DATA PROCESSING APPARATUS AND DATA PROCESSING METHOD

Abstract

Provided is a data processing device comprising: a division unit that divides a target period into a plurality of operating periods according to an operating condition; an identification unit that identifies a standard condition, which is a standard operating condition for each operating period; a calculation unit that divides each operating period into a plurality of constant performance periods in each of which the performance of a target device is considered to be constant, narrows down time series data for each constant performance period on the basis of the standard condition, and calculates a certain representative value on the basis of the time series data extracted through the narrowing down; and a correction unit that sets an overlapping period containing a boundary between two adjacent operating periods, narrows down, on the basis of each standard condition identified for each of the two operating periods, time series data in the overlapping period for each standard condition, and corrects, on the basis of a result of calculating each representative value on the basis of each piece of time series data extracted through the narrowing down, the representative value of at least one of the two operating periods.

Description

[Technical field]

[0001] The present disclosure relates to a data processing device and a data processing method. This application claims priority based on Japanese Patent Application No. 2022-065664 filed on April 12, 2022, the contents of which are incorporated herein by reference. [Background technology]

[0002] Patent Document 1 describes the following plant performance evaluation system. That is, the plant performance evaluation system described in Patent Document 1 uses the sensor measurements to examine the relationships between sensors, and creates a plant model from these relationships. Then, based on the model, predicted measurements are calculated from the measurements of each sensor at the time the model was created and the measurements received from each sensor over a predetermined period of time. Furthermore, the calculated measurements are compared with the measurements received from each sensor over a predetermined period of time, and the comparison result is used as the plant evaluation result. In the system described in Patent Document 1, it is said that a deterioration trend is detected by examining changes in the strength of the relationships between sensors, rather than comparing past and present values ​​of individual sensors attached to the equipment.

[0003] In addition, in the plant performance evaluation system described in Patent Document 1, the sensor measurement values ​​are subjected to processes such as discretizing and thinning the measurement values, removing outliers from the discretized measurement values, and removing seasonal return components from the discretized measurement values. It is said that by correcting the measurement values ​​through these processes, a model corresponding to the original state of the plant is created. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2021-111207 Summary of the Invention [Problem to be solved by the invention]

[0005] In the performance evaluation of various devices in a plant, etc., a value or index representing the performance to be evaluated may be affected by a change in the operating conditions of the device. For example, a value such as efficiency representing the performance of the device may be affected by a change in the operating conditions of the device, such as pressure, temperature, etc. In the evaluation of such values ​​or indexes, there is a problem that it may be difficult to grasp the deterioration trend of the device when the operating conditions change.

[0006] The present disclosure has been made in consideration of the above circumstances, and aims to provide a data processing device and a data processing method that are capable of appropriately evaluating the performance of a target device even when operating conditions change. [Means for solving the problem]

[0007] In order to solve the above problem, a data processing device according to the present disclosure includes an acquisition unit that acquires multiple types of time series data over a target period related to operation of a target device, a division unit that divides the target period into multiple operating periods according to operating conditions, an identification unit that identifies standard conditions that are standard operating conditions for each operating period, a calculation unit that divides the operating period into multiple constant performance periods during which performance of the target device can be considered constant, and for each constant performance period, narrows down the time series data based on the standard conditions and calculates a predetermined representative value based on the time series data extracted by the narrowing down, and a correction unit that sets an overlapping period that includes a boundary between two adjacent operating periods, narrows down the time series data within the overlapping period for each standard condition based on the standard conditions identified for the two operating periods, and corrects the representative value in at least one of the two operating periods based on a result of calculating each representative value based on each of the time series data extracted by the narrowing down.

[0008] The data processing method according to the present disclosure includes the steps of acquiring multiple types of time series data over a target period related to operation of a target apparatus, dividing the target period into multiple operating periods according to operating conditions, identifying standard conditions that are standard operating conditions for each of the operating periods, dividing the operating period into multiple constant performance periods during which performance of the target apparatus can be considered constant, narrowing down the time series data based on the standard conditions for each of the constant performance periods, and calculating a predetermined representative value based on the time series data extracted by narrowing down, and setting an overlapping period that includes a boundary between two adjacent operating periods, narrowing down the time series data within the overlapping period for each of the standard conditions based on the standard conditions identified for the two operating periods, and correcting the representative value in at least one of the two operating periods based on a result of calculating each of the representative values ​​based on each of the time series data extracted by narrowing down. Effect of the Invention

[0009] According to the data processing device and data processing method of the present disclosure, the performance of a target device can be appropriately evaluated even when the operating conditions change. [Brief description of the drawings]

[0010] [Figure 1] 1 is a block diagram showing an example configuration of a data processing device according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Diagram 3] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Figure 4] 10 is a flowchart for explaining an example of the operation of a data processing device according to an embodiment of the present disclosure. [Diagram 5] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Figure 6] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Figure 7] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Figure 8] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Figure 9] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Figure 10] FIG. 2 is a schematic diagram for explaining an example of the operation of the data processing device according to the embodiment of the present disclosure. [Figure 11] FIG. 11 is a schematic diagram for explaining a data processing device according to a second embodiment of the present disclosure. [Figure 12] FIG. 11 is a schematic diagram for explaining a data processing device according to a second embodiment of the present disclosure. [Figure 13] FIG. 13 is a schematic diagram for explaining a data processing device according to a third embodiment of the present disclosure. [Figure 14] FIG. 1 is a schematic block diagram illustrating a configuration of a computer according to at least one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] First Embodiment (Configuration of Data Processing Device) A data processing device and a data processing method according to an embodiment of the present disclosure will be described below with reference to Figs. 1 to 10. Fig. 1 is a block diagram showing a configuration example of a data processing device according to an embodiment of the present disclosure. Figs. 2 and 3 are schematic diagrams for explaining an operation example of a data processing device according to an embodiment of the present disclosure. Fig. 4 is a flowchart for explaining an operation example of a data processing device according to an embodiment of the present disclosure. Figs. 5 to 10 are schematic diagrams for explaining an operation example of a data processing device according to an embodiment of the present disclosure. Note that the same or corresponding configurations in each drawing are designated by the same reference numerals and explanations thereof will be omitted as appropriate.

[0012] The data processing device 1 shown in Fig. 1 can be configured, for example, using a computer such as a personal computer and its peripheral devices, etc. The data processing device 1 shown in Fig. 1 includes an acquisition unit 11, a division unit 12, an identification unit 13, a calculation unit 14, and a correction unit 15 as a functional configuration configured by a combination of hardware such as a computer and its peripheral devices, and software such as a program executed by the computer.

[0013] In this embodiment (and the second and third embodiments described below), the target device 2 to be evaluated includes, as an example, a steam turbine power generation system 20, or a steam turbine 21 in the steam turbine power generation system 20. However, the target device 2 is not limited to this configuration.

[0014] In FIG. 1, the steam turbine power generation system 20 includes, as a schematic configuration, a steam turbine 21, a generator 22, a condenser 23, a boiler 24, and a governor valve 25. Steam generated in the boiler 24 flows into the steam turbine 21 from a steam turbine inlet 21i via the governor valve 25. The steam turbine 21 rotates an internal impeller (not shown) using the energy of the steam to drive the generator 22. The steam turbine 21 discharges steam from a steam turbine outlet 21o, and the condenser 23 returns the steam to water, which is returned to the boiler 24 via a feedwater pump (not shown). In this embodiment, the steam temperature at the steam turbine inlet 21i is referred to as the inlet temperature, and the steam pressure is referred to as the inlet pressure. The steam temperature at the steam turbine outlet 21o is referred to as the outlet temperature, and the steam pressure is referred to as the outlet pressure. The steam turbine power generation system 20 transmits multiple types of time-series data 3 indicating the detection results of various sensors, the operating states of various actuators, the occurrence status of predetermined events, etc. to, for example, a server (not shown) and accumulates the data. The data processing device 1 acquires the accumulated multiple types of time-series data 3 from the server or the like, or receives the data directly from the steam turbine power generation system 20.

[0015] FIG. 2 shows an example of multiple types of time series data 3. The horizontal axis indicates the operating time, and the vertical axis indicates the internal efficiency, the condenser vacuum, the inlet pressure, the inlet temperature, the outlet pressure, the governor opening, and the outlet temperature. FIG. 2 shows values ​​measured at a predetermined cycle for more than 10 years and values ​​calculated based on the measured values. In this embodiment, the evaluation period is divided into multiple operating periods, standard conditions are specified for each operating period, and the time series data is processed using different standard conditions for each operating period.

[0016] In this embodiment, the operating period is a period in which the operating conditions are similar. The period in which the operating conditions are similar is, for example, a period in which the average values ​​and fluctuation ranges of the generator output, inlet temperature, inlet pressure, outlet pressure, condenser vacuum, governor opening, and the like are similar. In addition, the standard conditions refer to standard or average thermal conditions in each operating period. In this embodiment, they are mainly defined by the temperature and pressure at the turbine inlet and outlet and the condenser vacuum. In the example shown in FIG. 2, the target period is divided into an operating period A, an operating period B, and an operating period C. In addition, standard conditions A, B, and C are specified for the operating periods A, B, and C. In the example shown in FIG. 2, the temperature of the boiler 24 changes in the operating periods A, B, and C.

[0017] In this embodiment, the internal efficiency of the steam turbine 21 in the target device 2 is used as an example of the value to be evaluated. A method for calculating the internal efficiency will be briefly described with reference to FIG. 3. FIG. 3 is a steam diagram (or an hs diagram), which is a diagram illustrating a steam table with the horizontal axis representing entropy and the vertical axis representing enthalpy. The turbine internal efficiency is the ratio of thermal energy converted into work inside the turbine to thermal energy (adiabatic heat drop) that can be used until the steam at the turbine inlet reaches the pressure at the outlet. Specifically, the enthalpy and entropy at the turbine inlet and outlet are obtained using a steam table from the temperature and pressure at the turbine inlet and outlet, and are calculated using the formula shown in FIG. 2. Note that if the thermal conditions are different, the calculated efficiency will be different even for the same turbine. The value of the internal efficiency can be calculated based on the values ​​of the inlet temperature, inlet pressure, outlet temperature, and outlet pressure of the steam turbine 21.

[0018] Returning to FIG. 1, the acquisition unit 11 acquires multiple types of time-series data 3 relating to the operation of the target device 2 over a target period.

[0019] The division unit 12 divides the target period into a plurality of operating periods according to the operating conditions. The operating periods can be divided, for example, by displaying time-series data as shown in Fig. 2 on a predetermined display unit and setting the division positions according to an input operation by an operator on a predetermined input unit. Alternatively, for example, the division positions may be set based on a notification indicating a change in the operating conditions from the steam turbine power generation system 20.

[0020] The specifying unit 13 specifies standard conditions, which are standard operating conditions, for each operating period. For example, the specifying unit 13 calculates average values ​​of the inlet temperature, the inlet pressure, the outlet temperature, and the outlet pressure for each operating period, and defines the standard conditions by the calculated average values.

[0021] The calculation unit 14 divides each operating period into a plurality of constant performance periods during which the performance of the target device 2 can be considered constant, and for each constant performance period, the time series data is narrowed down based on standard conditions, and a predetermined representative value is calculated based on the time series data extracted by narrowing down. The constant performance period is, for example, a period during which the performance degradation of the target device 2 can be ignored on the assumption that the performance gradually deteriorates. For example, when the product life is several decades, and the operating period is sufficiently shorter than the product life, the constant performance period can be a period of about one week to several weeks, or a period of about one to two months. However, these periods are only examples, and the length of the period may be shorter or longer than these examples. In this embodiment, the constant performance period is a period during which the true turbine efficiency can be considered constant. It is assumed that the efficiency value will be the same if the turbine operating conditions are the same during that period (if the turbine structure and thermal conditions are the same, the efficiency should be the same). In this embodiment, the constant performance period means a period during which the efficiency is constant (a constant efficiency period).

[0022] Narrowing down the time series data based on the standard condition means extracting data near the standard condition and not extracting data far from the standard condition, thereby restricting the range of the data values ​​within a certain range. In addition, calculating a predetermined representative value based on the time series data extracted by narrowing down means, in this embodiment, calculating multiple internal efficiency values ​​using multiple combinations (data with the same time stamp) of the inlet temperature, inlet pressure, and outlet pressure narrowed down to near the standard condition and the outlet temperature (data with the same time stamp) corresponding to the combination, and further calculating the average value of the multiple internal efficiencies as the predetermined representative value. In this case, the outlet temperature is not subject to narrowing down based on the standard condition. That is, in this case, the calculation unit 14 excludes at least one type of time series data among the multiple types of time series data used as a parameter when calculating the representative value from the narrowing down based on the standard condition. In addition, hereinafter, the representative value is also called a representative efficiency value.

[0023] FIG. 7 shows an example of the relationship between the operation period and the constant performance period. The horizontal axis represents the operation time, and an example of the change in internal efficiency is shown. A representative value is calculated for each constant performance period. Note that the length of the constant performance periods may or may not be the same.

[0024] Here, with reference to FIG. 9, a specific example of narrowing down the time series data based on the standard condition will be described. In this embodiment, the standard condition includes values ​​representing three of the inlet temperature, inlet pressure, outlet temperature, and outlet pressure of the steam turbine, which are calculation parameters of the internal efficiency. In the example shown in FIG. 9, the standard condition includes the inlet temperature, inlet pressure, and outlet pressure of the steam turbine, which are calculation parameters of the internal efficiency. In the example shown in FIG. 9, the calculation unit 14 assigns three calculation parameters corresponding to the inlet temperature Tin, the inlet pressure Pin, and the outlet pressure Pout included in the standard condition to each side, and arranges all the time series data D1 within the performance fixed period in a cubic space QB1 set for each performance fixed period. In addition, the calculation unit 14 calculates a representative efficiency value based on the time series data arranged in a predetermined cube QB2 near the standard condition.

[0025] In this embodiment, the narrowing down technique shown in Fig. 9 is called the large and small cube method. In the large and small cube method, narrowing down in the time direction is performed using a large cube (cubic space QB1). Each cube corresponds to the time series data D1 for an individual performance period. The three axes of the cube are, for example, the inlet temperature and pressure and the outlet pressure. Furthermore, in a small cube (cube QB2), thermal conditions are narrowed down for the data for each performance period. In each small cube, the efficiency is set to a single value by averaging or the like.

[0026] According to this configuration, by introducing the concept of a constant performance period, the data can be narrowed down in both the time direction and thermal conditions (action), which further reduces the variation in efficiency values ​​(effect). In addition, the processing is very simple, making it easy to check conditions and convert values, and allowing uniform processing over the entire period.

[0027] Next, the correction unit 15 shown in FIG. 1 sets a trend overlapping section (one example of an overlapping section) including the boundary between two adjacent operating periods, narrows down the time series data in the trend overlapping section for each standard condition based on each standard condition specified for the two operating periods, and corrects the representative value in at least one of the two operating periods based on the result of calculating each representative value based on each time series data extracted by narrowing down. As shown in FIG. 2, the trend overlapping section is a certain period including the boundary between the two operating periods. For example, the correction unit 15 calculates a representative value (representative value of the trend overlapping section) based on time series data extracted by narrowing down based on standard condition A from the time series data in the trend overlapping section. Also, the correction unit 15 calculates a representative value (representative value of the trend overlapping section) based on time series data extracted by narrowing down based on standard condition B from the time series data in the same trend overlapping section. Then, as shown in Fig. 8, for example, the correction unit 15 corrects the representative value in at least one of the two operating periods A and B based on the difference between a representative value based on standard condition A (also referred to as a reference efficiency value) and a representative value based on standard condition B (also referred to as a reference efficiency value). This difference between the reference efficiency values ​​is also referred to as an efficiency conversion value. Note that the efficiency conversion value is also calculated in a similar manner for operating period C, and the representative value is corrected.

[0028] FIG. 10 shows an example of calculating an efficiency conversion value for a trend overlap period overlapping operation period B and operation period C by a method similar to the large and small cube method described with reference to FIG. 9. In the example shown in FIG. 10, data for the trend overlap period is arranged in a large cube (cubic space QB1). Then, a small cube (cube QB2B) in the vicinity of standard condition B for operation period B and a small cube (cube QB2C) in the vicinity of standard condition C for operation period C are set in the large cube (cubic space QB1). An internal efficiency ηB is calculated based on the data in the small cube (cube QB2B), and an internal efficiency ηC is calculated based on the data in the small cube (cube QB2C). The difference between the internal efficiency ηB and the internal efficiency ηC corresponds to the conversion amount under different standard conditions, and the standard conditions can be unified by shifting the entire trend in parallel.

[0029] (Example of operation of data processing device) Next, an example of the operation of the data processing device 1 shown in FIG. 1 will be described with reference to FIG. 4 to FIG. 11. The process shown in FIG. 4 is started, for example, according to a predetermined input operation by an operator. When the process shown in FIG. 4 is started, for example, the acquisition unit 11 extracts steady state data (generator output, inlet temperature and pressure, outlet pressure, etc.) from the acquired multiple types of time series data 3 (step S11). In this embodiment, the steady state data is data measured in a state where the operating state can be considered to be constant to a certain extent and its thermal conditions (temperature, pressure, flow rate, output, etc.). It usually refers to data measured in an operating state near the rated output. Next, for example, the acquisition unit 11 performs simple narrowing down of similar data (condenser vacuum, governor opening, etc.) (step S12). In step S12, one similar data is kept and the other data is excluded. Next, for example, the acquisition unit 11 removes outliers (step S13). In step S13, for example, data other than rated output operation is excluded.

[0030] Fig. 5 shows an example of data before processing, taking the time series data of internal efficiency as an example. Fig. 6 shows an example of data after processing of steps S11 to S13, taking the time series data of internal efficiency as an example. Note that the scale of internal efficiency is different between Fig. 5 and Fig. 6.

[0031] Next, the division unit 12 and the determination unit 13 execute time-direction division (1) (step S14). In time-direction division (1), the division unit 12 divides the period based on the similarity of the operating conditions. The determination unit 13 also determines the standard conditions for each period.

[0032] Next, the calculation unit 14 executes time direction division and narrowing down (2) (step S15). In the time direction division and narrowing down (2), the calculation unit 14 performs division in a constant performance period.

[0033] Next, the calculation unit 14 executes data extraction and calculation of a representative efficiency value (step S16). The calculation unit 14 extracts data near the standard conditions for each period of the constant performance period, and calculates a representative efficiency value using the data near the standard conditions (for each constant performance period).

[0034] FIG. 7 shows an example of data processing in steps S14 to S16.

[0035] Next, the correction unit 15 calculates an efficiency conversion value (step S17). The correction unit 15 calculates the difference between the reference efficiency values ​​for the periods under different standard conditions.

[0036] Next, the correction unit 15 generates a trend under the uniform conditions (step S18). The correction unit 15 calculates the efficiency under the standard conditions that are uniform over the entire period by using the difference between the reference efficiency values.

[0037] FIG. 8 shows an example of data processing in steps S17 to S18.

[0038] (supplementary explanation) In the first embodiment, long-term operating data is divided into a number of consecutive periods (operating periods) based on the similarity of operating conditions, and standard operating conditions (reference conditions) (e.g., average values ​​of temperature and pressure at the turbine inlet and outlet) are defined for each of the divided periods, and the internal efficiency is evaluated based on the standard conditions.

[0039] In addition, a period during which the true turbine efficiency can be considered constant (constant performance period) is defined, and it is assumed that if the turbine operating conditions are kept the same during that period, the efficiency value will also be the same (if the turbine structure and thermal conditions are the same, the efficiency should be the same). Then, for the data from the multiple divided constant performance periods, the efficiency value for each period is defined (calculated) using data close to the standard conditions.

[0040] For periods under different standard conditions, adjacent data (trend overlapping sections) are used to calculate efficiency values ​​for the two standard conditions. Furthermore, based on the concept of a constant performance period, one of the efficiency trend graphs is translated using the amount of shift in the efficiency trend for periods corresponding to different standard conditions (the difference between the two efficiency values ​​calculated above). By carrying out the same process for the remaining periods under standard conditions, a trend graph of efficiency changes is generated based on the same criteria (standard conditions) throughout the entire period.

[0041] (Actions and Effects of the First Embodiment) (1) By dividing the evaluation period into multiple periods based on the similarity of operating conditions and evaluating the internal efficiency based on the standard conditions specific to each period (effect), the target data is not lost even if the range of thermal conditions used in the evaluation is significantly narrowed down to values ​​close to the standard conditions for each period (effect). In other words, data loss can be prevented while data homogenization can be achieved.

[0042] (2) By introducing the concept of a constant performance period and narrowing down the data in terms of both time and thermal conditions (action), the variation in efficiency values ​​can be further reduced (effect).

[0043] (3) By applying the concept of a constant performance period to the trend overlap section and calculating the conversion amount of the efficiency value for adjacent different standard conditions (effect), a trend graph of efficiency change can be generated and evaluated using the same standard (standard conditions) throughout the entire period (effect).

[0044] As described above, according to this embodiment, the performance of the target device 2 can be appropriately evaluated even when the operating conditions change.

[0045] <Second embodiment> The second embodiment is another example (called multiple regression plane method in this embodiment) of the specific example (large and small cube method) of narrowing down time series data based on standard conditions described in the first embodiment with reference to Fig. 9. In the multiple regression plane method of this embodiment, the calculation unit 14 divides the time series data D1 contained in a cube (cubic space QB1) collected over a fixed performance period and organized by thermal conditions into a number of groups (clusters) G1 to G5 according to the efficiency values ​​(Fig. 11). Note that since only one point of data belongs to group G5, no plane is created.

[0046] Next, the calculation unit 14 calculates linear approximation planes (multiple regression surfaces) AP1 to AP4 for each of the clustered data (FIG. 12). The calculation unit 14 also generates an intermediate (interpolated) regression surface between two adjacent multiple regression surfaces as necessary. The calculation unit 14 also generates the intermediate (interpolated) regression surface, for example, as follows: (1) the normal vector is the average vector of the normal vectors of the adjacent multiple regression surfaces; and (2) the reference point (point on the surface) is the midpoint between the centers of gravity (two points) of the data points used to generate the multiple regression surface. If the point under the standard conditions is not on the multiple regression surface, it is complemented based on the distance from the two adjacent multiple regression surfaces. Since the efficiency conversion is expressed as a functional relationship, extrapolation is possible (however, extrapolation over a wide range reduces accuracy).

[0047] 11 and 12 are schematic diagrams for explaining a data processing device according to the second embodiment of the present disclosure.

[0048] In this embodiment, the standard conditions include values ​​representing three of the inlet temperature, inlet pressure, outlet temperature, and outlet pressure of the steam turbine, which are calculation parameters for the internal efficiency. The calculation unit 14 also assigns the three calculation parameters included in the standard conditions to each side, arranges time-series data in a cubic space QB1 set for each fixed performance period, and divides the space into a plurality of groups G1 to G5 according to the internal efficiency, calculates linear approximation planes AP1 to AP4 for each group, and calculates a representative value based on the positional relationship between the calculation results of the linear approximation planes and the points in the cubic space corresponding to the standard conditions.

[0049] (Actions and Effects of the Second Embodiment) By introducing the concept of a constant performance period, the data can be narrowed down in both the time direction and thermal conditions (action), and the variation in efficiency values ​​can be further reduced (effect). In addition, since the efficiency conversion is expressed as a functional relationship, extrapolation is possible (however, extrapolation over a wide range reduces accuracy).

[0050] <Third embodiment> The third embodiment is another example (called a multiple approximation straight line method in this embodiment) of the specific example (large and small cube method) of narrowing down time series data based on the standard conditions described in the first embodiment with reference to Fig. 9. Fig. 13 is a schematic diagram for explaining a data processing device according to the third embodiment of the present disclosure.

[0051] In this embodiment, in the multiple approximation line method, the calculation unit 14 generates a two-dimensional graph (plane P1) of turbine inlet temperature and pressure for each data point group divided into multiple parts over a fixed performance period, and divides the graph into several small areas SA in a grid shape, as shown in Fig. 13. The calculation unit 14 also displays the data points in each grid as a graph of turbine outlet pressure and efficiency, finds each approximation line AL, and calculates an efficiency value for any standard condition using this large number of approximation lines.

[0052] Point C1 is a representative value of the pair of temperature and pressure determined for each small area SA. The value of point C1 can be calculated by averaging the sampling points in the small area SA or by simply averaging the coordinates of the small area SA (center point position).

[0053] The method for calculating the efficiency value for any standard condition is as follows: (1) identify a grid from the temperature and pressure values ​​corresponding to the given standard condition, and (2) calculate the efficiency value from the outlet pressure condition using an approximation line of the identified grid.

[0054] As described above, according to this embodiment, the standard conditions include values ​​representing three of the inlet temperature, inlet pressure, outlet temperature, and outlet pressure of the steam turbine, which are calculation parameters for the internal efficiency. The calculation unit 14 also assigns two of the three calculation parameters corresponding to those included in the standard conditions to each axis, arranges time-series data on a plane P1 set for each fixed performance period, divides the plane P1, and sets an approximation line AL of a representative value based on the remaining one of the three calculation parameters for each of a plurality of small areas SA specified by the standard conditions, and calculates a representative value based on the standard conditions and the approximation line.

[0055] (Actions and Effects of the Third Embodiment) By introducing the concept of a constant performance period, the data can be narrowed down in both the time direction and thermal conditions (action), and the variation in efficiency values ​​can be further reduced (effect). In addition, since the efficiency conversion is expressed as a functional relationship, extrapolation is possible (however, extrapolation over a wide range reduces accuracy).

[0056] (Action and effect) In the data processing device and data processing method configured as above, the target period is divided into a plurality of operating periods according to the operating conditions. In addition, standard conditions, which are standard operating conditions, are specified for each operating period. In addition, each operating period is divided into a plurality of fixed performance periods in which the performance of the target device is considered to be constant, and for each fixed performance period, time series data is narrowed down based on the standard conditions, and a predetermined representative value is calculated based on the time series data extracted by narrowing down. In addition, an overlapping period including a boundary between two adjacent operating periods is set, and time series data within the overlapping period is narrowed down for each standard condition based on each standard condition specified for the two operating periods, and the representative value in at least one of the two operating periods is corrected based on the result of calculating each representative value based on each time series data extracted by narrowing down. Therefore, according to the data processing device and data processing method of the embodiment, the performance of the target device can be appropriately evaluated even when the operating conditions change.

[0057] (Other embodiments) Although the embodiments of the present disclosure have been described in detail above with reference to the drawings, the specific configuration is not limited to this embodiment, and design changes and the like that do not depart from the gist of the present disclosure are also included.

[0058] Computer Configuration FIG. 14 is a schematic block diagram illustrating a configuration of a computer according to at least one embodiment. The computer 90 comprises a processor 91, a main memory 92, a storage 93, and an interface 94. The above-mentioned data processing device 1 is implemented in a computer 90. The operations of the above-mentioned processing units are stored in the form of a program in a storage 93. A processor 91 reads the program from the storage 93, loads it in a main memory 92, and executes the above-mentioned processes in accordance with the program. The processor 91 also secures storage areas in the main memory 92 corresponding to the above-mentioned storage units in accordance with the program.

[0059] The program may be for realizing a part of the functions to be performed by the computer 90. For example, the program may be for realizing the functions by combining with other programs already stored in the storage or by combining with other programs implemented in other devices. In another embodiment, the computer may include a custom LSI (Large Scale Integrated Circuit) such as a PLD (Programmable Logic Device) in addition to or instead of the above configuration. Examples of PLDs include PAL (Programmable Array Logic), GAL (Generic Array Logic), CPLD (Complex Programmable Logic Device), and FPGA (Field Programmable Gate Array). In this case, some or all of the functions to be realized by the processor may be realized by the integrated circuit.

[0060] Examples of the storage 93 include a hard disk drive (HDD), a solid state drive (SSD), a magnetic disk, a magneto-optical disk, a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), and a semiconductor memory. The storage 93 may be an internal medium directly connected to the bus of the computer 90, or an external medium connected to the computer 90 via an interface 94 or a communication line. In addition, when the program is distributed to the computer 90 via a communication line, the computer 90 that receives the program may load the program into the main memory 92 and execute the above-mentioned process. In at least one embodiment, the storage 93 is a non-transitory tangible storage medium.

[0061] <Additional Notes> The data processing device 1 described in each embodiment can be understood, for example, as follows.

[0062] (1) A data processing device 1 according to a first embodiment includes an acquisition unit 11 that acquires a plurality of types of time series data 3 over a target period related to the operation of a target device 2, a division unit 12 that divides the target period into a plurality of operating periods according to operating conditions, an identification unit 13 that identifies standard conditions that are standard operating conditions for each of the operating periods, a calculation unit 14 that divides each of the operating periods into a plurality of fixed performance periods in which the performance of the target device can be considered constant, narrows down the time series data based on the standard conditions for each of the fixed performance periods, and calculates a predetermined representative value based on the time series data extracted by narrowing down, and a correction unit 15 that sets an overlapping period (trend overlapping section) including a boundary between two adjacent operating periods, narrows down the time series data within the overlapping period for each of the standard conditions based on each of the standard conditions identified for the two operating periods, and corrects the representative value in at least one of the two operating periods based on the result of calculating each of the representative values ​​based on each of the time series data extracted by narrowing down. According to this embodiment and each of the following embodiments, the performance of the target device can be appropriately evaluated even when the operating conditions change.

[0063] (2) A data processing device 1 according to a second aspect is the data processing device 1 of (1), in which the calculation unit excludes at least one type of time series data among the multiple types of time series data used as a parameter when calculating the representative value from the narrowing down based on the standard conditions.

[0064] (3) A data processing device 1 according to a third aspect is the data processing device 1 according to (1) or (2), in which the representative value is a value corresponding to the efficiency of the target device.

[0065] (4) A data processing device 1 according to a fourth aspect is the data processing device 1 of (1) to (3), in which the target device is a steam turbine 21, and the representative value is an internal efficiency of the steam turbine.

[0066] (5) A data processing device 1 according to a fifth aspect is the data processing device 1 of (1) to (4), wherein the standard conditions include values ​​representing three of the inlet temperature, inlet pressure, outlet temperature, or outlet pressure of the steam turbine, which are calculation parameters of the internal efficiency, and the calculation unit assigns the three calculation parameters corresponding to those included in the standard conditions to each side, arranges the time series data in a cubic space set for each of the constant performance periods, and calculates the representative value based on the time series data arranged within a specified cube near the standard conditions.

[0067] (6) A data processing device 1 according to a sixth aspect is the data processing device 1 of (1) to (4), wherein the standard conditions include values ​​representing three of the inlet temperature, inlet pressure, outlet temperature, or outlet pressure of the steam turbine, which are calculation parameters of the internal efficiency, and the calculation unit assigns the three calculation parameters corresponding to those included in the standard conditions to each side, arranges the time series data in a cubic space set for each of the constant performance periods, and divides the time series data into a plurality of groups according to the internal efficiency, calculates a linear approximation plane for each of the groups, and calculates the representative value based on the positional relationship between the calculation result of the linear approximation plane and a point in the cubic space corresponding to the standard conditions.

[0068] (7) A data processing device 1 according to a seventh aspect is the data processing device 1 of (1) to (4), wherein the standard conditions include values ​​representing three of the inlet temperature, inlet pressure, outlet temperature, or outlet pressure of the steam turbine, which are calculation parameters of the internal efficiency, and the calculation unit assigns two of the three calculation parameters corresponding to those included in the standard conditions to each axis, arranges the time series data on a plane set for each of the constant performance periods, divides the plane, and sets an approximation line of the representative value based on the remaining one of the three calculation parameters for each of a plurality of small regions specified by the standard conditions, and calculates the representative value based on the standard conditions and the approximation line. [Industrial Applicability]

[0069] According to the data processing device and data processing method of the present disclosure, the performance of a target device can be appropriately evaluated even when the operating conditions change. [Explanation of symbols]

[0070] 1...Data processing device 2. Target device 21...Steam turbine 11…Acquisition part 12...Divided part 13…Specific part 14...Calculation section 15...Compensation section

Claims

1. An acquisition unit that acquires multiple types of time series data over a target period related to the operation of the target device; A division unit that divides the target period into a plurality of operating periods according to operating conditions; A specification unit that specifies standard conditions that are standard operating conditions for each operating period; a calculation unit that divides each of the operating periods into a plurality of constant performance periods during which the performance of the target device can be considered constant, narrows down the time series data for each of the constant performance periods based on the standard conditions, and calculates a predetermined representative value based on the time series data extracted by narrowing down the time series data; a correction unit that sets an overlapping period including a boundary between two adjacent operating periods, narrows down the time series data within the overlapping period for each standard condition based on each of the standard conditions specified for the two operating periods, and corrects the representative value in at least one of the two operating periods based on a result of calculating each of the representative values ​​based on each of the time series data extracted by narrowing down; A data processing device comprising:

2. The calculation unit excludes at least one type of time-series data among the multiple types of time-series data used as a parameter when calculating the representative value from the narrowing down based on the standard condition.

2. A data processing apparatus according to claim 1.

3. The representative value is a value corresponding to the efficiency of the target device.

3. A data processing apparatus according to claim 2.

4. the target device is a steam turbine; The representative value is the internal efficiency of the steam turbine.

4. A data processing device according to claim 3.

5. the standard conditions include values ​​representing three of an inlet temperature, an inlet pressure, an outlet temperature, and an outlet pressure of the steam turbine, which are parameters for calculating the internal efficiency; The calculation unit assigns the three calculation parameters corresponding to those included in the standard conditions to each side, arranges the time-series data in a cubic space set for each of the fixed performance periods, and calculates the representative value based on the time-series data arranged within a predetermined cube near the standard conditions.

5. A data processing apparatus according to claim 4.

6. the standard conditions include values ​​representing three of an inlet temperature, an inlet pressure, an outlet temperature, and an outlet pressure of the steam turbine, which are parameters for calculating the internal efficiency; The calculation unit assigns the three calculation parameters corresponding to those included in the standard conditions to each side, arranges the time-series data in a cubic space set for each of the fixed performance periods, and divides the data into a plurality of groups according to the internal efficiency, calculates a linear approximation plane for each of the groups, and calculates the representative value based on a positional relationship between a calculation result of the linear approximation plane and a point in the cubic space corresponding to the standard conditions.

5. A data processing apparatus according to claim 4.

7. the standard conditions include values ​​representing three of an inlet temperature, an inlet pressure, an outlet temperature, and an outlet pressure of the steam turbine, which are parameters for calculating the internal efficiency; The calculation unit assigns two of the three calculation parameters corresponding to those included in the standard conditions to each axis, arranges the time-series data on a plane set for each of the fixed performance periods, divides the plane, and sets an approximation line of the representative value based on the remaining one of the three calculation parameters for each of a plurality of small regions specified by the standard conditions, and calculates the representative value based on the standard conditions and the approximation line.

5. A data processing apparatus according to claim 4.

8. A step of a data processing device acquiring multiple types of time series data over a target period related to the operation of a target device; The data processing device divides the target period into a plurality of operating periods according to operating conditions; The data processing device specifies standard conditions that are standard operating conditions for each operating period; the data processing device divides each of the operating periods into a plurality of constant performance periods during which the performance of the target device can be considered constant, narrows down the time series data for each of the constant performance periods based on the standard conditions, and calculates a predetermined representative value based on the time series data extracted by narrowing down the time series data; The data processing device sets an overlapping period including a boundary between two adjacent operating periods, narrows down the time series data within the overlapping period for each standard condition based on each of the standard conditions specified for the two operating periods, and corrects the representative value in at least one of the two operating periods based on a result of calculating each of the representative values ​​based on each of the time series data extracted by narrowing down; Data processing methods, including:

Images