Comprehensive operation economic index calculation method for garbage power plant
Through the principal component analysis and factor analysis methods of unsupervised learning, the economic indicators of waste power plants are processed to form comprehensive scoring data, solving the problems of excessive indicators and complex correlation, and improving the operating efficiency and economicality of waste power plants .
Patent Information
- Application Number
- CN202410988339.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-15
AI Technical Summary
The economic indicators of waste power plants are too numerous, professional and complex, which makes it difficult for operators to pay full attention, resulting in inefficiency and inefficiency.
Unsupervised learning principal component analysis and factor analysis methods are used to standardize the economic indicator data of waste power plants and orthogonal linear changes to form comprehensive scoring data, reduce the number of indicators and eliminate the impact of units and orders of magnitude.
The number of economic indicators is reduced, information is retained, and quantifiable comprehensive scoring data is formed, which improves the efficiency of production personnel in judging changes in waste power plants, and eliminates the complexity of correlation between indicators.
Smart Images

Figure CN118966871A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of garbage power plants, and in particular to a method for calculating comprehensive operating economic indicators of garbage power plants. Background Art
[0002] At present, the comprehensive operation of garbage power plants mainly relies on various economic indicators as a judgment. Because the system of garbage power plants is complex, there are many economic indicators involved, including: power generation, power grid-connected power of power plants, garbage entering the plant, garbage processing, power consumption of garbage incineration plants, power consumption of each subsystem, power consumption of living, administrative and office, comprehensive power consumption, power consumption of the whole plant, power consumption on the Internet, power consumption rate of incineration plants, power consumption rate of combined plants, power consumption rate of the whole plant, power generation per ton of garbage, power grid-connected power per ton of garbage, steam production per ton of garbage, power consumption per ton of garbage, steam consumption rate of steam turbines, heat consumption rate of steam turbines, flue gas indicators, average utilization hours of power generation equipment, average utilization rate of power generation equipment, equipment maintenance rate, equipment integrity rate, equipment leakage rate, boiler main steam pressure P, boiler main steam temperature T , exhaust temperature, flue gas temperature at the outlet of the last stage flue of the waste heat boiler, cold air temperature, wind temperature of the air entering the air preheater inlet of the garbage bin, primary air temperature, cumulative steam production of the boiler, thermal burn-off rate, main steam temperature of the steam turbine, main steam pressure of the steam turbine, steam inlet amount of the steam turbine, condenser vacuum, vacuum degree, condenser end difference, condensate subcooling, circulating water inlet temperature ℃, feed water temperature ℃, boiler blowdown rate, steam-water loss rate, make-up water rate, feed water pump electricity consumption, circulating water pump power consumption rate, primary fan electricity consumption, secondary fan electricity consumption, induced draft fan electricity consumption, leachate treatment electricity consumption, water production electricity consumption, water consumption per ton of garbage, slag rate, fly ash rate, leachate rate, lime consumption, activated carbon consumption, heat load rate, mechanical load rate, acid consumption for water production, alkali consumption for water production and more than 60 other indicators.
[0003] Which is divided into:
[0004] 1. Direct operating indicators (direct parameters of equipment operation), including boiler main steam pressure P, boiler main steam temperature T, exhaust temperature, flue gas temperature at the outlet of the last flue of the waste heat boiler, cold air temperature, air temperature at the inlet of the air preheater of the garbage power plant, primary air temperature, boiler cumulative steam production, thermal burn-off rate, steam turbine main steam temperature, steam turbine main steam pressure, steam turbine steam inlet, condenser vacuum, vacuum degree, condenser end difference, condensate subcooling, circulating water inlet temperature ℃, feed water temperature ℃, etc.
[0005] 2. Indirect operating indicators (results of system operation), including power generation, power grid-connected power of power plants, power consumption of waste incineration plants, power consumption of each subsystem, power consumption of living, administrative and office use, comprehensive power consumption, power consumption of the entire plant, steam production per ton of waste, power consumption per ton of waste, steam consumption rate of steam turbines, heat consumption rate of steam turbines, etc.
[0006] These indicators are closely related to the operation of the waste power plant. Any change in any parameters will affect the subsequent operating indicators. For example, the main steam temperature and main steam pressure of the steam turbine will affect the power generation. There are also economic indicators that will affect each other, such as power generation and condenser terminal difference.
[0007] These traditional indicators can cause the following problems for operators, technicians, and managers:
[0008] 1. Too many indicators mean that production staff can only look at key indicators and cannot pay full attention.
[0009] 2. The indicators are highly professional, and operators, technicians, and managers can only look at individual indicators of their profession.
[0010] 3. The indicators are complexly correlated, and the indicators that operators, technicians, and managers are concerned about may cause inefficiency and uneconomical situations.
[0011] 4. There are too many indicator units, including kW.h, tons, %, mg / Nm3, ℃, MPa, MPa, etc.
[0012] 5. The indicators vary in magnitude, from single digits to tens of thousands or more. Summary of the invention
[0013] In view of the defects in the prior art, the purpose of the present invention is to provide a method for calculating the comprehensive operating economic indicators of a waste power plant, which can solve the five problems raised in the background technology.
[0014] In order to achieve the above object, the present invention is implemented by the following technical solution: a method for calculating the comprehensive operating economic indicators of a waste power plant, comprising the following steps:
[0015] S1. Arrange all economic indicator data of the waste power plant in time series, and determine the time granularity of each economic indicator data to form time series panel data;
[0016] S2. Standardizing the economic indicator data;
[0017] S3. The economic indicator data after standardization are processed by principal component analysis using unsupervised learning, and the principal component with the greatest explanatory power is retained to form a matrix;
[0018] S4, performing factor analysis on the matrix to obtain a comprehensive evaluation function;
[0019] S5. Substitute the economic indicator data into the comprehensive evaluation function to obtain comprehensive scoring data.
[0020] Furthermore, in step S2, the economic indicator data is standardized in a zero mean unit variance manner, and the algorithm for the standardization is:
[0021]
[0022] Among them, X normalized is the data after standardization; X is the original data; μ is the mean of the original data; σ is the standard deviation of the original data.
[0023] Furthermore, in step S3, the principal component analysis process includes: performing orthogonal linear transformation on each economic indicator data after standardization, and taking the maximum variance as the principal component.
[0024] Furthermore, the economic indicator data is extracted regularly according to the time granularity of the economic indicator data, and steps S2 to S5 are repeated to form the corresponding comprehensive scoring data.
[0025] Beneficial effects of the present invention:
[0026] 1. It can reduce the number of economic indicators of waste-to-energy plants, retain the information of economic indicator data to the greatest extent, and retain the reflection of actual production conditions.
[0027] 2. Form quantifiable comprehensive scoring data for waste-to-energy plants, which can tell production personnel the changes that have occurred in the waste-to-energy plants without the need for professional judgment one by one.
[0028] 3. The correlation between various indicators of the waste-to-energy plant is eliminated as much as possible, and is not affected by the units and magnitudes of the original economic indicator data of the waste-to-energy plant. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 It is a schematic diagram of the structure of time series panel data;
[0030] Figure 2 It is a schematic diagram of the structure of orthogonal linear changes;
[0031] Figure 3 Schematic diagram of the matrix formed for the principal components. DETAILED DESCRIPTION
[0032] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.
[0033] In this application, unless otherwise clearly specified and limited, the terms "connection" and "fixation" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0034] In the description of the present application, it should be understood that the terms "longitudinal", "lateral", "horizontal", "top", "bottom", "up", "down", "inside" and "outside" etc. indicating orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.
[0035] In addition, the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. In the description of the present invention, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.
[0036] like Figure 1-Figure 3 As shown, the present invention provides a method for calculating comprehensive operating economic indicators of a waste power plant, comprising the following steps:
[0037] S1. Sort out the economic indicator data of the waste power plant and arrange all the economic indicator data of the waste power plant in time series. At the same time, determine the time granularity of each economic indicator data: such as day, week, month, quarter, year, etc. Determine the time granularity of the economic indicator data according to needs to form time series panel data.
[0038] The time series panel data is as follows Figure 1 shown.
[0039] S2. Standardize the economic indicator data.
[0040] S3. Perform machine learning calculations on the standardized economic indicator data: Use unsupervised learning principal component analysis to retain the principal components with the greatest explanatory power to form a matrix.
[0041] S4, factor analysis is performed on the matrix to obtain a comprehensive evaluation function;
[0042] S5. Substitute the economic indicator data into the comprehensive evaluation function to obtain comprehensive scoring data.
[0043] In one embodiment, in step S2, the economic indicator data is standardized in a zero mean unit variance manner. The processing process is: calculate the mean and standard deviation of each economic indicator data, then subtract the mean from each economic indicator data and divide it by the standard deviation. The specific algorithm of the standardization process is:
[0044]
[0045] Among them, X normalized is the data after standardization; X is the original data; μ is the mean of the original data; σ is the standard deviation of the original data.
[0046] In one embodiment, in step S3, the principal component analysis process includes: performing orthogonal linear transformation on each economic indicator data after the standardization process. Since the maximum value of the variance contains the most information, the maximum value of the variance is taken as the principal component.
[0047] The orthogonal linear changes are as follows Figure 2 As shown, the matrix formed is as follows Figure 3 shown.
[0048] At this time, the factor analysis in step S4 is:
[0049] F1=0.4*X1+0.23*X2+0.18*X3+…0.005*X72+0.002*X73
[0050] Among them, 0.4, 0.23, 0.18…, 0.005, and 0.002 are automatically generated weights. Through analysis and judgment, all weights are positive, so F1 is used as the evaluation function of the waste power plant.
[0051] Among them, X1, X2, X3…X72, X73 are the economic indicator data represented by the corresponding project numbers.
[0052] In one embodiment, economic indicator data are periodically extracted according to the time granularity of the economic indicator data, and steps S2 to S5 are repeated to form corresponding comprehensive scoring data.
[0053] For example, if the waste-to-energy plant is evaluated by month:
[0054] 1. Arrange the economic indicator data for each day of January in chronological order and make the Figure 1 .
[0055] 2. According to step S2, the economic indicator data is standardized to converge into a coordinate system.
[0056] 3. According to step 3, perform principal component analysis on the standardized economic indicator data to generate the first few groups of principal components;
[0057] 4. According to step S4, factor analysis is performed on the matrix to obtain a comprehensive evaluation function.
[0058] The present invention can achieve the following technical effects:
[0059] 1. It can reduce the number of economic indicators of waste-to-energy plants, retain the information of economic indicator data to the greatest extent, and retain the reflection of actual production conditions.
[0060] 2. Form quantifiable comprehensive scoring data for waste-to-energy plants, which can tell production personnel the changes that have occurred in the waste-to-energy plants without the need for professional judgment one by one.
[0061] 3. The correlation between various indicators of the waste-to-energy plant is eliminated as much as possible, and is not affected by the units and magnitudes of the original economic indicator data of the waste-to-energy plant.
[0062] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention.
[0063] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.
Claims
1. A method for calculating comprehensive operating economic indicators of a waste-to-energy plant, characterized in that: The following steps are involved: S1. Arrange all economic indicator data of the waste power plant in time series, and determine the time granularity of each economic indicator data to form time series panel data; S2. Standardizing the economic indicator data; S3. The economic indicator data after standardization are processed by principal component analysis using unsupervised learning, and the principal component with the greatest explanatory power is retained to form a matrix; S4, performing factor analysis on the matrix to obtain a comprehensive evaluation function; S5. Substitute the economic indicator data into the comprehensive evaluation function to obtain comprehensive scoring data.
2. The method for calculating comprehensive operating economic indicators of a waste-to-energy plant according to claim 1, characterized in that: In step S2, the economic indicator data is standardized in a zero mean unit variance manner, and the algorithm for the standardization is: Among them, X normalized is the data after standardization; X is the original data; μ is the mean of the original data; σ is the standard deviation of the original data.
3. The method for calculating comprehensive operating economic indicators of a waste-to-energy plant according to claim 2, characterized in that: In step S3, the principal component analysis process includes: performing orthogonal linear transformation on each economic indicator data after the standardization process, and taking the maximum variance as the principal component.
4. The method for calculating comprehensive operating economic indicators of a waste-to-energy plant according to claim 3 is characterized by: According to the time granularity of the economic indicator data, the economic indicator data is extracted regularly, and steps S2 to S5 are repeated to form the corresponding comprehensive score data.
