CN109074528B - Formulation auxiliary system and formulation auxiliary method for operation maintenance knowledge information - Google Patents

Abstract

So that knowledge information related to operation and maintenance can be efficiently extracted from the existing system. The formulation assistance system (1) assists formulation of knowledge information relating to operation and maintenance using information extracted from an existing system (4). The formulation support system includes: an information acquisition unit (F10) that acquires predetermined information relating to an existing system (4); a key element extraction unit (F12) that extracts key element information that is a key element relating to logical judgment of operation and maintenance by analyzing the acquired predetermined information; and an operation and maintenance knowledge information extraction unit (F14) for extracting and storing operation and maintenance knowledge information, which is knowledge information relating to operation and maintenance, by performing simulation analysis on the extracted key element information.

Description

Formulation auxiliary system and formulation auxiliary method for operation maintenance knowledge information

Technical Field

The invention relates to an auxiliary system and an auxiliary method for formulating operation and maintenance knowledge information.

Background

Conventionally, in various plants such as power plants, iron works, and chemical plants, a specific management company (operator) has been responsible for operation and maintenance for years, and attempts have been made to improve the quality of incorporated equipment and the like and to improve operation and maintenance techniques. Management companies that operate factories over the years accumulate intrinsic knowledge and operation methods based on experience.

However, in recent years, there is a tendency that reduction in construction cost or operation cost of a plant is sought by appropriately combining products purchased from a plurality of suppliers. Neither the supplier nor the product is limited, and sometimes the supplier or the product following the customer's desire is selected. Previously, products (in particular, for example, specials, specialties for a specific plant) provided by suppliers having high reliability and abundant practical results are used in a large number of plants. However, in recent years, customers desire to construct an inexpensive factory by combining inexpensive general-purpose products purchased from a variety of suppliers.

When a new plant is constructed of the same products as an existing plant and is operated by the same management company as the management company for operation and maintenance of the existing plant, the know-how of the operation and maintenance technique developed in the existing plant can be applied to the new plant almost as it is.

However, when a new plant is produced inexpensively by combining products of other companies or general-purpose products which are not actually successful, or when a new plant is operated by a newly added management company, it is difficult to apply the know-how of the operation and maintenance technique possessed by the existing plant to the new plant.

This is because: most of the know-how to run maintenance techniques does not become explicit knowledge, but probably implicit knowledge. In the case where a recipe for operation maintenance technology in an existing plant cannot be used for a new plant, it is difficult to stably operate or maintain the new plant. However, it is difficult to extract and make explicit knowledge of a recipe of operation and maintenance techniques accumulated in a conventional plant, and it is difficult to predict the cost.

Here, patent document 1 as a conventional technique detects an abnormality using an operating state such as an operating time of a plant and output signals of a plurality of sensors provided in the plant. In patent document 1, the diagnostic accuracy is improved by associating detected abnormalities with countermeasures based on past countermeasures such as work history and replacement part information.

Documents of the prior art

Patent document

Patent document 1: japanese unexamined patent publication No. 2013-41448

Disclosure of Invention

Problems to be solved by the invention

According to the conventional technique of patent document 1, it is possible to automate maintenance work based on the experience or intuition of an operator, and it is possible to make a recipe of an operation maintenance technique, which is implicit knowledge, explicit knowledge. However, patent document 1 is a technique as follows: on the premise that the monitoring object and the operation object are clear, a predetermined command is given to the operation object when the monitoring object satisfies a predetermined condition. Therefore, the present invention cannot be applied to a plant in which a monitoring object or an operation object is different. This is because: what should be monitored and what should be handled is inherently ambiguous.

The problem is solved more and more difficult when a plurality of collaboration enterprises construct a system by combining hardware and software provided by a large number of manufacturers.

The present invention has been made in view of the above-described problems, and an object of the present invention is to provide an operation and maintenance knowledge information preparation support system capable of efficiently extracting knowledge information related to operation and maintenance from a conventional system.

Means for solving the problems

In order to solve the above problems, an operation maintenance knowledge information formulation support system according to the present invention supports formulation of knowledge information related to operation maintenance using information extracted from an existing system, and includes: an information acquisition unit that acquires predetermined information relating to an existing system; a key element extraction unit that extracts key element information that is a key element relating to logical judgment of operation and maintenance by analyzing the acquired predetermined information; and an operation and maintenance knowledge information extraction unit that extracts and stores operation and maintenance knowledge information, which is knowledge information related to operation and maintenance, by performing simulation analysis on the extracted key element information.

Effects of the invention

According to the present invention, the operation and maintenance knowledge information can be extracted by extracting key element information related to the logical judgment of the operation and maintenance from the existing system and performing simulation analysis.

Drawings

Fig. 1 is an explanatory diagram showing an overall outline of the present embodiment.

Fig. 2 is a block diagram of a plant operation knowledge (knowledge) preparation support device.

Fig. 3 is a block diagram of a client terminal and an operation and maintenance terminal.

Fig. 4 is an example of system log data (input data).

Fig. 5 is an example of system log data (output data).

Fig. 6 is an example of job log data.

Fig. 7 is an example of external data.

Fig. 8 is an example of key element data.

Fig. 9 is an example of knowledge data.

Fig. 10 is a flowchart of knowledge formulation assistance processing.

Fig. 11 relates to a second embodiment, and is an example of log data.

Fig. 12 is an example of key element data.

Fig. 13 is a flowchart showing a process of searching for a knowledge satisfaction condition according to the third embodiment.

Fig. 14 relates to the fourth embodiment, and is a flowchart of a process of collecting screen operation logs.

Fig. 15 is an explanatory diagram of a case where knowledge extracted from an existing plant is applied to a new plant, relating to the fifth embodiment.

Fig. 16 is an explanatory diagram showing a case where knowledge extracted from a conventional plant is classified for each customer policy according to the sixth embodiment.

Detailed Description

The operation and maintenance knowledge information generation support system according to the present embodiment has a function of analyzing a monitoring record and a control record related to operation and maintenance of a system such as a plant, a function of classifying an analysis result for each logical judgment or action for performing control, a function of changing a frequency related to monitoring or control according to the classification result, and a function of performing simulation of operation and maintenance of the plant based on a condition similar to the analysis result and a frequency after the change, and determines a condition of the frequency related to monitoring or control necessary for the logical judgment or action according to the simulation result.

In the present embodiment, the monitoring data and the command data are analyzed by using a big data analysis technique based on 3 types of operation records, i.e., monitoring data (sensor data) related to operation and maintenance of the plant, logic judgment, and command data. Thus, in the present embodiment, the mechanical characteristic amount, specifically, the specific monitoring data and the command data, which are linked to the logical judgment can be extracted. In the present embodiment, these monitoring data, command data, and logic determination (detection of an abnormality sign, etc.) are stored as knowledge of operation and maintenance. By applying the knowledge extracted from the existing plant to the new plant, the convenience or reliability of the operation and maintenance of the new plant can be improved at low cost.

As a technique for extracting knowledge from the key element data, for example, Adaptive Resonance Theory (ART) can be used.

In the present embodiment, the frequency of the extracted feature values is changed for each logical judgment, so that the simulator confirms that the logical judgment can be performed, and determines the specification of the feature values. For example, it is found by simulation analysis that the abnormality sign can be detected when the number of times a signal of a certain sensor indicates a value within a predetermined range becomes a predetermined number of times. In the present embodiment, the specification of the feature amount for logical judgment of activation, such as the value and the number of times of the sensor signal, can be determined.

According to the present embodiment, operation and maintenance knowledge (recipe) buried as implicit knowledge in an existing plant can be automatically extracted and made explicit knowledge. Further, according to the present embodiment, the operation and maintenance knowledge that is explicit knowledge can be packaged and applied to the operation and maintenance of a new plant.

Fig. 1 shows an outline of the present embodiment. Fig. 1 shows an outline of the embodiment to the extent necessary for understanding and practicing the present invention, and the scope of the present invention is not limited to the structure shown in fig. 1.

The operation maintenance knowledge information preparation support system 1 is constituted by a computer device, and is connected to a client terminal 2 and an operation maintenance system 3. The preparation support system 1 realizes each function required as a preparation support system by executing a predetermined computer program by a microprocessor. Fig. 1 shows main functions F10, F12, F14, and the like among the functions F10 to F16 realized by the formulation support system 1.

The client terminal 2 is a computer terminal used by a user such as a system administrator, and inputs various data information such as log data to the formulation support system 1 or displays information from the formulation support system 1.

The operation and maintenance system 3 is a device for performing operation and maintenance of the existing system 4, which is a knowledge extraction target, and is a computer terminal. The operation and maintenance system 3 is referred to as an operation and maintenance terminal 3 in the embodiments described later. The operation and maintenance system 3 transmits, to the client terminal 2, monitoring data (also referred to as input data, sensor data, or acquisition data) acquired from the existing system 4 or instruction data (also referred to as output data or control data) given from the operation and maintenance system 3 to the existing system 4. In some cases, the data may be directly transmitted from the operation and maintenance system 3 to the formulation support system 1.

The conventional system 4 is configured as various plants such as a power plant, an iron works, a chemical plant, and a water supply and sewerage plant. The existing system 4 has at least one sensor 41 and a device 42.

Examples of the sensor 41 include a temperature sensor, a pressure sensor, a flow sensor, a liquid level sensor, a vibration detection sensor, a rotation sensor, an acoustic sensor, a flame detection sensor, an image sensor, a color sensor, a magnetic sensor, an ammeter, a voltmeter, a manual switch, a photoelectric switch, a mechanical limit switch, a keyboard switch, and a touch panel. In the device 42, there are, for example, a motor, a turbine, a cylinder, a solenoid, a valve, a pump, a heater, a boiler, a fan, and the like.

The operation and maintenance system 3 performs operation and maintenance of the existing system 4 based on a predetermined logical judgment (abnormality diagnosis and response thereof). Further, when a user such as an operator detects a sign of an abnormality from the dynamics of the signal of the predetermined sensor 41, the operation and maintenance system 3 gives an instruction to the predetermined device 42. This makes it possible to quickly respond to the detected sign of an abnormality and prevent the occurrence of an abnormality. The operation of the existing system 4 by the user is saved as a job record to the operation and maintenance system 3 and is also transmitted to the client terminal 2. Data input from the sensor 41 to the operation and maintenance system 3 and data given from the operation and maintenance system 3 to the device 42 are also transmitted to the client terminal 2.

The operation and maintenance knowledge formulation assistance system 1 extracts operation and maintenance knowledge (hereinafter, also referred to as knowledge or knowledge data) as "operation and maintenance knowledge information" by analyzing data related to the operation and maintenance of the existing system 4. The extracted operation and maintenance knowledge can be installed in the operation and maintenance system 5 in charge of the operation and maintenance of the new system 6.

The formulation support system 1 holds processing functions such as a data acquisition unit F10, a key element extraction unit F12, and a knowledge extraction unit F14, and record data T10-T13, key element data T13, and knowledge data T14. The detailed configuration of the support system 1 is described later with reference to fig. 2 and the like.

The data acquisition unit F10 corresponds to the "information acquisition unit". The data acquisition unit F10 acquires and stores log data T10-T12 as "predetermined information" from the client terminal 2 and/or the operation and maintenance system 3. The data acquisition unit F10 converts data having various data formats into a predetermined unified data format and stores the converted data. The data acquisition unit F10 can acquire log data periodically or aperiodically. For example, the data acquisition unit F10 can acquire and store log data at any one or more timings among a predetermined timing, when instructed from a system manager or the like, when some maintenance work is performed in the operation maintenance system 3, and when the configuration of the existing system 4 has changed.

The key element extraction unit F12 analyzes the log data, thereby extracting and storing data (key element data) T13 as key elements relating to logical judgment of operation and maintenance. The logical judgment of the operation and maintenance here is, for example, a logical judgment of the operation and maintenance such as a sign detection of an abnormality, a failure prediction, and the like. The logical judgment may include not only a mere judgment such as a warning detection but also actions such as "setting value change", "system stop", "route switching", and the like.

The key element data T13 as "key element information" is data extracted by performing large data analysis on the log data T10-T12, and is data considered to be closely related to logical judgment of operation and maintenance.

The knowledge extraction unit F14 obtains knowledge data as "operation and maintenance knowledge information" by performing simulation analysis on the key element data T13. The knowledge extraction unit F14 determines whether the key element data T13 is related to the logical judgment, and associates the related key element data with the logical judgment to generate and store knowledge data T14.

Further, the knowledge extraction unit F14 changes the generation condition of the input data among the key element data by the generation condition change unit F141. Thus, the knowledge extraction unit F14 checks whether or not the logical judgment corresponding to the key element data is executed regardless of the occurrence condition, and adds the occurrence condition to the knowledge data.

The knowledge data T14 thus generated automatically detects and makes explicit the implicit knowledge developed by the existing system 4 in the long-term operation and maintenance work. At least a part of the operation and maintenance recipe, which is hidden as a result of the experience or intuition of the operator, is made visible by the formulation of the auxiliary system 1, live for the operation and maintenance of the new system 6.

[ example 1 ]

The first embodiment will be described with reference to fig. 2 to 10. Fig. 2 is a configuration example of the entire system including the formulation support system 1 according to the present embodiment.

The overall system includes, for example, a plant operation and maintenance knowledge preparation support system (hereinafter referred to as a knowledge preparation support system) 1, a plurality of client terminals 2, and a plurality of operation and maintenance terminals 3, and these computer systems 1 to 3 are connected via a communication network CN 1.

The operation and maintenance terminal 3 for performing operation and maintenance of the plant is connected to the plurality of sensors 41 and the devices 42 via the communication network CN 2. These sensors 41 and devices 42 are included in the existing system (existing plant) 4 in fig. 1. Specifically, the operation maintenance terminal 3 is a computer terminal that is connected to the plant maintenance operation system outside the drawing and inputs instructions or setting values to the plant maintenance operation system. Hereinafter, for convenience of explanation, the plant maintenance operation system and the operation maintenance terminal 3 may be used without being particularly distinguished from each other.

The knowledge formulation support system 1 includes, for example, a CPU11, a memory (internal memory) 12, a communication unit 13, and a storage device 14. Various programs of the knowledge formulation assistance system 1 are stored in the storage device 14. The CPU11 reads and executes these computer programs as necessary via the memory 12. Thereby, the functions F10 to F16 are realized.

The communication unit 13 is a function for connecting to and communicating with the communication network CN 1. The knowledge formulation support system 1 communicates with the client terminal 2 and the operation and maintenance terminal 3 via the communication unit 13 and the communication network CN 1.

The storage device 14 is configured by, for example, a hard disk, a flash memory, or the like, and stores computer programs for realizing the functions F10 to F16 and data T10 to T14.

Examples of the computer programs stored in the storage device 14 include a data acquisition unit F10, a big data analysis unit F11, a key element extraction unit F12, a simulation analysis unit F13, a knowledge extraction unit F14, a screen control unit F15, and a communication control unit F16.

The data acquisition unit F10 is a function of acquiring logs of various data formats from the log T20 of the client terminal 2, and converting the format of the acquired data into a uniform format that can be handled by the knowledge formulation support system 1. In general, each client terminal 2 has a separate device or system, and the data formats are rarely the same. The data acquisition unit F10 is required to handle a plurality of data having different data formats. In addition, the function of standardizing the data format can be realized by commercially available software, and therefore, is not further mentioned in this embodiment.

The big data analysis unit F11 is a function of collecting items that can be related from 3 types of logs, for example, system log data T10, job log data T11, and external data T12. This function can be realized by a so-called data mining method, or by commercially available software, and therefore, a detailed description thereof is omitted.

The key element extraction unit F12 selects an element that becomes a key from among the candidates of the related items collected by the big data analysis unit F11, and stores the selected element in the key element data T13. The acquisition results are described later in fig. 8. The big data analysis unit F11 presents a plurality of related items in accordance with the magnitude of the relationship in general. For example, the top 3 related items may be mechanically selected as key elements, or the collection result may be displayed on a screen for the user to manually select key elements from the displayed result.

The simulation analyzer F13 is a function for confirming how the plant operation and maintenance system operates from various input data stored in the key element data T13. In the simulation analysis function F13, for example, a training simulator installed in a plant operation and maintenance system can be used. In a training simulator developed by an operator for training in an actual plant, data and preconditions used in an actual plant can be used as input sources, and the same result as that of an actual operation and maintenance operation can be output.

The knowledge extraction unit F14 checks whether or not a combination of input data and output data of the key elements enables a highly automatic logic determination function such as abnormality detection or detection of an abnormality sign to operate, based on the result of the simulation analysis unit F13. When the advanced and automatic logical judgment function is operated, the knowledge extraction unit F14 stores the input data and the output data of the key element data T13 as the knowledge data T14.

The screen control unit F15 creates a screen to be provided to the user by the knowledge base system 1, and displays the screen on the client terminal 2. The screen control unit F15 can display a part or all of the contents of the system log data T10, the job log data T11, the external data T12, and the key element data T13 on the screen, for example. Further, the screen controller F15 can display the analysis result of the big data analyzer F11 or the analysis result of the simulation analyzer F13 on the screen. The screen control unit F15 cooperates with the client execution unit F20 of the client terminal 2 to display the created screen on the client terminal 2. The screen control unit F15 can also detect and store an operation on the display screen.

The communication control unit F16 is a function of controlling the communication unit 13 and communicating with the client terminal 2 and the operation and maintenance terminal 3. The data transmission and reception between the knowledge management support system 1 and each of the terminals 2 and 3 include not only transmission and reception of log data but also transmission and reception of data used for screen display on, for example, a remote desktop. Further, for example, when the number of client terminals 2 increases, the communication control unit F16 can preferentially process data transmission and reception with a specific client terminal 2.

An example of the configuration of the client terminal 2 and the operation and maintenance terminal 3 will be described with reference to fig. 3. The structure of the client terminal 2 is explained first. The client terminal 2 includes, for example, a CPU 21, a memory (internal memory) 22, a communication unit 23, a storage unit 24, and a user interface unit (UI in the figure) 25.

The CPU 21 reads and executes the computer program stored in the storage unit 24 via the memory 22, thereby realizing the functions F20 to F22 required by the client terminal 2. The client terminal 2 is connected to the communication network CN1 via the communication unit 23, and communicates with the knowledge formulation support apparatus 1.

The storage unit 24 stores computer programs for realizing the client execution unit F20, the screen control unit F21, and the communication control unit F22, log data T20, and knowledge data T21.

The client execution unit F20 is connected to the knowledge formulation support system 1 as a server as a client, and has a function of exchanging information. The client execution unit F20 may be a dedicated program or a web browser.

The screen control unit F21 is a function for displaying the execution results of the respective functions of the knowledge preparation support apparatus 1 and the log data T20 and the knowledge data T21 held by the client terminal 2 on the user interface unit 25.

The user interface section 25 includes an information input section and an information output section. The information input unit is a function for a user to input an instruction or the like to the client terminal 2, and includes at least one of a keyboard, an instruction (pointing) device, a touch panel, an audio instruction device, and the like. The information output unit is a function for outputting information from the client terminal 2 to the user, and includes at least one of a display, a voice synthesizer, a printer, and the like.

The operation and maintenance terminal 3 includes a CPU31, a memory 32, a communication unit 33, a storage unit 34, and a user interface Unit (UI) 35.

The CPU31 reads and executes the computer program stored in the storage unit 34 via the memory 32, thereby realizing the functions F30 to F32 required for operating the maintenance terminal 3. The operation and maintenance terminal 3 is connected to the communication network CN1 via the communication unit 33, and communicates with the knowledge formulation support apparatus 1.

The storage unit 34 stores computer programs for realizing the operation maintenance unit F30, the screen control unit F31, and the communication control unit F32, log data T30, and knowledge data T31.

The operation and maintenance terminal 3 is connected to the communication network CN1 via the communication unit 33, and communicates with the knowledge formulation support apparatus 1. Further, the operation and maintenance terminal 3 can communicate with the plurality of sensors 41 and the plurality of devices 42 via the communication network CN 2. The operation and maintenance terminal 3 may be connected to the communication network CN2 via the communication unit 33, or may be connected to the communication network CN2 via another communication unit not shown.

The operation and maintenance unit F30 is a function for performing operation and maintenance of the plant 4 based on the knowledge data T31. The operation maintenance unit F30 performs highly automated logic determination such as abnormality detection or detection of abnormality prediction based on the monitoring data acquired from the sensor 41 and the data stored in the knowledge data T31. The operation maintenance unit F30 selects the command data in the knowledge data T31 according to the result of the logical judgment of the altitude, and instructs the device 42 with the selected command data. In this way, the operation and maintenance terminal 3 performs operation and maintenance of the plant 4 in real time based on the knowledge data T31 obtained from the actual result of the operation and maintenance and the state of the plant.

The screen control unit F31 is a function for displaying the execution result of the operation and maintenance unit F30, the log data T30 concerning the plant operation and maintenance included in the operation and maintenance terminal 3, and the acquired knowledge data T31 on the user interface unit 35.

Fig. 4 shows an example of system log data T10A related to input data among log data collected from the plant 4. The system log data of the input data is included in the system log data T10 shown in fig. 2.

The input data is data for acquiring the state of the plant 4, and may be referred to as sensor data, monitoring data, or acquisition data, for example. The data detected by the sensor 41 is input from the plant 4 side to the knowledge formulation support system 1, and is therefore referred to as input data (monitoring data and sensor data) in the present embodiment.

The data obtaining unit F10 converts input data in various data formats into data in a uniform format, thereby generating system log data T10A as input data.

The system log data (input data) T10A includes, for example, a date and time C100A indicating the date and time, an acquisition value C101A acquired by the sensor 41, a device name C102A indicating the device in which the sensor 41 is installed, and a sensor name C103A indicating the sensor name.

The acquired value C101A has a measured value C101a1 and a correction value C101a 2. The correction value C101a2 is a value obtained when the measurement value C101a1 is converted into a uniform format. If the measured value C101a1 is the same value as the value output by the sensor 41, the correction value C101a2 can be said to be a value obtained by unifying the units and the accuracy of the knowledge base assistance system 1 in order to calculate all the data in a unified manner.

Fig. 5 shows an example of the system log data T10B related to the output data among the system log data T10. The output data is data to be output to the device 42 included in the plant 4, and may also be referred to as command data or control data. The system log data T10B of the output data can also be referred to as drive instruction data. The driver is a device 42, and is an active mechanical element included in the plant 4.

The system log data (output data) T10B includes, for example, a date and time C100B indicating the date and time, a specified value C101B specifying a drive, a device name C102B indicating a device in which the drive is set, and a drive name C103B indicating the drive name.

The command value C101B has a specified value C101B1 and a correction value C101B 2. The correction value C101B2 is a value obtained by format-converting the specified value C101B 1. If the designated value C101B1 is the original value, the correction value C101B2 is a value obtained by unifying the units and styles in order for the knowledge base assistance system 1 to calculate all the data in a unified manner. Under the unified format, if, for example, "on switch" is shown as "1," then "off switch" is shown as "0. The actual command value differs depending on the specifications of the device 42. The actual command value according to the specification of the device 42 is stored to the specified value C101B 1.

Fig. 6 shows an example of the job log data T11. The job log data T11 is data of job records related to the operation and maintenance of the plant 4. The data obtaining unit F10 converts the various data formats into a unified format, thereby creating job log data T11.

The job log data T11 includes, for example, a date and time C110 indicating the date and time, a job ID C111 as an identifier indicating what kind of processing job has been performed, a job name C112 indicating the job content, and a device name C113 indicating which device 42 has been processed.

Fig. 7 shows an example of the external data T12. The external data T12 is data acquired from an external system such as a weather forecast system outside the knowledge support system 1. The data obtaining unit F10 converts various data formats into a unified format, thereby creating external data T12.

The external data T12 includes, for example, a date and time C120 indicating the date and time, an external data ID C121 as an identifier indicating the type of external data, a data name C122 indicating the content thereof, and a value C123 as the value thereof.

Examples of the external data include meteorological data, operation history data indicating a work day, a maintenance inspection day, and the like of a factory, and a predicted value output by a production prediction system.

Fig. 8 shows an example of the key element data T13. The key element data T13 is created by the key element extraction unit F12.

The key element data T13 includes, for example, an operation ID C130 indicating an identifier of a key element, acquired data C131 serving as a basis of logical judgment concerning operation or maintenance, and instruction data C132 indicating the content of an instruction to the device 42 as a result of the logical judgment.

The acquisition data C131 includes a device name C1311 indicating from which device 42 data is acquired, and a sensor name C1312 indicating from which sensor 41 data is acquired. In fig. 8, only 1 type of acquired data C131 is associated with one action ID C130, but a plurality of acquired data C131 may be stored in association with one action ID C130.

The command data C132 includes a device name C1321 indicating to which device 42 a command is given, and a control object C1322 to which element of the device 42 a control command is given. The control object C1322 can also be referred to as an element name or a drive name of the control object. In fig. 8, only 1 type of command data C132 is associated with one action ID C130, but a plurality of command data C132 may be associated with one action ID C130.

In fig. 8, the record having the action ID C130 of "001" is an example in which the big data analysis unit F11 has determined that the record has a relation by the mining process. In this case, "none" is stored in both the device name C1311 and the sensor name C1312.

In fig. 8, the record having the action ID C130 of "009" is another example in which the big data analysis unit F11 has determined that the record has a relation by the mining process. In this example, the sensor name C1312 of the acquisition data C131 is "vibration detection sensor", and the instruction data C132 is "external cooperation". That is, in this example, the device 42 is not directly instructed but instructed to an external system. For example, when it is considered that there is a sign of abnormality in the turbine vibration, the rotational speed of the turbine is not reduced, but an external maintenance management system (not shown) requests, for example, replacement of the equipment 42 or adjustment of the maintenance schedule.

In actual operation, since the operation of the device 42 is confirmed both before and after the command, the acquired data C131 is not "none" in principle, but is omitted here for the sake of simplicity of explanation.

Fig. 9 shows an example of the knowledge data T14. The knowledge data T14 is generated by the knowledge extraction unit F14.

The knowledge data T14 includes, for example, a knowledge ID C140, a logical judgment C141, a related key element ID C142, acquisition data C143, and instruction data C144.

The knowledge ID C140 is an identifier for determining knowledge related to the operation and maintenance of the plant 4. The logical judgment C141 is a judgment of the content to be the knowledge. Examples of the logical judgment include detection of an abnormality and detection of an abnormality sign. The associated key element ID C142 is an identifier for determining a key element associated with the knowledge determined by the knowledge ID C140.

The acquired data C143 is used to identify the type of input data (sensor data) that is a premise of knowledge. The acquired data C143 includes a device name C1431 for specifying the device in which the sensor is provided, and a sensor name C1432 for specifying the sensor.

The instruction data C144 is used to specify a destination of instruction data (output data, control data) as a result of application of knowledge, and the like. The instruction data C144 includes a device name C1441 for determining a device to give an instruction, and a control object C1442 for determining an object to be controlled by giving an instruction. The controlled object C1442 is an element name that becomes a controlled object as a result of knowledge among one or more controlled object elements included in the device.

Fig. 10 is a flowchart showing a process for assisting the formulation of the knowledge of the operation maintenance. The present process is performed by the knowledge formulation assistance system 1. The user can cause the knowledge formulation assistance system 1 to execute the present process at an appropriate timing.

As a rough distinction, the knowledge formulation support system 1 sequentially performs the following 2 types of processing. The 1 st process is a process of extracting data that becomes a key element (S10 to S15). The 2 nd process is a process of extracting and specifying knowledge data (S16 to S20).

The key element extraction process (S10 to S15) acquires and analyzes various data for extracting key element data, and stores the analysis results. The knowledge specification processing (S16 to S20) uses the extracted key element data to confirm whether or not the logical judgment function of the altitude automatically operates, and stores the data as knowledge data in which the confirmed key element data and the like are specified. Whether the key element data automatically performs the logical judgment of the height can be confirmed by the simulation processing.

First, the data obtaining unit F10 obtains data necessary for generating knowledge data from the log data T20 stored in each client terminal 2 (S10), and standardizes the format of the obtained data (S11). That is, the data obtaining unit F10 classifies the data collected from each client terminal 2 into the system log data, the job log, and the external data, unifies the formats of the classified data, and stores the unified data in the system log data T10, the job log data T11, and the external data T12 (S11).

The big data analysis unit F11 reads out data from the system log data T10, the job log data T11, and the external data T12, and performs data mining processing on the read-out data to perform analysis (S12). The analysis result thereof is displayed in the user interface section 25 of the client terminal 2 (S13).

The step S13 of displaying the analysis result is executed by the key element extraction unit F12, for example. The key element extraction unit F12 displays the analysis result output by the big data analysis unit F11 on the user interface unit 25 of the client terminal 2 via the screen control unit F15. The user can confirm the big data analysis result. In addition, step S13 may be omitted.

The key element extraction unit F12 extracts candidate data that can be key element data based on the data extracted in the big data analysis processing (S12), and stores the candidate data in the key element data T13 (S14).

When selecting a candidate for key element data from the result of the big data analysis processing, the judgment of the user can be added. That is, the user may select one or more pieces of data that are candidates for the key element data from the screen displayed in step S13. Alternatively, a predetermined number of data items in the results of the big data analysis may be automatically selected as candidates for the key element data.

The key element extraction unit F12 determines whether or not all data that are candidates for the key element data are extracted from the result of the big data analysis processing (S15). When all the candidates of the key element data have been extracted (yes in S15), the key element extraction unit F12 proceeds to the next step S16, and when not (no in S15), it returns to step S13 to determine another analysis result. The above is the key element extraction processing. Next, knowledge determination processing is performed.

The knowledge specifying process includes a step of creating input data for simulation (S16), a step of performing simulation analysis (S17), a step of determining whether or not to execute an automatic logical determination of a level such as abnormality detection (S18), a step of storing key element data (a set of input data and output data) and the logical determination in association with each other as knowledge data (S19), and a step of determining whether or not all the key element data have been analyzed (S20).

In the step of creating input data for simulation (S16), the input data (sensor data, monitoring data, acquisition data) among the data stored in the key element data T13 is processed as input data for simulation analysis processing.

In the step of performing the simulation analysis (S17), the simulation analyzer F13 analyzes how the plant operation and maintenance system operates and outputs the result when the automatic logic determination of the height such as the input data and the abnormality detection created in the step S16 is incorporated as the knowledge data in the plant operation and maintenance system. In step S16, a training simulator provided in advance for plant operation and maintenance may be used, or a simulator using a simple model may be used. Alternatively, the user may theoretically study the actions of the operation and maintenance system.

In the step (S18) of determining whether or not to execute the automatic logic determination of the abnormality detection level, the knowledge extraction unit F14 confirms whether or not the automatic logic determination of the abnormality detection level is executed, based on the result of the simulation analysis unit F13.

When the automatic logical judgment of the height has been performed (yes in S18), the knowledge extraction unit F14 stores the key element data and the logical judgment used in the simulation analysis processing as part of the knowledge data T14 (S19).

On the other hand, if the automatic logical determination of the height is not performed (no in S18), the knowledge extraction unit F14 determines whether or not simulation analysis has been performed on all the key element data (S20). If there is key element data for which simulation analysis has not been performed (S20: NO), the process returns to step S16. When simulation analysis is performed on all the extracted key element data (yes in S20), the present process is ended.

According to the present embodiment thus configured, knowledge data used in the existing plant 4 as implicit knowledge can be automatically extracted.

According to the present embodiment, at least a part of the operation and maintenance recipe hidden as experience or intuition of the operator can be made visible by the knowledge preparation support system 1, and can be used for operation and maintenance of the new plant 6.

Therefore, if knowledge data that has been made explicit knowledge by using the present embodiment is installed as software in an operation and maintenance system for a new plant, even a new operator who does not have a high plant operation and maintenance recipe can perform highly reliable operation and maintenance. Further, by applying knowledge data that is explicit knowledge according to the present embodiment to a plant in which other company products whose characteristics, actual results, and the like are unknown are combined, stable high-quality operation and maintenance can be provided.

In the present embodiment, as an example of knowledge, a function of automatically determining the height such as abnormality detection is described. However, the knowledge is not limited to the detection of an abnormality, the detection of a sign of an abnormality, or the like. A series of specific processes involved in the overall functions related to the operation and maintenance, that is, the machine and human judgment related to the specific sensor 41 or the specific equipment 42, are knowledge.

[ example 2 ]

The second embodiment will be described with reference to fig. 11 and 12. The following embodiments including the present embodiment correspond to modifications of the first embodiment, and therefore, differences from the first embodiment will be mainly described. In this embodiment, a case where knowledge is expanded will be described. In this embodiment, the log data of the plant 4 contains logical decisions or actions.

Fig. 11 shows an example of the logical judgment/action table T10C included in the system log data T10 according to the present embodiment.

The logical judgment/action table T10C includes, for example, a date and time C100C indicating the date and time, an execution name C101C indicating what process has been performed, a cause name C102C indicating an event causing the event, a subject C103C as an execution subject of the process, and a target device C104C indicating which device 42 the subject C103C has performed the process.

The subject C103C has 2 kinds of cases, i.e., "mechanical" and "human". The case where the body C103C is "mechanical" is automatically processed based on a predetermined condition, and human judgment is not included in the processing. For example, the process is a process of automatically turning off the switch when a certain set value is exceeded.

On the other hand, the case where the subject C103C is "human" is a case where the processing is performed by human judgment. For example, the processing is processing to which an obligation is given that the processing must be performed by human judgment, or processing for sudden failure or abnormality.

The big data analysis unit F11 of the present embodiment collects items that may be associated with actions via mechanical logic judgment or human judgment from 3 types of log data, i.e., the system log data T10, the job log data T11, and the external data T12. Since this function can be realized by a so-called data mining method, further description thereof is omitted.

Fig. 11 shows an example of the key element data T13_1 according to the present embodiment. The key element data T13_1 of the present embodiment also includes the contents of the logical judgment/action table T10C described with reference to the key element data T13 described with reference to fig. 8.

That is, the key element data T13_1 includes an action ID C130 indicating the identification of the key element, an action C133 indicating what logical judgment or action was performed, acquisition data C131 indicating the content acquired to achieve the action, and instruction data C132 indicating the content instructed to initiate the action.

The acquisition data C131 includes a device name C1311 indicating from which device 42 data is acquired, and a sensor name C1312 indicating from which sensor 41 data is acquired. In the present embodiment, only 1 type of acquired data C131 is associated with one action C133, but the present invention is not limited thereto, and a plurality of acquired data C131 may be associated with one action C133.

The command data C132 includes a device name C1321 indicating which device 42 has been commanded, and a control object C1322 indicating which control object owned by the device 42 has been commanded. In the present embodiment, only 1 type of instruction data C132 is associated with one action C133, but the present invention is not limited thereto, and a plurality of instruction data C132 may be associated with one action C133.

The record having the operation ID C130 of fig. 12 of "001" is focused. This indicates that operation C133 is "operation start" and the operation of the plant 42 is started. Here, since sensor data is not required at the start of operation, the acquisition data C131 is not set to a value. "none" is stored in both the device name C1311 and the sensor name C1312.

On the other hand, the command data C132 is required to start the operation of the device 42. Therefore, values for specifying the target of the control command are set for the device name C1321 and the control target name C1322 of the command data C132.

In addition, since the operation of the device 42 is confirmed before and after the command in the actual operation, the acquired data C131 is not set to "none" in general, but the description thereof is omitted here for simplicity.

The key element data T13_1 includes the following 5 types depending on the place of value acquisition and the method of setting the value. In the following description, the case where there is no setting value means that "none" is set in fig. 12.

The first is the following: in act C133, no setting value is set for the acquired data C131, and values are set for the device name C1321 and the control object name C1322 of the instruction data C132.

Second is the following: values are set for the device name C1311 and the sensor name C1312 of the acquisition data C131, respectively, and no value is set for the command data C132.

The third is the following case: values are set for the acquired data C131 and the instruction data C132, respectively.

The fourth is the case: the device name C1311 of the acquired data C131 is set to "external cooperation". In this case, the external system is coordinated by acquiring data from the external system.

The fifth is the case: the device name C1321 of the instruction data C132 is set to "external cooperation". In this case, the external system is instructed to cooperate with the external system.

When the knowledge creation support process (fig. 10) described in the first embodiment is executed using the key element data 13_1 shown in fig. 12, it is possible to support creation of knowledge data including general logic determination in addition to highly automatic logic determination such as abnormality detection.

The present embodiment thus configured also achieves the same operational effects as those described in the first embodiment. Further, according to the present embodiment, it is possible to obtain a wide range of knowledge including both general logical judgment and highly automatic logical judgment from an existing factory. Therefore, by applying the extensive knowledge to the operation and maintenance system of a new plant, it is possible to realize highly reliable operation and maintenance even when a new operator does not have a recipe or when a new plant is constructed by piecing together sensors and devices that are not used to the knowledge.

[ example 3 ]

The third embodiment will be described with reference to fig. 13. In the present embodiment, the frequency of acquiring key element data (data acquired from the sensor 41 and data instructing the device 42) necessary for obtaining a high and automatic logical judgment such as abnormality detection is determined. That is, in the present embodiment, in order to realize the operation and maintenance knowledge, the performances of the sensors 41 and the devices 42 are examined.

Fig. 13 is a flowchart of a process of searching for conditions for establishing knowledge. This process is referred to as knowledge satisfaction condition search process. The present process is executed by the knowledge extraction unit F14.

The knowledge satisfaction condition search process includes, as will be described later, detecting a time zone (start time and end time) related to the key element data (S30), changing the frequency of the command data or the sensor data (S31), creating input data for simulation (S32), performing simulation analysis (S33), determining whether or not the automatic determination function is executed or control is performed based on the automatic determination (S34), storing conditions (upper limit value/lower limit value, etc.) of the key element data (S35), and determining whether or not the analysis is ended in all the key elements (S36).

In step S30, a time period related to the key element data is set. The time period is defined, for example, by a start time and an end time. In step S30, the ID C142 of the related key element data is investigated from the knowledge data T14, and the ID C130 of the key element data T13 is retrieved using the ID C142.

In step S30, the system log data T10A and T10B are searched for the acquired data C131 (sensor data) and the command data C132 related to the knowledge, and the start time and the end time corresponding to the acquired data C131 and the command data C132 are determined. That is, in step S30, the time period in which the data (acquisition data and instruction data) that is the basis of the extracted knowledge is detected is specified.

In step S31, the frequency of acquisition of the command data (output data) or the acquisition data (input data) is changed. In step S31, the frequency of occurrence (detection frequency) of the instruction data and the acquisition data in the time zone set in step S30 is calculated, and a frequency lower than the latest frequency by a predetermined value is set (acquisition frequency — predetermined value).

In step S32, input data used in the simulation process is created. Step S32 acquires the related data (instruction data C101B and acquisition data C101A) from the log data T10A and T10B based on the time period of the key element data set in step S30 and the acquisition frequency set in step S31. In step S32, the frequency of these data is adjusted to the frequency set in step S31.

In step S33, the simulation analyzer F13 analyzes how the plant operation maintenance system operates based on various input data created when the input data for simulation is created (S32), and outputs the result. The simulator may be a training simulator for plant operation and maintenance, a simulator using a simple model, or a theoretical research.

In step S34, it is determined whether or not the automatic determination function or the control based on the automatic determination is executed even when the frequency of acquiring data is reduced. In step S34, it is confirmed whether or not the automatic determination function or the control based on the automatic determination is executed, based on the analysis result in the simulation analyzer F13. When they are executed (YES in S34), the process returns to step S31, and reanalysis is performed with the frequency further reduced (S32, S33). In the case where they are not executed (S18: NO), the process is advanced.

In step S35, the condition for knowledge reproduction (the upper limit value or the lower limit value of the acquisition frequency) is associated with the key element data, and the key element data is stored in the knowledge data T14.

In step S36, it is determined whether or not the reproduction conditions (conditions for executing the automatic determination function or the control based on the automatic determination) are analyzed for all the knowledge data. If there is any unanalyzed knowledge (S36: No), the process returns to step S30. When the analysis of all knowledge is completed (yes in S36), the process is terminated.

The present embodiment thus configured also achieves the same operational effects as the first embodiment. Further, according to the present embodiment, it is possible to determine the frequency of acquiring data from a sensor or the frequency of commands to a device (driver) required for knowledge. According to the present embodiment, the specifications of the sensors 41 and the devices 42 required to utilize knowledge in the new plant 6 can be determined, and therefore, operation and maintenance with less waste can be realized as compared with the first embodiment. This embodiment can be combined with any of the first and second embodiments.

[ example 4 ]

The fourth embodiment will be described with reference to fig. 14. In the present embodiment, the operation history of the screen provided to the client terminal 2 by the knowledge formulation assistance system 1 is automatically extracted and used as at least a part of the job log data T11.

Fig. 14 is a flowchart of a process of extracting and storing an operation history of the user with respect to the screen displayed in the client terminal 2. This processing is executed by the knowledge formulation assistance system 1 in cooperation with the client terminal 2 or the operation and maintenance terminal 3, for example. An example in which the knowledge preparation assistance system 1 acquires an operation on the display screen of the operation and maintenance terminal 3 and stores the operation as a screen operation log will be described below.

The user interface unit 35 of the operation and maintenance terminal 3 displays a screen related to the operation and maintenance (S40). The user operates a button displayed on the screen by clicking or the like. The user operation on the screen is detected by the user interface 35 of the operation and maintenance terminal 3 and transmitted to the knowledge formulation support system 1 via the communication unit 23 (S41).

Upon receiving the screen operation data from the operation and maintenance terminal 3 (S50), the screen control unit F15 of the knowledge formulation support system 1 analyzes the screen operation data (S51). The data obtaining unit F10 stores the analysis result in the screen control unit F15 as a screen operation log in the screen operation log data T15 (S52).

The screen operation log data T15 is managed by associating an operation ID, an operation date and time, an operation type, and an operation content, for example. The user ID may be further managed in association with each other. By referring to the screen operation log data T15, it is possible to confirm what kind of operation the user has performed on which screen element (button, input field, or the like).

The knowledge extraction section F14 uses the screen operation log data T15 as at least a part of the job log data T11. Thus, the knowledge extraction unit F14 extracts key element data that may constitute knowledge.

The present embodiment thus configured also achieves the same operational effects as the first embodiment. Further, in the present embodiment, the screen operation by the user is automatically acquired and analyzed, and screen operation log data T15 as a part of job log data T11 is created. Therefore, the user does not need to record the operation record in a manual mode, and the use convenience is improved. This embodiment can be combined with any of the first to third embodiments.

[ example 5 ]

The fifth embodiment will be described with reference to fig. 15. In the present embodiment, when applying the knowledge extracted from the existing plant to the operation and maintenance of the new plant, the viewpoint of the system structure of the plant and the policy of the customer who operates the plant are considered.

Fig. 15 shows an overall outline of the present embodiment. A plurality of pieces of knowledge are extracted from existing plants P1 to P3. The knowledge N10 to N1N are acquired from the plant P1, the knowledge N20 to N2N are acquired from the plant P2, and the knowledge N30 to N3N are acquired from the plant P3.

The present invention is not limited to the new plant P4, to which all the knowledge extracted from the existing plants P1 to P3 can be applied as is. The new plant P4 may have a different system configuration from the existing plants P1 to P3, and the policy of customers who operate the plants may be different. Therefore, in the present embodiment, it is determined whether or not the knowledge extracted from the existing plant can be applied to the new plant by comparing the structure of the existing plant and the structure of the new plant.

Further, in the present embodiment, regarding the knowledge determined to be appropriate in the system configuration, it is determined whether or not the policy is satisfied with the policy of the customer who operates the new plant. In the case of fig. 15, only the knowledge N1N, N21, N30, N32 that satisfies both the suitability possibility in the system configuration and the customer policy is applied to the new plant P4.

According to the present embodiment configured as described above, it is possible to select knowledge applicable to the new plant P4 from among the knowledge extracted from the plurality of existing plants P1 to P3, and apply the selected knowledge to the new plant P4. This embodiment can be combined with any of the first to fourth embodiments.

[ example 6 ]

The sixth embodiment will be described with reference to fig. 16. In the present embodiment, the knowledge extracted from the existing plants P5 to P7 is classified and stored for each policy prepared in advance. In the example shown in fig. 16, knowledge N50 to N5N is acquired from plant P5, knowledge N60 to N6N is acquired from plant P6, and knowledge N70 to N7N is acquired from plant P7. Among these knowledge, knowledge N51, N52, N60, N62, N70, N72 are classified as "security first" policies. Other knowledge N53, N5N, N63, N71, N73, N7N are classified as "cost first" such policies.

According to the present embodiment configured as described above, since the knowledge extracted from the existing plant is classified and stored for each policy, it is possible to select knowledge corresponding to the desire of the customer who operates the new plant and apply the selected knowledge to the new plant. This embodiment can be combined with any of the first to fourth embodiments.

The present invention is not limited to the above-described embodiments. Those skilled in the art can make various additions, modifications, and the like within the scope of the present invention. The above-described embodiments are not limited to the configuration examples illustrated in the drawings. The structure and processing method of the embodiments can be appropriately modified within the scope of achieving the object of the present invention.

Further, each component of the present invention can be arbitrarily selected, and an invention having a selected structure is also included in the present invention. The structures described in the claims may be combined with other structures than those explicitly described in the claims.

Description of reference numerals:

1: operation maintenance knowledge formulation auxiliary system, 2: client terminal, 3, 5: operation maintenance system (operation maintenance terminal), 4: existing system (existing factory), 6: new system (new plant), 41: sensor, 42: device, T10: system log data, T11: job log data, T12: external data, T13: key element data, T14: knowledge data, F10: data acquisition unit, F11: big data analysis section, F12: key element extraction unit, F13: simulation analysis section, F14: knowledge extraction unit, F15: screen control unit, F16: a communication control unit.

Claims (10)

1. An operation maintenance knowledge information formulation assistance system for assisting formulation of knowledge information relating to operation maintenance using information extracted from an existing system, comprising:

an information acquisition unit that acquires predetermined information relating to the existing system;

a key element extraction unit that extracts key element information that is a key element relating to logical judgment of operation and maintenance by analyzing the acquired predetermined information; and

an operation maintenance knowledge information extraction unit for extracting and storing operation maintenance knowledge information, which is knowledge information related to operation maintenance, by performing simulation analysis on the extracted key element information,

the information acquisition unit acquires, as the predetermined information, input information input to a device constituting the existing system, output information instructing output to the device, and job record information related to operation and maintenance,

the key element extracting unit extracts information corresponding to the logical judgment from among the input information and the output information as the key element information,

the operation maintenance knowledge information extraction unit confirms whether or not there is a relationship between the key element information and the logical judgment by the simulation analysis, and extracts the key element information and the logical judgment as the operation maintenance knowledge information when it is confirmed that there is a relationship between the key element information and the logical judgment.

2. The operation maintenance knowledge information formulation assistance system according to claim 1,

the operation and maintenance knowledge information extraction unit determines whether or not output information included in the key element information is present by performing the simulation analysis while changing occurrence conditions of input information included in the key element information, extracts occurrence conditions of the input information necessary for causing the output information to be present as a part of the operation and maintenance knowledge information, and stores the extracted occurrence conditions in association with the key element information and the logical judgment.

3. The operation maintenance knowledge information formulation assistance system according to claim 2,

outputting the operation and maintenance knowledge information extracted by the operation and maintenance knowledge information extraction section to be applied to a new system.

4. An operation maintenance knowledge information making assistance system according to claim 3,

the logical decision comprises a decision relating to a precursor to the occurrence of the obstacle.

5. The operation maintenance knowledge information formulation assistance system according to claim 4,

and determining whether the operation and maintenance knowledge information can be applied to the new system based on the difference of the system structures of the existing system and the new system, and applying only the operation and maintenance knowledge information determined to be applicable to the new system.

6. The operation maintenance knowledge information formulation assistance system according to claim 5,

among the operation maintenance knowledge information determined to be applicable to the new system, only the operation maintenance knowledge information suitable for the policy corresponding to the new system is applied to the new system.

7. The operation maintenance knowledge information formulation assistance system according to claim 4,

and classifying the operation and maintenance knowledge information into a plurality of preset strategies.

8. An operation maintenance knowledge information formulation assistance system according to any one of claims 1 to 7,

the predetermined information includes screen operation history information, which is a history of operations performed on a screen for operation and maintenance of the existing system.

9. An auxiliary method for making operation and maintenance knowledge information, which uses the information extracted from the existing system to assist the making of the knowledge information related to the operation and maintenance through a computer,

acquiring predetermined information related to the existing system;

extracting key element information which is a key element relating to logical judgment of operation and maintenance by analyzing the acquired predetermined information,

the extracted key element information is subjected to simulation analysis, so that the operation maintenance knowledge information which is knowledge information related to operation maintenance is extracted and stored,

the predetermined information includes input information to be input to a device constituting the existing system, output information instructing output to the device, and job record information related to operation and maintenance,

extracting information corresponding to the logical judgment from among the input information and the output information as the key element information,

and confirming whether a relationship exists between the key element information and the logic judgment through the simulation analysis, and extracting and storing the key element information and the logic judgment as the operation and maintenance knowledge information when the relationship exists between the key element information and the logic judgment.

10. A computer program medium recording a computer program for causing a computer to function as an operation maintenance knowledge information formulation assistance system that assists formulation of knowledge information relating to operation maintenance using information extracted from an existing system,

the computer program causes the computer to respectively implement:

an information acquisition unit that acquires, as predetermined information, input information input to a device constituting the existing system, output information instructing output to the device, and job record information related to operation and maintenance;

a key element extraction unit that extracts key element information that is a key element relating to logical determination of operation and maintenance from among the input information and the output information by analyzing the acquired predetermined information; and

an operation maintenance knowledge information extraction unit configured to confirm whether or not there is a relationship between the key element information and the logical judgment by simulation analysis, extract and store the key element information and the logical judgment as the operation maintenance knowledge information when the relationship between the key element information and the logical judgment is confirmed, determine whether or not output information included in the key element information appears by performing the simulation analysis while changing occurrence conditions of input information included in the key element information, extract and store the occurrence conditions of the input information necessary for causing the output information to appear as a part of the operation maintenance knowledge information in association with the key element information and the logical judgment.

Images