Air compressor energy consumption optimization system and method based on big data analysis

Abstract

The application discloses an air compressor energy consumption optimization system and method based on big data analysis, comprising a data acquisition module, a data processing module and an air compressor adjustment module; relates to the technical field of air compressor energy saving; solves the technical problem of high energy consumption of the air compressor in the prior art during operation; the application analyzes the operation state of each air compressor based on the gas consumption demand curve and a plurality of operation curves, obtains the corresponding operation characteristic data of each air compressor, constructs an exhaust priority sequence based on the operation characteristic data, and starts a plurality of air compressors based on the gas consumption prediction value and the exhaust priority sequence. The application constructs the gas consumption demand curve and the linear fitting operation curve, analyzes the operation characteristics of each air compressor and constructs the exhaust priority sequence, combines the gas consumption prediction model, realizes accurate prediction of future gas consumption demand, intelligently selects the optimal air compressor combination based on the prediction value and the priority sequence, and is favorable for reducing the operation energy consumption of the air compressor.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of air compressor energy saving, and particularly relates to an air compressor energy consumption optimization system and method based on big data analysis. BACKGROUND

[0002] In modern industrial production, as a key power source equipment, the energy consumption of an air compressor accounts for an important part of enterprise energy consumption. A traditional air compressor management system usually lacks in-depth analysis of operation data, resulting in low equipment efficiency, high energy consumption, and increased maintenance costs. The air compressor itself has the problem of high energy consumption, and if it is operated at low efficiency for a long time, resource waste is inevitable. Therefore, the operation of the air compressor needs to be optimized in a timely manner to reduce resource waste.

[0003] The prior art collects operation information of the air compressor, analyzes the operation information to obtain energy efficiency characteristic data of the air compressor, and adjusts the operation frequency of the air compressor based on the energy efficiency characteristic data, thereby reducing the energy consumption of the air compressor during operation. However, the technical solution of the prior art is difficult to optimize the operation state of the air compressors in the air compressor unit, resulting in high energy consumption of the air compressor during operation. In addition, the prior art is difficult to estimate the gas demand in advance according to the historical gas consumption, and adjust the operation state of the air compressor according to the gas demand, thereby leading to the energy consumption optimization of the air compressor being not timely and accurate enough.

[0004] The application proposes an air compressor energy consumption optimization system and method based on big data analysis to solve the above technical problems. SUMMARY

[0005] The application aims to solve at least one of the technical problems in the prior art. To this end, the application proposes an air compressor energy consumption optimization system and method based on big data analysis to solve the technical problems that the technical solution of the prior art is difficult to optimize the operation state of the air compressors in the air compressor unit, resulting in high energy consumption of the air compressor during operation. In addition, the prior art is difficult to estimate the gas demand in advance according to the historical gas consumption, and adjust the operation state of the air compressor according to the gas demand, thereby leading to the energy consumption optimization of the air compressor being not timely and accurate enough.

[0006] To achieve the above purpose, the first aspect of the application provides an air compressor energy consumption optimization system based on big data analysis, which comprises a data processing module, and a data acquisition module and an air compressor adjustment module connected thereto.

[0007] The data collection module is configured to collect historical gas consumption data of the park in a plurality of continuous periods, and to obtain operation data of each air compressor in the air compressor set in the plurality of continuous periods, wherein the air compressor set comprises a plurality of air compressors, and the operation data comprises exhaust volume and energy consumption.

[0008] The data processing module is configured to draw a gas consumption demand curve based on the historical gas consumption data, to linearly fit the operation data of each air compressor to obtain a plurality of operation curves, to analyze the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves to obtain operation characteristic data corresponding to each air compressor, and to construct an exhaust priority sequence based on the operation characteristic data.

[0009] The historical gas consumption data is input into a park gas consumption prediction model to obtain a predicted value of the gas consumption of the park, wherein the park gas consumption prediction model is constructed based on an artificial intelligence model.

[0010] The air compressor adjustment module is configured to enable a plurality of air compressors based on the predicted value of the gas consumption and the exhaust priority sequence.

[0011] Preferably, the drawing of the gas consumption demand curve based on the historical gas consumption data comprises:

[0012] The historical gas consumption data of the park in a plurality of continuous periods is extracted, and a gas consumption demand curve is drawn by linear fitting with time as the independent variable and the historical gas consumption data as the dependent variable.

[0013] Preferably, the linear fitting of the operation data of each air compressor comprises:

[0014] The exhaust volume and energy consumption in the operation data of each air compressor in a plurality of continuous periods are extracted, and an exhaust volume curve of each air compressor is drawn by linear fitting with time as the independent variable and the exhaust volume as the dependent variable, and an energy consumption curve of each air compressor is drawn by linear fitting with time as the independent variable and the energy consumption as the dependent variable.

[0015] Preferably, the analysis of the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves comprises:

[0016] The gas consumption demand curve in a plurality of continuous periods and the operation curves corresponding to a plurality of air compressors are extracted, the start time of the plurality of continuous periods is marked as t1, the end time of the plurality of continuous periods is marked as t2, the gas consumption demand curve is marked as g(t), the exhaust volume curves corresponding to the plurality of air compressors are marked as fi(t), and the energy consumption curves corresponding to the plurality of air compressors are marked as hi(t), wherein t is time, t1≦t≦t2, i=1, 2, …, n, and n is the total number of air compressors.

[0017] extracting the maximum value of the exhaust volume from the exhaust volume curve corresponding to each air compressor, and marking the maximum value of the exhaust volume as the maximum exhaust volume;

[0018] calculating the difference between the gas consumption demand curve and the exhaust volume curve corresponding to each air compressor to obtain the exhaust volume difference corresponding to each air compressor;

[0019] calculating the ratio between the exhaust volume curve fi(t) of each air compressor and the corresponding energy consumption curve hi(t), and marking the corresponding ratio as the energy efficiency ratio;

[0020] integrating the maximum exhaust volume, the exhaust volume difference and the energy efficiency ratio into the operation characteristic data.

[0021] It should be noted that the exhaust volume difference refers to the difference between the cumulative exhaust volume of each air compressor and the cumulative gas consumption of the park within the collection period;

[0022] Preferably, the calculation of the difference between the gas consumption demand curve and the exhaust volume curve corresponding to each air compressor comprises:

[0023] extracting the gas consumption demand curve g(t) and the exhaust volume curve fi(t) corresponding to each air compressor; through the formula calculating the exhaust volume difference PQCi corresponding to the air compressor i.

[0024] Preferably, the construction of the exhaust priority sequence based on the operation characteristic data comprises:

[0025] extracting the maximum exhaust volume, the exhaust volume difference and the energy efficiency ratio in the operation characteristic data of each air compressor; judging whether the energy efficiency ratio of each air compressor is greater than a preset energy efficiency threshold; if yes, marking the energy efficiency label of the corresponding air compressor as 1; if no, marking the energy efficiency label of the corresponding air compressor as 0;

[0026] adding the number corresponding to the air compressor with the energy efficiency label value of 1 to the first priority sequence, and adding the number corresponding to the air compressor with the energy efficiency label value of 0 to the second priority sequence;

[0027] calculating the energy-saving priority coefficient corresponding to each air compressor based on the operation characteristic data of each air compressor;

[0028] sequencing the first priority sequence and the second priority sequence in the order of the energy-saving priority coefficient from large to small;

[0029] integrating the first priority sequence and the second priority sequence into the exhaust priority sequence.

[0030] Preferably, the calculation of the energy-saving priority coefficient corresponding to each air compressor based on the operation characteristic data of each air compressor comprises:

[0031] extracting the maximum exhaust volume, the exhaust volume difference and the energy efficiency ratio in the operation characteristic data of each air compressor; through the formula calculating an energy-saving priority coefficient JYXi of the air compressor i; wherein, t2-t1 is the length of several continuous periods, ZPLi is the maximum exhaust capacity of the air compressor i, PQCi is the exhaust capacity difference of the air compressor i, NXSi is the energy efficiency ratio of the air compressor i; a, b, c are all influence coefficients greater than 0.

[0032] Preferably, the park gas consumption prediction model is constructed based on an artificial intelligence model, comprising:

[0033] extracting historical gas consumption data of the park in several continuous periods and integrating them into several groups of training data and test data; training the artificial intelligence model using the training data, testing the trained artificial intelligence model using the test data, and adjusting the artificial intelligence model according to the test results; finally obtaining a park gas consumption prediction model with the input being the historical gas consumption data of the recent several continuous periods and the output being the predicted gas consumption prediction value of the prediction period; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0034] Preferably, the enabling of the several air compressors based on the gas consumption prediction value and the exhaust priority sequence comprises:

[0035] T1: extracting the gas consumption prediction value, the first priority sequence, and the second priority sequence;

[0036] T2: calculating the sum of the maximum exhaust capacities of the several air compressors in the first priority sequence and marking it as the first gas consumption threshold;

[0037] T3: calculating the sum of the maximum exhaust capacities of the several air compressors in the second priority sequence and marking it as the second gas consumption threshold;

[0038] T4: marking the sum of the first gas consumption threshold and the second gas consumption threshold as the third gas consumption threshold;

[0039] T5: determining whether the gas consumption prediction value is greater than the third gas consumption threshold; if yes, generating a gas supply shortage prompt information; if no, jumping to T6;

[0040] T6: determining whether the gas consumption prediction value is less than the first gas consumption threshold;

[0041] if yes, sequentially selecting several air compressors from the first priority sequence, setting the running state of the selected several air compressors to on, and setting the running state of the air compressors in the second priority sequence to off;

[0042] if no, setting the running state of the several air compressors in the first priority sequence and the second priority sequence to on; wherein the running state of the air compressor includes on and off.

[0043] The second aspect of the application provides a big data analysis-based air compressor energy consumption optimization method, comprising:

[0044] S1: collecting historical gas consumption data of the park where the air compressor unit is located; and obtaining operation data of each air compressor in the air compressor unit;

[0045] S2: drawing a gas consumption demand curve based on the historical gas consumption data;

[0046] S3: linearly fitting the operation data of each air compressor to obtain a plurality of operation curves;

[0047] S4: analyzing the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves to obtain operation characteristic data corresponding to each air compressor; and constructing an exhaust priority sequence based on the operation characteristic data;

[0048] S5: inputting the historical gas consumption data into a park gas consumption prediction model to obtain a predicted value of the park gas consumption;

[0049] S6: starting a plurality of air compressors based on the predicted value of the gas consumption and the exhaust priority sequence.

[0050] Compared with the prior art, the application has the following advantages:

[0051] 1. The application is aimed at air compressor energy consumption optimization, and historical gas consumption data of the park and operation data of each air compressor are collected to construct a gas consumption demand curve and linearly fitted operation curves. The operation characteristics of each air compressor are analyzed based on this, and an exhaust priority sequence is constructed. In combination with a gas consumption prediction model, accurate prediction of future gas consumption demand is realized. Based on the predicted value and the priority sequence, the optimal air compressor combination is intelligently selected for starting, which effectively reduces energy consumption, reduces energy waste, improves system efficiency, prolongs the service life of the equipment, reduces operating costs, significantly improves the economic benefits and energy use efficiency of enterprises.

[0052] 2. The application comprehensively analyzes the gas consumption demand curve of the park, the exhaust volume curve and the energy consumption curve of each air compressor to obtain the maximum exhaust volume, the exhaust volume difference and the energy efficiency ratio, so that the operation characteristic data obtained by analysis can accurately reflect the actual operation status of each air compressor, facilitating subsequent targeted adjustment and optimization of the air compressor unit based on the operation characteristic data of each air compressor, thereby facilitating reduction of energy consumption of the air compressor unit during operation.

[0053] 3、The application marks the sum of the first gas consumption threshold and the second gas consumption threshold as a third gas consumption threshold; by judging the size relationship between the gas consumption prediction value and the first gas consumption threshold, the second gas consumption threshold and the third gas consumption threshold, the number of air compressors in the air compressor unit is adjusted, the number of air compressors started is reduced as much as possible under the premise of ensuring gas demand, thereby facilitating the reduction of energy consumption of the air compressor in operation. BRIEF DESCRIPTION OF DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0055] Fig. 1 The overall flowchart of the air compressor energy consumption optimization method based on big data analysis of the present application;

[0056] Fig. 2 The principle schematic diagram of the air compressor energy consumption optimization system based on big data analysis of the present application;

[0057] Fig. 3 The flowchart of starting the air compressor based on the gas consumption prediction value and the exhaust priority sequence in the present application. DETAILED DESCRIPTION

[0058] The technical solutions of the present application will be described clearly and completely in combination with the embodiments. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor belong to the protection scope of the present application.

[0059] Please refer to Figs. 1-3 The first aspect embodiment of the present application provides an air compressor energy consumption optimization system based on big data analysis, which comprises a data processing module, and a data acquisition module and an air compressor adjusting module connected thereto.

[0060] The data acquisition module is used to acquire historical gas consumption data of the park in a plurality of continuous periods; and obtain operation data of each air compressor in the air compressor unit in a plurality of continuous periods; wherein the air compressor unit comprises a plurality of air compressors; and the operation data comprises exhaust capacity and energy consumption.

[0061] The data processing module: drawing a gas consumption demand curve based on historical gas consumption data; linearly fitting the operation data of each air compressor respectively to obtain a plurality of operation curves; analyzing the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves to obtain operation characteristic data corresponding to each air compressor; constructing an exhaust priority sequence based on the operation characteristic data; wherein, the operation curve includes an exhaust volume curve and an energy consumption curve; and

[0062] The historical gas consumption data is input into a park gas consumption prediction model to obtain a park gas consumption prediction value; wherein, the park gas consumption prediction model is constructed based on an artificial intelligence model;

[0063] The air compressor adjusting module: enabling a plurality of air compressors based on the gas consumption prediction value and the exhaust priority sequence.

[0064] In this embodiment, the gas consumption demand curve is drawn based on historical gas consumption data, including:

[0065] Extract historical gas consumption data of the park in a plurality of consecutive periods; draw a gas consumption demand curve by linear fitting with time as the independent variable and historical gas consumption data as the dependent variable.

[0066] In this embodiment, the operation data of each air compressor is linearly fitted, including:

[0067] Extract the exhaust volume and energy consumption of each air compressor in the operation data in a plurality of consecutive periods; draw the exhaust volume curve of each air compressor by linear fitting with time as the independent variable and exhaust volume as the dependent variable; draw the energy consumption curve of each air compressor by linear fitting with time as the independent variable and energy consumption as the dependent variable.

[0068] The present application extracts the exhaust volume and energy consumption of each air compressor in the operation data in a plurality of consecutive periods, linearly fits the exhaust volume and energy consumption respectively, obtains the exhaust volume curve and the energy consumption curve, which is convenient for subsequent analysis according to the exhaust volume curve and the energy consumption curve, so that the operation characteristic data of each air compressor obtained by analysis is more accurate.

[0069] In this embodiment, the operation status of each air compressor is analyzed based on the gas consumption demand curve and the plurality of operation curves, including:

[0070] Extract the gas consumption demand curve and the operation curve corresponding to a plurality of air compressors in a plurality of consecutive periods; mark the start time of a plurality of consecutive periods as t1, mark the end time of a plurality of consecutive periods as t2, mark the gas consumption demand curve as g(t), mark the exhaust volume curve corresponding to a plurality of air compressors as fi(t), and mark the energy consumption curve corresponding to a plurality of air compressors as hi(t); wherein, t is time, and t1≦t≦t2; i=1, 2, …, n, n is the total number of air compressors;

[0071] extracting a maximum value of the exhaust volume from the exhaust volume curve corresponding to each air compressor, and marking the maximum value of the exhaust volume as a maximum exhaust volume;

[0072] calculating a difference value between the gas consumption demand curve and the exhaust volume curve corresponding to each air compressor to obtain an exhaust volume difference value corresponding to each air compressor;

[0073] calculating a ratio between the exhaust volume curve fi(t) of each air compressor and the corresponding energy consumption curve hi(t), and marking the corresponding ratio as an energy efficiency ratio;

[0074] integrating the maximum exhaust volume, the exhaust volume difference value and the energy efficiency ratio as operation characteristic data.

[0075] It should be noted that the exhaust volume difference value refers to the difference value between the cumulative value of the exhaust volume of each air compressor and the cumulative value of the gas consumption of the park within the collection period.

[0076] The maximum exhaust volume, the exhaust volume difference value and the energy efficiency ratio are obtained by comprehensively analyzing the gas consumption demand curve of the park, the exhaust volume curve of each air compressor and the energy consumption curve, so that the operation characteristic data obtained by analysis can accurately reflect the actual operation condition of each air compressor, and subsequent targeted adjustment and optimization of the air compressor unit according to the operation characteristic data of each air compressor is facilitated, thereby being beneficial to reducing the energy consumption of the air compressor unit during operation.

[0077] In this embodiment, the difference value between the gas consumption demand curve and the exhaust volume curve corresponding to each air compressor comprises:

[0078] extracting the gas consumption demand curve g(t) and the exhaust volume curve fi(t) corresponding to each air compressor; calculating the difference value between the gas consumption demand curve g(t) and the exhaust volume curve fi(t) corresponding to each air compressor by the formula calculating the exhaust volume difference value PQCi corresponding to the air compressor i.

[0079] For example, the cumulative value of the exhaust volume of the air compressor 1 within several consecutive 1 hours is set to 4500. The cumulative value of the gas consumption of the park within several consecutive 1 hours is set to 5000. The exhaust volume difference value PQC1 of the air compressor 1 is calculated by the formula to be 4500.

[0080] In this embodiment, the exhaust priority sequence is constructed based on the operation characteristic data, comprising:

[0081] extracting the maximum exhaust volume, the exhaust volume difference value and the energy efficiency ratio in the operation characteristic data of each air compressor; judging whether the energy efficiency ratio of each air compressor is greater than a preset energy efficiency threshold value; if yes, marking the energy efficiency label of the corresponding air compressor as 1; if no, marking the energy efficiency label of the corresponding air compressor as 0;

[0082] add the number corresponding to the air compressor with the energy efficiency label value of 1 to the first priority sequence, and add the number corresponding to the air compressor with the energy efficiency label value of 0 to the second priority sequence;

[0083] calculate the corresponding energy-saving priority coefficient based on the operation characteristic data of each air compressor;

[0084] sort the first priority sequence and the second priority sequence in descending order of the energy-saving priority coefficient;

[0085] integrate the first priority sequence and the second priority sequence into an exhaust priority sequence.

[0086] For example, the air compressors in the embodiment are fixed-frequency screw air compressors, and the maximum exhaust capacity, exhaust capacity difference, and energy efficiency ratio of the air compressors are as shown in the following table:

[0087]

[0088]

[0089] The energy efficiency threshold is set to 10 m 3 / kwh, and the energy efficiency label of the corresponding air compressor is set to 1 because the energy efficiency ratio of the air compressors 1, 2, and 6 is greater than the preset energy efficiency threshold. The energy efficiency label of the corresponding air compressor is set to 0 because the energy efficiency ratio of the air compressors 3, 4, and 5 is less than the preset energy efficiency threshold. The number corresponding to the air compressor with the energy efficiency label value of 1 is added to the first priority sequence, and the first priority sequence {1, 2, 6} is obtained. The number corresponding to the air compressor with the energy efficiency label value of 0 is added to the second priority sequence, and the second priority sequence {3, 4, 5} is obtained. The first priority sequence and the second priority sequence are sorted in descending order of the energy-saving priority coefficient. The first priority sequence and the second priority sequence are integrated into an exhaust priority sequence.

[0090] In the embodiment, the corresponding energy-saving priority coefficient is calculated based on the operation characteristic data of each air compressor, including:

[0091] extract the maximum exhaust capacity, exhaust capacity difference, and energy efficiency ratio in the operation characteristic data of each air compressor; calculate the energy-saving priority coefficient JYXi of the air compressor i by the formula ; wherein t2-t1 is the duration of a plurality of continuous periods, ZPLi is the maximum exhaust capacity of the air compressor i, PQCi is the exhaust capacity difference of the air compressor i, and NXSi is the energy efficiency ratio of the air compressor i; a, b, and c are all influence coefficients greater than 0, and the specific values of the influence coefficients a, b, and c are set by experts in the relevant field according to experience.

[0092] Exemplarily, the influence coefficients a=3, b=10, and c=1.5 are set; the time length of a plurality of continuous periods t2-t1=60 min, the maximum exhaust capacity of the air compressor 1 ZPL1=20, the exhaust capacity difference of the air compressor 1 PQC1=4500, and the energy efficiency ratio of the air compressor 1 NXS1=13.8; and the energy-saving priority coefficient JYX1 of the air compressor 1 is calculated by the formula to be approximately 39.11.

[0093] It is worth noting that the values of the influence coefficients a and b are related to the peak value of the gas consumption of the park, and the greater the peak value of the gas consumption of the park, the greater the values of the influence coefficients a and b are set; the value of the influence coefficient c is related to the electricity cost of the park, and the greater the electricity cost of the park, the greater the value of the influence coefficient c is set.

[0094] It should be noted that the greater the maximum exhaust capacity, the smaller the exhaust capacity difference, and the smaller the energy efficiency ratio, the greater the energy-saving priority coefficient calculated, and the greater the energy-saving priority coefficient, the lower the comprehensive energy consumption of the corresponding air compressor in the actual running process and the higher the running efficiency.

[0095] In this embodiment, the park gas consumption prediction model is constructed based on an artificial intelligence model, including:

[0096] The historical gas consumption data of the park in a plurality of continuous periods is extracted and integrated into a plurality of groups of original data, 80% of the original data is used as training data, and 20% is used as test data; the training data is used to train the artificial intelligence model, the test data is used to test the trained artificial intelligence model, and the artificial intelligence model is adjusted according to the test result; finally, the park gas consumption prediction model with the input being the historical gas consumption data of the recent plurality of continuous periods and the output being the predicted gas consumption prediction value of the prediction period is obtained; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

[0097] The historical gas consumption data of the park in a plurality of continuous periods is extracted, and the historical gas consumption data is used to train the artificial intelligence model, and the park gas consumption prediction model is obtained after the training; the historical gas consumption data of a plurality of continuous periods is input into the park gas consumption prediction model to obtain the gas consumption prediction value of the prediction period; so that the air compressor adjustment module can obtain the change of the gas consumption in advance, and timely adjust the running state of each air compressor in the air compressor unit, thereby facilitating the reduction of the energy consumption of the air compressor in operation.

[0098] In this embodiment, a plurality of air compressors are enabled based on the gas consumption prediction value and the exhaust priority sequence, including:

[0099] T1: extracting the gas consumption prediction value, the first priority sequence, and the second priority sequence;

[0100] T2: calculate the sum of the maximum exhaust capacity of the air compressors in the first priority sequence, and mark it as the first air consumption threshold;

[0101] T3: calculate the sum of the maximum exhaust capacity of the air compressors in the second priority sequence, and mark it as the second air consumption threshold;

[0102] T4: mark the sum of the first air consumption threshold and the second air consumption threshold as the third air consumption threshold;

[0103] T5: determine whether the air consumption prediction value is greater than the third air consumption threshold; if yes, generate a gas supply shortage prompt information; if no, jump to T6;

[0104] T6: determine whether the air consumption prediction value is less than the first air consumption threshold;

[0105] Yes, select the air compressors from the first priority sequence in turn, set the running state of the selected air compressors to start, and set the running state of the air compressors in the second priority sequence to stop;

[0106] No, set the running state of the air compressors in the first priority sequence and the second priority sequence to start; wherein the running state of the air compressor includes start and stop.

[0107] For example, the air consumption prediction value is set to 70m 3 / min, the first air consumption threshold is 92m 3 / min, the second air consumption threshold is 94m 3 / min, and the third air consumption threshold is 186m 3 / min; since the air consumption prediction value is less than the first air consumption threshold, the air compressors are selected from the first priority sequence in turn, the running state of the selected air compressors is set to start, and the running state of the air compressors in the second priority sequence is set to stop.

[0108] The present application calculates the first air consumption threshold and the second air consumption threshold corresponding to the first priority sequence and the second priority sequence, marks the sum of the first air consumption threshold and the second air consumption threshold as the third air consumption threshold; by judging the size relationship between the air consumption prediction value and the first air consumption threshold, the second air consumption threshold and the third air consumption threshold, the air compressors in the air compressor unit are adjusted, the number of air compressors started is reduced as much as possible under the premise of ensuring air consumption demand, thereby reducing the energy consumption of the air compressor during operation.

[0109] The second aspect of the present application provides an air compressor energy consumption optimization method based on big data analysis, comprising:

[0110] S1: collect historical air consumption data of the park where the air compressor unit is located; obtain the running data of each air compressor in the air compressor unit;

[0111] S2: draw the gas consumption demand curve based on the historical gas consumption data;

[0112] S3: linearly fit the operation data of each air compressor to obtain a plurality of operation curves;

[0113] S4: analyze the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves to obtain operation characteristic data corresponding to each air compressor; and construct an exhaust priority sequence based on the operation characteristic data;

[0114] S5: input the historical gas consumption data into a park gas consumption prediction model to obtain a predicted value of the park gas consumption;

[0115] S6: start a plurality of air compressors based on the predicted value of the gas consumption and the exhaust priority sequence.

[0116] Some data in the above formula are calculated by removing the dimension to obtain the numerical value, and the formula is obtained by software simulation of a large amount of collected data to obtain a formula closest to the actual situation; the preset parameters and the preset threshold in the formula are set by a person skilled in the art according to the actual situation or obtained by a large amount of data simulation.

[0117] Working principle of the present application:

[0118] The present application collects historical gas consumption data of a park where the air compressor unit is located; obtains operation data of each air compressor in the air compressor unit; draws a gas consumption demand curve based on the historical gas consumption data; linearly fits the operation data of each air compressor to obtain a plurality of operation curves; analyzes the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves to obtain operation characteristic data corresponding to each air compressor; constructs an exhaust priority sequence based on the operation characteristic data; inputs the historical gas consumption data into a park gas consumption prediction model to obtain a predicted value of the park gas consumption; and starts a plurality of air compressors based on the predicted value of the gas consumption and the exhaust priority sequence.

[0119] The above examples are only used to illustrate the technical method of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.

Claims

1. An air compressor energy consumption optimization system based on big data analysis, comprising: The data processing module, the data acquisition module connected with the data processing module, and the air compressor adjusting module connected with the data processing module; the data processing module is characterized in that, The data acquisition module is configured to collect historical gas consumption data of the park in a plurality of continuous periods, and to obtain operation data of each air compressor in the air compressor set in the plurality of continuous periods; the air compressor set includes a plurality of air compressors; The data processing module is configured to draw a gas consumption demand curve based on the historical gas consumption data, to perform linear fitting on the operation data of each air compressor to obtain a plurality of operation curves, to analyze the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves to obtain operation characteristic data corresponding to each air compressor, and to construct an exhaust priority sequence based on the operation characteristic data; and The historical gas consumption data is input into a park gas consumption prediction model to obtain a predicted value of the park gas consumption; the park gas consumption prediction model is constructed based on an artificial intelligence model; The air compressor adjusting module is configured to start a plurality of air compressors based on the predicted value of the park gas consumption and the exhaust priority sequence; The analysis of the operation status of each air compressor based on the gas consumption demand curve and the plurality of operation curves includes: extracting the gas consumption demand curve in the plurality of continuous periods and the operation curves corresponding to the plurality of air compressors, marking the start time of the plurality of continuous periods as t1, marking the end time of the plurality of continuous periods as t2, marking the gas consumption demand curve as g(t), marking the exhaust volume curves corresponding to the plurality of air compressors as fi(t), and marking the energy consumption curves corresponding to the plurality of air compressors as hi(t); wherein t is time, and t1≦t≦t2; i=1, 2, …, n, and n is the total number of air compressors; extracting the maximum exhaust volume from the exhaust volume curve corresponding to each air compressor, and marking the maximum exhaust volume as the maximum exhaust volume; calculating the difference between the gas consumption demand curve and the exhaust volume curve corresponding to each air compressor, and marking the corresponding difference as the exhaust volume difference; calculating the ratio between the exhaust volume curve fi(t) of each air compressor and the corresponding energy consumption curve hi(t), and marking the corresponding ratio as the energy efficiency ratio; integrating the maximum exhaust volume, the exhaust volume difference, and the energy efficiency ratio into the operation characteristic data; The construction of the exhaust priority sequence based on the operation characteristic data includes: extracting the maximum exhaust volume, the exhaust volume difference, and the energy efficiency ratio in the operation characteristic data of each air compressor, determining whether the energy efficiency ratio of each air compressor is greater than a preset energy efficiency threshold, marking the energy efficiency label of the corresponding air compressor as 1 if the answer is yes, and marking the energy efficiency label of the corresponding air compressor as 0 if the answer is no; adding the number corresponding to the air compressor with the energy efficiency label value of 1 to the first priority sequence, and adding the number corresponding to the air compressor with the energy efficiency label value of 0 to the second priority sequence; calculating the energy-saving priority coefficient corresponding to each air compressor based on the operation characteristic data of each air compressor; sorting the first priority sequence and the second priority sequence in the order of the energy-saving priority coefficient from large to small; integrating the first priority sequence and the second priority sequence into the exhaust priority sequence.

2. The big data analytics based energy consumption optimization system for air compressor machine as claimed in claim 1 wherein, The drawing of the gas consumption demand curve based on the historical gas consumption data includes: extract historical gas consumption data of the park in several consecutive periods; draw a gas consumption demand curve by linear fitting with time as the independent variable and historical gas consumption data as the dependent variable.

3. The big data analytics based air compressor energy consumption optimization system as claimed in claim 1, wherein, The linear fitting of the operation data of each air compressor includes: extract the exhaust volume and energy consumption of each air compressor in several consecutive periods; draw the exhaust volume curve of each air compressor by linear fitting with time as the independent variable and exhaust volume as the dependent variable; draw the energy consumption curve of each air compressor by linear fitting with time as the independent variable and energy consumption as the dependent variable; mark the exhaust volume curve and the energy consumption curve as operation curves.

4. The big data analytics based energy consumption optimization system for air compressor machine as claimed in claim 1 wherein, The difference between the gas consumption demand curve and the exhaust volume curve corresponding to each air compressor includes: Extract the gas demand curve g(t), the exhaust volume curve fi(t) corresponding to each air compressor; through the formula Calculate the exhaust volume difference PQCi corresponding to the air compressor i.

5. The big data analytics based energy consumption optimization system for air compressor machine as claimed in claim 1 wherein, The energy-saving priority coefficient corresponding to each air compressor is calculated based on the operation characteristic data, which includes: Extract the maximum exhaust capacity, exhaust capacity difference and energy efficiency ratio in the operation characteristic data of each air compressor; calculate the energy-saving priority coefficient JYXi of the air compressor i through the formula ; wherein, t2-t1 is the length of several continuous periods, ZPLi is the maximum exhaust capacity of the air compressor i, PQCi is the exhaust capacity difference of the air compressor i, NXSi is the energy efficiency ratio of the air compressor i; a, b and c are all influence coefficients greater than 0.

6. The big data analytics based energy consumption optimization system for air compression machine of claim 1, wherein, The park gas consumption prediction model is constructed based on an artificial intelligence model, which includes: extract historical gas consumption data of the park in several consecutive periods, and integrate them into several groups of training data and test data; train the artificial intelligence model using the training data, test the trained artificial intelligence model using the test data, and adjust the artificial intelligence model according to the test results; finally obtain a park gas consumption prediction model with the input being the historical gas consumption data of the last several consecutive periods and the output being the predicted gas consumption prediction value; wherein the artificial intelligence model includes a BP neural network model or an RBF neural network model.

7. The big data analytics based energy consumption optimization system for air compression machine of claim 1, wherein, The several air compressors are enabled based on the gas consumption prediction value and the exhaust priority sequence, which includes: T1: extract the gas consumption prediction value, the first priority sequence, and the second priority sequence; T2: calculate the sum of the maximum exhaust volumes of the several air compressors in the first priority sequence and mark it as the first gas consumption threshold; T3: calculate the sum of the maximum exhaust volumes of the several air compressors in the second priority sequence and mark it as the second gas consumption threshold; T4: mark the sum of the first gas consumption threshold and the second gas consumption threshold as the third gas consumption threshold; T5: determine whether the gas consumption prediction value is greater than the third gas consumption threshold; if yes, generate a gas supply shortage prompt information; if no, jump to T6; T6: determine whether the gas consumption prediction value is less than the first gas consumption threshold; if yes, select several air compressors from the first priority sequence in turn, set the running state of the selected several air compressors to on, and set the running state of the air compressors in the second priority sequence to off; if no, set the running state of the several air compressors in the first priority sequence and the second priority sequence to on; wherein the running state of the air compressor includes on and off.

8. The method of claim 1-7, wherein the system of claim 1-7 is operated based on big data analysis, characterized in that, It includes: S1: collect historical gas consumption data of the park where the air compressor unit is located; obtain the operation data of each air compressor in the air compressor unit; S2: draw a gas consumption demand curve based on the historical gas consumption data; S3: linearly fit the operation data of each air compressor to obtain several operation curves; S4: analyze the operation status of each air compressor based on the gas consumption demand curve and the several operation curves to obtain the operation characteristic data corresponding to each air compressor; construct an exhaust priority sequence based on the operation characteristic data; S5: input the historical gas consumption data into the park gas consumption prediction model to obtain the gas consumption prediction value of the park; S6: enabling several air compressors based on the gas usage prediction value and the exhaust priority sequence.

Images