CN114154692A - Air compressor starting optimization method cooperatively matched with pressure of production energy end - Google Patents
Air compressor starting optimization method cooperatively matched with pressure of production energy end Download PDFInfo
- Publication number
- CN114154692A CN114154692A CN202111375721.7A CN202111375721A CN114154692A CN 114154692 A CN114154692 A CN 114154692A CN 202111375721 A CN202111375721 A CN 202111375721A CN 114154692 A CN114154692 A CN 114154692A
- Authority
- CN
- China
- Prior art keywords
- air compressor
- pressure
- speed
- gas production
- energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000005457 optimization Methods 0.000 title claims abstract description 14
- 238000005265 energy consumption Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000009467 reduction Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000013499 data model Methods 0.000 claims description 2
- 239000002699 waste material Substances 0.000 abstract description 6
- 238000009472 formulation Methods 0.000 abstract description 3
- 239000000203 mixture Substances 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 21
- 238000005096 rolling process Methods 0.000 description 7
- 238000004134 energy conservation Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000000465 moulding Methods 0.000 description 5
- 238000007637 random forest analysis Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 238000012856 packing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 235000019504 cigarettes Nutrition 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 241000208125 Nicotiana Species 0.000 description 1
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention discloses an air compressor starting optimization method cooperatively matched with the pressure of a production energy end, belonging to the field of mechanical equipment control, and the air compressor starting optimization method cooperatively matched with the pressure of the production energy end comprises the following steps: predicting an energy demand pressure curve based on APS detailed scheduling; step two, calculating a set pressure curve of the air compressor based on the energy consumption demand pressure curve; thirdly, calculating an optimal gas production speed curve of each air compressor based on historical data; step four, predicting the gas consumption speed of the equipment terminal based on the set pressure curve and the APS detailed schedule; and step five, establishing a gas production speed and gas consumption speed cooperative matching model to carry out starting optimization on the air compressor. The invention provides corresponding data according to support, assists and verifies the formulation of internal control standards, adjusts the strategy in time, ensures that the compressed air capacity meets the demand, and reduces the power consumption of the air compressor and the waste of the compressed air to the maximum extent, thereby achieving the purposes of saving energy and reducing consumption.
Description
Technical Field
The invention belongs to the field of mechanical equipment control, and particularly relates to an air compressor starting optimization method cooperatively matched with pressure of a production energy end.
Background
Considering from the tobacco industry enterprise level, the problems of large energy consumption, much waste and the like are not beneficial to the development of the enterprise, and simultaneously, the great burden is also caused to the society, and the energy waste greatly increases the production cost. Upgrading equipment can reduce energy consumption to a certain extent, but the field of energy conservation still has a great exploration space, and especially has a great prospect on supply and demand balance. The energy is thinned to the compressed air, so that the compressed air is a representative energy which is worthy of research, is an important energy source for producing cigarettes, is a main power source except electricity, is generally used on equipment for making filaments, rolling, connecting and packaging cigarettes and the like, and is also used in multiple processes such as a boiler, blowing, forming and the like, so that the purposes of saving energy, reducing emission and reducing cost are achieved, and the problem of cooperative matching of the production and energy utilization ends of the compressed air is particularly important to solve.
The related art for compressing air mainly has the following problems:
the prior art can not achieve the dynamic accurate matching of the demand pressure (demand end) of the energy utilization equipment end and the supply pressure (supply end) of the air compressor, and the pressure supply and demand imbalance can cause the overfeeding of compressed air. The existing starting strategy of the air compressor for producing compressed air lacks scientific bases such as analysis, prediction, decision and the like, and is mainly controlled by human experience.
The problems encountered in the actual production process are as follows:
the demand of compressed air is related to many factors, including the magnitude of the required pressure, the yield, the production time, the difference of the process paths, the unit difference and the like; the yield of compressed air is also affected by different factors, such as individual differences of air compressors; uncertainty exists in the consumption process of the compressed air;
therefore, the requirements for energy management and control are higher and higher, the use process of the compressed air is more and more complex today, the control strategy needs to be updated timely through online real-time monitoring, the planned demand of the compressed air, the energy consumption time period, the energy consumption process requirement, the energy consumption end air supply pressure, the energy consumption equipment state, the air storage tank parameter, the air compressor operation parameter and other data are comprehensively collected, an analysis, monitoring and control model is constructed based on mechanism and big data, and is integrated with an air compressor group control system, the air pressure supply state monitoring, the abnormity early warning and the air pressure production automatic organization and the optimization regulation of the energy consumption end are realized, and the balance and the energy-saving operation of the demand end and the supply end are realized. Disclosure of Invention
With the increasingly outstanding requirements on accurate supply and energy conservation and emission reduction, an optimal supply strategy needs to be searched according to algorithms such as historical data analysis and curve fitting, corresponding data basis support is provided, the formulation of internal control standards is assisted and verified, the strategy is adjusted in time, the waste of compressed air is reduced to the greatest extent while the capacity of the compressed air is ensured to meet the requirements, and the purpose of energy conservation is further achieved.
In order to achieve the purpose, the invention adopts the following technical scheme: the optimization method comprises the following steps:
predicting an energy demand pressure curve based on APS detailed scheduling;
step two, calculating a set pressure curve of the air compressor based on the energy consumption demand pressure curve;
thirdly, calculating an optimal gas production speed curve of each air compressor based on historical data;
step four, predicting the gas consumption speed of the equipment terminal based on the set pressure curve and the APS detailed schedule;
and step five, establishing a gas production speed and gas consumption speed cooperative matching model to carry out starting optimization on the air compressor.
Preferably, in the second step, the set pressure curve of the air compressor is calculated based on the energy demand pressure curve; the detailed method comprises the following steps: the set pressure of the air compressor is matched with the equipment end demand pressure by taking the equipment end demand pressure plus the pipeline loss pressure (exhaust pressure 10%) as the demand pressure in the time period, so that the corresponding set pressure of the air compressor can be obtained, and the formula is as follows:
therefore, the method can obtain:
the curve of the set pressure can be drawn according to the time.
Preferably, the third step of calculating the optimal gas production speed curve of each air compressor based on historical data comprises the following detailed steps: dividing the value range of the set pressure of each air compressor into a plurality of intervals, counting the gas production speed and the power consumption speed in each pressure interval, drawing a curve with the vertical axis as a gas-electricity ratio and the ratio of the gas production speed to the power consumption speed and the horizontal axis as the gas production speed, finding the gas production speed with the maximum gas-electricity ratio, and taking the gas production speed as the production caliber of the air compressor, which is the most energy-saving gas production speed which can be achieved by the air compressor in the given pressure interval.
Preferably, the fourth step of predicting the gas consumption rate of the equipment terminal based on the set pressure curve and the detailed schedule of the APS comprises the following specific steps: establishing a data model for predicting the gas consumption speed of the equipment end, wherein the model prediction adopts a data-driven prediction algorithm, and the steps are as follows: data preprocessing, working condition segmentation, feature generation, feature dimension reduction or selection, model training and verification.
Preferably, the fifth step of establishing a cooperative matching model of gas production speed and gas consumption speed to optimize the starting of the air compressor is specifically realized by adopting the following steps:
step1, setting two states of opening and closing for n air compressors, wherein the states are represented as 1 and 0 in data and programs, and accordingly, all switch combinations of the air compressors are listed for the total
Seed combination;
step2, according to the second step, obtaining the optimal (energy-saving) gas production speed under different pressure intervals, wherein the optimal gas production speed is used as the gas production speed of each air compressor under the pressure;
step3, after the set pressure and the starting combination are given, according to the number of the started air compressors in each combination, and the gas production speed of each air compressor under the set pressure, the total gas production speed of the corresponding air compressor combination is calculated;
step4. taking the peak value of the predicted value of the air consumption speed of the compressed air in the previous period (for example, 30 minutes), and comparing the peak value with the predicted value
Respectively differentiating the total gas production speeds of the seed air compressor combination, taking an absolute value, and selecting the air compressor combination with the minimum absolute value as the starting combination on the same day;
step5, after the optimal starting combination on the same day is determined, a dynamic matching method is further adopted to timely change the starting combination to adapt to the change of the requirement, and the predicted value of the compressed air consumption speed in each specific time period is selected to be matched with the predicted value
The total gas production speed of the air compressor combination is respectively differentiated, the difference with the minimum absolute value is taken as an approaching basis, the algorithm logic is consistent with the first starting combination strategy, the starting combination can be continuously adjusted along with the time, the purposes of meeting the requirements and saving energy in each specific time period are achieved, and the purposes of meeting the requirements and saving energy all day long are achieved.
The invention has the beneficial effects that:
the starting method of the air compressor is obtained. And automatically setting a starting combination according to scheduling plan data preset in part of workshops to provide guidance for the production of compressed air. Energy-saving benefit. The supply and demand of compressed air are accurately matched, so that the purposes that the supply just meets the requirements of production departments and the waste caused by excess production is avoided are achieved. Environmental protection benefit. The energy production is not blind, the consumption is reduced, and the method can contribute to energy conservation, emission reduction and green factory establishment. The management level of compressed air production is improved. The leaders of factories and production departments needing compressed air can make production decisions according to real-time data on the network, and real-time and scientific references are provided for the decisions.
Drawings
FIG. 1 is a schematic flow chart of a starting method of an air compressor;
FIG. 2 is a block diagram of a compressed air consumption predictive modeling overview;
FIG. 3 implements a flow diagram;
FIG. 4 is a diagram of a model structure for predicting the gas consumption speed of the equipment end in the step four;
FIG. 5 is a diagram of a compressed air metering network;
FIG. 6 is a comparison graph of the prediction and the actual value of the compressed air in the filament making section;
FIG. 7 is a graph comparing predicted and actual values for compressed air in the wrapping section;
FIG. 8 is a plot of compressed air prediction versus real values for a forming section.
Detailed Description
In order to facilitate the understanding and implementation of the present invention for those skilled in the art, the technical solutions of the present invention will be further described with reference to the accompanying drawings and specific embodiments.
With the increasingly outstanding requirements on accurate supply and energy conservation and emission reduction, an optimal supply strategy needs to be searched according to algorithms such as historical data analysis and curve fitting, corresponding data basis support is provided, the formulation of internal control standards is assisted and verified, the strategy is adjusted in time, the waste of compressed air is reduced to the greatest extent while the capacity of the compressed air is ensured to meet the requirements, and the purpose of energy conservation is further achieved.
(1) Energy demand pressure curve based on APS detailed scheduling prediction
According to the APS scheduling work order, the next day work order execution arrangement can be obtained, and each work order corresponds to
The resulting devices all have their pressure requirements.
The pressure that the air compressor machine need provide only need make the biggest equipment of demand pressure also can normally operate can, consequently only need find all work orders in the execution under the specific time quantum, and select the equipment of the biggest demand pressure among them, just can use the equipment end demand pressure in the current time end.
(2) Calculating set pressure curve of air compressor based on energy consumption demand pressure curve
According to the document of GB50029-2014 compressed air station design specification, in a compressed air pipeline system with the working pressure not exceeding 1.6Mpa, namely 16bar, the pressure loss from the outlet of an air compressor to the most unfavorable point should not exceed 10% of the exhaust pressure, the working pressure of the system does not exceed 6.5bar, therefore, 10% of the exhaust pressure is taken as the pipeline loss pressure, which is enough to meet the requirement, and therefore, the equipment end demand pressure plus the pipeline loss pressure (10% of the exhaust pressure) can be taken as the demand pressure in the time period.
At this moment, match the set pressure of air compressor machine and equipment end demand pressure, alright in order to obtain the set pressure of the air compressor machine that corresponds, the formula is as follows:
therefore, the method can obtain:
the curve of the set pressure can be drawn according to the time.
(3) Calculating the optimal gas production speed curve of each air compressor based on historical data
Once the set pressure is given, the air compressor automatically performs pressure matching, the problem to be considered is changed into the condition for maintaining the current pressure, namely, the gas production speed is equal to the gas consumption speed, so that the gas quantity in the gas storage tank is not changed, and the pressure is not changed. Next, it should be considered that an air compressor with high gas production efficiency and energy saving is selected under different pressures, so that the air compressor can meet the pressure requirement and achieve the purpose of energy saving at the same time, and the specific implementation method is as follows:
dividing the value range of the set pressure of each air compressor into a plurality of intervals, and counting the pressure intervals
The vertical axis is drawn as the gas-electricity ratio (the ratio of the gas production speed to the power consumption speed), the horizontal axis is the curve of the gas production speed, the gas production speed with the largest gas-electricity ratio is found, and the gas production speed is taken as the production caliber of the air compressor, which is the most energy-saving gas production speed which can be achieved by the air compressor in a given pressure interval.
(4) Prediction of equipment end gas consumption speed based on set pressure curve and APS detailed schedule
In order to solve the problems of traditional control and asymmetric output and consumption caused by various influencing factors, the influence of various factors such as environment, work orders, equipment and the like on result variables is fully considered in combination with pressure setting requirements, and a function of predicting the compressed air consumption at the equipment end is designed in the step. The compressed air consumption prediction modeling overall structure is shown in fig. 2:
the model prediction adopts a data-driven prediction algorithm, and the general steps are as follows: data preprocessing, working condition segmentation, feature generation, feature dimension reduction or selection, model training and verification. The data preprocessing can carry out data cleaning (including abnormal value elimination and missing value interpolation) on the acquired original data; then, working condition segmentation is carried out, and data exploration is carried out according to the working conditions; then, generating more dimensional features including time domain features, frequency domain features and time-frequency domain features according to different characteristics of data, and performing dimension reduction or selection on the generated features, wherein the general feature dimension reduction or selection comprises a PCA (principal component analysis) method, a LASSO method and the like; next, modeling is carried out by utilizing a machine learning model, common machine learning methods comprise a decision tree, a random forest, Adaboost, a neural network and the like, and various models can be tested according to different real data so as to select an optimal model; finally, the model fitting result needs to be verified, and the most common method is a coefficient-determining method or a cross verification method.
And the influence of various factors such as work orders, equipment and the like on result variables is fully considered in combination with the pressure setting requirement, and the function of predicting the compressed air consumption speed at the equipment end is designed. Aiming at the selection of a prediction model, a large amount of historical data of departments such as coiling, wire making, forming and the like needs to be acquired, different data reconstruction methods of selectable prediction models (decision trees, random forests, Adaboost, neural networks and the like) are respectively tested on a data mining platform, comparison and evaluation are carried out on the aspects of goodness of fit, MSE, RMSE and the like, an optimal algorithm model is selected, and an algorithm with an optimal evaluation index, namely a compressed air gas consumption speed prediction model, is finally adopted after the comparison in the process.
(5) Optimization of starting of air compressor based on establishment of gas production speed and gas consumption speed cooperative matching model
For the predicted compressed air gas consumption speed in a specific time period, a set of air compressor starting strategies are designed for controlling the gas production speed of the air compressor so as to enable the gas production speed of the air compressor to be closest to the compressed air gas consumption speed in real time. The starting method of the air compressor is mainly characterized in that the gas production speed is adapted to the gas consumption speed so as to ensure the most energy-saving realization under the condition of pressure balance, the strategy can be automatically adjusted in real time according to historical data every day, the essence of statistics and machine learning is really realized, the history is learned so as to deduce the future, and the specific deduction and combination process is as follows:
setting two states of opening and closing for n air compressors, wherein the states are represented as 1 and 0 in data and programs, and accordingly, the switch combinations of the air compressors are listed up and have the same structure
And (4) combination.
According to the step (2), the optimal (energy-saving) gas production speed in different pressure intervals can be obtained, and because the air compressors are variable-frequency, the air compressors can achieve pressure balance under the set pressure and then are intelligently adjusted to the optimal gas production speed, the optimal gas production speed is taken as the gas production speed of each air compressor under the pressure
After the set pressure and the starting combination are given, the total gas production speed of the corresponding air compressor combination is calculated according to the number of the started air compressors in each combination and the gas production speed of each air compressor under the set pressure.
Taking the peak value of the predicted air consumption speed of the compressed air in the previous period (for example, 30 minutes) and comparing the peak value with the predicted air consumption speed
The total gas production speed of the air compressor combination is respectively differentiated, the absolute value is taken, and the air compressor combination with the minimum absolute value is selected as the starting combination on the same day.
When the total air production speed of the selected air compressor combination is greater than the peak value of the predicted value of the air consumption speed of the compressed air, the production requirement can be obviously met, and the air compressor combination is in the most energy-saving state; when the total gas production speed of the selected air compressor combination is less than the peak value of the predicted value of the gas consumption speed of the compressed air, the frequency conversion function of the air compressor can also automatically adjust and complement the shortage of the gas production speed, which is not the optimal gas production speed, but has small difference and can be completely accepted
After the optimal starting combination on the same day is determined, a dynamic matching method is further adopted to change the starting combination in time so as to adapt to the change of the requirement, and the predicted value of the compressed air consumption speed in each specific time period is selected firstly to be matched with the predicted value
The total gas production speed of the air compressor combination is respectively differentiated, the difference with the minimum absolute value is taken as an approaching basis, the algorithm logic is consistent with the first starting combination strategy, the starting combination can be continuously adjusted along with the time, the purposes of meeting the requirements and saving energy in each specific time period are achieved, and the purposes of meeting the requirements and saving energy all day long are achieved.
The first embodiment is as follows:
fig. 3 is a flow chart showing an implementation of an air compressor starting optimization method cooperatively matched with the pressure of a production energy end, and the method comprises the following steps: step one, predicting a required pressure curve of an equipment end; predicting a set pressure curve of the air compressor; calculating an optimal gas production speed curve of the air compressor; fourthly, predicting the gas consumption speed of the equipment end; and step five, setting a starting strategy of the air compressor.
1. In the first step, the required pressures of all production equipment are listed firstly, all the work orders planned to be executed in each fixed time period (for example, 10 minutes) are found according to the planned work orders, the equipment with the largest pressure requirement is selected according to the equipment condition used in each work order, the required pressure of the equipment is taken as the required pressure of the equipment end in the time period, and finally the required pressure is drawn into an equipment end required pressure curve according to time.
2. In the second step, the required pressure of the equipment end and the pipeline loss pressure are summed to obtain the total required pressure, and the total required pressure is used for matching the set pressure of the air compressor, namely the supply pressure, so that the production pressure which is finally required to be set for the air compressor can be obtained.
3. In the third step, the value range of the set pressure of each air compressor is divided into a plurality of intervals, the gas production speed and the power consumption speed in each pressure interval are counted, the curve with the vertical axis as the gas-electricity ratio (the ratio of the gas production speed to the power consumption speed) and the horizontal axis as the gas production speed is drawn, the gas production speed with the largest gas-electricity ratio is found, and the gas production speed is taken as the production caliber of the air compressor, which is the most energy-saving gas production speed which can be achieved by the air compressor in the pressure interval.
4. In the fourth step, the compressed air consumption speed is obtained by summing the air consumption speeds of different parts, and the data structures of the different parts are different, so that the air consumption speeds of the parts are required to be respectively predicted by modeling in different parts, and the prediction model structure is shown in fig. 4. Firstly, from the network diagram of compressed air energy metering, see fig. 5, it can be known that the air compressor mainly consumes the processes of rolling, shredding and forming.
Thus: predicted total compressed air consumption = predicted shred compressed air consumption + predicted package compressed air consumption + predicted forming compressed air consumption + power section compressed air consumption (constant).
The concrete modeling mode of each department is as follows:
selecting characteristics of a silk making consumption part: selecting a pressure related to the consumption of compressed air, a process path of the process section as an input variable, including, but not limited to, a current compressed air set pressure, a plurality of process paths of the process section for making filaments; the compressed air consumption of the silk production department (including the compressed air 1, the compressed air 2 and the dust removal compressed air of the silk making workshop) is taken as an output variable.
Selecting characteristics of a volume consumption part: selecting pressure related to compressed air consumption, and taking the serial numbers and the brand codes of a plurality of machine sets of the wrapping process section as input variables; the consumption of the compressed air in the rolling and packing process (including compressed air 1 in the rolling and packing process, compressed air 2 in the rolling and packing process and compressed air 3 in the rolling and packing process) is taken as an output variable.
Selecting characteristics of a forming consumption part: selecting a pressure related to the compressed air consumption, a plurality of unit codes of the forming process section as input variables; the molding compressed air consumption (including molding compressed air (total)) is taken as an output variable.
And (3) construction of a silk making model:
the original data comprises the sending data and the feedback data. In the feedback data, each work order corresponds to data such as a work time period and a corresponding process path, and the data is processed into data in units of a fixed time period (for example, 10 minutes). The daily working time is divided into a plurality of small sections with fixed time intervals (for example, 10 minutes), each small section corresponds to the working state of each work order, and the amount of the compressed air consumed in the time interval. And establishing a prediction model by taking the compressed air consumption as a response variable and the working state of each process path as an independent variable. And taking the last two days of the feedback data as test data, and taking the rest data as training data. Fitting multiple models (neural nets) with training dataLuo, random forest, XGboost, Adaboost, etc.), and then selecting the model (in the test data) with the best test effect by using the test data
As a criterion). And finally selecting a random forest model. The issued data is also processed into data corresponding to the working state of each process path in a unit of 10 minutes. And the consumption of the compressed air at the corresponding time can be predicted by substituting the processed issuing data into the model.
And (3) building a rolling model:
the original data also comprises the sending data and the feedback data. The data is processed into data in units of a fixed period of time (e.g., 10 minutes). The daily working time is divided into a plurality of small sections with the width of a fixed time period (for example, 10 minutes), the planned output of the set-up time corresponding to different unit codes and the planned output of the set-up time with different brand codes in the fixed time period (for example, 10 minutes) in each day are calculated and used as input variables, and meanwhile, the consumption of compressed air (comprising compressed air in a bale workshop, compressed air in the bale workshop and compressed air 3 in the bale workshop) in the fixed time period (for example, 10 minutes) in the bale part is used as a response variable. The method comprises the steps of constructing a self-adaptive data driving model according to input variables and response variables, comprehensively evaluating unit codes and brand codes, predicting the volume of the wrapped compressed air consumption according to planned unit codes and brand codes, calculating errors with actually monitored compressed air consumption, correcting data and the model by using analysis feedback of the errors, and forming parameter regulation and control suggestion instructions. Aiming at prediction model selection, a large amount of historical data of relevant parameters are required to be obtained, different data reconstruction methods of selectable prediction models (decision trees, random forests, Adaboost and the like) are respectively tested on a data mining platform, comparison evaluation is carried out on the aspects of goodness of fit, MSE, RMSE and the like, and an optimal algorithm model is selected. The model finally selected is the Adaboost model.
Building a forming model:
the original data comprises issued data and feedback data of the mouth rod and the sealing box. Because the consumption of the compressed air is only the total consumption of the molding part, the assigned data and the feedback data of the mouth bar and the box sealing part are respectively combined to obtain the total assigned work order data and the feedback work order data of the molding. Still, the data is processed into data in units of a fixed period of time (e.g., 10 minutes). The daily working time is divided into a plurality of small sections with the width of a fixed time period (for example, 10 minutes), the starting time corresponding to different unit codes per day is calculated as an input variable, and the compressed air consumption of each fixed time period (for example, 10 minutes) of the molding part is used as a response variable. And (4) carrying out comparison evaluation on the processed feedback data fitting model from the aspects of goodness of fit, MSE, RMSE and the like, selecting an optimal algorithm model, and finally selecting a bar Boosting model. And then, the processed issuing data is brought into the constructed model, so that the consumption of the compressed air molded in the corresponding time period can be predicted.
5. In the fifth step, the step adopts the predicted value of the compressed air gas consumption speed of each fixed time period (for example, 10 minutes) obtained in the step4, a set represents the air compressor combination, the optimal gas production speed of the air compressor obtained in the step3 is taken as a production caliber and substituted into the set to obtain the gas production speed of the combination, the peak value of the predicted value of the gas consumption speed in the previous period (for example, 10 minutes) traverses the gas production speed of all the combinations to further obtain the air compressor combination corresponding to the gas production speed closest to the gas consumption speed, the combination is taken as the starting combination in the fixed time period (for example, 10 minutes), and then each fixed time period (for example, 10 minutes) is iterated once to obtain a new starting combination.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. The utility model provides an air compressor machine that matches with pressure cooperation of production energy end starts optimization method which characterized in that: the optimization method comprises the following steps:
predicting an energy demand pressure curve based on APS detailed scheduling;
step two, calculating a set pressure curve of the air compressor based on the energy consumption demand pressure curve;
thirdly, calculating an optimal gas production speed curve of each air compressor based on historical data;
step four, predicting the gas consumption speed of the equipment terminal based on the set pressure curve and the APS detailed schedule;
and step five, establishing a gas production speed and gas consumption speed cooperative matching model to carry out starting optimization on the air compressor.
2. The method for optimizing the starting of the air compressor cooperatively matched with the pressure of the energy end for production as claimed in claim 1, wherein: secondly, calculating a set pressure curve of the air compressor based on the energy consumption demand pressure curve; the detailed method comprises the following steps: the set pressure of the air compressor is matched with the equipment end demand pressure by taking the equipment end demand pressure plus the pipeline loss pressure (exhaust pressure 10%) as the demand pressure in the time period, so that the corresponding set pressure of the air compressor can be obtained, and the formula is as follows:
therefore, the method can obtain:
the curve of the set pressure can be drawn according to the time.
3. The method for optimizing the starting of the air compressor cooperatively matched with the pressure of the energy end for production as claimed in claim 1, wherein: step three, calculating the optimal gas production speed curve of each air compressor based on historical data, and the detailed steps are as follows: dividing the value range of the set pressure of each air compressor into a plurality of intervals, counting the gas production speed and the power consumption speed in each pressure interval, drawing a curve with the vertical axis as a gas-electricity ratio and the ratio of the gas production speed to the power consumption speed and the horizontal axis as the gas production speed, finding the gas production speed with the maximum gas-electricity ratio, and taking the gas production speed as the production caliber of the air compressor, which is the most energy-saving gas production speed which can be achieved by the air compressor in the given pressure interval.
4. The method for optimizing the starting of the air compressor cooperatively matched with the pressure of the energy end for production as claimed in claim 1, wherein: step four, predicting the gas consumption speed of the equipment terminal based on the set pressure curve and the APS detailed schedule, wherein the specific method comprises the following steps: establishing a data model for predicting the gas consumption speed of the equipment end, wherein the model prediction adopts a data-driven prediction algorithm, and the steps are as follows: data preprocessing, working condition segmentation, feature generation, feature dimension reduction or selection, model training and verification.
5. The method for optimizing the starting of the air compressor cooperatively matched with the pressure of the energy end for production as claimed in claim 1, wherein: and step five, establishing a gas production speed and gas consumption speed cooperative matching model for starting and optimizing the air compressor, and specifically adopting the following steps:
step1, setting two states of opening and closing for n air compressors, wherein the states are represented as 1 and 0 in data and programs, and accordingly, all switch combinations of the air compressors are listed for the total
Seed combination;
step2, according to the second step, obtaining the optimal (energy-saving) gas production speed under different pressure intervals, wherein the optimal gas production speed is used as the gas production speed of each air compressor under the pressure;
step3, after the set pressure and the starting combination are given, according to the number of the started air compressors in each combination, and the gas production speed of each air compressor under the set pressure, the total gas production speed of the corresponding air compressor combination is calculated;
step4. taking the peak value of the predicted value of the air consumption speed of the compressed air in the previous period (for example, 30 minutes), and comparing the peak value with the predicted value
Respectively differentiating the total gas production speeds of the seed air compressor combination, taking an absolute value, and selecting the air compressor combination with the minimum absolute value as the starting combination on the same day;
step5, after the optimal starting combination on the same day is determined, a dynamic matching method is further adopted to timely change the starting combination to adapt to the change of the requirement, and the predicted value of the compressed air consumption speed in each specific time period is selected to be matched with the predicted value
The total gas production speed of the air compressor combination is respectively differentiated, the difference with the minimum absolute value is taken as an approaching basis, the algorithm logic is consistent with the first starting combination strategy, the starting combination can be continuously adjusted along with the time, the purposes of meeting the requirements and saving energy in each specific time period are achieved, and the purposes of meeting the requirements and saving energy all day long are achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111375721.7A CN114154692A (en) | 2021-11-19 | 2021-11-19 | Air compressor starting optimization method cooperatively matched with pressure of production energy end |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111375721.7A CN114154692A (en) | 2021-11-19 | 2021-11-19 | Air compressor starting optimization method cooperatively matched with pressure of production energy end |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114154692A true CN114154692A (en) | 2022-03-08 |
Family
ID=80456768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111375721.7A Pending CN114154692A (en) | 2021-11-19 | 2021-11-19 | Air compressor starting optimization method cooperatively matched with pressure of production energy end |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114154692A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115471145A (en) * | 2022-11-15 | 2022-12-13 | 碳管家智能云平台有限公司 | Enterprise energy consumption double-control management method, device and medium |
| TWI806611B (en) * | 2022-04-25 | 2023-06-21 | 緯創資通股份有限公司 | Optimization systems and methods for operating air compressor groups |
-
2021
- 2021-11-19 CN CN202111375721.7A patent/CN114154692A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI806611B (en) * | 2022-04-25 | 2023-06-21 | 緯創資通股份有限公司 | Optimization systems and methods for operating air compressor groups |
| CN115471145A (en) * | 2022-11-15 | 2022-12-13 | 碳管家智能云平台有限公司 | Enterprise energy consumption double-control management method, device and medium |
| CN115471145B (en) * | 2022-11-15 | 2024-06-04 | 碳管家智能云平台有限公司 | Dual-control management method, device and medium for enterprise energy consumption |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114154692A (en) | Air compressor starting optimization method cooperatively matched with pressure of production energy end | |
| WO2021189739A1 (en) | Production plan-based iron and steel plant oxygen load prediction method | |
| CN105275508A (en) | Steam turbine flow curve identification and optimization method based on power value calculation | |
| CN107292766A (en) | Towards the power system peak regulation means economic evaluation method and system of wind electricity digestion | |
| CN105787583A (en) | Metallurgical gas integrated dynamic balance scheduling system and method | |
| EP3974918B1 (en) | A method for controlling a compressor room and an apparatus thereof | |
| CN110414725B (en) | Wind power plant energy storage system scheduling method and device integrating prediction and decision | |
| CN110513281A (en) | Compressed air system optimal control method based on load prediction | |
| CN113107626A (en) | Combined cycle generator set load prediction method based on multivariable LSTM | |
| CN107612045A (en) | A kind of Power Plant generated energy intelligent dispensing system and method | |
| CN114688010B (en) | Water pump energy-saving consumption-reducing control method | |
| CN117514727B (en) | Digital energy air compression station | |
| CN114266408A (en) | Power distribution network engineering operation and maintenance cost optimization method and system | |
| CN111950166B (en) | Cost optimization method for household paper making machine based on data mining | |
| CN117312763A (en) | Variable frequency household appliance performance visual supervision system and method based on cloud platform | |
| CN115841081A (en) | Welding process parameter optimization method based on welding quality, cost and carbon emission | |
| CN114219204A (en) | Intelligent management system for energy demand | |
| CN111461449A (en) | Power load prediction method and computer program product | |
| CN104866725A (en) | Method for predicting steam consumption of cigarette enterprise on the basis of least squares support vector machine | |
| Gao et al. | A review of different methodologies for solving the problem of wind power's fluctuation | |
| CN110633844A (en) | Building energy system simulation prediction method based on EMD and ANN and application | |
| CN111852596B (en) | Method for predicting operation parameters and relative power generation coal consumption rate of boiler steam turbine generator unit | |
| CN117556217B (en) | Water-cooling central air conditioner energy-saving control method based on heterogeneous graph neural network and reinforcement learning | |
| CN114658499B (en) | Control method and device for operation of steam turbine of thermal power plant | |
| CN113361763B (en) | Full-time operation optimization method and system for gas transmission pipe network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |