Monitoring system, monitoring method, and monitoring program

Abstract

This monitoring system comprises an acquisition unit, an estimation unit, a prediction unit, and an output unit. The acquisition unit acquires measurement data relating to equipment of a plant. The estimation unit estimates environmental information that cannot be measured relating to the plant, on the basis of the measurement data. The prediction unit predicts a deterioration state of the plant on the basis of at the least environmental information that cannot be measured. The output unit outputs an estimated maintenance timing.

Description

Surveillance system, surveillance method, and recording medium

[0001] The present disclosure relates to monitoring systems and the like.

[0002] In a factory plant, for example, equipment maintenance is performed. In the maintenance of plant equipment, for example, inspection of the internal and external conditions of the equipment, replacement of parts used in the equipment, or cleaning of the parts used in the equipment is performed. In the maintenance of plant equipment, for example, if the maintenance of plant equipment is performed earlier than appropriate, the efficiency of plant operation may decrease due to, for example, operation shutdowns or frequent use of parts. Furthermore, if the maintenance of plant equipment is performed later than appropriate, for example, an accident or a decrease in production efficiency may occur. For this reason, it is desirable to perform the maintenance of plant equipment at appropriate times.

[0003] The maintenance management system of Patent Document 1 compares actual measurement data for each inspection target of a power plant with calculation results using a physical model, and then selects inspection targets for the next inspection based on the comparison results.

[0004] Japanese Patent Application Laid-Open No. 2020-176883

[0005] With the technology described in Patent Document 1, it may be difficult to appropriately estimate the maintenance timing.

[0006] In order to solve the above-mentioned problems, the present disclosure aims to provide a monitoring system etc. that can improve the accuracy of estimating maintenance timing.

[0007] In order to solve the above problems, the monitoring system disclosed herein includes an acquisition means for acquiring measurement data related to plant equipment, an estimation means for estimating unmeasurable environmental information related to the plant based on the measurement data, a prediction means for predicting the deterioration state of the plant based on at least the unmeasurable environmental information, a maintenance timing estimation means for estimating the timing of maintenance of the plant based on the predicted result of the deterioration state, and an output means for outputting the estimated maintenance timing.

[0008] The monitoring method disclosed herein acquires measurement data related to plant equipment, estimates unmeasurable environmental information related to the plant based on the measurement data, predicts the deterioration state of the equipment based on at least the unmeasurable environmental information, estimates the timing of maintenance for the plant based on the predicted deterioration state, and outputs the estimated maintenance timing.

[0009] The recording medium of the present disclosure non-temporarily records a monitoring program that causes a computer to execute the following processes: acquiring measurement data related to plant equipment; estimating unmeasurable environmental information related to the plant based on the measurement data; predicting the deterioration state of the equipment based on at least the unmeasurable environmental information; estimating the timing of maintenance for the plant based on the predicted results of the deterioration state; and outputting the estimated maintenance timing.

[0010] According to the present disclosure, the accuracy of estimating the maintenance timing can be improved.

[0011] FIG. 1 is a diagram illustrating an example of the configuration of a plant monitoring system according to the present disclosure. FIG. 2 is a diagram illustrating an example of the configuration of a chemical plant according to the present disclosure. FIG. 3 is a diagram illustrating an example of the configuration of a monitoring system according to the present disclosure. FIG. 4 is a diagram illustrating an example of a display screen according to the present disclosure. FIG. 5 is a diagram illustrating an example of a display screen according to the present disclosure. FIG. 6 is a diagram illustrating an example of an operation flow of the monitoring system according to the present disclosure. FIG. 7 is a diagram illustrating an example of the hardware configuration of the monitoring system according to the present disclosure.

[0012] An embodiment of the present disclosure will be described in detail with reference to the drawings. FIG. 1 is a diagram illustrating an example of the configuration of a plant monitoring system according to the present embodiment. The plant monitoring system includes, for example, a monitoring system 10, a sensor 20, and a terminal device 30. The monitoring system 10 is connected to the sensor 20 via, for example, a network. The monitoring system 10 is also connected to the terminal device 30 via, for example, a network. The monitoring system 10 may acquire measurement data from the sensor 20 via a storage medium. There may be multiple sensors 20 and multiple terminal devices 30. The number of sensors 20 and multiple terminal devices 30 may be set as appropriate.

[0013] A plant monitoring system is, for example, a system that monitors the operating status of a plant. A plant monitor, for example, refers to the operating status and makes decisions regarding plant control and plant maintenance. Decisions regarding plant maintenance include, for example, determining maintenance targets, work items, and maintenance timing.

[0014] The monitoring system 10 is, for example, a system that estimates the timing of plant maintenance. Plant maintenance is, for example, an activity to maintain a plant so that it can operate in an appropriate state. Plant maintenance is, for example, the maintenance of plant equipment. Plant maintenance is, for example, one or more tasks among inspection, replacement, repair, adjustment, and cleaning of plant equipment. Plant maintenance is not limited to the above. Plant maintenance may also include maintenance of the plant's power unit. Furthermore, the timing of plant maintenance is the time to perform work related to plant maintenance. For example, if plant maintenance is the maintenance of plant equipment, the timing of plant maintenance is the time to perform one or more tasks among inspection, replacement, repair, adjustment, and cleaning of plant equipment.

[0015] The plant is, for example, a chemical plant. The plant may also be a plant of a factory other than a chemical plant. For example, the plant may be a steel plant. The plant may also be a waste incineration plant, a power plant, a dam, a sewage treatment plant, or a water purification plant. Facilities in which the plant is used are not limited to the above. The plant may also be an internal combustion engine, a power generation device, a cooling device, a supply device, a purification device, or an air conditioning device. Equipment that falls under the category of a plant is not limited to the above.

[0016] The plant equipment is, for example, one or more units selected from the group consisting of piping, valves, pressurizers, pressure reducers, combustors, reactors, distillers, coolers, molding machines, filters, injectors, and agitators. The plant equipment is not limited to the above. The plant power unit is, for example, one or more units selected from the group consisting of pumps, blowers, fans, and compressors. The plant power unit is not limited to the above.

[0017] FIG. 2 is a diagram schematically illustrating an example of a chemical plant. In the example of the chemical plant in FIG. 2, a plurality of sensors are attached to measure data related to a reactor. In the example of the chemical plant in FIG. 2, flow rate sensors are attached to the inlet pipe and the outlet pipe of the reactor. In addition, in the example of the chemical plant in FIG. 2, a temperature sensor is attached to the reactor. The flow rate sensor and the temperature sensor are examples of the sensor 20. The sensor 20 is not limited to a flow rate sensor and a temperature sensor. In addition, the sensor 20 may be attached to measure data related to a unit other than the reactor.

[0018] The timing of plant maintenance is estimated, for example, using the results of plant deterioration prediction. Plant deterioration prediction is performed, for example, based on unmeasurable environmental information. The unmeasurable environmental information is, for example, environmental information that cannot be measured while the plant is in operation. The environmental information that cannot be measured while the plant is in operation is, for example, environmental information that cannot be measured in principle, or environmental information from which meaningful data cannot be obtained while the plant is in operation when monitoring the plant. The unmeasurable environmental information may include environmental information for which it is difficult to create a measurement environment. The unmeasurable environmental information is, for example, data related to the internal state of plant equipment or the internal state of a power plant that operates the equipment. The internal state includes, for example, the state of materials present inside. Furthermore, the measurement data is data obtained by measuring the plant equipment. The measurement data may include data obtained by measuring the plant's power plant. The measurement data is, for example, measured by a sensor 20.

[0019] Unmeasurable environmental information is, for example, data related to a state of a monitored object that cannot be directly measured. For example, unmeasurable environmental information may be data related to a monitored object for which a measurement sample cannot be collected. The inability to collect a measurement sample means that collecting a measurement sample results in the monitored object having characteristics different from its original characteristics. Alternatively, the inability to collect a measurement sample may mean that changes occur so rapidly that a sample suitable for measurement cannot be obtained. In the example of the chemical plant in Figure 2, the monitored object is activity, which indicates the activity of a catalyst inside a reactor. In this case, removing the catalyst from the reactor may deactivate the catalyst, making it impossible to measure the catalyst activity. Therefore, catalyst activity is unmeasurable environmental information.

[0020] Unmeasurable environmental information is, for example, data whose values ​​cannot be obtained within the time required for monitoring a plant. Unmeasurable environmental information may refer, for example, to the inability to measure in real time using a sensor. Unmeasurable environmental information may refer, for example, to the inability to obtain measurement results within the time allowed for monitoring. For example, if the target of monitoring is a pipe clog, the pipe must be removed from the plant to check for a clog, making it impossible to check for a clog inside the pipe during normal operation. In other words, pipe clogs cannot be measured in real time. Furthermore, if the target of monitoring is the degree of polymerization of a product produced by a chemical reaction, the degree of polymerization must be measured, for example, using a sampled product using a measuring instrument outside the plant. For this reason, it is difficult to measure the degree of polymerization, which requires measurement using an external measuring instrument, in real time within the time allowed for monitoring. Unmeasurable environmental information may also refer to the rapid progression of changes, making it impossible to identify the state from the measurement data.

[0021] Furthermore, the unmeasurable environmental information is, for example, data that cannot be measured by a sensor. The data that cannot be measured by a sensor is, for example, data that cannot be measured directly by a sensor. The data that cannot be measured by a sensor is, for example, the internal state of plant equipment and power plants. The internal state of plant equipment is, for example, one or more of reaction rate, degree of polymerization, degree of dispersion, catalyst activity, pipe clogging, solvent, and scale. The unmeasurable internal state is not limited to the above. The unmeasurable environmental information may be, for example, data of equipment and power plants to which a sensor cannot be attached. The data that cannot be measured by a sensor may be, for example, data that cannot be measured normally due to vibration or heat generation. The unmeasurable environmental information may be, for example, data that requires a special measurement environment or expensive measurement equipment to measure.

[0022] Furthermore, the monitoring system 10 predicts the deterioration state of the plant based on, for example, unmeasurable environmental information. Then, the monitoring system 10 estimates the timing of plant maintenance based on, for example, the predicted deterioration state of the plant. The monitoring system 10 outputs the estimated maintenance time of the plant to, for example, a terminal device 30 used by a plant monitor. In this way, by predicting the deterioration state of the plant based on unmeasurable environmental information such as the internal state of the plant equipment, the accuracy of the prediction of the deterioration state of the plant is improved. Therefore, by estimating the maintenance time using the deterioration state predicted based on unmeasurable environmental information, the accuracy of the estimation of the maintenance time of the plant can be improved.

[0023] Here, a specific example of the configuration of the monitoring system 10 will be described. Fig. 3 is a diagram showing an example of the configuration of the monitoring system 10. The monitoring system 10 basically includes an acquisition unit 101, an estimation unit 102, a prediction unit 103, a maintenance timing estimation unit 104, and an output unit 109. The monitoring system 10 also includes, for example, a cause estimation unit 105, an effect estimation unit 106, an accuracy estimation unit 107, a plan creation unit 108, and a storage unit 110.

[0024] The acquisition unit 101 acquires measurement data of the plant equipment. The acquisition unit 101 acquires the measurement data of the plant equipment from, for example, the sensor 20. The acquisition unit 101 may acquire the measurement data of the plant equipment from multiple sensors 20. The acquisition unit 101 may also acquire the measurement data of the plant equipment via a storage medium. The measurement data of the plant equipment is, for example, data obtained by measuring the internal environment of the plant equipment. The measurement data of the plant equipment is, for example, data on one or more items of temperature, humidity, pressure, flow rate, flow velocity, transmittance, viscosity, rotation speed, and torque. The measurement data of the plant equipment may be data measured from outside the plant equipment. For example, if the plant equipment is piping, the measurement data of the plant equipment may be data obtained by measuring the temperature of the outer surface of the piping. The measurement data of the plant equipment is not limited to the above.

[0025] The acquiring unit 101 may acquire plant control data. The acquiring unit 101 acquires the plant control data, for example, from a plant control system (not shown). The plant control data is, for example, setting values ​​of control parameters of the plant. The plant control data may be setting values ​​of control parameters of the plant at multiple points in time on a time series. The plant control data is, for example, setting values ​​that indicate operating conditions of equipment and power plants of the plant. The plant control data is, for example, data on setting values ​​of one or more items of temperature, amount of heating, humidity, pressure, amount of pressurization, flow rate, flow velocity, mixing ratio, rotation speed, and torque. The plant control data is not limited to the above.

[0026] The estimation unit 102 estimates unmeasurable environmental information related to the plant based on the measurement data. The estimation unit 102 estimates the unmeasurable environmental information using, for example, an estimation model. The estimation model is, for example, a model that estimates unmeasurable environmental information from the measurement data. The estimation model is also called an agent. The estimation unit 102 estimates the internal state of the plant equipment based on the measurement data. The estimation unit 102 may also estimate unmeasurable environmental information of a power plant that operates the plant equipment based on the measurement data.

[0027] The estimation model is generated, for example, by system identification. The estimation model is generated, for example, using a behavior estimation model that reproduces the behavior of the plant. The behavior estimation model estimates output data from input data based on, for example, a model that reproduces the internal state of the plant. In generating the estimation model, for example, each parameter of the behavior estimation model is determined so that the actually measured input data and output data match the input data and output data of the behavior estimation model. The input data may include control data. When estimating the internal state of the plant, the estimation model estimates the internal state of the plant from the measured input data and output data using each parameter of the determined behavior estimation model. At this time, the internal state of the plant that is the target of estimation by the estimation model is unmeasurable environmental information. Then, the estimation model outputs, for example, a value indicating the estimated internal state as unmeasurable environmental information.

[0028] When the unmeasurable environmental information is the internal state of a unit in a plant, the measurement data on the inlet side of the unit is, for example, measurement data upstream of the unit whose internal state is estimated. When the unmeasurable environmental information is the internal state of a unit in a plant, the measurement data on the outlet side of the unit is, for example, measurement data downstream of the unit whose internal state is estimated.

[0029] For example, suppose a chemical plant includes pipes A, B, a reactor R, and C. Furthermore, suppose reactor R reacts raw material X supplied through pipe A with raw material Y supplied through pipe B using a catalyst inside. Then, suppose reactor R supplies the synthesized product Z to pipe C. Furthermore, suppose the unmeasurable environmental information to be estimated is the activity of the catalyst used in the reaction in reactor R. In this case, the measurement data on the inlet side are, for example, the flow rate and temperature of raw material A measured in pipe A, and the flow rate and temperature of raw material B measured in pipe B. Furthermore, the measurement data on the outlet side are, for example, the flow rate of product Z measured in pipe C. In such a case, for example, an estimation model that estimates the activity of the catalyst in reactor R as unmeasurable environmental information is generated using the measurement data on the inlet side and the measurement data on the outlet side.

[0030] The estimation model is, for example, a model that uses a function in which unmeasurable environmental information and measurement data on the entrance side are explanatory variables and measurement data on the exit side are objective variables.

[0031] The estimation model may be a learning model generated by machine learning. When generated by machine learning, the estimation model is generated by learning the relationship between time-series data of measurement data and unmeasurable environmental information. For example, data measured outside the plant by sampling is used as the unmeasurable environmental information. The estimation model may be generated by learning the relationship between the time-series data of measurement data and the time-series data of control data and the unmeasurable environmental information. When generated by machine learning, the estimation model is generated by, for example, deep learning using a neural network. The estimation model may also be generated by reinforcement learning. The learning algorithm for generating the estimation model is not limited to the above. For example, the estimation model is generated in a system external to the monitoring system 10. The estimation model may also be generated in a learning unit (not shown) within the monitoring system 10.

[0032] The prediction unit 103 predicts the deterioration state of the plant based on at least unmeasurable environmental information. The prediction unit 103 may predict the deterioration state of the plant based on measurement data and unmeasurable environmental information. Furthermore, the prediction unit 103 may predict the deterioration state of the plant based on measurement data, control data, and unmeasurable environmental information. The deterioration state of the plant is the deterioration state of at least one of the equipment and the power plant of the plant. The prediction unit 103 predicts the deterioration state of the equipment based on, for example, the internal state of the equipment. Furthermore, the prediction unit 103 may predict the deterioration state of the power plant based on unmeasurable environmental information of the power plant.

[0033] The prediction unit 103 predicts time-series changes in the deterioration degree of the plant based on, for example, unmeasurable environmental information. The deterioration degree of the plant is, for example, an index that indicates the progress of deterioration of the plant. The deterioration degree of the plant is, for example, an index whose value increases as the deterioration of the plant progresses. The deterioration degree of the plant may be, for example, an index whose value decreases as the deterioration of the plant progresses. Furthermore, the prediction unit 103 may predict time-series changes in the deterioration degree of the plant based on measurement data and unmeasurable environmental information. Furthermore, the prediction unit 103 may predict time-series changes in the deterioration degree of the plant based on measurement data, control data, and unmeasurable environmental information.

[0034] The time-series change in the deterioration degree of the plant is, for example, a result of predicting how the deterioration degree will change in the future based on measurement data up to the present time and unmeasurable environmental information. The prediction unit 103 predicts, for example, time-series data of the deterioration degree of the plant as the time-series change in the deterioration degree of the plant. The deterioration degree of the plant is, for example, an index based on unmeasurable information. For example, when plant maintenance is performed according to the degree of clogging of piping used in the plant equipment, the deterioration degree of the plant is an index based on the extent to which the piping is clogged.

[0035] The prediction unit 103 uses, for example, a simulator to predict time series data of downstream measurement data based on time series data of measurement data upstream of the unit whose degradation level is to be predicted and control data. The prediction unit 103 acquires time series data of unmeasurable environmental information estimated by an estimation model based on values ​​calculated by the simulator. The prediction unit 103 then predicts time series data of the degradation level based on the time series data of the unmeasurable environmental information.

[0036] The prediction unit 103 may estimate the degree of deterioration using a deterioration prediction model. The deterioration prediction model is, for example, a learning model that estimates the degree of deterioration based on unmeasurable environmental information. The deterioration prediction model predicts time-series data of the degree of deterioration based on time-series data of unmeasurable environmental information. The deterioration prediction model may be a learning model that estimates the degree of deterioration based on measurement data and unmeasurable environmental information. The deterioration prediction model may be a learning model that estimates the degree of deterioration based on measurement data, control data, and unmeasurable environmental information. The deterioration prediction model is generated by learning the relationship between the unmeasurable environmental information and the degree of deterioration. The deterioration prediction model may be generated by learning the relationship between the measurement data, unmeasurable environmental information, and the degree of deterioration. The deterioration prediction model may be generated by learning the relationship between the measurement data, control data, and unmeasurable environmental information, and the degree of deterioration. The deterioration prediction model is generated by, for example, deep learning using a neural network. The learning algorithm for generating the deterioration prediction model is not limited to the above. The deterioration prediction model may also be generated in a system external to the monitoring system 10, for example. The deterioration level prediction model may be generated in a learning unit (not shown) in the monitoring system 10 .

[0037] The deterioration level of the plant may be an index estimated based on a plurality of pieces of unmeasurable environmental information, or may be an index estimated by weighting each of the plurality of pieces of unmeasurable environmental information.

[0038] The maintenance timing estimation unit 104 estimates the timing of plant maintenance based on the prediction result of the deterioration state. The maintenance timing estimation unit 104 estimates the timing of plant maintenance based on, for example, the time when the deterioration state of the plant in the prediction result of the deterioration state will exceed a predetermined standard. The maintenance timing estimation unit 104 estimates, for example, the time when the value of the time-series data of the deterioration degree exceeds the predetermined standard as the timing of plant maintenance. The predetermined standard is set, for example, as a standard for performing plant maintenance when the value of the deterioration degree reaches a value indicated by the standard. In other words, the predetermined standard is set, for example, using the value of the deterioration degree when the state of the plant reaches a state where plant maintenance is necessary. The predetermined standard is set, for example, by a plant supervisor or manager.

[0039] The maintenance timing estimation unit 104 may estimate maintenance timings for multiple stages. When estimating maintenance timings for multiple stages, a predetermined criterion is set for each of the multiple stages. For example, if the plant equipment is piping, the maintenance timing estimation unit 104 estimates maintenance timings for two stages: piping inspection and piping replacement. In this case, a predetermined criterion is set for each of the piping inspection and piping replacement. The piping inspection may be further divided into multiple stages. The piping inspection may be further divided into multiple stages with different inspection items. For example, the inspection items may be divided into hammering inspection, inspection using equipment, and inspection by sample collection depending on the elapsed time since the piping was replaced. The maintenance timing estimation unit 104 may also estimate the maintenance timings for the later stages when multiple maintenance stages are performed and when they are not performed. For example, when maintenance is divided into two stages: piping cleaning and piping replacement, the maintenance timing estimation unit 104 may estimate the maintenance timing for piping replacement depending on whether the piping is cleaned or not.

[0040] The cause estimation unit 105 estimates the cause of the deterioration state of the plant based on, for example, the measurement data and the unmeasurable environmental information. For example, the cause estimation unit 105 compares each of the measurement data and the unmeasurable environmental information with a reference value. Then, the cause estimation unit estimates the cause of the deterioration based on, for example, items in the measurement data and the unmeasurable environmental information that deviate from the reference value. For example, the cause estimation unit 105 estimates the cause of the deterioration based on an event that is predicted from items in the measurement data and the unmeasurable environmental information that deviate from the reference value. For example, if the temperature inside the reactor is higher than the appropriate range, the catalyst activity decreases more rapidly, and deterioration progresses. In this case, when the temperature inside the reactor is higher than the reference value, the cause estimation unit 105 estimates that the deterioration state is caused by the deterioration of the catalyst activity due to the temperature inside the reactor. Furthermore, the cause of the deterioration state is set, for example, in a table showing each item of the measurement data and the unmeasurable environmental information and the cause of the deterioration state. The cause estimation unit 105 may estimate the cause of the deterioration state of the plant based on the measurement data, control data, and unmeasurable environmental information. For example, the cause estimation unit 105 compares each of the measurement data, control data, and unmeasurable environmental information with a reference value. Then, the cause estimation unit 105 estimates the cause of the deterioration based on, for example, items of the measurement data, control data, and unmeasurable environmental information that deviate from the reference value. The reference values ​​of the measurement data, control data, and unmeasurable environmental information are set, for example, in a table indicating the relationship between the measurement data, control data, and unmeasurable environmental information and the reference values.

[0041] The cause estimation unit 105 may estimate the cause of deterioration of the plant based on, for example, the amount of deviation between the measurement data and the unmeasurable environmental information and their respective reference values. The cause estimation unit 105 may score the degree of influence on the deterioration state of the plant based on, for example, the amount of deviation between the measurement data and the unmeasurable environmental information and their respective reference values. For example, the score is set so that the greater the influence on the deterioration state of the plant, the higher the score. The cause estimation unit 105 then estimates the cause of deterioration based on the item with the highest score. The score indicating the degree of influence on the deterioration level may be set, for example, in a table indicating the relationship between the amount of deviation between the measurement data and the unmeasurable environmental information and their respective reference values ​​and the score. The score indicating the degree of influence on the deterioration level may be set using a function indicating the relationship between the amount of deviation between the measurement data and the unmeasurable environmental information and their respective reference values ​​and the score. The cause estimation unit 105 may estimate an item with a score equal to or higher than a reference value as the cause of deterioration. Alternatively, the cause estimation unit 105 may estimate a predetermined number of items with the highest scores as the cause of deterioration. In addition, the cause estimation unit 105 may estimate the cause of deterioration of the plant based on at least one of the length of time and the number of times that the measurement data and the unmeasurable environmental information deviate from the standard, and the amount of deviation from the standard value.

[0042] The cause estimation unit 105 may estimate the cause of deterioration of the plant using a cause estimation model. The cause estimation model is, for example, a learning model that has learned the relationship between the measurement data, unmeasurable environmental information, and the cause of deterioration. The cause estimation model estimates the cause of deterioration based on, for example, the measurement data and unmeasurable environmental information. The cause estimation model takes, for example, the measurement data and unmeasurable environmental information as input, and outputs an estimation result of the cause of deterioration. The cause estimation model may be a learning model that has learned the relationship between the measurement data, control data, and unmeasurable environmental information, and the cause of deterioration. The cause estimation model estimates the cause of deterioration based on, for example, the measurement data, control data, and unmeasurable environmental information. The cause estimation model takes, for example, the measurement data, control data, and unmeasurable environmental information as input, and outputs an estimation result of the cause of deterioration.

[0043] The cause estimation model is generated, for example, by deep learning using a neural network. The cause estimation model is generated, for example, by performing learning using feature vectors converted from time-series data of the measurement data and unmeasurable environmental information as input data and causes of deterioration as labels. The learning algorithm for generating the cause estimation model is not limited to the above. The cause estimation model may be generated, for example, in a system external to the monitoring system 10. The cause estimation model may also be generated in a learning unit (not shown) within the monitoring system 10.

[0044] The effect estimation unit 106 estimates the effect of plant maintenance to be performed at the estimated maintenance time based on, for example, predicted values ​​of measurement data and predicted values ​​of unmeasurable environmental information in the case where plant maintenance is not performed. The effect estimation unit 106 may estimate the effect of plant maintenance to be performed at the estimated maintenance time based on predicted values ​​of measurement data, control data, and predicted values ​​of unmeasurable environmental information.

[0045] The effect estimation unit 106 estimates, for example, the degree of improvement of the deteriorated state of the plant due to maintenance performed at the estimated maintenance time. The effect estimation unit 106 estimates the degree of improvement based on, for example, the state of the plant if maintenance was not performed and the state of the plant expected after maintenance. The effect estimation unit 106, for example, predicts time-series data of measurement data from the time-series data up to the current time point. The current time point is, for example, the time point on the time series at which the effect estimation unit 106 estimates the degree of improvement of the deteriorated state of the plant. Furthermore, the effect estimation unit 106 estimates the value of the unmeasurable environmental information at each time point after the current time point, for example, using an estimation model. Then, the effect estimation unit 106 sets, for example, the estimated value of the unmeasurable environmental information at each time point after the current time point as the predicted value at each time point. For example, data on the state of the plant after maintenance performed in the past is used as the state of the plant expected after maintenance. The effect estimation unit 106 estimates, for example, the degree of improvement in the production efficiency of the plant due to maintenance performed at the estimated maintenance time. The production efficiency of the plant is calculated, for example, based on immeasurable environmental information. The effect estimation unit 106 estimates the degree of improvement in the production efficiency based, for example, on an index related to the production efficiency calculated based on immeasurable environmental information and an estimated value of an index related to the production efficiency when maintenance is performed. For example, if the plant is a chemical plant, the effect estimation unit 106 calculates the yield of the reactant based on the activity of the catalyst. Then, the effect estimation unit 106 estimates the degree of improvement in the yield of the reactant based on the calculated yield of the reactant and the estimated yield of the reactant after maintenance. The target for estimating the effect of maintenance is not limited to the above.

[0046] The accuracy estimation unit 107 estimates the accuracy of the estimated value of the unmeasurable environmental information, for example. The accuracy estimation unit 107 estimates the accuracy of the estimated value of the unmeasurable environmental information, for example, based on the result of comparing the plant's measurement data with the simulator's value. For example, assume that a discrepancy occurs between the plant's measurement data corresponding to the simulator's output value and the simulator's output value. In this case, the accuracy estimation unit 107 matches, for example, a simulator parameter corresponding to the unmeasurable environmental information with the estimated value of the unmeasurable environmental information estimated by the estimation unit 102. If, as a result of the matching, the difference between the measurement data and the simulator's output value falls within a predetermined standard, the accuracy estimation unit 107 determines that the estimated value of the unmeasurable environmental information is highly accurate. The predetermined standard is set, for example, by a monitor or a manager.

[0047] For example, assume that the unmeasurable environmental information is catalyst activity and the measurement data is temperature. In this case, the accuracy estimation unit 107, for example, matches the simulator parameters to an estimated value of the catalyst activity, where the unmeasurable environmental information is the unmeasurable environmental information. If, as a result of the matching, the difference between the temperature of the measurement data and the temperature output value of the simulator falls within a predetermined standard, the accuracy estimation unit 107 determines that the accuracy of the estimated value of the unmeasurable environmental information is high. The accuracy estimation unit 107 may also estimate an index of accuracy of the estimated value of the unmeasurable environmental information based on the difference between the measurement data and the output value of the simulator. For example, the accuracy estimation unit 107 normalizes the difference between the measurement data and the output value of the simulator using the average value of the corresponding measurement data. Then, the accuracy estimation unit 107 estimates the accuracy of the estimated value of the unmeasurable environmental information using, for example, the absolute value of the normalized value as an index. For example, the accuracy estimation unit 107 estimates the accuracy of the estimated value of the unmeasurable environmental information such that the smaller the absolute value of the normalized value, the higher the accuracy of the estimated value of the environmental information.

[0048] The plan creation unit 108 creates an operation plan for the plant to improve the degradation state based on, for example, measurement data, unmeasurable environmental information, and plant control data. The plan creation unit 108, for example, creates control data to suppress the progression of plant degradation. The plan creation unit 108 may determine a change value for the control data based on the measurement data and unmeasurable environmental information so as to suppress the progression of plant degradation. Then, the plan creation unit 108 creates the control data to suppress the progression of plant degradation based on, for example, the change value for the control data. The relationship between the measurement data and unmeasurable environmental information and the control data that suppresses degradation or the change value for the control data may be set as table-format data. The relationship between the measurement data and unmeasurable environmental information and the control data that suppresses degradation may be established using a function. The plan creation unit 108, for example, creates the operation plan using time-series data of the control data. For example, if suppressing the temperature of a reactor will lengthen the time until maintenance is required, the plan creation unit 108 creates the operation plan using, for example, time-series data of the temperature setpoint.

[0049] The output unit 109 outputs the maintenance timing estimated by the maintenance timing estimation unit 104. The output unit 109 outputs the maintenance timing estimated by the maintenance timing estimation unit 104 to, for example, the terminal device 30. The output unit 109 outputs the maintenance timing estimated by the maintenance timing estimation unit 104 to a display device (not shown) connected to the monitoring system 10. In addition to the estimated maintenance timing, the output unit 109 may also output at least one of measurement data, estimated non-measurable environmental information, and control data. The output unit 109 outputs at least one of measurement data, estimated non-measurable environmental information, and control data to, for example, the terminal device 30. In addition to the estimated maintenance timing, the output unit 109 may also output the cause of deterioration estimated by the cause estimation unit 105. The output unit 109 outputs the cause of deterioration estimated by the cause estimation unit 105 to, for example, the terminal device 30. The output unit 109 may output information on items that cause the deterioration of the plant estimated by the cause estimation unit 105 in association with maintenance timings. Furthermore, the output unit 109 may output the effect of maintenance estimated by the effect estimation unit 106 in addition to the estimated maintenance timings. The output unit 109 outputs the effect of maintenance to, for example, the terminal device 30. Furthermore, the output unit 109 may output the accuracy of the estimation of the maintenance timings estimated by the accuracy estimation unit 107 in addition to the estimated maintenance timings. The output unit 109 outputs the accuracy of the estimation of the maintenance timings estimated by the accuracy estimation unit 107 in addition to the terminal device 30. The output unit 109 may output the operation plan created by the plan creation unit 108 in addition to the estimated maintenance timings. The output unit 109 outputs the created operation plan to, for example, the terminal device 30.

[0050] Fig. 4 is a diagram showing an example of a display screen for the results of the estimation of the maintenance timing. The example of the display screen in Fig. 4 is a screen that displays data related to the "R unit" which is a reactor. In the example of the display screen in Fig. 4, graphs of "Feedstock A supply amount," "Feedstock B supply amount," "Reactor temperature," "Catalyst activity," and "Deterioration level (estimated value)" are displayed.

[0051] In the example of the display screen of FIG. 4 , the vertical axis of the graph for "Feedstock A Supply Amount" represents the flow rate of "Feedstock A" supplied to the reactor. In the example of the display screen of FIG. 4 , the horizontal axis of the graph for "Feedstock A Supply Amount" represents time. The "Current Time" on the horizontal axis of the graph for "Feedstock A Supply Amount" represents, for example, the time at the time the display screen is displayed. In addition, in the graph for "Feedstock A Supply Amount," data to the left of the current time represents measurement data of the flow rate obtained by the sensor 20. In addition, in the graph for "Feedstock A Supply Amount," data to the right of the current time represents an estimated value of the flow rate after the current time, estimated based on the measurement data. In addition, in the example of the display screen of FIG. 4 , the vertical axis of the graph for "Feedstock B Supply Amount" represents the flow rate of "Feedstock B" supplied to the reactor. In addition, in the example of the display screen of FIG. 4 , the horizontal axis of the graph for "Feedstock B Supply Amount" represents time. In the example of the display screen of FIG. 4 , the vertical axis of the graph for "Reactor Temperature" represents the measured value of the temperature inside the reactor. In the example of the display screen in Figure 4, the horizontal axis of the graph for "Reactor Temperature" represents time. In the graph for "Feed Rate of Raw Material B," the data on the left side of the current time represent measurement data of the flow rate obtained by the sensor 20. In the graph for "Feed Rate of Raw Material A," the data on the right side of the current time represent estimated values ​​of the flow rate after the current time, which are estimated based on the measurement data.

[0052] In addition, in the example of the display screen of Figure 4, the vertical axis of the "catalytic activity" graph indicates an estimated value of the activity of the catalyst in the reactor. The estimated value of the catalyst activity is unmeasurable environmental information estimated by the estimation unit 102 based on measurement data. In the example of the display screen of Figure 4, the horizontal axis of the "reactor temperature" graph indicates time. In the "catalytic activity" graph, the data to the left of the current time are estimated values ​​of the catalyst activity estimated based on measurement data by the sensor 20. In addition, in the "catalytic activity" graph, the data to the right of the current time indicate estimated values ​​of the catalyst activity from the current time onwards, estimated by the estimation unit 102 based on estimated values ​​up to the current time.

[0053] In the example of the display screen of FIG. 4 , the vertical axis of the graph of "Deterioration Level (Predicted Value)" represents the value of the deterioration level of the plant. This is the predicted value of the deterioration level of the plant predicted by the prediction unit 103. In the graph of "Deterioration Level (Predicted Value)," data to the left of the current time represents the deterioration level calculated by the prediction unit 103. In the example of the display screen of FIG. 4 , the deterioration level is an index whose value decreases as deterioration progresses. In the graph of "Deterioration Level (Predicted Value)," data to the right of the current time represents, for example, the predicted value of the deterioration level after the current time, predicted by the prediction unit 103. In the graph of "Deterioration Level (Predicted Value)," "Maintenance Timing" represents the time of the maintenance timing estimated by the maintenance timing estimation unit 104. In the example of the display screen of FIG. 4 , information indicating the maintenance timing estimated by the maintenance timing estimation unit 104 is displayed as "Recommended Maintenance Timing: June 24, 2023." A plant supervisor can appropriately determine the maintenance timing of plant equipment by, for example, referring to the display screen of FIG. 4 .

[0054] FIG. 5 is a diagram showing an example of a display screen that further displays the estimation accuracy of the maintenance timing estimation result in addition to the same display content as FIG. 4 . The example of the display screen in FIG. 5 displays graphs of the “Feedstock A Supply Amount,” “Feedstock B Supply Amount,” “Reactor Temperature,” “Catalyst Activity,” and “Deterioration Level (Estimated Value),” similar to FIG. 4 . The example of the display screen in FIG. 5 also displays information indicating the maintenance timing estimated by the maintenance timing estimation unit 104, similar to FIG. 4 . The example of the display screen in FIG. 5 further displays the accuracy of the maintenance timing estimation estimated by the accuracy estimation unit 107 in addition to the maintenance timing estimation result. The example of the display screen in FIG. 5 displays information indicating the estimation accuracy estimated by the accuracy estimation unit 107, such as “Estimated Accuracy: 95%.” For example, by referring to the display screen in FIG. 5 , a plant supervisor can determine the validity of the estimation result of the maintenance timing of plant equipment.

[0055] FIG. 6 is a diagram showing an example of a display screen that displays the same display content as FIG. 4 , as well as the results of an estimation of the cause of the plant's deteriorated state. The example of the display screen of FIG. 6 displays graphs of "Feedstock A Supply Amount," "Feedstock B Supply Amount," "Reactor Temperature," "Catalyst Activity," and "Deterioration Level (Estimated Value)," as in FIG. 4 . The example of the display screen of FIG. 6 also displays information indicating the maintenance timing estimated by the maintenance timing estimation unit 104, as in FIG. 4 . In the example of the display screen of FIG. 6 , "Cause of Deterioration" is information indicating the cause of the plant deterioration estimated by the cause estimation unit 105. In the example of the display screen of FIG. 6 , the causes of the plant deterioration estimated by the cause estimation unit 105 are displayed as "High Reactor Temperature" and "Large Feedstock A Supply Amount." By referring to the example of the display screen of FIG. 6 , for example, a plant supervisor can easily understand the cause of the plant's deteriorated state and the maintenance timing. Therefore, by referring to the example of the display screen of FIG. 6 , the plant supervisor can, for example, more appropriately determine the plant's operation and maintenance timing.

[0056] The memory unit 110 stores, for example, data related to the plant. The data related to the plant is, for example, data related to prediction of the deterioration state of the plant. The data related to prediction of the deterioration state of the plant is, for example, measurement data of the plant's equipment and control data of the plant. The data related to prediction of the deterioration state of the plant is, for example, estimation results of unmeasurable environmental information and prediction results of the deterioration state of the plant. The data related to prediction of the deterioration state of the plant may be, for example, estimation results of the cause of plant deterioration, estimation results of the effectiveness of plant maintenance, estimation results of the accuracy of estimated values ​​of unmeasurable environmental information, and plant operation plans. The data related to prediction of the deterioration state of the plant stored in the memory unit 110 is not limited to the above.

[0057] The storage unit 110 may further store a table relating to standards set for predicting the degradation state of the plant. The storage unit 110 may store a learning model relating to predicting the degradation state of the plant. The storage unit 110 stores, for example, an estimation model. The storage unit 110 stores, for example, a degradation degree prediction model. The storage unit 110 stores, for example, a cause estimation model. Furthermore, the estimation model, the degradation degree prediction model, and the cause estimation model may be stored in a storage means other than the storage unit 110.

[0058] The sensor 20 measures, for example, the status of plant equipment. The sensor 20 outputs measured data to, for example, the acquisition unit 101 of the monitoring system 10. The sensor 20 may be installed at multiple locations in the plant equipment. Furthermore, the sensor 20 may be installed in each of the multiple pieces of plant equipment. For example, a type of sensor corresponding to the physical quantity to be measured is used as the sensor 20. For example, a temperature sensor, a pressure sensor, a flow velocimetry, a flow meter, a viscometer, a transmittance sensor, or a torque measuring instrument is used as the sensor 20. The sensor 20 is not limited to the above. When the measurement target is a plant pipe, the sensor 20 measures data on at least one item of temperature, flow rate, flow velocity, pressure, vibration, and transmittance inside the plant pipe. The data items measured by the sensor 20 are not limited to the above. Furthermore, the measurement target is not limited to the plant pipe. The sensor 20 may be installed in a power plant of the plant. For example, the sensor 20 measures the status of the power plant of the plant.

[0059] The terminal device 30 is, for example, a terminal device used to monitor the state of a plant. The terminal device 30 is, for example, a terminal device used by a plant monitor to check the estimation result of the maintenance timing. The terminal device 30 acquires the estimation result of the maintenance timing, for example, from the output unit 109 of the monitoring system 10. Then, the terminal device 30 outputs the estimation result of the maintenance timing to a display device (not shown). The terminal device 30 may acquire the effect of maintenance from the output unit 109 of the monitoring system 10. Then, for example, the terminal device 30 outputs the effect of maintenance to a display device (not shown). The terminal device 30 may acquire the cause of deterioration of the plant from the output unit 109 of the monitoring system 10. Then, for example, the terminal device 30 outputs the cause of deterioration of the plant to a display device (not shown). The terminal device 30 may acquire an operation plan from the output unit 109 of the monitoring system 10. Then, the terminal device 30 outputs the operation plan to a display device (not shown).

[0060] For example, a personal computer, a tablet computer, a smartphone, or a wearable terminal device is used as the terminal device 30. Examples of the terminal device used as the terminal device 30 are not limited to those mentioned above.

[0061] An example of an operation of the monitoring system 10 to estimate a maintenance time will be described below. Fig. 7 is a diagram showing an example of an operation flow in a process in which the monitoring system 10 estimates a maintenance time.

[0062] The acquisition unit 101 acquires measurement data relating to the plant equipment (step S11). The acquisition unit 101 acquires the measurement data relating to the plant equipment from the sensor 20, for example.

[0063] When the measurement data relating to the equipment of the plant is acquired, the estimation unit 102 estimates unmeasurable environmental information relating to the plant based on the measurement data relating to the equipment (step S12).

[0064] If there is unmeasurable environmental information data required for degradation prediction (Yes in step S13), the prediction unit 103 predicts the degradation state of the plant based on the unmeasurable environmental information (step S14).

[0065] When the deterioration state of the plant is predicted, the maintenance timing estimation unit 104 estimates the maintenance timing of the plant based on the prediction result of the deterioration state (step S15).

[0066] When the plant maintenance time is estimated, the output unit 109 outputs the plant maintenance time (step S16). The output unit 109 outputs the plant maintenance time to, for example, the terminal device 30.

[0067] In step S13, if there is no unmeasurable environmental information data necessary for deterioration prediction (No in step S13), for example, the process returns to step S11, and the acquisition unit 101 acquires measurement data of the plant equipment.

[0068] The monitoring system 10 estimates unmeasurable environmental information about the plant based on measurement data of the plant's equipment. The monitoring system 10 also estimates the deterioration state of the plant based on the estimated unmeasurable environmental information. The monitoring system 10 then estimates the timing of plant maintenance based on the predicted deterioration state of the plant. For example, the monitoring system 10 estimates the internal state of the plant's equipment based on measurement data of the plant's equipment. The monitoring system 10 also predicts, for example, the deterioration state of the plant's equipment. The monitoring system 10 then estimates the timing of plant maintenance based on the predicted deterioration state of the plant's equipment. By estimating the timing of plant maintenance based on unmeasurable environmental information in this way, the monitoring system 10 can appropriately estimate the timing of maintenance according to the unmeasurable plant condition. Therefore, use of the monitoring system 10 can improve the accuracy of estimating the timing of plant maintenance.

[0069] For example, the monitoring system 10 can estimate an appropriate maintenance timing according to the internal state of the plant equipment. For example, if the plant equipment is piping, the monitoring system 10 can estimate the maintenance timing according to the internal state of the piping. By estimating the maintenance timing according to the internal state of the piping, it is possible to prevent the occurrence of plant malfunctions due to delays in replacing and maintaining the piping while it is still in a usable state. In other words, the monitoring system 10 can appropriately estimate the maintenance timing of the piping. In this way, by using the monitoring system 10, it is possible to estimate an appropriate maintenance timing for the plant.

[0070] The processes in the monitoring system 10 may be distributed and executed among a plurality of information processing devices connected via a network. For example, the process of estimating unmeasurable environmental information in the estimation unit 102, the process of predicting the deterioration state of the plant in the prediction unit 103, and the process of estimating the maintenance timing in the maintenance timing estimation unit 104 may be performed in different information processing devices. Furthermore, for example, the process of estimating unmeasurable environmental information in the estimation unit 102, the process of predicting the deterioration state of the plant in the prediction unit 103, and the process of estimating the maintenance timing in the maintenance timing estimation unit 104 may be performed in different information processing devices. Which of the processes performed in the monitoring system 10 is to be performed by the terminal device can be set as appropriate.

[0071] Each process in the monitoring system 10 can be realized by executing a computer program on a computer. Fig. 8 shows an example of the configuration of a computer 200 that executes a computer program that performs each process in the monitoring system 10. The computer 200 includes a CPU (Central Processing Unit) 201, a memory 202, a storage device 203, an input / output I / F (Interface) 204, and a communication I / F 205.

[0072] The CPU 201 reads and executes computer programs for performing each process from the storage device 203. The CPU 201 may be configured with a combination of multiple CPUs. The memory 202 is configured with a dynamic random access memory (DRAM) or the like, and temporarily stores the computer programs executed by the CPU 201 and data being processed. The storage device 203 stores the computer programs executed by the CPU 201. The storage device 203 is configured with, for example, a non-volatile semiconductor storage device. Other storage devices such as a hard disk drive may also be used for the storage device 203. The input / output I / F 204 is an interface that receives input from an operator and outputs display data, etc. The communication I / F 205 is an interface that transmits and receives data between the sensor 20 and the terminal device 30. The terminal device 30 may also have a configuration similar to that of the computer 200.

[0073] The computer program used to execute each process can also be stored and distributed on a computer-readable recording medium that non-temporarily stores data. Examples of recording media that can be used include magnetic tapes for recording data and magnetic disks such as hard disks. Optical disks such as CD-ROMs (Compact Disc Read Only Memory) can also be used as recording media. Non-volatile semiconductor storage devices can also be used as recording media.

[0074] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0075] [Supplementary Note 1] A monitoring system comprising: an acquisition means for acquiring measurement data relating to equipment of a plant; an estimation means for estimating unmeasurable environmental information relating to the plant based on the measurement data; a prediction means for predicting a deterioration state of the plant based on at least the unmeasurable environmental information; a maintenance timing estimation means for estimating a maintenance timing for the plant based on a result of the prediction of the deterioration state; and an output means for outputting the estimated maintenance timing.

[0076] [Supplementary Note 2] The monitoring system according to Supplementary Note 1, wherein the estimation means estimates an internal state of the facility based on the measurement data, and the prediction means predicts a deterioration state inside the facility based on the internal state of the facility.

[0077] [Supplementary Note 3] The monitoring system described in Supplementary Note 1, wherein the estimation means estimates unmeasurable environmental information of a power plant that operates equipment of the plant based on the measurement data, and the prediction means predicts a deterioration state of the power plant based on the unmeasurable environmental information of the power plant.

[0078] [Supplementary Note 4] The monitoring system according to any one of Supplementary Notes 1 to 3, wherein the acquisition means further acquires control data related to the plant, and the estimation means estimates unmeasurable environmental information related to the plant based on the measurement data and the control data.

[0079] [Supplementary Note 5] The monitoring system according to Supplementary Note 4, wherein the prediction means predicts a deterioration state of the plant based on the measurement data, the control data, and the unmeasurable environmental information.

[0080] [Supplementary Note 6] The monitoring system according to any one of Supplementary Notes 1 to 3, further comprising a cause estimation means for estimating a cause of deterioration of the plant based on the measurement data and the unmeasurable environmental information, and the output means further outputs the cause of deterioration of the plant.

[0081] [Supplementary Note 7] The monitoring system described in any one of Supplementary Notes 1 to 3, further comprising an effect estimation means for estimating an effect of maintenance of the plant based on the estimated value of the measurement data and the estimated value of the unmeasurable environmental information, and the output means further outputs the effect of the maintenance.

[0082] [Supplementary Note 8] The monitoring system described in any one of Supplementary Notes 1 to 3, further comprising an influence estimation means for estimating an influence of at least one of the measurement data and the unmeasurable environmental information on the prediction of the degradation state, wherein the output means further outputs the estimated influence.

[0083] [Supplementary Note 9] The monitoring system according to any one of Supplementary Notes 1 to 3, further comprising an accuracy estimation unit that estimates accuracy of the estimated value of the unmeasurable environmental information, wherein the output unit further outputs the estimated accuracy.

[0084] [Supplementary Note 10] The monitoring system according to any one of Supplementary Notes 1 to 3, further comprising a plan creation means for creating an operation plan for the plant to improve the deteriorated state based on the measurement data, the unmeasurable environmental information, and control data of the plant, wherein the output means further outputs the operation plan.

[0085] [Supplementary Note 11] A monitoring method comprising: acquiring measurement data relating to equipment of a plant; estimating unmeasurable environmental information relating to the plant based on the measurement data; predicting a deterioration state of the equipment based on at least the unmeasurable environmental information; estimating a maintenance timing for the plant based on the predicted result of the deterioration state; and outputting the estimated maintenance timing.

[0086] [Supplementary Note 12] A recording medium that non-temporarily records a monitoring program that causes a computer to execute the following processes: a process of acquiring measurement data related to equipment of a plant; a process of estimating unmeasurable environmental information related to the plant based on the measurement data; a process of predicting a deterioration state of the equipment based on at least the unmeasurable environmental information; a process of estimating a maintenance timing for the plant based on the predicted result of the deterioration state; and a process of outputting the estimated maintenance timing.

[0087] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 10, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 11 and 12 in the same dependent relationship as Supplementary Notes 2 to 10. Furthermore, not limited to Supplementary Notes 1, 11, and 12, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0088] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0089] This application claims priority based on Japanese Patent Application No. 2023-096106, filed on June 12, 2023, the disclosure of which is incorporated herein in its entirety.

[0090] REFERENCE SIGNS LIST 10 Monitoring system 101 Acquisition unit 102 Estimation unit 103 Prediction unit 104 Maintenance timing estimation unit 105 Cause estimation unit 106 Effect estimation unit 107 Accuracy estimation unit 108 Plan creation unit 109 Output unit 110 Storage unit 20 Sensor 30 Terminal device 200 Computer 201 CPU 202 Memory 203 Storage device 204 Input / output I / F 205 Communication I / F

Claims

1. an acquisition means for acquiring measurement data relating to equipment of the plant; an estimation means for estimating unmeasurable environmental information related to the plant based on the measurement data; a prediction means for predicting a deterioration state of the plant based on at least the unmeasurable environmental information; a maintenance timing estimation means for estimating a maintenance timing of the plant based on the predicted result of the deterioration state; an output means for outputting the estimated maintenance time; A monitoring system comprising:

2. the estimation means estimates an internal state of the equipment based on the measurement data; the prediction means predicts a deterioration state inside the facility based on the internal state of the facility. The monitoring system of claim 1 .

3. the estimation means estimates unmeasurable environmental information of a power plant that operates equipment of the plant based on the measurement data; the prediction means predicts the deterioration state of the power plant based on unmeasurable environmental information of the power plant. The monitoring system of claim 1 .

4. the acquiring means further acquires control data relating to the plant; the estimation means estimates unmeasurable environmental information related to the plant based on the measurement data and the control data.

4. A monitoring system according to claim 1.

5. the prediction means predicts a deterioration state of the plant based on the measurement data, the control data, and the unmeasurable environmental information. The monitoring system of claim 4.

6. further comprising a cause estimation means for estimating a cause of deterioration of the plant based on the measurement data and the unmeasurable environmental information; The output means further outputs a cause of deterioration of the plant.

4. A monitoring system according to claim 1.

7. further comprising an effect estimation means for estimating an effect of the maintenance of the plant based on a predicted value of the measurement data and a predicted value of the unmeasurable environmental information in a case where the maintenance of the plant is not performed, The output means further outputs the effect of the maintenance.

4. A monitoring system according to claim 1.

8. further comprising an influence estimation means for estimating an influence of at least one of the measurement data and the unmeasurable environmental information on the prediction of the degradation state, The output means further outputs the estimated degree of influence.

4. A monitoring system according to claim 1.

9. Acquire measurement data on plant equipment, estimating unmeasurable environmental information about the plant based on the measurement data; predicting a degradation state of the plant based on at least the unmeasurable environmental information; estimating a maintenance timing for the plant based on the predicted deterioration state; outputting the estimated maintenance time; Monitoring method.

10. A process of acquiring measurement data relating to plant equipment; a process of estimating non-measurable environmental information about the plant based on the measurement data; predicting a degradation state of the plant based on at least the unmeasurable environmental information; a process of estimating a maintenance timing of the plant based on the predicted result of the deterioration state; A process of outputting the estimated maintenance time. A monitoring program that causes a computer to run the following.