Gas supply peak regulation management system and method based on big data analysis

Through big data analysis and predicting gas demand and turning on backup equipment, the problem of severe load fluctuations in gas boilers during peak hours is solved, and a faster and balanced gas supply and peak-shaving management is achieved to avoid waste of resources.

CN119090230APending Publication Date: 2024-12-06SHANGHAI BOILER WORKS CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411260840.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-09
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing gas boiler peak regulating control system fluctuates violently during peak peaks, and the response speed is limited and cannot be adjusted quickly, resulting in waste of resources and unbalanced equipment load.

Method used

Adopt the gas supply peak-shaving management system based on big data analysis, and through the data acquisition module, the fusion data analysis module and the threshold setting module, a linear regression model is established to predict the gas demand at peak, and the backup equipment is turned on according to the predicted value to ensure gas supply. adequate.

Benefits of technology

It improves the response speed of gas boilers during peak hours, avoids waste of resources, ensures the load balance of the main equipment, and reduces unnecessary loads for equipment operation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090230A_ABST
    Figure CN119090230A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of air supply management, in particular to an air supply peak regulation management system and method based on big data analysis, and the system comprises a data collection module, a fusion data analysis module and a threshold setting module. The data acquisition module is used for acquiring operation data during gas supply of a main equipment boiler; the fusion data analysis module is used for fusing the historical database and the gas supply data into a linear regression model, and performing prediction by using the linear regression model; the threshold value setting module is used for tracking a boiler gas demand quantity value during boiler gas supply peak regulation, and when the value exceeds a set threshold value, standby equipment needs to be started; according to the method, the fuel gas demand quantity during the peak period of the boiler is predicted through model establishment, the situation that the main equipment boiler operates in a load mode due to the fact that the fuel gas demand quantity is not predicted during the peak period of gas supply is avoided, the standby equipment is accurately started under the load operation of the main equipment boiler, and the operation state of the boiler during peak regulation is rapidly adapted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of gas supply management, and in particular to a gas supply peak-shaving management system and method based on big data analysis. Background Art

[0002] A gas boiler is a device that generates heat energy by burning natural gas, liquefied petroleum gas (LPG) or other gaseous fuels. Its main function is to convert the chemical energy in the fuel into heat energy and output it to the system that needs heating or heat energy production in the form of steam or hot water. Gas boilers are widely used in industrial production, commercial buildings, residential heating and other scenarios that require heat energy.

[0003] Boiler plants often use gas as fuel, but due to load, fuel volume, and external factors, the boiler will run at full load to meet demand during peak hours, and will operate at a reduced load during off-peak hours. Boiler plants generally use multiple devices to provide resources. If peak-shaving measures are not taken, it may lead to waste of resources and insufficient gas supply and equipment failure to operate normally. During peak hours, backup equipment is often used to share the load according to the load of the boiler, and the equipment does not operate during off-peak hours. The existing automatic control system (PLC) automatically starts and stops the backup boiler according to the operating status of the main boiler and the load demand, but this control is only used to process deterministic and pre-set tasks. The response speed of the PLC is limited by its processing capacity. During peak hours, the load fluctuates violently and cannot respond quickly, which affects the peak-shaving effect of the system. The system introduces data delays and is not sensitive enough to peak-shaving applications with high real-time requirements. Summary of the invention

[0004] The purpose of the present invention is to provide a patent name to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a gas supply peak-shaving management system based on big data analysis, the management system comprising a data acquisition module, a fusion data analysis module, and a threshold setting module;

[0006] The data acquisition module is used to collect the operation data of the main equipment boiler when supplying gas, calculate the basic heat load demand of the boiler according to the operation data, and calculate the gas demand of the boiler according to the basic heat load data of the boiler;

[0007] The fusion data analysis module is used to fuse the heat load value, gas demand, and pressure value of the boiler in the historical data with the heat load value, gas demand, and pressure value of the boiler in the real-time data during gas supply, establish a linear regression model, and use the fused linear regression model to predict the gas demand during peak hours;

[0008] The threshold setting module is used to compare the peak gas demand predicted by the linear regression model with the set gas demand threshold, and when the gas demand value exceeds the set threshold, the backup equipment is turned on;

[0009] The data acquisition module includes a data acquisition unit and a data processing unit; the data acquisition unit is used to collect gas pipe network data during gas supply, and the gas pipe network data includes: the flow rate of gas in the pipe network, the volume of heated fluid, and the temperature difference between the air inlet and the air outlet of the gas supply pipeline; the data processing unit is used to receive the gas pipe network data during boiler gas supply, and calculate the boiler load demand and gas demand according to the received gas pipe network data;

[0010] The fusion data analysis module includes a storage unit and a data analysis unit; the storage unit is used to store the thermal load of the boiler, the gas demand and the pressure value inside the boiler during gas supply; the data analysis unit is used to fuse the real-time data and the historical data, and predict the gas demand of the boiler according to the linear regression model;

[0011] The threshold setting module includes a threshold model unit and a data comparison unit; the threshold model unit is used to determine whether the gas demand in the boiler has reached a peak based on the predicted gas demand in the boiler, and set the threshold at the same time; the data comparison unit is used to compare the gas demand in the boiler at the peak and the size of the set threshold.

[0012] A gas supply peak-shaving management method based on big data analysis, the method comprising the following steps:

[0013] Step S1, collecting the operation data of the main equipment boiler when supplying gas, the operation data including the flow rate of gas in the pipe network, the volume of fluid heated in the boiler, the air inlet temperature of the gas supply pipeline, the air outlet temperature of the gas supply pipeline, the specific heat capacity of the fluid, the calorific value of the gas and the thermal efficiency of the boiler, calculating the basic heat load demand of the boiler according to the operation data, and calculating the gas demand of the boiler according to the basic heat load data of the boiler;

[0014] Step S1 also includes:

[0015] Step S101, installing an ultrasonic transmitter and an ultrasonic receiver on the outer surface of the gas supply pipe, wherein the ultrasonic receiver is used to receive a pulse signal from the ultrasonic transmitter;

[0016] Step S102: The ultrasonic transmitter sends out a pulse signal, which propagates in the fluid and is received by the ultrasonic receiver. The propagation time of the ultrasonic wave in the downstream and upstream directions is obtained, and the flow velocity Vt of the gas in the pipe network is calculated according to the difference in propagation time. The calculation formula is as follows:

[0017] Vt=[(t2-t1)÷(t1+t2)]×(D÷2)

[0018] Where D is the distance between sensors, t1 is the propagation time in the downstream direction, and t2 is the propagation time in the upstream direction;

[0019] The gas flow rate is used to calculate the fluid volume V. The calculation formula is as follows:

[0020] V=Vt×A×(ta-tb)

[0021] Wherein, Vt represents the flow velocity, A represents the cross-sectional area through which the fluid passes, ta represents the time when the boiler's gas supply reaches its peak, and tb represents the time when the boiler starts to supply gas;

[0022] Step S103, temperature sensors are installed at the air inlet and the air outlet of the air supply pipeline respectively, and the temperature sensors are used to collect the air inlet temperature of the air supply pipeline and the air outlet temperature of the air supply pipeline. The temperature difference ΔT of the gas flowing in the air supply pipeline is calculated according to the air inlet temperature Tin and the air outlet temperature Tout. The calculation formula is as follows:

[0023] △T=Tin-Tout

[0024] Among them, △T represents the temperature difference of the gas, Tin represents the inlet temperature when the pipeline is supplied with gas from the boiler, and Tout represents the outlet temperature when the pipeline is supplied with gas from the boiler;

[0025] Step S104: Install a pressure sensor on the boiler to measure the pressure value P, calculate the basic heat load demand Qdemand by multiplying the heated fluid volume V, the temperature difference ΔT and the fluid specific heat capacity Cp, and calculate the gas demand Qgas using the following formula:

[0026] Qdemand=V×△T×Cp

[0027] Qgas=Qdemand÷(η×GCV)

[0028] Where Qdemand represents the heat load demand of the boiler during peak load regulation, V represents the volume of the fluid to be heated, △T represents the required temperature increase, Cp represents the specific heat capacity of the fluid, Qgas represents the gas demand, η represents the thermal efficiency of the boiler, and GCV represents the calorific value of the gas.

[0029] Step S2, recording the calculated heat load value, gas demand, and pressure value of the boiler, obtaining historical operation data of the main equipment boiler and the standby boiler, marking the event of starting the standby equipment boiler when the main equipment boiler reaches the peak in the historical operation data as a historical target event, obtaining the heat load value, gas demand, and pressure value of the main equipment boiler when it reaches the peak in the historical target event and recording them as a historical array, establishing real-time data based on the recorded heat load value, gas demand, and pressure value of the boiler, integrating the real-time data with the data in the historical database, and establishing a linear regression model, wherein the linear regression model is used to predict the gas demand in the boiler at the peak;

[0030] Step S2 also includes:

[0031] Step S201, extracting data during the peak gas supply period from a historical database, wherein the historical data includes historical heat load, historical gas demand, and historical pressure data;

[0032] The collected historical heat load data forms a historical heat load set: L t-Δt ={L t-1 , L t-2 , L t-3 ...}; The collected historical gas demand data forms a historical gas demand set: Q gas-Δt = {Q gas-1 , Q gas-2 , Q gas-3 ......}; The collected historical pressure data forms a historical pressure set: P t-Δt = {P t-1 , P t-2 , P t-3 ......};

[0033] Combine multiple groups of historical data for integration and take the average value to obtain a historical data set A linear regression model is established by integrating real-time data and historical data sets to obtain the target variable, which is the predicted boiler gas consumption Qt. The linear regression model calculation formula is as follows:

[0034]

[0035] Where Qt represents the predicted boiler gas demand, Represents the mean of multiple groups of historical heat load data, Represents the mean of multiple groups of historical gas demand data, represents the mean of multiple groups of historical pressure data, α1, α2, α3, β are model parameters;

[0036] Step S3, according to the peak gas demand predicted by the linear regression model, a threshold value is set, and the threshold value is set as the gas demand threshold. When the gas demand of the main boiler equipment during peak operation exceeds the set gas demand threshold, the standby equipment boiler is turned on.

[0037] Step S3 also includes:

[0038] Step S301: Calculate the peak gas demand Qpeak and the off-peak gas demand Qoff-peak according to the predicted boiler gas demand Qt. The calculation formula is as follows:

[0039] Qpeak=max(Qt)

[0040] Qoff-peak=min(Qt)

[0041] Among them, Qpeak represents the gas demand during peak hours, Qoff-peak represents the gas demand during off-peak hours, Qt represents the predicted boiler gas demand, max represents the maximum value, and min represents the minimum value;

[0042] Step S302: Establish a threshold model and set a gas demand threshold Dpeak. The calculation formula is as follows:

[0043] Dpeak=(Qpeak-Qoff-peak)÷△t

[0044] Among them, Dpeak represents the gas demand threshold at peak time, Qpeak represents the gas demand at peak time, Qoff-peak represents the gas demand of the boiler at off-peak time, and △t represents the time change from the gas demand of the boiler at off-peak time to the gas demand of the boiler at peak time;

[0045] Step S303: When the real-time gas demand Qgas in the boiler is greater than the peak gas demand threshold Dpeak, the main device is overloaded and the backup device is turned on; when Qgas is less than Dpeak, the main device operates normally and the backup device is shut down and not enabled.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention can solve the problem that when the gas volume of the boiler reaches a peak, the load fluctuates violently, the system cannot respond quickly, and can only process deterministic and pre-set tasks. By collecting the gas demand of the boiler and the gas network supply capacity data, the linear regression model is established by integrating historical data. The gas demand at the peak in the boiler is predicted by the model, which avoids the waste of resources and the load operation of the main equipment boiler due to the failure to predict the gas demand during the peak gas supply period. At the same time, by comparing the predicted data with the established threshold model, the standby equipment boiler is accurately started. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a structural schematic diagram of a gas supply peak-shaving management system based on big data analysis of the present invention;

[0049] Figure 2 It is a flow chart of a gas supply peak-shaving management method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] Example 1, please refer to Figure 1 ,The present invention provides a technical solution: a gas supply peak-shaving management system based on big data analysis, the system comprising a system architecture module, a fusion data analysis module and a threshold setting module;

[0052] The data acquisition module is used to collect the operation data of the main equipment boiler when supplying gas, calculate the basic heat load demand of the boiler according to the operation data, and calculate the gas demand of the boiler according to the basic heat load data of the boiler;

[0053] The fusion data analysis module is used to fuse the heat load value, gas demand, and pressure value of the boiler in the historical data with the heat load value, gas demand, and pressure value of the boiler in the real-time data during gas supply, establish a linear regression model, and use the fused linear regression model to predict the gas demand during peak hours;

[0054] The threshold setting module is used to compare the peak gas demand predicted by the linear regression model with the set gas demand threshold, and when the gas demand value exceeds the set threshold, the backup equipment is turned on;

[0055] The data acquisition module includes a data acquisition unit and a data processing unit; the data acquisition unit is used to collect gas pipe network data during gas supply, and the gas pipe network data includes: the flow rate of gas in the pipe network, the volume of heated fluid, and the temperature difference between the air inlet and the air outlet of the gas supply pipeline; the data processing unit is used to receive the gas pipe network data during boiler gas supply, and calculate the boiler load demand and gas demand according to the received gas pipe network data;

[0056] The fusion data analysis module includes a storage unit and a data analysis unit; the storage unit is used to store the thermal load of the boiler, the gas demand and the pressure value inside the boiler during gas supply; the data analysis unit is used to fuse the real-time data and the historical data, and predict the gas demand of the boiler according to the linear regression model;

[0057] The threshold setting module includes a threshold model unit and a data comparison unit; the threshold model unit is used to determine whether the gas demand in the boiler has reached a peak based on the predicted gas demand in the boiler, and set the threshold at the same time; the data comparison unit is used to compare the gas demand in the boiler at the peak and the size of the set threshold.

[0058] Example 2, please refer to Figure 2 , a gas supply peak-shaving management method based on big data analysis, the method comprising the following steps:

[0059] Step S1, collecting the operation data of the main equipment boiler when supplying gas, the operation data including the flow rate of gas in the pipe network, the volume of fluid heated in the boiler, the air inlet temperature of the gas supply pipeline, the air outlet temperature of the gas supply pipeline, the specific heat capacity of the fluid, the calorific value of the gas and the thermal efficiency of the boiler, calculating the basic heat load demand of the boiler according to the operation data, and calculating the gas demand of the boiler according to the basic heat load data of the boiler;

[0060] Step S1 also includes:

[0061] Step S101, installing an ultrasonic transmitter and an ultrasonic receiver on the outer surface of the gas supply pipe, wherein the ultrasonic receiver is used to receive a pulse signal from the ultrasonic transmitter;

[0062] Step S102: The ultrasonic transmitter sends out a pulse signal, which propagates in the fluid and is received by the ultrasonic receiver. The propagation time of the ultrasonic wave in the downstream and upstream directions is obtained, and the flow velocity Vt of the gas in the pipe network is calculated according to the difference in propagation time. The calculation formula is as follows:

[0063] Vt=[(t2-t1)÷(t1+t2)]×(D÷2)

[0064] Where D is the distance between sensors, t1 is the propagation time in the downstream direction, and t2 is the propagation time in the upstream direction;

[0065] Set the propagation time t1 of the ultrasonic pulse signal in the downstream direction to 0.010s, the propagation time t2 of the ultrasonic pulse signal in the upstream direction to 0.015s, and the pipe length to 1m. The calculation formula is as follows:

[0066] Vt=[(t2-t1)÷(t1+t2)]×(D÷2)=[(0.015-0.010)÷(0.015+0.010)]×0.5=0.1m / s

[0067] The gas flow rate is used to calculate the fluid volume V. The calculation formula is as follows:

[0068] V=Vt×A×(ta-tb)

[0069] Wherein, Vt represents the flow velocity, A represents the cross-sectional area through which the fluid passes, ta represents the time when the boiler's gas supply reaches its peak, and tb represents the time when the boiler starts to supply gas;

[0070] Assume that the cross-sectional area through which the fluid flows is 0.05m 3 , from the start of gas supply to the peak of gas supply is 0.5h = 3600s, the calculation formula is as follows:

[0071] V=Vt×A×(ta-tb)=0.1×0.05×0.5×3600=9m 3

[0072] Step S103, temperature sensors are installed at the air inlet and the air outlet of the air supply pipeline respectively, and the temperature sensors are used to collect the air inlet temperature of the air supply pipeline and the air outlet temperature of the air supply pipeline. The temperature difference ΔT of the gas flowing in the air supply pipeline is calculated according to the air inlet temperature Tin and the air outlet temperature Tout. The calculation formula is as follows:

[0073] △T=Tin-Tout

[0074] Among them, △T represents the temperature difference of the gas, Tin represents the inlet temperature when the pipeline is supplied with gas from the boiler, and Tout represents the outlet temperature when the pipeline is supplied with gas from the boiler;

[0075] When the inlet temperature Tin is 25°C and the outlet temperature Tout is 15°C, the calculation formula is as follows:

[0076] △T=Tin-Tout=25-15=10℃

[0077] Step S104: Install a pressure sensor on the boiler to measure the pressure value P, calculate the basic heat load demand Qdemand by multiplying the heated fluid volume V, the temperature difference ΔT and the fluid specific heat capacity Cp, and calculate the gas demand Qgas using the following formula:

[0078] Qdemand=V×△T×Cp

[0079] Qgas=Qdemand÷(η×GCV)

[0080] Where Qdemand represents the heat load demand of the boiler during peak load regulation, V represents the volume of the fluid to be heated, △T represents the required temperature increase, Cp represents the specific heat capacity of the fluid, Qgas represents the gas demand, η represents the thermal efficiency of the boiler, and GCV represents the calorific value of the gas.

[0081] It is known that the specific heat capacity of the fluid Cp is 2.15 kJ / (kg·℃), and the high calorific value GCV of the gas (natural gas) is 35000 kJ / m 3 Calculate the gas demand according to the formula:

[0082] Qdemand=V×△T×Cp=9×10×2.15=193.5

[0083] Qgas=Qdemand÷(η×GCV)=193.5÷(0.85×35000)=0.0065m 3

[0084] Step S2, recording the calculated heat load value, gas demand, and pressure value of the boiler, obtaining historical operation data of the main equipment boiler and the standby boiler, marking the event of starting the standby equipment boiler when the main equipment boiler reaches the peak in the historical operation data as a historical target event, obtaining the heat load value, gas demand, and pressure value of the main equipment boiler when it reaches the peak in the historical target event and recording them as a historical array, establishing real-time data based on the recorded heat load value, gas demand, and pressure value of the boiler, integrating the real-time data with the data in the historical database, and establishing a linear regression model, wherein the linear regression model is used to predict the gas demand in the boiler at the peak;

[0085] Step S2 also includes:

[0086] Step S201, extracting data during the peak gas supply period from a historical database, wherein the historical data includes historical heat load, historical gas demand, and historical pressure data;

[0087] The collected historical heat load data forms a historical heat load set: L t-Δt ={L t-1 , Lt-2 , L t-3 ...}; The collected historical gas demand data forms a historical gas demand set: Q gas-Δt = {Q gas-1 , Q gas-2 , Q gas-3 ......}; The collected historical pressure data forms a historical pressure set: P t-Δt = {P t-1 , P t-2 , P t-3 ......};

[0088] Combine multiple groups of historical data for integration and take the average value to obtain a historical data set A linear regression model is established by integrating real-time data and historical data sets to obtain the target variable, which is the predicted boiler gas consumption Qt. The linear regression model calculation formula is as follows:

[0089]

[0090] Where Qt represents the predicted boiler gas demand, Represents the mean of multiple groups of historical heat load data, Represents the mean of multiple groups of historical gas demand data, represents the mean of multiple groups of historical pressure data, α1, α2, α3, β are model parameters;

[0091] Step S3, according to the peak gas demand predicted by the linear regression model, a threshold value is set, and the threshold value is set as the gas demand threshold. When the gas demand of the main boiler equipment during peak operation exceeds the set gas demand threshold, the standby equipment boiler is turned on.

[0092] Step S3 also includes:

[0093] Step S301: Calculate the peak gas demand Qpeak and the off-peak gas demand Qoff-peak according to the predicted boiler gas demand Qt. The calculation formula is as follows:

[0094] Qpeak=max(Qt)

[0095] Qoff-peak=min(Qt)

[0096] Among them, Qpeak represents the gas demand during peak hours, Qoff-peak represents the gas demand during off-peak hours, Qt represents the predicted boiler gas demand, max represents the maximum value, and min represents the minimum value;

[0097] Step S302: Establish a threshold model and set a gas demand threshold Dpeak. The calculation formula is as follows:

[0098] Dpeak=(Qpeak-Qoff-peak)÷△t

[0099] Among them, Dpeak represents the gas demand threshold at peak time, Qpeak represents the gas demand at peak time, Qoff-peak represents the gas demand of the boiler at off-peak time, and △t represents the time change from the gas demand of the boiler at off-peak time to the gas demand of the boiler at peak time;

[0100] Step S303: When the real-time gas demand Qgas in the boiler is greater than the peak gas demand threshold Dpeak, the main device is overloaded and the backup device is turned on; when Qgas is less than Dpeak, the main device operates normally and the backup device is shut down and not enabled.

[0101] Assume that a set of historical heat load data {L t-1 , L t-2 , L t-3}={1500, 2000, 2500}, historical gas demand data {Q gas-1 , Q gas-2 , Q gas-3}={200, 250, 300}, historical pressure data {P t-1 , P t-2 , P t-3} = {5.1, 5.2, 5.3}, the average value is Assuming the model α1=1,α2=2,α3=3,β=10, the following formula is used for calculation:

[0102]

[0103] Take the second set of historical heat load data {L t-1 , L t-2 , L t-3}={1550, 1600, 1650}, historical gas demand data {Q gas-1 , Q gas-2 , Q gas-3}={250, 260, 270}, historical pressure data {P t-1 , P t-2 , P t-3}={5.2, 5.4, 5.6}, take the average of each Calculate according to the formula:

[0104]

[0105] We get Qt = {2525.6, 2146.2...}. Based on the predicted boiler gas demand Qt, we calculate the peak gas demand Qpeak and the off-peak gas demand Qoff-peak. Assuming that the time difference from off-peak to peak is 0.15h, the calculation formula is as follows:

[0106] Qpeak=max(Qt)=2525.6m 3

[0107] Qoff-peak=min(Qt)=2146.2m 3

[0108] Dpeak=(Qpeak-Qoff-peak)÷△t=(2525.6-2146.2)÷0.15=2529.3m 3

[0109] The threshold is set based on the predicted peak boiler gas demand. The gas demand threshold is set to 2529.3m 3 , when the actual gas demand in the boiler is greater than 2529.3m 3 , turn on the backup boiler equipment.

[0110] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0111] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A gas supply peak-shaving management system based on big data analysis, Features: The system includes data acquisition module, fusion data analysis module and threshold setting module: The data acquisition module is used to collect the operation data of the main equipment boiler when supplying gas, calculate the basic heat load demand of the boiler according to the operation data, and calculate the gas demand of the boiler according to the basic heat load data of the boiler; The fusion data analysis module is used to fuse the heat load value, gas demand, and pressure value of the boiler in the historical data with the heat load value, gas demand, and pressure value of the boiler in the real-time data during gas supply, establish a linear regression model, and use the fused linear regression model to predict the gas demand during peak hours; The threshold setting module is used to compare the peak gas demand predicted by the linear regression model with the set gas demand threshold, and when the gas demand value exceeds the set threshold, the backup equipment is turned on.

2. According to the gas supply peak-shaving management system based on big data analysis according to claim 1, Features: The data acquisition module includes a data acquisition unit and a data processing unit; The data acquisition unit is used to collect gas pipeline network data during gas supply, and the gas pipeline network data includes: the flow rate of gas in the pipeline network, the volume of heated fluid and the temperature difference between the air inlet and the air outlet of the gas supply pipeline; the data processing unit is used to receive the gas pipeline network data during boiler gas supply, and calculate the boiler's heat load demand and gas demand based on the received gas pipeline network data.

3. According to the gas supply peak-shaving management system based on big data analysis as described in claim 1, Features: The fusion data analysis module includes a storage unit and a data analysis unit; The storage unit is used to store the thermal load and gas demand of the boiler during gas supply; the data analysis unit is used to integrate real-time data and historical data, the real-time data includes the thermal load value of the boiler, the gas demand, and the pressure value inside the boiler; the historical data includes the historical thermal load value of the boiler, the historical gas demand, and the historical pressure value inside the boiler, and the gas demand of the boiler is predicted according to the linear regression model.

4. According to the gas supply peak-shaving management system based on big data analysis as described in claim 1, Features: The threshold setting module includes a threshold model unit and a data comparison unit; The threshold model unit is used to determine whether the gas demand in the boiler has reached a peak based on the predicted gas demand in the boiler, and to set a threshold at the same time; the data comparison unit is used to compare the gas demand in the boiler at the peak and the size of the set threshold.

5. A gas supply peak-shaving management method based on big data analysis, which is applied to a gas supply peak-shaving management system based on big data analysis as claimed in any one of claims 1 to 4, Features: The method comprises the following steps: Step S1, collecting the operation data of the main equipment boiler when supplying gas, the operation data including the flow rate of gas in the pipe network, the volume of fluid heated in the boiler, the air inlet temperature of the gas supply pipeline, the air outlet temperature of the gas supply pipeline, the specific heat capacity of the fluid, the calorific value of the gas and the thermal efficiency of the boiler, calculating the basic heat load demand of the boiler according to the operation data, and calculating the gas demand of the boiler according to the basic heat load data of the boiler; Step S2, recording the calculated heat load value, gas demand, and pressure value of the boiler, obtaining historical operation data of the main equipment boiler and the standby boiler, marking the event of starting the standby equipment boiler when the main equipment boiler reaches the peak in the historical operation data as a historical target event, obtaining the heat load value, gas demand, and pressure value of the main equipment boiler when it reaches the peak in the historical target event and recording them as a historical array, establishing real-time data based on the recorded heat load value, gas demand, and pressure value of the boiler, integrating the real-time data with the data in the historical database, and establishing a linear regression model, wherein the linear regression model is used to predict the gas demand in the boiler at the peak; Step S3, according to the peak gas demand predicted by the linear regression model, a threshold value is set, and the threshold value is set as the gas demand threshold. When the gas demand of the main boiler equipment during peak operation exceeds the set gas demand threshold, the standby equipment boiler is turned on.

6. A gas supply peak load management method based on big data analysis according to claim 5, Features: The step S1 further comprises: Step S101, installing an ultrasonic transmitter and an ultrasonic receiver on the outer surface of the gas supply pipe, wherein the ultrasonic receiver is used to receive a pulse signal from the ultrasonic transmitter; Step S102: The ultrasonic transmitter sends out a pulse signal, which propagates in the fluid and is received by the ultrasonic receiver. The propagation time of the ultrasonic wave in the downstream and upstream directions is obtained, and the flow velocity Vt of the gas in the pipe network is calculated according to the difference in propagation time. The calculation formula is as follows: Vt=[(t2-t1)÷(t1+t2)]×(D÷2) Where D is the distance between sensors, t1 is the propagation time in the downstream direction, and t2 is the propagation time in the upstream direction; The gas flow rate is used to calculate the fluid volume V. The calculation formula is as follows: V=Vt×A×(ta-tb) Wherein, Vt represents the flow velocity, A represents the cross-sectional area through which the fluid passes, ta represents the time when the boiler's gas supply reaches its peak, and tb represents the time when the boiler starts to supply gas; Step S103, temperature sensors are installed at the air inlet and the air outlet of the air supply pipeline respectively, and the temperature sensors are used to collect the air inlet temperature of the air supply pipeline and the air outlet temperature of the air supply pipeline. The temperature difference ΔT of the gas flowing in the air supply pipeline is calculated according to the air inlet temperature Tin and the air outlet temperature Tout. The calculation formula is as follows: △T=Tin-Tout Among them, △T represents the temperature difference of the gas, Tin represents the inlet temperature when the pipeline is supplied with gas from the boiler, and Tout represents the outlet temperature when the pipeline is supplied with gas from the boiler; Step S104: Install a pressure sensor on the boiler to measure the pressure value P, calculate the basic heat load demand Qdemand by multiplying the heated fluid volume V, the temperature difference ΔT and the fluid specific heat capacity Cp, and calculate the gas demand Qgas using the following formula: Qdemand=V×△T×Cp Qgas=Qdemand÷(η×GCV) Where Qdemand represents the heat load demand of the boiler during peak load regulation, V represents the volume of the fluid to be heated, △T represents the required temperature increase, Cp represents the specific heat capacity of the fluid, Qgas represents the gas demand, η represents the thermal efficiency of the boiler, and GCV represents the calorific value of the gas.

7. According to claim 5, a gas supply peak load management method based on big data analysis, Features: The step S2 further comprises: Step S201, extracting data during the peak gas supply period from a historical database, wherein the historical data includes historical heat load, historical gas demand, and historical pressure data; The collected historical heat load data forms a historical heat load set: L t-△t ={L t-1 , L t-2 , L t-3 ...}; The collected historical gas demand data forms a historical gas demand set: The collected historical pressure data forms a historical pressure set: P t-Δt = {P t-1 , P t-2 , P t-3 ......}; Combine multiple groups of historical data for integration and take the average value to obtain the historical data set A linear regression model is established by integrating real-time data and historical data sets to obtain the target variable, which is the predicted boiler gas consumption Qt. The linear regression model calculation formula is as follows: Where Qt represents the predicted boiler gas demand, Represents the mean of multiple groups of historical heat load data, Represents the mean of multiple groups of historical gas demand data, Represents the mean of multiple sets of historical pressure data, α 1 , α 2 , α 3 , β are model parameters.

8. According to claim 5, a gas supply peak load management method based on big data analysis, Features: The step S3 further comprises: Step S301: Calculate the peak gas demand Qpeak and the off-peak gas demand Qoff-peak according to the predicted boiler gas demand Qt. The calculation formula is as follows: Qpeak=max(Qt) Qoff-peak=min(Qt) Among them, Qpeak represents the gas demand during peak hours, Qoff-peak represents the gas demand during off-peak hours, Qt represents the predicted boiler gas demand, max represents the maximum value, and min represents the minimum value; Step S302: Establish a threshold model and set a gas demand threshold Dpeak. The calculation formula is as follows: Dpeak=(Qpeak-Qoff-peak)÷△t Among them, Dpeak represents the gas demand threshold at peak time, Qpeak represents the gas demand at peak time, Qoff-peak represents the gas demand of the boiler at off-peak time, and △t represents the time change from the gas demand of the boiler at off-peak time to the gas demand of the boiler at peak time; Step S303: When the real-time gas demand Qgas in the boiler is greater than the peak gas demand threshold Dpeak, the main device is overloaded and the backup device is turned on; when Qgas is less than Dpeak, the main device operates normally and the backup device is shut down and not enabled.