Operation management method and operation management device

Abstract

To make it possible to accurately and easily determine replacement timing of a functional material in a system and detect an occurrence of an abnormality based on time-series data obtained from the system regarding an operation and status of a management target system, whatever that system may be.SOLUTION: An operation management method for managing an operation of a system of a management target includes: a process (steps 101, 106) of acquiring time-series data for each of N kinds of quantities related to an operation and status of the system from the management target system, where N is an integer equal to or greater than 2; a process (steps 102, 107) of calculating an average value of each time-series data for each of a series of averaging periods; and a process (steps 103, 108) of generating dispersion data by plotting an average value for each averaging period in an N-dimensional space (discrimination space) with each of the N types of quantities as a coordinate axis.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an operation management method and an operation management device for monitoring the states of various systems, such as water treatment systems for producing pure water or ultrapure water, and managing the operation of these systems. [Background technology]

[0002] Water treatment systems, such as pure water production systems that produce pure water or ultrapure water from raw water and wastewater treatment systems that perform wastewater treatment, are configured by combining various devices such as filtration devices, activated carbon devices, ion exchange devices, reverse osmosis membrane devices, ultraviolet oxidation devices, coagulation sedimentation devices, and electrodeionization water production devices (EDI (electrodeionization) devices), and further include pipes, heat exchangers, pumps, and the like. Activated carbon filled in activated carbon devices is a functional material that needs to be replaced at appropriate times. Ion exchange resins used in ion exchange devices are also functional materials that need to be regenerated or replaced. Such functional materials are replaced based on, for example, the operating time or the amount of treated water. However, when replacing based on the operating time or the amount of treated water, functional materials that are still usable may be replaced, and therefore optimization of the replacement timing of functional materials is required. In order to optimize the replacement timing of functional materials, for example, it is conceivable to measure the water quality of the treated water, analyze the fluctuation in the water quality data, evaluate the performance of the functional material, and determine whether it has deteriorated. Furthermore, in a water treatment system, malfunctions can occur in each device, including pumps, and there is a demand for early detection of such abnormalities and identification of the cause of the malfunction.

[0003] In a water treatment system, evaluating the performance of a functional material based on actually measured data, determining when to replace the functional material, detecting the occurrence of an abnormality, and identifying the cause of the failure are the operations of managing and optimizing the water treatment system. In the following explanation, optimizing the operation is also included in managing the operation. In the past, it was considered that skilled skill was required to analyze water quality data in evaluating the performance of a functional material based on water quality data, determining when to replace the functional material, detecting the occurrence of an abnormality, and identifying the cause of the failure. Therefore, various methods have been proposed to make it easier to manage the operation of a water treatment system.

[0004] Patent Document 1 discloses a method for evaluating the performance of anion exchange resin packed in an ion exchange resin tower in a water treatment system, in which a mass transfer coefficient of the anion exchange resin for inorganic carbonic acid is calculated from the measured inorganic carbonic acid concentrations in the inlet water and outlet water of the ion exchange resin tower, and the dynamic characteristics and the degree of deterioration of the anion exchange resin are evaluated based on the mass transfer coefficient. Patent Document 2 discloses a method for evaluating the performance of the ion exchange resin by mixing and contacting a salt aqueous solution of a predetermined concentration with a predetermined amount of ion exchange resin, and measuring the change over time in the electrical conductivity of the salt aqueous solution after the mixing and contact. Patent Document 3 discloses a water treatment system having a plurality of ion exchange resin towers of the same type and treatment capacity installed in parallel, in which the same water to be treated is passed through each ion exchange resin tower to obtain treated water, in which the load of water passed through some ion exchange resin towers is higher than that of other ion exchange resin towers, and when deterioration in the water treated by the highly loaded ion exchange resin tower occurs, the lifespan of the other ion exchange resin towers is predicted based on the integrated load at that time, and the amount and time of water passed through each ion exchange resin tower thereafter is controlled based on the prediction result.

[0005] Patent Documents 4-8 disclose that when an ion exchange apparatus is operated to repeat a water passing process and a regeneration process, the water quality of the raw water is measured, a prediction is made based on the measured values, and the water passing process is switched to the regeneration process based on the prediction. Patent Document 9 discloses that in a moving bed ion exchange apparatus, the amount of water passing through a water passing tower, the conductivity of the raw water, and the silica concentration of ion-exchanged water are detected, the amount of regenerating agent to be injected into the regeneration tower is calculated from the amount of water passing and the conductivity, the calculated value is corrected by the silica concentration, and the amount of regenerating agent injected is adjusted based on the corrected calculated value.

[0006] In systems other than water treatment systems, there is a demand for reliable and easy detection of occurrence of abnormalities in the system. To solve such a problem, Patent Document 10 discloses a method for diagnosing abnormalities in equipment that operates by strictly repeating a certain pattern, such as a sizing press equipment, which is one type of continuous rolling equipment, by sampling time series data that shows the state of the equipment, which repeats a pattern corresponding to the certain pattern, and diagnosing the equipment abnormality based on the sampled time series data. In the diagnosis of the equipment abnormality, a first principal component analysis is performed on one pattern in the sampled time series data to determine whether or not there is a first abnormality, and if the first abnormality determination indicates that there is an abnormality, a second principal component analysis is performed collectively on a plurality of patterns that are consecutive in time, including the pattern subjected to the first principal component analysis, to determine whether or not there is a second abnormality, and if the second abnormality determination indicates that there is an abnormality, it is determined that there is an equipment abnormality. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2002-48776 A [Patent Document 2] JP 2015-13276 A [Patent Document 3] JP 2018-111058 A [Patent Document 4] JP 2023-34710 A [Patent Document 5] JP 2014-188456 A [Patent Document 6] Patent Publication No. 2021-3675 [Patent Document 7] Japanese Patent Application Publication No. 5-277382 [Patent Document 8] Japanese Patent Application Publication No. 6-55082 [Patent Document 9] Special Publication No. 59-31377 [Patent Document 10] International Publication No. 2021 / 145156 Summary of the Invention [Problem to be solved by the invention]

[0008] Regarding the management of the operation of a water treatment system, many proposals have been made for a method of predicting the regeneration or replacement timing of ion exchange resin in an ion exchange device, but few proposals have been made for easily detecting the occurrence of an abnormality and identifying the cause of the failure. The abnormality diagnosis method described in Patent Document 10 is intended for equipment that operates in a strictly constant cycle, and is difficult to apply to a water treatment system in which, for example, the operating state changes depending on the water quality of the raw water, and the timing of regeneration of the ion exchange resin changes significantly accordingly. In addition, some water treatment systems do not have a clear cycle such as a cycle consisting of a water flow process and a regeneration process, and it is difficult to apply the technology of Patent Document 10 to such water treatment systems. In addition, although water quality data obtained from a water treatment system can also be said to be time-series data, when processing time-series data obtained from a managed system to determine the replacement timing of a functional material or detect the occurrence of an abnormality in the system, the accuracy of the determination or detection may be reduced due to variations in values ​​in the time-series data due to hunting, etc.

[0009] An object of the present invention is to provide an operation management method and an operation management device that can accurately and easily manage the operation of a system based on time-series data obtained from the system regarding the operation and status of the system, regardless of the system to be managed. [Means for solving the problem]

[0010] Although time series data on a quantity x related to the operation and state of a managed system may be discrete with respect to time t, it can be treated as a function x=f(t) with time t as an independent variable and quantity x as a dependent variable. Conventionally, when attempting to detect the occurrence of an abnormality in a system using time series data, analysis was performed by detecting changes in the value of a function f(t) that explicitly includes time t. However, the time series data obtained from the managed system includes effects such as hunting, which reduces the accuracy of the analysis. In addition, analysis of the time series data itself often requires skilled techniques. Therefore, in the present invention, multiple time series data x1=f1(t), x2=f2(t), ..., which are time series data on different types of quantities, are obtained from the managed system, and a dimensionality reduction method is used to reduce the dimension of time t, and scatter data is generated by plotting the values ​​x1, x2, ... of each time series data at the same time t as points P(x1, x2, ...) in a space whose coordinate axis is the quantity represented by each time series data. The space in which the scatter data is generated is called a discriminant space. In reality, it is difficult to measure each quantity at exactly the same time in the managed system, and also to reduce the effects of hunting, an averaging period is determined, and the averages m1, m2, ... of the time series data x1 = f1(t), x2 = f2(t), ... are calculated for each averaging period, and point P(m1, m2, ...) is arranged in the discriminant space to create scatter data. The averaging period can be appropriately determined according to the operating mode of the managed system, as long as it is common to multiple types of time series data.

[0011] Therefore, an operation management method of one embodiment of the present invention is an operation management method for managing the operation of a managed system, which obtains time series data for each of N types of quantities related to the operation and status of the system, where N is an integer of 2 or greater, from the system, calculates the average value of each of the time series data for each of a series of averaging periods defined in the system, and generates scatter data by plotting the average values ​​for each averaging period in an N-dimensional space, i.e., a discriminant space, with each of the N types of quantities as its coordinate axes.

[0012] Once the scatter data is generated in this manner, the occurrence of an abnormality in the managed system can be detected from the arrangement of each plot point constituting the scatter data in the discriminant space. In addition, since points are plotted in the discriminant space for each of a series of averaging periods, changes in the state of the managed system can be known by tracking how the positions of the plotted points in the discriminant space change over time. In particular, when N is 2 or 3, the scatter data is represented in a two-dimensional or three-dimensional space, so that the arrangement of each plot point in the scatter data can be visually confirmed, and it becomes easy to know the occurrence of an abnormality in the managed system. Even when N is 4 or more, the occurrence of an abnormality can be detected based on whether or not a plot point exists in a specific area in the discriminant space, and the accuracy of detecting the occurrence of an abnormality and identifying the location of a fault can be improved by using, for example, a machine learning technique.

[0013] Any data continuously obtained from the managed system can be used as the time series data. When the managed system is a water treatment system, data such as flow rate, temperature, pressure, pH, concentration of a specific component, conductivity (or resistivity), and turbidity can be used as the time series data. The time series data may be obtained directly from a sensor provided in the managed system, or may be obtained by performing calculations on data obtained from the sensor. For example, when an absorbance sensor is provided, the concentration of a specific component calculated from absorbance may be used as the time series data. When two pressure sensors are provided, the differential pressure, which is the difference between the measured values ​​from the two sensors, may be used as the time series data.

[0014] Any average value may be used as long as it can represent the data values ​​within the averaging period. For example, the average value may be the center of gravity of the data values ​​within the averaging period, i.e., the arithmetic average value, the geometric average value, or the harmonic average value. It may also be an average value calculated by taking the logarithm of each data value and calculating the logarithmic value.

[0015] An operation management device of one embodiment of the present invention is an operation management device used to manage the operation of a system to be managed, and has: average value calculation means for acquiring time series data for each of N types of quantities related to the operation and status of the system from the system, where N is an integer of 2 or greater, and calculating an average value of each of the time series data for each of a series of averaging periods defined in the system; and scatter data generation means for generating scatter data by plotting the average values ​​for each averaging period in an N-dimensional space with each of the N types of quantities as its coordinate axes. Effect of the Invention

[0016] According to the present invention, whatever the system to be managed may be, the operation of the system can be accurately and easily managed based on time-series data obtained from the system regarding the operation and status of the system. [Brief description of the drawings]

[0017] [Figure 1] 1 is a flowchart illustrating an operation management method according to an embodiment of the present invention. [Diagram 2] FIG. 1 is a diagram illustrating the principle of an operation management method. [Diagram 3] FIG. 2 is a diagram illustrating an example of a configuration of an operation management device. [Figure 4] FIG. 1 is a flow diagram showing an example of the configuration of a water treatment system. [Diagram 5] FIG. 1 illustrates an example of analysis based on time series data from a water treatment system. [Figure 6] FIG. 1 illustrates an example of analysis based on time series data from a water treatment system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Next, an embodiment of the present invention will be described with reference to the drawings. Fig. 1 is a flow chart for explaining an operation management method according to an embodiment of the present invention, and Fig. 2 explains the principle of the operation management method by taking as an example a case where a system to be managed is a water treatment system, and two types of time series data, namely, a water quality value (e.g., resistivity value) and a differential pressure, are obtained from the water treatment system.

[0019] The operation management method of this embodiment is for determining the replacement time of functional materials in a managed system, detecting the occurrence of an abnormality, and identifying the location of a fault, based on time series data obtained from the managed system. As shown in Fig. 1, in this operation management method, first, in step 101, time series data for each of a plurality of types of quantities related to the operation and status of the system are obtained from the system to be processed. The number of types of time series data to be obtained is N, where N is an integer equal to or greater than 2. In the example shown in Fig. 2, two types of time series data, water quality value and differential pressure, are obtained from the managed system, so N=2.

[0020] Next, in step 102, the average value of each time series data within the averaging period is calculated. As described above, the averaging period is also called a cycle. The averaging period needs to be a common period for a plurality of time series data, but the number of data points included in each time series data for each averaging period may be different for each time series data. The averaging period can be set appropriately, but it is preferable to set it according to the operation mode of the system to be managed. For example, if the system to be managed includes an ion exchange device that alternately executes a water passing process and a regeneration process, one water passing process of the ion exchange device can be set as one averaging period. Of course, one water passing process can be divided into multiple averaging periods. The lengths of the averaging periods may be different from each other. As a method for calculating the average value, any calculation method such as the arithmetic mean, the geometric mean, or the harmonic mean can be used. However, usually, the arithmetic mean value (i.e., the center of gravity value) within the averaging period for the data values ​​of the time series data is used as the average value. FIG. 2(a) shows time series data on the differential pressure and time series data on the water quality value during the first averaging period as the measured values ​​of the first cycle. In addition, in Figure 2(a), the arithmetic mean value (centroid value) calculated from each time series data is also indicated by the symbol "◎".

[0021] Next, in step 103, the average values ​​obtained in step 102 are plotted in a discriminant space whose coordinate axes represent the quantities of the types of time-series data, to obtain scatter data. Since the number of types of time-series data is N (where N ≥ 2), the discriminant space is an N-dimensional space. Figure 2(b) shows the discriminant space obtained from the two time-series data shown in Figure 2(a), where N = 2, so the discriminant space is a two-dimensional space. Since it is two-dimensional, the scatter data is also called a scatter diagram. In the case of Figure 2(b), the time-series data is of two types, water quality value and differential pressure, so one coordinate axis of the discriminant space (horizontal axis in the figure) represents the differential pressure, and the other coordinate axis (vertical axis in the figure) represents the water quality value. Then, as shown in [1] in Figure 2(b), points are plotted at positions represented by the average value of differential pressure and the average value of water quality in the discriminant space to obtain a scatter diagram.

[0022] When the scatter data (or scatter diagram) is obtained in step 103, the occurrence of an abnormality in the managed system is detected based on the scatter data in step 104. The detection of the occurrence of an abnormality here includes judging whether or not it is time to replace the functional material used in the managed system. For example, if the position of the plotted point in the scatter data is deviated from the position assumed in normal operation by a certain amount or more, it can be judged that an abnormality has occurred in the managed system. Also, depending on the direction in which the position of the plotted point in the discriminant space deviates from the position assumed in normal operation, it is possible to identify the location of the failure and the cause of the failure. If the purpose is only to obtain the scatter data, the process may proceed to step 105 without executing step 104. If the number of plotted points included in the scatter data is small, step 104 may not be executed.

[0023] In step 105, it is determined whether or not the same processing as that described in steps 101 to 104 is to be performed in the next averaging period. If the processing is not to be performed in the next averaging period, the processing of the operation management method is terminated here. On the other hand, if the processing is to be performed in the next averaging period, in step 106, each time series data in the next averaging period is acquired as in step 101, and in step 107, an average value in the averaging period is calculated for each time series data as in step 102. FIG. 2(c) shows each time series data in the second averaging period (i.e., the second cycle) and its corresponding average value (centroid value). After the average value is calculated, in step 108, the average value obtained in step 107 is plotted in the discriminant space as in step 103. In this case, since there is scatter data in which the average value calculated in the previous averaging period has already been plotted in the discriminant space, plot points are added to the scatter data, and the scatter data is updated. Fig. 2(d) shows a scatter plot obtained by adding plot points based on the average values ​​calculated from the measurements in the second cycle shown in Fig. 2(c) to the scatter plot obtained in Fig. 2(b). The added plot points are indicated by [2]. After step 108 is completed, the process from step 104 is repeated.

[0024] By repeating the process of steps 104 to 108, the number of plot points included in the scatter data in the discriminant space increases. That is, the average value of each of the time series data is calculated for each of a series of averaging periods, and the average value for each averaging period is plotted in the discriminant space, thereby generating scatter data including a large number of plot points. FIG. 2(e) shows a scatter diagram, i.e., scatter data, obtained by repeating the process of steps 104 to 108 in the case shown in FIG. 2. This scatter diagram has the differential pressure on the horizontal axis and the water quality value on the vertical axis, and the plot points corresponding to the normal state of the managed system are concentrated in the upper left of the scatter diagram. When the plot points are arranged away from the normal position, it can be considered that an abnormality has occurred in the managed system. As will be described later, it is not necessary to obtain in advance the position in the scatter data corresponding to the normal state of the system. If the plot points are arranged in a dispersed manner beyond a certain range, this in itself suggests the occurrence of an abnormality in the managed system.

[0025] As the managed system deteriorates or an abnormality occurs, the position of the plot point in the scatter diagram may gradually shift from the normal position. In the example shown in FIG. 2(e), the position of the plot point gradually shifts from the normal plot point toward the lower right in the figure. If this is called the tendency of event A, event A is a phenomenon in which the water quality value deteriorates even though the increase in differential pressure is small, and therefore it can be considered to correspond to, for example, a decrease in the reactivity of the ion exchange resin due to the progress of adsorption of impurity ions to the ion exchange resin, aging due to use in the ion exchange resin, detachment of ion exchange groups due to oxidizing substances, and poor regeneration. If the occurrence of event A is observed, it can be determined that the time to replace or regenerate the ion exchange resin is approaching. In addition, the position of the plot point may shift toward the right in the figure from the normal plot point. If we call this a trend of event B, then event B, since it is an increase in the water flow differential pressure despite a small fluctuation in the water quality value, can be thought of as corresponding to, for example, clogging of the ion exchange resin layer due to fracture of the ion exchange resin, clogging due to swelling and shrinkage of the ion exchange resin, clogging due to the inflow of turbidity from pretreatment equipment, etc. In other words, by detecting the deviation of the position of the plot point from the normal position, the occurrence of an abnormality in the system under management can be detected and its cause can be identified.

[0026] When the system to be managed includes an ion exchange device that repeatedly executes a water passing process and a regeneration process, the entire one water passing process between the regeneration processes can be set as the averaging period as described above. However, in the ion exchange device, the interval between regeneration processes is at least 24 hours, and at most 2 to 3 weeks, and if one water passing process is set as one averaging period, the averaging period will be about one day to several weeks. The operation management method of this embodiment detects the occurrence of an abnormality in the system to be managed based on the average value calculated for each averaging period and its transition, and the longer the averaging period, the longer the time required to determine whether or not an abnormality has occurred. Therefore, by dividing one water passing process into multiple sections and setting each divided section as an averaging period, the time required to determine whether or not an abnormality has occurred can be shortened. As a criterion or method for dividing into multiple sections, any one of time, water passing amount, and other related parameters (for example, time series data such as pressure and conductivity) values ​​can be used alone or in combination. For example, if the interval between regeneration steps is 24 hours, and this is divided into 5 so that one water flow step consists of 5 averaging periods, then when judging whether or not an abnormality has occurred based on the average value obtained in one averaging period, it will be possible to make the judgment in just over 4 hours at the earliest, and even when making the judgment from the trend in the average value over two or three averaging periods, it will be possible to make the judgment in about 10 hours.Even if the interval between regeneration steps is longer than 24 hours, by setting the length of each averaging period to 3 hours and repeating the averaging periods in one water flow step, it will be possible to judge whether or not an abnormality has occurred in as little as 3 hours.

[0027] Thus, according to the operation management method of the present embodiment, it is possible to automatically determine whether the system to be managed is normal or an abnormality has occurred, and to analyze the cause of the failure. In particular, by tracking the change in the position of the plot points in the scatter data over a long period of time, it is possible to automatically detect the occurrence of an abnormality, without having to prepare teacher data corresponding to normal times in advance. This makes it easier to perform predictive analysis using techniques such as machine learning. The method of the present embodiment does not understand individual time series data as a relationship between quantities or functions, but summarizes the data by deleting the time dimension in each time series data, and combines multiple time series data to make it possible to understand them graphically. This makes it possible to eliminate the effects of hunting, and makes it easy to identify not only the presence or absence of an abnormality but also the cause of the failure from the positions of the plot points in the discriminant space and their changes.

[0028] 3 shows an example of the configuration of an operation management device 10 that implements the above-mentioned operation management method. This operation management device 10 is used to manage the operation of a managed system 20. The managed system 20 is provided with a plurality of sensors 21. The sensors 21 acquire time series data on quantities related to the operation and state of the managed system 20. Different sensors 21 acquire different types of time series data, and input these time series data to the operation management device 10.

[0029] The operation management device 10 includes an average value calculation unit 11 that acquires multiple types of time series data from the managed system 20 and calculates the average value of each of the time series data for each of a series of averaging periods, and a scatter data generation unit 13 that plots the average value for each averaging period in a discriminant space to generate scatter data. The average value calculation unit 11 includes a calculation unit 12 provided for each input time series data, and the calculation unit 12 calculates the average value of the time series data for each averaging period for the corresponding time series data. The generated scatter data is output from the scatter data generation unit 13. An administrator who operates the managed system 20 can determine whether or not an abnormality has occurred in the managed system 20, including the arrival of the time to replace functional materials, by observing and analyzing the scatter data, such as a scatter diagram, output from the scatter data creation unit 13.

[0030] The operation management device 10 may further include a discrimination unit 14 that discriminates whether or not an abnormality has occurred in the managed system 20 from the arrangement of plot points in the scatter data in the discriminant space. The discrimination unit 14 outputs a discrimination result that discriminates whether or not an abnormality has occurred. The discrimination unit 14 can determine whether or not a plot point exists in a specific area in the discriminant space, discriminate whether or not an abnormality has occurred in the managed system 20, and identify the cause of the failure. The discrimination unit 14 can also detect a sign of an abnormality occurring in the managed system 20 from the tendency of how the positions of the plot points have changed over a series of many averaging periods in the discriminant space. Furthermore, by incorporating a machine learning engine that executes machine learning into the discrimination unit 14, the accuracy of detecting the occurrence of an abnormality and identifying the location of the failure can be improved. When N is 4 or more, that is, when the number of dimensions of the discriminant space is 4 or more, it is difficult for a person to visually observe and analyze the scatter data, but by using the discrimination unit 14, it is possible to easily detect the occurrence of an abnormality in the managed system 20 and identify the cause of the failure even when N is 4 or more.

[0031] Next, we will explain an example of applying the above-mentioned operation management method to an actual system. Here, we will explain the case where the system to be managed is a water treatment system that produces pure water from raw water such as city water or well water. Figure 4 shows an example of the configuration of a water treatment system.

[0032] A storage tank 51 is provided to store raw water, and the raw water in the storage tank 51 is pumped by a pump 52, and solids and the like are removed by a filter 53. The outlet water of the filter 53 is stored in a storage tank 54. The storage tank 54 is also supplied with recovered water recovered from equipment that uses pure water. The water in the storage tank 54 is pumped by a pump 55 and sent to an activated carbon tower 56 for activated carbon treatment. The outlet water of the activated carbon tower 56 is supplied to an ion exchange device 60. The ion exchange device 60 includes a first cation exchange resin tower 61 filled with a cation exchange resin and supplied with the outlet water of the activated carbon tower 56, a decarbonation tower 62 supplied with the outlet water of the first cation exchange resin tower 61, an anion exchange resin tower 63 filled with an anion exchange resin and supplied with the outlet water of the decarbonation tower 62, and a second cation exchange resin tower 64 filled with a cation exchange resin and supplied with the outlet water of the anion exchange resin tower 63. The outlet water of the second cation exchange resin tower 64 is the outlet water of the ion exchange device 60. As a result of the ion exchange treatment in the first cation exchange resin tower 61, the outlet water of the first cation exchange resin tower 61 contains hydrogen ions (H + ), making the water acidic, and the carbonate ions and bicarbonate ions in the outlet water are converted to free carbon dioxide. The decarbonation tower 62 is provided to remove this free carbon dioxide by blowing in air or by membrane deaeration. As a result of providing the decarbonation tower 62, water that does not contain carbon dioxide components is supplied to the anion exchange resin tower 63.

[0033] The ion exchange device 60 further includes a flowmeter (FI) 65 provided at its inlet for measuring the flow rate of water supplied to the ion exchange device 60, i.e., the flow rate of treated water in the ion exchange device 60, a conductivity meter (CI) 66 for measuring the conductivity of the inlet water of the first cation exchange resin tower 61, a pressure gauge (PI) 67 for measuring the pressure at the inlet of the anion exchange resin tower 63, a pressure gauge (PI) 68 for measuring the pressure at the outlet of the anion exchange resin tower 63, and a resistivity meter (RI) 69 for measuring the resistivity of the outlet water of the second cation exchange resin tower 64. The outlet water of the ion exchange device 60 is fed by a pump 71 and supplied to a reverse osmosis membrane device 72. Pure water is discharged from the reverse osmosis membrane device 72.

[0034] The flowmeter 65, the conductivity meter 66, the pressure gauges 67 and 68, and the resistivity meter 69 are all sensors that output time-series data related to the operation and state of the water treatment system. The difference between the pressure measurements made by the pressure gauges 67 and 68 indicates the differential pressure of the anion exchange resin tower 63, and this differential pressure of the anion exchange resin tower 63 can also be considered as time-series data related to the operation and state of the water treatment system. FIG. 5(a) shows the results of measuring the quality of the outlet water of the second cation exchange resin tower 64 by the resistivity meter 69 when the water treatment system was continuously operated for a long period of time as time-series data. Here, the time-series data for the period from March 3 to March 8 is shown. In the figure, the periods marked "Water Flow" and "Regeneration" indicate whether the ion exchange device 60 was performing the water flow process or the regeneration process, respectively. The water treatment system operated normally until around noon on March 7, but the water quality value was unstable after that due to a malfunction.

[0035] In the past, when time-series data such as that shown in Fig. 5(a) is obtained, the occurrence of an abnormality in a water treatment system was detected, for example, by comparing the data value with a threshold value. Fig. 5(b) shows an example of applying a threshold value to the time-series data shown in Fig. 5(a). In order to avoid false detection of hunting in the measured values, it is necessary to set the threshold value to a value that is far from the normal value, but in that case, there is a risk of overlooking an abnormality that brings about a small change in the time-series data. In addition, it is difficult to identify the cause of a failure by only comparing with a threshold value.

[0036] One conventional method of anomaly detection is to use the slope of change in time-series data. Figure 5(c) shows an example of applying anomaly detection based on the slope of change to the time-series data shown in Figure 5(a). In anomaly detection based on the slope of change, a threshold is set for the slope, and it is determined that an anomaly has occurred when the slope of change in the time-series data exceeds the threshold. However, this method often results in false positives, and it is difficult to identify the cause of a fault.

[0037] FIG. 6(a) shows an example in which the operation management method of this embodiment is applied to the time series data shown in FIG. 5(a). The operation management method of this embodiment requires at least two types of time series data. In the example shown here, in addition to the time series data of the water quality value of the outlet water of the second cation exchange resin tower 64 shown in FIG. 6(a), time series data of the treated water flow rate measured by a flow meter (not shown) is used as the time series data. FIG. 6(b) shows the obtained scatter data (a scatter diagram because it is two-dimensional here), with the horizontal axis representing the treated water flow rate and the vertical axis representing the water quality value. In addition, the period of one water passing step is regarded as one averaging period, i.e., cycle, and average values ​​are plotted for a series of averaging periods. In FIG. 6(a), #1 to #6 show the results of numbering each averaging period. In reality, a larger number of averaging periods was used.

[0038] The average value obtained from the averaging period #3, which is normal, is within the range of the plot points of normal values ​​located in the upper right part of FIG. 6(b). In contrast, in the averaging periods #5 and #6 corresponding to the occurrence of the failure, the treated water flow rate is significantly reduced, and the water quality value is also reduced. In particular, the reduction in the water quality value was remarkable in the averaging period #5. In this water treatment system, the raw water conductivity did not change significantly from the afternoon of March 5 to the afternoon of March 7, but it was confirmed that a large amount of organic carbon components flowed into the ion exchange device 60 during this period. Therefore, the reason why the treated water flow rate is reduced in the averaging periods #5 and #6 is thought to be because fouling occurred in the ion exchange device 60, causing the ion exchange reaction rate to decrease, and ions that should have been adsorbed by ion exchange were not adsorbed and leaked out. The reason why the water quality value is significantly reduced in the averaging period #5 is thought to be because the organic carbon components that flowed in contained ionic substances, and the ion exchange capacity of the ion exchange resin was used up. After averaging period #5, the ion exchange resin was regenerated, and in the subsequent averaging period #6, the water quality values ​​tended to improve.

[0039] In the above, the detection of occurrence of an abnormality in the water treatment system shown in FIG. 4 using the time series data of the treated water flow rate and the time series data of the water quality value of the outlet water of the second cation exchange resin tower 64 has been described. In this case, a conductivity meter or a resistivity meter is installed at the outlet of the anion exchange resin tower 63 to obtain the time series data of the water quality value of the outlet water of the anion exchange resin tower 63, and this can be used instead of the time series data of the water quality value of the outlet water of the second cation exchange resin tower 64 obtained by the resistivity meter 69. Furthermore, in this embodiment, the multiple time series data that can be used to detect occurrence of an abnormality in the water treatment system shown in FIG. 4 are not limited to these. For example, the time series data of the electrical conductivity of the inlet water of the ion exchange device 60 obtained by the conductivity meter 66, the time series data of the water flow differential pressure of the anion exchange resin tower 63 obtained as the difference between the measured values ​​of the pressure gauges 67 and 68, and the time series data of the resistivity of the outlet water of the second cation exchange resin tower 64 obtained by the resistivity meter 69 may be used to generate scattering data to detect occurrence of an abnormality in the water treatment system. In this case, since time series data of three types of quantities are used, the discriminant space is a three-dimensional interval, and the scatter data is also three-dimensional data. Here, since time series data on the water quality of the inlet water of the ion exchange device 60 is used, if an abnormality occurs in the water treatment system, it is possible to determine whether the water quality of the water supplied to the ion exchange device 60 is affecting the cause of the failure. When the number of types of time series data used is increased in this way, it becomes easier to associate multiple unit operations performed in the water treatment system and analyze the data. [Explanation of symbols]

[0040] 10 Operation management device 11 Average value calculation section 12 Arithmetic section 13 Scattering Data Creation Department 14 Judgment section 20 Managed Systems 21 Sensors 51,54 Storage tank 52,55,71 Pump 53 Filter 55 Activated carbon tower 60 Ion exchange device 61,64 Cation exchange resin tower 62 Decarboxylation tower 63 Anion exchange resin tower 65 Flow meter 66 Conductivity meter 67,68 Pressure gauge 69 Resistivity meter 72 Reverse osmosis membrane equipment

Claims

1. An operation management method for managing an operation of a managed system, comprising: acquiring time series data for each of N types of quantities related to the operation and state of the system from the system, where N is an integer equal to or greater than 2; Calculating an average value of each of the time series data for each of a series of averaging periods defined in the system; generating scatter data by plotting the average values ​​for each of the averaging periods in an N-dimensional space having each of the N types of quantities as a coordinate axis; Operational management methods.

2. The operation management method according to claim 1 , further comprising the step of detecting an occurrence of an abnormality in the system from an arrangement of plot points in the scatter data in the N-dimensional space.

3. The operation management method according to claim 2 , further comprising detecting the occurrence of an abnormality in the system based also on a change in the position of the plot points in the N-dimensional space for each averaging period over time.

4. The operation management method according to claim 1 , wherein the average value is expressed as a centroid value of the corresponding values ​​of the time series data within the averaging period.

5. The operation management method according to claim 1 , wherein the system is a water treatment system including at least an ion exchange device, and the time-series data includes data on water quality in the water treatment system.

6. The operation management method according to claim 5 , wherein each water passing step in the ion exchange apparatus is divided into a plurality of periods, and each of the divided periods is set as the averaging period.

7. An operation management device used to manage the operation of a managed system, an average value calculation means for acquiring time series data for each of N types of quantities related to the operation and state of the system from the system, where N is an integer of 2 or more, and calculating an average value of each of the time series data for each of a series of averaging periods defined in the system; a scatter data generating means for generating scatter data by plotting the average values ​​for each averaging period in an N-dimensional space having each of the N types of quantities as a coordinate axis; An operation management device having the above configuration.

8. The operation management device according to claim 7 , further comprising a determination means for determining whether or not an abnormality has occurred in the system from an arrangement of plot points in the scatter data in the N-dimensional space.

9. 9. The operation management device according to claim 8, wherein the determination means determines whether or not an abnormality has occurred in the system based also on a change in position of the plot point in the N-dimensional space for each averaging period over time.

10. The operation management device according to claim 7 , wherein the average value calculation means calculates, as the average value, a center of gravity value of the corresponding values ​​of the time series data within the averaging period.

Images