JP7145242B2 - Diagnostic system and diagnostic method - Google Patents

Description

The present invention relates to diagnostic systems and methods.

Plants such as various factories and power generation facilities, or infrastructures such as water supply networks and power transmission networks, are subject to loads depending on the operation content and surrounding environment, and may deteriorate or break down over time.

Therefore, maintenance at regular intervals, that is, TBM (Time Based Maintenance) is mainly performed to deal with such deterioration and failure. Since maintenance work naturally requires time and effort and costs, various conventional techniques have been proposed to improve efficiency and accuracy.

For example, in a health management system for monitoring the health condition of mechanical equipment, sensor data acquired from a plurality of sensors installed in the mechanical equipment, or environmental data representing the sensor data and the installation environment of the mechanical equipment, A time-series data acquisition unit that acquires time-series data, and a statistical method that uses normal data, which is the time-series data acquired when the mechanical equipment is in a normal state, as learning data. a state quantification unit for quantifying a health state indicating the state of performance or quality of the mechanical equipment; an output unit for displaying and/or outputting the quantified equipment state and the quantified health state to an external device; A health management system (see Patent Literature 1), etc., characterized by comprising

Also, an abnormality detection/diagnosis method for detecting an abnormality or a sign thereof in a plant or equipment and diagnosing the plant or equipment, wherein the abnormality in the plant or equipment is detected based on data acquired from a plurality of sensors, extracting keywords from the maintenance history information of the plant or equipment, generating a diagnostic model of the plant or equipment using the extracted keywords, and diagnosing the plant or equipment using the generated diagnostic model; An anomaly detection/diagnosis method characterized by: (see Patent Document 2), etc. have also been proposed.

JP 2015-088079 A JP 2011-227706 A

However, no method has been proposed for efficiently estimating the effects of various maintenance work and operating details on the subject of maintenance in terms of failure probability, necessary cost, etc., and presenting them to the user. This means that there is no provision of useful information for determining the appropriate timing and content of maintenance work. In addition, the state of implementation of the above-mentioned maintenance work and the transition of failure probability resulting from it can be used as material for value judgment regarding the maintenance target, but such information has not been provided.

SUMMARY OF THE INVENTION Accordingly, an object of the present invention is to provide a technique capable of providing suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

The diagnostic system of the present invention for solving the above problems is an annual insurance premium to be paid to an insurance company and a storage device that holds at least one of the following information: an insurance payment to be paid by an insurance company for each opportunity to perform maintenance on the maintenance object; When the estimated information of the failure probability transition at least after the predetermined time in the maintenance object is displayed in a graph when maintenance is performed and operation is performed according to each of a plurality of operation contents, the annual insurance premium and the insurance based on at least one of the above information, with respect to the standard of the failure probability that is the threshold for the annual insurance premium and the insurance money to change, the insurance premium and the insurance money are maintained at the current state, and the insurance premium is a fixed percentage from the current state. and an arithmetic unit that displays, in the graph display, incentive fluctuation lines of the insurance that indicate an increase and an insurance premium that decreases by a certain percentage from the current state.

In addition, the diagnostic method of the present invention is an annual insurance payable to an insurance company when an information processing system maintains a predetermined standard failure probability in a maintenance object with respect to the insurance contracted for the maintenance object. a storage device that holds information on at least one of a fee and insurance money paid by an insurance company for each maintenance execution opportunity for the maintenance object, and a plurality of maintenance contents for the maintenance object at a predetermined time. The annual insurance premium when displaying the estimated information of the failure probability transition at least after the predetermined time in the maintenance target object in a graph when maintenance is performed for each and operation is performed for each of the plurality of operation contents and based on at least one of the information of the insurance money, the insurance premium and the insurance money are maintained at the current state with respect to the failure probability standard that is the threshold for the annual insurance premium and the insurance money to fluctuate. Incentive fluctuation lines of the insurance are displayed in the graph display, respectively, indicating a constant percentage increase from the current level and a constant percentage decrease in insurance premiums from the current state.

ADVANTAGE OF THE INVENTION According to this invention, it becomes possible to provide the suitable judgment material regarding the planning and execution of a maintenance work, or the value of a maintenance object.

It is a network block diagram containing the diagnostic system in this embodiment. It is a figure which shows the hardware structural example of the diagnostic system in this embodiment. It is a figure which shows the structural example of sensor DB in this embodiment. It is a figure which shows the structural example of the measurement data in this embodiment. It is a figure which shows the structural example of event DB in this embodiment. It is a figure which shows the structural example of operation|movement DB in this embodiment. It is a figure which shows the structural example of estimation result DB in this embodiment. It is a figure which shows the structural example of incentive variation reference|standard DB in this embodiment. It is a figure which shows the structural example of credit value DB in this embodiment. It is a figure which shows the flow example 1 of the diagnostic method in this embodiment. It is a figure which shows the example 2 of the flow of the diagnostic method in this embodiment. It is a figure which shows the example 3 of the flow of the diagnostic method in this embodiment. FIG. 10 is a diagram showing an output example 1 according to the embodiment; It is a figure which shows the example 4 of the flow of the diagnostic method in this embodiment. FIG. 10 is a diagram showing an output example 2 in this embodiment; It is a figure which shows the example 5 of the flow of the diagnostic method in this embodiment. It is a figure which shows the example 6 of the flow of the diagnostic method in this embodiment. It is a figure which shows the calculation formula example of a credit value in this embodiment. FIG. 11 is a diagram showing an output example 3 in this embodiment;

--- Network configuration ---
Embodiments of the present invention will be described in detail below with reference to the drawings. FIG. 1 is a diagram showing a network configuration example including a diagnostic system 100 of this embodiment. A diagnostic system 100 shown in FIG. 1 is a computer system for providing suitable judgment materials regarding planning and execution of maintenance work or the value of maintenance objects.

The diagnostic system 100 can be assumed to be, for example, an information processing system that is operated by a so-called O&M (Operation & Management) business operator and used for drafting and executing a maintenance plan for maintenance objects. Of course, this operation form is just an example, and may be operated and used by other businesses such as insurance companies and financial institutions that find business value in maintenance objects.

Such a diagnostic system 100 is connected to an appropriate network 10 such as the Internet or a dedicated line, and is capable of data communication with a plant 200, a sensor unit 300, an insurance company system 400, and a financial institution system 500, which are maintenance objects. Note that the diagnostic system 100 may include the sensor unit 300 .

Among them, the plant 200 is an example of the object to be maintained as described above, and specifically, a power plant, a chemical plant, or the like can be assumed. The sensor unit 300 is arranged at a predetermined location or in the vicinity of the plant 200, obtains the sensing object, that is, the observed value regarding the observed event as measurement data 325 at regular intervals, and provides it to the diagnostic system 100 via the network 10. will be.

As observation events of the sensor unit 300, for example, various things such as temperature, vibration amount, rotation speed, current value, voltage value, flow rate, flow velocity, etc. of various mechanisms, processed objects, conveyed objects, etc. in the plant 200 can be assumed. be.

Also, the insurance company system 400 is a system of a business operator who has entered into an insurance contract with the plant owner or the O&M (Operation & Management) business operator described above regarding the plant 200, which is a maintenance object. The insurance to be contracted here is insurance that compensates for damages caused by a failure or accident in the plant 200, and a predetermined insurance money is paid when the event occurs.

Moreover, the financial institution system 500 is a system of a financial institution that provides loans to the plant owner using the above-described plant 200 as collateral. Therefore, this financial institution needs to recognize the value of the plant 200 with high accuracy.

--- Hardware configuration example ---
Also, the hardware configuration of the diagnostic system 100 is as shown in FIG. That is, diagnostic system 100 includes storage device 101 , memory 103 , CPU 104 (arithmetic device), input device 105 , output device 106 , and communication device 107 .

Among these, the storage device 101 is composed of an appropriate non-volatile storage element such as a hard disk drive.

Also, the memory 103 is composed of a volatile memory element such as a RAM.

Also, the CPU 104 is an arithmetic unit that reads the program 102 held in the storage device 101 into the memory 103 and executes it, performs overall control of the system itself, and performs various determinations, calculations, and control processes.

Also, the input device 105 is assumed to be a keyboard, a mouse, and a microphone that receive user's input operations.

Also, the output device 106 is assumed to be a display or a speaker that outputs the processing result of the CPU 104 in an appropriate form such as an image or sound.

The communication device 107 is a network interface card or the like that connects to the network 10 and performs communication processing with other devices such as the sensor unit 300 , the insurance company system 400 , and the financial institution system 500 .

--- Data configuration example ---
Next, information used by the diagnostic system 100 of this embodiment will be described. FIG. 3 shows an example of the sensor DB 125 in this embodiment.

The sensor DB 125 is a database in which observed values obtained by the diagnostic system 100 from the sensor unit 300, that is, measurement data 325 (FIG. 4) are accumulated.

The data structure is, for example, a set of records consisting of data such as a sensor ID that uniquely identifies the sensor unit 300 of the data resource, an observed event, and an observed value, with measurement date and time as a key.

Note that the measurement data 325 described above has the same configuration as the record of the sensor DB 125, as shown in FIG.

Also, FIG. 5 is a diagram showing a configuration example of the event DB 126 in this embodiment. The event DB 126 in this embodiment is a database that accumulates information on various events such as failures and accidents that occur in the plant 200 and maintenance work performed in the plant 200 .

Such information is, for example, input by the administrator or the like of the plant 200 by operating the input device 105, or a predetermined signal (corresponding to a failure or accident) transmitted from the sensor unit 300, which is used by the diagnostic system. 100 acquired, and so on.

The data structure is a set of records consisting of data such as event type, occurrence location, and cost required for response, with date and time of occurrence as a key.

Moreover, FIG. 6 is a figure which shows the structural example of operation DB127 in this embodiment. The operation DB 127 in this embodiment is a database that stores information about the operation details actually set and operated in the plant 200 .

The data structure is a set of records consisting of data such as target and content with target period as a key.

Moreover, FIG. 7 is a figure which shows the structural example of estimation result DB128 in this embodiment. The estimation result DB 128 in this embodiment is a database in which estimation results of failure probability transitions in the plant 200 are accumulated.

The data structure uses the device ID that uniquely identifies the device to be estimated as a key, and includes the maintenance content or operation content assumed for the device, the cost when the maintenance content or operation content is performed (maintenance implementation cost , failure cost, and accident cost), failure probability transition, and expected cost value.

Note that the failure probability transition is a mathematical expression representing a line segment representing the time transition of the failure probability, so in the example of FIG. 7, a file describing the mathematical expression is stored as a value.

Further, the expected cost value indicates the expected cost value for each month, such as one month or two months from the present time. The time elapsed in units of months may be assumed to be the most recent scheduled scheduled maintenance date to come next.

Moreover, this estimation result DB128 will be in a non-storage state of a record, when the diagnostic method of this embodiment is not implemented.

Also, FIG. 8 is a diagram showing a configuration example of the incentive variation reference DB 129 in this embodiment. The incentive fluctuation reference DB 129 in this embodiment sets a threshold value for fluctuation of insurance premiums and insurance money to be applied with respect to the insurance contract held by the operator of the plant 200 described above, with respect to the failure probability of the insurance object, that is, the maintenance object. This is a database accumulated as fluctuation reference values.

The data structure consists of data such as the policy number, which is the identification information of the insurance contract, as a key, the insurance name, the failure probability reference value that is the threshold for insurance premium fluctuation, and the failure probability reference value that is the threshold for insurance payment fluctuation. It is a set of records consisting of

Of these, the standard value of failure probability related to insurance premium fluctuation is set to “maintain” and “increase by 10%” for each condition, and the standard value of failure probability related to insurance payment fluctuation is set to “maintain” and “10% increase”. % reduction”, and an example in which each condition is defined. In the case of "maintenance", it indicates the conditions under which the insurance premium and insurance money at the time of contracting the insurance can be maintained. Moreover, in the case of "increase by 10%", it indicates a condition in which the insurance premium at the time of contracting the insurance is increased by 10%. In addition, in the case of "10% reduction", it indicates a condition that the insurance money at the time of contracting the insurance is reduced by 10%.

Also, FIG. 9 is a diagram showing a configuration example of the credit value DB 130 in this embodiment. The credit value DB 130 in this embodiment is a database that accumulates information on the credit value of the plant 200 . This credit value indicates the percentage of the total operating time of the plant 200 at which the probability of failure is equal to or less than a predetermined level. Also, the credit value is at least one of one calculated for the plant 200 as a whole and one calculated for each device included in the plant 200 .

The data structure is a set of records consisting of data such as the type of device, the period covered, and the credit value, using the device ID that uniquely identifies the target device as a key.

--- Flow example 1 ---
The actual procedure of the diagnostic method according to this embodiment will be described below with reference to the drawings. Various operations corresponding to the diagnostic method described below are realized by a program that the diagnostic system 100 reads out to the memory 103 and executes. These programs are composed of codes for performing various operations described below.

FIG. 10 is a diagram showing a flow example 1 of a diagnostic method according to this embodiment. In this case, first, the sensor unit 300 in the plant 200 transmits the measurement data 325 held regarding its own observation target to the diagnostic system 100 (s1).

On the other hand, the diagnostic system 100 receives measurement data 325 from the sensor unit 300 (s2).

Further, the diagnostic system 100 generates a record including the measurement data 325 obtained s2d (s3), stores this in the sensor DB 125 (s4), and terminates the process. The sensor DB 125 is generated by the processing up to this point.

--- Flow example 2 ---
FIG. 11 is a diagram showing a flow example 2 of the diagnostic method according to this embodiment. Next, an event DB generation flow will be described.

In this case, the sensor unit 300 of the plant 200 transmits the measurement data 325 to the diagnostic system 100 (s5).

On the other hand, the diagnostic system 100 compares the measurement data 325 obtained from the sensor unit 300 described above with a predetermined determination rule to determine whether an event has occurred (s6).

The above-described determination rule is, for example, a range of observed values at normal time, a range at failure time, and a range at time of accident, which are predetermined for each observation event, and the measurement data 325 is within any one of these ranges. It is possible to assume a form in which the event occurrence status related to the observation event is determined based on whether or not it belongs.

As a result of the determination described above, if it is determined that the operation is normal (s7: N), the diagnostic system 100 terminates the process.

On the other hand, if the occurrence of a failure or accident event is specified as a result of the above determination (s7: Y), the diagnosis system 100 determines the date and time of occurrence, which is the measurement date and time indicated by the measurement data 325, and the event indicated by the determination result of the event. A record containing each value of the type and the location based on the observed event indicated by the measurement data 325 is generated, stored in the event DB 126 (s8), and the process is terminated.

The event DB 126 is generated by the processing up to this point.

--- Flow example 3 ---
FIG. 12 is a diagram showing a flow example 3 of the diagnostic method according to this embodiment. Next, a flow for estimating the failure probability transition in the plant 200 will be described.

In this case, the diagnostic system 100 applies the observation value indicated by the sensor DB 125 and the maintenance history or operation details indicated by the event DB 126 to the machine learning algorithm 110 as input, and observes the corresponding event by the operation content and the operation performed by it. The correlation between the content of fluctuation in the value, or the correlation between the content of maintenance indicated by the above-mentioned maintenance history and the content of change in the observed value of the event due to the implementation of maintenance with the content of maintenance is specified (s10). As the correlation specified here, for example, when "maintenance A" is performed as maintenance content, the observation event "shaft temperature" of the sensor "S1" is "5% down".

Subsequently, the diagnostic system 100 applies the correlation information obtained in s10 to the failure probability evaluation engine 111, and performs "maintenance A", "maintenance B ”, and when operation is performed with multiple types of operation contents such as “operation rate: 75%” and “operation rate: 70%”, at least In either case, the transition of the failure probability after the above-described predetermined time in the plant 200 is estimated (s11).

The above-described failure probability evaluation engine 111 has a failure probability evaluation algorithm including explanatory variable formulas defined in advance regarding the effects of observation events in the sensor unit 300 on the failure probability of the plant 200 or its constituent equipment. Applicable.

The above-mentioned explanatory variable formula defines the failure probability Y by a polynomial expression in which a predetermined weighting coefficient (example: a to c) is given to the variable (example: X to Z) that inputs the observed value for each observation event. =aX+bY+cZ can be assumed.

Note that the explanatory variable formula described above is a formula for the failure probability when the variation in the lifetime (which can also be said to be the probability of failure occurrence) indicated by a predetermined learned lifetime model is minimized. This learned life model is a failure rate function that expresses the distribution of failure occurrence probability over time (eg, normal distribution).

This failure rate function is, for example, a function obtained by statistical processing based on the failure history and maintenance history (information on failure events and maintenance events in the event DB 126) of the plant 200, which is a maintenance object.

In this case, the failure probability evaluation engine 111 of the diagnostic system 100 pre-stores, for example, the time corresponding to the current time (eg, the elapsed time from a predetermined time to the current time) before performing maintenance work for each maintenance content. A failure probability Y1 is obtained by substituting the latest observed value of each observed event obtained at the present time into the explanatory variable formula.

In addition, the failure probability evaluation engine 111 of the diagnostic system 100 identifies, based on the above-described correlation, the observed value fluctuations in each observation event when maintenance work is performed for each maintenance content, for example. That is, the observed value of each observed event after maintenance work is estimated. Here, it is assumed that such fluctuations in observed values occur one month after maintenance work is performed.

Subsequently, the failure probability evaluation engine 111 of the diagnostic system 100 adds the above estimated observation value to the explanatory variable formula held in advance regarding the time corresponding to, for example, one month from the present time when the maintenance work is performed with each of the maintenance contents described above. (fluctuated due to maintenance work) is substituted to obtain the failure probability Y2 one month from the present time.

The diagnostic system 100 can estimate the transition of the failure probability by sequentially executing such estimation of the failure probability for each period.

Subsequently, the diagnostic system 100 performs maintenance for each of a plurality of types of maintenance contents such as "maintenance A" and "maintenance B" at predetermined times, such as one month and two months from the current time obtained in s11. transition of the failure probability in the plant 200 in at least one of the following cases: 13) is displayed on, for example, the display device 106 (s12), and the process ends.

In addition, as illustrated in the screen 1000 of FIG. 13, the user can also specify each condition that defines the details of the operation when estimating the transition of the failure probability. Therefore, diagnostic system 100 displays interface 1001 on screen 1000 in order to accept this user designation.

This interface 1001 accepts items such as the operation rate of the plant 200, which is a maintenance object, the amount of materials used, and the attributes of the component parts, namely, regular/non-regular parts, as specified by the user.

In this case, the diagnostic system 100 similarly executes each step of the above-described flow when the operation is performed under the operation content defined under the user-specified conditions, and after the maintenance work etc. in the plant 200 , the transition of the failure probability is estimated.

--- Flow example 4 ---
FIG. 14 is a diagram showing a flow example 4 of the diagnostic method according to this embodiment. Next, the calculation flow of the expected cost value will be explained.

In this case, the diagnosis system 100 calculates the cost of performing maintenance on the plant 200 based on the maintenance costs indicated by the maintenance history in the event DB 126 and the costs of failures and accidents. , and each operation content, a table is generated that defines the maintenance implementation cost, the failure cost, and the accident cost in at least one of the plant 200 (s15).

Specifically, the average or median cost during maintenance, the average or median cost at the time of failure, and the average or median cost at the time of accident, indicated by the maintenance history, are determined for each device or device. It is calculated for the plant 200, and this calculated value is set in each cost column of the estimation result DB 128.

Subsequently, the diagnostic system 100 multiplies the failure probability at each time indicated by the transition of the failure probability obtained in the flow of FIG. When maintenance is performed for each maintenance content and when operation is performed for each operation content, the cost at the time of performing maintenance in at least one of the cases is added to the above multiplication processing result, An expected cost value is calculated (s16).

It should be noted that the diagnostic system 100 calculates the expected cost value described above for each piece of equipment in the plant 200 .

Subsequently, the diagnosis system 100 causes the display device 106 to display the expected cost value obtained in s16 (screen 1100 in FIG. 17) together with, for example, the transition of the failure probability (s17), and ends the process.

An example of a screen 1100 in FIG. 17 shows a mode in which changes in failure probabilities and expected cost values are displayed together with respect to “equipment A” and “equipment B” in the plant 200 .

--- Flow example 5 ---
FIG. 16 is a diagram showing a flow example 5 of a diagnostic method according to this embodiment. Next, the calculation flow of the future value of the plant 200, which is the object of maintenance, will be described.

Here, the diagnostic system 100 provides the plant 200 with useful life, production volume per unit time, downtime during maintenance, annual insurance premiums when a predetermined standard failure probability is maintained, and an insurance company for each maintenance implementation opportunity. It is assumed that the storage device 101 holds in advance information such as the insurance money paid from the insurance company.

In this case, the diagnostic system 100 accepts user designations for maintenance content scheduled to be performed for the plant 200 and failure probabilities triggered by the maintenance content by the input device 105 (s20).

Subsequently, the diagnosis system 100 counts the frequency of failure probabilities specified by the user in s20 above, in transition of the failure probability estimated in the flow example of FIG. is multiplied by the service life described above to calculate the number of times maintenance is performed (s21). In addition, the diagnostic system 100 multiplies the downtime during the maintenance implementation specified by the user in s20 by the number of times of maintenance implementation obtained in s21 from the remaining operating time from the present time to the above-mentioned useful life. The value is subtracted to calculate the total operating time (s22).

Further, the diagnostic system 100 multiplies the above-mentioned production amount per unit time by this total operating time to calculate the total production amount (s23).

Further, the diagnostic system 100 calculates the total maintenance cost by multiplying the above-mentioned maintenance implementation cost by the number of maintenance implementation times obtained in s21 (s24).

Further, the diagnostic system 100 multiplies the above annual premium by the above service life to calculate the total premium paid (s25).

Further, the diagnosis system 100 calculates the total amount of insurance money by multiplying the above-mentioned insurance money for each maintenance execution opportunity by the number of maintenance execution times obtained in s21 (s26).

Subsequently, the diagnostic system 100 subtracts the total maintenance cost and the total insurance premium paid in s24 from the total production volume obtained in s23, and adds the total insurance money obtained in s26 to the result of this subtraction. By adding, the future value of the plant 200 is calculated (s27).

Also, the diagnostic system 100 displays this future value on the display device 106 or transmits it to the insurance company system 400 and financial institution system 500 (s28), and ends the process.

--- Flow example 6 ---
FIG. 17 is a diagram showing a flow example 6 of the diagnostic method according to this embodiment. Next, the credit value calculation flow will be described.

In this case, the diagnosis system 100 determines that the failure probability within the total operating time is below a predetermined level based on the total operating time obtained in the flow of FIG. 16 and the transition of the failure probability obtained in the flow of FIG. (Example: 10% or less) is calculated as the credit value of the maintenance object (s30). Specifically, it is assumed that the credit score is calculated by the calculation formula shown in FIG.

Also, the diagnostic system 100 displays the credit value obtained in s30 on the display device 106 or transmits it to the insurance company system 400 and the financial institution system 500 (s31), and ends the process.

Diagnosis system 100 refers to incentive fluctuation standard DB 129 (FIG. 8) regarding insurance contracted for plant 200, and determines annual insurance payable to the insurance company when plant 200 maintains a predetermined standard failure probability. and the insurance money paid by the insurance company for each maintenance performance opportunity for the plant 200 is extracted, and based on this information, an incentive fluctuation line (Fig. 18 It is preferable to display line segments 1201 and 1202 on the screen 1200 of .

An incentive fluctuation line 1201 in FIG. 18 indicates a reference value of failure probability related to insurance premium fluctuation that "maintains" the insurance premium and the insurance money in the current state.

In addition, the incentive fluctuation line 1202 corresponds to the reference value of the probability of failure related to the fluctuation of the insurance premium, which increases the insurance premium by 10% from the current level, and the reference value of the probability of failure related to the fluctuation of the insurance premium to 10% from the current level. % reduction” is shown.

According to this, the person in charge of operation and maintenance of the plant 200, which is the object of maintenance, is instructed to perform maintenance work at a suitable timing and frequency, set operation details, etc. from the viewpoint of insurance premiums and insurance claims. You can clearly present your needs. It can be expected that this will lead to an increase in conservative awareness.

According to the diagnostic system and diagnostic method of the present embodiment, the history of various events such as maintenance work, operation settings, failures, etc. in a plant etc., and the sensor data related to the relevant period are used as inputs to perform the maintenance work and the operation. Using machine learning, it is possible to estimate the relationship with the transition of sensor data associated with this and present it to the user.

In addition, by applying these relationships to a predetermined failure probability evaluation system, it is possible to determine how the failure probability will change in the future and what costs will be required for maintenance and failures, etc., depending on the selection of maintenance work and operation methods. It is possible to simulate whether the

On the user side, it is possible to easily recognize transitions in failure probability and fluctuations in costs for each of multiple maintenance and operation scenarios, and use this as a basis for making decisions regarding the timing and content of maintenance work. This can lead to a transition from TBM to CBM (Condition Based Maintenance) for users who maintain and manage plants, etc. As a result, maintenance costs can be reduced and optimized.

In addition, since the transition of the above-mentioned failure probability can be a factor of variation in insurance premiums and insurance money in the insurance contract related to the insured object, by presenting the fluctuation criteria of the insurance premium and insurance money related to the failure probability to the user, It is expected to improve and maintain motivation for maintenance work in

In addition, based on the transition of the failure probability described above, it is also possible to calculate the value of the plant, etc. to be maintained, present it to insurance companies and banks, etc., and use it for insurance product design work and credit work for loan projects. It becomes possible.

That is, it is possible to provide suitable information for making decisions regarding the planning and execution of maintenance work or the value of maintenance objects.

At least the following will be clarified by the description of this specification. That is, in the diagnostic system of the present embodiment, the storage device further holds the operation history of the maintenance object, and the arithmetic device inputs the observation value and at least one of the maintenance history and the operation history. As applied to a predetermined machine learning algorithm, at least one of the operation content indicated by the operation history or the maintenance content indicated by the maintenance history, and at least one of operation implementation with the operation content or maintenance implementation with the maintenance content It is also possible to specify the correlation between the observed value of the event and the variation content of the event.

According to this, it is possible to identify the correlation of fluctuations in observed values such as sensor data based on the influence of the operation details of the plant or the like, in addition to the maintenance work on the plant or the like. As a result, it becomes possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the computing device is based on a failure probability evaluation algorithm including an explanatory variable formula defined in advance regarding the effect of the event on the failure probability of the maintenance object, and the correlation. and estimating the transition of the failure probability of the maintenance object after the predetermined period of time when maintenance is performed for each of the plurality of maintenance contents at the predetermined period of time.

According to this, it is possible to more specifically identify the influence of maintenance work and operation details on the maintenance object on fluctuations in observed values in the form of changes in the failure probability of the maintenance object. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the computing device performs maintenance for each of the one or more maintenance contents at the predetermined time based on the explanatory variable expression and the correlation, and It is also possible to estimate the transition of the failure probability of the maintenance object at least after the predetermined period in at least one of the cases where the operation is carried out in each of one or more operation contents.

According to this, it is possible to estimate the transition of the failure probability in a form that can take into account the influence of the operation details of the maintenance target in addition to the maintenance work on the maintenance target. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, when estimating the transition of the failure probability, the arithmetic device receives user designation of a predetermined condition that defines the operation content for each of the one or more operation details, and the condition at least after the predetermined period of time in the maintenance object when the operation under the operation content defined in the above is performed at the predetermined period of time.

According to this, it becomes possible to specify the transition of the failure probability in a form in which the conditions of the operation details are specified in detail. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the computing device receives at least one of the operation rate of the maintenance object, materials used, and attributes of constituent parts as the user designation of the predetermined condition. good too.

According to this, it becomes possible to specify the transition of the failure probability in a form in which more specific conditions of the operation content are specified. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the storage device further retains information on each cost required when past failures and accidents occurred in the maintenance object, and the arithmetic device stores the maintenance history and the cost of performing maintenance indicated by and each cost of the failure and the accident, when maintenance is performed on the maintenance object according to each of the one or more maintenance contents, and the one Alternatively, a table is generated that defines the cost at the time of maintenance, the cost at the time of failure, and the cost at the time of accident in at least one of the maintenance objects when operation is performed for each of a plurality of operation contents. good too.

According to this, it becomes possible to specify various costs that may vary depending on maintenance work and operation contents. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the arithmetic unit multiplies the failure probability at each period indicated by the transition of the failure probability by the failure cost defined by the table, Alternatively, the cost at the time of performing maintenance in at least one of the cases where maintenance is performed for each of the plurality of maintenance contents, and when operation is performed for each of the one or more operation contents, is the result of the multiplication process. and calculating the expected cost value of the maintenance object.

According to this, it is possible to specify the expected cost value that may vary depending on the maintenance work and operation details. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the computing device may calculate the expected cost values for a plurality of maintenance objects.

According to this, it is possible to specify the expected cost value described above, which may differ for each maintenance object and may also vary depending on maintenance work and operation details. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the storage device stores the service life, the production volume per unit time, the downtime during maintenance, and the annual insurance premium when a predetermined standard failure probability is maintained for the maintenance object. , and insurance money to be paid by the insurance company for each maintenance implementation opportunity, and the arithmetic unit stores maintenance details scheduled to be performed on the maintenance object, and a trigger for performing maintenance based on the maintenance details. and counting the frequency of the failure probability specified by the user in the transition of the estimated failure probability, and multiplying the counted frequency by the service life. and subtracting the value obtained by multiplying the downtime during the maintenance implementation according to the maintenance content designated by the user by the maintenance implementation frequency from the remaining operating time until the useful life. a process of calculating the total operating time, multiplying the production amount per unit time by the total operating time, and calculating the total production amount; a process of multiplying the annual premium by the useful life to calculate the total premium paid; and a process of multiplying the insurance money for each maintenance performance opportunity by the number of maintenance performances to obtain the total insurance money and calculating the future value of the object to be maintained by subtracting the total maintenance cost and the total insurance premium paid from the total production volume and adding the total amount of insurance money to the result of the subtraction. and may be further executed.

According to this, it becomes possible to identify the future value of the maintenance object under predetermined conditions such as user-specified maintenance contents and operation contents, and by extension, provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of the maintenance object. It becomes possible.

Further, in the diagnostic system of the present embodiment, the computing device calculates the percentage of the total operating time at which the failure probability is equal to or less than a predetermined level based on the total operating time and the transition of the estimated failure probability. It may be calculated as the credit value of the object.

According to this, for insurance companies that need to evaluate the value of the maintenance target as an insured property, or financial institutions that consider the maintenance target as collateral, for example, as movable property and perform credit screening, etc. It is possible to identify and present the value of the object from the viewpoint of the ability to continuously produce goods as a credit value. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the storage device holds observation values of a predetermined event regarding the maintenance target, maintenance history regarding the maintenance target, and operation history of the maintenance target, and the computing device includes the Observed values and at least one of the maintenance history and the operation history are applied to a predetermined machine learning algorithm as input, and at least one of the operation content indicated by the operation history or the maintenance content indicated by the maintenance history and the operation Identify the correlation between the observed value variation of the event and the content of the change due to at least one of the operation performed under the content and the maintenance performed under the maintenance content, and the effect of the event on the failure probability of the maintenance object Based on a failure probability evaluation algorithm including a predetermined explanatory variable expression and the correlation, at least the predetermined time for the maintenance object when maintenance is performed for each of the plurality of maintenance contents at the predetermined time. It is also possible to estimate the subsequent transition of the failure probability, and display the information of the estimated transition of the failure probability in a graph as the information of the failure probability transition.

According to this, it is possible to visually clearly indicate the transition of the failure probability in the maintenance object to the person in charge of operation and maintenance of the plant or the like, which is the maintenance object, or to the person in charge of the financial institution or the insurance company. It becomes possible. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, when estimating the transition of the failure probability, the arithmetic device receives user designation of a predetermined condition that defines the operation content for each of the one or more operation details, and the condition at least after the predetermined period of time in the maintenance object when the operation under the operation content defined in the above is performed at the predetermined period of time.

According to this, it is possible to specify the transition of the failure probability in a form in which the conditions of the operation details are specified in detail, and visually present this to the person in charge described above. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

Further, in the diagnostic system of the present embodiment, the computing device receives at least one of the operation rate of the maintenance object, materials used, and attributes of constituent parts as the user designation of the predetermined condition. good too.

According to this, it becomes possible to specify the transition of the failure probability in a form specifying more specific conditions of the operation content, and visually present it to the person in charge described above. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

In addition, in the diagnostic system of the present embodiment, with respect to the insurance contracted for the maintenance object, the annual insurance premium to be paid to the insurance company and the maintenance object when the maintenance object maintains a predetermined standard failure probability insurance money paid by an insurance company for each opportunity to perform maintenance on the object, wherein the computing device stores the annual insurance premium when graphically displaying the estimated information of the failure probability transition. and based on information on at least one of the insurance money, the standard of the failure probability, which is a threshold for fluctuation of the annual insurance premium and the insurance money, is displayed in the graph display as an incentive fluctuation line of the insurance. Yes, you can.

According to this, it is possible to clearly present the necessity of performing maintenance work at a suitable timing and frequency, setting operation details, etc., to a person in charge of operation and maintenance of a plant or the like, which is an object to be maintained. It can be expected that this will lead to an increase in conservative awareness. As a result, it is possible to provide more suitable judgment materials regarding the planning and execution of maintenance work or the value of maintenance objects.

10 network 100 diagnostic system 101 storage device 102 program 103 memory 104 CPU (arithmetic unit)
105 Input device 106 Output device 107 Communication device 110 Machine learning engine 111 Failure probability evaluation engine 125 Sensor DB
126 event database
127 Operation DB
128 Estimation result DB
129 Incentive Fluctuation Criteria DB
130 Trust value DB
200 plants (maintenance target)
300 sensor unit 325 measurement data 400 insurance company system 500 financial institution system

Claims (5)

Annual insurance premiums payable to an insurance company and the insurance company for each opportunity to perform maintenance on the maintenance object when a predetermined standard failure probability is maintained in the maintenance object with respect to the insurance contracted for the maintenance object a storage device holding information of at least one of: insurance claims paid from
When the maintenance object is maintained at a predetermined time according to each of a plurality of maintenance contents and is operated according to a plurality of operation contents, at least after the predetermined time at the maintenance object When displaying estimated failure probability transition information in a graph, based on information on at least one of the annual insurance premium and the insurance money, the criteria for the failure probability that serve as thresholds for fluctuations in the annual insurance premium and the insurance money are as follows: The above-mentioned graph display as incentive fluctuation lines of the insurance respectively showing the insurance premium and the insurance money to be maintained at the current state, the insurance premium to increase by a certain percentage from the current situation, and the insurance premium to decrease by a certain percentage from the current situation. A computing device displayed in the
A diagnostic system comprising: The storage device
holding an observed value of a predetermined event related to the maintenance object, a maintenance history related to the maintenance object, and an operation history of the maintenance object;
The computing device is
The observation value and at least one of the maintenance history and the operation history are applied to a predetermined machine learning algorithm as input, and at least one of the operation content indicated by the operation history and the maintenance content indicated by the maintenance history is obtained. Identifying the correlation between the variation in the observed value of the event due to at least one of the operation performed under the operation content and the maintenance performed under the maintenance content,
Maintenance for each of the plurality of maintenance contents at the predetermined time based on the failure probability evaluation algorithm including the explanatory variable formula defined in advance regarding the effect of the event on the failure probability of the maintenance object and the correlation. Estimating the transition of the failure probability at least after the predetermined time in the maintenance object when implemented,
2. The diagnostic system of claim 1 , wherein: The computing device is
When estimating the transition of the failure probability, with respect to each of the one or more operation contents, a user specification of a predetermined condition that defines the operation contents is accepted, and the operation is performed at the predetermined time according to the operation contents defined by the conditions. estimating the transition of the failure probability at least after the predetermined time in the maintenance object when
3. The diagnostic system of claim 2 , wherein: The computing device is
As the user designation of the predetermined condition, at least one of the operation rate of the maintenance object, the materials used, and the attributes of the constituent parts is accepted.
4. The diagnostic system of claim 3 , wherein: Information processing system
Annual insurance premiums payable to an insurance company and the insurance company for each opportunity to perform maintenance on the maintenance object when a predetermined standard failure probability is maintained in the maintenance object with respect to the insurance contracted for the maintenance object a storage device that holds information on at least one of insurance claims paid from
When the maintenance object is maintained at a predetermined time according to each of a plurality of maintenance contents and is operated according to a plurality of operation contents, at least after the predetermined time at the maintenance object When displaying estimated failure probability transition information in a graph, based on information on at least one of the annual insurance premium and the insurance money, the criteria for the failure probability that serve as thresholds for fluctuations in the annual insurance premium and the insurance money are as follows: The above-mentioned graph display as incentive fluctuation lines of the insurance respectively showing the insurance premium and the insurance money to be maintained at the current state, the insurance premium to increase by a certain percentage from the current situation, and the insurance premium to decrease by a certain percentage from the current situation. to display in
A diagnostic method characterized by:

Images