A neural network energy-saving potential analysis platform based on energy consumption data

Abstract

The present invention relates to the field of energy-saving potential analysis platform, specifically a neural network energy-saving potential analysis platform based on energy consumption data, which includes a data layer, a business layer and a presentation layer; the data layer includes an energy consumption data acquisition module, a data storage module and a data classification module; the energy consumption data acquisition module is used to obtain the actual number of electric degrees used by the boiler, the total number of standard coal used and the actual power generation; the business layer includes a correction module, an energy-saving potential analysis module, a modeling module and a chart generation module; the correction module is used to correct the power generation C per standard coal; the energy-saving potential analysis module is used to calculate and analyze the energy-saving potential; the modeling module is used to establish a curve relationship model between time and energy-saving rate and predict subsequent trends. In the present invention, by correcting the power generation C per standard coal, the accuracy of the boiler energy-saving potential calculation is improved, and in addition, by modeling to predict the subsequent trend of energy-saving potential, it is convenient to avoid risks in advance.

Description

Technical Field

[0001] The present invention relates to the field of energy-saving potential analysis platforms, and in particular to a neural network energy-saving potential analysis platform based on energy consumption data. Background Art

[0002] The boiler used by the power plant to generate electricity is called the power station boiler. The energy consumption of the power station boiler is very large, so the current power station boilers are saving energy through various means. The current thermal power plant boilers often have the problem of low coal utilization rate and unclear energy-saving effect. It is necessary to analyze the energy consumption data of the thermal power plant boilers and calculate the energy-saving potential, so that the thermal power plant boilers can be repaired or replaced at any time to improve the energy utilization rate. The existing thermal power plant boiler energy-saving potential analysis is completed by comparing the theory with the actual use value over a period of time. The actual use value is only calculated by the average, and the calculation error is large. Because there are many influencing factors, such as the working environment temperature of the boiler, the boiler load rate and the use time (life) of the boiler, the calculation result is not accurate enough, and only the energy-saving potential analysis value in the current time period is provided. It is impossible to predict the subsequent energy-saving potential analysis trend and avoid risks in advance.

[0003] A Chinese patent with authorization announcement number CN114037297A discloses a method for analyzing the energy-saving potential of a thermal power plant boiler, comprising the following steps: obtaining the actual standard coal consumption per kilowatt-hour of the boiler A1, the coal consumption per kilowatt-hour of the boiler without taking any energy-saving measures B1, correcting B1 for the influence of load rate, ambient temperature and equipment use time, obtaining the actual power supply coal consumption after secondary correction, calculating the power generation per ton of coal of the generator set under normal circumstances C1, increasing the coal supply, the quantities of A2, A3 and A4 in sequence; obtaining the coal consumption B2, B3 and B4 under the adoption of energy-saving measures; calculating the power generation D1, D2 and D3 under the adoption of energy-saving measures; and calculating the energy-saving rate of the thermal power plant boiler.

[0004] However, the above-mentioned publicly available schemes have the following shortcomings: it is impossible to predict the trend of subsequent energy-saving potential analysis, and it is impossible to avoid risks or take relevant measures in advance. Summary of the invention

[0005] The purpose of the present invention is to address the problems existing in the background technology and to propose a neural network energy-saving potential analysis platform based on energy consumption data, which has accurate analysis results and can predict subsequent energy-saving potential trends.

[0006] On the one hand, the present invention proposes a neural network energy-saving potential analysis platform based on energy consumption data, including a data layer, a business layer and a presentation layer;

[0007] The data layer includes an energy data acquisition module, a data storage module and a data classification module; the energy data acquisition module is used to obtain the actual electricity used by the boiler, the total standard coal used and the actual power generation, and obtain the number of standard coal consumed per kilowatt-hour of electricity A, the power generation per standard coal under actual use C, the theoretical number of standard coal consumed per kilowatt-hour of electricity B and the theoretical power generation per standard coal D; the data storage module is used to store data; the data classification module is used to classify data according to pre-set classification rules;

[0008] The business layer includes a correction module, an energy-saving potential analysis module, a modeling module, and a chart generation module; the correction module is used to correct the power generation C per standard coal; the energy-saving potential analysis module is used to analyze the energy-saving potential, and the calculation formula of the energy-saving potential E is: The modeling module is used to establish a curve relationship model between time and energy saving rate, output a two-dimensional curve trend graph and predict subsequent trends; the chart generation module is used to generate a boiler energy saving rate E trend graph with prediction results and display it in the presentation layer;

[0009] The presentation layer includes a display module, which is used to display the calculation formula, calculation results and energy saving rate trend chart of the energy saving potential E.

[0010] Preferably, A=standard coal consumption / power consumption, C=actual power generation / total standard coal amount.

[0011] Preferably, the data stored in the data storage module includes the actual number of kilowatt-hours of electricity used by the boiler, the total number of standard coal used, the actual power generation, the number of standard coal consumed per kilowatt-hour of electricity A, the theoretical number of standard coal consumed per kilowatt-hour of electricity B provided by the manufacturer, the actual power generation per standard coal C and the theoretical power generation per standard coal D.

[0012] Preferably, the data classification module classifies the data according to the ambient temperature of the boiler, the boiler load rate and the boiler usage time.

[0013] Preferably, the correction module corrects the power generation C per standard coal according to the ambient temperature, boiler load rate and boiler use time, and the correction process is as follows:

[0014] S11. The total standard coal used and the actual power generation are classified according to different ambient temperature ranges. The actual power generation per standard coal in different ranges is recorded as C 11 , C 12 , C 13 ...C 1n , ambient temperature correction value

[0015] S12. The total standard coal used and the actual power generation are classified according to different boiler load rate ranges. The actual power generation per standard coal in different ranges is recorded as C 21 , C 22 , C 23 ...C 2n , boiler load factor correction value

[0016] S13. The total standard coal used and the actual power generation are classified according to different boiler use time ranges. The actual power generation per standard coal in different ranges is recorded as C 31 , C 32 , C 33 ...C 3n , boiler usage time correction value

[0017] S14. The correction formula for power generation C per standard coal is:

[0018] Preferably, the modeling module is used to establish a curve relationship model between time and energy saving rate, and the boiler energy saving rate E is calculated once in each time period T, and each time period is recorded as T1, T2, T3...T n , and obtain multiple sets of energy saving rate data E1, E2, E3...E n , forming multiple sets of two-dimensional coordinates (T1, E1), (T2, E2), (T3, E3)...(T n , E n ); construct a boiler energy saving rate E trend chart, with the horizontal axis being time T and the vertical axis being the boiler energy saving rate E; construct a subsequent trend equation based on the current trend chart and predict the subsequent curve trend, with the subsequent curve trend represented by a dotted line.

[0019] Preferably, the energy-saving potential E is greater than 2, indicating that the boiler has an energy-saving effect, and the larger the value, the greater the energy-saving potential.

[0020] On the other hand, the present invention proposes an energy saving potential analysis method based on a neural network energy saving potential analysis platform of energy consumption data, comprising the following steps:

[0021] S21, obtaining the actual electricity used by the boiler, the total amount of standard coal used and the actual power generation;

[0022] S22, calculate the amount of standard coal consumed per kilowatt-hour of electricity A and the power generation per standard coal in actual use C, and obtain the theoretical amount of standard coal consumed per kilowatt-hour of electricity B and the theoretical power generation per standard coal D from the boiler manufacturer;

[0023] S23, correcting the power generation C per standard coal;

[0024] S24. Analyze the energy saving potential. The calculation formula of energy saving potential E is:

[0025] S25. Establish a curve relationship model between time T and energy saving rate E, output a curve trend chart and predict subsequent trends, generate a boiler energy saving rate E trend chart with prediction results, and display it in the presentation layer.

[0026] Compared with the prior art, the present invention has the following beneficial technical effects: by correcting the power generation C per standard coal, the influence of the working environment temperature of the boiler, the boiler load rate and the use time of the boiler on the calculation result is reduced, thereby improving the accuracy of the calculation of the boiler energy-saving potential. In addition, through modeling, the subsequent trend of the energy-saving potential is predicted, which provides a reference for the follow-up, facilitates timely maintenance or replacement of the boiler, and can avoid risks in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of the structure of an embodiment of the present invention;

[0028] Figure 2 The revised flow chart of power generation C per standard coal;

[0029] Figure 3 It is the curve trend chart of energy saving rate E;

[0030] Figure 4 Flow chart of the energy saving potential analysis method. DETAILED DESCRIPTION

[0031] Embodiment 1

[0032] like Figure 1 As shown, the present invention proposes a neural network energy-saving potential analysis platform based on energy consumption data, including a data layer, a business layer and a presentation layer;

[0033] The data layer includes an energy data acquisition module, a data storage module and a data classification module; the energy data acquisition module is used to obtain the actual number of kilowatt-hours of electricity used by the boiler, the total number of standard coal used and the actual power generation, and obtain the number of standard coal consumed per kilowatt-hour of electricity A, the power generation per standard coal under actual use C, the theoretical number of standard coal consumed per kilowatt-hour of electricity B and the theoretical power generation per standard coal D, A = standard coal consumption / power consumption, C = actual power generation / total number of standard coal; the data storage module is used to store data, including the actual number of kilowatt-hours of electricity used by the boiler, the total number of standard coal used, the actual power generation, the number of standard coal consumed per kilowatt-hour of electricity A, the theoretical number of standard coal consumed per kilowatt-hour of electricity provided by the manufacturer B, the actual power generation per standard coal C and the theoretical power generation per standard coal D; the data classification module classifies the data according to the ambient temperature of the boiler, the boiler load rate and the boiler usage time;

[0034] The business layer includes a correction module, an energy-saving potential analysis module, a modeling module, and a chart generation module; the correction module is used to correct the power generation C per standard coal; the energy-saving potential analysis module is used to analyze the energy-saving potential, and the calculation formula of the energy-saving potential E is: If the energy-saving potential E is greater than 2, it means that the boiler has energy-saving effect, and the larger the value, the greater the energy-saving potential; the modeling module is used to establish a curve relationship model between time and energy-saving rate, output a two-dimensional curve trend graph and predict subsequent trends; the chart generation module is used to generate a boiler energy-saving rate E trend graph with prediction results and display it in the presentation layer;

[0035] The presentation layer includes a display module, which is used to display the calculation formula, calculation results and energy saving rate trend chart of the energy saving potential E.

[0036] In this embodiment, the actual number of kilowatt-hours of electricity used by the boiler, the total number of standard coals used, and the actual power generation are obtained, and the number of standard coals consumed per kilowatt-hour of electricity and the power generation per standard coal under actual use are calculated. The theoretical number of standard coals consumed per kilowatt-hour of electricity and the theoretical power generation per standard coal D are obtained from the boiler manufacturer, and the power generation per standard coal C is corrected. The energy-saving potential is analyzed, and the calculation formula of the energy-saving potential E is: A curve relationship model between time T and energy saving rate E is established, a curve trend chart is output and subsequent trends are predicted, a boiler energy saving rate E trend chart with predicted results is generated, and displayed in the presentation layer. In this embodiment, by correcting the power generation C per standard coal, the influence of the working environment temperature of the boiler, the boiler load rate and the use time of the boiler on the calculation results is reduced, and the accuracy of the boiler energy saving potential calculation is improved. In addition, through modeling, the subsequent trend of energy saving potential is predicted, which provides a reference for the subsequent maintenance or replacement of the boiler, and can avoid risks in advance.

[0037] Embodiment 2

[0038] like Figure 2 As shown, the present invention proposes a neural network energy-saving potential analysis platform based on energy consumption data. Compared with the first embodiment, the correction module corrects the power generation C per standard coal according to the ambient temperature, boiler load rate and boiler use time. The correction process is as follows:

[0039] S11. The total standard coal used and the actual power generation are classified according to different ambient temperature ranges. The actual power generation per standard coal in different ranges is recorded as C 11 , C 12 , C 13 ...C 1n , ambient temperature correction value

[0040] S12. The total standard coal used and the actual power generation are classified according to different boiler load rate ranges. The actual power generation per standard coal in different ranges is recorded as C 21 , C 22 , C 23 ...C 2n , boiler load factor correction value

[0041] S13. The total standard coal used and the actual power generation are classified according to different boiler use time ranges. The actual power generation per standard coal in different ranges is recorded as C 31 , C 32 , C 33 ...C 3n , boiler usage time correction value

[0042] S14. The correction formula for power generation C per standard coal is:

[0043] In this embodiment, the power generation C per standard coal is corrected based on the ambient temperature, boiler load rate and boiler use time, so as to improve the accuracy of energy saving potential calculation.

[0044] Embodiment 3

[0045] like Figure 3 As shown, the present invention proposes a neural network energy-saving potential analysis platform based on energy consumption data. Compared with the first embodiment, the modeling module is used to establish a curve relationship model between time and energy-saving rate. The boiler energy-saving rate E is calculated once in each time period T, and each time period is recorded as T1, T2, T3...T n , and obtain multiple sets of energy saving rate data E1, E2, E3...E n , forming multiple sets of two-dimensional coordinates (T1, E1), (T2, E2), (T3, E3)...(T n , E n ); construct a boiler energy saving rate E trend chart, with the horizontal axis being time T and the vertical axis being the boiler energy saving rate E; construct a subsequent trend equation based on the current trend chart and predict the subsequent curve trend, with the subsequent curve trend represented by a dotted line.

[0046] In this embodiment, the energy-saving potential trend of the boiler can be intuitively seen through the constructed two-dimensional trend chart. Combined with the predicted subsequent trend, the boiler can be repaired or replaced before the energy-saving potential drops to the expected value, so as to avoid risks in advance.

[0047] Embodiment 4

[0048] like Figure 4As shown, the energy saving potential analysis method based on the above-mentioned embodiment of the neural network energy saving potential analysis platform based on energy consumption data includes the following steps:

[0049] S21, obtaining the actual electricity used by the boiler, the total amount of standard coal used and the actual power generation;

[0050] S22, calculate the amount of standard coal consumed per kilowatt-hour of electricity A and the power generation per standard coal in actual use C, and obtain the theoretical amount of standard coal consumed per kilowatt-hour of electricity B and the theoretical power generation per standard coal D from the boiler manufacturer;

[0051] S23, correcting the power generation C per standard coal;

[0052] S24. Analyze the energy saving potential. The calculation formula of energy saving potential E is:

[0053] S25. Establish a curve relationship model between time T and energy saving rate E, output a curve trend chart and predict subsequent trends, generate a boiler energy saving rate E trend chart with prediction results, and display it in the presentation layer.

[0054] In this embodiment, by correcting the power generation C per standard coal, the influence of the working environment temperature of the boiler, the boiler load rate and the use time of the boiler on the calculation result is reduced, thereby improving the accuracy of the calculation of the boiler energy-saving potential. In addition, through modeling, the subsequent trend of the energy-saving potential is predicted, which provides a reference for the follow-up, facilitates timely maintenance or replacement of the boiler, and can avoid risks in advance.

[0055] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto, and various changes can be made within the knowledge scope of technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A neural network energy-saving potential analysis platform based on energy consumption data, characterized in that: Includes data layer, business layer and presentation layer; The data layer includes an energy data acquisition module, a data storage module, and a data classification module; the energy data acquisition module is used to obtain the actual electricity used by the boiler, the total standard coal used, and the actual power generation, and obtain the number of standard coal consumed per kilowatt-hour of electricity A, the power generation per standard coal under actual use C, the theoretical number of standard coal consumed per kilowatt-hour of electricity B, and the theoretical power generation per standard coal D; The data storage module is used to store data; the data classification module is used to classify data according to pre-set classification rules; The business layer includes the correction module, energy saving potential analysis module, modeling module and chart generation module; The correction module is used to correct the power generation C per standard coal; the energy-saving potential analysis module is used to analyze the energy-saving potential. The calculation formula of the energy-saving potential E is: The modeling module is used to establish a curve relationship model between time and energy saving rate, output a two-dimensional curve trend graph and predict subsequent trends; the chart generation module is used to generate a boiler energy saving rate E trend graph with prediction results and display it in the presentation layer; The presentation layer includes a display module, which is used to display the calculation formula, calculation results and energy saving rate trend chart of the energy saving potential E.

2. The neural network energy saving potential analysis platform based on energy consumption data according to claim 1 is characterized in that: A = standard coal consumption / power consumption, C = actual power generation / total standard coal consumption.

3. The neural network energy saving potential analysis platform based on energy consumption data according to claim 1 is characterized in that: The data stored in the data storage module include the actual electricity used by the boiler, the total amount of standard coal used, the actual power generation, the amount of standard coal consumed per kilowatt-hour of electricity A, the theoretical amount of standard coal consumed per kilowatt-hour of electricity B provided by the manufacturer, the actual power generation per standard coal C and the theoretical power generation per standard coal D.

4. The neural network energy saving potential analysis platform based on energy consumption data according to claim 1 is characterized in that: The data classification module classifies the data according to the ambient temperature of the boiler, the boiler load rate and the boiler usage time.

5. The neural network energy saving potential analysis platform based on energy consumption data according to claim 1 is characterized in that: The correction module corrects the power generation C per standard coal according to the ambient temperature, boiler load rate and boiler use time. The correction process is as follows: S11. The total standard coal used and the actual power generation are classified according to different ambient temperature ranges. The actual power generation per standard coal in different ranges is recorded as C 11 , C 12 , C 13 ...C 1n , ambient temperature correction value S12. The total standard coal used and the actual power generation are classified according to different boiler load rate ranges. The actual power generation per standard coal in different ranges is recorded as C 21 , C 22 , C 23 ...C 2n , boiler load factor correction value S13. The total standard coal used and the actual power generation are classified according to different boiler use time ranges. The actual power generation per standard coal in different ranges is recorded as C 31 , C 32 , C 33 ...C 3n , boiler usage time correction value S14. The correction formula for power generation C per standard coal is:

6. The neural network energy saving potential analysis platform based on energy consumption data according to claim 1 is characterized in that: The modeling module is used to establish a curve relationship model between time and energy saving rate. The boiler energy saving rate E is calculated once in each time period T. Each time period is recorded as T1, T2, T3...T n , and obtain multiple sets of energy saving rate data E1, E2, E3...E n , forming multiple sets of two-dimensional coordinates (T1, E1), (T2, E2), (T3, E3)...(T n , E n ); construct a boiler energy saving rate E trend chart, with the horizontal axis being time T and the vertical axis being the boiler energy saving rate E; construct a subsequent trend equation based on the current trend chart and predict the subsequent curve trend, with the subsequent curve trend represented by a dotted line.

7. The neural network energy saving potential analysis platform based on energy consumption data according to claim 1 is characterized in that: If the energy-saving potential E is greater than 2, it means that the boiler has energy-saving effect, and the larger the value, the greater the energy-saving potential.

8. An energy saving potential analysis method based on a neural network energy saving potential analysis platform based on energy consumption data according to claim 1, characterized in that: The following steps are involved: S21, obtaining the actual electricity used by the boiler, the total amount of standard coal used and the actual power generation; S22, calculate the amount of standard coal consumed per kilowatt-hour of electricity A and the power generation per standard coal in actual use C, and obtain the theoretical amount of standard coal consumed per kilowatt-hour of electricity B and the theoretical power generation per standard coal D from the boiler manufacturer; S23, correcting the power generation C per standard coal; S24. Analyze the energy saving potential. The calculation formula of energy saving potential E is: S25. Establish a curve relationship model between time T and energy saving rate E, output a curve trend chart and predict subsequent trends, generate a boiler energy saving rate E trend chart with prediction results, and display it in the presentation layer.

Images