CN114417530B - Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station - Google Patents

Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station Download PDF

Info

Publication number
CN114417530B
CN114417530B CN202210044719.XA CN202210044719A CN114417530B CN 114417530 B CN114417530 B CN 114417530B CN 202210044719 A CN202210044719 A CN 202210044719A CN 114417530 B CN114417530 B CN 114417530B
Authority
CN
China
Prior art keywords
cooling water
pump station
rolling
laminar cooling
laminar
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.)
Active
Application number
CN202210044719.XA
Other languages
Chinese (zh)
Other versions
CN114417530A (en
Inventor
宋勇
王奋嘉
何安瑞
荆丰伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Science and Technology Beijing USTB
Original Assignee
University of Science and Technology Beijing USTB
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Science and Technology Beijing USTB filed Critical University of Science and Technology Beijing USTB
Priority to CN202210044719.XA priority Critical patent/CN114417530B/en
Publication of CN114417530A publication Critical patent/CN114417530A/en
Application granted granted Critical
Publication of CN114417530B publication Critical patent/CN114417530B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/08—Fluids
    • 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
    • G06F2119/08—Thermal analysis or thermal optimisation

Abstract

The invention discloses an optimal scheduling method and device for a hot continuous rolling laminar cooling water supply pump station, wherein the method comprises the following steps: acquiring rolling process data related to the water consumption for laminar cooling and the water consumption for laminar cooling, and preprocessing the acquired data to generate a training sample; training a laminar cooling water consumption prediction model by using a training sample, calculating the laminar cooling water consumption of a single strip steel, and predicting the laminar cooling water trend of a unit rolling period according to rolling rhythm time; performing real-time feedback optimization on a pump station scheduling instruction according to the trend of laminar cooling water and the technological requirement of laminar cooling water, and reducing cooling water overflow while stabilizing the pressure of cooling water; and optimizing the pump station operation scheme of the unit rolling period by taking the minimum total shaft power of the pump station as a target according to the optimized scheduling instruction. The invention ensures the cooling quality of the strip steel and effectively reduces the resource waste while keeping the supply and demand balance of the system.

Description

Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station
Technical Field
The invention relates to the technical field of hot continuous rolling, in particular to an optimal scheduling method and device for a hot continuous rolling laminar cooling water supply pump station.
Background
The hot continuous rolling laminar cooling system provides cooling which accords with the production process for strip steel so as to ensure the quality of strip steel products, but because of the diversity of product specifications and the complexity of intermittent production working conditions, a pump station is difficult to meet the water demand which changes frequently. The cooling quality of the strip steel is ensured by generally adopting a mode of filling the high-level water tank in a long-term full state on site, the scheduling mode increases the ineffective power consumption of a pump station and the sewage treatment cost of a workshop, and reduces the effective utilization rate of resources. Therefore, the method has high application value for the optimized scheduling of the laminar cooling water supply pump station.
The current laminar flow cooling water supply pump station optimized scheduling has the following technical difficulties:
1. laminar cooling adopts a segmented feedback control mechanism, the cooling water of each segment of strip steel is in a real-time change state, and the water consumption of the whole piece of strip steel is difficult to accurately predict by a traditional mechanism model.
2. The strip steel rolling rhythm is fast, and the scheduling instruction is difficult to update for the pump station in real time according to the cooling characteristic and the rolling rhythm time on an industrial site.
3. The operation efficiency of the water pump is difficult to guarantee under the intermittent production working condition, and meanwhile, the solving precision and the time of the optimization model of the water pump operation scheme are also a main factor for restricting the energy efficiency improvement of the system.
Therefore, in order to improve the energy efficiency of the laminar cooling water supply pump station, how to make a set of flexible and efficient laminar cooling water supply pump station optimization scheduling technical scheme according to the laminar cooling characteristic and the rolling rhythm time is considered at first.
Disclosure of Invention
The invention provides an optimal scheduling method and device for a hot continuous rolling laminar cooling water supply pump station, which are used for solving the problem of resource waste of the conventional laminar cooling system and ensuring the cooling quality of strip steel.
In order to solve the technical problems, the invention provides the following technical scheme:
in one aspect, the invention provides an optimized scheduling method for a hot continuous rolling laminar cooling water supply pump station, which comprises the following steps:
acquiring rolling process data related to the water consumption for laminar cooling and the water consumption for laminar cooling of a single strip steel, and preprocessing the acquired rolling process data and the water consumption for laminar cooling to generate a training sample;
training a preset laminar cooling water consumption prediction model by using the training sample; the input of the laminar cooling water consumption prediction model is rolling process data, and the output is single strip steel laminar cooling water consumption;
calculating the predicted value of the water consumption for laminar cooling of the single strip steel by using the trained model for predicting the water consumption for laminar cooling, and predicting the trend of the water consumption for laminar cooling in a unit rolling period according to the rolling rhythm time;
according to the predicted trend of the laminar cooling water and the technological requirement of the laminar cooling water, real-time feedback optimization is carried out on a pump station scheduling instruction, so that the cooling water overflow is reduced while the pressure of the cooling water is stabilized;
and optimizing the pump station operation scheme of the unit rolling cycle by taking the minimum total shaft power of the pump station as a target according to the optimized pump station scheduling instruction to obtain the optimal pump station operation scheme of the unit rolling cycle.
Further, the step of obtaining rolling process data and laminar cooling water consumption related to the laminar cooling water consumption of the single strip steel, and preprocessing the obtained rolling process data and laminar cooling water consumption to generate a training sample includes:
extracting all relevant rolling process data and laminar cooling information in a single strip steel laminar cooling sectional feedback control record set, averaging the extracted data, calculating the laminar cooling water consumption of the single strip steel based on the averaged laminar cooling information, and forming an initial training sample by the averaged rolling process data and the laminar cooling water consumption; wherein the rolling process data comprises: the method comprises the following steps of strip steel specification, rolling rhythm time and rolling process parameters, wherein the strip steel specification comprises the following steps: strip steel thickness, width and steel type; the rolling process parameters comprise: rolling force, rolling speed, strip steel finish rolling temperature and coiling temperature; the laminar cooling information refers to a laminar cooling header switch set value, cooling water temperature and header rated flow;
preprocessing the initial sample to generate preprocessed sample data; wherein the pre-processing comprises: abnormal value detection processing and normalization processing;
and uniformly sampling the preprocessed sample data according to the specification of the strip steel to generate a final training sample. Further, the calculation formula of the water consumption for laminar cooling of the single strip steel is as follows:
C w ＝(R mean V R +F mean V F )t C
wherein, C W Represents the water consumption, R, of laminar cooling of a single strip steel mean Header switch average, V, representing coarse tuning region R Unit header flow rate, F, indicating coarse tuning zone mean Mean number of header switches, V, representing fine tuning area F Unit header flow rate, t, representing fine adjustment zone C The cooling time is indicated.
Further, pre-processing the initial sample, comprising:
and carrying out abnormal value detection on the initial samples according to a 3 sigma rule, removing data which do not conform to the specification, and then carrying out Max-Min standardization processing on the samples after data removal.
Further, the preset laminar cooling water consumption prediction model is an OS-ELM model;
the method for predicting the laminar cooling water consumption of the single strip steel by utilizing the trained laminar cooling water consumption prediction model and predicting the laminar cooling water consumption trend of a unit rolling period according to the rolling rhythm time comprises the following steps:
generating a predicted value of the water consumption for laminar cooling of each strip steel in the current rolling period according to current rolling process data by using a trained laminar cooling water consumption prediction model;
obtaining rolling rhythm time information of a current rolling period; wherein, the rolling rhythm time information comprises: cooling time and cooling interval time of adjacent strip steels;
and calculating the change trend of the current laminar cooling water consumption of the rolling period according to the current rolling period rolling rhythm time information on the basis of the predicted value of the cooling water consumption of the single strip steel.
Further, according to the predicted laminar flow cooling water trend and the laminar flow cooling water process demand, the pump station scheduling instruction is subjected to real-time feedback optimization so as to reduce cooling water overflow while stabilizing the cooling water pressure, and the method comprises the following steps:
selecting water level characteristic points according to the rolling rhythm; the water level characteristic points are the water level of a high-level water tank at the beginning of strip steel cooling and the water level of the high-level water tank at the end of strip steel cooling;
determining a pump station scheduling instruction optimization objective function and constraint conditions; the constraint conditions comprise the upper limit and the lower limit of the water level of the high-level water tank and the overflow quantity of cooling water; the pump station scheduling instruction optimization objective function is as follows:
min{β[θ(C 1 +C 2 )]+(1-β)(YL 1 +YL 2 )}
wherein, C 1 Representing the total of the variation of the water level of the high-level water tank in the rolling period, YL 1 Indicating the total overflow of the head tank during operation, C 2 Representing a penalty item of a limiting water level constraint condition of the high-level water tank; YL (aryl alcohol) 2 The method comprises the steps of representing an overflow quantity constraint condition penalty term, representing a bias coefficient by beta, and representing a water level-overflow quantity conversion coefficient by theta;
solving the pump station dispatching instruction optimization objective function, and outputting the dispatching instruction after the rolling cycle pump station optimization;
and updating and adjusting the pump station dispatching instruction in real time according to the predicted laminar cooling water trend, the laminar cooling water process demand and the water level measured value based on the optimized dispatching instruction.
Further, a penalty term C of a limiting water level constraint condition under the high-level water tank 2 Comprises the following steps:
Figure BDA0003471676330000031
Figure BDA0003471676330000032
wherein the content of the first and second substances,
Figure BDA0003471676330000033
represents the penalty coefficient, i represents the number of the strip steel, m represents the number of the strip steel, h 1,i Indicates the water level of the high level tank at the end of strip cooling, h min The lower limit of the water level of the high-level water tank is represented;
overflow constraint penalty term YL 2 Comprises the following steps:
Figure BDA0003471676330000041
wherein γ represents a penalty coefficient, Y i And the overflow amount of the high-level water tank when the ith strip steel is cooled is shown.
Further, according to the optimized pump station scheduling instruction, optimizing the pump station operation scheme of the unit rolling cycle by taking the minimum power of the total shaft of the pump station as a target to obtain the optimal pump station operation scheme of the unit rolling cycle, wherein the method comprises the following steps:
acquiring an optimal pump station scheduling instruction;
determining an optimized objective function and constraint conditions of a pump station operation scheme; wherein the constraint condition comprises: speed regulation ratio constraint, water pump lift constraint, pump station total flow constraint and high-efficiency interval constraint;
converting the constraint condition into an external punishment item of the pump station operation scheme optimization objective function; the pump station operation scheme optimization objective function with the external constraint penalty term is as follows:
min{TF 1 +εδ(TF 2 +TF 3 )}
wherein, TF 1 Minimum term, TF, representing the total shaft power of the pumping station 2 And TF 3 Respectively representing an external punishment item of total flow of a pump station and an external punishment item of a high-efficiency interval of the water pump, wherein epsilon is a punishment coefficient, and delta is an axial power-water conversion coefficient;
developing a decision variable coder;
developing a decision variable self-adaptive selection mechanism;
and solving the optimized objective function of the pump station operation scheme, and outputting the optimal operation scheme of the pump station.
Further, when the decision variable encoder converts a 0-1 decision variable into a continuous variable in the iterative optimization process of the optimization algorithm, the continuous variable is restored to the 0-1 decision variable through encoding conversion;
the decision variable adaptive selection mechanism is expressed as:
setting the operation priority of the variable frequency pump to be higher than that of the power frequency pump, and closing the power frequency pump by default;
calculating the maximum and minimum values of the water supply speed of each water pump through a pump station scheduling instruction;
decision variable selection is carried out, assuming that the number of variable frequency water pumps is k and the number of power frequency pumps is n, the total flow value Q of the dispatching instruction is judged st Whether or not to be located in (Q) min ，kQ max ) Within the interval, Q min 、Q max Respectively supplying water to the variable frequency pump at an upper limit and a lower limit; if the variable is positioned in the interval, determining the decision variables as the start-stop state and the speed regulation ratio of the variable frequency pump, wherein the total dimension is 2 k; otherwise, the decision variables are the starting and stopping states of the power frequency pump and the variable frequency pump and the speed regulation ratio of the variable frequency pump, and are (n +2 k) dimensions in total.
In another aspect, the present invention further provides an optimized scheduling device for a continuous hot-rolling laminar cooling water supply pump station, where the optimized scheduling device for a continuous hot-rolling laminar cooling water supply pump station includes:
the sample data acquisition and processing module is used for acquiring rolling process data related to the laminar cooling water consumption of a single strip steel and the laminar cooling water consumption, and preprocessing the acquired rolling process data and the laminar cooling water consumption to generate a training sample;
the prediction model training module is used for training a preset laminar cooling water consumption prediction model by using the training sample generated by the sample data acquisition and processing module; the input of the laminar cooling water consumption prediction model is rolling process data, and the output is single strip steel laminar cooling water consumption;
the laminar cooling water trend prediction module is used for calculating a predicted value of the laminar cooling water consumption of the single strip steel by using the laminar cooling water consumption prediction model trained by the prediction model training module and predicting the laminar cooling water consumption trend of a unit rolling period according to rolling rhythm time;
the feedback optimization module is used for carrying out real-time feedback optimization on a pump station scheduling instruction according to the laminar cooling water trend predicted by the laminar cooling water trend prediction module and the laminar cooling water process requirement so as to stabilize the pressure of the cooling water and reduce the overflow of the cooling water;
and the pump station operation scheme optimization module is used for optimizing the pump station operation scheme of the unit rolling cycle by taking the minimum total shaft power of the pump station as a target according to the optimized pump station scheduling instruction fed back by the feedback optimization module to obtain the optimal pump station operation scheme of the unit rolling cycle.
In yet another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory has stored therein at least one instruction that is loaded and executed by the processor to implement the above-described method.
In yet another aspect, the present invention also provides a computer-readable storage medium having at least one instruction stored therein, which is loaded and executed by a processor to implement the above-mentioned method.
The technical scheme provided by the invention has the beneficial effects that at least:
1. according to the method, the related parameters of the laminar cooling are processed according to the sectional feedback control characteristics of the laminar cooling to generate sample data, and meanwhile, the sample is subjected to data screening and is uniformly sampled according to the product occupation ratio of each specification on site, so that the generalization capability of a water consumption prediction model of the laminar cooling is improved.
2. The method and the device predict the water consumption trend of laminar cooling in unit rolling period according to the water consumption prediction value and rolling rhythm time of the single strip steel, and are favorable for a laminar cooling system to keep a supply and demand balance relationship.
3. According to the water use trend and the cooling water process requirement, the invention carries out real-time feedback optimization on the scheduling instruction of the pump station, is beneficial to reducing the cooling water overflow of the on-site high-level water tank, ensures the cooling quality of the strip steel, and reduces the ineffective power consumption and the sewage treatment cost of the pump station. Extracting the characteristic points of the water level of the high-level water tank is beneficial to simplifying the optimized scheduling process of the pump station; and the external constraint condition is converted into the objective function penalty term, so that the model is simplified, and the convergence rate of the model is improved.
4. According to the invention, the operation scheme of the pump station is optimized according to the scheduling instruction, so that the water pump can operate safely and efficiently, the total shaft power of the pump station is reduced, and the effective utilization rate of the pump station resources is improved. Converting the external constraint condition into a target function penalty term is beneficial to simplifying the model and improving the convergence speed of the model; the decision variable encoder can solve the problem that the iteration process of the optimization algorithm is defaulted to convert 0-1 decision variables into continuous variables, and improves the success rate of model solution; the adaptive decision variable selection mechanism can greatly shorten the model solving time.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is an execution flow diagram of an optimized scheduling method for a hot continuous rolling laminar cooling water supply pump station according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating an implementation principle of an optimized scheduling method for a hot continuous rolling laminar cooling water supply pumping station according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an actual operation flow of an optimized scheduling method for a hot continuous rolling laminar cooling water supply pump station according to an embodiment of the present invention;
FIG. 4 is a flow chart of a real-time feedback optimization for pump station scheduling instructions according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a decision variable encoder according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
First embodiment
The embodiment provides an optimized scheduling method for a hot continuous rolling laminar cooling water supply pump station, which can be implemented by electronic equipment, and the execution flow of the method is shown in fig. 1, and the method comprises the following steps:
s1, obtaining rolling process data related to laminar cooling water consumption and laminar cooling water consumption of a single piece of strip steel, and preprocessing the obtained rolling process data and the laminar cooling water consumption to generate a training sample;
s2, training a preset laminar cooling water consumption prediction model by using a training sample; the input of the laminar cooling water consumption prediction model is rolling process data, and the output is single strip steel laminar cooling water consumption;
s3, calculating a predicted value of the water consumption for laminar cooling of the single strip steel by using the trained model for predicting the water consumption for laminar cooling, and predicting the trend of the water consumption for laminar cooling in a unit rolling period according to the rolling rhythm time;
s4, according to the predicted laminar cooling water trend and the process demand of laminar cooling water, real-time feedback optimization is carried out on the pump station scheduling instruction, so that cooling water overflow is reduced while the cooling water pressure is stabilized;
and S5, optimizing the pump station operation scheme of the unit rolling cycle by taking the minimum total shaft power of the pump station as a target according to the optimized pump station scheduling instruction to obtain the optimal pump station operation scheme of the unit rolling cycle.
Further, in this embodiment, the implementation process of S1 is as follows:
s11, extracting all relevant rolling process data and laminar cooling information in a single strip steel laminar cooling sectional feedback control record set, averaging the extracted data, calculating the laminar cooling water consumption of the single strip steel based on the averaged laminar cooling information, and forming an initial training sample by the averaged rolling process data and laminar cooling water consumption; wherein the rolling process data comprises: the method comprises the following steps of strip steel specification, rolling rhythm time and rolling process parameters, wherein the strip steel specification comprises the following steps: thickness, width and steel type of the strip steel; the rolling process parameters comprise: rolling force, rolling speed, strip steel finish rolling temperature and coiling temperature; the laminar cooling information refers to a laminar cooling header switch set value, cooling water temperature and header rated flow;
the calculation formula of the water consumption for laminar cooling of the single strip steel is as follows:
C w ＝(R mean V R +F mean V F )t C
wherein, C W Represents the water consumption, R, of laminar cooling of a single strip steel mean Header switch average, V, representing coarse tuning region R Unit manifold flow rate, F, representing coarse tuning zone mean Mean number of header switches, V, representing fine tuning area F Unit header flow rate, t, representing fine adjustment zone C The cooling time is indicated.
S12, preprocessing the initial sample to generate preprocessed sample data; wherein the pre-processing comprises: abnormal value detection is carried out on the initial sample according to a 3 sigma rule, data which do not accord with the regulation are removed, and then Max-Min standardization processing is carried out on the sample which is subjected to the data removal;
and S13, uniformly sampling the preprocessed sample data according to the specification of the strip steel, the steel grade and other information to generate a final training sample for training a subsequent laminar cooling water consumption prediction model.
Further, in this embodiment, the model for predicting the water consumption of laminar cooling is an OS-ELM model;
in this embodiment, the implementation process of S3 is as follows:
s31, generating a predicted value of the laminar cooling water consumption of each strip steel in the current rolling period according to current rolling process data by using the trained laminar cooling water consumption prediction model;
s32, obtaining rolling rhythm time information of the current rolling cycle; wherein, the rolling rhythm time information comprises: cooling time and cooling interval time of adjacent strip steels;
and S33, calculating the change trend of the current laminar cooling water consumption of the rolling cycle according to the current rolling cycle rolling rhythm time information based on the predicted cooling water consumption of the single strip steel.
Further, in this embodiment, the implementation process of S4 is as follows:
s41, selecting water level characteristic points according to the rolling rhythm; wherein the characteristic point of the water level is the water level h of a high-level water tank at the beginning of strip steel cooling i And high-level water tank water at the end of strip steel coolingBit h 1,i (ii) a The calculation formula is as follows:
Figure BDA0003471676330000081
h 1,i ＝h i +(Q i -Q 1,i )t 1,i /A
h i+1 ＝h 1,i +Q i ×t 2,i /A
wherein i represents the number of the strip steel; h is a total of max And h min Respectively indicating the upper limit and the lower limit of the water level of the high-level water tank; a represents the bottom area of the high-level water tank; q i Representing the water supply speed of the water pump; q 1,i Representing the water consumption rate of the laminar cooling process; t is t 1,i The cooling time of the strip steel is shown; t is t 2,i Indicating the cooling interval time.
S42, determining a pump station scheduling instruction optimization objective function and constraint conditions; wherein the constraint conditions are the upper limit and the lower limit of the water level of the high-level water tank and the overflow amount of cooling water; the pump station scheduling instruction optimization objective function is as follows:
min{β[θ(C 1 +C 2 )]+(1-β)(YL 1 +YL 2 )}
wherein, C 1 Representing the total amount of variation of water level of a high level cistern in a rolling cycle, YL 1 Indicating total head tank overflow during operation, C 2 Representing a penalty item of a limiting water level constraint condition of the high-level water tank; YL 2 An overflow quantity constraint condition penalty term is represented, beta represents a bias coefficient, and theta represents a water level-overflow quantity conversion coefficient;
penalty item C of limiting water level constraint condition under high-level water tank 2 Comprises the following steps:
Figure BDA0003471676330000082
Figure BDA0003471676330000083
wherein the content of the first and second substances,
Figure BDA0003471676330000084
represents the penalty coefficient, i represents the number of the strip steel, m represents the number of the strip steel, h 1,i Indicates the water level of the high level tank at the end of strip cooling, h min The lower limit of the water level of the high-level water tank is represented;
overflow constraint penalty term YL 2 Comprises the following steps:
Figure BDA0003471676330000085
wherein γ represents a penalty coefficient, Y i And the overflow amount of the high-level water tank when the ith strip steel is cooled is shown.
S43, solving the pump station dispatching instruction optimization objective function by using an ISSA optimization algorithm, and outputting the dispatching instruction after the pump station optimization in the rolling cycle;
and S44, updating and adjusting the pump station dispatching instruction in real time according to the predicted laminar cooling water trend, the laminar cooling water process demand and the water level measured value based on the optimized dispatching instruction.
Further, in this embodiment, the implementation process of S5 is as follows:
s51, acquiring an optimal pump station scheduling instruction;
s52, determining an optimized objective function and constraint conditions of a pump station operation scheme; wherein the constraint condition comprises: speed regulation ratio constraint, water pump lift constraint, pump station total flow constraint and high-efficiency interval constraint;
converting the constraint condition into an external punishment item of the pump station operation scheme optimization objective function; the pump station operation scheme optimization objective function with the external constraint penalty term is as follows:
min{TF 1 +εδ(TF 2 +TF 3 )}
wherein, TF 1 Minimum term, TF, representing the total shaft power of the pumping station 2 And TF 3 Respectively representing the external punishment item of the total flow of the pump station and the external punishment item of the high-efficiency interval of the water pump, wherein epsilon is a punishment coefficient, and delta is the shaft power-waterA quantitative conversion factor;
s53, developing a decision variable coder; when a decision variable encoder converts a 0-1 decision variable into a continuous variable in an optimization algorithm iterative optimization process, restoring the continuous variable into the 0-1 decision variable through encoding conversion;
s54, developing a decision variable self-adaptive selection mechanism; the decision variable adaptive selection mechanism can be expressed as:
1. setting the operation priority of the variable frequency pump to be higher than that of the power frequency pump, and closing the power frequency pump by default;
2. calculating the maximum and minimum values of the water supply speed of each water pump through a pump station scheduling instruction;
3. decision variable selection is carried out, the number of variable frequency water pumps is set to be k, the number of power frequency pumps is set to be n, and the total flow value Q of the dispatching instruction is judged st Whether or not to be located in (Q) min ，kQ max ) Within the interval, Q min 、Q max Respectively supplying water to the variable frequency pump at an upper limit and a lower limit; if the variable is positioned in the interval, determining the decision variables as the start-stop state and the speed regulation ratio of the variable frequency pump, wherein the number of the decision variables is 2 k; otherwise, the decision variables are the starting and stopping states of the power frequency pump and the variable frequency pump and the speed regulation ratio of the variable frequency pump, and are (n +2 k) dimensions in total.
And S55, solving the optimized objective function of the pump station operation scheme, and outputting the optimal operation scheme of the pump station.
Further, please refer to fig. 2 and fig. 3, in order to facilitate better understanding of the optimal scheduling method for the hot continuous rolling laminar cooling water supply pump station of the present embodiment by those skilled in the art, the following detailed description is provided with reference to specific application examples, and in actual application, the execution process of the optimal scheduling method for the hot continuous rolling laminar cooling water supply pump station is as follows:
step one, information acquisition and data preprocessing
Specifically, the collected laminar flow cooling related production data includes: the method comprises the following steps of (1) strip steel specification information, rolling rhythm information, rolling process parameters and laminar cooling information; wherein, the strip steel specification information comprises: thickness, width and steel type of strip steel; the rolling process parameters comprise: rolling force, rolling speed, strip steel finish rolling temperature and coiling temperature; the laminar cooling information refers to a laminar cooling header switch set value, a cooling water temperature and a header rated flow.
All relevant rolling process parameters and laminar cooling information of the laminar cooling sectional feedback control of the single strip steel are extracted, and the extracted information is averaged to generate an initial sample.
Wherein, the actual value of the water consumption for laminar cooling of the single strip steel in the sample is as follows:
C w ＝(R mean V R +F mean V F )t C
wherein, C W For cooling water consumption, R mean The header switch average number in the coarse adjustment area; v R The unit collecting pipe flow rate in the coarse adjustment area; f mean Is the fine adjustment zone header switch average; v F The flow rate of a unit collecting pipe in a fine adjustment area; t is t C The cooling time is indicated.
And (3) abnormal value detection is carried out on the data by adopting a 3 sigma rule, the data which do not conform to the specification are removed, and then Max-Min standardization processing is carried out.
Step two, predicting the change trend of the water consumption of laminar cooling in the current rolling period of the system
The water consumption prediction is carried out by selecting a certain unit rolling period for producing Q235B (C) strip steel, 35 coils of strip steel are produced in the period, the time of the rolling period is 1 hour and 50 minutes, and the neural network model is selected from OS-ELM.
The rolling rhythm information comprises the cooling time and the cooling interval time of the adjacent steel strips.
Step three, optimizing the scheduling instruction of the pump station in real time
Setting the highest water level h of high-level water tank max 7.7m, the lowest water level h of the process requirement min It was 7.3m.
Selecting the water level h of a high-level water tank when the strip steel cooling starts and ends i And h 1,i For the water level characteristic point, the calculation formula is as follows:
Figure BDA0003471676330000101
h 1,i ＝h i +(Q i -Q 1,i )t 1,i /A
h i+1 ＝h 1,i +Q i ×t 2,i /A
wherein i is the serial number of the strip steel; h is max And h min Respectively is the upper limit and the lower limit of the water level of the high-level water tank; a is the bottom area of the high-level water tank; q i The water supply speed of the water pump; q 1,i The water consumption speed of the laminar cooling process is high; t is t 1,i The cooling time of the strip steel is taken; t is t 2,i The cooling interval time.
Determining constraint conditions as the upper and lower limits of the water level of the high-level water tank and the overflow amount of cooling water, and converting the external constraint conditions into penalty items of an objective function, wherein the objective function is as follows:
min{β[θ(C 1 +C 2 )]+(1-β)(YL 1 +YL 2 )}
wherein, C 1 For the rolling cycle high level water tank level h i Sum of the variation amounts; YL 1 The total overflow volume of the high-level water tank during the operation period; c 2 A penalty item for a lower limit water level constraint condition; YL 2 And the penalty term is an overflow quantity constraint condition, beta is an offset coefficient, and theta is a water level-overflow quantity conversion coefficient.
In the embodiment, the water level control effect is emphasized, and the offset coefficient beta is 0.6; the water level-overflow conversion factor theta is taken as 300.
The penalty term of the lower limit water level constraint condition of the objective function is as follows:
Figure BDA0003471676330000102
Figure BDA0003471676330000103
wherein the content of the first and second substances,
Figure BDA0003471676330000104
for penalty factor, in this embodiment
Figure BDA0003471676330000105
And 300 is taken.
The overflow constraint penalty of the objective function is:
Figure BDA0003471676330000106
wherein γ is a penalty coefficient, and in this embodiment γ is 200; y is i The overflow quantity of the high-level water tank is the overflow quantity of the ith strip steel when the ith strip steel is cooled.
Solving the model by using an ISSA optimization algorithm, and starting a feedback optimization module by the model after obtaining the optimal water supply scheduling instruction of the current rolling period, wherein the operation flow of the feedback optimization module is shown in FIG. 4.
Step four, optimizing the running scheme of the pump station
Firstly, an optimal scheduling instruction is obtained.
And determining constraint conditions including speed ratio constraint, water pump lift constraint, pump station total flow constraint and high-efficiency interval constraint.
Converting part of constraint conditions into external penalty terms of an objective function, wherein the objective function is as follows:
min{TF 1 +εδ(TF 2 +TF 3 )}
wherein, TF 1 Is the minimum term of the power of the main shaft of the pump station; TF 2 And TF 3 The method comprises the following steps of respectively obtaining a pump station total flow external penalty term and a water pump high-efficiency interval external penalty term, wherein epsilon is a penalty coefficient, and delta is an axial power-water quantity conversion coefficient.
In this embodiment, the penalty coefficient epsilon is 300; the axial power-water conversion coefficient delta is 0.0885.
Developing a decision variable encoder, as shown in FIG. 5;
developing a decision variable adaptive selection mechanism:
setting the operation priority of the variable frequency pump to be higher than that of the power frequency pump, and closing the power frequency pump by default;
calculating the maximum and minimum values of the water supply speed of each water pump through a pump station scheduling instruction;
decision variable selection is carried out, assuming that the number of variable frequency water pumps is k and the number of power frequency pumps is n, the total flow value Q of the dispatching instruction is judged st Whether or not to be located in (Q) min ，kQ max ) Within the interval. Q min 、Q max Respectively the upper limit and the lower limit of the water supply speed of the variable frequency pump. If the variable is positioned in the interval, determining the decision variables as the start-stop state and the speed regulation ratio of the variable frequency pump, wherein the decision variables are 2k dimensions; otherwise, the decision variables are the starting and stopping states of the power frequency pump and the variable frequency pump and the speed regulating ratio of the variable frequency pump, and the decision variables are (n +2 k) dimensions in total.
In the embodiment, the number k of the variable frequency water pumps is set to 3; the number n of the power frequency pumps is set to be 4; frequency conversion pump Q min Is 1027.2m3/h; q max 2396.08m3/h.
Finally, the ISSA optimization algorithm is adopted to carry out model solution, and the optimal operation scheme of the pump station is output.
By operating the optimized scheduling method of the hot continuous rolling laminar cooling water supply pump station, the system keeps balance of supply and demand, meanwhile, the cooling quality of the strip steel is ensured, and the waste of system resources is effectively reduced.
In conclusion, the optimized scheduling method for the hot continuous rolling laminar cooling water supply pump station predicts the laminar cooling water trend of a unit rolling period according to the water consumption prediction value of a single strip steel and the rolling rhythm time, and is favorable for a laminar cooling system to keep a supply-demand balance relationship. The pump station dispatching instruction is subjected to real-time feedback optimization according to the water use trend and the cooling water process requirement, so that the cooling water overflow of the on-site high-level water tank is favorably reduced, the cooling quality of strip steel is ensured, the ineffective power consumption and sewage treatment cost of the pump station are reduced, and the extraction of the water level characteristic point of the high-level water tank is favorable for simplifying the optimized dispatching process of the pump station; and the external constraint condition is converted into the target function penalty term, so that the model is simplified, and the convergence rate of the model is improved. The operation scheme of the pump station is optimized according to the scheduling instruction, so that the water pump can operate safely and efficiently, the total shaft power of the pump station is reduced, and the effective utilization rate of pump station resources is improved, wherein the external constraint condition is converted into a target function punishment item, so that the model is simplified, and the convergence speed of the model is improved; the decision variable encoder can solve the problem that the iteration process of the optimization algorithm is defaulted to convert 0-1 decision variables into continuous variables, and the success rate of model solving is improved; the adaptive decision variable selection mechanism can greatly shorten the model solving time.
Second embodiment
The embodiment provides a hot continuous rolling laminar flow cooling working shaft station optimizes scheduling device, includes:
the sample data acquisition and processing module is used for acquiring rolling process data related to the laminar cooling water consumption of a single strip steel and the laminar cooling water consumption, and preprocessing the acquired rolling process data and the laminar cooling water consumption to generate a training sample;
the prediction model training module is used for training a preset laminar cooling water consumption prediction model by using the training sample generated by the sample data acquisition and processing module; the input of the model for predicting the water consumption for laminar cooling is rolling process data, and the output is the water consumption for laminar cooling of a single strip steel;
the laminar cooling water trend prediction module is used for calculating a predicted value of the laminar cooling water consumption of the single strip steel by utilizing the laminar cooling water consumption prediction model trained by the prediction model training module and predicting the laminar cooling water trend of a unit rolling period according to rolling rhythm time;
the feedback optimization module is used for carrying out real-time feedback optimization on a pump station scheduling instruction according to the laminar cooling water trend predicted by the laminar cooling water trend prediction module and the laminar cooling water process demand so as to stabilize the pressure of the cooling water and reduce the overflow of the cooling water;
and the pump station operation scheme optimization module is used for optimizing the pump station operation scheme of the unit rolling cycle by taking the minimum total shaft power of the pump station as a target according to the optimized pump station scheduling instruction fed back by the feedback optimization module to obtain the optimal pump station operation scheme of the unit rolling cycle.
The optimal scheduling device for the hot continuous rolling laminar cooling water supply pumping station of the embodiment corresponds to the optimal scheduling method for the hot continuous rolling laminar cooling water supply pumping station of the first embodiment; the functions realized by each functional module in the optimal scheduling device for the hot continuous rolling laminar flow cooling water supply pump station of the embodiment correspond to each flow step in the optimal scheduling method for the hot continuous rolling laminar flow cooling water supply pump station of the first embodiment one by one; therefore, it is not described herein.
Third embodiment
The present embodiment provides an electronic device, which includes a processor and a memory; wherein the memory has stored therein at least one instruction that is loaded and executed by the processor to implement the method of the first embodiment.
The electronic device may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) and one or more memories, where at least one instruction is stored in the memory, and the instruction is loaded by the processor and executes the method.
Fourth embodiment
The present embodiment provides a computer-readable storage medium, which stores at least one instruction, and the instruction is loaded and executed by a processor to implement the method of the first embodiment. The computer readable storage medium may be, among others, ROM, random access memory, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. The instructions stored therein may be loaded by a processor in the terminal and perform the above-described method.
Furthermore, it should be noted that the present invention may be provided as a method, apparatus or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied in the medium.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It should also be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or terminal apparatus that comprises the element.
Finally, it should be noted that while the above describes a preferred embodiment of the invention, it will be appreciated by those skilled in the art that, once the basic inventive concepts have been learned, numerous changes and modifications may be made without departing from the principles of the invention, which shall be deemed to be within the scope of the invention. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Claims (9)

1. The optimized scheduling method for the hot continuous rolling laminar cooling water supply pump station is characterized by comprising the following steps of:
acquiring rolling process data related to the water consumption for laminar cooling and the water consumption for laminar cooling of a single strip steel, and preprocessing the acquired rolling process data and the water consumption for laminar cooling to generate a training sample;
training a preset laminar cooling water consumption prediction model by using the training sample; the input of the laminar cooling water consumption prediction model is rolling process data, and the output is single strip steel laminar cooling water consumption;
calculating the predicted value of the water consumption for laminar cooling of the single strip steel by using the trained model for predicting the water consumption for laminar cooling, and predicting the trend of the water consumption for laminar cooling in a unit rolling period according to the rolling rhythm time;
according to the predicted trend of the laminar cooling water and the technological requirement of the laminar cooling water, real-time feedback optimization is carried out on a scheduling instruction of the pump station so as to reduce cooling water overflow while stabilizing the pressure of the cooling water;
according to the optimized pump station scheduling instruction, optimizing the pump station operation scheme of a unit rolling cycle by taking the minimum total shaft power of the pump station as a target to obtain the optimal pump station operation scheme of the unit rolling cycle;
according to the laminar flow cooling water trend and laminar flow cooling water technology demand that predict, carry out real-time feedback optimization to pump station scheduling instruction to when stabilizing the cooling water pressure, reduce the cooling water overflow, include:
selecting water level characteristic points according to the rolling rhythm; the water level characteristic points are the water level of a high-level water tank at the beginning of strip steel cooling and the water level of the high-level water tank at the end of strip steel cooling;
determining a pump station scheduling instruction optimization objective function and constraint conditions; wherein the constraint conditions are the upper limit and the lower limit of the water level of the high-level water tank and the overflow amount of cooling water; the pump station scheduling instruction optimization objective function is as follows:
min{β[θ(C 1 +C 2 )]+(1-β)(YL 1 +YL 2 )}
wherein, C 1 Representing the total amount of variation of water level of a high level cistern in a rolling cycle, YL 1 Indicating the total overflow of the head tank during operation, C 2 Representing a penalty item of a lower limit water level constraint condition of the high-level water tank; YL 2 An overflow quantity constraint condition penalty term is represented, beta represents a bias coefficient, and theta represents a water level-overflow quantity conversion coefficient;
solving the pump station dispatching instruction optimization objective function, and outputting the dispatching instruction after the rolling cycle pump station optimization;
and based on the optimized dispatching instruction, updating and adjusting the dispatching instruction of the pump station in real time according to the predicted trend of the laminar cooling water, the technological requirement of the laminar cooling water and the measured water level value.
2. The optimal scheduling method for the hot continuous rolling laminar cooling water supply pump station according to claim 1, wherein the step of obtaining the rolling process data and the laminar cooling water consumption of the single strip steel related to the laminar cooling water consumption, and preprocessing the obtained rolling process data and the laminar cooling water consumption to generate the training sample comprises the following steps:
extracting all relevant rolling process data and laminar cooling information in a single strip steel laminar cooling sectional feedback control record set, averaging the extracted data, calculating the laminar cooling water consumption of the single strip steel based on the averaged laminar cooling information, and forming an initial training sample by the averaged rolling process data and the laminar cooling water consumption; wherein the rolling process data comprises: the method comprises the following steps of strip steel specification, rolling rhythm time and rolling process parameters, wherein the strip steel specification comprises the following steps: thickness, width and steel type of the strip steel; the rolling process parameters comprise: rolling force, rolling speed, strip steel finish rolling temperature and coiling temperature; the laminar cooling information refers to a laminar cooling header switch set value, cooling water temperature and header rated flow;
preprocessing the initial training sample to generate preprocessed sample data; wherein the pre-processing comprises: abnormal value detection processing and normalization processing;
and uniformly sampling the preprocessed sample data according to the specification of the strip steel to generate a final training sample.
3. The optimal scheduling method for the water supply pump station for the hot continuous rolling laminar cooling according to claim 2, wherein the calculation formula of the water consumption for the laminar cooling of the single strip steel is as follows:
C w ＝(R mean V R +F mean V F )t C
wherein, C W Represents the water consumption, R, of laminar cooling of a single strip steel mean Header switch average, V, representing coarse tuning region R Unit manifold flow rate, F, representing coarse tuning zone mean Mean number of header switches, V, representing fine tuning area F Unit header flow rate, t, representing fine adjustment zone C The cooling time is indicated.
4. The optimal scheduling method for the water supply pump station for the laminar cooling of the hot continuous rolling mill as claimed in claim 2, wherein the pre-processing of the initial training samples comprises:
and carrying out abnormal value detection on the initial training sample according to a 3 sigma rule, removing data which do not meet the specification, and then carrying out Max-Min standardization processing on the sample subjected to data removal.
5. The optimal scheduling method for the hot continuous rolling laminar cooling water supply pump station according to claim 1, wherein the preset laminar cooling water consumption prediction model is an OS-ELM model;
the method for predicting the laminar cooling water consumption of the single strip steel by utilizing the trained laminar cooling water consumption prediction model and predicting the laminar cooling water consumption trend of a unit rolling period according to the rolling rhythm time comprises the following steps:
generating a predicted value of the cooling water consumption of each strip steel laminar flow in the current rolling period by using the trained laminar flow cooling water consumption prediction model according to the current rolling process data;
obtaining rolling rhythm time information of a current rolling cycle; wherein, the rolling rhythm time information comprises: cooling time and cooling interval time of adjacent strip steels;
and calculating the change trend of the current laminar cooling water consumption of the rolling period according to the current rolling period rolling rhythm time information on the basis of the predicted value of the cooling water consumption of the single strip steel.
6. The optimal scheduling method for the hot continuous rolling laminar cooling water supply pump station as claimed in claim 1, wherein a penalty term C is given to the constraint condition of the lower limit water level of the head tank 2 Comprises the following steps:
Figure FDA0003898550570000031
wherein, the first and the second end of the pipe are connected with each other,
Figure FDA0003898550570000032
represents the penalty coefficient, i represents the number of the strip steel, m represents the number of the strip steel, h 1,i Indicating the water level of the high level tank at the end of the strip cooling min The lower limit of the water level of the high-level water tank is represented;
overflow constraint penalty term YL 2 Comprises the following steps:
Figure FDA0003898550570000033
wherein γ represents a penalty coefficient, Y i And the overflow amount of the high-level water tank when the ith strip steel is cooled is shown.
7. The optimal scheduling method for the hot continuous rolling laminar flow cooling water supply pump station according to claim 1, wherein the step of optimizing the pump station operation scheme of a unit rolling cycle to obtain the optimal pump station operation scheme of the unit rolling cycle by aiming at the minimum total shaft power of the pump station according to the optimized pump station scheduling instruction comprises the following steps:
acquiring an optimal pump station scheduling instruction;
determining an optimized objective function and constraint conditions of a pump station operation scheme; wherein the constraint condition comprises: speed regulation ratio constraint, water pump lift constraint, pump station total flow constraint and high-efficiency interval constraint;
converting the constraint condition into an external punishment item of the pump station operation scheme optimization objective function; the pump station operation scheme optimization objective function with the external constraint penalty term is as follows:
min{TF 1 +εδ(TF 2 +TF 3 )}
wherein, TF 1 Minimum term, TF, representing the total shaft power of the pumping station 2 And TF 3 Respectively representing an external punishment item of the total flow of a pump station and an external punishment item of a high-efficiency interval of the water pump, wherein epsilon is a punishment coefficient, and delta is an axial power-water quantity conversion coefficient;
developing a decision variable coder;
developing a decision variable self-adaptive selection mechanism;
and solving the optimized objective function of the pump station operation scheme, and outputting the optimal operation scheme of the pump station.
8. The optimal scheduling method for the water supply pump station for the laminar cooling of the hot continuous rolling mill as claimed in claim 7, wherein the decision variable encoder restores the continuous variable to the 0-1 decision variable through encoding conversion when the 0-1 decision variable is converted to the continuous variable in the iterative optimization process of the optimization algorithm;
the decision variable adaptive selection mechanism is expressed as:
setting the operation priority of the variable frequency pump to be higher than that of the power frequency pump, and closing the power frequency pump by default;
calculating the maximum and minimum values of the water supply speed of each water pump through a pump station scheduling instruction;
decision variable selection is carried out, assuming that the number of variable frequency water pumps is k and the number of power frequency pumps is n, the total flow value Q of the dispatching instruction is judged st Whether or not to be located in (Q) min ，kQ max ) Within the interval, Q min 、Q max Respectively supplying water to the variable frequency pump at an upper limit and a lower limit; if the variable is positioned in the interval, determining the decision variables as the start-stop state and the speed regulation ratio of the variable frequency pump, wherein the number of the decision variables is 2 k; otherwise, the decision variables are the starting and stopping states of the power frequency pump and the variable frequency pump and the speed regulation ratio of the variable frequency pump, and are (n +2 k) dimensions in total.
9. The utility model provides a hot continuous rolling laminar flow cooling working shaft station optimizes scheduling device which characterized in that includes:
the sample data acquisition and processing module is used for acquiring rolling process data related to the water consumption of laminar cooling of a single piece of strip steel and the water consumption of laminar cooling, and preprocessing the acquired rolling process data and the water consumption of laminar cooling to generate a training sample;
the prediction model training module is used for training a preset laminar cooling water consumption prediction model by using the training sample generated by the sample data acquisition and processing module; the input of the laminar cooling water consumption prediction model is rolling process data, and the output is single strip steel laminar cooling water consumption;
the laminar cooling water trend prediction module is used for calculating a predicted value of the laminar cooling water consumption of the single strip steel by utilizing the laminar cooling water consumption prediction model trained by the prediction model training module and predicting the laminar cooling water trend of a unit rolling period according to rolling rhythm time;
the feedback optimization module is used for carrying out real-time feedback optimization on a pump station scheduling instruction according to the laminar cooling water trend predicted by the laminar cooling water trend prediction module and the laminar cooling water process demand so as to stabilize the pressure of the cooling water and reduce the overflow of the cooling water;
the pump station operation scheme optimization module is used for optimizing the pump station operation scheme of a unit rolling cycle by taking the minimum total shaft power of the pump station as a target according to the optimized pump station scheduling instruction fed back by the feedback optimization module to obtain the optimal pump station operation scheme of the unit rolling cycle;
according to the laminar flow cooling water trend and laminar flow cooling water technology demand that predict, carry out real-time feedback optimization to pump station scheduling instruction to when stabilizing the cooling water pressure, reduce the cooling water overflow, include:
selecting water level characteristic points according to the rolling rhythm; the water level characteristic points are the water level of a high-level water tank at the beginning of strip steel cooling and the water level of the high-level water tank at the end of strip steel cooling;
determining a pump station scheduling instruction optimization objective function and constraint conditions; wherein the constraint conditions are the upper limit and the lower limit of the water level of the high-level water tank and the overflow amount of cooling water; the pump station scheduling instruction optimization objective function is as follows:
min{β[θ(C 1 +C 2 )]+(1-β)(YL 1 +YL 2 )}
wherein, C 1 Representing the total amount of variation of water level of a high level cistern in a rolling cycle, YL 1 Indicating the total overflow of the head tank during operation, C 2 Representing a penalty item of a limiting water level constraint condition of the high-level water tank; YL 2 The method comprises the steps of representing an overflow quantity constraint condition penalty term, representing a bias coefficient by beta, and representing a water level-overflow quantity conversion coefficient by theta;
solving the pump station dispatching instruction optimization objective function, and outputting the dispatching instruction after the rolling cycle pump station optimization;
and updating and adjusting the pump station dispatching instruction in real time according to the predicted laminar cooling water trend, the laminar cooling water process demand and the water level measured value based on the optimized dispatching instruction.
CN202210044719.XA 2022-01-14 2022-01-14 Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station Active CN114417530B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210044719.XA CN114417530B (en) 2022-01-14 2022-01-14 Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210044719.XA CN114417530B (en) 2022-01-14 2022-01-14 Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station

Publications (2)

Publication Number Publication Date
CN114417530A CN114417530A (en) 2022-04-29
CN114417530B true CN114417530B (en) 2023-01-20

Family

ID=81274331

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210044719.XA Active CN114417530B (en) 2022-01-14 2022-01-14 Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station

Country Status (1)

Country Link
CN (1) CN114417530B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115218603B (en) * 2022-07-15 2023-11-24 北京京诚瑞达电气工程技术有限公司 Cooling flow control method and device

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5564704B2 (en) * 2009-09-02 2014-08-06 株式会社日立製作所 Hot finish rolling mill outlet side temperature control device and control method
JP5492910B2 (en) * 2010-01-29 2014-05-14 東芝三菱電機産業システム株式会社 Water injection control device, water injection control method, water injection control program in rolling line
CN101972782B (en) * 2010-09-15 2012-06-06 北京科技大学 Device and method for cooling intermediate rolled blank of hot rolled strip
JP5616817B2 (en) * 2011-02-18 2014-10-29 東芝三菱電機産業システム株式会社 Control device for hot rolling line
CN103028615B (en) * 2012-11-29 2014-12-10 一重集团大连设计研究院有限公司 Method for predicting temperature evolution in hot continuous rolling process of strip steel
CN103605390B (en) * 2013-10-16 2015-11-11 东北大学 A kind of water-supply control of hot-rolling line ultra-rapid cooling system
CN103878186B (en) * 2014-03-24 2015-05-06 华中科技大学 Method for determining hot rolled strip steel laminar cooling temperature
CN109550794B (en) * 2018-12-25 2020-12-08 鞍钢集团朝阳钢铁有限公司 Feedforward control method for outlet temperature of hot rolling and finish rolling
JP6716186B1 (en) * 2019-02-04 2020-07-01 東芝三菱電機産業システム株式会社 Pumping pump speed controller
CN112437702B (en) * 2019-06-26 2023-02-10 东芝三菱电机产业系统株式会社 Temperature control device of hot rolling production line

Also Published As

Publication number Publication date
CN114417530A (en) 2022-04-29

Similar Documents

Publication Publication Date Title
JP7059989B2 (en) Control system and control method
CN114417530B (en) Optimized scheduling method and device for hot continuous rolling laminar cooling water supply pump station
CN101718270A (en) Prediction and pressure regulation method for control system of air compressor
CN111563776B (en) Electric quantity decomposition and prediction method based on K neighbor anomaly detection and Prophet model
CN113131523A (en) Method and system for predicting variety-based power supply
CN113675863B (en) Digital twin-based micro-grid frequency secondary cooperative control method
CN115186916A (en) Load prediction method, device, equipment and computer readable storage medium
CN117093823B (en) Factory energy consumption management method based on data analysis
CN115062904A (en) Digital water supply pipe network scheduling method and system
CN116596139A (en) Short-term load prediction method and system based on Elman neural network
CN114385962A (en) Day-ahead photovoltaic power generation power prediction method and system based on similar days
CN114396385B (en) Scheduling control method based on pump station operation
CN114542442A (en) Water treatment lift pump scheduling control method and device, electronic equipment and medium
CN113867905A (en) Real-time energy consumption optimization method for application server cluster
CN113298240B (en) Method and device for predicting life cycle of servo drive system
CN116090678B (en) Data processing method, device and equipment
CN111766839B (en) Computer-implemented system for self-adaptive update of intelligent workshop scheduling knowledge
CN116629027B (en) Wind power prediction method and system based on radar data
CN110458364B (en) Smooth data preprocessing method for short-term load prediction
CN117910908A (en) Efficient distribution method for grease stack table and storage tank based on optimization algorithm
Raff et al. Model predictive control of uncertain continuous-time systems with piecewise constant control input: a convex approach
CN117932537A (en) Water pump characteristic curve fitting method and system based on multi-source data fusion
Zhang et al. Power System Short-Term Load Forecasting Method
CN114936523A (en) Method and system for forecasting warehousing runoff of hydroelectric power station
CN117713063A (en) Control method of photovoltaic hydrogen production device with self-adaptive regulation of direct-current bus voltage

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
GR01 Patent grant
GR01 Patent grant