WO2023074834A1 - 鉱山管理システム - Google Patents
鉱山管理システム Download PDFInfo
- Publication number
- WO2023074834A1 WO2023074834A1 PCT/JP2022/040298 JP2022040298W WO2023074834A1 WO 2023074834 A1 WO2023074834 A1 WO 2023074834A1 JP 2022040298 W JP2022040298 W JP 2022040298W WO 2023074834 A1 WO2023074834 A1 WO 2023074834A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- productivity
- unplanned
- management system
- dump truck
- data
- Prior art date
Links
- 238000012545 processing Methods 0.000 claims abstract description 61
- 238000005065 mining Methods 0.000 claims abstract description 59
- 238000010801 machine learning Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 17
- 230000002776 aggregation Effects 0.000 claims description 16
- 238000004220 aggregation Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 15
- 238000009412 basement excavation Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 10
- 230000007704 transition Effects 0.000 claims description 10
- 238000002360 preparation method Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 28
- 230000006870 function Effects 0.000 description 15
- 238000012423 maintenance Methods 0.000 description 12
- 230000006872 improvement Effects 0.000 description 11
- 238000013145 classification model Methods 0.000 description 9
- 238000012800 visualization Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 238000007599 discharging Methods 0.000 description 6
- 230000015654 memory Effects 0.000 description 5
- 239000002689 soil Substances 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 4
- 239000004576 sand Substances 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 239000000446 fuel Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 239000000725 suspension Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000032258 transport Effects 0.000 description 1
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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Definitions
- the present invention relates to a mine management system that manages the productivity of mines.
- Patent Literature 1 discloses a system that calculates various management indices based on the operating status of mining machines. The system of Patent Literature 1 calculates an index related to the productivity of the mining machine, such as the amount of fuel consumed or the amount of cargo carried per unit time, in a specific section on the route of the mine.
- Patent Literature 2 discloses a system for allocating dump trucks based on time information and position information on a specific route. The system of Patent Literature 2 outputs a dump truck assignment command based on the waiting time and position information occurring on a specific route.
- Patent Document 1 detects an increase in fuel consumption per unit time and a decrease in the amount of cargo transported for a specific route, but it does not fully understand the effects of route length and slopes on fuel consumption. Not considered.
- the system of Patent Document 2 allocates dump trucks in order to improve productivity based on the waiting time and positional information that occurred on the route, but the route is limited, and it is possible to use an unknown route. Responses and other productivity unplanned (lower than planned or expected productivity) factors (e.g. road conditions, excavator or dump truck operator operations, etc.) not sufficiently considered.
- the systems of Patent Documents 1 and 2 are difficult to apply to mines with multiple routes or unknown routes. Furthermore, in the systems of Patent Documents 1 and 2, it is difficult to accurately detect when productivity is out of plan due to multiple factors. It is difficult to present information appropriately to each party.
- a mine management system of the present invention is a mine management system that manages the productivity of a mine, and is a server device that accumulates and processes operation data of the mining machines collected from the mining machines. and a determination device that performs determination processing for determining whether or not an operation status of the mining machine that causes the productivity to exceed the plan has occurred, based on the operation data.
- an extraction unit for extracting cycle data, which is the operation data for each work cycle of the mining machine, from the operation data obtained; and machine learning for causing the determination device to learn the relationship between the plurality of indicators that specify the cycle data that makes the productivity within the plan, using the plurality of calculated indicators.
- a learning unit for performing the determination, wherein the determination device performs the determination process based on the relationship between the plurality of indices learned by the learning unit.
- FIG. 1 is a diagram schematically showing the configuration of a mine management system according to Embodiment 1; FIG. The figure explaining the work cycle of a dump truck, and an unplanned factor index.
- FIG. 2 is a block diagram showing the machine learning function of the processing device shown in FIG. 1;
- FIG. 4 is a diagram showing an example of a cluster classification result by the learning unit shown in FIG. 3;
- FIG. 2 is a block diagram showing a visualization function of the processing device shown in FIG. 1; The figure which shows the result of having totaled the score for every dump truck for the predetermined period.
- FIG. 11 is a diagram showing the result of summing the scores for each date in the same period as in FIG. 10; The figure which shows the result of having counted the appearance frequency of the occurrence factor of the unplanned operation status.
- FIG. 13 is a diagram showing the result of tallying the number of appearances of the occurrence factors shown in FIG. 12 for each date; A chart of operational data with unplanned stop times. Chart of operational data with unplanned loading wait times. A chart of operation data when the waiting time for earth discharge is outside the plan. Chart of operational data with unplanned loading times.
- FIG. 11 is a diagram showing another display example of operation data in which the waiting time for discharging earth is out of the plan; The figure which shows the result of having aggregated the frequency of occurrence of the unplanned operation status for every dump truck.
- FIG. 22 is a diagram showing the result of summing up the frequency of occurrence of the unplanned operation status shown in FIG. 21 for each date;
- FIG. 22 is a diagram showing the result of totaling the frequency of occurrence of the unplanned operation status shown in FIG. 21 for each route;
- FIG. 9 is a diagram for explaining a work cycle of a hydraulic excavator and an unplanned factor index applied in the mine management system of the second embodiment;
- FIG. 1 is a diagram schematically showing the configuration of a mine management system 1 according to Embodiment 1. As shown in FIG.
- the mine management system 1 is a system that collectively manages the overall productivity of the mine 100 (for example, the amount of cargo transported per unit time).
- the mine management system 1 includes a plurality of mining machines 101 to 103, a server device 200, a determination device 250, and a terminal device 300.
- the mining machines 101 to 103 are working machines that perform mining work in the mine 100.
- the mining machines 101 to 103 can include, for example, a hydraulic excavator 102 that loads excavated earth and sand onto a dump truck 101, a dump truck 101 that transports the cargo, and a bulldozer 103 that levels the road surface.
- the mining machines of the mine management system 1 are not limited to these.
- the server device 200 manages the mining machines 101-103.
- the server device 200 accumulates and processes operation data of the mining machines 101-103 collected from the mining machines 101-103.
- the server device 200 includes a recording device 201 and a processing device 202 .
- the recording device 201 is configured by a database that records the operation data and position data collected from the mining machines 101-103. Operation data is collected from each of the plurality of mining machines 101 to 103 over a predetermined period and accumulated in the recording device 201 .
- the processing unit 202 is configured with a processor and memory. The processing device 202 implements the functions of the processing device 202 by executing programs stored in the memory by the processor.
- the operation data of the mining machines 101 to 103 be sequentially transmitted to the server device 200, but considering the communication environment and communication costs, it is not necessarily transmitted sequentially.
- the server device 200 of this embodiment starts processing after accumulating a certain amount of operation data.
- the amount collected to some extent can be determined by, for example, the time required for the dump truck 101 in the longest work cycle in the past or the amount of operation data transmitted in the longest work cycle in the past.
- the determination device 250 determines whether or not an operating condition of the mining machines 101 to 103 that causes the productivity of the mine 100 to be unplanned has occurred, based on the operation data accumulated in the recording device 201 of the server device 200. judgment processing is performed.
- the unplanned productivity indicates a state in which the productivity is lower than the previously planned productivity.
- the productivity within the plan indicates a state in which the productivity planned in advance is obtained.
- the determination device 250 transmits the determination result to the processing device 202 of the server device 200 .
- the determination device 250 is configured with a processor and memory. The determination device 250 realizes the functions of the determination device 250 by executing the program stored in the memory by the processor.
- the determination device 250 may be configured as part of the processing device 202 of the server device 200, may be configured as part of the control devices of the mining machines 101 to 103, or may be configured as part of the terminal device 300. may be If the determination device 250 is configured as a part of the control device of the mining machines 101-103, it can notify the operators of the mining machines 101-103 of the determination results without communication delay. Further, in this case, the determination device 250 can transmit the determination result to the processing device 202 in real time and display the determination result on the terminal device 300 without delay.
- the terminal device 300 displays information such as the processing result of the server device 200 and the determination result of the determination device 250 on the display 301 .
- the terminal device 300 is configured by a smartphone, tablet PC, notebook PC, or the like that communicates with the server device 200 .
- the terminal device 300 can display information to be displayed on the display 301 in a dashboard format.
- the terminal device 300 may display the information to be displayed on the display 301 in a report format or an e-mail format.
- the terminal device 300 is used by the user of the mine management system 1.
- Users of the mine management system 1 include, for example, an operation planner 501 who creates an operation plan for the mining machines 101 to 103 according to the mining/maintenance plan for the mine 100, an operator for the mining machines 101 to 103, and an operator instructor 502. , road surface maintenance personnel 503 who maintain and inspect the road surface such as the route of the mine 100, equipment maintenance personnel 504 who maintain and inspect the mining machines 101 to 103 or various equipment, and a mining manager 505 who creates mining and maintenance plans for the mine 100. etc. are included.
- the terminal device 300 may be possessed by each of these users.
- the user of the terminal device 300 Based on the information displayed on the terminal device 300, the user of the terminal device 300 appropriately grasps that the productivity of the mine 100 is out of the plan, and appropriately takes measures to improve the productivity within the plan. By doing so, the productivity of the mine 100 can be improved.
- the operation planner 501 of the mine 100 can use the information displayed on the terminal device 300 to modify the operation plan of the mining machines 101-103.
- the operator instructor 502 can use the information displayed on the terminal device 300 to find an operator whose operation should be improved and provide instruction on the operation.
- the road maintenance staff 503 can use the information displayed on the terminal device 300 to quickly identify and repair the road surface that caused the unplanned productivity.
- the equipment maintenance staff 504 can use the information displayed on the terminal device 300 to identify at an early stage the failure of the equipment that has caused productivity to go unplanned, and to order repairs and replacement parts in advance.
- the mining manager 505 receives information displayed on the terminal device 300, weather information (including history, current and forecast information) and mineral price information (including history, current and forecast information) obtained via the Internet 400. ) to review mining and maintenance plans.
- the person in charge of mining 505 can correct the mining/maintenance plan, and can issue improvement instructions to the operation planner 501, the leader 502, the road surface maintenance staff 503, or the equipment maintenance staff 504.
- the mine management system 1 that detects that the productivity of the mine 100 has become unplanned from the operation data of the dump truck 101, which is one of the mining machines 101 to 103, will be described as an example.
- FIG. 2 is a diagram explaining the work cycle of the dump truck 101 and the unplanned factor index.
- the mine 100 connects a loading area where the earth and sand excavated by the hydraulic excavator 102 is loaded onto the dump truck 101 as cargo, an earth discharging area where the dump truck 101 discharges the earth and sand from the cargo, and the loading area and the earth discharging area. have multiple routes.
- the dump truck 101 discharges soil in the dumping area, moves from the dumping area to the loading area through a path, and after loading in the loading area, moves to the dumping area through the path. Perform a series of actions.
- the payload of the dump truck 101 and the waiting time of the dump truck 101 in the dumping area are the payload of the dump truck 101 and the waiting time of the dump truck 101 in the dumping area.
- queuing time queuing dump
- queuing time queuing load
- waiting time the waiting time of the dump truck 101 on the route.
- the loading time of the hydraulic excavator 102 onto the dump truck 101 the spotting time (change over time; COT), which is the time required for the dump truck 101 to transition to a state ready for loading in the loading area, and , the average speed of the dump truck 101 .
- COT change over time
- these items are used as indexes representing the factors that cause the operational status of the dump truck 101 to cause unplanned productivity (hereinafter also referred to as "unplanned factor indexes").
- the unplanned factor index of the dump truck 101 includes an ID for identifying each index and information on the entity that affects the fluctuation of each index (that is, the cause of the fluctuation of each index). pre-bound.
- the determination device 250 evaluates the operation data of the dump truck 101 using the unplanned factor index, and identifies factors that cause the operation status of the dump truck 101 to cause unplanned productivity.
- the processing device 202 can assign the person concerned of the subject linked to the unplanned factor index representing the occurrence factor identified by the determination device 250 to the person in charge of measures to improve productivity within the plan. .
- the processing device 202 transmits a message such as an improvement instruction to the person in charge of the countermeasures to the terminal device 300 of the person in charge of the countermeasures.
- the terminal device 300 can display the message on the display 301 and notify the person in charge.
- the mine management system 1 may adopt at least two of the indicators shown in the table of FIG. In this embodiment, it is assumed that the mine management system 1 employs all indicators shown in the table of FIG.
- FIG. 3 is a block diagram showing the machine learning function of the processing device 202 shown in FIG.
- the processing device 202 of the server device 200 constructs a model that implements a part of the functions of the determination device 250 by machine learning.
- the processing device 202 has an extraction unit 211 , an index calculation unit 212 , a preprocessing unit 213 and a learning unit 214 .
- the extraction unit 211 extracts cycle data, which is operation data for each work cycle of the dump truck 101, from the operation data accumulated in the recording device 201 (hereinafter also referred to as "accumulated data"). Specifically, the extraction unit 211 identifies the work cycle based on the transition of the load amount of the dump truck 101 and extracts cycle data.
- the cycle data includes operation data of the dump truck 101 that has traveled multiple routes during one work cycle.
- the extraction unit 211 assigns a cycle ID, which is identification information, to the extracted cycle data.
- the extraction unit 211 associates the cycle data with the vehicle ID, which is the identification information of the dump truck 101 , and the cycle start time and end time, and registers them in the recording device 201 . Note that the extraction unit 211 does not need to extract cycle data from all the operation data accumulated in the recording device 201, and can extract cycle data from operation data collected or recorded during a preset extraction period. can.
- the index calculation unit 212 calculates an unplanned factor index in the extracted cycle data. Specifically, the index calculator 212 can calculate the load based on the suspension pressure of the dump truck 101 . The index calculation unit 212 can detect whether the dump truck 101 is located in the loading area, the dumping area, or on the route from the position data acquired by the GPS sensor of the dump truck 101 . The index calculation unit 212 can calculate the waiting time based on the fact that the vehicle speed or the engine speed of the dump truck 101 has become smaller than a predetermined value. The index calculator 212 can calculate the discharge waiting time, the loading waiting time, and the stopping time based on the waiting time and the position data.
- the index calculation unit 212 can calculate the loading time by calculating the time from the start of the increase in the load to the end of the increase in the load.
- the index calculator 212 can calculate the spotting time by calculating the time from when the dump truck 101 enters the loading area to when loading starts.
- the index calculation unit 212 can calculate the average vehicle speed from the travel time and travel distance excluding the state where the dump truck 101 is stopped.
- the index calculation unit 212 calculates an index representing a characteristic operation or state in the work area or work process of the dump truck 101, which is likely to affect the productivity of the mine 100. Calculated as an unplanned factor index for the truck 101 .
- the mine management system 1 can accurately determine which work area or which operation or state during the work process is causing the operation status of the dump truck 101 that causes the productivity to be unplanned. can be detected. Since the mine management system 1 can appropriately take measures to improve productivity within the plan, the productivity of the mine 100 can be improved.
- the preprocessing unit 213 uses the cycle data extracted by the extraction unit 211 based on the conditions of the work cycle to be excluded from machine learning or the conditions of the unplanned factor index to be excluded from machine learning (learning conditions) as learning data. Exclude irrelevant cycle data. Conditions for work cycles to be excluded from machine learning include, for example, work cycles with extremely short travel distances on the route, and work cycles where the previous dumping position and the current dumping position are significantly different. mentioned. As a result, the learning unit 214 can perform machine learning by excluding cycle data of work cycles that do not significantly affect productivity, such as infrequent route travel and earth and sand transportation for road surface leveling.
- the preprocessing unit 213 sets upper and lower limit values of the unplanned factor index as conditions for the unplanned factor index to be excluded from machine learning. Out-of-range unplanned factor indicators can be filtered out.
- the learning unit 214 can perform machine learning only with unplanned factor indices within the range of upper and lower limits that specify cycle data whose productivity is within the plan. Therefore, the mine management system 1 can improve the determination accuracy of the determination device 250 .
- the learning unit 214 performs machine learning that causes the determination device 250 to learn the relationship between a plurality of unplanned factor indices that identify cycle data that brings the productivity within the plan.
- the learning unit 214 of this embodiment performs the machine learning by clustering a plurality of cycle data whose productivity is within the plan.
- the learning unit 214 of the present embodiment can build a classification model in which the relationship between a plurality of unplanned factor indices that identify cycle data whose productivity is within the plan is learned.
- the learning unit 214 of this embodiment uses k-means, which is one of the clustering methods, but other clustering methods may be used.
- FIG. 4 is a diagram showing an example of cluster classification results by the learning unit 214 shown in FIG.
- the vertical axis in FIG. 4 indicates the number of cycle data
- the horizontal axis in FIG. 4 indicates cluster IDs, which are cluster identification information.
- k-means the relationship of a plurality of unplanned factor indices that specify cycle data whose productivity is within the plan is learned as each cluster center as shown in FIG.
- the distance eg, Euclidean distance or Mahalanobis distance
- the score calculated according to the distance between the target cycle data and the cluster center of the cluster into which the target cycle data is classified determines whether the target cycle data is a cycle in which the productivity is within the plan. Evaluate how much it deviates from the data. Furthermore, the determination device 250 identifies the unplanned factor index that has the largest contribution to the score among the plurality of unplanned factor indices as the cause of the operating situation that causes unplanned productivity. As a result, the processing device 202 can allocate the person concerned who is the subject linked to the unplanned factor index representing the specified cause of occurrence to the person in charge of measures to improve productivity within the plan. The processing device 202 can transmit a message such as an improvement instruction to the person in charge of countermeasures to the terminal device 300 and display it on the display 301 . The mine management system 1 can improve the productivity of the mine 100. FIG.
- the mine management system 1 does not treat the unplanned factor index individually, but machine-learns the relationship between multiple unplanned factor indexes, so that multiple factors are involved and the productivity becomes unplanned. can be detected accurately. Moreover, the mine management system 1 quantitatively evaluates the cycle data using a unified evaluation value called a score, thereby determining whether or not an operating situation that causes unplanned productivity occurs. Accurately detect unplanned productivity in various mines with routes or unknown routes.
- the learning unit 214 learns the relationship between the plurality of unplanned factor indicators that identify the cycle data whose productivity is within the plan by clustering the plurality of cycle data whose productivity is within the plan.
- Classification models can be built. Using the classification model, the determination device 250 calculates a score represented according to the distance from the cluster center, and evaluates how much the productivity deviates from the cycle data within the plan. can.
- the learning unit 214 constructs a classification model in which relationships of unplanned factor indexes in the cycle data of the dump truck 101 traveling on multiple routes are learned, so that the mine management system 1 can improve productivity in various mines. Unplanned events can be accurately detected.
- FIG. 6 is a flowchart of processing performed by the processing device 202 shown in FIG. 3 during machine learning.
- step S601 the processing device 202 extracts cycle data from the accumulated data accumulated in the recording device 201.
- step S602 the processing device 202 calculates the unplanned factor index of the extracted cycle data.
- step S603 the processing device 202 determines whether unextracted cycle data remains in the accumulated data. If unextracted cycle data remains, the processing device 202 proceeds to step S601. If there is no unextracted cycle data remaining, the processing device 202 proceeds to step S604.
- step S604 the processing device 202 performs preprocessing to exclude cycle data unsuitable as learning data from the extracted cycle data.
- step S605 the processing device 202 clusters a plurality of preprocessed cycle data, and causes the determination device 250 to learn the relationship between a plurality of unplanned factor indices that identify cycle data whose productivity is within the plan. . That is, the processing device 202 constructs a classification model of cycle data in which the relationship between the plurality of unplanned factor indices as described above is learned.
- step S606 the processing device 202 calculates cluster centers and scores, and determines whether cycle data that is not suitable as learning data is learned.
- the processing device 202 makes the determination in step S606 by determining whether the score calculated for each cluster is smaller than a preset value. Alternatively, the processing device 202 may display a graph showing the relationship of cluster centers as shown in FIG.
- the processing device 202 learns cycle data that is not suitable as learning data as a determination in step S606 (NO)
- the process proceeds to step S604.
- the processing device 202 has not learned cycle data that is not suitable as learning data as a determination in step S606, in other words, if it has learned cycle data that is suitable as learning data (YES), the processing shown in FIG. This processing shown is terminated.
- FIG. 7 is a block diagram showing functions of the determination device 250 shown in FIG.
- the determination device 250 extracts from the accumulated data accumulated in the recording device 201 based on the previously learned relationship between the plurality of unplanned factor indexes that identify the cycle data whose productivity is within the plan. Evaluate the extent to which the calculated cycle data deviates from the cycle data in which the productivity is within the plan. As a result, the determination device 250 performs a determination process of determining whether or not an operation status of the dump truck 101 that causes unplanned productivity has occurred.
- the determination device 250 has an extraction unit 251 , an index calculation unit 252 , a score calculation unit 253 , a determination unit 254 , a factor identification unit 255 and a registration unit 256 .
- the extraction unit 251 extracts cycle data from the accumulated data accumulated in the recording device 201 in the same manner as the extraction unit 211 of the processing device 202 .
- the index calculation unit 252 calculates an unplanned factor index in the cycle data extracted by the extraction unit 251 in the same manner as the index calculation unit 212 of the processing device 202 .
- the score calculation unit 253 uses the classification model constructed by the learning unit 214 of the processing device 202 to calculate the distance between the cycle data extracted by the extraction unit 251 and the center of each cluster of the classification model. The score calculation unit 253 calculates the value with the smallest distance as the score. The greater the score of the extracted cycle data, the greater the deviation of the extracted cycle data from the cycle data whose productivity is within the plan.
- the determination unit 254 determines whether the score calculated by the score calculation unit 253 is greater than a predetermined threshold. If the score calculated by the score calculation unit 253 is greater than a predetermined threshold value, the determination unit 254 determines that the operation status of the dump truck 101 that causes the productivity to fall outside the plan has occurred. If the score calculated by the score calculation unit 253 is equal to or less than a predetermined threshold value, the determination unit 254 determines that the dump truck 101 is not operating in such a manner that the productivity is not planned. If the determination unit 254 determines that the operation status of the dump truck 101 that causes the productivity to fall outside the plan has occurred, it generates a flag to that effect.
- the factor identifying unit 255 identifies factors that cause the operation status of the dump truck 101 to cause the productivity to go beyond the plan.
- the factor identifying unit 255 calculates the degree of contribution of each of the plurality of unplanned factor indices to the score, and identifies the unplanned factor index with the highest degree of contribution as the cause of the unplanned operating status. That is, the factor identifying unit 255 can identify the main cause of the unplanned operating status by identifying the unplanned factor index that has the greatest impact when the score is calculated.
- the registration unit 256 registers information such as the cycle ID of the cycle data, the cycle start time and end time, the unplanned factor index, the score, the flag, and the occurrence factor in the recording device 201 in association with each other.
- the registration unit 256 further links the vehicle ID of the dump truck 101 and the route ID, which is the identification information of the route along which the dump truck 101 travels, to these pieces of information and registers them in the recording device 201 .
- the route along which the dump truck 101 travels can be detected from position data acquired by the GPS sensor of the dump truck 101 or by receiving an operation command for the dump truck 101 .
- FIG. 8 is a flowchart of determination processing performed by the determination device 250 shown in FIG.
- step S801 the determination device 250 extracts cycle data from accumulated data accumulated in the recording device 201.
- step S802 the determination device 250 associates the cycle ID of the extracted cycle data with the cycle start time and cycle end time and registers them in the recording device 201. At this time, the determination device 250 preferably also registers the vehicle ID of the dump truck 101 and the route ID of the route along which the dump truck 101 travels in association with these pieces of information.
- step S803 the determination device 250 calculates the unplanned factor index of the extracted cycle data.
- step S804 the determination device 250 associates the calculated unplanned factor index with the cycle ID and registers it in the recording device 201.
- step S805 the determination device 250 uses the classification model to calculate the score of the extracted cycle data.
- step S806 the determination device 250 associates the calculated score with the cycle ID and registers it in the recording device 201.
- step S807 the determination device 250 determines whether the calculated score is greater than the threshold. If the calculated score is equal to or less than the threshold, the determination device 250 ends the processing shown in FIG. If the calculated score is greater than the threshold, the determination device 250 generates a flag indicating that an unplanned operating status has occurred, and proceeds to step S808.
- step S808 the determination device 250 calculates the degree of contribution of each of the plurality of unplanned factor indices to the calculated score.
- the determination device 250 identifies the unplanned factor index with the highest degree of contribution as the cause of the unplanned operating status.
- step S809 the determination device 250 registers in the recording device 201 a flag indicating that an unplanned operation status has occurred and the cause of the unplanned operation status in association with the cycle ID. After that, the determination device 250 ends the process shown in FIG.
- FIG. 9 is a block diagram showing the visualization function of the processing device 202 shown in FIG.
- the processing device 202 collects and visualizes information on the operational status of the dump truck 101 that causes unplanned productivity.
- the processing device 202 has an aggregation unit 221 , an acquisition unit 222 and a visualization unit 223 .
- the aggregation unit 221 calculates the frequency of occurrence of unplanned operating conditions, the frequency of appearance of causes of occurrence, or scores for each period, each dump truck 101, or , based on the aggregation conditions such as each route. For example, the aggregation unit 221 aggregates the number of flags or occurrence factors linked to the cycle ID recorded in the recording device 201 over a predetermined period, Appearance frequencies can be aggregated. The tallying unit 221 can tally the scores associated with the cycle IDs recorded in the recording device 201 for each vehicle ID.
- the acquisition unit 222 obtains the operation data of the dump truck 101 in which the unplanned operation status has occurred, from the accumulated data accumulated in the recording device 201 as analysis data for detailed analysis of the cause of the unplanned operation status. to get For example, the acquisition unit 222 acquires operation data (one or a plurality of cycle data) of the dump truck 101 in which the unplanned operation status has occurred, based on the flag linked to the cycle ID recorded in the recording device 201. can do.
- the visualization unit 223 visualizes the aggregation result of the aggregation unit 221 or the analysis data acquired by the acquisition unit 222 .
- the visualization unit 223 creates graphs showing the aggregated results of the aggregation unit 221 and transmits the graphs to the terminal device 300, as shown in FIGS. 10 to 13 or FIGS.
- the visualization unit 223 creates a chart showing the transition of the operation data acquired as the analysis data, and transmits the chart to the terminal device 300, as shown in FIGS. 14 to 19 described later.
- the visualization unit 223 creates a map of the work area specified from the operation data acquired as analysis data, and transmits the map to the terminal device 300, as shown in FIG. 20 to be described later.
- the terminal device 300 can display graphs and the like created by the visualization unit 223 on the display 301 .
- the processing device 202 not only visualizes the aggregation result of the aggregation unit 221 or the analysis data acquired by the acquisition unit 222, but also analyzes the aggregation result or the analysis data and transmits necessary information to the terminal. It can be sent to the device 300 .
- the processing device 202 sends a message such as an improvement instruction corresponding to the occurrence factor to the terminal device 300 of each party associated with the unplanned factor index representing the cause of the unplanned operating status. can be sent.
- the terminal device 300 can display the message on the display 301 and notify each person concerned.
- the visualization unit 223 may be provided in the terminal device 300 instead of being provided in the processing device 202 . That is, the processing device 202 transmits the aggregation result of the aggregation unit 221 or the analysis data acquired by the acquisition unit 222 to the terminal device 300, and the terminal device 300 visualizes the aggregation result or the analysis data.
- FIG. 10 is a diagram showing the result of totaling scores for each dump truck 101 for a predetermined period.
- FIG. 11 is a diagram showing the result of totaling the scores for the same period as in FIG. 10 for each date.
- the user of the terminal device 300 displaying FIG. 10 can determine whether or not the operating status of the unplanned productivity is dependent on the individual differences of the dump trucks 101 or not. In the example of FIG. 10, there is no difference for each dump truck 101 in the median value and interquartile range of the boxplot. In the example of FIG. 10 , it can be determined that the occurrence of unplanned operating conditions does not depend on the individual differences of the dump trucks 101 . If the occurrence of an unplanned operating condition depends on the individual difference of the dump truck 101 , the terminal device 300 can display a message to that effect on the display 301 and notify the equipment maintenance personnel 504 . Thereby, the mine management system 1 can improve productivity.
- the score fluctuates depending on the day, and the occurrence of unplanned operating conditions depends on the date and related items (weather, road surface, operation instructions, etc.).
- the terminal device 300 can display on the display 301 the cause of occurrence, which will be described later with reference to FIG.
- the road surface maintenance staff 503 or the operation planner 501 can analyze the cause in detail and take necessary measures. Thereby, the mine management system 1 can improve productivity.
- the processing device 202 can aggregate scores for each operator by associating the identification information of the operator of the dump truck 101 with the cycle ID.
- the terminal device 300 can display on the display 301 a message to the effect that the score is high to the coach 502 of the specific operator with the high score, and notify the coach 502 of it.
- a coach 502 can coach a particular operator with a high score to a lower score. Thereby, the mine management system 1 can improve productivity.
- FIG. 12 is a diagram showing the result of counting the frequency of appearance of factors that cause unplanned operating conditions.
- FIG. 13 is a diagram showing the result of tallying the number of appearances of the occurrence factors shown in FIG. 12 for each date.
- FIG. 12 shows the causes of unplanned operating conditions, arranged in descending order of appearance frequency.
- the user of the terminal device 300 displaying FIG. 12 can easily grasp the cause of the unplanned operation status and the frequency of appearance thereof.
- the occurrence factor with a high appearance frequency is the stopping time of the dump truck 101 on the route.
- the terminal device 300 can display a message on the display 301 to the effect that the stop time has become unplanned, and notify the mining manager 505 of this.
- the mining manager 505 can issue improvement instructions to the operation planner 501 .
- each The concerned party's terminal device 300 can display the message on the display 301 and notify each concerned party.
- the form of notification is not limited to a message, and may be displayed as an area chart, for example.
- the daily work cycles of the mining machines 101 to 103 are shown in chronological order, and are classified according to preset work areas using different colors.
- an area chart can be displayed in association with an unplanned factor index representing the cause of the occurrence.
- the recording device 201 records the location information (path ID) and the time information (cycle start time and end time) where the unplanned operating status occurred. Therefore, by referring to the operation data of the dump truck 101 at the time when the unplanned operation state occurred, the user can analyze the cause of the unplanned operation state in more detail.
- 14 to 19 show charts of operation data of the dump truck 101 in which an unplanned operation situation has occurred.
- reference numerals 1401 to 1403 denote vehicle IDs, cycle IDs and route IDs, respectively.
- a reference numeral 1404 denotes an unplanned factor index representing a cause of an unplanned operation status.
- a reference numeral 1405 denotes a chart showing transition of the vehicle speed of the dump truck 101 .
- Reference numeral 1406 denotes a chart showing changes in the engine speed of the dump truck 101 .
- Reference numeral 1407 denotes a chart showing changes in the load amount of the dump truck 101 .
- Fig. 14 is a chart of operation data in which the stop time is outside the plan.
- the dump truck 101 travels along the route for a while after dumping soil (around 19:07), and then stops for about 10 minutes.
- the user of the terminal device 300 displaying FIG. 14 can analyze the operation command at this time, the position of the bulldozer 103 on the route, the presence or absence of an alert for the dump truck 101, etc. from the accumulated data of the recording device 201.
- Fig. 15 is a chart of operation data in which the waiting time for loading is unplanned.
- loading waits occur from 15:56 to 16:05.
- the user of the terminal device 300 displaying FIG. 15 can analyze the operation data of the dump truck 101 and the hydraulic excavator 102 that were being loaded at this location and time. In this case, if the spotting time of the dump truck 101 that is being loaded is long, the operator of the dump truck 101 may be instructed. If the loading time of the hydraulic excavator 102 during loading is long, the operator of the hydraulic excavator 102 may be instructed.
- the dump trucks 101 operating in the dumping area are notified of the adjustment of the operation interval, or the operation plan is reviewed to optimize the allocation of the area. You may notify the route. Thereby, the mine management system 1 can improve productivity.
- Fig. 16 is a chart of operation data in which the waiting time for discharging earth is outside the plan.
- FIG. 16 As indicated by the dashed-dotted line, it can be seen that there is a wait for earth removal from time 00:21 to time 00:24.
- the user of the terminal device 300 displaying FIG. 16 can analyze the presence or absence of another dump truck 101 in the dumping area and the layout of the dumping area. If necessary, the layout of the dumping area may be changed, or the operation plan may be reviewed. Thereby, the mine management system 1 can improve productivity.
- Fig. 17 is a chart of operation data when the loading time is outside the plan.
- FIG. 17 As indicated by the dashed line, it can be seen that loading from around 9:40 takes a long time.
- the user of the terminal device 300 displaying FIG. 17 can analyze the operation data of the hydraulic excavator 102 at this time. If there is an alert for the hydraulic excavator 102, the hydraulic excavator 102 should be repaired. If it takes a long time to move or load the hydraulic excavator 102, the operator of the hydraulic excavator 102 should be instructed.
- the display of the analysis results of "stop time”, “loading waiting time”, “earth discharging waiting time”, and "loading time” is not limited to the chart format.
- location history may be displayed on a map showing the operating environment. In this case, since the travel history at an arbitrary time can be known, it is possible to intuitively grasp at which point (position) the operation data is when an unplanned factor index occurs, so that further analysis can be performed. Thereby, the mine management system 1 can improve productivity.
- Fig. 18 is a chart of operation data with unplanned spotting time.
- Fig. 19 is a chart of operation data when the load capacity is outside the plan.
- the load amount due to loading from around 20:00 is small.
- the user of the terminal device 300 displaying FIG. 19 can identify the cause by analyzing the operation data of the hydraulic excavator 102 that has performed the loading or by interviewing the operator of the hydraulic excavator 102 . Thereby, the mine management system 1 can improve productivity.
- FIG. 20 is a diagram showing another display example of operation data in which the waiting time for discharging earth is outside the plan.
- the location and time of the dumping area where the waiting time for dumping is unplanned can be identified from the operation data of the dump truck 101 whose waiting time for dumping is unplanned.
- the dumping position A in the dumping area and the stop position B of the dump truck 101 can be calculated from the position data of the GPS sensor of the dump truck 101 .
- the terminal device 300 can display the unloading position A and the stop position B on a map or satellite photograph of the vicinity of the unloading area where the waiting time for unloading has become unplanned.
- the user of the terminal device 300 displaying FIG. 20 can analyze the positional relationship between the unloading position A and the stop position B and the situation in the unloading area. If necessary, the layout of the dumping area may be changed, or the operation plan may be reviewed. Thereby, the mine management system 1 can improve productivity.
- FIG. 21 is a diagram showing the results of tabulating the frequency of occurrence of unplanned operating conditions for each dump truck 101.
- FIG. FIG. 22 is a diagram showing the result of tabulating the frequency of occurrence of the unplanned operation status shown in FIG. 21 for each date.
- FIG. 23 is a diagram showing the result of totaling the frequency of occurrence of the unplanned operation status shown in FIG. 21 for each route.
- FIG. 21 it can be seen that there are differences in the frequency of occurrence of unplanned operating conditions depending on the dump truck 101.
- FIG. 22 it can be seen that there is a difference in the frequency of occurrence of unplanned operating conditions depending on the date.
- FIG. 23 it can be seen that there is a route (a route with an occurrence frequency of 1.0) in which unplanned operating conditions always occur. From these things, it turns out that there is a problem with a specific route.
- the user of the terminal device 300 displaying FIGS. 21 to 23 can analyze the operation data on the date when the unplanned operation status frequently occurs on a specific route, and identify the cause. Thereby, the mine management system 1 can improve productivity.
- the mine management system 1 of Embodiment 1 is a system for managing the productivity of the mine 100, and accumulates and processes the operation data of the mining machines 101 to 103 collected from the mining machines 101 to 103. It comprises a server device 200 and a determination device 250 that performs determination processing for determining whether or not an operation status of the mining machines 101 to 103 that causes unplanned productivity occurs based on the operation data.
- the server device 200 includes an extraction unit 211 that extracts cycle data, which is operation data for each work cycle of the mining machines 101 to 103, from the accumulated operation data, and an operation status extractor 211 that extracts, in the cycle data, an operation status in which productivity is out of plan.
- a plurality of unplanned factor indices for identifying cycle data in which the productivity is within the plan using an index calculation unit 212 that calculates a plurality of unplanned factor indices representing occurrence factors, and the calculated plurality of unplanned factor indices. and a learning unit 214 that performs machine learning for causing the determination device 250 to learn the relationship of The determination device 250 determines how much the cycle data extracted from the accumulated operation data deviates from the cycle data in which the productivity is within the plan, based on the relationships of a plurality of unplanned factor indices that have been learned in advance. Determination processing is performed by evaluating .
- the mine management system 1 of the first embodiment does not treat the unplanned factor index alone, but machine-learns the relationship of a plurality of unplanned factor indexes, so that the productivity is improved by the relationship of the plurality of factors. Unplanned events can be accurately detected. Moreover, the mine management system 1 of the first embodiment can detect that the productivity has become unplanned in various mines having multiple routes or unknown routes by performing machine learning on the relationship of a plurality of unplanned factor indices. can be detected accurately. Therefore, the mine management system 1 of Embodiment 1 can appropriately take measures to improve productivity within the plan, so that the productivity of the mine 100 can be improved.
- the mining machines 101 to 103 are dump trucks 101.
- the plurality of unplanned factor indicators are the loading amount of the dump truck 101, the dump truck 101 waiting time in the dumping area of the mine 100, and the dump truck 101 waiting time in the loading area of the mine 100.
- an index representing a characteristic operation or state in the work area or work process of the dump truck 101 that easily affects the productivity of the mine 100 is set. , is calculated as an unplanned factor index of the dump truck 101 .
- the operation status of the dump truck 101 that causes the productivity to be unplanned occurs due to the operation or state in which work area or work process. can be accurately detected. Therefore, the mine management system 1 of Embodiment 1 can more appropriately take measures to improve productivity within the plan, so that the productivity of the mine 100 can be further improved.
- the learning unit 214 performs machine learning by clustering a plurality of cycle data whose productivity is within the plan.
- the determination device 250 calculates a score represented according to the distance between the cycle data extracted from the accumulated operation data and the center of the cluster. determined to have occurred.
- the mine management system 1 of Embodiment 1 can easily construct a classification model in which the relationship between a plurality of unplanned factor indicators that identify cycle data that brings productivity within the plan is learned. Moreover, the mine management system 1 of Embodiment 1 quantitatively evaluates cycle data using a unified evaluation value called a score, thereby determining whether or not an operating situation that causes unplanned productivity has occurred. do. Therefore, the mine management system 1 of Embodiment 1 can more accurately and easily detect unplanned productivity in various mines having multiple routes or unknown routes. Therefore, the mine management system 1 of Embodiment 1 can more appropriately take measures to improve productivity within the plan, so that the productivity of the mine 100 can be further improved.
- the determination device 250 when determining that an operating situation in which the productivity is unplanned has occurred, calculates the degree of contribution of each of the plurality of unplanned factor indicators to the score. , the unplanned factor index with the largest contribution is identified as the occurrence factor.
- the mine management system 1 of Embodiment 1 can uniquely identify the main cause of the operational status that causes unplanned productivity using a unified evaluation value called score. Therefore, the mine management system 1 of Embodiment 1 can accurately detect the main factor of unplanned productivity in various mines having multiple routes or unknown routes. Therefore, the mine management system 1 of Embodiment 1 can more appropriately take measures to improve productivity within the plan, so that the productivity of the mine 100 can be further improved.
- the mine management system 1 of Embodiment 1 further includes a terminal device 300 having a display 301 .
- the server device 200 aggregates the frequency of occurrence of operating conditions in which productivity is unplanned, the frequency of occurrence of occurrence factors, or scores for each period or each of the mining machines 101 to 103, and transmits the aggregation results to the terminal device 300. do.
- the terminal device 300 displays the tallied result on the display 301 .
- the unplanned factor indicator with the highest occurrence frequency (number of times) among the multiple unplanned factor indicators is notified to identify the trend of operation, and the unplanned factor indicator between operators
- the improvement instruction By calculating the average number of factor indices and notifying the unplanned factor index that exceeds the cumulative average number of times, it may be associated with the improvement instruction. Also, if there is an operator's operation history, points to be improved, points improved, or a combination thereof may be displayed.
- the mine management system 1 of the first embodiment determines how the frequency of occurrence of operating conditions in which the productivity is unplanned, the frequency of occurrence of occurrence factors, or the score for each period or each of the mining machines 101 to 103. It is possible to notify the user of whether there is a change in a form that is intuitively easy to grasp. Therefore, according to the mine management system 1 of Embodiment 1, it becomes easier for the user to analyze the cause of the operating situation causing the unplanned productivity. Furthermore, the number of mining machines 101 to 103 to be displayed is not limited to one, and a plurality of machines may be displayed, and not only the tendency specific to any one machine but also the overall tendency may be specified. Therefore, the mine management system 1 of Embodiment 1 can more appropriately take measures to improve productivity within the plan, so that the productivity of the mine 100 can be further improved.
- the server device 200 acquires the operation data of the mining machines 101 to 103 in which an operation state in which the productivity is unplanned occurs, and stores the acquired operation data or its transition. It transmits to the terminal device 300 .
- the terminal device 300 displays the transition of the operating data on the display 301 .
- the mine management system 1 of Embodiment 1 can analyze in detail the factors that have caused the operating conditions that result in unplanned productivity based on the operating data of the mining machines 101 to 103. can. Therefore, the mine management system 1 of Embodiment 1 can more appropriately take measures to improve productivity within the plan, so that the productivity of the mine 100 can be further improved.
- the plurality of unplanned factor indexes are linked in advance with information on subjects that affect fluctuations in the unplanned factor indexes.
- the terminal device 300 displays, on the display 301 , a message for the relevant person of the subject indicated by the information linked to the unplanned factor index representing the occurrence factor identified by the determination device 250 .
- the message may be displayed in the form of a simulated display of a model operation, or in the form of a graph/chart/score compared to the current occurrence situation.
- the mine management system 1 of the first embodiment assigns the relevant parties of the subject linked to the unplanned factor index representing the occurrence factor identified by the determination device 250 to be in charge of measures to improve productivity within the plan.
- the mine management system 1 of Embodiment 1 can display a message such as an improvement instruction to the person in charge of countermeasures on the display 301 of the terminal device 300 of the person in charge of countermeasures, and notify the person in charge of countermeasures.
- a message such as an improvement instruction may be a direct notification to the operator.
- the message is not limited to text, but includes audio or a visible identification such as a different colored flag.
- the notification interval can be arbitrarily set at regular intervals, such as every half day or every day, depending on the cumulative occurrence frequency and degree of urgency/importance. For example, if you set an hourly, three hourly, etc. based on the above time series, if you set the aggregation time in the morning and identify the unplanned factor indicators that occur frequently, you can see improvement in the afternoon. You can expect the effect of connecting. Therefore, in the mine management system 1 of Embodiment 1, the person in charge of countermeasures can early take measures to improve productivity within the plan, so the productivity of the mine 100 can be improved early.
- Embodiment 2 A mine management system 1 according to the second embodiment will be described with reference to FIG. In the mine management system 1 of Embodiment 2, descriptions of the same configurations and operations as in Embodiment 1 are omitted.
- the mine management system 1 that detects that the productivity of the mine 100 has become unplanned from the operation data of the hydraulic excavator 102, which is one of the mining machines 101 to 103, will be described as an example.
- FIG. 24 is a diagram for explaining the work cycle and unplanned factor index of the hydraulic excavator 102 applied in the mine management system 1 of the second embodiment.
- the hydraulic excavator 102 loads excavated soil or the like as a cargo onto the dump truck 101, prepares for excavation after loading, excavates the soil or the like, and dumps the excavated soil or the like from the excavation surface.
- a series of operations for transporting onto the vessel of the truck 101 are performed.
- the work cycle does not need to be defined with loading onto the dump truck 101 as the starting point, and may be defined with other operations such as excavation as the starting point.
- items that affect the productivity of the mine 100 include the excavation amount (payload) of the hydraulic excavator 102 and the amount of time the hydraulic excavator takes after loading for the next excavation.
- Digging preparation time (reaching time) which is the time required for preparation, digging time of the hydraulic excavator 102, and time required for transporting the load excavated by the hydraulic excavator 102 to the dump truck 101 which is the loading machine.
- a certain carrying time a loading time that is the time required to load the load carried by the hydraulic excavator 102 onto the dump truck 101 that is the loading machine, and a waiting time of the hydraulic excavator 102.
- these items are defined as unplanned factor indexes of the excavator 102, as shown in the table of FIG.
- the excavation amount of the hydraulic excavator 102 can be calculated from each angle of the boom, arm, and bucket of the hydraulic excavator 102 and each cylinder pressure. Alternatively, as the excavation amount of the hydraulic excavator 102 , the load amount calculated from the suspension pressure of the dump truck 101 can be received from the dump truck 101 .
- Excavation preparation time, excavation time, loading time, transportation time, waiting time, and travel time are each angle and each cylinder pressure of the boom, arm, and bucket of the hydraulic excavator 102, the slewing angle of the upper slewing structure, and the traveling speed of the lower slewing structure. etc.
- the unplanned factor index of the hydraulic excavator 102 is associated in advance with an ID that identifies each index and information on the entity that affects the fluctuation of each index.
- the determination device 250 evaluates the operation data of the hydraulic excavator 102 using the unplanned factor index, and identifies the factors that cause the operating status of the hydraulic excavator 102 to cause unplanned productivity.
- the processing device 202 sends information corresponding to the occurrence factor to the terminal device 300 of each party of the subject linked to the unplanned factor index representing the occurrence factor of the unplanned operating status. You can send messages such as improvement instructions.
- the terminal device 300 can display a message on the display 301 and notify each person concerned, as in the first embodiment.
- the mine management system 1 may adopt at least two of the indicators shown in the table of FIG. 24 as the unplanned indicators for the hydraulic excavator 102 .
- the mine management system 1 of the second embodiment uses an index representing a characteristic operation or state during the work process of the hydraulic excavator 102, which is likely to affect the productivity of the mine 100. Calculated as an unplanned factor index. As a result, the mine management system 1 of the second embodiment can accurately determine which operation or state in the work process is causing the operation status of the hydraulic excavator 102 that causes unplanned productivity. can be detected. Therefore, the mine management system 1 of the second embodiment can appropriately take measures to improve the productivity within the plan even if the hydraulic excavator 102 operates in such a way that the productivity is out of the plan. , the productivity of the mine 100 can be improved.
- the present invention is not limited to the above-described embodiments, and includes various modifications.
- the above embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the configurations described.
- it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment and it is also possible to add the configuration of another embodiment to the configuration of one embodiment.
- each of the above configurations, functions, processing units, processing means, etc. may be realized by hardware, for example, by designing them in integrated circuits, in part or in whole.
- each of the above configurations, functions, etc. may be realized by software by a processor interpreting and executing a program for realizing each function.
- Information such as programs, tapes, and files that implement each function can be stored in recording devices such as memories, hard disks, SSDs (solid state drives), or recording media such as IC cards, SD cards, and DVDs.
- control lines and information lines indicate what is considered necessary for explanation, and not all control lines and information lines are necessarily indicated on the product. In practice, it may be considered that almost all configurations are interconnected.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Agronomy & Crop Science (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Husbandry (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
上記以外の課題、構成および効果は、以下の実施形態の説明により明らかにされる。
図1~図23を用いて、実施形態1の鉱山管理システム1について説明する。
図1は、実施形態1の鉱山管理システム1の構成を模式的に示す図である。
サーバ装置200は、記録装置201と、処理装置202とを備える。
処理装置202は、抽出部211と、指標算出部212と、前処理部213と、学習部214とを有する。
処理装置202は、集計部221と、取得部222と、可視化部223とを有する。
図24を用いて、実施形態2の鉱山管理システム1について説明する。実施形態2の鉱山管理システム1において、実施形態1と同様の構成及び動作については、その説明を省略する。
なお、本発明は上記の実施形態に限定されるものではなく、様々な変形例が含まれる。例えば、上記の実施形態は本発明を分かりやすく説明するために詳細に説明したものであり、必ずしも説明した全ての構成を備えるものに限定されるものではない。また、或る実施形態の構成の一部を他の実施形態の構成に置き換えることが可能であり、また、或る実施形態の構成に他の実施形態の構成を加えることも可能である。また、各実施形態の構成の一部について、他の構成の追加・削除・置換をすることが可能である。
Claims (8)
- 鉱山の生産性を管理する鉱山管理システムであって、
鉱山機械から収集された前記鉱山機械の稼働データを蓄積し、処理するサーバ装置と、 前記稼働データに基づいて、前記生産性が計画外になる前記鉱山機械の稼働状況が発生したか否かを判定する判定処理を行う判定装置と、を備え、
前記サーバ装置は、
蓄積された前記稼働データから、前記鉱山機械の作業サイクル毎の前記稼働データであるサイクルデータを抽出する抽出部と、
前記サイクルデータにおいて、前記生産性が計画外になる前記稼働状況の発生要因を表す複数の指標を算出する算出部と、
算出された前記複数の指標を用いて、前記生産性が計画内になる前記サイクルデータを特定する前記複数の指標の関係を前記判定装置に学習させる機械学習を行う学習部と、を有し、
前記判定装置は、前記学習部によって学習された前記複数の指標の関係に基づいて前記判定処理を行う
ことを特徴とする鉱山管理システム。 - 前記鉱山機械は、ダンプトラックであり、
前記複数の指標は、前記ダンプトラックの積載量、前記鉱山の排土エリアでの前記ダンプトラックの待ち時間である排土待ち時間、前記鉱山の積み込みエリアでの前記ダンプトラックの待ち時間である積み込み待ち時間、前記積み込みエリアと前記排土エリアとを繋ぐ経路上での前記ダンプトラックの停車時間、前記ダンプトラックへの積荷の積み込み時間、前記積み込みエリアにおいて前記ダンプトラックが積み込み可能な状態に移行するのに要する時間であるスポッティング時間、及び、前記ダンプトラックの平均車速のうちの少なくとも2つを含む
ことを特徴とする請求項1に記載の鉱山管理システム。 - 前記鉱山機械は、油圧ショベルであり、
前記複数の指標は、前記油圧ショベルの掘削量、積み込み後の前記油圧ショベルが次の掘削を行うための準備に要する時間である掘削準備時間、前記油圧ショベルの掘削時間、前記油圧ショベルが掘削した積荷を被積込機械まで運搬するのに要する時間である運搬時間、前記油圧ショベルが運搬した積荷を被積込機械に積み込むのに要する時間である積み込み時間、前記油圧ショベルの待ち時間、及び、前記油圧ショベルの移動時間のうちの少なくとも2つを含む
ことを特徴とする請求項1に記載の鉱山管理システム。 - 前記学習部は、前記生産性が計画内になる複数の前記サイクルデータをクラスタリングすることによって前記機械学習を行い、
前記判定装置は、蓄積された前記稼働データから抽出された前記サイクルデータとクラスタ中心との距離に応じて表されるスコアを算出し、前記スコアが閾値より大きい場合、前記生産性が計画外になる前記稼働状況が発生したと判定する
ことを特徴とする請求項1に記載の鉱山管理システム。 - 前記判定装置は、前記生産性が計画外になる前記稼働状況が発生したと判定した場合、前記スコアに対する前記複数の指標のそれぞれの寄与度を算出し、前記寄与度が最も大きい前記指標を、前記発生要因として特定する
ことを特徴とする請求項4に記載の鉱山管理システム。 - ディスプレイを備える端末装置を更に備え、
前記サーバ装置は、前記生産性が計画外になる前記稼働状況の発生頻度、前記発生要因の出現頻度、又は、前記スコアを、期間毎又は前記鉱山機械毎に集計し、集計結果を前記端末装置に送信し、
前記端末装置は、前記集計結果を前記ディスプレイに表示する
ことを特徴とする請求項5に記載の鉱山管理システム。 - ディスプレイを備える端末装置を更に備え、
前記サーバ装置は、前記生産性が計画外になる前記稼働状況が発生した前記鉱山機械の前記稼働データを取得し、取得された前記稼働データ又はその推移を前記端末装置に送信し、
前記端末装置は、前記稼働データの推移を前記ディスプレイに表示する
ことを特徴とする請求項5に記載の鉱山管理システム。 - ディスプレイを備える端末装置を更に備え、
前記複数の指標には、前記指標の変動に影響を与える主体の情報が予め紐付けられており、
前記端末装置は、前記判定装置により特定された前記発生要因を表す前記指標に紐付けられた前記情報が示す前記主体の関係者に対するメッセージを、前記ディスプレイに表示する
ことを特徴とする請求項5に記載の鉱山管理システム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202280057305.9A CN117836801A (zh) | 2021-10-29 | 2022-10-28 | 矿山管理系统 |
EP22887159.6A EP4375914A1 (en) | 2021-10-29 | 2022-10-28 | Mine management system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021178037A JP7241846B1 (ja) | 2021-10-29 | 2021-10-29 | 鉱山管理システム |
JP2021-178037 | 2021-10-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023074834A1 true WO2023074834A1 (ja) | 2023-05-04 |
Family
ID=85600345
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/040298 WO2023074834A1 (ja) | 2021-10-29 | 2022-10-28 | 鉱山管理システム |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP4375914A1 (ja) |
JP (1) | JP7241846B1 (ja) |
CN (1) | CN117836801A (ja) |
WO (1) | WO2023074834A1 (ja) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013041448A (ja) * | 2011-08-17 | 2013-02-28 | Hitachi Ltd | 異常検知・診断方法、および異常検知・診断システム |
JP2013105278A (ja) * | 2011-11-11 | 2013-05-30 | Komatsu Ltd | 鉱山機械の管理システム及び鉱山機械の管理方法 |
WO2015029229A1 (ja) | 2013-08-30 | 2015-03-05 | 株式会社小松製作所 | 鉱山機械の管理システム及び管理方法 |
JP5809710B2 (ja) | 2013-08-20 | 2015-11-11 | 株式会社小松製作所 | 管理システム及び管理方法 |
JP2017045215A (ja) * | 2015-08-26 | 2017-03-02 | 日立建機株式会社 | 診断装置 |
-
2021
- 2021-10-29 JP JP2021178037A patent/JP7241846B1/ja active Active
-
2022
- 2022-10-28 CN CN202280057305.9A patent/CN117836801A/zh active Pending
- 2022-10-28 WO PCT/JP2022/040298 patent/WO2023074834A1/ja active Application Filing
- 2022-10-28 EP EP22887159.6A patent/EP4375914A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2013041448A (ja) * | 2011-08-17 | 2013-02-28 | Hitachi Ltd | 異常検知・診断方法、および異常検知・診断システム |
JP2013105278A (ja) * | 2011-11-11 | 2013-05-30 | Komatsu Ltd | 鉱山機械の管理システム及び鉱山機械の管理方法 |
JP5809710B2 (ja) | 2013-08-20 | 2015-11-11 | 株式会社小松製作所 | 管理システム及び管理方法 |
WO2015029229A1 (ja) | 2013-08-30 | 2015-03-05 | 株式会社小松製作所 | 鉱山機械の管理システム及び管理方法 |
JP2017045215A (ja) * | 2015-08-26 | 2017-03-02 | 日立建機株式会社 | 診断装置 |
Also Published As
Publication number | Publication date |
---|---|
JP7241846B1 (ja) | 2023-03-17 |
JP2023067073A (ja) | 2023-05-16 |
CN117836801A (zh) | 2024-04-05 |
EP4375914A1 (en) | 2024-05-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104764595B (zh) | 远程诊断系统 | |
CN103080956A (zh) | 传感器系统、计算机、以及设备 | |
US9836893B2 (en) | Computing and tracking locomotive health | |
JP6906209B2 (ja) | 建設機械稼働状況管理システム及び管理方法 | |
CN111324092B (zh) | 使用遥测数据管理现场生产率 | |
US20140350993A1 (en) | Information management device and method | |
JP2015009938A (ja) | エレベーター管理装置、エレベーター管理システム及びエレベーター管理方法 | |
WO2018130993A2 (en) | Integrated project and equipment management system and method using iot devices and software applications | |
Hodkiewicz et al. | Why autonomous assets are good for reliability–the impact of ‘operator-related component’failures on heavy mobile equipment reliability | |
JP6836954B2 (ja) | 車両保守計画装置、及び車両保守計画評価方法 | |
WO2023074834A1 (ja) | 鉱山管理システム | |
TW202233464A (zh) | 駕駛評價裝置、駕駛評價程式及報告資料 | |
Felsch et al. | An innovative cyber-physical system aimed at increasing productivity in the mining industry | |
Hodkiewicz et al. | Data fitness for purpose: assessing the quality of industrial data for use in mathematical models | |
Abdi-Oskouei et al. | Role of the operator in dragline energy efficiency | |
Hsu | Data quality of fleet management systems in open pit mining: issues and impacts on key performance indicators for haul truck fleets | |
JPWO2015114792A1 (ja) | 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 | |
Szymanski et al. | An integrated monitoring system and simulation analysis model for trucks operation using SLAM II | |
US20170108875A1 (en) | Vehicle Control System | |
US11995577B2 (en) | System and method for estimating a machine's potential usage, profitability, and cost of ownership based on machine's value and mechanical state | |
WO2024203565A1 (ja) | 鉱山管理システム | |
US11288614B2 (en) | Role-based asset tagging for quantification and reporting of asset performance | |
Shahandashti et al. | Identification of information requirements using simulation for supporting construction productivity assessment | |
CN117333271A (zh) | 一种内置设备利用率分析的吊车租赁平台系统 | |
Antal et al. | Implementation of business intelligence system to analyze the data for mining mechanization-case study. |
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: 22887159 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280057305.9 Country of ref document: CN Ref document number: 2022887159 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2022887159 Country of ref document: EP Effective date: 20240222 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |