JP2019003545A - Operation support device, operation support method, operation support program, and storage medium - Google Patents

Abstract

To provide an operation support device, an operation support method, an operation support program, and a storage medium capable of facilitating succession of skills relating to a work corresponding to an event occurring in the operation of a plant.SOLUTION: An operation support device comprises: an event information acquisition part for acquiring event information relating to an event occurring during the operation of a plant; a phenomenon information acquisition part for acquiring phenomenon information relating to a phenomenon detected in the plant; a perception information acquisition part for acquiring perception information relating to a perception recognized by an operator; an operation information acquisition part for acquiring operation information relating to the operation of the plant performed by the operator; an extraction part for extracting a correlation between the event information and at least one of the phenomenon information, the perception information, or the operation information; and a solution generation part for generating a solution supporting the operation of the plant on the basis of the extracted correlation.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an operation support apparatus, an operation support method, an operation support program, and a recording medium.

  Conventionally, the operation content when operating a plant or the like at a production site or the like may differ depending on the skill level of an operator (operator). For example, when an event such as an alarm occurrence, data abnormality, facility or environment abnormality occurs in the plant, the operator grasps the details of the abnormality that causes the event and determines the appropriateness according to the degree of urgency. It is necessary to operate the plant (operation when there is an abnormality). The prediction of event occurrence, the discovery of an abnormality after the event occurrence, the contents of the operation at the time of the abnormality, the return time from the abnormality, etc. may vary depending on the skill level of the operator.

  In addition, in a plant, the batch behavior (trend) varies depending on the production method such as the plant operation method, and as a result, the quality, production amount, and the like of the product produced may vary. A batch that has obtained the best result in the quality of the product is called a golden batch, and an optimal production method is required to obtain the result of the golden batch.

  Further, skill improvement in the operation method of the plant and the like is performed by educating and nurturing operators. The training of the workers is performed, for example, when a skilled worker (experienced) having a high skill level who is skilled in the work accompanies the worker with a low skill level. The skilled worker, for example, informs the worker of the points in the work, and also guides the worker by performing the operation of the plant and the contents of the work (operation contents), and the skill of the skilled worker (know-how) ). In order to improve the skill level, in addition to the operation method when the plant is in a normal state, it is necessary to instruct the operation method when the plant is in an abnormal state with a low occurrence frequency. In production sites where the number of skilled workers is decreasing, it is difficult to carry out worker education, and the labor cost of skilled workers may increase.

  Production sites include, for example, chemical and other industrial plants, plants that control and control wells such as gas fields and oil fields, plants that manage and control power generation such as hydropower, thermal power, and nuclear power, solar power and wind power, etc. There are plants such as plants that manage and control energy harvesting, plants that manage and control water and sewage, dams, etc., and factories such as machines, electric machines, and automobiles (hereinafter collectively referred to as “plants”). In the plant, a distributed control system (DCS: Distributed Control System) in which field devices called field devices and control devices for controlling these devices are connected via communication means is constructed. Advanced automatic operation has been realized. In a plant in which such a distributed control system is constructed, a logic system that collects information from various devices such as sensors in order to enhance safety, detects an abnormality based on the collected information, and generates an alarm. Registered in

  However, the logic at the time of alarm occurrence does not necessarily correspond to the operation at the time of abnormality at the time of alarm occurrence, and it may not be possible to instruct the worker to take appropriate measures only by the occurrence of the alarm. Skilled workers collect various information through the five senses at the production site. Among these pieces of information, there is information that is difficult to collect depending on the sensors installed in the plant. The information collected by skilled workers may include, for example, information on the quality of produced products, information on production plans, weather information, equipment operating conditions, and the like. The skilled worker may perform an appropriate operation based on the collected information with a judgment different from the logic in which an event such as an alarm occurs.

  By the way, in a production site, there exists a technique which controls a plant etc. based on various information (for example, refer patent documents 1-6). In particular, in recent years, it has been proposed to acquire information from any object by IoT (Internet of Things) in addition to information acquired from a sensor or the like installed in a plant. As a concept aiming at improving the efficiency of a production site using various information acquired by IoT, there are, for example, Industry 4.0 and Industrial Internet. These concepts include analyzing a huge amount of data (big data) obtained by accumulating information obtained by IoT and utilizing it on a production site. Big data collects and accumulates a wide range of data that could not be collected by a single device or system until now. By using big data, it becomes possible to analyze a wide range of data that could not be analyzed so far, and it may be possible to analyze many events whose causal relationship is unknown. Therefore, IoT is expected to be applied to various industrial fields.

  In addition, as a data analysis method, a method using machine learning such as deep learning that generates a model of the relationship between input and output with a neural network with a multilayer structure and a support vector machine that generates a pattern recognition model based on teacher data is proposed. Has been.

JP 11-287400 A JP 2003-177818 A JP 2003-167624 A JP 2003-140741 A International Publication No. 02/35302 JP 2006-185120 A

  However, in order to analyze the acquired data, in what case (event in the plant), the criteria for determining what data should be analyzed and what judgment (determination of the operation to be performed) should be made. Although it is necessary to determine in advance, the judgment standard is that the skilled worker is handed down to the worker by matching, and the worker cannot succeed to the skill of the skilled worker simply by collecting data by IoT. There was a case.

  In addition, when a determination criterion is generated by machine learning based on data collected by IoT, it is difficult to learn an event or an event having a low occurrence frequency in an actual plant. In addition, it takes time to collect occurrence frequency events and event data, and in some cases, it is not possible to succeed to skills related to work corresponding to events that occur at low frequency in plant operations.

  Further, in order to obtain judgment standards of skilled workers through interviews and to express the logic by a program or the like to form a standard, it is necessary for the skilled workers to have an interview for each work decision. For example, when an interview is performed every time an event occurs, the load on skilled workers may increase. On the other hand, when interviewing a plurality of events together, the skilled worker's memory faded with time, and accurate judgment criteria could not be obtained. In addition, when a skilled worker passes on the judgment criteria, it is possible to convey what is within the consciousness of the skilled worker, but the judgment is made unconsciously (implicit knowledge because it is skilled) It may be difficult to convey.

  Also, when skilled workers accompany you to train workers, it takes a considerable period of time to pass on the judgment criteria for all the events that occur in the plant, and the automation and labor saving of the production site progresses. In particular, it is difficult to secure skilled workers, and it may be difficult to transfer skills of skilled workers.

  In addition, since the workers who receive the succession of skills differ from worker to worker, it is difficult to transfer the skills according to the skill level of the worker using the training tools such as manuals that are standardized based on the judgment criteria of skilled workers. There was a case.

  The present invention has been made in view of the above circumstances, and can facilitate the succession of skills relating to work corresponding to an event occurring in plant operation, an operation support device, an operation support method, an operation support program, and An object is to provide a recording medium.

  (1) In order to solve the above-described problem, the operation support apparatus of the present invention includes an event information acquisition unit that acquires event information related to an event that occurs during operation of the plant, and an event that relates to an event detected in the plant An event information acquisition unit that acquires information, a perception information acquisition unit that acquires perception information related to the perception recognized by the worker, and an operation information acquisition unit that acquires operation information related to the operation of the plant performed by the worker And an extractor that extracts the relationship between the event information and at least one of the event information, the perceptual information, and the operation information, and supports the operation of the plant based on the extracted relationship And a solution generation unit for generating a solution to be performed.

  (2) Further, in the operation support device of the present invention, the extraction unit is based on a time-series comparison between the event information and at least one of the event information, the perceptual information, and the operation information. Extract relevance.

  (3) Moreover, in the operation support apparatus of the present invention, the event information acquisition unit acquires an alarm generation event that notifies the abnormality of the plant, and the operation information acquisition unit performs an operation at the time of abnormality performed by the operator. The operation information related to is acquired.

  (4) Moreover, in the operation support apparatus of the present invention, the event information acquisition unit acquires a batch generation event indicating generation of a batch indicating a predetermined behavior in the plant, and the operation information acquisition unit is Operation information related to the exemplary operation for generating the batch generation event is acquired.

  (5) In the operation support device of the present invention, the extraction unit extracts the relevance according to the skill level of the worker, and the solution generation unit generates the solution according to the skill level. To do.

  (6) Moreover, the operation assistance apparatus of this invention is further equipped with the solution provision part which provides the produced | generated said solution according to generation | occurrence | production of the said event during operation of the said plant.

  (7) In the operation support device of the present invention, the perceptual information acquisition unit acquires information of an external device connected via a network.

  (8) In the operation support device of the present invention, the perceptual information acquisition unit acquires at least one information of vibration, sound, or alarm generated by the facility.

  (9) Further, in the operation support device of the present invention, the perceptual information acquisition unit acquires visual information that the worker is viewing from a gaze detection device that detects the gaze of the worker.

  (10) In the operation support device of the present invention, the operation support device further includes a determination criterion acquisition unit that acquires a determination criterion of the worker who performed the operation, and the extraction unit is further based on the acquired determination criterion Extract relevance.

  (11) In order to solve the above problem, the operation support method of the present invention includes an event information acquisition step for acquiring event information related to an event that occurs during operation of the plant, and an event related to the event detected in the plant An event information acquisition step for acquiring information, a sensory information acquisition step for acquiring sensory information related to the perception recognized by the worker, and an operation information acquisition step for acquiring operation information related to the operation of the plant performed by the worker And an extraction step for extracting the relationship between the event information and at least one of the event information, the perceptual information, and the operation information, and the operation of the plant is supported based on the extracted relationship Generating a solution to be generated.

  (12) In order to solve the above problems, the operation support program of the present invention includes an event information acquisition process for acquiring event information related to an event that occurs during operation of the plant, and an event related to an event detected in the plant Event information acquisition processing for acquiring information, sensory information acquisition processing for acquiring sensory information related to the perception recognized by the worker, and operation information acquisition processing for acquiring operation information related to the operation of the plant performed by the worker And an extraction process for extracting a relationship between the event information and at least one of the event information, the perceptual information, and the operation information, and the operation of the plant is supported based on the extracted relationship The computer executes a solution generation process for generating a solution to be executed.

  (13) In order to solve the above problem, the recording medium of the present invention includes an event information acquisition process for acquiring event information related to an event that occurs during operation of the plant, and event information related to an event detected in the plant. Event information acquisition processing for acquiring sensory information, sensory information acquisition processing for acquiring sensory information related to the perception recognized by the worker, and operation information acquisition processing for acquiring operation information related to the operation of the plant performed by the worker, , Supporting the operation of the plant based on the extracted processing that extracts the relationship between the event information and at least one of the event information, the perceptual information, and the operation information. An operation support program for causing a computer to execute a solution generation process for generating a solution is recorded.

  According to the present invention, it is possible to provide an operation support device, an operation support method, an operation support program, and a recording medium that can facilitate succession of skills related to work corresponding to an event that occurs in plant operation. .

It is a block diagram which shows an example of the system configuration | structure containing the operation assistance apparatus in embodiment. It is a block diagram which shows an example of the software structure of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the event information acquisition operation | movement of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the event information acquisition operation | movement of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the perceptual information acquisition operation | movement of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the operation information acquisition operation | movement of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the solution production | generation operation according to skill of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the relevance extraction operation | movement of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the solution provision operation | movement according to level of the operation assistance apparatus in embodiment. It is a flowchart which shows an example of the operation assistance feedback operation | movement of the operation assistance apparatus in embodiment. It is a block diagram which shows an example of the hardware constitutions of the operation assistance apparatus in embodiment.

  Hereinafter, an operation support device, an operation support method, an operation support program, and a recording medium according to an embodiment of the present invention will be described in detail with reference to the drawings.

  First, the outline of the operation support apparatus will be described with reference to FIG. FIG. 1 is a block diagram illustrating an example of a system configuration including an operation support apparatus according to the embodiment.

  In FIG. 1, the operation support system 100 includes an operation support apparatus 1, a sales database 2 </ b> A, a quality database 2 </ b> B, a site database 2 </ b> C, a skill-specific solution database 3, and an execution environment 4.

  The sales database 2A, the quality database 2B, and the on-site database 2C exemplify sources of big data acquired by IoT. In the IoT concept, it has been proposed to connect a wide range of information (big data) acquired from any object by connecting any object to a network and a work such as the Internet. The provider of big data acquired by IoT is not limited to these databases, and anything that can be connected to a network to provide data is assumed. Big data may include data such as measurement data acquired from a measuring instrument, image data acquired from a camera, audio data acquired from a microphone, mail data, communication data, and the like. The acquired big data is accumulated by the operation support apparatus 1. Big data is acquired by selecting from the data that can be acquired. The acquisition of big data may be selected, for example, as needed for analysis or the like, or data selected in advance may be acquired regularly or irregularly.

  The sales database 2A is a database having customer information, logistics information, sales information, and the like. The sales database 2A is realized, for example, by a core business system that manages management resources of the entire company. In addition to these pieces of information, the core business system may have, for example, accounting information, production management information, sales management information, inventory management information, and the like. As the core business system, for example, an ERP (Enterprise Resource Planning) system for the process manufacturing industry can be used.

  Further, the core business system may include a maintenance management system that manages information on the operating state of the plant, business information on maintenance and repair of the plant, and the like. The information on the core business system may be referred to when an operator determines maintenance contents or makes a schedule. For example, an operator refers to a requirement specification included in customer information and operates the plant so as to produce a product that matches the requirement specification. The skilled worker may produce a product that meets the customer's needs by referring to the past order information included in the customer information together with the required specifications. Further, the skilled worker may determine the operation of adjusting the production speed of the product or switching the production type while confirming the distribution information and the production management information. That is, the worker may change the operation of the plant based on the acquired information by acquiring and perceiving the information from the sales database 2A.

  The quality database 2B is a database having inspection data, analysis data, and the like. The quality database 2B can also be realized by, for example, a core business system that manages management resources of the entire company. For example, the worker can refer to the inspection data and analysis data to confirm whether or not the product quality is acceptable and determine whether or not the product shipping work is possible. A skilled worker may finely adjust a process setting value or the like with reference to a temporal change (trend) of inspection data or analysis data.

  Note that the quality database 2B may be realized by, for example, MES (Manufacturing Execution System). MES is a system that monitors or manages the state of a plant. The MES may have functions such as PIMS (Plant Information Management System) or CMMS (Computerized Maintenance Management System). The PIMS functions as a plant data management system that collects and records plant data. For example, the PIMS collects information on an inspection device or an analysis device and records it as inspection data or analysis data. In addition, the CMMS may record a maintenance history of the inspection device or the analysis device. That is, the operator may change the operation of the plant based on the acquired information by acquiring and perceiving the information from the quality database 2B.

  The on-site database 2C is a database having normal event information, abnormal event information, plant data, control data, monitor information, sensor data, operator data, operation history, sensory information, and the like. The on-site database 2C can also be realized by MES.

  Normal event information is event information that occurs at the normal time of the plant. For example, a start notification event that notifies the start of a process, a state notification event that notifies that a process has reached a predetermined state, and an end of the process For example, an end notification event. For example, the worker starts a predetermined work in response to the occurrence of a normal event.

  Abnormal event information is event information that occurs in the event of a plant abnormality. For example, a process alarm event for notifying a process abnormality automatically detected by a sensor or the like, an operation error, or an abnormal operation is notified. This is an operation alarm or the like. The worker who has recognized these alarm events performs, for example, an abnormal operation, which is an operation for a process for eliminating the abnormality, according to the cause of the occurrence of the alarm event.

  The plant data is information related to the operation of the plant, such as the operation state of the plant and the production quantity. The control data is control data for controlling the plant. The control data can be acquired as a control program from a control device that controls the plant, for example. The monitor information is a monitor image acquired from a monitor camera arranged in the plant. Sensor data is data acquired from sensors arranged in a plant. The operator data is data that is identified by the worker, and may include, for example, information on the skill (knowledge or skill) level of the worker. The operation history is history information that records the operation contents of the operator. The perceptual information is information obtained by measuring and recording visual, auditory, olfactory, tactile, taste, etc. that can be perceived by the worker.

  For example, the operator gradually operates the gas concentration adjusting valve while referring to gas concentration data output from a gas concentration sensor arranged in the plant as sensor data. In addition to the gas concentration data, the skilled worker may determine the operation amount of the gas concentration adjusting valve while referring to, for example, the gas concentration trend, the composition data at the reactor outlet, and the monitor information. That is, the worker may change the operation of the plant based on the acquired information by acquiring and perceiving the information from the site database 2C.

  The operation support apparatus 1 collects and stores information selected from big data provided by the sales database 2A, the quality database 2B, and the on-site database 2C. The operation support apparatus 1 searches and reads the stored information, and generates a determination logic when the operation content is determined when the operator performs the operation. The operation support apparatus 1 generates and provides a skill-specific solution according to the skill level of the worker from the generated determination logic. Details of the operation support apparatus 1 will be described later.

  The skill-specific solution database 3 stores skill-specific solutions provided from the operation support apparatus 1. The skill-specific solution is a solution used according to the skill level of the worker. In the present embodiment, examples of the skill-specific solution include abnormal-time operation information, model operation information, automation information, and e-learning information.

<Operation information for abnormal conditions>
The abnormal-time operation information is information for supporting an abnormal-time operation (an abnormal-time operation) of the plant when an abnormality occurs in the plant. The abnormal operation information supports an appropriate abnormal operation according to the skill level of the worker. The plant operations that can be performed by the worker vary depending on the skill level of the worker. For example, a new worker can set a device such as one valve to an instructed state (for example, a valve opening for a valve). On the other hand, a veteran worker can adjust a plurality of devices while checking the instruments. The operation information at the time of abnormality gives the operator an operation instruction according to the skill level, thereby enabling an accurate (without mistake) and quick response according to the abnormality occurring in the plant. As the operation information at the time of abnormality, the operation content according to the skill level of the worker who operates the plant is generated based on the operation performed by the worker with a high skill level. The abnormal operation information is provided to the worker in association with the alarm event. The operation information at the time of abnormality is provided by, for example, displaying characters, still images, moving images, etc. on a display device, and notifying by voice.

<Model operation information>
The exemplary operation information is information for supporting exemplary plant operation (exemplary operation) for generating a golden batch. The exemplary operation information supports an appropriate operation according to the skill level of the worker, as in the case of an abnormal operation. For example, a new worker can operate the equipment while checking the value of one meter. On the other hand, an experienced worker can adjust the equipment while checking the trends of a plurality of instruments. The model operation information enables an operation for generating a trend that approximates the golden batch by giving an operation instruction according to the skill level to the worker. The model operation information is generated based on an operation performed by an operator with a high skill level according to the skill level of the operator operating the plant. The abnormal operation information is provided to the worker in association with the normal event. The exemplary operation information is provided by, for example, displaying characters, still images, moving images, etc. on a display device, and notifying by voice.

<Automation information>
The automation information is information for operating a control device that controls the plant. The automation information is a program that can be executed by, for example, a DCS (Distributed Control System) control device that automatically controls a plant, or a PLC (Programmable Logic Controller) control device. The automation information is generated in a form that can be executed by each control device. The automation information may be a program itself that can be executed in the control device, for example, a linkable library. Further, the automation information may represent a program code or may give predetermined parameters to the control device.

<E-learning information>
The e-learning information is e-learning learning content that can be provided to the worker. The abnormal operation information and the model operation information are so-called online contents that provide information such as operation instructions when the operator operates the plant at the production site, whereas e-learning is performed on the desktop. This is so-called offline content for improving knowledge. The e-learning information includes learning contents according to the skill level of the worker who operates the plant based on the operation performed by the worker with a high skill level. In e-learning, the skill level may be appropriately selected. Further, depending on the result of learning, skill level authorization or level up authorization may be performed. The e-learning information is provided by, for example, displaying characters, still images, moving images, etc. on a display device, and notifying by voice. The e-learning information may provide, for example, an operating environment for a plant using VR (Virtual Reality) goggles.

  Note that the solution provided from the operation support apparatus 1 may be a skill-specific manual generated according to the skill level. The manual is content in which the work procedure is documented, and can be referred to when the worker performs the work.

  The execution environment 4 is an environment that uses a skill-specific solution. The skill-specific solution can be used by being executed in a plant control device, for example. The execution environment 4 can support an abnormal operation corresponding to an alarm event or support an exemplary operation by executing a skill-specific solution in a plant control device. Moreover, it becomes possible to utilize automation information for plant control.

  The execution environment 4 is, for example, an environment in which a skilled worker instructs an operation content to a new worker, confirms and guides the operation content of the new worker, or discusses a work method (waigaya environment). Can also be used. The skill of the skilled worker can be transmitted to the worker in such a Waigaya environment. In the present embodiment, for example, by executing e-learning information in the Waigaya environment, it is possible to receive guidance from a skilled worker and improve the learning effect. The execution environment 4 may be the VR goggles described above or a computer installed at a production site, or a handheld computer or a smartphone carried by an operator.

  The execution environment 4 may acquire the skill-specific solution generated in the skill-specific solution database 3 by requesting the skill-specific solution database 3 from the execution environment 4, for example.

  The execution environment 4 provides feedback information for the skill-specific solution to the operation support apparatus 1. The feedback information is information that feeds back such information to the operation support apparatus 1 when there is an error or additional information in the content of instructions in the operation of the plant, for example. The operation support apparatus 1 provided with the feedback information can correct the skill-specific solution. The execution environment 4 may be implemented as a part of the operation support apparatus 1. In the present embodiment, a case where the execution environment 4 is implemented as a function of the operation support apparatus 1 will be described below as an example.

  By the way, skilled workers perceive various information and make decisions in the operation of the plant. Skilled workers, for example, look at documents and equipment (visual), hear sounds from other people and equipment (hearing), feel the temperature (tactile sense), smell the smell (Smell) to perceive information. When an object is connected to a network by IoT, it becomes possible to collect and formalize the information perceived by the worker by a computer. In addition, it becomes possible to formalize know-how by clarifying which information the worker has made a decision based on. By collecting information perceived by skilled workers using IoT, work in various fields can be formalized. Examples of perceptual information that can be used in this embodiment will be described below.

<Scheduler information>
The scheduler information is information for managing the worker's schedule. The scheduler information includes, for example, various information such as date and time, place, action schedule, contact information, order list, and the like. By collecting scheduler information by IoT, it is possible to collect information on what the worker has done as an information source, what kind of action he / she has made, and a plan. The scheduler information may be a restricting condition that restricts actions in worker decision making. By formalizing the scheduler information, it is possible to improve the prediction accuracy of the intention to be determined.

<Order information>
The order information is, for example, information on what order the salesperson (worker) has made by contacting the person by telephone or e-mail and in what kind of negotiation. By collecting order information by IoT, it becomes possible to clarify a sales process that has been considered as a personal skill until now. For example, the accuracy of a standardized manual can be improved.

<Design and production information>
For example, in the manufacture of a product such as a mold, a high-performance (high accuracy) product can be manufactured by adding know-how to information described in a design drawing by a skilled worker. Design / manufacturing information refers to who and what kind of meeting the operator (customer's request, etc.), where to confirm or change the blueprint, and which part of the mold produced by palpation It is information such as how it was judged. By collecting design / production information by IoT, it is possible to formalize the product design process and production process of skilled workers.

<Quality control information>
The quality management information is information on quality management work, for example, information on work procedures in analysis work, contents of referenced instructions, analysis results, and the like. By collecting quality control information by IoT, it is possible to improve the work efficiency or improve the accuracy of the manual by formalizing the operation contents in the quality control work.

<Field information>
On-site information is information on work at the production site. For example, the location of the site, the date and time of the work, the flow line (movement path) of the worker, perceived information (sound, temperature, etc.), This is information such as contents and operation contents. By collecting on-site information by IoT, it is possible to formalize the operation contents in the on-site work, improve the work efficiency, or improve the accuracy of the manual.

<Educational information>
Education information is information when worker education for workers is carried out at the production site. For example, the skill level of the educated person, the events at the site (the numerical value of the instrument, the state of the equipment, the passage of time, etc.) This is information such as what can be recognized by the worker on site), what kind of judgment has been made, what kind of work has been instructed, and so on. By collecting educational information by IoT, it becomes possible to formalize the contents of education in worker education and implement pseudo on-the-job training (OJT).

  Note that the collection and effect of information by IoT as described above are examples of this embodiment, and do not limit the field of use of this embodiment.

  Next, the software configuration of the operation support apparatus 1 will be described with reference to FIG. FIG. 2 is a block diagram illustrating an example of a software configuration of the operation support apparatus 1 according to the embodiment.

  In FIG. 2, the operation support apparatus 1 has functions of an information acquisition unit 11, a solution analysis unit 12, a solution provision unit 13, and a solution correction unit 14. The information acquisition unit 11 has functions of an event information acquisition unit 111, an event information acquisition unit 112, a perceptual information acquisition unit 113, an operation information acquisition unit 114, and a determination criterion acquisition unit 115. The solution analysis unit 12 has functions of an extraction unit 121 and a solution generation unit 122. The solution providing unit 13 has functions of an abnormal operation information providing unit 131, an exemplary operation information providing unit 132, an automation information providing unit 133, and an e-learning information providing unit 134. The solution correction unit 14 has functions of a feedback information acquisition unit 141 and a feedback information application unit 142.

  Each function of the operation support apparatus 1 in the present embodiment will be described as a function module realized by an operation support program (software) that controls the operation support apparatus 1.

  The information acquisition unit 11 acquires information from outside or inside the operation support apparatus 1. The information collected by the information acquisition unit 11 may include information collected by the IoT described above.

  The event information acquisition unit 111 acquires event information related to an event that occurs during plant operation. The event information generated during the operation of the plant is information generated when a predetermined condition is satisfied during the operation of the plant, and is generated from, for example, a process control device. The event information is, for example, abnormal event information that occurs under a predetermined condition when the plant is abnormal, or a normal event that occurs under a predetermined condition when the process is normal.

  The abnormal event includes, for example, an alarm event for notifying the abnormality. An abnormal event is an irregular and non-stationary event that occurs when an abnormality occurs, and the frequency of occurrence is low and the frequency that an operator experiences may be low.

  On the other hand, the normal event includes, for example, a batch event indicating the batch state of the process. The batch event is an event for notifying that the batch is in a predetermined state. A batch event occurs, for example, when trend data indicating the behavior of a batch is in a predetermined state. The batch event is, for example, a batch start event indicating that the process has started, a threshold event indicating that the trend data has reached a predetermined threshold, or a batch end event indicating that the process has ended.

  In addition, the trend data may include trend data obtained as a result of the golden batch that obtains the best result in the quality and production amount of the product in the process. Whether or not the batch result is a golden batch is a result of the operation of the plant, and there may be a time lag with the operation of the plant. When trend data obtained as a result of the golden batch is detected, it is possible to notify that the result of the golden batch has been obtained by generating a batch event. The operation of the plant is acquired and recorded in an operation information acquisition unit 114 described later. The event information acquisition unit 111 notifies the solution analysis unit 12 (to be described later) that the result of the golden batch has been obtained by acquiring the batch event, and generates the batch event acquired by the operation information acquisition unit 114. Can be associated with the operation of the plant.

  The event information acquisition unit 111 records the acquired event information together with predetermined accompanying information. The accompanying information is, for example, event information acquisition date / time (or event occurrence date / time), event occurrence location (part in the plant), worker identification information at the time of event occurrence, and the like. The accompanying information is information used to associate event information with event information, perceptual information, or operation information.

  The event information acquisition unit 112 acquires event information related to an event detected in the plant. Event information is information related to all events that can be detected in the plant, for example, numerical values of measuring instruments installed in the plant, sensor status, equipment status, etc., including event information and sensory information. Also good. The event information acquisition part 112 may acquire the information input into control apparatuses, such as PLC which controls a plant, for example.

  The event information acquisition unit 112 records the acquired event information together with predetermined accompanying information. Accompanying information is, for example, event information acquisition date (or event occurrence date), event occurrence location (part in plant, sensor ID, field device ID, etc.), worker identification information at the time of event occurrence, etc. is there. The accompanying information is information used to associate event information with event information, perceptual information, or operation information.

  The perceptual information acquisition unit 113 acquires perceptual information related to perception recognized by the worker. The perceptual information includes, for example, visual information that can be recognized by the worker's vision, auditory information that can be recognized by the worker's auditory sense, tactile information that can be recognized by the worker's tactile sense, olfactory information that can be recognized by the worker's sense of smell, Includes taste information that can be recognized by taste. Perceptual information is acquired in order to analyze what the operator operating the plant perceived and acted on. Therefore, events that the worker cannot actually recognize are not included.

  The visual information is, for example, information obtained from numerical values of the instrument, information included in the display screen of the display device, information on the printed matter, visual information such as the state of the product, actions of other workers, and the like. The visual information is, for example, information on what the worker is viewing (gazing at) with the line of sight of the worker detected by the line-of-sight detection device that can analyze the movement of the human eyeball.

  The auditory information is information obtained from, for example, an alarm sound, an abnormal sound generated from equipment, an auscultatory sound using a stethoscope, a received sound from a transceiver or an intercom, and the like. The auditory information is, for example, voice data collected by a microphone attached to the worker.

  The tactile information is information obtained from, for example, abnormal vibration or abnormal temperature when palpating equipment. The olfactory information is information obtained from a bad odor generated from equipment, a odor generated from a product, or the like. The taste information is information obtained from the taste of a product such as food.

  The perceptual information acquisition unit 113 acquires information about an external device connected via a network such as the Internet. The external device is a device outside the operation support device 1 connected to the operation support device 1 via a network. For example, the perceptual information acquisition unit 113 may acquire information on field devices connected by field communication and may also acquire big data using IoT. The perceptual information acquisition unit 113 may select and acquire information acquired from big data using IoT. The perceptual information acquisition unit 113 records the acquired perceptual information together with predetermined accompanying information. The accompanying information is, for example, the acquisition date and time (or worker's perception date) of perceptual information, the worker's identification information, the location perceived by the worker, the movement path of the worker, the skill level of the worker, and the like. The accompanying information is information used to associate perceptual information with operation information and the like. That is, the perceptual information includes who (performer identification information), when (acquisition date and time), and what was perceived. The perceptual information acquisition unit 113 records the acquired perceptual information, for example, for each worker in time series.

  The perceptual information acquisition unit 113 may acquire only perceptual information of a specific worker. Workers include workers of various skill levels such as new workers, mid-career workers, and skilled workers. For example, when recording the behavior of a skilled worker, the perceptual information acquisition unit 113 may acquire the perceptual information of the skilled worker to be recorded. Unlike sensor detection data used in plant control, sensory information has been difficult to record until now. In the present embodiment, by using perceptual information among various pieces of information that can be acquired by IoT, it is possible to analyze the behavior of an operator that has been difficult to analyze.

  Note that the perceptual information acquisition unit 113 may acquire perceptual information based on an explicit instruction from the worker, for example, when the worker determines the operation content. The perceptual information acquisition unit 113 may acquire perceptual information according to the selection of the worker when the worker confirms the work record at a later date. Further, the perceptual information acquisition unit 113 may acquire perceptual information based on an interview with the worker at a later date.

  The operation information acquisition unit 114 acquires operation information related to the operation of the plant performed by the worker. Plant operations include all operations performed by workers on the production site, such as operation of switches on operation panels, valve operation, input of raw materials, product recovery, equipment inspection, equipment cleaning, etc. May be included. The operation information acquisition unit 114 may acquire operation information in association with worker and time information. That is, the operation information includes who (which worker), what, and what was operated. The operation information acquisition unit 114 records the acquired perceptual information in time series for each worker, for example.

  Similar to the sensory information acquisition unit 113, the operation information acquisition unit 114 may acquire operation information performed by the skilled worker, for example, when recording the work information of the skilled worker. That is, the operation information acquired by the operation information acquisition unit 114 can be acquired in association with the perceptual information acquired by the perceptual information acquisition unit 113.

  The operation information acquired by the operation information acquisition unit 114 may include an operation target and an operation method for the operation target. For example, when the operation target is a switch, the operation information may include information such as button presses, long presses, and continuous hits. When the operation target is a valve, the operation information may include information such as full opening, full closing, rotation direction, rotation angle, rotation speed, or opening degree of the valve. In addition, when the operation target is a moving article, the operation information may include information such as the movement path, movement speed, and movement order of the article. Further, when there are a plurality of operation targets, the operation information may include information such as an operation order and a timing of a plurality of operations. The operation information acquisition unit 114 records the operation performed by the worker, for example, a captured image of a television camera that can photograph the appearance of the worker, a signal indicating that the operation from the operation target has been performed, and the operator recording It is obtained from the completed work record. For example, the operation information acquisition unit 114 starts acquisition of operation information by an input of work start by an operator, and ends the acquisition by input of work end. The operation information acquisition unit 114 may start acquisition of operation information upon occurrence of an event such as an alarm event, and end acquisition upon cancellation of the event. The operation information acquisition unit 114 records the acquired operation information together with predetermined accompanying information. The accompanying information includes, for example, operation information acquisition date / time (or work execution date / time), worker identification information, place where the work was performed, worker skill level, and the like. The accompanying information is information used to associate operation information with perceptual information.

  The operation information acquired by the operation information acquisition unit 114 includes the operation information of the plant when the result of the golden batch is obtained.

  The determination criterion acquisition unit 115 acquires the determination criterion of the worker who has operated the plant. The determination criterion acquisition unit 115 acquires the determination criterion of the operator who has operated the plant according to the operation information acquired by the operation information acquisition unit 114. Since the perceptual information is referred to in order to determine the operation content and timing, it is desirable not to include information that does not affect the operation determination even if the information is actually perceived by the worker. . Therefore, it may be impossible to determine whether or not the worker actually refers to the perceptual information only with the accompanying information. Further, only the operator himself can understand what kind of thought (logic) the operator has determined to execute the operation based on the perceptual information. The determination criterion acquisition unit 115 acquires, from the operator, a determination criterion as to what operation information is determined based on what perceptual information. The determination criterion acquisition unit 115 may acquire the determination criterion based on a later interview with the worker. The determination criterion acquisition unit 115 records the acquired determination criterion.

  For example, the worker may decide to perform one operation based on one piece of perceptual information and determine the next operation content by perceiving the result as the perceptual information. In addition, the worker may acquire a plurality of perceptual information and determine one operation content based on the acquired plurality of information. For example, in order to acquire what perceptual information the operator perceived, the determination criterion acquisition unit 115 displays the perceptual information acquired by the perceptual information acquisition unit 113 in a selectable manner and allows the operator to select the perceptual information. To obtain the criteria. Further, for example, the determination criterion acquisition unit 115 displays perceptual information in a selectable manner, and further displays a determination condition indicating how the judgment is made based on the selected perceptual information, and acquires a determination criterion. May be.

  The solution analysis unit 12 has functions of an extraction unit 121 and a solution generation unit 122, and analyzes the information acquired by the information acquisition unit 11 to generate a solution.

  The extraction unit 121 includes the event information acquired by the event information acquisition unit 111, at least the event information acquired by the event information acquisition unit 112, the perceptual information acquired by the perceptual information acquisition unit 113, or the operation information acquisition unit 114. The relevance with any one of the operation information acquired in is extracted. The extraction of the relevance is performed based on the accompanying information described above, for example.

  For example, the extraction unit 121 sorts each information in time series using the date and time information included in the incidental information of the event information and the date and time information included in the incidental information of the event information, perceptual information, or operation information as a search condition. By comparing, the event information whose date and time are approaching and at least one of the event information, the perceptual information, and the operation information are extracted as related information. For the relevance of these pieces of information, for example, a plant name, an operator name, a skill level, etc. may be extracted as an extraction search condition in addition to the date / time information.

  Further, the extraction unit 121 extracts, for example, perception information and determination criterion information from the operations performed by a worker (extraction target worker) within a predetermined period using the operation content as a search condition. It is possible to extract (analyze) the judgment criteria for performing the operation in association with each other. In addition, the extraction unit 121 extracts, for example, a criterion and operation information using perceptual information as a search condition, thereby associating what operation should be performed when the perceptual information is satisfied. Can be extracted.

  Further, the extraction unit 121 can extract the determination criterion according to the extraction target worker (including the skill level of the worker). For example, when the extraction target worker is a specific skilled worker, the extraction unit 121 extracts correspondences of determination criteria for various operations (work) performed by the skilled worker at the production site. Can do. In addition, when there are a plurality of extraction target workers, it is possible to extract the average and variation of the determination criteria among the plurality of workers and collect a large number of opinions. In addition, when the extraction target workers are a plurality of workers having different skill levels, it is possible to extract a difference in judgment criteria for each skill level.

  The extraction unit 121 can generate the operator's determination logic based on the extracted relevance. Judgment logic is a formalization of the worker's thinking. For example, the judgment logic is an output result corresponding to the condition with the perception information and the judgment criterion as input conditions. The decision logic can be formalized by expressing it in a standardized manner such as a flowchart, a sequence diagram, or a collaboration diagram (UML). By generating the determination logic, it is possible to visualize the determination logic, which is the content of the worker's thought, and it is possible to transfer the skill by formalizing it.

  For example, the extraction unit 121 is configured to generate an alarm occurrence event based on the alarm occurrence event that notifies the abnormality of the plant acquired in the event information acquisition unit 111 and the operation information related to the abnormal operation acquired in the operation information acquisition unit. Extract the relevance to the abnormal operation.

  Further, the extraction unit 121 includes a batch generation event indicating generation of a batch indicating a predetermined behavior in the plant acquired by the event information acquisition unit 111, and a batch generation event performed by an operator acquired by the operation information acquisition unit. The relevance between the golden batch and the exemplary operation may be extracted based on the operation information related to the exemplary operation to be generated.

  Further, the extraction unit 121 enables generation of e-learning information according to the skill level by performing the above-described relevance according to the skill level of the worker.

  By the way, among skilled workers, there is an operator called “Takumi”. A craftsman is a person who has advanced knowledge and skills in the field of performing work, and should be a model for other workers. A skilled worker having a certain level of skill can aim for further skill improvement by receiving succession of the skill of the master while receiving guidance from the master. The extraction unit 121 extracts information that is useful for improving skills of other skilled workers or workers having a skill level lower than that of the skilled worker by extracting the judgment criteria of the skilled worker (for example, a skill-specific solution). It is possible to obtain information for generation. Similarly, criteria for skilled workers are useful information for mid-level workers or workers with skill levels lower than mid-level, and criteria for mid-level workers are useful information for new-level workers. can do.

  The solution generation unit 122 generates a solution that supports the operation of the plant by associating the event information with at least one of the event information, the perceptual information, and the operation information based on the relationship extracted by the extraction unit 121. .

  For example, the solution generation unit 122 generates a solution related to the abnormal operation information that associates the alarm occurrence event with the abnormal operation. Moreover, the solution production | generation part 122 may produce | generate the solution which concerns on model operation information which linked | related golden batch and model operation. Further, the solution generation unit 122 may generate a solution related to automation information in which event information and operation information are associated. The solution generation unit 122 may generate a solution related to e-learning that associates event information, perceptual information, and operation information. The solution generation unit 122 may generate these solutions based on the determination logic generated by the extraction unit 121.

  The solution providing unit 13 has functions of an abnormal operation information providing unit 131, an exemplary operation information providing unit 132, an automation information providing unit 133, and an e-learning information providing unit 134, and the solution generated by the solution generating unit 122 provide.

  The abnormal-time operation information providing unit 131 provides a solution related to abnormal-time operation information according to an alarm occurrence event that occurs during operation of the plant. The abnormal operation information is information for supporting the abnormal operation of the plant when an abnormality occurs in the plant as described above. The abnormal operation information providing unit 131 supports appropriate abnormal operation according to the skill level of the worker. For example, the abnormal-time operation information providing unit 131 acquires the skill level of the worker who is working on the plant from the event information, and selects and provides operation information according to the skill level of the worker. The abnormal operation information providing unit 131 grasps the progress of the abnormal operation based on the operation information acquired by the operation information acquiring unit 114, and instructs the operator to perform an appropriate operation at an appropriate timing. Also good. As a result, it is possible to instruct an appropriate and quick response to the abnormality that causes the alarm. The abnormal-time operation information providing unit 131 provides abnormal-time operation information, for example, by displaying characters, still images, moving images, or the like on the display device, or by voice notification.

  The exemplary operation information providing unit 132 provides a solution related to exemplary operation information so as to obtain a golden batch result. The exemplary operation information is information for supporting exemplary plant operation (exemplary operation) for generating a golden batch as described above. The model operation information providing unit 132 acquires the skill level of the worker from the event information, and selects and provides the model operation information according to the skill level of the worker, similarly to the operation information providing unit 131 at the time of abnormality. . Since the golden batch has a predetermined trend over time, the exemplary operation information providing unit 132 provides an appropriate operation method at an appropriate timing. The exemplary operation information providing unit 132 provides exemplary operation information by, for example, displaying characters, still images, moving images, and the like on a display device, and notifying by sound. The exemplary operation information providing unit 132 may generate feedback information for the solution correcting unit 14 to be described later by collecting operation results performed on the provided exemplary operation information and results of process trends. .

  The automation information providing unit 133 provides a solution related to automation information to a plant control device. As described above, the automation information is information for operating the control device that controls the plant. The automation information providing unit 133 provides the DCS or PLC with a program that can be executed by the DCS or PLC, for example. For example, when the operation to be performed on a predetermined event is simple enough to be performed in a simple determination, the automated information providing unit 133 provides the automated information to the control device by providing the automated information. It can be incorporated as a program.

  The e-learning information providing unit 134 provides e-learning information related to e-learning as a solution according to the level of the worker who is an educated person. The e-learning information is e-learning learning content that can be provided to the worker. The educated person is a worker whose skill is to be improved. The e-learning information is content for improving the skill level of the worker, and is, for example, a manual document, a work training program, or a work support program.

  For example, the e-learning information providing unit 134 may provide e-learning information for each skill level of the educated person. For example, the e-learning information providing unit 134 can select the skill level of the worker and provides e-learning information corresponding to the selected skill level. The skill level may be a plurality of levels, for example, for newcomers, for mid-level employees, and for skill levels. The e-learning information may be, for example, an operation training program. The operation training program, for example, asks the trainee a task that simulates an event corresponding to the work site, and determines the trainee's level by asking the trainee for an answer. The knowledge level of the trainer may be improved. The operation training program may utilize a program obtained by collecting the actions and sensibilities of workers at a mid-level or skilled level by IoT. Further, the operation training program may recognize a skill level as an operator based on the correct answer rate of the trainee and provide a higher level task. The operation training program may adjust the difficulty level of questions according to the skill level of the trainee. The program for operation training is a formalization of the knowledge of a worker with a high skill level, and it is possible to transfer skills.

  The e-learning information providing unit 134 may be, for example, a web server that can provide a web page to a web browser. By providing e-learning information in a Web browser, use from a wide range of devices such as PCs and smartphones can be facilitated.

  The solution correction unit 14 has functions of a feedback information acquisition unit 141 and a feedback information application unit 142, and provides information for correcting the content of the solution provided in the solution providing unit 13.

  When the content to be corrected is found in the content of the solution content generated by the solution generation unit 122, the feedback information acquisition unit 141 acquires the content to be corrected as feedback information. The modification of the content content includes deletion, addition or change of part or all of the content. The feedback information acquisition unit 141 acquires, for example, correction information corrected by an operator who uses content. The content correction is performed, for example, when there is a change in the operation target or a change in the set value of the device due to a change in the plant process.

  The feedback information application unit 142 applies the feedback information acquired by the feedback information acquisition unit 141 to the content content. For example, the feedback information application unit 142 provides feedback information to the extraction unit 121 and causes regeneration of the determination logic. Further, the feedback information application unit 142 may directly correct the content generated by the solution generation unit 122 based on the feedback information.

  The operation support apparatus 1 has an information acquisition unit 11, a solution analysis unit 12, a solution provision unit 13, a solution correction unit 14, an event information acquisition unit 111, an event information acquisition unit 112, a perceptual information acquisition unit 113, and an operation information acquisition. Unit 114, determination criterion acquisition unit 115, extraction unit 121, solution generation unit 122, abnormal operation information provision unit 131, exemplary operation information provision unit 132, automation information provision unit 133, e-learning information provision unit 134, feedback information acquisition unit Each function of 141 and the feedback information application unit 142 has been described as being realized by software as described above. However, at least one or more of the above functions of the operation support apparatus 1 may be realized by hardware.

  In addition, any one of the above functions that the operation support apparatus 1 has may be implemented by dividing one function into a plurality of functions. In addition, the operation support device 1 may implement any two or more functions in a single function.

  Further, the operation support device 1 may be a device realized by a single housing or a system realized by a plurality of devices connected via a network or the like. For example, the operation support device 1 may be a virtual device such as a cloud service provided by a cloud computing system. The operation support device 1 may be a general-purpose computer such as a server device or a dedicated device with limited functions.

  Moreover, you may make it implement | achieve at least 1 or more functions in another apparatus among said each function of the operation assistance apparatus 1. FIG. That is, the operation support apparatus 1 does not have to have all the functions described above, and may have some functions.

  Next, the event information acquisition operation will be described with reference to FIG. FIG. 3 is a flowchart illustrating an example of an event information acquisition operation of the operation support apparatus 1 according to the embodiment. The operation of the operation support apparatus 1 described below is executed by an operation support program executed by the operation support apparatus 1. Therefore, the operation subject will be described as the operation support apparatus 1.

  In FIG. 3, the operation support apparatus 1 determines whether event information has been acquired (step S11). Whether or not event information has been acquired can be determined, for example, by whether or not the event information acquisition unit 111 has acquired event information. If it is determined that event information has not been acquired (step S11: NO), the operation support apparatus 1 repeats the operation of step S11 and waits for acquisition of event information.

  On the other hand, if it is determined that event information has been acquired (step S11: YES), the operation support apparatus 1 records the acquired event information (step S12). The event information recorded in step S12 can include accompanying information for associating with perceptual information, for example. As described above, the accompanying information is, for example, event information acquisition date and time (or event occurrence date and time), event occurrence location (part in the plant), worker identification information at the time of event occurrence, and the like.

  After performing the process of step S12, the operation assistance apparatus 1 determines whether recording is complete | finished (step S13). The determination as to whether or not to end the recording can be made based on, for example, whether or not a recording end instruction from the operator has been acquired. An operator may perform operations for a plurality of events sequentially. One event may be recorded as one event information (step S12), and when an operation for continuous events is performed, the recording operation may be continued until a recording end instruction is given. When it is determined not to end the recording (step S13: NO), the operation support device 1 returns to the process of step S11 and repeats the operation of acquiring event information. On the other hand, when it is determined that the recording is to be ended (step S13: YES), the operation support apparatus 1 ends the operation shown in the flowchart.

  Next, the event information acquisition operation will be described with reference to FIG. FIG. 4 is a flowchart illustrating an example of the event information acquisition operation of the operation support apparatus 1 according to the embodiment.

  In FIG. 4, the operation support apparatus 1 determines whether event information has been acquired (step S21). Whether or not event information has been acquired can be determined, for example, by whether or not the event information acquisition unit 112 has acquired event information. If it is determined that event information has not been acquired (step S21: NO), the operation support apparatus 1 waits for acquisition of event information by repeating the operation of step S21.

  On the other hand, when it is determined that event information has been acquired (step S21: YES), the operation support apparatus 1 records the acquired event information (step S22). The event information recorded in step S22 can include accompanying information for associating with perceptual information, for example. As described above, the incidental information includes, for example, event information acquisition date (or event occurrence date), event occurrence location (plant site, sensor ID, field device ID, etc.), operator's time at the event occurrence Identification information and the like.

  After performing the process of step S22, the operation assistance apparatus 1 determines whether recording is complete | finished (step S23). The determination as to whether or not to end the recording can be made based on, for example, whether or not a recording end instruction from the operator has been acquired. An operator may perform operations for a plurality of events sequentially. One event may be recorded as one event information (step S22), and when an operation for continuous events is performed, the recording operation may be continued until a recording end instruction is given. When it is determined not to end the recording (step S23: NO), the operation support apparatus 1 returns to the process of step S21 and repeats the event information acquisition operation. On the other hand, when it is determined that the recording is to be ended (step S23: YES), the operation support apparatus 1 ends the operation shown in the flowchart.

  Next, the perceptual information acquisition operation will be described with reference to FIG. FIG. 5 is a flowchart illustrating an example of the perceptual information acquisition operation of the operation support apparatus 1 according to the embodiment.

  In FIG. 5, the operation support apparatus 1 determines whether or not perceptual information has been acquired (step S31). Whether or not perceptual information has been acquired can be determined by whether or not the perceptual information acquisition unit 113 has acquired perceptual information, for example. If it is determined that the perceptual information has not been acquired (step S31: NO), the operation support device 1 repeats the operation of step S31 and waits for the acquisition of the perceptual information.

  On the other hand, when it is determined that the perceptual information has been acquired (step S31: YES), the operation support apparatus 1 records the acquired perceptual information (step S32). The perceptual information recorded in step S32 can include accompanying information for associating with event information or the like, for example. As described above, the accompanying information is, for example, perception information acquisition date (or worker perception date), worker identification information, location perceived by the worker, worker movement route, worker skill level, and the like. is there.

  After performing the process of step S32, the operation assistance apparatus 1 determines whether recording is complete | finished (step S33). The determination as to whether or not to end the recording can be made based on, for example, whether or not a recording end instruction from the operator has been acquired. An operator may perform operations for a plurality of perceptions sequentially. One perception may be recorded as one perceptual information (step S32), and when an operation for continuous perception is performed, the recording operation may be continued until a recording end instruction is given. When it is determined not to end the recording (step S33: NO), the operation support device 1 returns to the process of step S31 and repeats the perceptual information acquisition operation. On the other hand, when it is determined that the recording is to be ended (step S33: YES), the operation support apparatus 1 ends the operation shown in the flowchart.

  Next, the operation information acquisition operation will be described with reference to FIG. FIG. 6 is a flowchart illustrating an example of operation information acquisition operation of the operation support apparatus 1 according to the embodiment.

  In FIG. 6, the operation support apparatus 1 determines whether operation information has been acquired (step S41). Whether or not the operation information has been acquired can be determined based on, for example, whether or not the operation information acquisition unit 114 has acquired the operation information. When it is determined that the operation information has not been acquired (step S41: NO), the operation support apparatus 1 repeats the operation of step S41 and waits for the acquisition of operation information.

  On the other hand, when it is determined that the operation information has been acquired (step S41: YES), the operation support apparatus 1 records the acquired operation information (step S42). The perceptual information recorded in step S42 can include accompanying information to be associated with, for example, event information. As described above, the accompanying information includes, for example, operation information acquisition date / time (or work execution date / time), worker identification information, place where the work was performed, worker skill level, and the like.

  After performing the process of step S42, the operation assistance apparatus 1 judges whether recording is complete | finished (step S43). The determination as to whether or not to end the recording can be made based on, for example, whether or not a recording end instruction from the operator has been acquired. An operator may perform a plurality of operations sequentially. One operation may be recorded as one piece of operation information (step S42), and when a continuous operation is performed, the recording operation may be continued until a recording end instruction is given. When it is determined not to end the recording (step S43: NO), the operation support device 1 returns to the process of step S41 and repeats the operation information acquisition operation. On the other hand, when it is determined that the recording is to be ended (step S43: YES), the operation support apparatus 1 ends the operation shown in the flowchart.

  Next, the skill-specific solution generation operation will be described with reference to FIG. FIG. 7 is a flowchart illustrating an example of the skill-specific solution generation operation of the operation support apparatus according to the embodiment.

  In FIG. 7, the operation support apparatus 1 acquires the event information recorded by the process of step S12 (step S51). After performing the process of step S51, the operation assistance apparatus 1 acquires the event information recorded by the process of step S22 (step S52). After performing the process of step S52, the operation assistance apparatus 1 acquires the perceptual information recorded by the process of step S32 (step S53). After performing the process of step S53, the operation assistance apparatus 1 acquires the operation information recorded by the process of step S42 (step S54). After performing the process of step S54, the operation assistance apparatus 1 acquires a criterion (step S55). The determination criterion is acquired and recorded by the determination criterion acquisition unit 115.

  After executing the process of step S55, the operation support apparatus 1 sorts the acquired event information, event information, perceptual information, and operation information in time series based on the time information of the accompanying information, and sets the time of each information. The specific order is clarified (step S56). For example, in a large-scale plant, a huge number of event information and event information are acquired. By sorting and comparing information in time series in the process of step S56, it is possible to sort out a huge amount of information and facilitate the extraction of the relationship between the information.

  After performing the process of step S56, the operation assistance apparatus 1 extracts relevance (step S57). Details of the process in step S57 will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of the relevance extraction operation of the operation support apparatus in the embodiment.

  In FIG. 8, the operation support apparatus 1 extracts event information (step S571). The extraction of event information can be executed by the extraction unit 121 extracting event information to be searched, for example. For example, the extraction unit 121 extracts event information by searching event information recorded from identification information that identifies an alarm event that has occurred in the past in a predetermined process and a skilled worker who has performed an abnormal operation on the alarm event. To do.

  After performing the process of step S571, the operation assistance apparatus 1 extracts the event information corresponding to the event extracted by the process of step S571 (step S572). The event information is sorted in time series in the process of step S56, for example. For example, the operation support apparatus 1 extracts an event whose occurrence time is close from recorded events. For example, a plant or process in which an alarm event has occurred may be extracted as a search condition. Further, the operation support apparatus 1 may search for sales data, quality data, and environmental data related to the plant in which the alarm event has occurred as a search condition.

  After executing the process of step S572, the operation support apparatus 1 determines whether or not the extracted event number n is 1 (n = 1) (step S573). The number of events varies depending on the search condition when extracted in the process of step S752. When the number of events n is 1 (step S573: YES), the operation support apparatus 1 determines whether or not automation is possible (step S574). Whether or not automation is possible is a case where the relationship between the occurrence of an event and an event is clear and it is determined that the event can be considered as an event occurrence condition. Whether or not automation is possible can be executed, for example, in a determination program of the operation support apparatus 1. Further, whether or not automation is possible may be executed by allowing the operation support apparatus 1 to input a determination and allowing a skilled worker or the like to input the determination.

  If it is determined that automation is possible (step S574: YES), the operation support apparatus 1 extracts the relationship between the extracted event information and event information (step S575), and the relationship extraction process (step S57). Terminate the process.

  On the other hand, when it is determined that automation is not possible (step S574: NO), or when the number of events n is not one (step S573: NO), the operation support device 1 receives perceptual information corresponding to each event. Operation information is extracted (step S576). For example, when the number of events is n, the operation support apparatus 1 extracts perceptual information and operation information corresponding to the event (i) (where i = 1 to n is a natural number). In this embodiment, the operation method is extracted for each skill. For example, even if the perception information is the same for the same event, workers with different skill levels may perform different operations. For example, if an event is within a predetermined range of pressure measured by a pressure gauge installed in the reaction tank, a new worker is skilled in controlling the input valve of the raw material injected into the reaction tank. An operator may increase the rotation speed of a pump that discharges a product from a reaction tank. By extracting the operation method for each skill, it is possible to extract the difference in operation according to the skill level.

  After executing the process of step S576, the operation support apparatus 1 extracts skill-specific logic (step S577). The skill-specific logic can be executed by, for example, extracting a judgment standard corresponding to an event, perceptual information, or operation information based on the judgment standard acquired by the judgment standard acquisition unit 115 and associating each information. . The information to be associated is not limited. For example, two or more pieces of information among event information, event information, perceptual information, and operation information can be associated with each other. Information may be associated with, for example, event information and operation information associated with different types of information, or event information and event information associated with the same type of information. Good. The skill-specific logic may include one of these associations (associations) or may be a combination of a plurality of associations. By extracting skill-specific logic, it becomes possible to specify skill-specific operations based on event information, event information, and perceptual information.

  After executing the process of step S577, the operation support apparatus 1 determines whether i = n (step S578). If it is determined that i = n is not satisfied (step S578: NO), i is incremented by 1 (step S579), and the processes of steps S576 to S578 are repeated. On the other hand, if it is determined that i = n (step S578: YES), the operation support apparatus 1 ends the relevance extraction process (step S57). That is, in steps S576 to S579, a process for extracting logic according to skill in each event (i) is executed.

  Returning to the description of FIG. After performing the process of step S57, the operation assistance apparatus 1 produces | generates a logic according to skill (step S58). The generation of logic for each skill can be executed by integrating all the events for the logic for each skill extracted in the process of step S577. For example, the skill-specific logic may be generated by selecting only logics that are highly related from the extracted logic. The magnitude of relevance may be calculated by, for example, the frequency of association and the number of cases. Further, the generation of skill-specific logic may be generated including all the extracted logic.

  After performing the process of step S58, the operation assistance apparatus 1 produces | generates the solution according to skill (step S59). The skill-specific solution is, for example, abnormal operation information, model operation information, automation information, or e-learning information. Which solution is to be generated may be specified by selection, for example.

  After executing the process of step S59, the operation support apparatus 1 records the skill-specific solution generated by the process of step S59 (step S60), and ends the operation shown in the flowchart. The recorded solution is read from the solution providing unit 13 and provided.

  Next, the solution providing operation will be described with reference to FIG. FIG. 9 is a flowchart illustrating an example of the level-specific solution providing operation of the operation support apparatus according to the embodiment.

  In FIG. 9, the operation assistance apparatus 1 acquires a skill level (step S61). The skill level may be acquired, for example, when the solution providing unit 13 displays the skill level so that the skill level can be selected, and an operator who receives the provision of the solution selects the skill level.

  After performing the process of step S61, the operation assistance apparatus 1 branches a process according to the selected skill level (step S62). The number of skill levels that can be branched in step 62 may be a predetermined number of levels from newcomers to takumi levels, for example. FIG. 9 shows a case where the mid-level is n stages from LV1 to LVn.

  When the selected skill level is the “new face level” (step S62: “new face level”), the operation support apparatus 1 provides content corresponding to the new face level (step S63). When the selected skill level is “LV (level) 1 mid-level” (step S62: “LV 1 mid-level”), the operation support apparatus 1 provides content corresponding to the LV 1 mid-level (step S64). . When the selected skill level is “LV2 mid-level” (step S62: “LV2 mid-level”), the operation support apparatus 1 provides content corresponding to the LV2 mid-level (step S65). When the selected skill level is “LVn mid-level” (step S62: “LVn mid-level”), the operation support device 1 provides content corresponding to the LVn mid-level (not shown).

  Content at each skill level is selected corresponding to event information relating to an event that occurs during operation of the plant. For example, a confirmation item (event) to be confirmed by the operator may be instructed based on event information corresponding to the event information, and an operation item (operation content) may be instructed according to the content of the confirmation item. In addition, the content at each skill level may indicate a confirmation item (event) based on event information corresponding to event information and operation information. Further, as content at each skill level, an operation item (operation content) may be instructed based on event information corresponding to event information and perceptual information. These contents can be generated by associating the acquired event information, event information, perceptual information, and operation information as described with reference to FIG.

  Next, the operation support feedback operation will be described with reference to FIG. FIG. 10 is a flowchart illustrating an example of a work support feedback operation of the operation support apparatus 1 according to the embodiment.

  In FIG. 10, the operation support apparatus 1 determines whether feedback information has been acquired (step S71). The determination as to whether or not the feedback information has been acquired can be made based on whether or not the feedback information acquisition unit 141 has received input of information from the worker, for example. If it is determined that the feedback information has not been acquired (step S71: NO), the operation support apparatus 1 repeats the process of step S71 and waits for the acquisition of feedback information.

  When it is determined that the feedback information has been acquired (step S71: YES), the operation support apparatus 1 determines whether or not the proposed content is appropriate (step S72). The determination as to whether or not the content of the proposal is appropriate can be made, for example, based on whether or not the feedback information acquisition unit 141 includes correction information in the feedback information input from the operator. If it is determined that the proposed content is appropriate (step S72: YES), the operation support apparatus 1 ends the operation support feedback operation shown in the flowchart. In other words, the skill-based solution is not modified. If the proposal content is appropriate, that fact may be recorded and used to generate the proposal content in the decision logic.

  On the other hand, when it is determined that the proposed content is not appropriate (step S72: NO), the operation support apparatus 1 corrects the proposed operation content (step S73). The operation content may be corrected by correcting the skill-specific logic extraction in step S577, or only by correcting the solution content such as the generated work support program. After executing the process of step S73, the operation support apparatus 1 regenerates the skill-specific solution (step S74) and ends the operation support feedback operation shown in the flowchart.

  Note that machine learning may be used to correct the operation content. For example, by inputting the determination result in step S72 to the support vector machine, appropriate proposal contents can be learned. In this embodiment, since it is possible to obtain big data other than the perceptual information used by the operator to determine the operation content, information that is significant to information that even a craftsman-level worker did not notice through machine learning May be able to discover.

  Next, the hardware configuration of the operation support apparatus 1 will be described with reference to FIG. FIG. 11 is a block diagram illustrating an example of a hardware configuration of the operation support apparatus 1 according to the embodiment.

  11, the operation support apparatus 1 includes a CPU 101, a RAM (Random Access Memory) 102, a ROM (Read Only Memory) 103, an HDD 104, a touch panel 105, a communication I / F (Interface) 106, and a communication I / F 107.

  The operation support device 1 can be realized by a general-purpose device such as a notebook PC, a tablet PC, a PDA, or a smartphone, or a device dedicated to operation support, for example. The operation support apparatus 1 is an apparatus that executes the operation support program described with reference to FIG.

  The CPU 101 controls the operation support apparatus 1 by executing an operation support program stored in the RAM 102, ROM 103, or HDD 104. The operation support program is acquired from, for example, a recording medium that records the operation support program or a server that provides the operation support program via a network, is installed in the HDD 104, and is stored in the RAM 102 so as to be readable from the CPU 101.

  The touch panel 105 has an operation display function having an operation input function and a display function. The touch panel 105 displays a UI (User Interface) of a program executed by the operation support apparatus 1. The touch panel 105 enables an operator to input an operation using a fingertip or a touch pen. The operation support apparatus 1 in this embodiment will be described using a touch panel 105 having an operation display function. However, the operation support apparatus 1 includes a display apparatus having a display function and an operation input apparatus having an operation input function. There may be. In that case, the display screen of the touch panel 105 can be implemented as a display screen of the display apparatus, and the operation of the touch panel 105 can be implemented as an operation of the operation input apparatus. Note that the touch panel 105 may be realized in various forms such as a head mount type, a glasses type, and a watch type display.

  The communication I / F 106 controls communication via the network 9 with other devices that use general-purpose communication such as wireless LAN communication, wired LAN communication, infrared communication, and short-range wireless communication. Other devices are, for example, devices on which the cloud server 91 and the external application 92 are arranged. The cloud server 91 is a server that provides a cloud service by cloud computing. The cloud server 91 may primarily store big data, for example. The cloud server 91 can provide information common to the operation support apparatus 1 to other operation support apparatuses (not shown). The external application 92 is an application that operates outside the operation support apparatus 1, and may be a part of the function of the operation support apparatus described with reference to FIG. The communication I / F 106 includes other operation support devices (not shown), field devices capable of general-purpose communication, a maintenance information management server that manages maintenance information, a DCS (Distributed Control System) control device, and a PLC (PLC). Programmable Logic Controller) or the like. Although FIG. 12 shows the case where the external application 92 is arranged in a device connected via a network, an application having the same function can be recorded on a recording medium readable from the operation support device 1 or the operation support device 1. May be present in the content.

  The communication I / F 107 controls field communication with the field device 2 using a communication protocol that can be used in the field device. Various field communication protocols are used in various field devices used in a plant. The communication I / F 107 controls communication with the field device 2 that uses field communication such as ISA100, HART (registered trademark), BRAIN (registered trademark), FOUNDATION Fieldbus, PROFIBUS, and the like. The operation support apparatus 1 may have a plurality of communication I / Fs 107 according to the type of field communication.

  As described above, the operation support apparatus according to the present embodiment acquires an event information acquisition unit that acquires event information related to an event that occurs during operation of the plant, and event information related to an event detected in the plant. An event information acquisition unit, a perception information acquisition unit that acquires perception information related to perception recognized by an operator, an operation information acquisition unit that acquires operation information related to the operation of the plant performed by the worker, and the event An extraction unit that extracts the relationship between the information and at least one of the event information, the perceptual information, and the operation information, and a solution that supports the operation of the plant based on the extracted relationship A solution generation unit. Thereby, the succession of the skill concerning the work corresponding to the event which generate | occur | produces in operation of a plant can be made easy.

  Note that the above-described operation support device may be a device having the above-described function. For example, the operation support device may be realized by a system configured by combining a plurality of devices and communicatively connecting each device. Good. Further, the operation support device may be realized as a part of the function of another device connected via a network.

  The operation support method in the present embodiment includes an event information acquisition step for acquiring event information related to an event that occurs during operation of the plant, and an event information acquisition step for acquiring event information related to an event detected in the plant A sensory information acquisition step for acquiring sensory information related to the perception recognized by the worker, a control information acquisition step for acquiring control information related to the operation of the plant performed by the worker, and the event information, An extraction step for extracting a relationship with any one of the event information, the perceptual information or the operation information, and a solution generation step for generating a solution for supporting the operation of the plant based on the extracted relationship Including. Thereby, the succession of the skill concerning the work corresponding to the event which generate | occur | produces in operation of a plant can be made easy.

  The operation support method described above may be any method including the steps described above, and the execution of these steps may be performed in an arbitrary order. That is, the execution timing of each step described above is arbitrary. For example, one of the above steps may be executed several times before another step is executed.

  Further, a program for realizing the functions constituting the apparatus described in the present embodiment is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into a computer system and executed. Thus, the various processes described above in the present embodiment may be performed. Here, the “computer system” may include an OS and hardware such as peripheral devices. Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used. The “computer-readable recording medium” means a flexible disk, a magneto-optical disk, a ROM, a writable nonvolatile memory such as a flash memory, a portable medium such as a CD-ROM, a hard disk built in a computer system, etc. This is a storage device.

  Further, the “computer-readable recording medium” refers to a volatile memory (for example, DRAM (Dynamic) in a computer system serving as a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. Random Access Memory)) that holds a program for a certain period of time is also included. The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. The program may be for realizing a part of the functions described above. Furthermore, what implement | achieves the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

  The embodiment of the present invention has been described above with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes various modifications within the scope of the present invention. It is.

DESCRIPTION OF SYMBOLS 1 Operation support apparatus 11 Information acquisition part 100 Operation support system 111 Event information acquisition part 112 Event information acquisition part 113 Perception information acquisition part 114 Operation information acquisition part 115 Judgment criteria acquisition part 12 Solution analysis part 121 Extraction part 122 Solution generation part 13 Solution Providing unit 131 Abnormal operation information providing unit 132 Model operation information providing unit 133 Automation information providing unit 134 e-Learning information providing unit 14 Solution correcting unit 141 Feedback information obtaining unit 142 Feedback information applying unit 2A Sales database 2B Quality database 2C On-site database 3 Solution database by skill 4 Execution environment 101 CPU
102 RAM
103 ROM
104 HDD
105 Touch panel 106 Communication I / F
107 Communication I / F
5 Field device 9 Network 91 Cloud server 92 External application

Claims (13)

An event information acquisition unit for acquiring event information related to an event that occurs during operation of the plant;
An event information acquisition unit for acquiring event information relating to an event detected in the plant;
A perceptual information acquisition unit for acquiring perceptual information related to the perception recognized by the worker;
An operation information acquisition unit that acquires operation information related to the operation of the plant performed by the worker;
An extraction unit that extracts a relationship between the event information and at least one of the event information, the perceptual information, and the operation information;
An operation support apparatus comprising: a solution generation unit that generates a solution that supports the operation of the plant based on the extracted relevance.   The operation according to claim 1, wherein the extraction unit extracts the association based on a time-series comparison between the event information and at least one of the event information, the perceptual information, and the operation information. Support device. The event information acquisition unit acquires an alarm occurrence event to notify the abnormality of the plant,
The operation support apparatus according to claim 1, wherein the operation information acquisition unit acquires the operation information related to an abnormal operation performed by the worker. The event information acquisition unit acquires a batch occurrence event indicating occurrence of a batch indicating a predetermined behavior in the plant,
The operation support apparatus according to any one of claims 1 to 3, wherein the operation information acquisition unit acquires operation information related to an exemplary operation for generating the batch occurrence event performed by an operator. The extraction unit extracts the relevance according to the skill level of the worker,
The operation support device according to any one of claims 1 to 4, wherein the solution generation unit generates the solution according to the skill level.   The operation support apparatus according to claim 1, further comprising a solution providing unit that provides the generated solution in response to the occurrence of the event during operation of the plant.   The operation support apparatus according to claim 1, wherein the perceptual information acquisition unit acquires information about an external apparatus connected via a network.   The operation support apparatus according to any one of claims 1 to 7, wherein the perceptual information acquisition unit acquires at least one information of vibration, sound, or alarm generated by the facility.   The operation support device according to any one of claims 1 to 8, wherein the perceptual information acquisition unit acquires visual information that the worker is visually recognizing from a gaze detection device that detects the gaze of the worker. A judgment criterion obtaining unit for obtaining a judgment criterion of the worker who performed the operation;
The operation support apparatus according to any one of claims 1 to 9, wherein the extraction unit further extracts the relevance based on the acquired determination criterion. An event information acquisition step for acquiring event information relating to an event that occurs during operation of the plant;
An event information acquisition step of acquiring event information relating to an event detected in the plant;
A perceptual information acquisition step of acquiring perceptual information related to the perception recognized by the worker;
An operation information acquisition step for acquiring operation information related to the operation of the plant performed by the worker,
An extraction step of extracting a relationship between the event information and at least one of the event information, the perceptual information, and the operation information;
A solution generation step of generating a solution for supporting the operation of the plant based on the extracted relation. An event information acquisition process for acquiring event information relating to an event that occurs during operation of the plant;
Event information acquisition processing for acquiring event information relating to an event detected in the plant;
Perceptual information acquisition processing for acquiring perceptual information related to the perception recognized by the worker;
Operation information acquisition processing for acquiring operation information related to the operation of the plant performed by the worker;
An extraction process for extracting a relationship between the event information and at least one of the event information, the perceptual information, and the operation information;
An operation support program that causes a computer to execute a solution generation process for generating a solution that supports the operation of the plant based on the extracted relation. An event information acquisition process for acquiring event information relating to an event that occurs during operation of the plant;
Event information acquisition processing for acquiring event information relating to an event detected in the plant;
Perceptual information acquisition processing for acquiring perceptual information related to the perception recognized by the worker;
Operation information acquisition processing for acquiring operation information related to the operation of the plant performed by the worker;
An extraction process for extracting a relationship between the event information and at least one of the event information, the perceptual information, and the operation information;
A recording medium recording an operation support program that causes a computer to execute a solution generation process for generating a solution that supports the operation of the plant based on the extracted relation.

Images