Apparatus, method, and program for exploring recovery operations.

Abstract

To provide a device, method, and program for searching for a return operation.SOLUTION: A device includes: a state data acquisition unit that acquires state data indicating the state of a facility; an evaluation unit that evaluates a trial operation based on a change in the state data when a control target is controlled according to the trial operation to return the facility from an abnormality to a normal state; and a search unit that searches for a return operation for returning the facility from an abnormality to a normal state based on the evaluation result. The device may further include a target data determination unit that determines target data indicating a target state of the facility for returning the facility from an abnormality to a normal state, and the evaluation unit may evaluate the trial operation based on a change in distance between the state data and the target data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an apparatus, a method, and a program for searching for a restoration operation. [Background Art]

[0002] Patent Document 1 describes that "a plant operation apparatus is provided which can identify an abnormal cause of a plant and automatically perform a restoration operation from an abnormal state without operator intervention." [Prior Art Document] [Patent Document] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-229109 [Summary of the Invention]

[0003] According to a first aspect of the present invention, there is provided an apparatus for searching for a restoration operation. The apparatus comprises: a state data acquisition unit that acquires state data indicating a state of a facility; an evaluation unit that evaluates a trial operation based on a change in the state data when a controlled object is controlled in accordance with the trial operation to be tried for restoring the facility from an abnormality to a normal state; and a search unit that searches for a restoration operation for restoring the facility from the abnormality to the normal state based on the evaluation result.

[0004] The apparatus may further include a target data determination unit that determines target data indicating a target state of the facility for restoring the facility from the abnormality to the normal state, and the evaluation unit may evaluate the trial operation based on a change in a distance between the state data and the target data.

[0005] In any of the above apparatuses, the target data determination unit may determine the target data based on a plurality of normal data pieces indicating the state data when the facility is in a normal state.

[0006] In any of the above apparatuses, the target data determination unit may determine the target data based on a statistic of the plurality of normal data pieces.

[0007] In any of the above devices, the target data determination unit may determine the target data based on the time series of the plurality of normal data.

[0008] Any of the above devices further includes an index acquisition unit that acquires an evaluation index that evaluates the state of the equipment in response to inputting the state data into an evaluation model, and the evaluation unit may evaluate the trial operation based on the change in the evaluation index.

[0009] Any of the above devices may further include the evaluation model.

[0010] In any of the above devices, the search unit may sequentially change one of the multiple operation parameters included in the trial operation when searching for the return operation.

[0011] In any of the above-mentioned devices, the search unit may omit changing one of the operation parameters to some of the candidate operation parameters among the multiple candidate operation parameters.

[0012] Any of the above devices may further include a detection unit that detects abnormalities in the equipment based on the status data.

[0013] Any of the above devices may further include a warning unit that issues a warning if the equipment does not return to normal from an abnormal state within predetermined conditions even after the recovery operation has been searched for.

[0014] In any of the above devices, the warning unit may issue a warning if the elapsed time until the equipment returns to normal after an abnormality has been detected exceeds a predetermined threshold.

[0015] In any of the above devices, the warning unit may issue a warning if the number of times the controlled object has been controlled in accordance with the trial operation exceeds a predetermined threshold.

[0016] Any of the above devices may further include a control unit that controls the controlled object in accordance with the trial operation.

[0017] A second aspect of the present invention provides a method for searching for a recovery operation. The method comprises a computer acquiring state data indicating the state of equipment, evaluating the trial operation based on changes in the state data when the controlled object is controlled according to the trial operation attempted to restore the equipment from an abnormality to normal, and searching for a recovery operation to restore the equipment from an abnormality to normal based on the evaluated result.

[0018] A third aspect of the present invention provides a program for searching for a recovery operation. The program is executed by a computer and causes the computer to function as: a state data acquisition unit that acquires state data indicating the state of equipment; an evaluation unit that evaluates the trial operation based on changes in the state data when the controlled object is controlled according to a trial operation attempted to restore the equipment from an abnormality to normal; and a search unit that searches for a recovery operation to restore the equipment from an abnormality to normal based on the evaluated results.

[0019] It should be noted that the above summary of the invention does not enumerate all of its features. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0020] [Figure 1] An example of a block diagram of a control system 1 which may include the device 1000 according to this embodiment is shown. [Figure 2] Here is the first example of determining target data. [Figure 3] Here is a second example of determining target data. [Figure 4] An example of a flowchart showing a method that the apparatus 1000 according to this embodiment may perform is shown. [Figure 5]Another example in the block diagram of the control system 1 which may include the apparatus 1000 according to the present embodiment is shown. [Figure 6] An example in the block diagram of the control system 1 which may include the apparatus 1000 according to a modification of the present embodiment is shown. [Figure 7] An example in the flow diagram of a method that may be executed by the apparatus 1000 according to a modification of the present embodiment is shown. [Figure 8] Another example in the block diagram of the control system 1 which may include the apparatus 1000 according to a modification of the present embodiment is shown. [Figure 9] An example of a computer 9900 in which a plurality of aspects of the present invention may be embodied in whole or in part is shown. DETAILED DESCRIPTION OF THE INVENTION

[0021] Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the claimed invention. In addition, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0022] FIG. 1 shows an example in a block diagram of a control system 1 which may include an apparatus 1000 according to the present embodiment. Note that each of these blocks is a functionally separated functional block, and does not necessarily have to match an actual device configuration. That is, being shown as a single block in the present drawing does not necessarily mean that the block is configured by a single device. Also, being shown as separate blocks in the present drawing does not necessarily mean that these blocks are configured by separate devices. The same applies to all subsequent block diagrams. The control system 1 may include a facility 10, a control device 20, and the apparatus 1000.

[0023] Equipment 10 is a device that manufactures products from raw materials. Equipment 10 may be a single device or a composite device formed by combining multiple devices. Equipment 10 may be, for example, an entire plant or factory, or a group of devices in a segment of a plant or factory. Examples of plants include industrial plants such as chemical and biotechnology plants, plants that manage and control wellheads and surrounding areas of gas and oil fields, plants that manage and control power generation such as hydroelectric, thermal, and nuclear power plants, plants that manage and control environmental power generation such as solar and wind power plants, and plants that manage and control water and sewage systems and dams.

[0024] Equipment 10 may be equipped with one or more sensors (not shown) capable of measuring various conditions (physical quantities) inside and outside Equipment 10. The sensors may output measured values ​​PV (Process Variable) such as temperature, pressure, or flow rate at various points in Equipment 10. State data indicating the state of Equipment 10 may include such measured values ​​PV. The state data may further include manipulated variables MV (Manipulated Variable) indicating the degree of opening or closing of valves. The state data may further include consumption data indicating the amount of energy consumed or raw materials consumed in Equipment 10. The state data may further include environmental data indicating physical quantities that may act as disturbances in Equipment 10.

[0025] Equipment 10 may be provided with a control object 15. In this figure, for the sake of explanation, only one control object 15 is shown, but equipment 10 may be provided with one or more control objects 15.

[0026] The controlled object 15 is the equipment to be controlled. The controlled object 15 may be an actuator such as a valve, heater, motor, fan, or switch, i.e., an operating end, that controls at least one physical quantity of an object related to the process of the equipment 10, such as the quantity, temperature, pressure, flow rate, speed, or pH, and may perform a given operation according to the operating quantity. However, it is not limited to this. The controlled object 15 may also be a controller that controls the operating end. In other words, the term "control" as used herein may be interpreted broadly to include not only direct control of the operating end but also indirect control of the operating end via a controller.

[0027] The control device 20 is a device that controls the controlled object 15. The control device 20 may acquire state data indicating the state of the equipment 10 and control the controlled object 15 based on the state data. In this case, the control device 20 may control the controlled object 15 by PID (Proportional Integral Differential) control or by AI (Artificial Intelligence) control.

[0028] AI control refers to control using an operational model generated by machine learning. Such an operational model may be generated, for example, by reinforcement learning, in which an evaluation index that assesses the state of equipment 10 is used as at least part of the reward. Furthermore, the evaluation index used in such reinforcement learning may be output from an evaluation model that has been trained by machine learning to output an evaluation index in response to state data being input.

[0029] An abnormality may occur in the equipment 10 while the control target 15 is under the control of the control device 20. In such cases, it is desirable to automatically restore the equipment 10 by controlling the control target 15 according to the recovery operation. However, the equipment 10 can take on various abnormal states depending on various conditions. To address such cases, it is conceivable to define a recovery operation for each abnormal state in a database or the like. However, it is practically impossible to consider all abnormal states in advance, and this problem is particularly pronounced in complex equipment such as plants where various conditions interact with each other.

[0030] Therefore, the device 1000 according to this embodiment searches for a recovery operation to restore the equipment 10 from an abnormal state to normal through trial and error using the actual equipment. As a result, the device 1000 according to this embodiment can search for a recovery operation through trial and error even when the equipment 10 is in various abnormal states. This will be explained in detail. The device 1000 may include a state data acquisition unit 110, a detection unit 120, a target data determination unit 130, an evaluation unit 170, a search unit 180, and a warning unit 190.

[0031] The status data acquisition unit 110 acquires status data indicating the status of the equipment 10. The status data acquisition unit 110 may be provided mainly by a communication interface and may acquire status data from the equipment 10 via a network in a time series. However, it is not limited to this. The status data acquisition unit 110 may acquire status data from a device other than the equipment 10, or via means other than a network (various memory devices, or user input, etc.). The status data acquisition unit 110 supplies the acquired status data to the detection unit 120.

[0032] The detection unit 120 detects abnormalities in the equipment 10 based on status data. The detection unit 120 may be provided mainly by executing a program using a CPU or other processor, and may detect abnormalities in the equipment 10 based on status data acquired by the status data acquisition unit 110. In this case, the detection unit 120 may use a machine learning model that classifies the equipment 10 into a normal state and an abnormal state based on the status data. If it is determined that no abnormality has been detected in the equipment 10, the detection unit 120 attaches a normal label to the status data and supplies it to the target data determination unit 130. If it is determined that an abnormality has been detected in the equipment 10, the detection unit 120 attaches an abnormal label to the status data and supplies it to the target data determination unit 130 and the evaluation unit 170. The detection unit 120 also notifies the search unit 180 and the warning unit 190 that an abnormality has been detected in the equipment 10.

[0033] The target data determination unit 130 determines target data that indicates the target state of the equipment 10 in order to restore the equipment 10 from abnormal to normal. The target data determination unit 130 may mainly determine the target data based on a plurality of state data that are provided by the CPU and labeled as normal by the detection unit 120, i.e., a plurality of normal data that indicate the state data when the equipment is functioning normally. Details of this will be described later. The target data determination unit 130 supplies the determined target data to the evaluation unit 170.

[0034] The evaluation unit 170 evaluates the trial operation based on the changes in state data when the controlled object 15 is controlled according to the trial operation attempted to restore the equipment 10 from abnormal to normal. The evaluation unit 170 may mainly evaluate the trial operation based on the change in distance between state data, which may be provided by the CPU and labeled as abnormal by the detection unit 120, and target data determined by the target data determination unit 130. The evaluation unit 170 supplies the evaluated results to the search unit 180.

[0035] The search unit 180 searches for a recovery operation to restore the equipment 10 from abnormal to normal based on the evaluated results. The search unit 180 may be mainly provided by a communication interface and a CPU, and may supply trial operations to the control device 20 via a network. The control device 20 may then control the controlled object 15 according to the trial operations. As a result, the state of the equipment 10 changes. The state data acquisition unit 110 may acquire state data again after the control according to the trial operations. The evaluation unit 170 may evaluate the trial operations based on the changes in state data. The search unit 180 may then sequentially change one of the operation parameters included in the trial operations based on the evaluated results. By repeatedly executing this process, the search unit 180 can search for a recovery operation through trial and error based on the results evaluated by the evaluation unit 170.

[0036] The warning unit 190 issues a warning if the equipment 10 does not recover normally from an abnormal state within predetermined conditions even after the recovery operation is searched for. The warning unit 190 may be mainly provided by a display device and may display a warning screen indicating that the equipment 10 does not recover normally from an abnormal state within predetermined conditions even after the recovery operation is searched for.

[0037] The device 1000 equipped with such a functional unit may be a computer such as a PC (personal computer), tablet computer, smartphone, workstation, server computer, or general-purpose computer, or it may be a computer system in which multiple computers are connected. Such a computer system is also a computer in a broad sense. The device 1000 may also be implemented by a virtual computer environment that can run one or more times within the computer. Alternatively, the device 1000 may be a dedicated computer designed to search for recovery operations, or dedicated hardware realized by dedicated circuitry. Furthermore, if the device 1000 is connected to the internet, the device 1000 may be implemented by cloud computing.

[0038] Such a computer may include a memory for storing programs and a processor for executing programs, and the processor may implement the functions of a device 1000 by executing the programs. That is, a program may be provided which is executed by the computer and causes the computer to function as a state data acquisition unit 110 that acquires state data indicating the state of the equipment 10, an evaluation unit 170 that evaluates the trial operations based on changes in state data when the controlled object 15 is controlled according to trial operations attempted to restore the equipment 10 from abnormal to normal, and a search unit 180 that searches for a recovery operation to restore the equipment 10 from abnormal to normal based on the evaluated results.

[0039] Figure 2 shows a first example of determining target data. This figure shows the feature space defined by state data. In this figure, circles (〇) represent normal data, i.e., state data that has been labeled as normal by the detection unit 120, and crosses (×) represent abnormal data, i.e., state data that has been labeled as abnormal by the detection unit 120. The symbol 210 visualizes the decision boundary. The machine learning model that the detection unit 120 may use may be tuned by machine learning in this way to determine the boundary for classifying the equipment 10 as normal or abnormal.

[0040] Reference numeral 220 indicates the target abnormal data. When the target abnormal data is supplied from the detection unit 120, the target data determination unit 130 may determine target data that indicates the target state of the equipment 10 in order to restore the equipment 10 from abnormal to normal. In this case, the target data determination unit 130 may determine the target data based on a plurality of normal data. The target data determination unit 130 can determine such target data using various methods.

[0041] This figure illustrates an example of a method for determining target data based on statistics from multiple normal data points. Reference numeral 230 indicates the centroid of the multiple normal data points. The target data determination unit 130 may calculate the sum of the squares of the distances from the multiple normal data points and define the point where the sum of the squares of the distances is minimized as the centroid 230. In this case, the target data determination unit 130 may select the multiple normal data points to be used for statistical processing according to predetermined rules. For example, when the target abnormal data is supplied from the detection unit 120, the target data determination unit 130 may select m normal data points supplied from the detection unit 120 up to that point in chronological order and use the selected m normal data points for statistical processing.

[0042] The target data determination unit 130 may calculate a vector 240 pointing from the target abnormal data 220 to the centroid 230 of multiple normal data. The target data determination unit 130 may then determine the intersection point 250 of the vector 240 and the determination boundary 210 as the target data. In the above description, the case where the intersection point 250 of the vector 240 and the determination boundary 210 is used as the target data was shown as an example, but the target data determination unit 130 may also determine the centroid 230 itself as the target data, or any point on the vector 240 between the intersection point 250 and the centroid 230 as the target data. Furthermore, in the above description, the case where the centroid is used as a statistic was explained as an example, but the target data determination unit 130 may also determine the target data based on other statistics such as the mean, median, or mode. For example, the target data determination unit 130 can determine the target data based on statistics in multiple normal data in this way.

[0043] Figure 3 shows a second example of determining target data. In this figure, components with the same function and configuration as in Figure 2 are given the same reference numerals, and explanations are omitted below except for differences. In this figure, the numbers in circles (〇) indicate the time-series order of normal data, with smaller values ​​indicating newer data and larger values ​​indicating older data.

[0044] This figure illustrates an example of a method for determining target data based on the time series of multiple normal data points. Reference numeral 310 indicates the most recent normal data point among the selected m (m=10 in this figure) normal data points. The target data determination unit 130 may calculate a vector 320 pointing from the target abnormal data point 220 to the most recent normal data point 310. The target data determination unit 130 may then determine the intersection point 330 of the vector 320 and the determination boundary 210 as the target data point. While the above explanation uses the intersection point 330 of the vector 320 and the determination boundary 210 as the target data point, the target data determination unit 130 may also determine the most recent normal data point 310 itself as the target data point, or it may determine any point between the intersection point 330 on the vector 320 and the most recent normal data point 310 as the target data point. The target data determination unit 130 can also determine target data based on the time series of multiple normal data points in this manner, for example.

[0045] Although the methods for determining target data based on statistics from multiple normal data and the methods for determining target data based on time series from multiple normal data have been described as separate methods, the two can be combined. For example, the target data determination unit 130 may calculate a weighted average for multiple normal data by setting weights according to the time series order, such that newer data contribute more and older data contribute less. The target data determination unit 130 may then determine the target data based on the weighted average. In this way, the target data determination unit 130 can also determine the target data based on statistics from multiple normal data and time series.

[0046] Figure 4 shows an example of a flowchart of a method that the apparatus 1000 according to this embodiment may perform. Each step in this figure may be performed by the apparatus 1000, i.e., the computer, as the main operator. However, in each step, it is sufficient that the computer is the main operator overall, and it may include cases where a part other than the computer performs a part that is not the main part.

[0047] In step S1400, the computer performs initialization. For example, the computer may initialize a counter that counts the number of times the controlled object 15 has been controlled according to the trial operation k. That is, the computer may set k=0. The computer may also initialize a timer that measures the elapsed time t corresponding to the detection of an abnormality in the equipment 10. That is, the computer may set t=0.

[0048] In step S1410, the computer acquires status data indicating the state of the equipment 10. For example, a status data acquisition unit 110, which may be implemented in the computer, may acquire status data S indicating the state of the equipment 10 from the equipment 10 via the network in a time series. As an example, when k=0, the status data acquisition unit 110 may acquire status data S0. The status data acquisition unit 110 supplies the acquired status data S to the detection unit 120.

[0049] In step S1420, the computer determines whether or not it has detected an abnormality in the equipment 10 based on the state data. For example, a detection unit 120, which may be implemented in the computer, may determine whether or not it has detected an abnormality in the equipment 10 based on the state data S acquired in step S1410. As an example, when k=0, the detection unit 120 may determine whether or not it has detected an abnormality in the equipment 10 based on the state data S0. In this case, the detection unit 120 may use a machine learning model that classifies the equipment 10 into a normal state and an abnormal state based on the state data S, as described above.

[0050] If the machine learning model classifies the equipment 10 as being in a normal state in response to the input state data S, the detection unit 120 may determine that it has not detected any abnormality in the equipment 10 (No). In this case, the detection unit 120 assigns a normal label n to the state data S and supplies it to the target data determination unit 130. The computer then returns to step S1400 to continue the flow.

[0051] On the other hand, if the machine learning model classifies the equipment 10 as being in an abnormal state in response to the input state data S, the detection unit 120 may determine that it has detected an abnormality in the equipment 10 (Yes). In this case, the detection unit 120 attaches an abnormality label a to the state data S and supplies it to the target data determination unit 130 and the evaluation unit 170. The detection unit 120 also notifies the search unit 180 and the warning unit 190 that it has detected an abnormality in the equipment 10. The computer then proceeds to step S1430.

[0052] In step S1430, the computer determines whether the conditions are within a predetermined range. For example, a warning unit 190, which may be implemented in the computer, may determine whether the number of attempts k is within a predetermined threshold K (where K is 1 or an integer greater than or equal to 2). The warning unit 190 may also determine whether the elapsed time t is within a predetermined threshold T. However, it is not limited to these conditions. Various conditions for stopping, interrupting, or terminating the search for a recovery operation may be predetermined. If it is determined that the conditions are within a predetermined range (Yes), the computer proceeds to step S1440.

[0053] In step S1440, the computer determines whether or not the recovery process is currently running. For example, the computer may determine whether the count k is 0. If k=0, the computer may determine that the recovery process is not currently running (No). If it is determined that the recovery process is not currently running, the computer proceeds to step S1445.

[0054] In step S1445, the computer starts a timer that measures the elapsed time t corresponding to the detection of an abnormality in equipment 10. Here, the computer may start the timer from a predetermined starting point in response to the detection of an abnormality in equipment 10. For example, the computer may start the timer at the moment the abnormality in equipment 10 is detected (after YES in S1420) to measure the elapsed time t since the abnormality in equipment 10 was detected. Alternatively, the computer may measure the elapsed time t from the time the first trial operation is decided or executed after the abnormality in equipment 10 is detected (S480). The computer may also use any other starting point that can measure the time required for equipment 10 to recover from the abnormality. Then, the computer proceeds to step S1450.

[0055] In step S1450, the computer determines target data that indicates the target state of the equipment 10 in order to restore the equipment 10 from abnormal to normal. For example, a target data determination unit 130, which may be implemented in the computer, may determine the target data St in step S1420 based on the state data S to which the normal label n is attached, that is, the normal data Sn which indicates the state data S when it is normal.

[0056] In this case, the target data determination unit 130 may determine the target data St based on a plurality of normal data Sn1, Sn2, ..., Snm that represent the state data S under normal conditions. Here, the normal data Sn1, Sn2, ..., Snm are m normal data Sn selected in reverse chronological order from before the time when the abnormality of the equipment 10 was detected. m indicates the chronological order of the normal data Sn, with a smaller value indicating newer data and a larger value indicating older data.

[0057] In this case, the target data determination unit 130 may determine the target data St based on statistical quantities in multiple normal data Sn1, Sn2, ..., Snm using, for example, the method shown in Figure 2. Alternatively, the target data determination unit 130 may determine the target data St based on the time series of multiple normal data Sn1, Sn2, ..., Snm using, for example, the method shown in Figure 3. Furthermore, the target data determination unit 130 may combine, for example, the methods shown in Figure 2 and Figure 3 to determine the target data St based on statistical quantities and time series in multiple normal data Sn1, Sn2, ..., Snm. The target data determination unit 130 supplies the determined target data St to the evaluation unit 170.

[0058] In step S1455, the computer supplies the control device 20 with a trial operation A0 to attempt to restore the equipment 10 from abnormality to normal. For example, a search unit 180, which may be implemented in the computer, may supply the trial operation A0 to the control device 20 via a network. Note that in step S1455, this is the first time that trial operation A is supplied after an abnormality in the equipment 10 has been detected, and since the evaluation of trial operation A has not yet been obtained, trial operation A0 may be set to an initial value.

[0059] Here, trial operation A may include multiple operating parameters. Furthermore, each of the multiple operating parameters may be selected from multiple candidate operating quantities. Here, as an example, let's assume that trial operation A consists of a set of multiple operating parameters [Aa, Ab, Ac, Ad, ...]. Operating parameter Aa is a parameter for controlling the illumination of the light and shall be selected from candidate operating quantities {OFF (off), ON (on)}. Operating parameter Ab is a parameter for controlling the supply of the additive and shall be selected from candidate operating quantities {OFF (cut off), ON (supply)}. Operating parameter Ac is a parameter for controlling the opening degree of the valve and shall be selected from candidate operating quantities {-5 (close by 5 degrees), 0 (no change), +5 (open by 5 degrees)}. Operating parameter Ad is a parameter for controlling the temperature of the heater and shall be selected from candidate operating quantities {-3 (decrease by 3 degrees), 0 (no change), +3 (increase by 3 degrees)}.

[0060] In such a case, the trial operation A0 may be set to, for example, [OFF,OFF,0,0,…]. The search unit 180 may supply such a trial operation A0 to the control device 20. In response, the control device 20 may control the controlled object 15 according to the trial operation A0. The computer then proceeds to step S1460.

[0061] In step S1460, the computer performs an increment operation. For example, the computer may set k to k+1. If k=0, for example, the computer may set k to 1. Then, the computer returns to step S1410 and continues the flow.

[0062] In other words, if k=1, the state data acquisition unit 110 may acquire state data S1 indicating the state of the equipment 10 after the controlled object 15 has been controlled according to the trial operation A0, and the detection unit 120 may determine whether or not it has detected an abnormality in the equipment 10 based on the state data S1.

[0063] Here, if k=1, in step S1440, the computer may determine that k≠0 and therefore the recovery process is in progress (Yes). If it is determined that the recovery process is in progress, the computer proceeds to step S1470.

[0064] In step S1470, the computer evaluates the trial operation based on the change in state data when it controls the controlled object 15 according to the trial operation attempted to restore the equipment 10 from abnormal to normal. For example, an evaluation unit 170, which may be implemented in the computer, may evaluate the trial operation based on the change in distance between the state data to which an abnormality label was assigned in step S1420 and the target data determined in step S1450.

[0065] For example, when k=1, the evaluation unit 170 may calculate the distance D0 between the state data S0 and the target data St. In this case, the evaluation unit 170 may calculate at least one of the Euclidean distance, Manhattan distance, Chebyshev distance, or Mahalanobis distance. Similarly, the evaluation unit 170 may calculate the distance D1 between the state data S1 and the target data St. Then, the evaluation unit 170 may calculate the difference d01 by subtracting distance D1 from distance D0.

[0066] If the difference d01 is greater than 0, that is, if the distance D1 is less than the distance D0, it means that the state of the equipment 10 has approached the target state as a result of trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value greater than 0 to trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value such that the value increases as the absolute value of the difference d01 increases.

[0067] If the difference d01 is 0, that is, if distance D0 and distance D1 are the same, it means that the state of the equipment 10 did not change as a result of trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value of 0 to trial operation A0.

[0068] If the difference d01 is less than 0, that is, if distance D1 is greater than distance D0, it means that the state of the equipment 10 has moved away from the target state due to trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value less than 0 to trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value such that the value decreases as the absolute value of the difference d01 increases.

[0069] The evaluation unit 170 may evaluate the trial operation A based on the change in distance D between the state data S and the target data St, for example, as shown above. The evaluation unit 170 supplies the evaluated result to the search unit 180.

[0070] In step S1475, the computer searches for a recovery operation to restore the equipment 10 from abnormal to normal based on the evaluated results. For example, a search unit 180, which may be implemented in the computer, may search for a recovery operation based on the evaluated results in step S1470. In this case, the search unit 180 may sequentially change one of the operation parameters included in the trial operation when searching for a recovery operation. For example, suppose that when k=1, the evaluation value of trial operation A0 is 0. In this case, the search unit 180 may randomly select one of the operation parameters and change one operation parameter to another candidate operation quantity. For example, the search unit 180 may change the operation parameter Aa in trial operation A0[OFF,OFF,0,0,…] from "OFF" to "ON" and set trial operation A1 to [ON,OFF,0,0,…].

[0071] In step S1480, the computer supplies the control device 20 with a trial operation A to attempt to restore the equipment 10 from abnormal to normal. For example, a search unit 180, which may be implemented in the computer, may supply the trial operation A, which was modified in step S1475, to the control device 20 via the network. As an example, when k=1, the search unit 180 may supply trial operation A1 [ON, OFF, 0, 0, ...] to the control device 20. In response, the control device 20 may control the controlled object 15 according to trial operation A1. The computer then proceeds to step S1460 and repeatedly executes the recovery process.

[0072] In other words, when k=2, the state data acquisition unit 110 acquires state data S2 indicating the state of the equipment 10 after the controlled object 15 has been controlled according to the trial operation A1, and the evaluation unit 170 may calculate the distance D2 between the state data S2 and the target data St. The evaluation unit 170 then calculates the difference d12 by subtracting distance D2 from distance D1, and may assign an evaluation value to the trial operation A1 corresponding to the difference d12.

[0073] Here, suppose that when the controlled object 15 is controlled according to trial operation A1, the evaluation value of trial operation A1 is 0. Upon obtaining such an evaluation result, the search unit 180 can recognize that the change in operation parameter Aa does not contribute to the return operation (i.e., operation parameter Aa is an insensitive parameter). In this case, the search unit 180 may decide on an arbitrary candidate operation quantity (for example, "OFF"). The search unit 180 may then select one of the multiple undecided operation parameters and change it to another candidate operation quantity. As an example, the search unit 180 may change operation parameter Ab from "OFF" to "ON" and set trial operation A2 to [OFF,ON,0,0,…].

[0074] Next, suppose that when the controlled object 15 is controlled according to trial operation A2, the evaluation value of trial operation A2 is greater than 0. Having obtained such an evaluation result, the search unit 180 can recognize that the state of the equipment 10 has improved due to the change in operation parameter Ab. In this case, the search unit 180 may decide on the candidate operation quantity after changing operation parameter Ab (here, "ON"). Then, the search unit 180 may select one of the multiple undecided operation parameters and change it to another candidate operation quantity. For example, the search unit 180 may change operation parameter Ac from "0" to "+5" and set trial operation A3 to [OFF, ON, +5, 0, ...].

[0075] Next, suppose that when the controlled object 15 is controlled according to trial operation A3, the evaluation value of trial operation A3 is less than 0. Upon obtaining such an evaluation result, the search unit 180 can recognize that the state of the equipment 10 has deteriorated due to the change in the operation parameter Ac. In this case, the search unit 180 may change the operation parameter Ac to another candidate control variable (in this case, "-5") and set trial operation A4 to [OFF, ON, -5, 0, ...].

[0076] Next, suppose that when the controlled object 15 is controlled according to trial operation A4, the evaluation value of trial operation A4 is greater than 0. Having obtained such an evaluation result, the search unit 180 can recognize that the state of the equipment 10 has improved by changing the operation parameter Ac. In this case, the search unit 180 may decide on a candidate control quantity after changing the operation parameter Ac (here, "-5"). The search unit 180 may then select one of the undecided operation parameters from among the multiple operation parameters and change it to another candidate control quantity. For example, the search unit 180 may change the operation parameter Ad from "0" to "+3" and set trial operation A5 to [OFF, ON, -5, +3, ...].

[0077] Next, suppose that when the controlled object 15 is controlled according to trial operation A5, the evaluation value of trial operation A5 is greater than 0. Having obtained such an evaluation result, the search unit 180 can recognize that the state of the equipment 10 has improved by changing the operation parameter Ad. Here, "-3" can also be selected as another candidate operation quantity for operation parameter Ad. However, since the state of the equipment 10 improved as a result of changing operation parameter Ad to "+", it is expected that the state of the equipment 10 will worsen if operation parameter Ad is changed to "-3", which has a different polarity from "+3". In such a case, the search unit 180 may decide on the candidate operation quantity after changing operation parameter Ad (in this case, "+3") without trying the trial operation in which operation parameter Ad is changed to "-3". In this way, for example, the search unit 180 can also omit changing to some of the candidate operation quantities among multiple candidate operation quantities for one operation parameter.

[0078] The computer may, by using the actual equipment in this way through trial and error, search for a recovery operation until it no longer detects any abnormality in the equipment 10 in step S1420, or until it exceeds predetermined conditions in step S1430.

[0079] During the search for such a recovery operation, if in step S1430 the number of times k exceeds the threshold K, or if the elapsed time t since the timer was started in S1445 in response to the detection of an abnormality in the equipment 10 exceeds the threshold T, the warning unit 190 may determine that it is not within the predetermined conditions (No). In this case, the computer proceeds to step S1490.

[0080] In step S1490, the computer issues a warning if the equipment 10 does not recover from an abnormality within predetermined conditions. For example, a warning unit 190, which may be implemented in the computer, may display a warning screen indicating that the number of times k exceeds a threshold K, or that the elapsed time t exceeds a threshold T. In this case, the warning unit 190 may also display the execution history of the search on the screen. As an example, the warning unit 160 may display the progress of trial operation A and state data S on the screen using a graph or the like. The warning unit 190 may issue a warning if, for example, the number of times (e.g. k) the controlled object 15 has been controlled according to the trial operation exceeds a predetermined threshold (e.g. K). The warning unit 190 may also issue a warning if the elapsed time (e.g. t) until the equipment 10 recovers normally after an abnormality is detected exceeds a predetermined threshold (e.g. T).

[0081] Thus, a method may be provided that includes: a computer acquiring state data indicating the state of equipment 10; evaluating the trial operations based on changes in the state data when the controlled object 15 is controlled according to trial operations attempted to restore equipment 10 from abnormal to normal; and searching for a recovery operation to restore equipment 10 from abnormal to normal based on the evaluated results.

[0082] Traditionally, recovery procedures for abnormal conditions were determined by referring to a recovery procedure determination database that predefined recovery procedures for abnormal conditions. However, it is practically impossible to consider various abnormal conditions in advance, and this problem is particularly pronounced in complex facilities such as plants where various conditions interact with each other.

[0083] In contrast, the device 1000 according to this embodiment evaluates the trial operation based on the change in state data when the controlled object 15 is controlled according to the trial operation, and searches for a recovery operation based on the evaluation result. Thus, according to the device 1000 according to this embodiment, a recovery operation to restore the equipment 10 from abnormal to normal is searched for through trial and error using the actual equipment, so it is possible to attempt recovery from various abnormal states without having to prepare in advance a database for determining the recovery operation or a simulator that simulates the equipment 10.

[0084] Furthermore, the apparatus 1000 according to this embodiment may determine target data and evaluate trial operations based on the change in distance between state data and target data. As a result, the apparatus 1000 according to this embodiment can give a higher evaluation to trial operations that bring the state of the equipment 10 closer to the target state.

[0085] Furthermore, the apparatus 1000 according to this embodiment may determine target data based on multiple normal data points. This allows the apparatus 1000 according to this embodiment to objectively set the target to be achieved when restoring the equipment 10 from abnormal to normal, based on multiple normal data points, rather than setting the target randomly.

[0086] In this case, the apparatus 1000 according to this embodiment may determine the target data based on statistical values ​​from multiple normal data sets, or it may determine the target data based on time series data from multiple normal data sets. There are many different types of abnormalities, including static abnormalities where there is no order or other relationship between the data, and dynamic abnormalities where there is an order relationship between the data. According to the apparatus 1000 according to this embodiment, even in the case of such a wide variety of abnormalities, it is possible to appropriately set the target to be aimed for in order to restore the equipment 10 from abnormality to normal.

[0087] Furthermore, in the apparatus 1000 according to this embodiment, when searching for a recovery operation, one of the operation parameters included in the trial operation may be changed sequentially. As a result, with the apparatus 1000 according to this embodiment, even when it is unclear which operation parameter contributes to the recovery operation, the recovery operation can be searched for by evaluating each operation parameter one by one in order.

[0088] In this case, the device 1000 according to this embodiment may omit changing one operation parameter to some of the candidate operation quantities among multiple candidate operation quantities. As a result, the device 1000 according to this embodiment can efficiently search for a return operation without exhaustively trying all combinations of candidate operation quantities.

[0089] Furthermore, the device 1000 according to this embodiment may also be equipped with a function to detect abnormalities in the equipment 10 based on status data. This allows the device 1000 according to this embodiment to realize both an abnormality detection function and a recovery operation search function in a single device. Moreover, the device 1000 according to this embodiment can autonomously detect abnormalities in the equipment 10 without human intervention, and can automatically sort normal data and abnormal data necessary for searching for recovery operations by assigning normal labels and abnormal labels to the status data.

[0090] Furthermore, the device 1000 according to this embodiment may also be equipped with a function to issue a warning if the equipment 10 does not recover normally from an abnormality within predetermined conditions. This allows the device 1000 according to this embodiment to inform the user if the equipment 10 fails to recover normally from an abnormality within the conditions despite searching for a recovery operation. Therefore, even if it is difficult to automatically recover the equipment 10 according to the device 1000 according to this embodiment, the user can be prompted to switch to manual recovery, etc., without unnecessarily repeating the recovery operation search process.

[0091] In this case, the device 1000 according to this embodiment may issue a warning if the number of times the controlled object 15 has been controlled according to the trial operation exceeds a predetermined threshold, or if the elapsed time until the equipment 10 returns to normal after an abnormality has been detected exceeds a predetermined threshold. Since the time constant and settling time vary depending on the equipment 10, the rate at which the state of the equipment changes when the controlled object 15 is controlled according to the trial operation varies. According to the device 1000 according to this embodiment, even in such cases, the timing for stopping, interrupting, or ending the search for the return operation can be set to the optimal timing for each piece of equipment 10.

[0092] Figure 5 shows another example of a block diagram of a control system 1 which may include the device 1000 according to this embodiment. In this figure, the same reference numerals are used for components having the same function and configuration as in Figure 1, and descriptions are omitted below except for differences. Up to this point, the case in which the control device 20 and the device 1000 are provided as separate, independent devices has been shown as an example. However, the control device 20 and the device 1000 may be provided as a single integrated device, either partially or entirely. In this figure, the case in which the device 1000 also provides the functions of the control device 20 is shown.

[0093] In this figure, the device 1000 further comprises a control unit 510. In this figure, the state data acquisition unit 110 may supply the acquired state data to the control unit 510 in addition to the detection unit 120. Also, the search unit 180 may supply trial operations to the control unit 510 instead of the control device 20.

[0094] The control unit 510 may be mainly provided by a CPU and may be implemented in the device 1000 as a functional unit similar to the control device 20. That is, if no abnormality occurs in the equipment 10, the control unit 510 may control the controlled object 15 based on the state data acquired by the state data acquisition unit 110. In this case, the control unit 510 may control the controlled object 15 by PID control or by AI control. On the other hand, if an abnormality occurs in the equipment 10, the control unit 510 may control the controlled object 15 according to trial operations supplied by the search unit 180. In this case, the control unit 510 may switch the control mode depending on whether or not an abnormality in the equipment 10 has been detected by the detection unit 120.

[0095] Thus, the device 1000 according to this embodiment may further include a control unit 510. With this, the device 1000 according to this embodiment can realize the function of searching for a recovery operation and the function of controlling the controlled object 15 in a single device. Therefore, with the device 1000 according to this embodiment, there is no need to supply trial operations from the device 1000 to the control device 20, and the risk of trial operations being tampered with during communication between the device 1000 and the control device 20 can be eliminated, thus protecting the equipment 10 from security threats.

[0096] Figure 6 shows an example of a block diagram of a control system 1 which may include the apparatus 1000 according to a modified example of this embodiment. In this figure, the same reference numerals are used for components having the same function and configuration as in Figure 1, and descriptions are omitted below except for differences. In the above description, an example was shown in which the apparatus 1000 evaluates the trial operation using target data. However, in this modified example, the apparatus 1000 evaluates the trial operation using an evaluation index.

[0097] In this modified example, the control system 1 may further include an evaluation model 40. The evaluation model 40 outputs an evaluation index that assesses the state of the equipment 10 in response to state data indicating the state of the equipment 10 being input. In generating such an evaluation model 40, for example, labeling data may be generated based on the operational objectives (plant KPIs (Key Performance Indicators), etc.) for the equipment 10, state data indicating the state of the equipment 10, and training labels. Such operational objectives may be the operational objectives for the entire plant or factory if the equipment 10 is the entire plant or factory, the operational objectives for a segment if the equipment 10 is a part of the plant or factory, or the operational objectives for a single device or a single process if the equipment 10 corresponds to a single device or a single process. The generated labeling data may then be used as training data to generate the evaluation model 40 using a machine learning algorithm. The process of generating the evaluation model 40 itself is optional, so further details are omitted here.

[0098] In this modified example, the control device 20 performs AI control using an operation model. In this figure, the case where the evaluation model 40 is the same as the evaluation model used during reinforcement learning of the operation model is shown as an example. That is, the evaluation index used for evaluating the trial operation and the evaluation index used for reinforcement learning of the operation model may be output from the same model. However, it is not limited to this. The evaluation model 40 may be different from the evaluation model used during reinforcement learning of the operation model. That is, the evaluation index used for evaluating the trial operation and the evaluation index used for reinforcement learning of the operation model may be output from different models.

[0099] In this modified example, the device 1000 further includes an indicator acquisition unit 610 instead of the target data determination unit 130. Furthermore, if the detection unit 120 determines that it has detected an abnormality in the equipment 10, it attaches an abnormality label to the status data and supplies it to the indicator acquisition unit 610.

[0100] The index acquisition unit 610 acquires an evaluation index that evaluates the state of the equipment 10 in response to the input of state data to the evaluation model 40. The index acquisition unit 610 may mainly provide state data that has been labeled with an abnormality by the detection unit 120 via a network, which may be provided via a communication interface. The evaluation model 40 may output an evaluation index that evaluates the state of the equipment 10 in response to the input of state data. The index acquisition unit 610 may acquire the evaluation index output from the evaluation model 40 in this manner via the network. The index acquisition unit 610 supplies the acquired evaluation index to the evaluation unit 170.

[0101] In this modified example, the evaluation unit 170 evaluates the trial operation based on changes in the evaluation index. The evaluation unit 170 may be mainly provided by the CPU and may derive changes in the evaluation index by analyzing evaluation index acquired in time series from the index acquisition unit 610. The evaluation unit 170 may then evaluate the trial operation based on the changes in the evaluation index. The evaluation unit 170 supplies the evaluated results to the search unit 180. The search unit 180 may search for a recovery operation based on these evaluation results.

[0102] Figure 7 shows an example of a flowchart of a method that the apparatus 1000 according to a modified version of this embodiment may perform. Steps S1400 to S1460 and steps S1475 to S1490 may be the same as in Figure 4, except that step S1450 is not included, so a detailed explanation is omitted here. In this modified version, if the computer determines in step S1440 that a recovery process is being performed, the computer proceeds to step S1465.

[0103] In step S1465, the computer acquires an evaluation index that evaluates the state of the equipment 10 in response to inputting state data into the evaluation model 40. For example, an index acquisition unit 610, which may be implemented in the computer, may supply the state data S, to which an abnormality label has been attached in step S1420, to the evaluation model 40 via the network.

[0104] The evaluation model 40 may output an evaluation index I that evaluates the state of the equipment 10 in response to the input of state data S. For example, when k=1, the evaluation model 40 may output an evaluation index I1 that evaluates the state of the equipment 10 before the controlled object 15 is controlled according to trial operation A0 in response to the input of state data S0. The evaluation model 40 may also output an evaluation index I1 that evaluates the state of the equipment 10 after the controlled object 15 has been controlled according to trial operation A0 in response to the input of state data S1. Thus, the evaluation model 40 may output evaluation indices I0 and I1 before and after the controlled object 15 is controlled according to trial operation A0. The index acquisition unit 610 may acquire the evaluation indices I0 and I1 output from the evaluation model 40 via the network.

[0105] Similarly, when k=2, the evaluation model 40 may output an evaluation index I2 that evaluates the state of the equipment 10 after the controlled object 15 has been controlled according to the trial operation A1, in response to the input of state data S2. The index acquisition unit 610 may then acquire the evaluation index I2 output from the evaluation model 40 via the network. The index acquisition unit 610 acquires an evaluation index I that evaluates the state of the equipment 10 in response to the input of state data S to the evaluation model 40, for example in this way. The index acquisition unit 610 then supplies the acquired evaluation index I to the evaluation unit 170.

[0106] In step S1470, the computer evaluates the trial operation based on the change in the evaluation index. For example, an evaluation unit 170, which may be implemented in the computer, may evaluate the trial operation A based on the change in the evaluation index I obtained in step S1465.

[0107] For example, when k=1, the evaluation unit 170 may calculate the difference i01 by subtracting the evaluation index I1 from the evaluation index I0. If the difference i01 is less than 0, that is, if the evaluation index I1 is higher than the evaluation index I0, it means that the condition of the equipment 10 has improved as a result of trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value greater than 0 to trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value such that the value increases as the absolute value of the difference i01 increases.

[0108] If the difference i01 is 0, that is, if evaluation index I0 and evaluation index I1 are the same, it means that the state of the equipment 10 did not change as a result of trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value of 0 to trial operation A0.

[0109] If the difference i01 is greater than 0, that is, if the evaluation index I1 is lower than the evaluation index I0, it means that the condition of the equipment 10 has deteriorated due to trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value less than 0 to trial operation A0. In this case, the evaluation unit 170 may assign an evaluation value such that the value decreases as the absolute value of the difference d01 increases.

[0110] The evaluation unit 170 may evaluate the trial operation A based on the change in the evaluation index I, for example, as shown above. The evaluation unit 170 supplies the evaluated result to the search unit 180. The search unit 180 may then search for a recovery operation based on such an evaluation result.

[0111] As described above, various methods can be considered for setting the target to be achieved when restoring the equipment 10 from abnormal to normal, and it may be unclear which method is optimal for determining the target data. In contrast, the device 1000 according to this modified example searches for a recovery operation based on the results of evaluating the trial operation in cooperation with the evaluation model 40. Thus, with the device 1000 according to this modified example, instead of determining specific target data with the target data determination unit 130 and determining a recovery operation to approach that target data when restoring the equipment 10 from abnormal to normal, it is possible to search for a recovery operation that improves the evaluation index obtained using the evaluation model 40.

[0112] In particular, if the evaluation model 40 that outputs the evaluation index is the same as the evaluation model used during reinforcement learning of the operation model, the apparatus 1000 according to this modified example can search for a return operation that is consistent with, or has little consistency with, the operation under AI control.

[0113] On the other hand, if an abnormality occurs in the equipment 10, the cause may lie in the operation model or evaluation model used for AI control (for example, undertraining, overtraining, or labeling errors). Therefore, if the evaluation model 40 that outputs evaluation indicators is different from the evaluation model used during reinforcement learning of the operation model, the device 1000 according to this modified example can search for an independent operation separate from the operation under AI control as a recovery operation.

[0114] Figure 8 shows another example in the block diagram of a control system 1 which may include a modified device 1000 according to this embodiment. In this figure, the same reference numerals are used for components having the same function and configuration as in Figure 5 or Figure 6, and descriptions are omitted below except for differences. Up to this point, an example has been shown in which the evaluation model 40 is stored outside the device 1000. However, the evaluation model 40 may be stored inside the device 1000. In this figure, the device 1000 further comprises the evaluation model 40.

[0115] Thus, the modified device 1000 may further include an evaluation model 40. This allows the device 1000 to implement both a function for searching for a recovery operation and a function for storing the evaluation model 40 within a single device. Therefore, the device 1000, when acquiring evaluation indicators, does not require external communication, thus reducing communication costs and time, and preventing information leakage to external parties.

[0116] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where a block may represent (1) a stage in a process in which an operation is performed or (2) a section of a device having the role of performing the operation. Specific stages and sections may be implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on a computer-readable medium, and / or processors supplied with computer-readable instructions stored on a computer-readable medium. Dedicated circuits may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuits may include reconfigurable hardware circuits, including logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logic operations, flip-flops, registers, memory elements such as field-programmable gate arrays (FPGAs), programmable logic arrays (PLAs), etc.

[0117] Computer-readable media may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, computer-readable media having instructions stored therein will comprise a product containing instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital versatile disk (DVD), Blu-ray (RTM) disk, memory stick, integrated circuit card, etc.

[0118] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0119] Computer-readable instructions may be provided locally or via a wide area network (WAN), such as a local area network (LAN) or the internet, to a processor or programmable circuit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, and these instructions may be executed to create means for performing operations specified in a flowchart or block diagram. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

[0120] Figure 9 shows an example of a computer 9900 in which multiple aspects of the present invention may be embodied in whole or in part. A program installed on the computer 9900 can cause the computer 9900 to function as an operation or one or more sections of an apparatus according to an embodiment of the present invention, or to execute such operation or one or more sections, and / or to cause the computer 9900 to execute a process or a stage of such process according to an embodiment of the present invention. Such a program may be executed by the CPU 9912 to cause the computer 9900 to perform a particular operation associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0121] The computer 9900 according to this embodiment includes a CPU 9912, RAM 9914, a graphics controller 9916, and a display device 9918, which are interconnected by a host controller 9910. The computer 9900 also includes input / output units such as a communication interface 9922, a hard disk drive 9924, a DVD drive 9926, and an IC card drive, which are connected to the host controller 9910 via an input / output controller 9920. The computer also includes legacy input / output units such as a ROM 9930 and a keyboard 9942, which are connected to the input / output controller 9920 via an input / output chip 9940.

[0122] The CPU 9912 operates according to programs stored in the ROM 9930 and RAM 9914, thereby controlling each unit. The graphics controller 9916 acquires image data generated by the CPU 9912 from a frame buffer provided in RAM 9914 or from itself, and displays the image data on the display device 9918.

[0123] The communication interface 9922 communicates with other electronic devices via a network. The hard disk drive 9924 stores programs and data used by the CPU 9912 in the computer 9900. The DVD drive 9926 reads programs or data from the DVD-ROM 9901 and provides them to the hard disk drive 9924 via the RAM 9914. The IC card drive reads programs and data from and / or writes programs and data to the IC card.

[0124] The ROM 9930 stores boot programs and / or programs that depend on the computer 9900's hardware, which are executed by the computer 9900 when activated. The input / output chip 9940 may also connect various input / output units to the input / output controller 9920 via parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0125] The program is provided on a computer-readable medium such as a DVD-ROM 9901 or an IC card. The program is read from the computer-readable medium and installed on a hard disk drive 9924, RAM 9914, or ROM 9930, which are also examples of computer-readable medium, and executed by the CPU 9912. The information processing described within these programs is read by the computer 9900, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the manipulation or processing of information in accordance with the use of the computer 9900.

[0126] For example, when communication is performed between computer 9900 and an external device, CPU 9912 may execute a communication program loaded into RAM 9914 and instruct communication interface 9922 to perform communication processing based on the processing described in the communication program. Under the control of CPU 9912, communication interface 9922 reads transmission data stored in a transmission buffer processing area provided in a recording medium such as RAM 9914, hard disk drive 9924, DVD-ROM 9901, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a receive buffer processing area provided on the recording medium.

[0127] Furthermore, the CPU 9912 may read all or necessary parts of files or databases stored on external recording media such as the hard disk drive 9924, DVD drive 9926 (DVD-ROM 9901), or IC card into the RAM 9914, and perform various types of processing on the data in the RAM 9914. The CPU 9912 then writes the processed data back to the external recording media.

[0128] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 9912 may perform various types of processing on the data read from the RAM 9914, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to the RAM 9914. The CPU 9912 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 9912 may search among the multiple entries for an entry that matches the condition for which the attribute value of the first attribute is specified, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0129] The programs or software modules described above may be stored on or near computer-readable media on computer 9900. Alternatively, recording media such as hard disks or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as computer-readable media, thereby providing programs to computer 9900 via the network.

[0130] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0131] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before," "prior to," etc., and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," "next," etc. for convenience, it does not mean that it is essential to perform the operations in that order. [Explanation of Symbols]

[0132] 10 Equipment 15. Controlled object 20 Control device 40 Evaluation Models 1000 devices 110 Status data acquisition unit 120 Detection unit 130 Target Data Determination Unit 170 Evaluation Department 180 Search Department 190 Warning section 510 Control Unit 610 Index acquisition part 9900 Computer 9901 DVD-ROM 9910 Host Controller 9912 CPU 9914 RAM 9916 Graphics Controller 9918 Display Device 9920 Input / Output Controller 9922 Communication Interface 9924 Hard Disk Drive 9926 DVD drive 9930 ROM 9940 Input / Output Chip 9942 Keyboard

Claims

1. A status data acquisition unit that acquires status data indicating the status of the equipment, An evaluation unit evaluates the trial operation based on the change in state data when the controlled object is controlled in accordance with the trial operation attempted to restore the equipment from an abnormal state to normal, Based on the evaluation results, a search unit searches for a recovery operation to restore the equipment from an abnormal state to a normal state, Equipped with, The evaluation unit evaluates the trial operation based on the change in distance between the state data and the target data indicating the target state of the equipment for restoring the equipment to normal operation. The search unit modifies the trial operation based on the evaluated results, The apparatus wherein the search unit searches for the return operation by repeating the above evaluation and the above modification.

2. The apparatus according to claim 1, further comprising a target data determination unit for determining the aforementioned target data.

3. The apparatus according to claim 2, wherein the target data determination unit determines the target data based on a plurality of normal data indicating the state data during normal operation.

4. The apparatus according to claim 3, wherein the target data determination unit determines the target data based on statistical quantities in the plurality of normal data.

5. The apparatus according to claim 3, wherein the target data determination unit determines the target data based on the time series of the plurality of normal data.

6. The system further includes an index acquisition unit that acquires an evaluation index that evaluates the state of the equipment in response to inputting the aforementioned state data into the evaluation model. The apparatus according to claim 1, wherein the evaluation unit evaluates the trial operation based on the change in the evaluation index.

7. The apparatus according to claim 6, further comprising the evaluation model.

8. The apparatus according to any one of claims 1 to 7, wherein the search unit sequentially changes one of the multiple operation parameters included in the trial operation when searching for the return operation.

9. The apparatus according to claim 8, wherein the search unit omits changing one operation parameter to some of the candidate operation quantities among a plurality of candidate operation quantities.

10. The apparatus according to any one of claims 1 to 7, further comprising a detection unit for detecting an abnormality in the equipment based on the aforementioned state data.

11. The apparatus according to claim 1, further comprising a warning unit that issues a warning if the equipment does not return to normal from an abnormal state within predetermined conditions even after the recovery operation has been explored.

12. The apparatus according to claim 11, wherein the warning unit issues a warning when the elapsed time until the equipment returns to normal exceeds a predetermined threshold in response to the detection of an abnormality in the equipment.

13. The apparatus according to claim 11, wherein the warning unit issues a warning when the number of times the controlled object has been controlled in accordance with the trial operation exceeds a predetermined threshold.

14. The apparatus according to any one of claims 1 to 7, further comprising a control unit for controlling the controlled object in accordance with the aforementioned trial operation.

15. Computers To acquire status data that indicates the status of the equipment, The trial operation is evaluated based on the change in state data when the controlled object is controlled in accordance with the trial operation attempted to restore the equipment from an abnormal state to normal, Based on the results of the evaluation, the following steps are taken: Equipped with, In evaluating the trial operation, the trial operation is evaluated based on the change in distance between the state data and the target data indicating the target state of the equipment for restoring the equipment to normal operation. In the search for the recovery operation, the trial operation is modified based on the evaluated results. A method for exploring the recovery operation by repeatedly performing the evaluation and the modification.

16. It is executed by a computer, and the computer, A status data acquisition unit that acquires status data indicating the status of the equipment, An evaluation unit evaluates the trial operation based on the change in state data when the controlled object is controlled in accordance with the trial operation attempted to restore the equipment from an abnormal state to normal, Based on the evaluation results, a search unit searches for a recovery operation to restore the equipment from an abnormal state to a normal state, and make it work The evaluation unit evaluates the trial operation based on the change in distance between the state data and the target data indicating the target state of the equipment for restoring the equipment to normal operation. The search unit modifies the trial operation based on the evaluated results, A program in which the search unit searches for the return operation by repeatedly performing the above evaluation and the above modification.

Images