CN112602024A - KPI improvement support system and KPI improvement support method - Google Patents
KPI improvement support system and KPI improvement support method Download PDFInfo
- Publication number
- CN112602024A CN112602024A CN201980056051.7A CN201980056051A CN112602024A CN 112602024 A CN112602024 A CN 112602024A CN 201980056051 A CN201980056051 A CN 201980056051A CN 112602024 A CN112602024 A CN 112602024A
- Authority
- CN
- China
- Prior art keywords
- kpi
- evaluation
- application object
- dynamic
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000006872 improvement Effects 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000011156 evaluation Methods 0.000 claims abstract description 202
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims abstract description 6
- 230000003068 static effect Effects 0.000 claims description 82
- 208000018910 keratinopathic ichthyosis Diseases 0.000 claims description 56
- 239000003245 coal Substances 0.000 claims description 43
- 230000008859 change Effects 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 25
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 claims description 18
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 12
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 12
- 239000000446 fuel Substances 0.000 claims description 10
- 238000010248 power generation Methods 0.000 claims description 10
- 230000001052 transient effect Effects 0.000 claims description 10
- 230000007704 transition Effects 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 5
- PXGOKWXKJXAPGV-UHFFFAOYSA-N Fluorine Chemical compound FF PXGOKWXKJXAPGV-UHFFFAOYSA-N 0.000 claims description 4
- 239000002817 coal dust Substances 0.000 claims description 4
- 239000010419 fine particle Substances 0.000 claims description 4
- 229910052731 fluorine Inorganic materials 0.000 claims description 4
- 239000011737 fluorine Substances 0.000 claims description 4
- QSHDDOUJBYECFT-UHFFFAOYSA-N mercury Chemical compound [Hg] QSHDDOUJBYECFT-UHFFFAOYSA-N 0.000 claims description 4
- 229910052753 mercury Inorganic materials 0.000 claims description 4
- 239000003595 mist Substances 0.000 claims description 4
- 239000012855 volatile organic compound Substances 0.000 claims description 4
- UCKMPCXJQFINFW-UHFFFAOYSA-N Sulphide Chemical compound [S-2] UCKMPCXJQFINFW-UHFFFAOYSA-N 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 2
- 230000004044 response Effects 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 31
- 238000010586 diagram Methods 0.000 description 29
- 230000008569 process Effects 0.000 description 15
- 239000007789 gas Substances 0.000 description 11
- 238000005096 rolling process Methods 0.000 description 11
- 230000007613 environmental effect Effects 0.000 description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 9
- 238000003062 neural network model Methods 0.000 description 7
- 230000003247 decreasing effect Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 238000002485 combustion reaction Methods 0.000 description 5
- 239000000567 combustion gas Substances 0.000 description 4
- 230000007423 decrease Effects 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 229910000037 hydrogen sulfide Inorganic materials 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010298 pulverizing process Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- XTQHKBHJIVJGKJ-UHFFFAOYSA-N sulfur monoxide Chemical class S=O XTQHKBHJIVJGKJ-UHFFFAOYSA-N 0.000 description 1
- 229910052815 sulfur oxide Inorganic materials 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Feedback Control In General (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
本发明提供一边实时地预测响应特性，一边追随实时变化的目标值而进行最佳操作，由此能够总体上进行最佳的运转的KPI改善辅助系统及KPI改善辅助方法。一种KPI改善辅助系统，其获得来自反复执行恒定运转状态和变动运转状态的应用对象的运转数据，并给予所述应用对象的操作条件，其特征在于，所述KPI改善辅助系统具有：动态特性评价单元，其至少使用变动运转状态下的操作条件和运转数据来评价应用对象的变动运转状态下的KPI的动态特性；学习单元，其根据动态特性评价单元中的评价结果学习应用对象的操作条件；以及操作条件信号生成单元，其按照学习单元的学习结果生成应用对象的操作条件。
The present invention provides a KPI improvement assistance system and a KPI improvement assistance method capable of performing an optimal operation as a whole while predicting a response characteristic in real time while following a target value that changes in real time and performing an optimal operation. A KPI improvement assistance system, which obtains operation data from an application object repeatedly performing a constant operation state and a variable operation state, and gives operating conditions to the application object, characterized in that the KPI improvement assistance system has: dynamic characteristics An evaluation unit, which uses at least the operating conditions and operation data under the variable operation state to evaluate the dynamic characteristics of the KPI under the variable operation state of the application object; the learning unit, which learns the operation conditions of the application object according to the evaluation results in the dynamic characteristic evaluation unit ; and an operation condition signal generation unit, which generates an operation condition of the application object according to the learning result of the learning unit.
Description
Technical Field
The present invention relates to a KPI improvement support system and a KPI improvement support method for supporting KPI improvement of various machines.
Background
In recent years, with the innovation of ict (information and Communication technology) and iot (internet of thing), an environment in which high-speed computers, network Communication, and large-capacity data storage devices can be used has become more and more uniform. In the process of receiving attention for effective use of data accumulated in large quantities in many industrial fields, improvement of the operation of Key Performance Indicators (KPI) by integrating systems for managing data collected at site sites, such as measurement data and inspection and maintenance data of machines, and management and asset information of enterprises is required.
For example, in the field of power generation business, there is a fear that the stability of a power system is lowered by a fluctuation in the amount of power generation due to an increase in the use of renewable energy such as wind power generation or solar power generation, and therefore, the importance of a thermal power generation plant as a backup power source is increasing. The thermal power plant plays a role not only as a load regulator but also as a base load power source, and it is required to consider operation performance such as efficiency, environmental performance, and operation rate as KPI operation.
In order to improve the operational performance of a thermal power plant, patent documents 1 and 2 disclose a control device for reducing the concentration of nitrogen oxides and the concentration of carbon monoxide, which are environmental performance.
Documents of the prior art
Patent document
Patent document 1: japanese patent laid-open publication No. 2012-141862
Patent document 2: japanese laid-open patent publication No. 2009-244933
Disclosure of Invention
Problems to be solved by the invention
In the technique described in the prior art document, a model simulating static characteristics and learning means for learning an optimum operation method for the model are combined to generate an operation signal. By using this technique, the type of fuel used in the machine, the content of the product to be produced, and the production amount can be changed, and the operation condition can be moved to the optimum value following the change in the optimum operation condition. However, since transient changes during movement are not taken into consideration, the KPI temporarily deteriorates and may not be an optimum operation as a whole.
The purpose of the present invention is to provide a KPI improvement support system and a KPI improvement support method that can perform an optimum operation while predicting a response characteristic in real time and following a target value that changes in real time, thereby achieving an overall optimum operation.
Means for solving the problems
In accordance with the above, in the present invention, a KPI improvement support system for acquiring operation data from an application object that repeatedly executes a constant operation state and a variable operation state, and providing an operation condition to the application object, the KPI improvement support system includes: a dynamic characteristic evaluation unit that evaluates a dynamic characteristic of the KPI in the varying operating state of the application object using at least the operating condition and the operating data in the varying operating state; a learning unit that learns the operation condition of the application object based on the evaluation result in the dynamic characteristic evaluation unit; and an operation condition signal generation unit that generates an operation condition of the application object in accordance with a learning result of the learning unit.
In the present invention, the KPI improvement support method is characterized in that the dynamic characteristics of the KPI in the variable operation state of the application object are evaluated using at least the operation conditions and the operation data in the variable operation state, the operation conditions of the application object are learned from the evaluation result of the dynamic characteristics, and the operation conditions of the application object are generated in accordance with the learning result.
Effects of the invention
By using the KPI improvement support system and KPI improvement support method of the present invention, KPIs of various machines can be improved. Particularly, when the system is applied to a thermal power plant or a power plant, the efficiency of the plant can be improved and the coal consumption can be reduced.
Drawings
Fig. 1 is a block diagram illustrating a configuration example of a KPI improvement support system according to an embodiment of the present invention.
Fig. 2(a) is a flowchart illustrating a learning operation in the KPI improvement support system.
Fig. 2(b) is a flow chart for generating an operating condition signal based on the learning result in the KPI improvement assist system.
Fig. 3 is a diagram illustrating a relationship between the operation of the application object 100 and KPIs.
Fig. 4(a) is a diagram showing the construction of the static characteristic evaluation unit 300 by the neural network model.
Fig. 4(b) is a diagram showing a relationship between input and output of the neural network model.
Fig. 4(c) is a diagram showing an example of the result of operating learning section 400.
Fig. 5(a) is a diagram illustrating a form of data stored in the operation database DB 1.
Fig. 5(b) is a diagram illustrating the form of data stored in the operation plan database DB 2.
Fig. 6 is a flowchart showing the processing of fig. 2 further divided into a static characteristic side and a dynamic characteristic side.
Fig. 7(a) is a diagram showing an example of the operation result of the plant when the evaluation value Sg10 is calculated using only the static characteristic evaluation result Sg8 in the evaluation value calculation unit 500.
Fig. 7(b) is a diagram showing an example of the operation result of the plant when the evaluation value Sg10 is calculated using only the static characteristic evaluation result Sg8 in the evaluation value calculation unit 500.
Fig. 7(c) is a diagram showing an example of the operation result of the plant when the evaluation value Sg10 is calculated in the evaluation value calculation unit 500 using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg 9.
Fig. 7(d) is a diagram showing an example of the operation result of the plant when the evaluation value Sg10 is calculated in the evaluation value calculation unit 500 using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg 9.
Fig. 8 is a schematic diagram showing the configuration of a coal thermal power plant as an example of the application object 100.
Fig. 9(a) is a graph showing a relationship between an operating condition change width and an overshoot width of a process value.
Fig. 9(b) is a diagram showing an example of the operation result of the plant when the evaluation value Sg10 is calculated using only the static characteristic evaluation result Sg 8.
Fig. 9(c) is a diagram showing a case where the evaluation value Sg10 is calculated using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg 9.
Fig. 10(a) is a diagram illustrating the contents of the operation plan data Sg6 used by the operation plan coordination unit 620.
Fig. 10(b) is a diagram illustrating the result of operating learning section 400 using the evaluation value for operating operation plan cooperation evaluation section 620.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
Example 1
Fig. 1 is a block diagram illustrating a configuration example of a KPI improvement support system 200 according to an embodiment of the present invention. In the present embodiment, the KPI improvement support system 200 is connected to the application object 100 and the external device 900 of the present system.
The KPI improvement support system 200 shown in fig. 1 is generally configured by a computer device, and schematically shows processing functions in the computing device, it can be referred to as a system including a static characteristic evaluation unit 300, a learning unit 400, an evaluation value calculation unit 500, a dynamic characteristic evaluation unit 600, and an operation condition signal generation unit 700. Further, dynamic characteristic evaluation section 600 includes transient characteristic evaluation section 610 and operation plan cooperation evaluation section 620. The operation of each unit in the KPI improvement support system 200 will be described later with reference to fig. 2.
The KPI improvement support system 200 includes, as the database DB: an operation data database DB1, an operation plan database DB2, and a learning result database DB 3. The database DB stores electronic information, and generally stores information in a form called an electronic file (electronic data).
The KPI improvement support system 200 includes an external input interface 210 and an external output interface 220 as interfaces with the outside, and is connected to the application object 100 and the external device 900 of the present system via the interfaces.
With such an interface configuration, the external input signal Sg1 generated by the operation of the external input device 910 (the keyboard 910 and the mouse 920) included in the external device 900 and the operation data Sg2 collected in the application object 100 via the external input interface 210 are extracted into the KPI improvement support system 200.
The application object 100 is composed of a control device 180 and a machine 190, and transmits a measurement signal Sg70 from the machine 190 to the control device 180, and transmits an operation signal Sg80 from the control device 180 to the machine 190. The operation data Sg2 described previously is data including the measurement signal Sg70 and the operation signal Sg 80. The data related to the operation included in the operation data Sg2 and the external input signal Sg1 extracted in the KPI improvement support system 200 is stored as the operation data Sg3 in the operation data database DB1, and the data related to the operation plan included in the external input signal Sg1 is stored as the operation plan data Sg4 in the operation plan database DB 2.
Here, the operation plan data Sg4 is data relating to the operation plan of the application object 100, and includes, for example, the type of fuel used by the application object 100, the content of a product generated by the application object 100, and a planned value of a manufacturing amount.
Further, the KPI improvement assisting apparatus 200 outputs the operation condition signal Sg14 to the control apparatus 180 within the application object 100 and the image display apparatus 940 within the application object 100 via the external output interface 220.
In the KPI improvement support system 200 of the present embodiment, an example is shown in which the computing device constituting the computer device and the database DB are provided inside the KPI improvement support system 200, but some of these devices may be disposed outside the KPI improvement support system 200, and only data may be communicated between the devices.
The signal database information 50, which is a signal stored in each database DB, can be all information displayed on the image display device 940 via the external output interface 220, and the information can be corrected by the external input signal Sg1 generated by operating the external input device 910.
In the present embodiment, the external input device 910 is constituted by the keyboard 920 and the mouse 930, but may be a device for inputting data such as a microphone for voice input or a touch panel.
It is needless to say that the embodiment of the present invention can be implemented as an operation assisting device or method. In the present embodiment, the application target of the KPI improvement support system 200 is set as a plant, but it is needless to say that the application target may be implemented as a plant other than a plant.
Fig. 2(a) and 2(b) are flowcharts illustrating the operation of the KPI improvement assist system 200. Fig. 2(a) is a flowchart of the KPI improvement method.
In the first processing step S100 of the learning flow in fig. 2(a), the initial value of the operating condition Sg7 generated by the learning unit 400 in fig. 1 is set, and the operating condition Sg7 is transmitted to the static characteristic evaluation unit 300 and the dynamic characteristic evaluation unit 600.
In processing step S110, in the static characteristic evaluation unit 300, the static characteristic evaluation result Sg8 is calculated from the input of the operation condition Sg7, and the static characteristic evaluation result Sg8 is sent to the evaluation value calculation unit 500.
In processing step S120, in the dynamic characteristic evaluation unit 600, the dynamic characteristic evaluation result Sg9 is calculated from the input of the operation condition Sg7, and the dynamic characteristic evaluation result Sg9 is sent to the evaluation value calculation unit 500.
The dynamic characteristic evaluation unit 600 includes: and a transient characteristic evaluation unit 610 for evaluating a relationship between at least 1 of a change width and a change rate of the operating condition Sg7 and a dynamic change of the KPI, and the evaluation result is included in the dynamic characteristic evaluation result Sg 9.
Further, the dynamic characteristics evaluation unit 600 includes: and an operation plan cooperation evaluation unit 620 that, when the operation plan including at least 1 of the planned values of the type of fuel used by the application object 100, the content of the product generated by the application object, and the manufacturing amount is changed, increases the evaluation value of the operation condition Sg7 close to the current operation condition Sg7, and the result of this evaluation is included in the dynamic characteristic evaluation result Sg 9.
In processing step S130, in the evaluation value calculation unit 500, the evaluation value Sg10 is calculated from the inputs of the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg9, and the evaluation value Sg10 is transmitted to the learning unit 400.
In processing step S140, the learning unit 400 learns the generation method of the operating condition Sg7 that maximizes the evaluation value Sg 10. Then, the next operation condition Sg7 is generated, and the operation condition Sg7 is transmitted to the static characteristic evaluation unit 300 and the dynamic characteristic evaluation unit 600.
Learning section 400 learns a method of calculating an operation amount for setting the operability of application object 100 to a desired characteristic. The learning unit 400 can be installed using a preferred algorithm such as reinforcement learning, a genetic algorithm, a nonlinear programming method, or the like, but the installation method of the learning unit 400 is not limited in the present invention.
The evaluation value Sg10 referred to by the learning unit 400 is calculated by the evaluation value calculation unit 500, but there are 3 kinds of calculation methods: the method of the formula (1) calculated from the static characteristic evaluation result Sg8, the method of the formula (2) calculated from the dynamic characteristic evaluation result Sg9, and the method of the formula (3) calculated from both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg 9. Further, R is an evaluation value Sg10, p is a static characteristic evaluation result Sg8, q is a dynamic characteristic evaluation result Sg9, and w1 and w2 are weighting coefficients.
[ mathematical formula 1]
R＝Σp (1)
[ mathematical formula 2]
R＝∫qdt (2)
[ mathematical formula 3]
R＝w1×Σp+w2×∫qdt (3)
In step S150, it is determined whether or not the number of operations in step S140 exceeds a predetermined threshold, and if not, the process returns to step S110, and if so, the process proceeds to step S160.
In step S160, it is determined whether or not the number of operations in step S100 exceeds a predetermined threshold, and if not, the process returns to step S100, and if so, the process ends.
The result of the operation of the arithmetic device in each processing step is transmitted to and stored in the processing result database DB3 as the processing result Sg 11. When the arithmetic device is operated in each processing step, the information stored in the processing result database DB3 can be used as needed.
Fig. 2(b) is a flowchart when the operation condition signal is generated from the learning result.
In fig. 2(b), in the processing step S170, in the operation condition signal generation unit 700, the operation condition signal Sg13 is calculated from the input of the processing result Sg12 and transmitted to the external output interface 220. After that, the operation condition signal Sg14 is sent to the control device 180 and the image display device 940. The application object 100 can be directly operated using the operation condition signal Sg 14. Further, the value of the operation condition signal Sg14 can be displayed as an operation guidance in the image display device 940.
Note that, as to the 3 types of learning results learned in the processing step S140, the value of each operation condition signal Sg14 may be displayed on the image display device 940, and any operation condition may be selected.
As shown in fig. 1, 2(a), and 2(b), in the embodiment of the present invention, it is desirable to predictively evaluate the KPI of the application object 100 by dividing the static characteristics and the dynamic characteristics. Therefore, as a premise to be described later, the relationship between the operation of the application object 100 and the KPI will be described with reference to fig. 3.
In fig. 3, the horizontal axis represents time, and the vertical axis represents, for example, the load of the application object 100. As shown in the figure, the load of the application object 100 to which the present invention is applied is not increased to 100% at once, and for example, 1 or more stages that are kept constant are provided in the middle of the increase stage. In the addition phase, the static characteristics of the application object 100 are evaluated at times T1, T2, and T3 of the constant phase to obtain a static characteristic evaluation result Sg8, and the dynamic characteristics of the application object 100 are evaluated during the addition phase periods T1, T2, and T3 to obtain a dynamic characteristic evaluation result Sg 9. In addition, although fig. 3 shows an example in which a constant holding step is provided in the increasing step, the constant holding step is similarly set in the decreasing step of the load.
The static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg9 are indicators indicating KPIs of the application target 100, and are indicators directly or indirectly indicating operation performance such as efficiency, environmental performance, and operation rate. These indices may be obtained for each time point and period to be measured, and a plurality of indices may be set for the indices at each time point and period.
Further, the operating condition Sg7 given by the learning unit 400 of fig. 2 determines the load pattern, which is the increase and decrease stages of the load illustrated in fig. 3, or determines various process amounts and operation amounts in this case. These operating conditions Sg7 converge to the appropriate operating conditions Sg7 by the subsequent learning, and as a result, the load pattern that is initially given as the operating conditions Sg7 is set as the other load pattern after the learning. The KPI improvement support system 200 according to the embodiment of the present invention can pursue an operation manner for optimizing KPI.
As described above, the KPI improvement support system 200 of the present invention proposes, for example, the following: as the load pattern up to the rated load at the stage before the start-up in fig. 3, the initial values of the operating conditions Sg7 (the magnitude, duration, change width, change rate, and the like of the load at each stage) shown by the solid lines are given, the operating state at the time of operating according to the operating conditions is predicted, and the static characteristics and the dynamic characteristics are evaluated, and the application object 100 is controlled by the operating conditions Sg13 shown by the broken lines as a new load pattern created based on the optimum evaluation value evaluated from both viewpoints.
The control based on the above prediction in the KPI improvement support system 200 may be performed such that the operation condition Sg13 is determined as the predicted load mode before the startup, and thereafter, the operation may be performed under the operation condition Sg13, or the prediction may be performed to the next stage or to the next stage during the startup, and the operation may be performed while determining the operation condition Sg13 as the sequential predicted load mode.
Next, the operations of the static characteristic evaluation means 300 and the learning means 400 will be described with reference to fig. 4(a), 4(b), and 4 (c).
Fig. 4(a) and 4(b) are diagrams illustrating an example of the static characteristic evaluation unit 300. The static characteristic evaluation unit 300 is constructed by a neural network model as shown in fig. 4(a), and outputs an index for evaluating the operability of the air flow rate setting value or the like, such as the efficiency of evaluation or the environmental load substance, with respect to the input of the operation amount.
Fig. 4(b) is a diagram showing a relationship between input and output of the neural network model, and is capable of interpolating the input operation data from the neural network model to obtain a value of an index for evaluating operability under an arbitrary operation condition. In the present example, the index for evaluating operability is assumed to be the amount of fuel consumption and the amount of emission of environmental load substances, and the lower the index is, the higher the KPI is.
Fig. 4(c) shows an example of the result of operating the learning unit 400. In the present embodiment, the results obtained by learning the relationship of the current operating condition to the magnitude of change in the operating condition are shown. In the example of fig. 4(c), the operation condition is increased when the current operation amount is in the region a, and the operation condition is decreased when the current operation amount is in the region B. By changing the operating conditions in this way, the index for evaluating the operability of fig. 4(b) is minimized, and KPI can be improved.
In the above description, the operations of static characteristic evaluation section 300 and learning section 400 are described with reference to fig. 4(a), 4(b), and 4(c), but it is needless to say that dynamic characteristic evaluation section 600 can be constructed by a technique other than the neural network model in the same manner. Note that the present invention is not an invention relating to a specific configuration method of the dynamic characteristic evaluation unit 600, and therefore, a detailed description of the dynamic characteristic evaluation unit 600 is omitted.
Fig. 5(a) and 5(b) are diagrams illustrating the form of data stored in the database DB of the KPI improvement support system 200.
Fig. 5(a) is a diagram illustrating a form of data stored in the operation database DB 1.
As shown in fig. 5(a), the operation data of items A, B, C measured by the sensor and the like are stored at sampling intervals. The trend graph of the operation data can be displayed on the image display device 940.
Fig. 5(b) is a diagram illustrating the form of data stored in the operation plan database DB 2. As shown in fig. 5(b), a schedule of materials used in the plant, products produced by the plant, and the like is stored in time series as the operation condition A, B, C. The planning data of the materials used in the plant, the products generated by the plant, and the like stored in the operation planning database DB2 are data in which time series such as the magnitude, duration, change width, change rate, and the like of the load at each stage are reflected as the load constant state or the load change state in fig. 3.
Although not shown, the processing result database DB3 stores therein the weight coefficients of the neural network model shown in fig. 4(a), information necessary for obtaining the results shown in fig. 4(b) and 4(c), and the like.
Fig. 6 is a flowchart showing the processing of fig. 2 further divided into a static characteristic side and a dynamic characteristic side.
According to the flow of fig. 6, in the first processing step S200, various data Sg5, Sg6 necessary for KPI calculation are extracted from the operation data database DB1 and the operation plan database DB 2. This is data obtained by extracting data participating in the operation section shown in fig. 3 from data accumulated in the database DB based on past operation experience of the application object 100 for the purpose of subsequent calculation. Or, the presence information reflects the current operating state of the application object 100.
These data are assigned as static characteristic side data and dynamic characteristic side data in the processing steps S201S, S201D. In a very simple manner, the static characteristic-side data is data obtained at times T1, T2, and T3 in the static state of fig. 3, and the dynamic characteristic-side data is data obtained in time periods T1, T2, and T3 in the operating state of fig. 3. In fig. 6, the right-hand process represents the dynamic characteristic-side process (denoted by D), the left-hand process represents the static characteristic-side process (denoted by S), and the central portion represents the common process.
Next, in the processing steps S202S, S202D, the operating conditions Sg7 regarding the static characteristic model and the dynamic characteristic model are set. In the initial state, for example, the time, which is the load pattern at that time, and the magnitude of the load are set for the times T1, T2, and T3 in the stationary state, and the change width, the change rate, and the magnitude of the load are set for the periods T1, T2, and T3 in the operating state, for example. In addition, other factors may be set as necessary.
In the processing steps S203S, S203D, an operation based on the static characteristic model and the dynamic characteristic model is performed under the given data and the operation conditions, and the static characteristic evaluation and the dynamic characteristic evaluation are performed. This process corresponds to the static characteristic evaluation unit 300 and the dynamic characteristic evaluation unit 600 of fig. 1. As the processing results of the processing steps S203S, S203D, the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg9 are obtained, respectively, but they may be 1 or more. For example, if a plurality of operational performances such as efficiency, environmental performance, and operation rate are considered as KPIs, KPIs in the viewpoints of efficiency, environmental performance, operation rate, and the like can be obtained in the static characteristic evaluation and the dynamic characteristic evaluation, respectively.
In the processing step S204, for example, a plurality of KPIs calculated from the viewpoint of static characteristic evaluation and dynamic characteristic evaluation are bound to 1 KPI by the mathematical expression (3), or important several indexes are used as representative indexes. The representative index is an index in which both static characteristic evaluation and dynamic characteristic evaluation are considered.
In the processing step S205, a new operation condition Sg7 is generated to achieve the representative index, and the processing steps S202S and S202D are again subjected to condition setting, respectively, and thereafter, the processing is repeatedly executed until the KPI serving as the initial purpose is achieved. In the processing step S206, external output is performed in a case where a result that should be satisfied is obtained. The final result is, for example, a result of setting a new load pattern, and is, for example, a result of teaching such that the load pattern in fig. 3 is a broken line. The load pattern of the dashed line corresponds to the operating signal Sg13 of fig. 1.
Next, the effects of the present invention will be described with reference to fig. 7(a), 7(b), 7(c), and 7 (d).
Fig. 7(a) and 7(b) are examples of operation results of the plant when the evaluation value calculation unit 500 calculates the evaluation value Sg10 using only the static characteristic evaluation result Sg 8. Fig. 7(c) and 7(d) show examples of operation results of the plant when the evaluation value calculation unit 500 calculates the evaluation value 10 using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg 9.
Fig. 7(a) is a diagram showing a time transition (horizontal axis) of KPIs (vertical axis), and shows that KPIs are evaluated in a static state (state where KPIs are constant) and reflected in the subsequent operation. In this example, the operating conditions were changed from Sp10 to Sp11 in the first static state and from Sp11 to Sp20 in the next static state. As a result, each time the KPI transitions to the next static state, it first shows a decreasing trend, and then increases to move to the steady state.
Fig. 7(B) shows the relationship between the operation conditions before and after the start-up, for example, and an intermediate point is set in consideration of operational restrictions and the like every time the operation condition is shifted from Sp10, which is the optimum point of the state a (100% load), to Sp20, which is the optimum point of the state B (80% load), and the intermediate point is selected as the operation condition and passed through Sp 11.
As shown in this example, when the evaluation value Sg10 is calculated using only the static characteristic evaluation result Sg8, the KPI is improved by changing the operation conditions in accordance with the result of operating the KPI improvement support system 200. As shown in fig. 7(b), since there are restrictions and restrictions on the range of operating conditions that can be changed by 1 operation, the operating conditions are changed a plurality of times to improve the KPI.
Further, while the KPI is improved by repeating the operation, the KPI is temporarily deteriorated when the operation condition is changed. This is because the KPI changes as the process value of the application object changes transiently.
On the other hand, when the evaluation value 10 is calculated using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg9, the following is performed.
Fig. 7 c is a diagram showing a time transition (horizontal axis) of KPIs (vertical axis), and shows that KPIs are evaluated in a dynamic state (a state in which KPIs are constant) and reflected in the subsequent operation. In this example, the operating conditions were changed from Sp10 to Sp12 in the first state and from Sp12 to Sp20 in the next state. As a result, each time the KPI shifts to the next state, the KPI first shows a decreasing tendency, and then increases to transition to the steady state, but the large decreasing tendency as shown in fig. 7(a) is reduced.
Fig. 7(d) shows the relationship between the operation conditions before and after the start-up, for example, and an intermediate point is set in consideration of operational restrictions and the like every time the operation condition is shifted from Sp10, which is the optimum point of the state a (100% load), to Sp20, which is the optimum point of the state B (80% load), and the intermediate point is selected as the operation condition via Sp 12. This route of operation via Sp12 is a route of operation excellent in dynamic characteristics.
From these comparisons, as shown in fig. 7(c), when the evaluation value Sg10 is calculated using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg9, the KPI is improved in the same manner as in fig. 7(a) by changing the operation conditions in accordance with the result of operating the KPI improvement support system 200. The final KPI values are the same in fig. 7(a) and 7(c), but the degradation of the transitional KPI is smaller in fig. 7(c), which is overall superior to fig. 7(a) when time integration is performed. This is because, in fig. 7(c), the evaluation value Sg10 is calculated using the dynamic characteristic evaluation result Sg9 as well, and therefore, the operation condition is determined so as to suppress the transient KPI drop.
In this way, by using the KPI improvement support system 200 of the present invention, the operating conditions can be determined so as to suppress the KPI drop of the transition, and the overall optimization of the time integral can be achieved.
Example 2
Since the basic concept of the KPI improvement support system and KPI improvement support method according to the present invention is described in example 1, example 2 describes a case where the application is a coal thermal power plant.
Fig. 8 is a schematic diagram showing the configuration of a coal thermal power plant as an example of the application object 100. First, a structure for generating power from a coal-fired power plant will be briefly described.
In fig. 8, a boiler 101 constituting a coal thermal power plant 100 to be applied is provided with a plurality of burners 102 for supplying pulverized coal, which is fuel obtained by finely pulverizing coal by a rolling mill 134, 1-time air for conveying pulverized coal, and 2-time air for adjusting combustion, and the pulverized coal supplied by the burners 102 is burned in the boiler 101. As shown in the figure, the combustor 102 is configured by arranging a plurality of stages before and after the boiler 101, and arranging a plurality of combustors in 1 row for each stage. With the burner configuration and arrangement shown in fig. 8, pulverized coal is burned from the front surface (hereinafter, referred to as the front of the boiler) and the back surface (hereinafter, referred to as the back of the boiler) of the boiler 101. The heat recovery effect of the boiler is improved by improving the combustion balance of the burners at the front and the rear of the tank, and the heat efficiency of the plant is also improved.
Further, pulverized coal and 1 st air are introduced from the pipe 139 to the combustor 102, and 2 nd air is introduced from the pipe 141 to the combustor 102. The 1 st air is guided from the fan 120 to the pipe 130, and is branched into the pipe 132 passing through the air heater 104 provided on the downstream side of the boiler 101 and the pipe 131 bypassing without passing through the air heater 104, but is merged again by the pipe 133 disposed on the downstream side of the air heater 104, and is guided to the mill 134 for producing pulverized coal provided on the upstream side of the burner 102. The 1 st air passing through the air heater 104 is heated by heat exchange with the combustion gas flowing down in the boiler 101. The 1 st air bypassing the air heater 104 delivers pulverized coal pulverized in the mill 134 to the burner 102 together with the heated 1 st air.
The rolling mill 134 is disposed so as to correspond to each burner stage (4 in fig. 8), and supplies pulverized coal and 1-time air to the burners constituting each stage. That is, when the coal supply amount is reduced such as when the power generation output is lowered, the rolling mill can be stopped and the burners can be stopped at the burner level. In the rolling mill 134, the rotation speed of the rolling mill is adjusted so that the pulverized coal having a desired particle size is obtained according to the properties of the coal used, in consideration of the combustibility of the boiler 101. The coal stored in the coal bunker 136 is guided to the coal feeder 135 via the coal conveyor 137, and the supply amount is adjusted by the coal feeder 135. Thereafter, the coal is supplied to the rolling mill 134 via a coal conveyor 138.
The boiler 101 is provided with a rear air port 103 for introducing air for 2-stage combustion into the boiler 101. The air for the 2-stage combustion is guided from the pipe 142 to the rear air port 103. In the boiler 101 shown in fig. 8, air introduced from a pipe 140 by a fan 121 is similarly heated by an air heater 104, and then branched to a pipe 141 for 2-time air and a pipe 142 for a rear air port, and guided to a burner 102 and a rear air port 103 of the boiler 101, respectively. The flow rate of air supplied to the combustor 102 and the rear air port 103 can be adjusted by operation of air dampers (not shown) provided in the pipes 141 and 142.
The high-temperature combustion gas generated by burning pulverized coal in the boiler 101 flows downstream along the path in the boiler 101, and after being subjected to heat exchange with the feed water by the heat exchanger 106 disposed in the boiler 101 to generate steam, the steam flows as exhaust gas into the air heater 104 disposed downstream of the boiler 101, and the air supplied to the boiler 101 is heated by heat exchange by the air heater 104.
The exhaust gas passing through the air heater 104 is subjected to an exhaust gas treatment, not shown, and then discharged from a stack into the air.
The feed water circulating through the heat exchanger 106 of the boiler 101 is supplied to the heat exchanger 106 via the feed water pump 105, and superheated by the combustion gas flowing down through the boiler 101 in the heat exchanger 106 to become high-temperature and high-pressure steam. In the present embodiment, the number of heat exchangers is set to one, but a plurality of heat exchangers may be arranged.
The high-temperature and high-pressure steam generated by the heat exchanger 106 is guided to the steam turbine 108 via the turbine governor 107, and the steam turbine 108 is driven by the energy of the steam to generate electricity by the generator 109.
In the coal thermal power plant to which the application 100 of example 2 is applied, various measuring instruments for detecting state quantities indicating the operation states thereof are arranged.
The measurement signals of the coal thermal power plant obtained from the measurement instruments disposed in the application object 100 are stored in the operation data DB1 as shown in fig. 1.
As shown in fig. 8, for example, there are a temperature measuring instrument 151 that measures the temperature of high-temperature and high-pressure steam supplied from the heat exchanger 106 to the steam turbine 108, a pressure measuring instrument 152 that measures the pressure of the steam, and a power generation output measuring instrument 153 that measures the amount of electric power generated by the generator 109.
Feed water generated by cooling steam by a condenser (not shown) of the steam turbine 108 is supplied to the heat exchanger 106 of the boiler 101 by the feed water pump 105, and the flow rate of the feed water is measured by the flow rate measuring instrument 150.
And components (nitrogen oxide (NOx), carbon monoxide (CO), and hydrogen sulfide (H) contained in exhaust gas that is combustion gas discharged from the boiler 1012S), etc.) are measured by a concentration measuring instrument 154 provided on the downstream side of the boiler 101.
Further, as the measuring instruments related to the coal supply system, there are a 1 st air flow meter 155 for measuring the flow rate of 1 st air supplied to the rolling mill 134 through the pipe 133, a coal supply meter 156 for measuring the coal supply amount of coal supplied from the coal feeder 135 to the rolling mill 134 through the coal conveyor 138, and a tachometer 157 for measuring the rotational speed of the rolling mill 134, and the above information can be measured for each rolling mill and coal feeder.
That is, the operation data database DB1 of the present invention includes: the state quantity of the coal thermal power plant 100 to be applied measured by each of the above-described measuring devices, that is, the flow rate of coal supplied to the boiler 101, the rotation speed of the rolling mill 134, the 1 st and 2 nd air flow rates supplied to the boiler 101, the feed water flow rate supplied to the heat exchanger 106 of the boiler 101, the steam temperature generated by the heat exchanger 106 of the boiler 101 and supplied to the steam turbine 108, the feed water pressure of the feed water supplied to the heat exchanger 106 of the boiler 101, the gas temperature of the exhaust gas discharged from the boiler 101, the gas concentration of the exhaust gas, and the exhaust gas recirculation flow rate at which a part of the exhaust gas discharged from the boiler 101 is recirculated in the boiler 101.
Note that, in general, although a plurality of measuring instruments are provided in the target object 100 for coal thermal power application in addition to those shown in fig. 8, illustration thereof is omitted.
When the KPI improvement support system 200 is applied to a thermal power plant, the following KPIs may be considered as a specific KPI. These are, for example, the flow rate of coal consumed by the thermal power plant, the state amounts of any of unburned components in ash discharged from the thermal power plant, carbon monoxide, nitrogen oxides, sulfide oxides, mercury, fluorine, fine particles composed of coal dust or mist, and volatile organic compounds, and reduction of these values is associated with improvement of KPI.
Fig. 9(a), 9(b), and 9(c) are diagrams illustrating the operation of transient characteristic evaluation section 610 in fig. 1. The transient characteristic evaluation means 610 evaluates the relationship between the change width and the change rate of the air flow rate, the coal flow rate, the state quantity of any of the ash unburned components, carbon monoxide, nitrogen oxides, sulfur oxides, mercury, fluorine, fine particles composed of coal dust or mist, and volatile organic compounds, which are the operation conditions.
As shown in fig. 9(a), transient characteristic evaluation section 610 stores the relationship between the operating condition change width and the overshoot width of the process value. This relationship is created from the operation results of the past plant and the results of the simulation using the model that simulates the characteristics of the plant.
When the overshoot amplitude is large, the KPI is a factor of decreasing, and therefore, the evaluation value decreases. As a result, an operation with less overshoot can be learned in the learning unit 400.
Fig. 9(b) is an example of the operation result of the plant when the evaluation value calculation unit 500 calculates the evaluation value Sg10 using only the static characteristic evaluation result Sg 8. Fig. 9(c) is an example of the operation result of the plant when the evaluation value calculation unit 500 calculates the evaluation value Sg10 using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg 9.
As shown in fig. 9(b), when the evaluation value Sg10 is calculated using only the static characteristic evaluation result Sg8, the KPI is improved by changing the operation conditions in accordance with the result of operating the KPI improvement support system 200. The CO concentration decreases by repeating the operation, but temporarily increases when the operation conditions are changed.
As shown in fig. 9(c), when the evaluation value Sg10 is calculated using both the static characteristic evaluation result Sg8 and the dynamic characteristic evaluation result Sg9, the CO concentration is improved in the same manner as in fig. 9(b) by changing the operation conditions in accordance with the result of operating the KPI improvement support system 200. The final CO concentration value is the same in fig. 9(b) and 9(c), but the transient CO concentration rise is small in fig. 9(c), and fig. 9(c) is generally more excellent than fig. 9(b) in performing time integration. This is because, in fig. 9(c), the evaluation value Sg10 is also calculated using the dynamic characteristic evaluation result Sg9, and therefore, the operation conditions are determined so as to suppress a transient KPI decrease, that is, an increase in the CO concentration.
Fig. 10(a) and 10(b) are diagrams illustrating the operation of the operation plan cooperation evaluation unit 620.
Fig. 10(a) is a diagram illustrating the contents of the operation plan data Sg6 used by the operation plan coordination unit 620. In a power generation plant, the load is adjusted according to the demand of electric power, and when the load condition changes, the flow rate of coal supplied to the plant is changed. With this change, the combustion state in the furnace also changes, and the optimum operating conditions also change. The operation plan data Sg6 includes a relationship between time and load.
Fig. 10(b) is a diagram illustrating the result of operating learning section 400 using the evaluation value for operating operation plan cooperation evaluation section 620. In the case where the operation time of 80% load is short, the KPI becomes high as a whole when arriving earlier even under the quasi-optimal condition, as compared with the time taken to change the operation condition a plurality of times in order to arrive at the optimal point.
By using the operation plan coordination unit 620 of the present invention, a generally good operation method can be found. Further, a plurality of operation routes may be displayed on the image display device 940, and the operation route may be selected.
Example 3
In examples 1 and 2, the case where the KPI improvement support apparatus of the present invention is applied to a plant is described, but the application target is not limited to the plant.
For example, when a facility having a heat cycle is operated, it is required to reduce the load on the environment as much as possible and to reduce the amount of fuel used. In a vehicle, there is a problem of achieving both reduction of environmental load substances contained in exhaust gas and improvement of fuel efficiency. In order to solve such a problem, KPIs of environmental load substances, fuel efficiency, and the like can be improved by determining the operation amount of the KPI improvement support system using the present invention.
Industrial applicability of the invention
The present invention can be widely used as a KPI improvement support system for various machines.
Description of the reference numerals
Sg 1: external input signal, Sg 2: operating data, Sg 3: operating data, Sg 4: operation plan data, Sg 5: operating data, Sg 6: operation plan data, Sg 7: operating conditions, Sg 8: static characteristics evaluation result, Sg 9: dynamic characteristics evaluation result, Sg 10: evaluation value, Sg 11: processing result, Sg 12: processing result, Sg 13: operating condition signal, Sg 14: operating condition signal, Sg 70: measurement signal, Sg 80: operation signal, 100: application object, 180: control device, 190: machine, 200: KPI improvement assistance system, 210: external input interface, 220: external output interface, DB 1: operation data DB, DB 2: operation schedule DB, DB 3: processing result DB, 300: static characteristic evaluation unit, 400: learning unit, 500: evaluation value calculation unit, 600: dynamic characteristics evaluation unit, 610: transition characteristic evaluation unit, 620: operation plan cooperation evaluation unit, 700: operation condition signal generation unit, 900: external device, 910: external input device, 920: keyboard, 930: mouse, 940: an image display device.
Claims (20)
1. A KPI improvement support system for acquiring operation data from an application object repeatedly executing a constant operation state and a varying operation state and giving an operation condition to the application object,
the KPI improvement assistance system has: a dynamic characteristic evaluation unit that evaluates a dynamic characteristic of the KPI in the varying operating state of the application target using at least the operating condition in the varying operating state and the operating data; a learning unit that learns the operation condition of the application object according to the evaluation result in the dynamic characteristic evaluation unit; and an operation condition signal generation unit that generates an operation condition of the application object in accordance with a learning result of the learning unit.
2. A KPI improvement assistance system according to claim 1,
the KPI improvement assistance system has: a static characteristic evaluation unit that evaluates a static characteristic of the KPI in the steady operation state of the application target using at least the operation condition in the steady operation state and the operation data; and an evaluation value calculation unit that obtains evaluation results for the static characteristics and the dynamic characteristics from the evaluation result in the dynamic characteristic evaluation unit and the evaluation result in the static characteristic evaluation unit,
the learning unit learns the operation condition of the application object in accordance with the evaluation result given by the evaluation value calculation unit.
3. A KPI improvement assistance system according to claim 1,
the dynamic characteristics evaluation unit evaluates the dynamic characteristics of the KPI in the fluctuating operating state of the application target using the operating conditions in the fluctuating operating state determined by the result of learning in the learning unit.
4. A KPI improvement assistance system according to claim 2,
the static characteristic evaluation unit evaluates the static characteristic of the KPI in the steady operation state of an application target using the operation condition in the steady operation state determined by the result of learning in the learning unit.
5. A KPI improvement assistance system according to any one of claims 1 to 4, wherein,
the dynamic characteristic evaluation unit includes: a transition characteristic evaluation unit that evaluates a relationship between at least 1 of a change width and a change rate as the operating condition and a dynamic change of the KPI.
6. A KPI improvement assistance system according to claim 5,
the dynamic characteristic evaluation unit includes: and an operation plan collaborative evaluation means for, when an operation plan including at least 1 of the planned values of the type of fuel used by the application object, the content of the product generated by the application object, and the manufacturing amount is changed, increasing the evaluation value of the operation condition close to the current operation condition.
7. A KPI improvement assistance system according to any one of claims 1 to 6, wherein,
the KPI improvement assistance system has: a static characteristic evaluation unit that evaluates a static characteristic of the KPI in a steady operation state of an application object using the operation condition in the steady operation state and the operation data,
the evaluation value referred to by the learning unit is in the following 3 cases: the present invention is made in view of the above-described circumstances, and an object thereof is to provide a method and a system for evaluating a dynamic characteristic of a vehicle, which can generate 3 kinds of operation conditions having the maximum or minimum evaluation results for 3 kinds of calculation methods, and can select an arbitrary operation condition, in a case of calculating from a static characteristic evaluation result in the static characteristic evaluation means, a case of calculating from a dynamic characteristic evaluation result in the dynamic characteristic evaluation means, and a case of calculating from both the static characteristic evaluation result and the dynamic characteristic evaluation result.
8. A KPI improvement assistance system according to any one of claims 1 to 6, wherein,
the KPI improvement assistance system has: a static characteristic evaluation unit that evaluates a static characteristic of the KPI in a steady operation state of an application object using the operation condition in the steady operation state and the operation data,
the static characteristic evaluation unit and the dynamic characteristic evaluation unit evaluate a plurality of KPIs, respectively, and the learning unit learns a representative value of evaluation results of the plurality of KPIs as an evaluation result.
9. A KPI improvement assistance system according to any one of claims 1 to 8, wherein,
the application object is a thermal power generation complete set of equipment,
the KPI is a state quantity of any of a coal flow rate consumed by the thermal power plant, an unburned portion in ash discharged from the thermal power plant, carbon monoxide, nitrogen oxides, sulfide oxides, mercury, fluorine, fine particles composed of coal dust or mist, and volatile organic compounds.
10. A KPI improvement assistance system according to claim 9,
the dynamic characteristic evaluation unit includes: and transient characteristic evaluation means for evaluating a relationship between a change width or a change rate of the air flow rate and a dynamic change of a state quantity of any one of a coal flow rate, an unburned component in ash, carbon monoxide, a nitrogen oxide, a sulfide oxide, mercury, fluorine, fine particles composed of coal dust or mist, and a volatile organic compound.
11. A KPI improvement assistance system according to claim 10,
the dynamic characteristic evaluation unit includes: and an operation plan cooperation evaluation means for increasing the evaluation value of the operation condition close to the current operation condition when the coal operation plan or the load plan is changed.
12. A KPI improvement assistance system according to any one of claims 9 to 11, wherein,
the KPI improvement assistance system has: static characteristic evaluation means for estimating KPI at a stationary time by predicting static characteristics of the thermal power generation plant, wherein the evaluation value referred to by the learning means may be 3 of: the present invention is made in view of the above-described circumstances, and an object thereof is to provide a method and a system for evaluating a dynamic characteristic of a vehicle, which can generate 3 kinds of operation conditions having the maximum or minimum evaluation results for 3 kinds of calculation methods, and can select an arbitrary operation condition, in a case of calculating from a static characteristic evaluation result in the static characteristic evaluation means, a case of calculating from a dynamic characteristic evaluation result in the dynamic characteristic evaluation means, and a case of calculating from both the static characteristic evaluation result and the dynamic characteristic evaluation result.
13. A KPI improvement assistance system according to any one of claims 9-12, wherein,
the dynamic characteristics evaluation unit calculates the overshoot range of the state quantity from the operation condition change range based on the operation result of the plant in the past and the simulation result using the model for simulating the plant characteristics.
14. A KPI improvement assisting method for giving an operating condition to an application object by using operation data from the application object repeatedly executing a constant operation state and a varying operation state,
the dynamic characteristics of the KPI in the varying operation state of the application object are evaluated by using at least the operation conditions in the varying operation state and the operation data, the operation conditions of the application object are learned according to the evaluation result of the dynamic characteristics, and the operation conditions of the application object are generated according to the learning result.
15. A KPI improvement assistance method according to claim 14,
the method includes evaluating a static characteristic of a KPI in a steady operation state of an application object using at least an operation condition in the steady operation state and the operation data, obtaining evaluation results of the static characteristic and the dynamic characteristic from an evaluation result of the dynamic characteristic and an evaluation result of the static characteristic, and learning the operation condition of the application object from the evaluation.
16. A KPI improvement assistance method according to claim 14,
and evaluating the dynamic characteristics of the KPI in the varying operation state of the application object by using the operation condition in the varying operation state determined by the learning result.
17. A KPI improvement assistance method according to claim 15, wherein,
evaluating a static characteristic of the KPI in the steady operation state of an application object using the operating condition in the steady operation state determined by the result of the learning.
18. A KPI improvement assisting method according to any one of claims 14 to 17, wherein,
evaluating a relationship of at least 1 of a change amplitude and a change rate as the operating condition to a dynamic change of the KPI each time the dynamic characteristic is evaluated.
19. A KPI improvement assistance method according to claim 18,
when an operation plan including at least 1 of the type of fuel used by the application object, the content of a product generated by the application object, and the planned value of the manufacturing amount is changed, the evaluation value of the operation condition close to the current operation condition is increased every time the dynamic characteristic is evaluated.
20. A KPI improvement assisting method according to any one of claims 14 to 19, wherein,
evaluating the static characteristics of the KPI under the constant operation state of the application object by using the operation condition under the constant operation state and the operation data,
the evaluation value referred to in the learning is in the following case 3: in the case of calculation from the evaluation result of the static characteristic, the case of calculation from the evaluation result of the dynamic characteristic, and the case of calculation from both the evaluation result of the static characteristic and the evaluation result of the dynamic characteristic, 3 kinds of operation conditions having the maximum or minimum evaluation results are generated for 3 kinds of calculation methods, and an arbitrary operation condition can be selected.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2019022589A JP7374590B2 (en) | 2019-02-12 | 2019-02-12 | KPI improvement support system and KPI improvement support method |
| JP2019-022589 | 2019-02-12 | ||
| PCT/JP2019/039569 WO2020166126A1 (en) | 2019-02-12 | 2019-10-08 | Kpi improvement assistance system and kpi improvement assistance method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112602024A true CN112602024A (en) | 2021-04-02 |
Family
ID=72043891
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980056051.7A Pending CN112602024A (en) | 2019-02-12 | 2019-10-08 | KPI improvement support system and KPI improvement support method |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP7374590B2 (en) |
| CN (1) | CN112602024A (en) |
| WO (1) | WO2020166126A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20240045255A (en) * | 2022-04-12 | 2024-04-05 | 미츠비시 파워 가부시키가이샤 | Data processing devices and data processing methods |
| JP2024063582A (en) * | 2022-10-26 | 2024-05-13 | 株式会社日立製作所 | DESIGN ASSISTANCE METHOD, DESIGN ASSISTANCE SYSTEM, AND PROGRAM |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6666049B1 (en) * | 2003-03-20 | 2003-12-23 | Praxair Technology, Inc. | Method for operating a cryogenic plant |
| CN101030074A (en) * | 2006-02-28 | 2007-09-05 | 株式会社日立制作所 | Control device and control method |
| JP2009244933A (en) * | 2008-03-28 | 2009-10-22 | Hitachi Ltd | Plant control system and thermal power generation plant control system |
| CN102418919A (en) * | 2010-08-31 | 2012-04-18 | 株式会社日立制作所 | Control devices for equipment and control devices for thermal power generation equipment |
| CN103282840A (en) * | 2011-01-05 | 2013-09-04 | 株式会社日立制作所 | Control device for large-scale equipment and control device for thermal power generation large-scale equipment |
| JP2014510315A (en) * | 2010-10-01 | 2014-04-24 | アーベーベー・リサーチ・リミテッド | Methods and systems for energy benchmarking for gap analysis for plants in the paper industry. |
| US20150262095A1 (en) * | 2014-03-12 | 2015-09-17 | Bahwan CyberTek Private Limited | Intelligent Decision Synchronization in Real Time for both Discrete and Continuous Process Industries |
| US20150317591A1 (en) * | 2014-05-02 | 2015-11-05 | Rockwell Automation Technologies, Inc. | Mobile computing application for industrial automation manufacturing data |
| CN106020154A (en) * | 2016-07-12 | 2016-10-12 | 中国石油化工股份有限公司 | Safe dynamic health assessment method and assessment system for ethylene production |
| US20180032940A1 (en) * | 2016-07-28 | 2018-02-01 | Honeywell International Inc. | Mpc with unconstrained dependent variables for kpi performance analysis |
| US20180129195A1 (en) * | 2016-11-09 | 2018-05-10 | Yokogawa Engineering Asia Pte. Ltd. | Kpi calculation rule builder for advance plant monitoring and diagnostics |
| CN108038583A (en) * | 2016-10-28 | 2018-05-15 | 开利公司 | For management performance index to solve the method and system of business facility operation management target |
| CN108073145A (en) * | 2016-11-14 | 2018-05-25 | 株式会社日立制作所 | Operation support device and program |
| US20180348717A1 (en) * | 2017-06-02 | 2018-12-06 | Aspen Technology, Inc. | Computer System And Method For Building And Deploying Predictive Inferential Models Online |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5117232B2 (en) * | 2008-03-18 | 2013-01-16 | 株式会社日立製作所 | Control device for plant with boiler and control method for plant with boiler |
| JP6667664B2 (en) * | 2016-11-24 | 2020-03-18 | 三菱日立パワーシステムズ株式会社 | Plant management apparatus, plant management method, and program |
-
2019
- 2019-02-12 JP JP2019022589A patent/JP7374590B2/en active Active
- 2019-10-08 CN CN201980056051.7A patent/CN112602024A/en active Pending
- 2019-10-08 WO PCT/JP2019/039569 patent/WO2020166126A1/en active Application Filing
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6666049B1 (en) * | 2003-03-20 | 2003-12-23 | Praxair Technology, Inc. | Method for operating a cryogenic plant |
| CN101030074A (en) * | 2006-02-28 | 2007-09-05 | 株式会社日立制作所 | Control device and control method |
| JP2009244933A (en) * | 2008-03-28 | 2009-10-22 | Hitachi Ltd | Plant control system and thermal power generation plant control system |
| CN102418919A (en) * | 2010-08-31 | 2012-04-18 | 株式会社日立制作所 | Control devices for equipment and control devices for thermal power generation equipment |
| JP2014510315A (en) * | 2010-10-01 | 2014-04-24 | アーベーベー・リサーチ・リミテッド | Methods and systems for energy benchmarking for gap analysis for plants in the paper industry. |
| CN103282840A (en) * | 2011-01-05 | 2013-09-04 | 株式会社日立制作所 | Control device for large-scale equipment and control device for thermal power generation large-scale equipment |
| US20150262095A1 (en) * | 2014-03-12 | 2015-09-17 | Bahwan CyberTek Private Limited | Intelligent Decision Synchronization in Real Time for both Discrete and Continuous Process Industries |
| US20150317591A1 (en) * | 2014-05-02 | 2015-11-05 | Rockwell Automation Technologies, Inc. | Mobile computing application for industrial automation manufacturing data |
| CN106020154A (en) * | 2016-07-12 | 2016-10-12 | 中国石油化工股份有限公司 | Safe dynamic health assessment method and assessment system for ethylene production |
| US20180032940A1 (en) * | 2016-07-28 | 2018-02-01 | Honeywell International Inc. | Mpc with unconstrained dependent variables for kpi performance analysis |
| CN108038583A (en) * | 2016-10-28 | 2018-05-15 | 开利公司 | For management performance index to solve the method and system of business facility operation management target |
| US20180129195A1 (en) * | 2016-11-09 | 2018-05-10 | Yokogawa Engineering Asia Pte. Ltd. | Kpi calculation rule builder for advance plant monitoring and diagnostics |
| CN108073145A (en) * | 2016-11-14 | 2018-05-25 | 株式会社日立制作所 | Operation support device and program |
| US20180348717A1 (en) * | 2017-06-02 | 2018-12-06 | Aspen Technology, Inc. | Computer System And Method For Building And Deploying Predictive Inferential Models Online |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2020129338A (en) | 2020-08-27 |
| JP7374590B2 (en) | 2023-11-07 |
| WO2020166126A1 (en) | 2020-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5251938B2 (en) | Plant control device and thermal power plant control device | |
| RU2559416C2 (en) | Optimised integrated control for oxy-fuel combustion power plant | |
| US7660639B2 (en) | Control system for control subject having combustion unit and control system for plant having boiler | |
| US8185216B2 (en) | Plant controlling device and method, thermal power plant, and its control method | |
| EP1921280A2 (en) | Systems and methods for multi-level optimizing control systems for boilers | |
| JP5663510B2 (en) | Coal-fired power plant control device and coal-fired power plant | |
| CN103282840B (en) | Control device for large-scale equipment and control device for thermal power generation large-scale equipment | |
| Hanak et al. | Evaluation and modeling of part-load performance of coal-fired power plant with postcombustion CO2 capture | |
| JP6742222B2 (en) | Driving support device and program | |
| JP2014052929A (en) | Control device and control method for thermal power plant | |
| CN112602024A (en) | KPI improvement support system and KPI improvement support method | |
| Zhang et al. | Optimization models for operation of a steam power system in integrated iron and steel works | |
| JP5117232B2 (en) | Control device for plant with boiler and control method for plant with boiler | |
| Gao et al. | Enhancement of SCR denitrification control strategy considering fluegas temperature fluctuation: Fundamental principle and performance evaluation | |
| JP4333766B2 (en) | Boiler control device and control method | |
| Gooty et al. | Incorporation of market signals for the optimal design of post combustion carbon capture systems | |
| Frangopoulos et al. | A contribution to the discussion on the future of thermoeconomics | |
| Al-Malak et al. | Soft analyzer for monitoring NOx emissions from a gas turbine combustor | |
| JP7368332B2 (en) | Guidance operation support device, guidance operation support method, and guidance operation support program | |
| Goßrau et al. | Reduction of the Emission Footprint of Gas Turbines in Future Energy System Scenarios Through Optimized Hydrogen Admixture Strategies | |
| JP7222943B2 (en) | Operation improvement support system, operation improvement support method, and operation improvement support program | |
| AU2021427367B2 (en) | Operation assistance device, operation assistance method, and operation assistance program | |
| Tverskoy et al. | About Control Systems of Gas-Oil Power Units | |
| Qin et al. | A Thermo-Economic Analysis Method for Combined Cycle Power Plants under Flexible Operation Modes | |
| Mandi et al. | Carbon emission reduction by improving performance of primary air fans in thermal power plants through energy conservation techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210402 |
|
| WD01 | Invention patent application deemed withdrawn after publication |