the user of the present invention can examine measures for improving the operating rate based on the visualized maintenance factor.
  • the factors that affect the operating rate are represented by three factors: operating factors, environmental factors, and maintenance factors.
  • Operating factors are factors related to the operation of the work machine, such as the cylinder hydraulic pressure of the work machine, engine speed, and motor applied voltage
  • environmental factors are factors caused by the surrounding environment such as road surface conditions and ambient temperature
  • maintenance factors are maintenance work It is defined as a human factor resulting from maintenance work such as accuracy and periodic maintenance.
  • operation factors and environmental factors are digitized from sensors attached to the work machine, and maintenance personnel are estimated from the digitized operation factors and environmental factors.
  • the operating factor and the environmental factor are factors estimated by executing the principal component analysis based on the sensor data.
  • the maintenance factor is a factor estimated by performing factor analysis based on the operation factor, the environmental factor, and the operation rate. In this embodiment, it is allowed to use any value observable by the sensor, and the maintenance factor shown in FIG. 18 means a factor that cannot be observed by the sensor.
  • the present invention estimates and visualizes maintenance factors that are difficult to observe directly by principal component analysis and factor analysis based on sensor data and operating rates.
  • FIG. 1 is a diagram showing a network configuration example including a maintenance operation support system 100 that estimates and visualizes operation factors, environmental factors, and maintenance factors using the model of FIG. 18 in the present embodiment.
  • a maintenance operation support system 100 shown in FIG. 1 is a computer system for visualizing a maintenance situation and comprehensively evaluating factors that affect an operation rate.
  • a dump truck which is a large mining machine, will be described as an example of a work machine.
  • the operation rate of the dump truck is affected by operating factors related to the operation, environmental factors related to the surrounding environment, and maintenance factors related to the maintenance status.
  • the maintenance operation support system 100 of this embodiment visualizes these operation factors, environmental factors, and maintenance factors.
  • the maintenance operation support system 100 is connected to the network 160 and can communicate data with the mining machine 140, the operation management system 150, and the client terminal 170. Data measured by various sensors attached to the mining machine 140 is transmitted to the maintenance operation system 100 through the network 160. The operation status of the mining machine 140 collected by the operation management system 150 is transmitted to the maintenance operation system 100 via the network 160.
  • the client terminal 170 accesses the maintenance operation support system 100, and receives each process of receiving data input from the user using a keyboard, a mouse, and the like, and displaying the data obtained from the maintenance planning support system 100. Is responsible.
  • the hardware configuration of the maintenance operation support system 100 is as follows.
  • the maintenance operation support system 100 reads out a storage device 120 configured with an appropriate nonvolatile storage device such as a hard disk drive, a memory 113 configured with a volatile storage device such as a RAM, and a program held in the storage device 120 into the memory 113.
  • the CPU 114 (arithmetic unit) for performing overall control of the system itself and performing various determinations, computations and control processes, and the communication device 112 connected to the network 160 and responsible for communication processing with other devices.
  • the functions implemented in the storage device 120 include a rated operation rate achievement degree calculation function 124, a feature amount calculation function 126, an operation / environment factor estimation function 128, and a maintenance factor estimation function 130.
  • the example of the maintenance operation support system 100 shown in FIG. 1 illustrates such a function group and a database group that stores data used by each function.
  • the maintenance operation support system 100 may have an input / output function and a device (display, keyboard, etc.).
  • the maintenance operation support system 100 receives operation result data from the operation management system 150, compares the received information with the machine master database 122, and calculates a rated operation rate achievement level calculation function. 124.
  • the working rate of the work machine decreases as the cumulative operation time increases.
  • the rated operating rate achievement is a value obtained by correcting the influence of the cumulative operating time using the rated operating rate for each cumulative operating time.
  • the maintenance operation system 100 has a feature amount calculation function 126 that receives sensor data from the mining machine 140 and compares the received information with the machine master database 122 to calculate a feature amount.
  • the feature amount is a maximum value or average value of sensor data, a time of operation exceeding the rating, or the like, and is a characteristic value that is considered to particularly affect the operation rate.
  • the maintenance operation system 100 has an operation / environment factor analysis function 128 that compares the feature amount calculated by the above-described function with the machine master table 122 to estimate an operation factor and an environmental factor.
  • the maintenance operation system 100 has a maintenance factor estimation function 130 that calculates a maintenance factor from the rated availability rate calculated by the above-described function, an operation factor, and an environmental factor.
  • FIG. 3 shows an example of the operation result database 121 in this embodiment.
  • the operation result database 121 is a database in which operation results of mining machines are accumulated.
  • the data structure is a set of records including a cumulative operation time 202, an operation time 203, a planned stop time 204, an unplanned stop time 205, and an operation rate 206 using the machine ID 201 and the period 207 as keys. .
  • the above-mentioned machine ID 201 stores an ID for uniquely identifying a mining machine.
  • the period 207 the calculation period of each record is stored.
  • the accumulated operation time 202 stores the accumulated operation time at the end of the period of the machine.
  • the operation time 203 includes the operation time of the machine during the period
  • the planned stop time 204 includes the planned stop time of the machine during the period
  • the unplanned stop time 205 includes the machine during the period.
  • the planned stop means a stop of the machine due to predetermined periodic maintenance or the like
  • the unplanned stop means a stop of the machine due to a sudden failure or the like.
  • the operation rate 206 stores an operation rate represented by operation time / (operation time + planned stop time + unplanned stop time) ⁇ 100.
  • the period 207 is divided by month, but an arbitrary value may be stored.
  • FIG. 4 shows an example of the rated operation rate table 210 in the machine master database 122 in the present embodiment.
  • the rated operating rate table 210 is a database in which standard operating rates of mining machines are accumulated.
  • the data structure is a collection of records including the rated operation rate 213 with the model name 211 and the accumulated operation time 212 as keys.
  • the accumulated operating time 212 stores a category of the accumulated operating time of the machine.
  • the rated operation rate 213 stores an operation rate that is standard when a certain model has a certain accumulated operation time.
  • the rated operating rate 213 is calculated from the interval between periodic machine maintenance and parts replacement, and is generally provided by a manufacturer or a vendor.
  • FIG. 5 shows an example of the machine specification table 220 in the machine master database 122.
  • the machine specification table 220 stores machine specifications.
  • the data structure is a collection of records consisting of a site ID 222, a customer ID 223, a model name 224, a vehicle body mass 225, a total vehicle mass 226, and a TKPH (Ton ⁇ Km Per Hour) 227 with the machine ID 221 as a key. It is.
  • the machine ID 221 described above stores an ID that uniquely identifies the machine.
  • the site ID 222 and the customer ID 223 store an ID that uniquely identifies the site where the machine operates and an ID that uniquely identifies the customer who owns the machine.
  • the model name 224 stores a character string for specifying the model.
  • the vehicle body mass 225 stores the mass of the machine body.
  • the total vehicle mass 226 stores the maximum rated value of the sum of the vehicle mass 225 and the mass of the load.
  • TKPH refers to the effects of the load (Ton), speed (Km), and outside temperature on the tire.
  • TKPH is the sum of the vehicle mass 225 and the mass of the load (Ton), and the machine operating speed.
  • the rated maximum value obtained by multiplying (Km) is stored.
  • the vehicle body mass 225, the total vehicle mass 226, and the TKPH 227 are specifications generally provided by a manufacturer.
  • FIG. 6 shows an example of the sensor data database 123.
  • the sensor data database 123 stores sensor data collected from the mining machine 140 via the network 160.
  • the data structure is a set of records composed of n pieces of sensor data 304 with the machine ID 301, the date 302, and the time 303 as keys.
  • the machine ID 301 stores an ID that uniquely identifies the machine.
  • the year / month / day 302 and the time 303 respectively store the date / time when the data 304 was acquired and the time.
  • the sensor data 304 stores various sensor data collected via the network 160.
  • Fig. 7 shows the relationship between the maximum, average, and rated operating time of sensor data (loading capacity).
  • the maximum and average are the maximum value and average value of sensor data within a specified period.
  • the operating time above the rated value means the sum of the operating time exceeding the rated value within a specified period.
  • the maximum and average values represented by the rating ratio and the operation time exceeding the rating are handled as the feature amount.
  • FIG. 8 shows an example of the rated availability achievement level database 125.
  • the rated operation rate achievement degree database 125 accumulates the ratio between the standard operation rate obtained from the accumulated operation time and the actual operation rate.
  • the data structure is a set of records composed of [operating rate] rated operating rate achievement degree 402 with machine ID 401 and period 403 as keys.
  • the machine ID 401 stores an ID that uniquely identifies the machine.
  • the period 403 stores a period for calculating the [operation rate] rated operation rate achievement level 402.
  • [Occupancy rate] Rated operation rate achievement degree 402 stores the value obtained by dividing the operation rate 206 of the machine for the relevant period by the rated operation rate 213 and multiplying it by 100, as the rated operation rate achievement degree.
  • the rated operating rate achievement level is calculated by the rated operating rate achievement level calculating function 124.
  • FIG. 9 shows an example of the load amount table 500 in the feature amount database 127.
  • the load amount table 500 stores the feature amount of the load amount extracted by the feature amount calculation function 126 from the load amount data stored in the sensor database 123.
  • the data structure is a set of records consisting of a machine ID 501 and a period 505 as a key, [loading capacity] rated ratio maximum 502, [loading capacity] rated ratio average 503, and [loading capacity] rated time or more operation time 504. It is.
  • the machine ID 501 stores an ID that uniquely identifies the machine.
  • the period 505 stores a period during which the [loading capacity] rating ratio maximum 502, the [loading capacity] rating ratio average 503, and the [loading capacity] rating or more operation time 504 are calculated.
  • the [loading capacity] rating ratio maximum 502 the [loading capacity] rating ratio average 503, and the [loading capacity] rating or more operation time 504, values obtained by extracting the feature values shown in FIG. Stored. Note that the feature amount extraction is executed by the feature amount calculation function 126.
  • FIG. 10 shows an example of the TKPH table 510 in the feature amount database 127.
  • the TKPH table 510 stores the feature amount of the load amount extracted by the feature amount calculation function 126 from the TKPH data stored in the sensor data database 123.
  • the data structure is a set of records including machine ID 511, period 515 as a key, [TKPH] rated ratio maximum 512, [TKPH] rated ratio average 513, and [TKPH] rated or more operating time 514. It has the same structure as the load amount table 500.
  • FIG. 11 shows an example of the vibration level table 600 in the feature amount database 127.
  • the vibration level table 600 stores the vibration level feature quantity extracted by the feature quantity calculation function 126 from the vibration level data stored in the sensor data database 123.
  • the data structure includes [machine vibration level] width direction maximum 602, [vibration level] width direction average 603, [vibration level] circumferential direction maximum 604, [vibration level] using machine ID 601 and period 606 as keys. This is an aggregate of records composed of an average 605 in the circumferential direction.
  • the structure is mainly the same as that of the load amount table 500 and the TKPH table 510, but in this embodiment, since the vibration level rating is not set, there is no operation time exceeding the rating.
  • the direction of vibration is divided into the tire width direction (602, 603) and the circumferential direction (604, 605).
  • the load amount, TKPH, and vibration level which are generally said to have a large influence on the operation rate, are shown as examples.
  • any data can be used as long as the data can be collected by the sensor. Good.
  • each sensor data may be normalized.
  • FIG. 12 shows an example of the operation / environment factor database 129.
  • the operation / environment factor database 129 stores the operation factor of each machine and the environment factor estimated from the feature amount database 127 by the operation / environment factor analysis function 128.
  • the data structure is composed of a set of records including an operation factor 702, an environment factor 703, a site ID 704, and a customer ID 705 with the machine ID 701 and the period 706 as keys.
  • the machine ID 701 stores an ID that uniquely identifies the machine.
  • the period 706 stores a period for calculating the operating factor 702 and the environmental factor 703.
  • the operation factor 702 and the environment factor 703 store values obtained by calculating the operation factor related to the operation and the environment factor related to the surrounding environment during the period 706, respectively.
  • the operation factor 702 and the environment factor 703 are obtained by executing principal component analysis based on each feature quantity in the feature quantity database 127.
  • the site ID 704 stores an ID that uniquely identifies the site where the machine operates.
  • the customer ID 705 stores an ID that uniquely identifies the customer who owns the machine.
  • FIG. 13 shows an example of the maintenance factor database 131.
  • the maintenance factor database 131 stores maintenance factors estimated from the rated operating rate achievement database 125 and the operation / environment factor database 129 by the maintenance factor estimation function 130.
  • the data structure is composed of a collection of records including an environmental factor 712, a site ID 713, and a customer ID 714 with the machine ID 711 and the period 716 as keys.
  • the machine ID 711 stores an ID that uniquely identifies the machine.
  • the period 715 stores a period for calculating the maintenance factor 712.
  • the maintenance factor 712 stores a factor related to the maintenance status that affects the operation rate.
  • the site ID 713 stores an ID that uniquely identifies the site where the machine operates.
  • the customer ID 714 stores an ID that uniquely identifies the customer who owns the machine.
  • FIG. 14 is an overall flowchart for explaining the processing procedure of the present embodiment.
  • the maintenance operation system 140 acquires various sensor data from the mining machine 140 (S1401).
  • the maintenance operation system 100 collates the acquired sensor data with the machine master database and calculates the feature amount (S1402).
  • the maintenance operation system 140 acquires operation result data of the mining machine 140 from the operation management system 150 (S1403).
  • the maintenance operation management system 100 collates the acquired operation result data with the machine master database, and calculates the rated operation rate achievement level (S1404).
  • the maintenance operation management system 100 compares the calculated feature quantity with the machine master table, and calculates an operation factor and an environmental factor (S1405).
  • the maintenance operation system 100 calculates a maintenance factor from the calculated rated operating rate achievement level, an operation factor, and an environmental factor (S1406).
  • the maintenance operation system 100 receives an inquiry about data related to the maintenance factor from the client terminal 170 (S1407), and transmits data related to the maintenance factor to the client terminal 170 (S1408).
  • the client terminal 170 outputs the received data related to the maintenance factor to the display unit (S1409). Output images are shown in FIGS.
  • FIG. 15 is a flowchart showing an example of a processing procedure of a maintenance operation support method for estimating and visualizing operation factors, environmental factors, and maintenance factors using the model of FIG. 18 in the present embodiment.
  • operation results, machine masters, and sensor data are input, and operating factors, environmental factors, and maintenance factors that affect the operating rate are estimated and visualized.
  • the process S801 is executed by the rated operation rate achievement degree calculation function 124.
  • the rated operation rate achievement level calculation function 124 refers to the operation result database 121 and the rated operation rate table 210 of the machine master database 122, and the machine ID 201, the accumulated operation time 202, and the machine specification table 220 of the operation result database 121.
  • the model name 224 is stored in the memory 112.
  • the rated operating rate achievement level calculation function 124 refers to the rated operating rate table 210 using the machine ID 201, the accumulated operating time 202, and the model name 224, and stores the rated operating rate 213 of the machine in the memory 112.
  • the rated operation rate achievement degree calculation function 124 calculates the rated operation based on the operation rate / rated operation rate ⁇ 100 from the rated operation rate 213 of the machine stored in the memory 112 and the operation rate 206 stored in the operation result database 121.
  • the rate achievement is calculated and stored in the memory 112.
  • the rated operation rate achievement calculation function 124 in process S802 converts the rated operation rate achievement stored in the memory 112 in process S801 into the [operation rate] rated operation rate achievement degree 402 of the rated operation rate achievement database 125. Store.
  • step S803 is executed by the feature amount calculation function 126.
  • the feature amount calculation 126 refers to the operation result database 121, the machine specification table 220 of the machine master database 122, and the sensor data database 123, and the machine ID 201, the period 207, and the machine specification table 220 of the operation result database 121.
  • the vehicle body mass 225, the total vehicle mass 226, TKPH 227, and sensor data 304 of the sensor data database 123 are stored in the memory 112.
  • the feature amount calculation function 126 calculates the maximum value, the average value, and the operation time exceeding the rating shown in FIG. 3A from the vehicle body mass, the total vehicle mass, the rated value such as TKPH, and the sensor data stored in the memory 112. And stored in the memory 112.
  • the feature amount calculation function 126 normalizes the maximum value and the average value stored in the memory 112 using each rated value, and stores the normalized value in the memory 112 as the maximum rated ratio and the average rated ratio.
  • the feature amount is calculated using the load amount, TKPH, and vibration level, which are generally said to have a large effect on the operation rate. Any data may be used. In addition, each sensor data may be normalized.
  • step S804 the feature amount calculation function 126 stores the feature amount stored in the memory 112 in step S803 in each table of the feature amount database 127 in association with the machine ID and the period.
  • the operation / environment factor analysis function 128 refers to the machine specification table 220 of the feature quantity database 127 and the machine master database 122, and each feature quantity, machine ID, period, and machine specification table 220 from the feature quantity database 127.
  • the machine site ID 222 and the customer ID 223 are read and stored in the memory 112.
  • the operation / environment factor analysis function performs principal component analysis based on each feature amount, calculates the obtained principal component as an operation factor and an environment factor, and stores it in the memory 112.
  • the operation factor refers to a principal component having a strong correlation with the feature amount resulting from the operation such as the loading amount or TKPH
  • the environmental factor is a principal component having a strong correlation with the feature amount due to the surrounding environment such as a vibration level depending on the road surface condition. Point to.
  • the operation / environment factor analysis function 128 in the process S806 the operation factor stored in the memory 112 in the process S805, the environment factor, the machine ID read from the feature amount database 127, the period, and the machine spec table 220
  • the read site ID and customer ID are stored in the operation / environment factor database 129.
  • step S807 is executed by the maintenance factor estimation function 130.
  • the maintenance factor estimation function 130 refers to the rated operating rate achievement database 125 and the operation / environment factor database 129, and from the rated operating rate achievement database 125, the machine ID 401, the period 403, and the [operating rate] rated operating rate are achieved.
  • the operation factor 702, the environment factor 703, the site ID 704, and the customer ID 705 are read from the operation / environment factor database 129 and stored in the memory 112.
  • the maintenance factor estimation function 130 performs factor analysis using the [operation rate] rated operation rate achievement degree 402, the operation factor 702, and the environmental factor 703, and operates other than the operation factor 702 and the environmental factor 703. Factors affecting the rate are estimated and stored in the memory 112 as maintenance factors.
  • the operating factor 702 and the environmental factor 703 are factors obtained from arbitrary sensor data, and a maintenance factor is defined as a factor that is not transferred to these factors.
  • a maintenance factor is defined as a factor that is not transferred to these factors. The relationship between the factors will be described in detail with reference to FIG.
  • the analysis may be performed by adding the factor caused by the unmeasurement.
  • the operating factor obtained by the principal component analysis or the factor having a strong correlation with the environmental factor is used as the operating factor or the environmental factor due to unmeasurement, respectively.
  • step S808 the maintenance factor estimation function 130 stores the maintenance factor, machine ID, period, site ID, and customer ID stored in the memory 112 in step S807 in the maintenance factor database 131.
  • FIG. 16 and 17 are examples of output results of this embodiment.
  • the customer ID 714 is plotted on the horizontal axis, and the maintenance factor 712 is plotted.
  • Maintenance operation support system 111 I / O (output device) 112 Communication device 113 Memory 114 CPU (arithmetic unit) DESCRIPTION OF SYMBOLS 120 Storage device 121 Operation performance database 122 Machine master database 123 Sensor data database 124 Rated operation rate achievement degree calculation function 125 Rated operation rate achievement degree database 126 Feature amount calculation function 127 Feature amount database 128 Operation / environmental factor analysis function 129 Operation / environment Factor database 130 Maintenance factor estimation function 131 Maintenance factor database 140 Mining equipment (work machine) 150 Operation management system 160 Network 170 Client terminal

Abstract

This invention allows maintenance factors that impact the operation rate to be visualized. Maintenance factors that cannot be sensed can be visualized by calculating feature quantities such as maximum values and mean values for load capacity, speed, acceleration, and the like from sensor data for the same, specifying operational and environmental factors by executing principal component analysis on the basis of the feature quantities, calculating, from operational performance and the rated operation rate, a rated operation rate achievement level that is corrected for accumulated operating time, and executing a factor analysis on the basis of the operational factors, environmental factors, and rated operation rate achievement level.

Description

保守運用支援システム、保守運用支援方法、保守運用支援プログラムMaintenance operation support system, maintenance operation support method, maintenance operation support program
　本発明は、作業機械等の保守運用支援システム、保守運用支援方法、保守運用支援プログラムに関する。 The present invention relates to a maintenance operation support system for a work machine, a maintenance operation support method, and a maintenance operation support program.
　背景技術として特開２００２－１８１６６８号公報（特許文献１）がある。この文献に記載されている技術では、鉱山で運用される鉱山機械について、鉱山機械が走行する路面の粗さ、走行速度、積載量から、機械の寿命を推定している。 As a background art, there is JP-A-2002-181668 (Patent Document 1). In the technique described in this document, the life of a machine is estimated from the roughness of the road surface on which the mining machine travels, the traveling speed, and the load amount of the mining machine operated in the mine.
特開２００２－１８１６６８号公報JP 2002-181668 A
　従来技術では、センサデータを分析することで寿命や周辺環境の優劣を推定している。特許文献１で述べられていない稼働率へ影響を及ぼす要因として、機械に対する保守作業の実施状況などの保守要因が挙げられる。保守要因を定量評価する方法として、保守作業者が入力する保守作業ログの解析が挙げられる。しかしながら、現場の保守作業者によって入力される保守作業ログは不正確で入力漏れが発生する恐れがある。そのため、保守作業ログを解析し、保守要因を推定するためには、不正確さや入力漏れを補完する技術が必要となる。 In the conventional technology, the sensor data is analyzed to estimate the life and the superiority of the surrounding environment. Maintenance factors such as the implementation status of maintenance work on the machine can be cited as factors that affect the operating rate that are not described in Patent Document 1. As a method for quantitatively evaluating maintenance factors, analysis of maintenance work logs input by maintenance workers can be mentioned. However, the maintenance work log input by the maintenance worker at the site is inaccurate and may cause an input omission. Therefore, in order to analyze the maintenance work log and estimate the maintenance factor, a technique for complementing inaccuracy and input omission is required.
　また、保守要因を推定する別の方法として、センサによる保守作業関連情報の取得が考えられる。しかしながら、保守作業が行われる際には、一般的には機械は稼働を停止しており、通常のセンサが使用できない。また、機器の着脱を検知する既存技術はあるものの、機器の洗浄や溶接など、センサでは取得が困難な作業に関する情報も多い。本発明は、従来、センサでは情報の取得が困難であった保守作業の状況を、保守作業ログに頼らずに、推定、可視化し、稼働率へ影響を及ぼす要因を網羅的に評価することを目的とする。 Also, as another method for estimating the maintenance factor, it is conceivable to acquire maintenance work related information using a sensor. However, when maintenance work is performed, the machine generally stops operating, and a normal sensor cannot be used. In addition, although there is an existing technique for detecting attachment / detachment of equipment, there is also a lot of information related to operations that are difficult to acquire with a sensor, such as equipment cleaning and welding. The present invention estimates and visualizes the status of maintenance work, which has conventionally been difficult to acquire information with sensors, without relying on maintenance work logs, and comprehensively evaluates factors that affect the operating rate. Objective.
　上記目的を達成するために、本発明の一つの観点から、作業機械の保守運用を支援する保守運用支援装置が提供される。当該保守運用支援装置、作業機械の稼働時間情報を含む運行実績データと作業機械に取り付けられたセンサにより計測されるセンサデータと、を受信する通信部と、作業機械の累積稼働時間に対する標準稼働率に関する情報を含む定格稼働率情報と、センサデータが示す値に対する閾値に関する情報を含むセンサ閾値情報と、を格納する格納部とを有する。また、処理部は、運行実績データと定格稼働率情報とに基づいて作業機械の稼働率と標準稼働率と比に関する情報である定格稼働率達成度を算出し、センサデータとセンサ閾値情報とに基づいて特徴量を算出し、特徴量に基づいて、作業機械の稼働率に影響を及ぼす要因であって作業機械の動作に関連する要因である動作要因と作業機械の動作環境に関連する要因である環境要因とを算出し、定格稼働率達成度と動作要因と環境要因とに基づいて、作業機械の稼働率に影響を及ぼす要因であって作業機械に対する保守作業に関連する要因である保守要因を算出する。 In order to achieve the above object, a maintenance operation support apparatus that supports maintenance operation of a work machine is provided from one aspect of the present invention. The maintenance operation support apparatus, a communication unit that receives operation result data including operation time information of the work machine and sensor data measured by a sensor attached to the work machine, and a standard operation rate with respect to the accumulated operation time of the work machine And a storage unit that stores rated operating rate information including information regarding the sensor and sensor threshold information including information regarding a threshold with respect to a value indicated by the sensor data. In addition, the processing unit calculates a rated operating rate achievement degree, which is information related to a ratio between the operating rate and the standard operating rate of the work machine, based on the operation result data and the rated operating rate information. Based on the feature quantity, it is a factor that affects the operating rate of the work machine and is a factor related to the operation of the work machine and a factor related to the work environment of the work machine. A maintenance factor that is a factor that affects the operating rate of a work machine and that is related to maintenance work on the work machine, based on the calculation of a certain environmental factor and based on the achievement rate of the rated operation rate, the operating factor, and the environmental factor Is calculated.
　本発明の別の観点から、作業機械に取り付けられたセンサとネットワークを介して通信し、作業機械の保守運用を支援する保守運用支援システムにおける保守運用支援方法を提供する。当該保守運用支援方法は、作業機械の稼働時間情報を含む運行実績データと前記センサにより計測されるセンサデータとを受信し、運行実績データと作業機械の累積稼働時間に対する標準稼働率に関する情報を含む格稼働率情報とに基づいて、作業機械の稼働率と標準稼働率と比に関する情報である定格稼働率達成度を算出し、センサデータとセンサデータが示す値に対する閾値に関する情報を含むセンサ閾値情報とに基づいて特徴量を算出し、特徴量に基づいて、作業機械の稼働率に影響を及ぼす要因であって作業機械の動作に関連する要因である動作要因と作業機械の動作環境に関連する要因である環境要因とを算出し、定格稼働率達成度と動作要因と環境要因とに基づいて、作業機械の稼働率に影響を及ぼす要因であって作業機械に対する保守作業に関連する要因である保守要因を算出する。 From another viewpoint of the present invention, a maintenance operation support method in a maintenance operation support system that supports maintenance operation of a work machine by communicating with a sensor attached to the work machine via a network is provided. The maintenance operation support method receives operation result data including operation time information of the work machine and sensor data measured by the sensor, and includes information on the operation result data and the standard operation rate with respect to the accumulated operation time of the work machine. Based on the rated availability information, sensor threshold information that calculates the rated availability achievement level, which is information related to the ratio between the availability and standard availability of the work machine, and includes sensor data and information on the threshold for the value indicated by the sensor data. The feature amount is calculated based on the above, and based on the feature amount, the operating factor of the work machine is related to the operating factor and the operating environment of the working machine, which are factors affecting the operation rate of the work machine The environmental factors that are the factors are calculated, and the factors affecting the operating rate of the work machine based on the achievement rate of the rated operating rate, the operating factor, and the environmental factor. To calculate the maintenance factor is a factor related to that maintenance work.
　本発明の更に別の観点から、作業機械に取り付けられたセンサと作業機械の運行管理システムと作業機械の保守運用を支援する保守運用支援装置と端末装置と、を含む保守運用支援システムを提供する。当該保守運用支援システムでは、運行管理システムは、作業機械の稼働時間情報を含む運行実績データを管理し、運行実績データを、ネットワークを介して保守運用支援装置に送信する。センサは、計測したセンサデータを、ネットワークを介して保守運用支援装置に送信する。保守運用支援装置は、作業機械の累積稼働時間に対する標準稼働率に関する情報を含む定格稼働率情報と、センサデータが示す値に対する閾値に関する情報を含むセンサ閾値情報とを備え、運行実績データとセンサデータとを受信し、運行実績データと定格稼働率情報とに基づいて作業機械の稼働率と標準稼働率と比に関する情報である定格稼働率達成度を算出し、センサデータとセンサ閾値情報とに基づいて特徴量を算出し、特徴量に基づいて、作業機械の稼働率に影響を及ぼす要因であって作業機械の動作に関連する要因である動作要因と作業機械の動作環境に関連する要因である環境要因とを算出し、定格稼働率達成度と動作要因と環境要因とに基づいて、作業機械の稼働率に影響を及ぼす要因であって作業機械に対する保守作業に関連する要因である保守要因を算出し、保守要因に関する情報を、ネットワークを介して端末装置に送信する。端末装置は、受信した保守要因に関する情報を表示部に表示する。 According to still another aspect of the present invention, a maintenance operation support system including a sensor attached to a work machine, a work machine operation management system, a maintenance operation support device that supports maintenance operation of the work machine, and a terminal device is provided. . In the maintenance operation support system, the operation management system manages the operation result data including the operation time information of the work machine, and transmits the operation result data to the maintenance operation support device via the network. The sensor transmits the measured sensor data to the maintenance operation support apparatus via the network. The maintenance operation support apparatus includes rated operation rate information including information on a standard operation rate with respect to the cumulative operation time of the work machine, and sensor threshold information including information on a threshold value with respect to a value indicated by the sensor data. Based on the operation result data and the rated operating rate information, the rated operating rate achievement level, which is information on the operating rate and standard operating rate of the work machine, is calculated, and based on the sensor data and the sensor threshold information This is a factor that affects the operating rate of the work machine based on the feature value and that is related to the operation of the work machine and the operating environment of the work machine. The environmental factors are calculated, and the factors affecting the operating rate of the work machine based on the degree of rated operating rate achievement, operating factors, and environmental factors. Calculating the maintenance factor is a factor that, transmits information on maintenance factors, to the terminal apparatus via the network. The terminal device displays the received information regarding the maintenance factor on the display unit.
　本発明に依れば、既存のセンサデータに基づいて保守要因を分析、可視化することが可能となる。依って、本発明のユーザは、可視化した保守要因を元に稼働率向上の施策を検討することが可能となる。 According to the present invention, maintenance factors can be analyzed and visualized based on existing sensor data. Therefore, the user of the present invention can examine measures for improving the operating rate based on the visualized maintenance factor.
本実施形態における保守運用支援システムを含むネットワーク構成図である。It is a network block diagram including the maintenance operation support system in this embodiment. 本実施形態における保守運用支援システムの機能ブロック図である。It is a functional block diagram of the maintenance operation support system in this embodiment. 本実施形態における運用実績データベース例を示す図である。It is a figure which shows the example of an operation performance database in this embodiment. 本実施形態における機械マスタデータベースにおける定格稼働率テーブルを示す図である。It is a figure which shows the rated operation rate table in the machine master database in this embodiment. 本実施形態における機械マスタデータベースにおける機械スペックテーブル例示す図である。It is a figure which shows the machine specification table example in the machine master database in this embodiment. 本実施形態におけるセンサデータデータベース例を示す図である。It is a figure which shows the example of a sensor data database in this embodiment. 本実施形態におけるセンサデータ（積載量）の最大、平均、定格以上運転時間の関係を示す図である。It is a figure which shows the relationship of the operation time more than the maximum of the sensor data (loading amount) in this embodiment, average, and a rating. 本実施形態における定格稼働率達成度データベース例を示す図である。It is a figure which shows the example of a rated operation rate achievement degree database in this embodiment. 本実施形態における特徴量データベースにおける積載量テーブル例を示す図である。It is a figure which shows the example of the loading amount table in the feature-value database in this embodiment. 本実施形態における特徴量データベースにおけるＴＫＰＨテーブル例を示す図である。It is a figure which shows the example of TKPH table in the feature-value database in this embodiment. 本実施形態における特徴量データベースにおける振動レベルテーブル例を示す図である。It is a figure which shows the example of the vibration level table in the feature-value database in this embodiment. 本実施形態における動作・環境要因データベース例を示す図である。It is a figure which shows the operation | movement / environment factor database example in this embodiment. 本実施形態における保守要因データベース例を示す図である。It is a figure which shows the example of a maintenance factor database in this embodiment. 本実施例における全体の処理フロー図である。It is the whole processing flow figure in a present Example. 本実施形態における保守運用支援方法の手順例を示すフロー図である。It is a flowchart which shows the example of a procedure of the maintenance operation assistance method in this embodiment. 本実施形態における出力例１を示す図である。It is a figure which shows the output example 1 in this embodiment. 本実施形態における出力例２を示す図である。It is a figure which shows the output example 2 in this embodiment. 本実施形態における稼働率と動作要因と環境要因と保守要因の関係を示す図である。It is a figure which shows the relationship between the operation rate in this embodiment, an operation factor, an environmental factor, and a maintenance factor.
　以下に本発明の実施形態について図面を用いて詳細に説明する。本実施形態では、稼働率に影響を与える要因を動作要因と、環境要因と、保守要因、の三つによって表す。動作要因は作業機械のシリンダ油圧やエンジン回転数、モータ印可電圧などの作業機械の動作に関連する要因、環境要因は路面状況や周辺温度などの周辺環境に起因する要因、保守要因は保守作業の精度や定期保守実施の有無などの保守員の作業に起因する人的な要因、として定義する。本実施形態では、作業機械に取り付けられたセンサから動作要因および環境要因を数値化し、数値化した動作要因および環境要因から保守要員を推定する。図１８は、本実施形態においてモデル化した動作要因と、環境要因と、保守要因と、定格稼働率達成度の関係を示す一例である。四角で囲まれたパラメータはセンサあるいは運行管理システムによって観測可能な値を表している。一方、楕円で囲まれたパラメータは、センサでは観測不可能な値を表している。動作要因と、環境要因、はセンサデータを元に主成分分析を実行することで推定される要因である。保守要因は、動作要因と、環境要因と、稼働率を元に因子分析を実行することで推定される要因である。本実施形態では、センサで観測可能なあらゆる値を用いることを許容しており、図１８に示す保守要因はセンサで観測できない要因を意味する。本発明は、直接観測することが困難な保守要因を、センサデータおよび稼働率を元にした主成分分析、因子分析によって推定、可視化する。 Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the present embodiment, the factors that affect the operating rate are represented by three factors: operating factors, environmental factors, and maintenance factors. Operating factors are factors related to the operation of the work machine, such as the cylinder hydraulic pressure of the work machine, engine speed, and motor applied voltage, environmental factors are factors caused by the surrounding environment such as road surface conditions and ambient temperature, and maintenance factors are maintenance work It is defined as a human factor resulting from maintenance work such as accuracy and periodic maintenance. In this embodiment, operation factors and environmental factors are digitized from sensors attached to the work machine, and maintenance personnel are estimated from the digitized operation factors and environmental factors. FIG. 18 is an example showing the relationship among operating factors, environmental factors, maintenance factors, and rated operating rate achievement levels modeled in this embodiment. The parameters surrounded by a square represent values that can be observed by the sensor or the operation management system. On the other hand, parameters surrounded by ellipses represent values that cannot be observed by the sensor. The operating factor and the environmental factor are factors estimated by executing the principal component analysis based on the sensor data. The maintenance factor is a factor estimated by performing factor analysis based on the operation factor, the environmental factor, and the operation rate. In this embodiment, it is allowed to use any value observable by the sensor, and the maintenance factor shown in FIG. 18 means a factor that cannot be observed by the sensor. The present invention estimates and visualizes maintenance factors that are difficult to observe directly by principal component analysis and factor analysis based on sensor data and operating rates.
　図１は本実施形態における図１８のモデルを用いて、動作要因と、環境要因と、保守要因、を推定、可視化する保守運用支援システム１００を含むネットワーク構成例を示す図である。図１に示す保守運用支援システム１００は、保守の状況を可視化し、稼働率へ影響を及ぼす要因を網羅的に評価するためのコンピュータシステムである。 FIG. 1 is a diagram showing a network configuration example including a maintenance operation support system 100 that estimates and visualizes operation factors, environmental factors, and maintenance factors using the model of FIG. 18 in the present embodiment. A maintenance operation support system 100 shown in FIG. 1 is a computer system for visualizing a maintenance situation and comprehensively evaluating factors that affect an operation rate.
　本実施形態では、作業機械の例として、大型鉱山機械であるダンプトラックをとりあげて説明を行うものとする。ダンプトラックの稼働率は、動作に関する動作要因、周辺環境に関する環境要因、保守状況に関する保守要因から影響を受ける。本実施形態の保守運用支援システム１００は、これら動作要因、環境要因、保守要因を可視化するものである。 In this embodiment, a dump truck, which is a large mining machine, will be described as an example of a work machine. The operation rate of the dump truck is affected by operating factors related to the operation, environmental factors related to the surrounding environment, and maintenance factors related to the maintenance status. The maintenance operation support system 100 of this embodiment visualizes these operation factors, environmental factors, and maintenance factors.
　保守運用支援システム１００はネットワーク１６０に接続され、鉱山機械１４０、運行管理システム１５０、クライアント端末１７０とデータ通信可能となっている。鉱山機械１４０に取付けられた各種センサで計測されたデータは、ネットワーク１６０を通じて、保守運用システム１００に送信される。また、運行管理システム１５０によって収集された鉱山機械１４０の運行状況はネットワーク１６０を介して、保守運用システム１００に送信される。クライアント端末１７０は、保守運用支援システム１００にアクセスし、キーボードやマウス等における、ユーザからのデータ入力の受付処理や、保守計画立案支援システム１００から得たデータのディスプレイ等における表示処理、の各処理を担っている。 The maintenance operation support system 100 is connected to the network 160 and can communicate data with the mining machine 140, the operation management system 150, and the client terminal 170. Data measured by various sensors attached to the mining machine 140 is transmitted to the maintenance operation system 100 through the network 160. The operation status of the mining machine 140 collected by the operation management system 150 is transmitted to the maintenance operation system 100 via the network 160. The client terminal 170 accesses the maintenance operation support system 100, and receives each process of receiving data input from the user using a keyboard, a mouse, and the like, and displaying the data obtained from the maintenance planning support system 100. Is responsible.
　また、保守運用支援システム１００のハードウェア構成は以下の如くとなる。保守運用支援システム１００は、ハードディスクドライブなど適宜な不揮発性記憶装置で構成される記憶装置１２０、ＲＡＭなど揮発性記憶装置で構成されるメモリ１１３、記憶装置１２０に保持されるプログラムをメモリ１１３に読み出すなどして実行しシステム自体の統括制御を行なうとともに各種判定、演算及び制御処理を行なうＣＰＵ１１４（演算装置）、ネットワーク１６０と接続し他装置との通信処理を担う通信装置１１２を備える。 The hardware configuration of the maintenance operation support system 100 is as follows. The maintenance operation support system 100 reads out a storage device 120 configured with an appropriate nonvolatile storage device such as a hard disk drive, a memory 113 configured with a volatile storage device such as a RAM, and a program held in the storage device 120 into the memory 113. The CPU 114 (arithmetic unit) for performing overall control of the system itself and performing various determinations, computations and control processes, and the communication device 112 connected to the network 160 and responsible for communication processing with other devices.
　記憶装置１２０に実装される機能としては、定格稼働率達成度算出機能１２４、特徴量算出機能１２６、動作・環境要因推定機能１２８、保守要因推定機能１３０、がある。図１で示す保守運用支援システム１００の例では、こうした各機能群と、各機能が利用するデータを記憶するデータベース群を例示している。 The functions implemented in the storage device 120 include a rated operation rate achievement degree calculation function 124, a feature amount calculation function 126, an operation / environment factor estimation function 128, and a maintenance factor estimation function 130. The example of the maintenance operation support system 100 shown in FIG. 1 illustrates such a function group and a database group that stores data used by each function.
　なお、本実施形態では、クライアント端末１７０によってデータ入出力を行うことを想定しているが、保守運用支援システム１００が入出力機能及びデバイス（ディスプレイやキーボード等）を有しているとしてもよい。 In this embodiment, it is assumed that data input / output is performed by the client terminal 170, but the maintenance operation support system 100 may have an input / output function and a device (display, keyboard, etc.).
　続いて、本実施形態の保守運用支援システム１００が備える機能について図２を用いて説明する。保守運用支援システム１００は、運行管理システム１５０より、運行実績データを受信し、当該受信した情報を、機械マスタデータベース１２２と照合して、定格稼働率達成度を算出する定格稼働率達成度算出機能１２４を有する。作業機械は一般に累積稼働時間が増えるにつれ、稼働率が下がる。定格稼働率達成度は、累積稼働時間毎の定格稼働率を用いて、累積稼働時間の影響を補正した値である。また、保守運用システム１００は、鉱山機械１４０より、センサデータを受信し、当該受信した情報を、機械マスタデータベース１２２と照合して、特徴量を算出する特徴量算出機能１２６を有する。ここで、特徴量とは、センサデータの最大値や平均値、定格を超えて運転された時間、などで、稼働率へ特に影響を与えると考えられる特徴的な値とする。また、保守運用システム１００は、上述の機能によって算出した特徴量と、機械マスタテーブル１２２を照合して、動作要因と環境要因を推定する動作・環境要因分析機能１２８を有する。また、保守運用システム１００は、上述の機能によって算出した定格稼働率達成度と、動作要因と、環境要因から保守要因を算出する保守要因推定機能１３０を有する。 Subsequently, functions provided in the maintenance operation support system 100 of the present embodiment will be described with reference to FIG. The maintenance operation support system 100 receives operation result data from the operation management system 150, compares the received information with the machine master database 122, and calculates a rated operation rate achievement level calculation function. 124. In general, the working rate of the work machine decreases as the cumulative operation time increases. The rated operating rate achievement is a value obtained by correcting the influence of the cumulative operating time using the rated operating rate for each cumulative operating time. In addition, the maintenance operation system 100 has a feature amount calculation function 126 that receives sensor data from the mining machine 140 and compares the received information with the machine master database 122 to calculate a feature amount. Here, the feature amount is a maximum value or average value of sensor data, a time of operation exceeding the rating, or the like, and is a characteristic value that is considered to particularly affect the operation rate. In addition, the maintenance operation system 100 has an operation / environment factor analysis function 128 that compares the feature amount calculated by the above-described function with the machine master table 122 to estimate an operation factor and an environmental factor. In addition, the maintenance operation system 100 has a maintenance factor estimation function 130 that calculates a maintenance factor from the rated availability rate calculated by the above-described function, an operation factor, and an environmental factor.
　続いて、本実施形態の保守運用支援システム１００が用いるデータベース類について説明する。 Subsequently, databases used by the maintenance operation support system 100 of this embodiment will be described.
　図３に、本実施形態における運用実績データベース１２１の一例を示す。運用実績データベース１２１は、鉱山機械の運用実績を蓄積したデータベースである。そのデータ構造は、機械ＩＤ２０１、および期間２０７をキーとして、累積稼働時間２０２と、稼働時間２０３と、計画停止時間２０４と、計画外停止時間２０５と、稼働率２０６からなるレコードの集合体である。 FIG. 3 shows an example of the operation result database 121 in this embodiment. The operation result database 121 is a database in which operation results of mining machines are accumulated. The data structure is a set of records including a cumulative operation time 202, an operation time 203, a planned stop time 204, an unplanned stop time 205, and an operation rate 206 using the machine ID 201 and the period 207 as keys. .
　上述の機械ＩＤ２０１には、鉱山機械を一意に特定するためのＩＤが格納されている。また、期間２０７には、各レコードの算出期間が格納されている。また、累積稼働時間２０２には、当該機械の当該期間末時点における、累積稼働時間が格納されている。また、稼働時間２０３には、当該機械の当該期間における稼働時間が、計画停止時間２０４には、当該機械の当該期間における計画停止時間が、計画外停止時間２０５には、当該機械の当該期間における計画外停止時間が格納されている。ここで、計画停止は予め定められた定期保守などによる機械の停止を、計画外停止は突発故障などによる機械の停止を意味する。また、稼働率２０６は、稼働時間／（稼働時間＋計画停止時間＋計画外停止時間）×１００で表される稼働率が格納されている。なお、本実施形態では、期間２０７は月で区切っているが、任意の値を格納するとしてもよい。 The above-mentioned machine ID 201 stores an ID for uniquely identifying a mining machine. In the period 207, the calculation period of each record is stored. The accumulated operation time 202 stores the accumulated operation time at the end of the period of the machine. In addition, the operation time 203 includes the operation time of the machine during the period, the planned stop time 204 includes the planned stop time of the machine during the period, and the unplanned stop time 205 includes the machine during the period. Stores unplanned downtime. Here, the planned stop means a stop of the machine due to predetermined periodic maintenance or the like, and the unplanned stop means a stop of the machine due to a sudden failure or the like. The operation rate 206 stores an operation rate represented by operation time / (operation time + planned stop time + unplanned stop time) × 100. In the present embodiment, the period 207 is divided by month, but an arbitrary value may be stored.
　図４に、本実施形態における機械マスタデータベース１２２における定格稼働率テーブル２１０の一例を示す。定格稼働率テーブル２１０は、鉱山機械の標準的な稼働率を蓄積したデータベースである。そのデータ構造は、機種名２１１と、累積稼働時間２１２とをキーとして、定格稼働率２１３からなるレコードの集合体である。上述の機種名２１１には、機種を特定するための文字列が格納されている。また、累積稼働時間２１２には、機械の累積稼働時間の区分が格納されている。また、定格稼働率２１３には、ある機種がある累積稼働時間である場合に標準とされる稼働率が格納されている。この定格稼働率２１３は、機械の定期保守や部品の定期交換の間隔などから算出され、一般にメーカーあるいはベンダーから提供される。 FIG. 4 shows an example of the rated operation rate table 210 in the machine master database 122 in the present embodiment. The rated operating rate table 210 is a database in which standard operating rates of mining machines are accumulated. The data structure is a collection of records including the rated operation rate 213 with the model name 211 and the accumulated operation time 212 as keys. In the model name 211 described above, a character string for specifying the model is stored. The accumulated operating time 212 stores a category of the accumulated operating time of the machine. The rated operation rate 213 stores an operation rate that is standard when a certain model has a certain accumulated operation time. The rated operating rate 213 is calculated from the interval between periodic machine maintenance and parts replacement, and is generally provided by a manufacturer or a vendor.
　図５に、機械マスタデータベース１２２における機械スペックテーブル２２０の一例を示す。機械スペックテーブル２２０は、機械のスペックを蓄積する。そのデータ構造は、機械ＩＤ２２１をキーとして、サイトＩＤ２２２と、顧客ＩＤ２２３と、機種名２２４と、車体質量２２５と、車両総質量２２６と、ＴＫＰＨ（Ｔｏｎ・Ｋｍ　Ｐｅｒ　Ｈｏｕｒ）２２７からなるレコードの集合体である。上述の機械ＩＤ２２１は、機械を一意に特定するＩＤが格納される。サイトＩＤ２２２、および顧客ＩＤ２２３には、当該機械が稼働するサイトを一意に特定するＩＤ、および当該機械を保有する顧客を一意に特定するＩＤが格納される。機種名２２４には、機種を特定するための文字列が格納される。車体質量２２５には、当該機械の本体の質量が格納される。車両総質量２２６には、車両質量２２５と積載物の質量の和の定格最大値が格納される。ＴＫＰＨは、荷重（Ｔｏｎ）、速度（Ｋｍ）と外気温がタイヤに及ぼす影響のことを言い、ＴＫＰＨには、車両質量２２５と積載物の質量の和した値（Ｔｏｎ）に、機械の運行速度（Ｋｍ）を乗じた値の定格最大値が格納される。車体質量２２５と、車両総質量２２６と、ＴＫＰＨ２２７は一般にメーカーから提供されるスペックである。 FIG. 5 shows an example of the machine specification table 220 in the machine master database 122. The machine specification table 220 stores machine specifications. The data structure is a collection of records consisting of a site ID 222, a customer ID 223, a model name 224, a vehicle body mass 225, a total vehicle mass 226, and a TKPH (Ton · Km Per Hour) 227 with the machine ID 221 as a key. It is. The machine ID 221 described above stores an ID that uniquely identifies the machine. The site ID 222 and the customer ID 223 store an ID that uniquely identifies the site where the machine operates and an ID that uniquely identifies the customer who owns the machine. The model name 224 stores a character string for specifying the model. The vehicle body mass 225 stores the mass of the machine body. The total vehicle mass 226 stores the maximum rated value of the sum of the vehicle mass 225 and the mass of the load. TKPH refers to the effects of the load (Ton), speed (Km), and outside temperature on the tire. TKPH is the sum of the vehicle mass 225 and the mass of the load (Ton), and the machine operating speed. The rated maximum value obtained by multiplying (Km) is stored. The vehicle body mass 225, the total vehicle mass 226, and the TKPH 227 are specifications generally provided by a manufacturer.
　図６に、センサデータデータベース１２３の一例を示す。センサデータデータベース１２３は、鉱山機械１４０からネットワーク１６０を介して収集されたセンサデータを蓄積する。そのデータ構造は、機械ＩＤ３０１と、年月日３０２と、時刻３０３とをキーとして、ｎ個のセンサデータ３０４からなるレコードの集合体である。機械ＩＤ３０１には、機械を一意に特定するＩＤが格納されている。年月日３０２と、時刻３０３には、データ３０４を取得した年月日と、時刻がそれぞれ格納されている。センサデータ３０４には、ネットワーク１６０を介して収集された各種センサデータが格納されている。 FIG. 6 shows an example of the sensor data database 123. The sensor data database 123 stores sensor data collected from the mining machine 140 via the network 160. The data structure is a set of records composed of n pieces of sensor data 304 with the machine ID 301, the date 302, and the time 303 as keys. The machine ID 301 stores an ID that uniquely identifies the machine. The year / month / day 302 and the time 303 respectively store the date / time when the data 304 was acquired and the time. The sensor data 304 stores various sensor data collected via the network 160.
　図７に、センサデータ（積載量）の最大、平均、定格以上運転時間の関係を示す。最大と、平均は、ある指定した期間内のセンサデータの最大値と、平均値である。定格以上運転時間は、ある指定した期間内において、定格値を上回って運転された時間の総和を意味する。本実施形態では、最大、平均を定格比で表した値と、定格以上運転時間、を特徴量として扱う。 Fig. 7 shows the relationship between the maximum, average, and rated operating time of sensor data (loading capacity). The maximum and average are the maximum value and average value of sensor data within a specified period. The operating time above the rated value means the sum of the operating time exceeding the rated value within a specified period. In the present embodiment, the maximum and average values represented by the rating ratio and the operation time exceeding the rating are handled as the feature amount.
　図８に、定格稼働率達成度データベース１２５の一例を示す。定格稼働率達成度データベース１２５は、累積稼働時間から求めた標準的な稼働率と、実際の稼働率との比を蓄積する。そのデータ構造は、機械ＩＤ４０１と、期間４０３をキーとして、[稼働率]定格稼働率達成度４０２から成るレコードの集合体である。機械ＩＤ４０１には、機械を一意に特定するＩＤが格納される。期間４０３には、[稼働率]定格稼働率達成度４０２を算出するための期間が格納される。[稼働率] 定格稼働率達成度４０２には、当該機械の当該期間における稼働率２０６を、定格稼働率２１３で除し、１００倍した値が定格稼働率達成度として格納される。なお、定格稼働率達成度の算出は、定格稼働率達成度算出機能１２４によってなされる。 FIG. 8 shows an example of the rated availability achievement level database 125. The rated operation rate achievement degree database 125 accumulates the ratio between the standard operation rate obtained from the accumulated operation time and the actual operation rate. The data structure is a set of records composed of [operating rate] rated operating rate achievement degree 402 with machine ID 401 and period 403 as keys. The machine ID 401 stores an ID that uniquely identifies the machine. The period 403 stores a period for calculating the [operation rate] rated operation rate achievement level 402. [Occupancy rate] Rated operation rate achievement degree 402 stores the value obtained by dividing the operation rate 206 of the machine for the relevant period by the rated operation rate 213 and multiplying it by 100, as the rated operation rate achievement degree. The rated operating rate achievement level is calculated by the rated operating rate achievement level calculating function 124.
　図９に、特徴量データベース１２７における、積載量テーブル５００の一例を示す。積載量テーブル５００は、センサデータベース１２３に蓄積された積載量データから、特徴量算出機能１２６によって抽出された積載量の特徴量を蓄積する。そのデータ構造は、機械ＩＤ５０１と、期間５０５をキーとして、[積載量]定格比最大５０２と、[積載量]定格比平均５０３と、[積載量]定格以上運転時間５０４からなるレコードの集合体である。機械ＩＤ５０１には機械を一意に特定するＩＤが格納される。期間５０５には、[積載量]定格比最大５０２と、[積載量]定格比平均５０３と、[積載量]定格以上運転時間５０４、を算出する期間が格納される。[積載量]定格比最大５０２と、[積載量]定格比平均５０３と、[積載量]定格以上運転時間５０４には、センサデータデータベース１２３のレコードから図７に示す特徴量を抽出した値が格納される。なお、特徴量の抽出は、特徴量算出機能１２６によって実行される。 FIG. 9 shows an example of the load amount table 500 in the feature amount database 127. The load amount table 500 stores the feature amount of the load amount extracted by the feature amount calculation function 126 from the load amount data stored in the sensor database 123. The data structure is a set of records consisting of a machine ID 501 and a period 505 as a key, [loading capacity] rated ratio maximum 502, [loading capacity] rated ratio average 503, and [loading capacity] rated time or more operation time 504. It is. The machine ID 501 stores an ID that uniquely identifies the machine. The period 505 stores a period during which the [loading capacity] rating ratio maximum 502, the [loading capacity] rating ratio average 503, and the [loading capacity] rating or more operation time 504 are calculated. In the [loading capacity] rating ratio maximum 502, the [loading capacity] rating ratio average 503, and the [loading capacity] rating or more operation time 504, values obtained by extracting the feature values shown in FIG. Stored. Note that the feature amount extraction is executed by the feature amount calculation function 126.
　図１０に、特徴量データベース１２７における、ＴＫＰＨテーブル５１０の一例を示す。ＴＫＰＨテーブル５１０は、センサデータデータベース１２３に蓄積されたＴＫＰＨデータから、特徴量算出機能１２６によって抽出された積載量の特徴量を蓄積する。そのデータ構造は、機械ＩＤ５１１と、期間５１５をキーとして、[ＴＫＰＨ]定格比最大５１２と、[ＴＫＰＨ]定格比平均５１３と、[ＴＫＰＨ]定格以上運転時間５１４からなるレコードの集合体であり、積載量テーブル５００と同じ構造を持つ。 FIG. 10 shows an example of the TKPH table 510 in the feature amount database 127. The TKPH table 510 stores the feature amount of the load amount extracted by the feature amount calculation function 126 from the TKPH data stored in the sensor data database 123. The data structure is a set of records including machine ID 511, period 515 as a key, [TKPH] rated ratio maximum 512, [TKPH] rated ratio average 513, and [TKPH] rated or more operating time 514. It has the same structure as the load amount table 500.
　図１１に、特徴量データベース１２７における、振動レベルテーブル６００の一例を示す。振動レベルテーブル６００は、センサデータデータベース１２３に蓄積された振動レベルデータから、特徴量算出機能１２６によって抽出された振動レベルの特徴量を蓄積する。そのデータ構造は、機械ＩＤ６０１と、期間６０６、をキーとして、[振動レベル]幅方向最大６０２と、[振動レベル]幅方向平均６０３と、[振動レベル]周方向最大６０４と、[振動レベル]周方向平均６０５、からなるレコードの集合体である。その構造は、主として積載量テーブル５００、およびＴＫＰＨテーブル５１０と同じであるが、本実施形態においては、振動レベルの定格を設定していないため、定格以上運転時間が存在しない。また、本実施例では振動の方向をタイヤの幅方向（６０２、６０３）と、周方向（６０４、６０５）に分けて示している。 FIG. 11 shows an example of the vibration level table 600 in the feature amount database 127. The vibration level table 600 stores the vibration level feature quantity extracted by the feature quantity calculation function 126 from the vibration level data stored in the sensor data database 123. The data structure includes [machine vibration level] width direction maximum 602, [vibration level] width direction average 603, [vibration level] circumferential direction maximum 604, [vibration level] using machine ID 601 and period 606 as keys. This is an aggregate of records composed of an average 605 in the circumferential direction. The structure is mainly the same as that of the load amount table 500 and the TKPH table 510, but in this embodiment, since the vibration level rating is not set, there is no operation time exceeding the rating. In this embodiment, the direction of vibration is divided into the tire width direction (602, 603) and the circumferential direction (604, 605).
　本実施形態においては、一般に稼働率への影響が大きいといわれている、積載量と、ＴＫＰＨと、振動レベルを例として示したが、センサによって収集可能なデータであれば如何なるデータを用いてもよい。また、各センサデータを如何に規格化してもよい。 In this embodiment, the load amount, TKPH, and vibration level, which are generally said to have a large influence on the operation rate, are shown as examples. However, any data can be used as long as the data can be collected by the sensor. Good. In addition, each sensor data may be normalized.
　図１２に、動作・環境要因データベース１２９の一例を示す。動作・環境要因データベース１２９は、動作・環境要因分析機能１２８によって、特徴量データベース１２７から推定した各当該機械の動作要因と、環境要因を蓄積する。そのデータ構造は、機械ＩＤ７０１と、期間７０６、をキーとして、動作要因７０２と、環境要因７０３と、サイトＩＤ７０４と、顧客ＩＤ７０５からなるレコードの集合体からなる。機械ＩＤ７０１は機械を一意に特定するＩＤが格納される。期間７０６は、動作要因７０２と、環境要因７０３、を算出する期間が格納される。動作要因７０２と、環境要因７０３、はそれぞれ動作に関する動作要因、周辺環境に関する環境要因を期間７０６の間で算出した値が格納される。動作要因７０２と、環境要因７０３、は特徴量データベース１２７の各特徴量を元に、主成分分析を実行することによって得られる。サイトＩＤ７０４は、当該機械が稼働するサイトを一意に特定するＩＤが格納される。顧客ＩＤ７０５は、当該機械を保有する顧客を一意に特定するＩＤが格納される。 FIG. 12 shows an example of the operation / environment factor database 129. The operation / environment factor database 129 stores the operation factor of each machine and the environment factor estimated from the feature amount database 127 by the operation / environment factor analysis function 128. The data structure is composed of a set of records including an operation factor 702, an environment factor 703, a site ID 704, and a customer ID 705 with the machine ID 701 and the period 706 as keys. The machine ID 701 stores an ID that uniquely identifies the machine. The period 706 stores a period for calculating the operating factor 702 and the environmental factor 703. The operation factor 702 and the environment factor 703 store values obtained by calculating the operation factor related to the operation and the environment factor related to the surrounding environment during the period 706, respectively. The operation factor 702 and the environment factor 703 are obtained by executing principal component analysis based on each feature quantity in the feature quantity database 127. The site ID 704 stores an ID that uniquely identifies the site where the machine operates. The customer ID 705 stores an ID that uniquely identifies the customer who owns the machine.
　図１３に、保守要因データベース１３１の一例を示す。保守要因データベース１３１は、保守要因推定機能１３０によって、定格稼働率達成度データベース１２５と、動作・環境要因データベース１２９、から推定した保守要因を蓄積する。そのデータ構造は、機械ＩＤ７１１と、期間７１６、をキーとして、環境要因７１２と、サイトＩＤ７１３と、顧客ＩＤ７１４からなるレコードの集合体からなる。機械ＩＤ７１１は機械を一意に特定するＩＤが格納される。期間７１５は、保守要因７１２を算出する期間が格納される。保守要因７１２は、稼働率へ影響を与える保守状況に関する要因が格納される。これは、定格稼働率達成度データベース１２５の[稼働率]定格稼働率達成度４０２と、動作・環境要因データベース１２９の動作要因７０２と、環境要因７０３、を元に因子分析を実行することで得られる。サイトＩＤ７１３は、当該機械が稼働するサイトを一意に特定するＩＤが格納される。顧客ＩＤ７１４は、当該機械を保有する顧客を一意に特定するＩＤが格納される。 FIG. 13 shows an example of the maintenance factor database 131. The maintenance factor database 131 stores maintenance factors estimated from the rated operating rate achievement database 125 and the operation / environment factor database 129 by the maintenance factor estimation function 130. The data structure is composed of a collection of records including an environmental factor 712, a site ID 713, and a customer ID 714 with the machine ID 711 and the period 716 as keys. The machine ID 711 stores an ID that uniquely identifies the machine. The period 715 stores a period for calculating the maintenance factor 712. The maintenance factor 712 stores a factor related to the maintenance status that affects the operation rate. This is obtained by performing factor analysis based on the [operation rate] rated operation rate achievement level 402 of the rated operation rate achievement level database 125, the operation factor 702 of the operation / environment factor database 129, and the environmental factor 703. It is done. The site ID 713 stores an ID that uniquely identifies the site where the machine operates. The customer ID 714 stores an ID that uniquely identifies the customer who owns the machine.
　図１４は、本実施例の処理手順を説明する全体フロー図である。保守運用システム１４０は、鉱山機械１４０から各種センサデータを取得する（Ｓ１４０１）。保守運用システム１００は、取得したセンサデータを機械マスタデータベースと照合して、特徴量を算出する（Ｓ１４０２）。保守運用システム１４０は、運行管理システム１５０から、鉱山機械１４０の運行実績データを取得する（Ｓ１４０３）。保守運用管理システム１００は、取得した運行実績データを機械マスタデータベースと照合して、定格稼働率達成度を算出する（Ｓ１４０４）。保守運用管理システム１００は、算出した特徴量と機械マスタテーブルを照合して、動作要因と環境要因を算出する（Ｓ１４０５）。保守運用システム１００は、算出した定格稼働率達成度と、動作要因と、環境要因から保守要因を算出する（Ｓ１４０６）。保守運用システム１００は、クライアント端末１７０から保守要因に関連するデータの問い合わせを受信し（Ｓ１４０７）、クライアント端末１７０に対し保守要因に関連するデータを送信する（Ｓ１４０８）。クライアント端末１７０は、受信した保守要因に関連するデータを表示部に出力する（Ｓ１４０９）。出力イメージは図１６、１７である。 FIG. 14 is an overall flowchart for explaining the processing procedure of the present embodiment. The maintenance operation system 140 acquires various sensor data from the mining machine 140 (S1401). The maintenance operation system 100 collates the acquired sensor data with the machine master database and calculates the feature amount (S1402). The maintenance operation system 140 acquires operation result data of the mining machine 140 from the operation management system 150 (S1403). The maintenance operation management system 100 collates the acquired operation result data with the machine master database, and calculates the rated operation rate achievement level (S1404). The maintenance operation management system 100 compares the calculated feature quantity with the machine master table, and calculates an operation factor and an environmental factor (S1405). The maintenance operation system 100 calculates a maintenance factor from the calculated rated operating rate achievement level, an operation factor, and an environmental factor (S1406). The maintenance operation system 100 receives an inquiry about data related to the maintenance factor from the client terminal 170 (S1407), and transmits data related to the maintenance factor to the client terminal 170 (S1408). The client terminal 170 outputs the received data related to the maintenance factor to the display unit (S1409). Output images are shown in FIGS.
　図１５は本実施形態における図１８のモデルを用いて、動作要因と、環境要因と、保守要因を推定、可視化する保守運用支援方法の処理手順例を示すフロー図である。本フローでは、運行実績と、機械マスタと、センサデータ、を入力として、稼働率へ影響を与える動作要因、環境要因、保守要因、を推定、可視化する。まず、処理Ｓ８０１は定格稼働率達成度算出機能１２４によって実行される。定格稼働率達成度算出機能１２４は、運行実績データベース１２１、および機械マスタデータベース１２２の定格稼働率テーブ２１０を参照し、運行実績データベース１２１の機械ＩＤ２０１と、累積稼働時間２０２と、機械スペックテーブル２２０の機種名２２４をメモリ１１２に格納する。定格稼働率達成度算出機能１２４は、機械ＩＤ２０１と、累積稼働時間２０２と、機種名２２４、を用いて定格稼働率テーブル２１０を参照し、当該機械の定格稼働率２１３をメモリ１１２に格納する。定格稼働率達成度算出機能１２４は、メモリ１１２に格納した当該機械の定格稼働率２１３と、運行実績データベース１２１に格納されている稼働率２０６から、稼働率／定格稼働率×１００、によって定格稼働率達成度を算出し、メモリ１１２に格納する。 FIG. 15 is a flowchart showing an example of a processing procedure of a maintenance operation support method for estimating and visualizing operation factors, environmental factors, and maintenance factors using the model of FIG. 18 in the present embodiment. In this flow, operation results, machine masters, and sensor data are input, and operating factors, environmental factors, and maintenance factors that affect the operating rate are estimated and visualized. First, the process S801 is executed by the rated operation rate achievement degree calculation function 124. The rated operation rate achievement level calculation function 124 refers to the operation result database 121 and the rated operation rate table 210 of the machine master database 122, and the machine ID 201, the accumulated operation time 202, and the machine specification table 220 of the operation result database 121. The model name 224 is stored in the memory 112. The rated operating rate achievement level calculation function 124 refers to the rated operating rate table 210 using the machine ID 201, the accumulated operating time 202, and the model name 224, and stores the rated operating rate 213 of the machine in the memory 112. The rated operation rate achievement degree calculation function 124 calculates the rated operation based on the operation rate / rated operation rate × 100 from the rated operation rate 213 of the machine stored in the memory 112 and the operation rate 206 stored in the operation result database 121. The rate achievement is calculated and stored in the memory 112.
　次に、処理Ｓ８０２で定格稼働率達成度算出機能１２４は、処理Ｓ８０１においてメモリ１１２に格納した定格稼働率達成度を、定格稼働率達成度データベース１２５の[稼働率]定格稼働率達成度４０２に格納する。 Next, the rated operation rate achievement calculation function 124 in process S802 converts the rated operation rate achievement stored in the memory 112 in process S801 into the [operation rate] rated operation rate achievement degree 402 of the rated operation rate achievement database 125. Store.
　また、処理Ｓ８０３は、特徴量算出機能１２６によって実行される。特徴量算出１２６は、運行実績データベース１２１と、機械マスタデータベース１２２の機械スペックテーブル２２０と、センサデータデータベース１２３、を参照し、運行実績データベース１２１の機械ＩＤ２０１と、期間２０７と、機械スペックテーブル２２０の車体質量２２５と、車両総質量２２６と、ＴＫＰＨ２２７と、センサデータデータベース１２３のセンサデータ３０４をメモリ１１２に格納する。特徴量算出機能１２６は、メモリ１１２に格納した、車体質量と、車両総質量と、ＴＫＰＨなどの定格値と、センサデータから、図３Ａに示す最大値、平均値、定格以上運転時間を算出し、メモリ１１２に格納する。また、特徴量算出機能１２６は、メモリ１１２に格納した最大値と、平均値を、各々の定格値を用いて規格化を行い、定格比最大と定格比平均としてメモリ１１２に格納する。なお、本実形態においては、一般的に稼働率への影響が大きいといわれる積載量と、ＴＫＰＨと、振動レベルを用いて特徴量を算出しているが、センサによって収集可能なデータであれば如何なるデータを用いてもよい。また、各センサデータを如何に規格化してもよい。 Also, step S803 is executed by the feature amount calculation function 126. The feature amount calculation 126 refers to the operation result database 121, the machine specification table 220 of the machine master database 122, and the sensor data database 123, and the machine ID 201, the period 207, and the machine specification table 220 of the operation result database 121. The vehicle body mass 225, the total vehicle mass 226, TKPH 227, and sensor data 304 of the sensor data database 123 are stored in the memory 112. The feature amount calculation function 126 calculates the maximum value, the average value, and the operation time exceeding the rating shown in FIG. 3A from the vehicle body mass, the total vehicle mass, the rated value such as TKPH, and the sensor data stored in the memory 112. And stored in the memory 112. The feature amount calculation function 126 normalizes the maximum value and the average value stored in the memory 112 using each rated value, and stores the normalized value in the memory 112 as the maximum rated ratio and the average rated ratio. In this embodiment, the feature amount is calculated using the load amount, TKPH, and vibration level, which are generally said to have a large effect on the operation rate. Any data may be used. In addition, each sensor data may be normalized.
　次に、処理Ｓ８０４で特徴量算出機能１２６は、処理Ｓ８０３においてメモリ１１２に格納した特徴量を、機械ＩＤと期間に紐づけて、特徴量データベース１２７の各テーブルに格納する。 Next, in step S804, the feature amount calculation function 126 stores the feature amount stored in the memory 112 in step S803 in each table of the feature amount database 127 in association with the machine ID and the period.
　次に、処理Ｓ８０５は、動作・環境要因分析機能１２８によって実行される。動作・環境要因分析機能１２８は、特徴量データベース１２７と機械マスタデータベース１２２の機械スペックテーブル２２０を参照し、特徴量データベース１２７から各特徴量と、機械ＩＤと、期間と、機械スペックテーブル２２０から当該機械のサイトＩＤ２２２と、顧客ＩＤ２２３を読み込み、メモリ１１２に格納する。動作・環境要因分析機能は、各特徴量を元に主成分分析を実行し、得られた主成分を動作要因と、環境要因として算出、メモリ１１２に格納する。ここで、動作要因は積載量やＴＫＰＨなど動作に起因する特徴量と相関が強い主成分を指し、環境要因は路面状況に依存する振動レベルなど周辺環境に起因する特徴量と相関が強い主成分を指す。 Next, the process S805 is executed by the operation / environment factor analysis function 128. The operation / environment factor analysis function 128 refers to the machine specification table 220 of the feature quantity database 127 and the machine master database 122, and each feature quantity, machine ID, period, and machine specification table 220 from the feature quantity database 127. The machine site ID 222 and the customer ID 223 are read and stored in the memory 112. The operation / environment factor analysis function performs principal component analysis based on each feature amount, calculates the obtained principal component as an operation factor and an environment factor, and stores it in the memory 112. Here, the operation factor refers to a principal component having a strong correlation with the feature amount resulting from the operation such as the loading amount or TKPH, and the environmental factor is a principal component having a strong correlation with the feature amount due to the surrounding environment such as a vibration level depending on the road surface condition. Point to.
　次に、処理Ｓ８０６で動作・環境要因分析機能１２８は、処理Ｓ８０５でメモリ１１２に格納した動作要因と、環境要因と、特徴量データベース１２７から読み込んだ機械ＩＤと、期間と、機械スペックテーブル２２０から読み込んだサイトＩＤと、顧客ＩＤ、を動作・環境要因データベース１２９に格納する。 Next, the operation / environment factor analysis function 128 in the process S806, the operation factor stored in the memory 112 in the process S805, the environment factor, the machine ID read from the feature amount database 127, the period, and the machine spec table 220 The read site ID and customer ID are stored in the operation / environment factor database 129.
　また、処理Ｓ８０７は、保守要因推定機能１３０によって実行される。保守要因推定機能１３０は、定格稼働率達成度データベース１２５と、動作・環境要因データベース１２９を参照し、定格稼働率達成度データベース１２５から機械ＩＤ４０１と、期間４０３と、[稼働率]定格稼働率達成度４０２と、動作・環境要因データベース１２９から動作要因７０２と、環境要因７０３と、サイトＩＤ７０４と、顧客ＩＤ７０５、を読み込み、メモリ１１２に格納する。保守要因推定機能１３０は、[稼働率]定格稼働率達成度４０２と、動作要因７０２と、環境要因７０３、を用いて、因子分析を実行し、動作要因７０２と、環境要因７０３、以外の稼働率へ影響を与える要因を推定し、保守要因としてメモリ１１２に格納する。ここで、動作要因７０２と、環境要因７０３、は任意のセンサデータより求まる要因であり、これらの要因に繰り込まれない要因として保守要因を定義している。各要因の関係は図１８の説明で詳述する。なお、作業機械に取り付けられたセンサの数が不十分で、環境要因および動作要因が既知と言えない場合、未計測に起因する要因を加えて分析しても良い。この場合、主成分分析によって得られた動作要因、あるいは、環境要因に対して強い相関を示す要因を、それぞれ、未計測に起因する動作要因、あるいは、環境要因として用いる。 Also, step S807 is executed by the maintenance factor estimation function 130. The maintenance factor estimation function 130 refers to the rated operating rate achievement database 125 and the operation / environment factor database 129, and from the rated operating rate achievement database 125, the machine ID 401, the period 403, and the [operating rate] rated operating rate are achieved. The operation factor 702, the environment factor 703, the site ID 704, and the customer ID 705 are read from the operation / environment factor database 129 and stored in the memory 112. The maintenance factor estimation function 130 performs factor analysis using the [operation rate] rated operation rate achievement degree 402, the operation factor 702, and the environmental factor 703, and operates other than the operation factor 702 and the environmental factor 703. Factors affecting the rate are estimated and stored in the memory 112 as maintenance factors. Here, the operating factor 702 and the environmental factor 703 are factors obtained from arbitrary sensor data, and a maintenance factor is defined as a factor that is not transferred to these factors. The relationship between the factors will be described in detail with reference to FIG. In addition, when the number of sensors attached to the work machine is insufficient and it cannot be said that the environmental factor and the operation factor are known, the analysis may be performed by adding the factor caused by the unmeasurement. In this case, the operating factor obtained by the principal component analysis or the factor having a strong correlation with the environmental factor is used as the operating factor or the environmental factor due to unmeasurement, respectively.
　次に、処理Ｓ８０８で保守要因推定機能１３０は、処理Ｓ８０７でメモリ１１２に格納した保守要因と、機械ＩＤと、期間と、サイトＩＤと、顧客ＩＤ、を保守要因データベース１３１に格納する。 Next, in step S808, the maintenance factor estimation function 130 stores the maintenance factor, machine ID, period, site ID, and customer ID stored in the memory 112 in step S807 in the maintenance factor database 131.
　図１６と図１７は、本実施形態の出力結果の一例である。図９では、顧客ＩＤ７１４を横軸にとり、保守要因７１２をプロットしている。図９Ａでは、顧客ＩＤ＝“ｃｕｓｔｏｍｅｒ－００１”のサイトＩＤ７１３を横軸にとり、保守要因７１２をプロットしている。図９より、ユーザは、“ｃｕｓｔｏｍｅｒ－００１”の保守要因のばらつきが、“ｃｕｓｔｏｍｅｒ－００２”の保守要因のばらつきに比べ大きいことを見ることが出来る。次に、図９Ａの“ｃｕｓｔｏｍｅｒ－００１”のサイト毎の保守要因から、例えば、“ｓｉｔｅ－Ｄ”が他のサイトと比較して保守要因が低くなっていることを見ることが出来る。この結果を元に、 “ｓｉｔｅ－Ｄ”の保守状況の調査など、稼働率改善に向けた提案が可能となる。 16 and 17 are examples of output results of this embodiment. In FIG. 9, the customer ID 714 is plotted on the horizontal axis, and the maintenance factor 712 is plotted. In FIG. 9A, the site ID 713 of customer ID = “customer-001” is plotted on the horizontal axis, and the maintenance factor 712 is plotted. From FIG. 9, the user can see that the variation of the maintenance factor of “customer-001” is larger than the variation of the maintenance factor of “customer-002”. Next, from the maintenance factor for each site of “customer-001” in FIG. 9A, for example, it can be seen that the maintenance factor for “site-D” is lower than that for other sites. Based on this result, it is possible to make proposals for improving the operating rate, such as a survey of the maintenance status of “site-D”.
　１００　保守運用支援システム
　１１１　Ｉ／Ｏ（出力装置）
　１１２　通信装置
　１１３　メモリ
　１１４　ＣＰＵ（演算装置）
　１２０　記憶装置
　１２１　運行実績データベース
　１２２　機械マスタデータベース
　１２３　センサデータデータベース
　１２４　定格稼働率達成度算出機能
　１２５　定格稼働率達成度データベース
　１２６　特徴量算出機能
　１２７　特徴量データベース
　１２８　動作・環境要因分析機能
　１２９　動作・環境要因データベース
　１３０　保守要因推定機能
　１３１　保守要因データベース
　１４０　鉱山機械（作業機械）
　１５０　運行管理システム
　１６０　ネットワーク
　１７０　クライアント端末 100 Maintenance operation support system 111 I / O (output device)
112 Communication device 113 Memory 114 CPU (arithmetic unit)
DESCRIPTION OF SYMBOLS 120 Storage device 121 Operation performance database 122 Machine master database 123 Sensor data database 124 Rated operation rate achievement degree calculation function 125 Rated operation rate achievement degree database 126 Feature amount calculation function 127 Feature amount database 128 Operation / environmental factor analysis function 129 Operation / environment Factor database 130 Maintenance factor estimation function 131 Maintenance factor database 140 Mining equipment (work machine)
150 Operation management system 160 Network 170 Client terminal

Claims (15)

  1. 　作業機械の保守運用を支援する保守運用支援装置であって、
    　前記作業機械の稼働時間情報を含む運行実績データと前記作業機械に取り付けられたセンサにより計測されるセンサデータと、を受信する通信部と、
    　前記作業機械の累積稼働時間に対する標準稼働率に関する情報を含む定格稼働率情報と、前記センサデータが示す値に対する閾値に関する情報を含むセンサ閾値情報と、を格納する格納部と、
    　前記運行実績データと前記定格稼働率情報とに基づいて前記作業機械の稼働率と前記標準稼働率と比に関する情報である定格稼働率達成度を算出し、前記センサデータと前記センサ閾値情報とに基づいて特徴量を算出し、前記特徴量に基づいて、前記作業機械の稼働率に影響を及ぼす要因であって前記作業機械の動作に関連する要因である動作要因と前記作業機械の動作環境に関連する要因である環境要因とを算出し、前記定格稼働率達成度と前記動作要因と前記環境要因とに基づいて、前記作業機械の稼働率に影響を及ぼす要因であって前記作業機械に対する保守作業に関連する要因である保守要因を算出する処理部と、を有することを特徴とする保守運用支援装置。     A maintenance operation support device that supports maintenance operation of a work machine,
    A communication unit that receives operation result data including operating time information of the work machine and sensor data measured by a sensor attached to the work machine,
    A storage unit for storing rated operating rate information including information on a standard operating rate with respect to a cumulative operating time of the work machine, and sensor threshold information including information on a threshold value with respect to a value indicated by the sensor data;
    Based on the operation record data and the rated operating rate information, a rated operating rate achievement degree, which is information related to a ratio between the operating rate of the work machine and the standard operating rate, is calculated, and the sensor data and the sensor threshold information are Based on the feature amount, an operating factor that affects the operating rate of the work machine and that is related to the operation of the work machine and an operating environment of the work machine are calculated. An environmental factor that is a related factor is calculated, and based on the degree of achievement of the rated operating rate, the operating factor, and the environmental factor, a factor that affects the operating rate of the working machine and that is a maintenance for the working machine A maintenance operation support apparatus comprising: a processing unit that calculates a maintenance factor that is a factor related to work.
  2. 　請求項１に記載の保守運用支援装置であって、
    　前記処理部は、前記動作要因と前記環境要因とを前記特徴量に基づく主成分分析により算出すること、を特徴とする保守運用支援装置。     The maintenance operation support apparatus according to claim 1,
    The maintenance operation support apparatus, wherein the processing unit calculates the operation factor and the environmental factor by principal component analysis based on the feature amount.
  3. 　請求項１に記載の保守運用支援装置であって、
    　前記処理部は、前記定格稼働率達成度と前記動作要因と前記環境要因とに基づく因子分析により、前記作業機械の稼働率に影響を及ぼす要因であって前記動作要因と前記環境要因以外の要因を算出し、前記動作要因と前記環境要因以外の要因を前記保守要因と推定する、ことを特徴とする保守運用支援装置。     The maintenance operation support apparatus according to claim 1,
    The processing unit is a factor that affects the operating rate of the work machine by factor analysis based on the achievement rate of the rated operating rate, the operating factor, and the environmental factor, and is a factor other than the operating factor and the environmental factor. And a factor other than the operating factor and the environmental factor is estimated as the maintenance factor.
  4. 　請求項１に記載の保守運用支援装置であって、
    　前記処理部は、前記作業機械の稼働率を前記運行実績データに含まれる前記稼働時間情報に基づいて算出する、ことを特徴とする保守運用支援装置。     The maintenance operation support apparatus according to claim 1,
    The maintenance operation support apparatus, wherein the processing unit calculates an operation rate of the work machine based on the operation time information included in the operation result data.
  5. 　請求項１に記載の保守運用支援装置であって、
    　前記通信部は、前記センサデータとして、前記作業機械の積載量データ、ＴＫＰＨ（Ｔｏｎ・Ｋｍ　Ｐｅｒ　Ｈｏｕｒ）データ、又は振動レベルデータを受信する、ことを特徴とする保守運用支援装置。     The maintenance operation support apparatus according to claim 1,
    The maintenance operation support apparatus, wherein the communication unit receives load data, TKPH (Ton · Km Per Hour) data, or vibration level data of the work machine as the sensor data.
  6. 　請求項５に記載の保守運用支援装置であって、
    　前記処理部は、前記特徴量として、前記積載量データに関する特徴量、前記ＴＫＰＨに関する特徴量、又は前記振動レベルに関する特徴量を算出する、ことを特徴とする保守運用支援装置。     The maintenance operation support device according to claim 5,
    The maintenance operation support apparatus, wherein the processing unit calculates a feature value related to the load amount data, a feature value related to the TKPH, or a feature value related to the vibration level as the feature value.
  7. 　作業機械に取り付けられたセンサとネットワークを介して通信し、前記作業機械の保守運用を支援する保守運用支援システムにおける保守運用支援方法であって、
    　前記作業機械の稼働時間情報を含む運行実績データと前記センサにより計測されるセンサデータと、を受信し、
    　前記運行実績データと前記作業機械の累積稼働時間に対する標準稼働率に関する情報を含む格稼働率情報とに基づいて、前記作業機械の稼働率と前記標準稼働率と比に関する情報である定格稼働率達成度を算出し、
    　前記センサデータと前記センサデータが示す値に対する閾値に関する情報を含むセンサ閾値情報とに基づいて特徴量を算出し、
    　前記特徴量に基づいて、前記作業機械の稼働率に影響を及ぼす要因であって前記作業機械の動作に関連する要因である動作要因と前記作業機械の動作環境に関連する要因である環境要因とを算出し、
    　前記定格稼働率達成度と前記動作要因と前記環境要因とに基づいて、前記作業機械の稼働率に影響を及ぼす要因であって前記作業機械に対する保守作業に関連する要因である保守要因を算出する、
    　ことを特徴とする保守運用支援方法。     A maintenance operation support method in a maintenance operation support system that communicates with a sensor attached to a work machine via a network and supports the maintenance operation of the work machine,
    Receiving operation result data including operating time information of the work machine and sensor data measured by the sensor;
    Based on the operation result data and the rated operating rate information including information on the standard operating rate with respect to the cumulative operating time of the work machine, the rated operating rate which is information on the operating rate of the working machine and the standard operating rate is achieved. Calculate the degree,
    A feature amount is calculated based on the sensor data and sensor threshold information including information on a threshold for a value indicated by the sensor data,
    Based on the feature amount, an operating factor that affects the operating rate of the work machine and is a factor related to the operation of the work machine, and an environmental factor that is a factor related to the operating environment of the work machine; To calculate
    Based on the rated operating rate achievement level, the operating factor, and the environmental factor, a maintenance factor that is a factor that affects the operating rate of the work machine and that is related to maintenance work on the work machine is calculated. ,
    A maintenance operation support method characterized by that.
  8. 　請求項７に記載の保守運用支援方法であって、
    　前記動作要因と前記環境要因とを前記特徴量に基づく主成分分析により算出すること、を特徴とする保守運用支援方法。     The maintenance operation support method according to claim 7,
    A maintenance operation support method, characterized in that the operation factor and the environmental factor are calculated by principal component analysis based on the feature amount.
  9. 　請求項７に記載の保守運用支援方法であって、
    　前記定格稼働率達成度と前記動作要因と前記環境要因とに基づく因子分析により、前記作業機械の稼働率に影響を及ぼす要因であって前記動作要因と前記環境要因以外の要因を算出し、
    　前記動作要因と前記環境要因以外の要因を前記保守要因と推定する、ことを特徴とする保守運用支援方法。     The maintenance operation support method according to claim 7,
    By factor analysis based on the rated operating rate achievement degree, the operating factor, and the environmental factor, a factor affecting the operating rate of the work machine and calculating a factor other than the operating factor and the environmental factor,
    A maintenance operation support method, wherein factors other than the operation factor and the environmental factor are estimated as the maintenance factor.
  10. 　請求項７に記載の保守運用支援方法であって、
    　前記作業機械の稼働率を前記運行実績データに含まれる前記稼働時間情報に基づいて算出する、ことを特徴とする保守運用支援方法。     The maintenance operation support method according to claim 7,
    A maintenance operation support method, wherein an operation rate of the work machine is calculated based on the operation time information included in the operation result data.
  11. 　請求項７に記載の保守運用支援方法であって、
    　前記センサデータとして、前記作業機械の積載量データ、ＴＫＰＨ（Ｔｏｎ・Ｋｍ　Ｐｅｒ　Ｈｏｕｒ）データ、又は振動レベルデータを受信する、ことを特徴とする保守運用支援方法。     The maintenance operation support method according to claim 7,
    A maintenance operation support method characterized by receiving load data, TKPH (Ton · Km Per Hour) data, or vibration level data of the work machine as the sensor data.
  12. 　請求項１１に記載の保守運用支援方法であって、
    　前記特徴量として、前記積載量データに関する特徴量、前記ＴＫＰＨに関する特徴量、又は前記振動レベルに関する特徴量を算出する、ことを特徴とする保守運用支援方法。     The maintenance operation support method according to claim 11,
    A maintenance operation support method characterized by calculating, as the feature amount, a feature amount relating to the load amount data, a feature amount relating to the TKPH, or a feature amount relating to the vibration level.
  13. 　作業機械に取り付けられたセンサと前記作業機械の運行管理システムと前記作業機械の保守運用を支援する保守運用支援装置と端末装置と、を含む保守運用支援システムであって、
    　前記運行管理システムは、
    　前記作業機械の稼働時間情報を含む運行実績データを管理し、前記運行実績データを、ネットワークを介して前記保守運用支援装置に送信し、
    　前記センサは、
    　計測したセンサデータを、前記ネットワークを介して前記保守運用支援装置に送信し、　前記保守運用支援装置は、
    　前記作業機械の累積稼働時間に対する標準稼働率に関する情報を含む定格稼働率情報と、前記センサデータが示す値に対する閾値に関する情報を含むセンサ閾値情報とを備え、　前記運行実績データと前記センサデータとを受信し、前記運行実績データと前記定格稼働率情報とに基づいて前記作業機械の稼働率と前記標準稼働率と比に関する情報である定格稼働率達成度を算出し、前記センサデータと前記センサ閾値情報とに基づいて特徴量を算出し、前記特徴量に基づいて、前記作業機械の稼働率に影響を及ぼす要因であって前記作業機械の動作に関連する要因である動作要因と前記作業機械の動作環境に関連する要因である環境要因とを算出し、前記定格稼働率達成度と前記動作要因と前記環境要因とに基づいて、前記作業機械の稼働率に影響を及ぼす要因であって前記作業機械に対する保守作業に関連する要因である保守要因を算出し、前記保守要因に関する情報を、前記ネットワークを介して前記端末装置に送信し、
    　前記端末装置は、受信した前記保守要因に関する情報を表示部に表示する、
    　ことを特徴とする保守運用支援システム。     A maintenance operation support system including a sensor attached to a work machine, an operation management system for the work machine, a maintenance operation support device that supports maintenance operation of the work machine, and a terminal device,
    The operation management system is
    Manage operation result data including operating time information of the work machine, and transmit the operation result data to the maintenance operation support device via a network,
    The sensor is
    Send the measured sensor data to the maintenance operation support device via the network, the maintenance operation support device,
    A rated operating rate information including information on a standard operating rate with respect to a cumulative operating time of the work machine, and sensor threshold information including information on a threshold with respect to a value indicated by the sensor data, and the operation result data and the sensor data. Receiving, calculating a rated operating rate achievement level, which is information relating to a ratio between the operating rate of the work machine and the standard operating rate, based on the operation result data and the rated operating rate information, and the sensor data and the sensor threshold value A feature amount is calculated based on the information, and based on the feature amount, an operating factor that is a factor that affects an operation rate of the work machine and that is related to the operation of the work machine, and the work machine An environmental factor that is a factor related to the operating environment is calculated, and the operating rate of the work machine is calculated based on the achievement rate of the rated operating rate, the operating factor, and the environmental factor. Calculating a maintenance factor that is a factor affecting and relating to maintenance work on the work machine, and transmits information on the maintenance factor to the terminal device via the network;
    The terminal device displays the received information on the maintenance factor on a display unit;
    Maintenance operation support system characterized by that.
  14. 　請求項１３に記載の保守運用支援システムであって、
    　前記保守運用支援装置は、前記動作要因と前記環境要因とを前記特徴量に基づく主成分分析により算出すること、を特徴とする保守運用支援システム。     The maintenance operation support system according to claim 13,
    The maintenance operation support system is characterized in that the operation factor and the environmental factor are calculated by principal component analysis based on the feature amount.
  15. 　請求項１３に記載の保守運用支援システムであって、
    　前記保守運用支援装置は、前記定格稼働率達成度と前記動作要因と前記環境要因とに基づく因子分析により、前記作業機械の稼働率に影響を及ぼす要因であって前記動作要因と前記環境要因以外の要因を算出し、前記動作要因と前記環境要因以外の要因を前記保守要因と推定する、ことを特徴とする保守運用支援システム。     The maintenance operation support system according to claim 13,
    The maintenance operation support device is a factor that affects the operating rate of the work machine by factor analysis based on the achievement rate of the rated operating rate, the operating factor, and the environmental factor, other than the operating factor and the environmental factor. And a factor other than the operating factor and the environmental factor is estimated as the maintenance factor.
PCT/JP2014/052203 2014-01-31 2014-01-31 Maintenance and operation assist system, maintenance and operation assist method, and maintenance and operation assist program WO2015114792A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2014/052203 WO2015114792A1 (en) 2014-01-31 2014-01-31 Maintenance and operation assist system, maintenance and operation assist method, and maintenance and operation assist program
JP2015559687A JP6285467B2 (en) 2014-01-31 2014-01-31 Maintenance operation support system, maintenance operation support method, maintenance operation support program

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2014/052203 WO2015114792A1 (en) 2014-01-31 2014-01-31 Maintenance and operation assist system, maintenance and operation assist method, and maintenance and operation assist program

Publications (1)

Publication Number Publication Date
WO2015114792A1 true WO2015114792A1 (en) 2015-08-06

Family

ID=53756404

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2014/052203 WO2015114792A1 (en) 2014-01-31 2014-01-31 Maintenance and operation assist system, maintenance and operation assist method, and maintenance and operation assist program

Country Status (2)

Country Link
JP (1) JP6285467B2 (en)
WO (1) WO2015114792A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2015040745A1 (en) * 2013-09-20 2017-03-02 株式会社小松製作所 Tire abnormality management system and tire abnormality management method
JPWO2017082362A1 (en) * 2015-11-10 2018-08-30 株式会社ブリヂストン Tire management method and tire management apparatus

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002181668A (en) * 2000-12-08 2002-06-26 Komatsu Ltd Service life estimating method and service life estimating system
JP2013041448A (en) * 2011-08-17 2013-02-28 Hitachi Ltd Method of abnormality detection/diagnosis and system of abnormality detection/diagnosis

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4856163B2 (en) * 2008-12-26 2012-01-18 日立建機株式会社 Equipment for providing diagnostic information for construction machinery

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002181668A (en) * 2000-12-08 2002-06-26 Komatsu Ltd Service life estimating method and service life estimating system
JP2013041448A (en) * 2011-08-17 2013-02-28 Hitachi Ltd Method of abnormality detection/diagnosis and system of abnormality detection/diagnosis

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2015040745A1 (en) * 2013-09-20 2017-03-02 株式会社小松製作所 Tire abnormality management system and tire abnormality management method
US10245905B2 (en) 2013-09-20 2019-04-02 Komatsu Ltd. Tire abnormality management system and tire abnormality management method
JPWO2017082362A1 (en) * 2015-11-10 2018-08-30 株式会社ブリヂストン Tire management method and tire management apparatus

Also Published As

Publication number Publication date
JPWO2015114792A1 (en) 2017-03-23
JP6285467B2 (en) 2018-02-28

Similar Documents

Publication Publication Date Title
CN111259515B (en) Aircraft health management method and system
JP5100675B2 (en) Instrument drift detection device and instrument drift detection method
JP5858839B2 (en) Work machine abnormality diagnosis device
US20130151170A1 (en) Sensor system, computer, and machine
US10620036B2 (en) Attachment monitoring system
JP2017205821A (en) Information processor, information processing method, information processing program, and information processing system
EP2597602A1 (en) Aircraft trending systems and methods
Chen et al. Analysis of common-cause and special-cause variation in the deterioration of transportation infrastructure: A field application of statistical process control for structural health monitoring
US10019895B2 (en) Method and system for detecting frequent lane changes of moving vehicles
CN101806666B (en) Health monitoring method for identifying damaged cable and support displacement based on space coordinate monitoring
JP6285467B2 (en) Maintenance operation support system, maintenance operation support method, maintenance operation support program
CN105632114A (en) Monitoring measurement point safety state monitoring method based on GIS technology
US20170063997A1 (en) Evaluation apparatus, evaluation system, device, and evaluation method
JP6968026B2 (en) Tire condition detector
US10288530B2 (en) Method for improving severity estimates
JP6509335B2 (en) Shovel support device
CN103493081B (en) The coating thickness of vehicle calculates system, computational methods
US11656595B2 (en) System and method for machine monitoring
US11415958B2 (en) Data extracting apparatus, data extracting method, and recording medium
JP2018001282A (en) Operational state detection method, operational state detection system and operational state detection program
JP6977455B2 (en) Vehicle management system
JP5303435B2 (en) Vehicle failure information management
Jakobsson et al. Data driven modeling and estimation of accumulated damage in mining vehicles using on-board sensors
CN114450647B (en) Diagnosis of technical systems
WO2023074834A1 (en) Mine management system

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: 14881187

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2015559687

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 14881187

Country of ref document: EP

Kind code of ref document: A1