JP7457601B2 - Factor estimation device, factor estimation system and program - Google Patents

Description

The present invention relates to a factor estimation device, a factor estimation system, and a program.

Patent Document 1 relates to a factor estimating device and states, ``The process control device estimates the cause of the defect from the defect results that occur in the system to be diagnosed. , the inference processing unit performs factor estimation processing, and in the process, the item data acquisition unit acquires data of input items corresponding to the conditions included in the causal network.Based on the acquired data, the degree to which the conditions are satisfied is determined. A goodness-of-fit calculation unit calculates the goodness of fit indicating the condition, and a value representing a set of goodness-of-fitness for the conditions included in the path of factor estimation is calculated as a certainty factor for each defective factor by the certainty calculation part. Regarding the input items, the influence calculation unit calculates the degree of influence indicating the degree of influence on the confidence level when the input item data is acquired.The item data acquisition unit acquires the data of the input items with high influence. ” is written.

Japanese Patent Application Publication No. 2007-193457

In the factor estimation device of Patent Document 1, the user inputs information on factor estimation knowledge, and the degree of compatibility with the knowledge and the certainty of the factor are calculated to perform factor estimation. However, it is a heavy burden on the user to input factor estimation knowledge each time. Furthermore, since the reliability of sensor values also changes depending on the component configuration of the observation target, it is difficult to perform highly accurate factor estimation without taking this into account.

The present invention has been made in view of the above-mentioned problems, and an object of the present invention is to provide users with more useful information by specifying estimated factors and countermeasures for defects in consideration of the reliability of sensor information.

The present application includes a plurality of means for solving at least part of the above problems, examples of which are as follows. A factor estimating device according to an aspect of the present invention that solves the above problems uses defect pattern information indicating a defect pattern that has occurred in equipment or products and sensing results of predetermined observation items in the equipment to be monitored . a communication unit that acquires an observation value including sensor information indicating a state of the equipment from an external device; the failure pattern; the observation value corresponding to each failure pattern ; the failure pattern and the observation value; The observation item indicating the state of the equipment corresponding to each combination of the failure pattern, the failure estimation factor and countermeasure corresponding to each combination of the observation value and the observation item are registered . Based on the storage unit storing estimated information, the defect pattern information acquired from the external device , and the observed value, the estimated cause and countermeasure for the defect corresponding to the defective pattern are determined from the factor estimation information. a factor estimating unit that estimates the cause of the defect by identifying the value of the sensor information, and the object handled by the equipment that was used in the sequence in which sensing of the observation item from which the sensor information was acquired; or a threshold value calculation unit that calculates, as a threshold value, a value of the predetermined element that no longer maintains a correlation between a predetermined element of the component of the equipment, and the factor estimation unit uses the threshold value. Then , the reliability of the sensor information is determined.

According to the present invention, more useful information can be provided to the user by specifying the estimated cause of failure and countermeasures that take into account the reliability of sensor information.

FIG. 1 is a diagram showing an example of a schematic configuration of a factor estimation system. It is a figure showing an example of plan information. FIG. 4 is a diagram showing an example of sensor related information. FIG. 3 is a diagram showing an example of normal state accumulation information. It is a figure showing an example of factor estimation information. FIG. 2 is a diagram showing a manufacturing line as an example to which the factor estimation system is applied. It is a figure showing an example of sensor related information used for an example. It is a figure showing an example of plan information used for a case. FIG. 7 is a diagram showing an example of normal state accumulation information generated in a case. It is a flow diagram showing an example of factor estimation processing. It is a figure showing an example of factor estimation information used for a case. FIG. 7 is a diagram illustrating an example of a screen showing the contents of estimated factor countermeasure information. FIG. 12(a) is a diagram showing a case where the number of identified estimated factors and countermeasures is one. FIG. 12(b) is a diagram showing a case where there are a plurality of identified estimated factors and countermeasures. 13 is a diagram showing a difference between an inferred factor identified by the factor inferring process of the first embodiment and an inferred factor identified by the factor inferring process of the second embodiment. FIG. It is a diagram showing an example of the hardware configuration of a factor estimation device.

Hereinafter, each embodiment of the present invention will be described using the drawings.

<First embodiment>
FIG. 1 is a diagram showing an example of a schematic configuration of a factor estimation system 1000 according to the present embodiment. As illustrated, the factor estimation system 1000 includes a factor estimation device 100 and an external device 200 that transmits various types of information used in the processing executed by the factor estimation device 100 to the factor estimation device 100. Further, the factor estimation device 100 and the external device 200 are connected to each other so as to be able to communicate with each other via a communication cable or a public network such as the Internet, a LAN (Local Area Network), or a WAN (Wide Area Network). .

The external device 200 may be, for example, a device that detects defective patterns, a device that stores the operation history of personnel on facility equipment (hereinafter sometimes referred to as "facility"), a device that generates facility logs, and various sensor devices that perform sensing on facility, manufactured products (or parts), or other targets (hereinafter sometimes collectively referred to as "monitored targets") and output sensor information that is the result of the sensing.

A device for detecting defective patterns is a device for detecting various defective patterns occurring in a monitored object. When such a device detects a defective pattern, it generates defective pattern information 210 and transmits this to the factor estimation device 100. Here, the failure pattern is information that indicates the characteristics of an event that differs from a preset or designed event when that event occurs. For example, when the monitoring target is equipment, the failure pattern information 210 is information indicating characteristics of the operation of the equipment that differ from a predetermined setting or plan. Further, when the monitoring target is a product, the defect pattern information 210 is information indicating characteristics of the product configuration that are different from a predetermined setting or plan.

Furthermore, the defect pattern information 210 includes information that identifies the equipment or product in which the defect has occurred. For example, when a defect occurs in equipment, the defect pattern information 210 includes a section (block) in which a series of processes including a processing step (hereinafter sometimes referred to as a "sequence") using the equipment is performed. Contains identifying information. Specifically, if the sequence is one process on a manufacturing line, the defective pattern information 210 includes identification information of the manufacturing line.

For example, when parts of equipment are replaced, a device that stores a person's operation history receives and stores the operation history for that work. Further, this device generates human operation history information 220 and transmits it to the factor estimation device 100 when receiving a new operation history input or periodically (for example, every hour).

The device that generates the equipment log is a device that generates the equipment log 230, which is equipment status information, and is, for example, the equipment itself. Such a device periodically (for example, every 10 seconds) transmits the equipment log 230 to the factor estimation device 100.

The sensor device is a device that senses predetermined observation items in a monitoring target and outputs sensor information 240 that is the sensing result. There are various types of sensor devices, such as cameras that capture images of the operation of equipment or the state of products, and sensors that capture the physical and chemical properties of monitored objects. Note that when multiple observation items are set for one monitoring target, sensor information 240 corresponding to each observation item is acquired by different types of sensor devices, and periodically (for example, every second), the sensor information 240 corresponding to each observation item is It is output (transmitted) to the estimation device 100. It should be noted that each sensor information 240 includes information indicating the observation item, numerical information expressing the sensing result of the observation item numerically, and the status of the monitoring target indicated by the numerical information (for example, "normal" or "abnormal"). ) is included.

The factor estimating device 100 is a device that identifies presumed causes and countermeasures for a defect occurring in a monitored object and presents them to a user. Specifically, the factor estimating device 100 uses predetermined information (factor estimating information) in which information indicating the defect pattern and the state of the monitored object, estimated factors of the defect, and countermeasures thereof are registered in association with each other, and the external device 200. Using the defect pattern information 210 and observed values (human operation history information 220, equipment log 230, and sensor information 240 are collectively referred to as "observed values") acquired from the system, estimated causes of defects and countermeasures are identified. Note that details of the factor estimation information will be described later.

The factor estimating device 100 also calculates the reliability value of the sensor information 240, and uses this to calculate the reliability values of the estimated factors and countermeasures. Furthermore, the factor estimating device 100 generates estimated factor countermeasure information that includes content in which the identified estimated factors and countermeasures are associated with their reliability values. Furthermore, the factor estimation device 100 generates screen information for displaying the estimated factor countermeasure information, and causes the screen information to be displayed on a display device that is visible to the user.

Such a factor estimation device 100 has a normal state accumulation unit 110, a threshold calculation unit 120, a factor estimation unit 130, a display information generation unit 140, a memory unit 150, and a communication unit 160.

The normal state accumulation unit 110 is a functional unit that acquires sensor information 240 and the like in a normal state in which no defects have occurred from the external device 200, and stores and accumulates this in the memory unit 150. Specifically, the normal state accumulation unit 110 acquires human operation history information 220, equipment log 230, and sensor information 240 from the external device 200 via the communication unit 160, and stores these in the memory unit 150.

In addition, the normal state storage unit 110 stores the sensor information 240 and the handling targets such as products and parts handled by the equipment or the constituent parts of the equipment ( Hereinafter, normal state accumulation information 153 indicating a predetermined relationship established between predetermined elements (hereinafter sometimes referred to as "handling objects corresponding to sensor information, etc.") is generated.

The threshold calculation unit 120 is a functional unit that calculates a threshold for determining the reliability of the sensor information 240. Specifically, the threshold calculation unit 120 uses the normal state accumulation information 153 to determine whether a predetermined relationship established between the sensor information 240 and a predetermined element such as a handling object corresponding to the sensor information 240 changes. Calculate the boundary (threshold).

The factor estimating unit 130 is a functional unit that uses the factor estimating information 154 to identify estimated causes of defects and countermeasures. Specifically, the factor estimating unit 130 executes a factor estimating process to identify the estimated cause of the defect and countermeasures. More specifically, the factor estimating unit 130 uses the estimated factors associated with the contents that match the failure pattern information 210, human operation history information 220, equipment log 230, and sensor information 240 acquired from the external device 200. and countermeasures are identified from the factor estimation information 154.

Furthermore, the factor estimating unit 130 calculates reliability values of the identified estimated factors and countermeasures. Specifically, the factor estimation unit 130 compares a predetermined element such as a handling object corresponding to the sensor information 240 with a threshold value, thereby determining whether the reliability of the sensor information 240 is high when such handling object is used. , or low. Furthermore, the factor estimating unit 130 calculates the reliability value of the sensor information 240 when such a handling object is used by assigning a predetermined value corresponding to the specified reliability.

In addition, the factor estimation unit 130 associates reliability values of the sensor information 240 with observation items of the factor estimation information 154 in which content matching the sensor information 240 is registered, and sets reliability values associated with each observation item. By aggregating the values, the reliability values of the identified estimated factors and countermeasures are calculated.

The display information generation unit 140 is a functional unit that generates screen information to be displayed on a display device. Specifically, the display information generation unit 140 generates screen information for displaying the contents of information including the identified estimated cause and countermeasure (estimated factor countermeasure information). Further, the display information generation unit 140 transmits the generated screen information to an external display device 300 (for example, a display device such as a display that is visually recognized by the user) via the communication unit 160, and causes the screen information to be displayed.

The storage unit 150 is a functional unit that stores various information. Specifically, the storage unit 150 stores plan information 151, sensor related information 152, normal state accumulation information 153, and factor estimation information 154. Furthermore, the storage unit 150 temporarily stores defective pattern information 210 acquired from the external device 200, human operation history information 220, equipment log 230, and sensor information 240 periodically acquired from the external device 200.

FIG. 2 is a diagram showing an example of the plan information 151. The plan information 151 is information indicating various plans for various objects such as product manufacturing plans and storage plans. As shown in the figure, the plan information 151 includes a sequence 151a, an implementation block 151b, a handling target 151c, a predetermined element 151d of the handling target, a component 151e, and a predetermined element 151f of the component. have a record.

The sequence 151a is information for specifying a processing step, and for example, the type or name of the processing step is registered. The execution block 151b is information indicating a section (block) in which a series of processes including a corresponding sequence is executed, and is information common to the execution block included in the defective pattern information 210. For example, if the sequence is one process on a manufacturing line, identification information of the manufacturing line is registered in the execution block.

Handling object 151c is information indicating handling objects such as products and parts handled in each sequence, and for example, their names and model numbers are registered. Specific elements of handling object 151d are information indicating various characteristics of handling object, such as height, width, and weight. Component part 151e is information indicating components (parts) of the equipment that executes the sequence, and for example, part name, type, or model number is registered. Specific elements of component part 151f are information indicating various characteristics of component part, such as height, width, and weight.

FIG. 3 is a diagram showing an example of the sensor related information 152. The sensor related information 152 is information in which a sequence and an implementation block in which sensing of the observation item for which the sensor information 240 was acquired are associated. Specifically, the sensor related information 152 includes a record in which an observation item 152a, a sequence 152b, and an implementation block 152c are associated with each other.

The observation item 152a is information indicating the sensing target of the sensor information 240. The sequence 152b and the implementation block 152c are information common to the sequence 151a and the implementation block 151b in the plan information 151, respectively.

FIG. 4 is a diagram showing an example of the normal state accumulation information 153. The normal state accumulation information 153 is information indicating a predetermined relationship established between the sensor information 240 and the handling object corresponding to the sensor information 240. In the illustrated example, the vertical axis indicates the value of the sensor information 240 for a certain observation item, and the horizontal axis indicates the value of a predetermined element of the object to be handled or the component. Further, circles indicate plot positions showing these relationships.

FIG. 5 is a diagram showing an example of the factor estimation information 154. The factor estimation information 154 is information including estimated factors and countermeasures for the defective pattern. Specifically, the factor estimation information 154 includes a rule 154a, a failure pattern 154b, a human operation history 154c, an equipment log 154d, and observation item 1 (154e) to observation item n (n is an integer and the number of observation items). ) 154f, an estimated factor 154g, and a countermeasure 154h are associated with each other.

The rule 154a is information that identifies estimated factors and countermeasures registered in each record. The defective pattern 154b is information indicating a detected defective pattern. The human operation history 154c is information indicating the history of human operations on equipment. The equipment log 154d is log information output from equipment to be monitored.

Furthermore, observation item 1 (154e) to observation item n (154f) are information indicating observation items in the monitoring target. There are 1 to n observation items depending on the sensing target, and status information (for example, "normal", "abnormal", etc.) of the monitoring target specified based on the numerical information of the sensing result is registered. ing. Note that the state information registered in the observation item corresponds to the state information of the monitoring target included in the sensor information 240. The estimated factor 154g is information indicating the cause of the defect estimated from the defect pattern 154b, the human operation history 154c, the equipment log 154d, and the registered contents of observation item 1 (154e) to observation item n (154f). The countermeasure 154h is information indicating a countermeasure for solving the problem of the estimated factor.

Note that the equipment and observation items to be monitored differ depending on the target to which the factor estimation system 1000 is applied. Therefore, information corresponding to the target to which the factor estimation system 1000 is applied is registered in the plan information 151, sensor related information 152, and factor estimation information 154, and the factor estimation unit 130 uses these information to Execute estimation processing. In addition, the normal state accumulation unit 110 stores normal state accumulation information 153 indicating the relationship between the sensor information 240 corresponding to the observation item corresponding to the object and a predetermined element such as the object to be handled corresponding to the sensor information 240. generate.

The communication unit 160 is a functional unit that performs information communication with the external device 200. Specifically, the communication unit 160 acquires defective pattern information 210, human operation history information 220, equipment log 230, and sensor information 240 from the external device 200. Further, the communication unit 160 transmits screen information of the estimated factor countermeasure information to a predetermined display device.

An example of the functional configuration of the factor estimation device 100 has been described above.

[Explanation of operation]
Next, the factor estimation process executed by the factor estimation device 100 will be described in accordance with one example in which the factor estimation system 1000 is applied.

Figure 6 shows a manufacturing line, which is an example of an application of the factor estimation system 1000. As shown in the figure, the manufacturing line 400 has a worker 410, a display device 300 that displays predetermined information to the worker 410, a robot 420, a storage box 430, a belt conveyor 440, a workpiece 450, and a supply device 460. The manufacturing line 400 also has, as external devices 200, a device that detects defective patterns (not shown), a device that generates human operation history information 220, and a sensor device that senses predetermined observation items in a predetermined monitoring target. The equipment log 230 may be generated by each device, such as the robot 420 or the belt conveyor 440.

The illustrated manufacturing line 400 includes a process in which a robot 420 picks up a workpiece 450 flowing on a belt conveyor 440 and stores it in a storage box 430. Specifically, in the manufacturing line 400, a supply device 460 conveys a workpiece 450 at a constant speed to a fixed position on the belt conveyor 440 (for example, the center of the belt conveyor 440). Furthermore, the belt conveyor 440 moves the workpiece 450 toward the robot 420 . Further, when the workpiece 450 reaches a predetermined position, the robot 420 repeatedly performs an operation of picking up the workpiece 450 with a hand 470 attached to its tip and storing it in the storage box 430.

Further, in this example, it is assumed that a plurality of production lines having the same configuration and having different weights of works 450 are in operation. Additionally, defective pattern information 210, human operation history information 220, and sensor information 240 are sent to the factor estimation device 100 from external devices 200 possessed by each manufacturing line, and equipment logs 230 are sent from each piece of equipment such as a robot 420 and a belt conveyor 440. is transmitted to the factor estimation device 100. Note that the sources of various information are not limited to the above examples.

When the normal state storage unit 110 acquires the sensor information 240 from the external device 200 via the communication unit 160, it generates or updates the normal state storage information 153. For example, when the information indicating the observation item included in the sensor information 240 is "gripping force of the hand 470", the normal state storage unit 110 stores the sequence and execution block in which sensing of the observation item is performed in relation to the sensor. It is specified from the information 152.

FIG. 7 is a diagram showing an example of the sensor related information 152 used in this example. As shown in the figure, the observation item 152a includes, for example, "hand gripping force". Further, in the sequence 152b, for example, "storage process" is registered. Furthermore, information such as "manufacturing line M" is registered in the implementation block 152c.

In this case, for example, the sequence = "storage process" and the implementation block = "manufacturing line M", which are associated with the observation item = "hand gripping force", are identified from the sensor related information 152. .

Further, the normal state storage unit 110 identifies a predetermined element such as a handling target corresponding to the sensor information 240 from the plan information 151.

Figure 8 is a diagram showing an example of the planning information 151 used in this example. As shown in the figure, for example, the predetermined element 151d of the handling object and the predetermined element 151f of the component in Figure 2 are associated with elements such as height 151d1, 151f1, width 151d2, 151f2, and weight 151d3, 151f3. In addition, in the sequence 151a, information common to the sequence 152b of the sensor relationship information 152 shown in Figure 7 is registered. In addition, for example, "work X" is registered in the handling object 151c. In addition, the height, width, and weight "10 kg" of each work 450 are registered in the height 151d1, width 151d2, and weight 151d3 of the handling object. In addition, for example, "hand Y" is registered in the component 151e. Additionally, the height 151f1, width 151f2, and weight 151f3 of the component include the height, width, and weight of the hand 470, such as "5 kg."

In this case, for example, the handling object = "Work X" which is associated with the sequence = "Storage process" and the implementation block = "Production line M", and the height, width and weight of the handling object = "10 kg". ”, the component = “hand Y”, and the height, width and weight of the component = “5 kg” are specified from the plan information 151.

Further, the normal state accumulation unit 110 generates the normal state accumulation information 153 based on a predetermined viewpoint using numerical information included in the sensor information 240 and predetermined elements such as the specified handling object. Here, the predetermined viewpoint (not shown) is a viewpoint that serves as a generation standard for the normal state accumulated information 153, and is calculated from the predetermined observation items and the normal state accumulated information 153 generated based on this viewpoint. and the threshold values are stored in the storage unit 150 in association with each other.

In this case, for example, the viewpoint of "the relationship between the gripping force of the hand and the weight of the workpiece" is determined from the observation item "gripping force of the hand" and the normal state accumulation information 153 generated based on this viewpoint. It is stored in the storage unit 150 in association with the calculated threshold value.

FIG. 9 is a diagram showing an example of the normal state accumulation information 153 generated in this example. As shown in the figure, the normal state accumulation information 153 includes, for example, the relationship between the value of the sensor information 240 (vertical axis) including the observation item "hand gripping force" and the weight of the workpiece 450 (horizontal axis). The normal state accumulation information 153 indicating the normal state accumulation information 153 is generated.

Further, the normal state storage unit 110 stores the generated normal state storage information 153 in the storage unit 150. Further, the normal state storage unit 110 performs similar processing every time new sensor information 240 is acquired, and updates the normal state storage information 153.

Further, the threshold calculation unit 120 calculates a threshold for specifying the reliability of the sensor information 240 using the generated normal state accumulation information 153. Specifically, the threshold calculation unit 120 uses the normal state accumulation information 153 to determine, as the threshold, a value at which a change occurs in the relationship established between the sensor information 240 and a predetermined element of the handling object or component. calculate.

For example, in the example shown in FIG. 9, it can be seen that as the weight of the workpiece becomes lighter, the gripping force of the hand also decreases, and when the weight of the workpiece 450 becomes less than a predetermined value, the gripping force of the hand takes on a substantially constant value. That is, when the weight of the workpiece is more than a certain value, a correlation is established between the gripping force of the hand and the weight of the workpiece, but when the weight of the workpiece becomes less than a certain value, the correlation is no longer maintained. Therefore, the threshold calculation unit 120 calculates a certain weight of the workpiece at which the correlation is no longer maintained as the threshold.

When the workpiece weight is heavier than the threshold, the threshold calculation unit 120 determines that the reliability of the sensor information 240 when a workpiece weight heavier than the threshold is handled is high reliability because a correlation is established between the workpiece weight and the gripping force of the hand. The threshold calculation unit 120 determines that the reliability of the sensor information 240 when a workpiece weight lighter than the threshold is handled is low reliability. The threshold calculation unit 120 also associates each piece of information including the threshold and reliability indicated by the normal state accumulation information 153 and stores them in the memory unit 150.

The generation of the normal state accumulation information 153 and the calculation of the threshold value have been described above.

Figure 10 is a flow diagram showing an example of the cause estimation process. The cause estimation process is started, for example, when the cause estimation unit 130 acquires the failure pattern information 210 via the communication unit 160. In this example, it is assumed that a failure pattern of "Manufacturing line M, robot No Pick" is detected.

When the process is started, the factor estimating unit 130 identifies the estimated cause of the defect and countermeasures (step S001). Specifically, when the factor estimating unit 130 acquires the defective pattern information 210 via the communication unit 160, the factor estimating unit 130 extracts the defective pattern information 210, the latest (recent) human operation history information 220 at that point, and the equipment log 230. , sensor information 240 corresponding to the observation item, and records in which contents matching are registered are narrowed down from the factor estimation information 154 .

FIG. 11 is a diagram showing an example of the factor estimation information 154 used in this example. As shown in the figure, for example, observation item 1 in FIG. 5 is associated with "hand gripping force." Further, as a defective pattern, for example, "Robot NoPick" is registered. In addition, in the gripping force of the hand (observation item 1), state information of the monitoring target, such as "normal" or "abnormal", which is specified based on the numerical information of the sensing result of the corresponding observation item, is registered. Further, as the estimated factors, for example, "hand component abnormality" and "misalignment of gripping position" are registered. In addition, as countermeasures, for example, "replacement of hand parts" and "adjustment of position of hand and workpiece" are registered.

In this example, records of rules 2 and 3 in which contents matching the contents of the defect pattern information 210, human operation history information 220, equipment log 230, and sensor information 240 acquired from the external device 200 are registered are narrowed down. Suppose that

The factor estimation unit 130 also identifies the estimated factors and measures registered in the narrowed-down records. In addition, the factor estimation information 154 may contain multiple records in which the same content is registered in the failure pattern 154b and observation item 154e, which are conditions when the factor estimation unit 130 narrows down the records, and the estimated factors 154g and measures 154h are different from each other. This is because multiple different estimated factors and measures are possible even if the state of the monitored object indicated by the failure pattern and observation item is the same. Therefore, when there are multiple records in which content matching the failure pattern information 210 acquired from the external device 200, the latest (most recent) human operation history information 220 at that time, the equipment log 230, and the sensor information 240 corresponding to the observation item is registered, the factor estimation unit 130 identifies each estimated factor and measure registered in those records.

In addition, in this case, for example, the presumed cause of "hand component abnormality" and the countermeasure of "replacement of the hand component" and the presumed factor of "misalignment of gripping position" and the countermeasure of "position adjustment of the hand and workpiece" are combined. Two sets are identified.

Next, the factor estimating unit 130 performs preliminary processing to calculate reliability values of the identified estimated factors and countermeasures. The reliability of the estimated factors and countermeasures depends on the reliability of the sensor information 240 acquired in the observation item of the factor estimation information 154 to which the estimated factors and the like are associated. Further, the reliability of the sensor information 240 depends on a predetermined element of the object corresponding to the sensor information 240. Therefore, the factor estimating unit 130 calculates the reliability value of the sensor information 240, and uses that value to calculate the reliability value of the identified estimated factor and countermeasure.

In calculating the reliability value of the sensor information 240, the factor estimation unit 130 specifies a predetermined viewpoint (step S002). Specifically, the factor estimating unit 130 identifies, from the storage unit 150, a viewpoint that is associated with the same observation item as the observation item 154e of the factor estimation information 154 that is associated with the identified estimated factor 154g and countermeasure 154h. do.

In this example, for example, the viewpoint of "the relationship between the gripping force of the hand and the weight of the workpiece" that is associated with the observation item "gripping force of the hand" is specified.

Next, the factor estimation unit 130 identifies a specific element to be treated that is defined by the viewpoint identified in step S002 from the sensor information 240 that is the latest (most recent) at the time when the failure pattern information 210 is acquired and that includes the same observation item as the observation item 154e of the factor estimation information 154 that is associated with the identified estimated factor 154g and countermeasure 154h (step S003).

Specifically, the factor estimating unit 130 uses the implementation block included in the defective pattern information 210 acquired from the external device 200 and the information indicating the observation items included in the sensor information 240 to calculate the corresponding sequence using the sensor. It is specified from the relationship information 152.

In this example, for example, a sequence called "storage process" is specified from the sensor-related information 152 using an implementation block called "manufacturing line M" and an observation item called "gripping force of hand 470."

The factor estimation unit 130 also identifies from the plan information 151 specific elements that are defined by a viewpoint from among the specific elements of the handling target, etc., that correspond to the identified sequence and the implementation block.

In this example, for example, the weight "10 kg" of the handling target "work X" to which the sequence "storage process" and the execution block "manufacturing line M" are associated is specified.

Next, the factor estimation unit 130 identifies the reliability of the sensor information 240 based on the threshold value associated with the viewpoint (step S004). Specifically, the factor estimation unit 130 identifies the threshold value associated with the viewpoint from the storage unit 150. In addition, the factor estimation unit 130 compares a specific element such as the handling object with the threshold value, and identifies whether the reliability of the sensor information 240 is high reliability or low reliability depending on the value of the specific element such as the handling object.

Next, the factor estimation unit 130 calculates the reliability value of the sensor information 240 (step S005). Specifically, the factor estimation unit 130 assigns a predetermined value corresponding to the identified reliability as the reliability value of the sensor information 240. More specifically, when the identified reliability is high reliability, the factor estimation unit 130 assigns a predetermined value (for example, 80%) to the reliability value of the sensor information 240. On the other hand, when the specified reliability is low reliability, the factor estimation unit 130 assigns a predetermined value (for example, 50%) to the reliability value of the sensor information 240.

Next, the factor estimation unit 130 determines whether or not the reliability values of the sensor information 240 corresponding to all observation items 1 (154e) to observation items n (154f) of the factor estimation information 154 have been calculated ( Step S006). If it is determined that reliability values have not been calculated for all of the sensor information 240 (No in step S006), the factor estimation unit 130 performs the process of step S006 again.

On the other hand, if it is determined that the reliability values have been calculated for all of the sensor information 240 (Yes in step S006), the factor estimation unit 130 calculates the reliability values of the identified estimated factors and countermeasures (step S007). ). Specifically, the factor estimation unit 130 assigns observation items 1 (154e) to observation item n (154f) of the factor estimation information 154 to which the identified estimated factors and countermeasures are associated with the same observation items as these observation items. The reliability value of sensor information 240 that includes information indicating .

In addition, the factor estimation unit 130 aggregates the reliability values associated with all observation items associated with the identified estimated factors and countermeasures, and uses the average value as the reliability value of the estimated factors and countermeasures. calculate.

Note that when there are a plurality of identified estimated factors and countermeasures, the factor estimation unit 130 calculates a reliability value for each estimated factor and countermeasure.

Next, the factor estimation unit 130 generates estimated factor countermeasure information (step S008). Specifically, the factor estimating unit 130 generates estimated factor countermeasure information including the identified estimated factor and countermeasure, and a reliability value.

Next, the display information generation unit 140 generates screen information for displaying the contents of the estimated factor countermeasure information on a display device (step S009). Further, the display information generation unit 140 transmits the generated screen information to the display device 300 that can be viewed by the user via the communication unit 160 (step S010), and causes the display device 300 to display the screen information. Furthermore, after the display information generation unit 140 performs the process of step S010, this flow ends.

FIG. 12 is a diagram showing an example screen 500 showing the contents of the estimated factor countermeasure information. FIG. 12A is a diagram showing an example screen 500 when there is only one identified estimated factor and one countermeasure. FIG. 12(b) is a diagram showing an example screen 500 with a plurality of identified estimated factors and countermeasures.

As illustrated, the example screen 500 includes a defect information display area 510, an estimated cause display area 520, a countermeasure display area 530, and a reliability display area 540. The defect information display area 510 displays the location of the defect, the time of occurrence of the defect, and error details indicating the defect pattern. Furthermore, the estimated cause and countermeasure that have been identified are displayed in the estimated factor display area 520 and the countermeasure display area 530, respectively. Furthermore, the reliability display area 540 displays the reliability values of the estimated factors and countermeasures.

The factor estimation system according to this embodiment has been described above. According to the factor estimating device in such a factor estimating system, more useful information can be provided to the user by specifying estimated factors and countermeasures for defects in consideration of the reliability of sensor information. Normally, even if the observation item is the same, the reliability of sensor information changes depending on the physical characteristics such as the weight, size, or shape of the object being handled or the component parts of the equipment. Therefore, the factor estimation device calculates the reliability value of the sensor information by considering the relationship between the sensor information and the physical characteristics of the corresponding object, etc., and uses this to determine the estimated factors and countermeasures. Calculate the reliability value of. The factor estimation device also presents the calculated reliability value to the user in association with the estimated factor and countermeasure. Therefore, the factor estimation device can present more useful information to the user.

<Second embodiment>
The factor estimating device 100 according to the second embodiment identifies estimated factors and countermeasures using highly reliable sensor information 240. Specifically, upon starting the factor estimation process, the factor estimation unit 130 generates information indicating the same observation items as all observation items 1 (154e) to observation items n (154f) included in the factor estimation information 154. The reliability value of the included sensor information 240 is calculated. Note that the same method as described above may be used to calculate the sensor information 240.

The factor estimation unit 130 also identifies the estimated factors and countermeasures using factor estimation information 154 that excludes observation items corresponding to sensor information 240 with reliability values below a predetermined value (e.g., below 80%). Note that the method of identifying the estimated factors and countermeasures may be the same as that described above.

Further, when there are a plurality of identified estimated factors and countermeasures, the factor estimation unit 130 calculates a reliability value for each estimated factor and countermeasure.

Note that the factor estimating unit 130 sets a predetermined value (for example, 80%) as the reliability value of the identified estimated factor and countermeasure. This is because the estimated factors and countermeasures are specified based on the observation items of the factor estimation information 154 corresponding to the highly reliable sensor information 240.

Further, similarly to the first embodiment, the factor estimating unit 130 generates estimated factor countermeasure information using the specified estimated factor and countermeasure, and transmits the screen information to a predetermined display device.

FIG. 13 is a diagram showing the difference between the inferred factors identified by the factor inference process of the first embodiment and the inferred factors identified by the factor inference process of the second embodiment. As shown in the figure, there may be cases where the inferred factors identified by the factor inference process of the first embodiment differ from the inferred factors identified by the factor inference process of the second embodiment. For example, when an inferred factor is identified taking into account low-reliability sensor information 240, the reliability value of the inferred factor will be lower than that of an inferred factor identified taking into account only high-reliability sensor information 240. Therefore, while the inferred factors corresponding to distribution area A are identified in the factor inference process of the first embodiment, the inferred factors corresponding to distribution area B may be identified in the factor inference process of the second embodiment.

The factor estimation system and factor estimation device according to the second embodiment have been described above.

Such a factor estimation device identifies the estimated cause of a defect and countermeasures using only highly reliable sensor information, making it possible to provide the user with more accurate and useful information. In particular, the factor estimation device identifies the estimated cause and countermeasures using factor estimation information that excludes observation items corresponding to low-reliability sensor information, making it possible to identify the estimated cause and countermeasures with higher accuracy.

<Third embodiment>
The factor estimation device 100 according to the third embodiment receives feedback regarding the identified estimated factors and countermeasures from the user, reflects the feedback results in the reliability value of the sensor information 240, and calculates the reliability value of the sensor information 240. The factor estimation process of the first embodiment or the second embodiment described above is performed using the above-described method.

Specifically, the factor estimating unit 130 obtains feedback regarding the identified estimated factors and the correctness of the countermeasure from the user via the communication unit 160. Further, if the feedback result indicates that the estimated factors and countermeasures presented to the user were correct, the factor estimation unit 130 selects observation item 1 of the factor estimation information 154 to which the estimated factors and countermeasures are associated. (154e) ~ Specify the reliability value of the sensor information 240 including information indicating the same observation item as observation item n (154f) (for example, 80% for high reliability, 50% for low reliability) Add a value (eg, 1%).

The factor estimation unit 130 also uses the reliability value of the sensor information 240 to perform factor estimation processing similar to that of the first or second embodiment described above.

Note that if the feedback result indicates that the estimated factor and countermeasure were incorrect, the factor estimation unit 130 may subtract a predetermined value (for example, 1%) from the reliability value of the sensor information 240. .

Note that the method of reflecting the feedback result is not limited to adding and subtracting a predetermined value to and from the reliability value, but may also be, for example, multiplying the reliability value by a predetermined coefficient (weight value).

According to such a factor estimating device, it is possible to calculate a more accurate reliability value of sensor information, and therefore it is possible to specify estimated factors and countermeasures with higher accuracy.

Note that the factor estimation system 1000 according to the present invention can be modified in various ways within the same technical idea as the above-described embodiment. For example, if the reliability value of the identified estimated factor and countermeasure is less than or equal to a predetermined value (for example, 50% or less), the factor estimating unit 130 of the factor estimating device 100 according to the first modified example , make an on-call call to the repair company by phone, email, or other means.

If the reliability values of the identified estimated factors and countermeasures are low, it is assumed that the cause of the defect may not be resolved even with the countermeasures presented to the user. Therefore, when the reliability values of the estimated factors and countermeasures are low to some extent, the factor estimating device 100 automatically calls a repair shop, thereby saving the user's effort.

Furthermore, the factor estimating device 100 generates the normal state accumulation information 153 during the same time period. Thereby, a standard value of the sensor information 240 can be obtained, more accurate normal state accumulation information 153 can be generated, and a more accurate threshold value can be calculated.

An example of the hardware configuration of the factor estimation device 100 will be described below.

FIG. 14 is a diagram showing an example of the hardware configuration of the factor estimation device 100. The factor estimation device 100 is realized by, for example, a high-performance information processing device such as a server device.

As illustrated, the factor estimating device 100 includes an arithmetic device 610, a main storage device 620, an auxiliary storage device 630, a communication device 640, and a bus 650 that electrically interconnects these devices.

The computing device 610 is, for example, a CPU (Central Processing Unit). The main memory device 620 is a memory device such as a RAM (Random Access Memory) or a ROM (Read Only Memory).

The auxiliary storage device 630 is a nonvolatile storage device such as a so-called hard disk drive, SSD (Solid State Drive), or flash memory that can store digital information.

The communication device 640 is a wired communication device that performs wired communication via a network cable, or a wireless communication device that performs wireless communication via an antenna. The communication device 640 performs information communication with the external device 200 connected to the network.

Note that the factor estimation device 100 may include an input device and a display device. In this case, the input device is, for example, an input device such as a touch panel, keyboard, or mouse. The display device is a display device such as a liquid crystal display or an organic display.

An example of the hardware configuration of the factor estimation device 100 has been described above.

The normal state accumulation unit 110, threshold calculation unit 120, factor estimation unit 130, and display information generation unit 140 of the factor estimation device 100 are realized by a program that causes the calculation device 610 to perform processing. This program is stored in the main memory device 620 or the auxiliary memory device 630, and is loaded onto the main memory device 620 when the program is executed, and is executed by the calculation device 610. The storage unit 150 is realized by the main memory device 620 or the auxiliary memory device 630, or a combination of these. The communication unit 160 is realized by the communication device 640.

Further, each of the above-mentioned configurations, functions, processing units, processing means, etc. of the factor estimating device 100 may be partially or entirely realized in hardware by designing, for example, an integrated circuit. Further, the above configuration and functions may be realized by software by a processor interpreting and executing programs for realizing the respective functions. Information such as programs, tables, files, etc. that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD, or a recording medium such as an IC card, an SD card, or a DVD.

Further, the present invention is not limited to the above-described embodiments and modifications, but includes various modifications within the same technical idea. For example, the embodiments described above are described in detail to explain the present invention in an easy-to-understand manner, and the present invention is not necessarily limited to having all the configurations described. Furthermore, it is possible to replace a 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. Furthermore, it is possible to add, delete, or replace a part of the configuration of each embodiment with other configurations.

In addition, in the above explanation, the control lines and information lines are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be considered that almost all components are interconnected.

1000... Factor estimation system, 100... Factor estimation device, 110... Normal state accumulation section, 120... Threshold calculation section, 130... Factor estimation section, 140... Display information generation section, 150...Storage unit, 151...Plan information, 152...Sensor related information, 153...Normal state accumulation information, 154...Factor estimation information, 160...Communication unit, 200... External device, 210... Failure pattern information, 220... Human operation history information, 230... Equipment log, 240... Sensor information, 300... External display device, 420... Robot, 430 . . . Storage box, 440 . - Auxiliary storage device, 640... Communication device, 650... Bus

Claims (9)

A communication unit that acquires from an external device failure pattern information indicating a failure pattern occurring in a facility or a product, and an observation value that is a sensing result of a predetermined observation item in the facility to be monitored and includes sensor information indicating a state of the facility;
a storage unit that stores cause estimation information in which the failure patterns, the observation values corresponding to each of the failure patterns, the observation items that indicate the state of the equipment and correspond to each combination of the failure patterns and the observation values, and the cause of failure and measures corresponding to each combination of the failure patterns, the observation values, and the observation items are registered ;
a factor estimation unit that estimates a factor of a failure by identifying an estimated factor of the failure and a countermeasure for the failure corresponding to the failure pattern from the factor estimation information based on the failure pattern information acquired from the external device and the observed value;
a threshold calculation unit that calculates a value of the predetermined element as a threshold value at which a correlation between the value of the sensor information and a predetermined element of an object to be handled in the equipment or a component of the equipment used in a sequence in which sensing of the observation item from which the sensor information was obtained is not maintained;
The factor estimation unit is
A factor estimation device, comprising: a factor estimation unit that determines a reliability of the sensor information by using the threshold value. The factor estimation device according to claim 1,
The factor estimation unit is
Calculating a reliability value based on the identified reliability of the sensor information;
a factor estimation device, characterized in that it calculates reliability values of the estimated factors and countermeasures corresponding to the observation items by aggregating the reliability values of the sensor information as reliability values of the observation items in the factor estimation information indicating the state of the equipment corresponding to the sensor information. The factor estimation device according to claim 1 ,
The threshold calculation unit includes:
The sensor information has a value of the predetermined element in which the correlation is maintained, and the reliability of the sensor information obtained using the handling object or the component is set as high reliability,
A factor characterized in that the sensor information has a value of the predetermined element in which the correlation is not maintained, and the reliability of the sensor information obtained using the handling object or the component part is set to low reliability. Estimation device. The factor estimation device according to claim 2,
further comprising a display information generation unit that generates display information that displays the identified estimated factors and countermeasures in association with calculated reliability values of the estimated factors and countermeasures,
The communication department includes:
A factor estimation device characterized in that the display information is transmitted to a predetermined display device. The factor estimation device according to claim 1,
The factor estimator includes:
Calculating the reliability value based on the reliability of the identified sensor information,
Among the observation items of the factor estimation information, the observation item indicating the state of the equipment corresponding to the sensor information having the reliability value equal to or higher than a predetermined value is used to identify the estimated cause and the countermeasure. A factor estimation device characterized by: The factor estimation device according to claim 2,
The communication unit acquires a feedback result regarding the identified estimated cause and the correctness of the countermeasure,
The factor estimation unit is
a factor estimation device that, when the feedback result indicates that the estimated factor and countermeasures were correct, calculates a reliability value of the sensor information by adding a predetermined value to the reliability value of the sensor information. The factor estimation device according to claim 2,
The factor estimator includes:
A factor estimation device characterized in that when the calculated reliability value is less than a predetermined value, an on-call is made to a repair company. An external device including a device for outputting failure pattern information indicating a failure pattern occurring in a facility or a product, and a device for outputting an observation value including sensor information indicating a state of the facility, the observation value being a sensing result of a predetermined observation item in the facility to be monitored;
a communication unit that acquires the failure pattern information and the observed value from the external device;
a storage unit that stores cause estimation information in which the failure patterns, the observation values corresponding to each of the failure patterns , observation items that indicate the state of the equipment and correspond to each combination of the failure patterns and the observation values, and estimated causes of failure and countermeasures corresponding to each combination of the failure patterns, the observation values, and the observation items are registered ;
a factor estimation unit that estimates a factor of a failure by identifying an estimated factor of the failure and a countermeasure for the failure pattern from the factor estimation information based on the failure pattern information acquired from the external device and the observed value ;
a threshold calculation unit that calculates a value of the predetermined element as a threshold value at which a correlation established between a value of the sensor information and a predetermined element of an object to be handled in the equipment or a component of the equipment, which was used in a sequence in which sensing of the observation item in which the sensor information was acquired was performed, is no longer maintained ;
The factor estimating unit of the factor estimating device
A factor estimation system, comprising: a factor estimation unit that determines a reliability of the sensor information by using the threshold value. A program that causes a computer to function as a factor estimation device,
The computer,
Defective pattern information indicating a defective pattern that has occurred in equipment or products, and observation values that are sensing results of predetermined observation items in the equipment to be monitored and include sensor information indicating the status of the equipment, are externally transmitted. a communication unit that obtains information from the device;
The defective pattern, the observed value corresponding to each defective pattern , the observation item indicating the state of the equipment corresponding to each combination of the defective pattern and the observed value , the defective pattern, the observed value, and a storage unit storing factor estimation information in which estimated factors and countermeasures for defects corresponding to each combination of observation items are registered ;
Based on the defective pattern information acquired from the external device and the observed value, the defective cause is estimated by identifying the defective estimated cause and countermeasure corresponding to the defective pattern from the factor estimation information. a factor estimation section;
established between the value of the sensor information and a predetermined element of the object handled by the equipment or the component of the equipment used in the sequence in which sensing of the observation item for which the sensor information was acquired is performed. functioning as a threshold calculation unit that calculates as a threshold the value of the predetermined element where the correlation is no longer maintained ;
The factor estimator includes:
A program characterized in that the reliability of the sensor information is specified using the threshold value.

Images