CN113289542B - Mixing machine control system and method based on optimal mixing energy efficiency ratio - Google Patents

Mixing machine control system and method based on optimal mixing energy efficiency ratio Download PDF

Info

Publication number
CN113289542B
CN113289542B CN202010845710.XA CN202010845710A CN113289542B CN 113289542 B CN113289542 B CN 113289542B CN 202010845710 A CN202010845710 A CN 202010845710A CN 113289542 B CN113289542 B CN 113289542B
Authority
CN
China
Prior art keywords
rotating speed
mixing
mixture
mixer
period
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
CN202010845710.XA
Other languages
Chinese (zh)
Other versions
CN113289542A (en
Inventor
邱立运
朱佼佼
袁立新
朱国华
周斌
莫旭红
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.)
Hunan Changtian Automation Engineering Co ltd
Zhongye Changtian International Engineering Co Ltd
Original Assignee
Hunan Changtian Automation Engineering Co ltd
Zhongye Changtian International Engineering Co Ltd
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 Hunan Changtian Automation Engineering Co ltd, Zhongye Changtian International Engineering Co Ltd filed Critical Hunan Changtian Automation Engineering Co ltd
Priority to CN202010845710.XA priority Critical patent/CN113289542B/en
Publication of CN113289542A publication Critical patent/CN113289542A/en
Application granted granted Critical
Publication of CN113289542B publication Critical patent/CN113289542B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
    • B01F35/20—Measuring; Control or regulation
    • B01F35/22—Control or regulation
    • B01F35/221—Control or regulation of operational parameters, e.g. level of material in the mixer, temperature or pressure
    • B01F35/2216—Time, i.e. duration, of at least one parameter during the operation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
    • B01F35/20—Measuring; Control or regulation
    • B01F35/21—Measuring
    • B01F35/211—Measuring of the operational parameters
    • B01F35/2112—Level of material in a container or the position or shape of the upper surface of the material
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
    • B01F35/20—Measuring; Control or regulation
    • B01F35/21—Measuring
    • B01F35/211—Measuring of the operational parameters
    • B01F35/2116—Volume
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
    • B01F35/20—Measuring; Control or regulation
    • B01F35/21—Measuring
    • B01F35/2134—Density or solids or particle number
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
    • B01F35/20—Measuring; Control or regulation
    • B01F35/21—Measuring
    • B01F35/2135—Humidity, e.g. moisture content
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
    • B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
    • B01F35/00—Accessories for mixers; Auxiliary operations or auxiliary devices; Parts or details of general application
    • B01F35/20—Measuring; Control or regulation
    • B01F35/22—Control or regulation
    • B01F35/221—Control or regulation of operational parameters, e.g. level of material in the mixer, temperature or pressure
    • B01F35/2214—Speed during the operation
    • B01F35/22142—Speed of the mixing device during the operation
    • B01F35/221422—Speed of rotation of the mixing axis, stirrer or receptacle during the operation
    • 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
    • G06N3/045—Combinations of networks
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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"
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/20—Recycling

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Chemical & Material Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Human Resources & Organizations (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Tourism & Hospitality (AREA)
  • Mixers Of The Rotary Stirring Type (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Computer Hardware Design (AREA)
  • Geometry (AREA)
  • Development Economics (AREA)

Abstract

The application relates to the technical field of metal sintering, and provides a mixing machine control system and a method based on optimal mixing energy efficiency ratio, wherein the mixing machine control system comprises a mixing machine and a mixture supply device, and the mixture supply device is connected with a feed inlet of the mixing machine; the control system of the mixing machine also comprises a rotating speed controller, a feeding and discharging controller, a feeding controller and a central processing unit, wherein the rotating speed controller and the feeding and discharging controller are connected with the mixing machine, the feeding controller is connected with the mixture supply equipment, and the central processing unit is respectively connected with the rotating speed controller and the feeding controller. In the practical application process, the central processing unit obtains mixture parameters and mixer state parameters, predicts the shortest mixing period and mixer energy consumption, establishes a mixing energy efficiency ratio model, performs global optimization on the established mixing energy efficiency ratio model, obtains mixer control parameters when the energy efficiency ratio is optimal, and drives the rotating speed controller to adjust the rotating speeds of the mixing drum motor, the main paddle motor and the auxiliary paddle motor into the actual control parameters as the actual control parameters of the mixer.

Description

Mixing machine control system and method based on optimal mixing energy efficiency ratio
Technical Field
The application relates to the technical field of metal sintering, in particular to a mixing machine control system and method based on optimal mixing energy efficiency ratio.
Background
The intensive mixer is a continuously rotating cylindrical machine, and is divided into a horizontal intensive mixer and a vertical intensive mixer, although the equipment structure is slightly different, the principle of control is basically similar, hereinafter referred to as a mixer for short, and the intensive mixer is used for stirring materials to achieve the purpose of uniformly mixing. Referring to fig. 1 and 2, fig. 1 is a front view of a vertical intensive mixer of the prior art, and fig. 2 is a plan view corresponding to fig. 1. The intensive mixer 100 shown in fig. 1 and 2 comprises a mixing cylinder 1, a paddle (not shown in the figure) including a main paddle and an auxiliary paddle, a load cell 2, a discharge port 3, and a feed port 4. When the mixer works normally, materials enter the mixing drum 1 from the feeding hole 4, the stirring paddle and the mixing drum 1 uniformly mix the materials contained in the mixing drum 1 in a rotating mode, and the uniformly mixed materials are discharged from the discharging hole 3 at the bottom of the mixing drum.
The mixer is one of the main equipments in the metallurgical sintering and pelletizing process. In the sintering process, a powerful mixer is arranged after the batching process, and the prepared iron raw material, fuel, flux and the like are efficiently and uniformly mixed. In the pelletizing process, the mixer is arranged between the high-pressure roller mill and the pelletizing equipment, and the mixer is mainly used for fully and uniformly mixing the finely ground iron concentrate powder or other iron-containing powder with a small amount of binder, and is one of key processes for ensuring the quality of pellet ore. Therefore, the material mixing degree of the intensive mixer has important significance on the quality of subsequent sintering or pelletizing of the materials.
In the actual production process, factors influencing the mixing uniformity of the mixer mainly comprise two aspects, namely, the state of the mixture, such as the weight, the water content and the binder ratio of the mixture; the second is the state of the mixer. Such as the mixing drum speed, the main paddle speed, the auxiliary paddle speed, the filling rate of the mixture in the mixing drum and the mixing time. Because the state of the mixture needs to be considered in the whole production process, the state of the mixture is generally not adjusted when mixing is carried out. Therefore, the worker generally controls the mixing degree of the mixer by regulating and controlling the rotating speed of the mixing drum, the rotating speed of the main paddle and/or the rotating speed of the auxiliary paddle or prolonging the mixing time.
In the prior art, in order to meet the requirement of the degree of mixing, a worker generally controls the mixer according to working experience and sampling off-line detection of the mixture, and in order to meet the requirement of the degree of mixing, the worker often increases the rotating speed of the equipment or prolongs the mixing time within the range of the allowable rotating speed of the equipment (the rotating speed of the mixing drum, the rotating speed of the main paddle and/or the rotating speed of the auxiliary paddle), although the mixture with the degree of mixing meeting the requirement can be obtained in this way, unnecessary energy loss and running loss of the equipment can be caused by the excessively high rotating speed or the excessively long mixing time, that is, the energy efficiency of the running of the equipment is relatively high.
Disclosure of Invention
The application provides a mixing machine control system and method based on optimal mixing energy efficiency ratio, and aims to solve the problems that in the prior art, in order to obtain a mixture with a blending degree meeting requirements, an excessively high rotating speed or an excessively long mixing time is adopted, and unnecessary energy loss and running loss of equipment can be caused.
The first aspect of the application provides a mixing machine control system based on optimal mixing energy efficiency ratio, the mixing machine control system comprises a mixing machine and a mixture supply device, and the mixture supply device is connected with a feeding hole of the mixing machine and is used for providing a mixture for the mixing machine; the mixing machine control system is characterized by further comprising a rotating speed controller, a feeding and discharging controller, a feeding controller and a central processing unit, wherein the rotating speed controller and the feeding and discharging controller are connected with the mixing machine; wherein the central processor is configured to perform the steps of:
receiving the filling rate of the mixture sent by a feeding and discharging controller, the components of the mixture sent by a feeding controller, the mixture ratio, the bulk density, the water content and the binder ratio of each component, and the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle sent by a rotating speed controller;
predicting the mixing time according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the components, the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle to obtain the shortest mixing period;
predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the energy consumption of the mixer;
calculating the production rate of the mixture according to the shortest mixing period, the bulk density and the filling rate of the mixture; establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the productivity of the mixture;
performing global optimization on the mixing energy efficiency ratio model until a mixing machine control parameter when the energy efficiency ratio is optimal is obtained and is used as an actual control parameter of the mixing machine; the driving speed controller adjusts the rotating speeds of the mixing drum motor, the main paddle motor and the auxiliary paddle motor into actual control parameters, and the actual control parameters comprise the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle.
Optionally, the method includes the steps of predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle, and obtaining the energy consumption of the mixer:
quantifying the bulk density of the mixture, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to the same interval according to a certain shrinkage proportion;
obtaining energy consumption characteristic vectors according to the quantized bulk density of the mixed material, the rotating speed of the mixing drum, the rotating speed of the main paddle, the rotating speed of the auxiliary paddle, the water content, the binder ratio, the filling rate and the shortest mixing period;
and inputting the energy consumption characteristic vector into a pre-established energy consumption prediction model to obtain the energy consumption of the mixer, wherein the energy consumption prediction model comprises a mapping relation between the energy consumption characteristic vector and the energy consumption of the mixer.
Optionally, the mixer control system further includes a motor power detection device for connecting the mixing drum rotating motor, the main paddle rotating motor and the auxiliary paddle rotating motor;
the energy consumption prediction model is generated based on neural network model training and is established according to the following steps:
acquiring N groups of independent mixing drum rotating speeds, main paddle rotating speeds, auxiliary paddle rotating speeds, bulk density of mixed materials, water content, binder proportion and filling rate, and corresponding shortest mixing periods, and taking the obtained mixture as input of N groups of energy consumption training samples;
acquiring mixer energy consumption corresponding to the N groups of energy consumption training samples, and outputting the mixer energy consumption as the N groups of energy consumption training samples;
training a neural network model by using the input of the energy consumption training sample and the output of the energy consumption training sample and adopting a time back propagation method;
continuously updating the weight parameters, the bias parameters and the learning factors of the neural network model through iterative training;
and if the predicted value and the measured value of the neural network model reach the set tolerance range or the neural network model reaches the set maximum iteration number, ending the training, and storing the finally updated weight parameter, bias parameter and learning factor to obtain the energy consumption prediction model.
Optionally, a hybrid energy efficiency ratio model is established in the following manner;
the mixing energy efficiency ratio of the mixer can be expressed as follows:
Figure BDA0002642986290000031
wherein y is the mixing energy efficiency ratio, E is the energy consumption of the mixer, and u is the mixture production rate.
Optionally, the step of performing global optimization on the hybrid energy efficiency ratio model until obtaining the control parameter of the hybrid energy efficiency ratio when the energy efficiency ratio is optimal includes:
setting an N-dimensional feasible solution space of the hybrid energy efficiency ratio model, wherein N is 3 and is respectively the rotating speed of a mixing cylinder, the rotating speed of a main propeller and the rotating speed of an auxiliary propeller;
randomly initializing a particle group with the size of M, and setting an initial particle position, a search speed, an individual extreme value and a group extreme value; the initial particle position is the initial control parameter of the mixer, and the initial control parameter comprises the initial values of the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle; the search speed is the initial rate of change of the initial control parameter; the individual extreme value is the mixing energy efficiency ratio of the mixer corresponding to the position of a single particle; the group extreme value is the minimum value in the mixed energy efficiency ratios corresponding to the M particles;
iteratively updating the positions of the particles and the searching speed according to the following mixed energy efficiency ratio model, and calculating an individual extreme value corresponding to each particle, so as to continuously update the individual extreme value and the group extreme value of the mixed energy efficiency ratio model;
Figure BDA0002642986290000032
Figure BDA0002642986290000033
wherein, the initial position of the individual population
Figure BDA0002642986290000034
Search speed
Figure BDA0002642986290000035
Individual extremum
Figure BDA0002642986290000036
And group extremum Pn(ii) a n and n +1 represent the current iteration number; i represents the ith particle in the population; c1And C2Is a non-negative constant; w is the inertia factor; a is a constraint factor; n is a radical of1And N2Represents two mutually independent random numbers, and has a value range of [0, 1%]；
Figure BDA0002642986290000037
Is of particle i in the nth iterationThe speed of the search is such that,
Figure BDA0002642986290000038
is the current position of particle i in the ith iteration;
and after the optimization of the mixed energy efficiency ratio model is completed, outputting a group extreme value and a particle position corresponding to the group extreme value, wherein the particle position corresponding to the group extreme value is an actual control parameter of the mixer.
Optionally, according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of each component, the rotating speed of the mixing cylinder, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle, predicting the mixing time to obtain the shortest mixing period; the following steps are specifically executed:
quantifying the bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle at the same moment to the same interval according to a certain shrinkage proportion;
generating a period prediction sample according to the quantized bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle, the components of the mixture, the mixture ratio, the water content, the binder ratio and the filling rate of each component;
inputting the period prediction sample into a pre-established blending period prediction model, predicting the shortest blending period, wherein the blending period prediction model comprises a mapping relation between the period prediction sample and the shortest blending period.
Optionally, the mixer control system further comprises a mixing degree detection mechanism for the mixture, wherein the mixing degree detection mechanism comprises a sampling device and an off-line detection device; the sampling device is used for acquiring mixture detection samples from different depths of the mixer according to preset time intervals, inputting the mixture detection samples into the off-line detection device, and the off-line detection device is used for measuring the uniformity of the detection samples and obtaining the shortest mixing period according to the obtained uniformity of the mixture at different time intervals;
before the step of inputting the period prediction sample into the pre-established blending period prediction model to obtain the shortest blending period, the method further comprises the following steps:
acquiring a period learning sample which is before the acquisition time point of the period prediction sample and is closest to the period prediction sample, wherein the period learning sample comprises period learning sample input and a shortest blending period measured value corresponding to the period learning sample input;
and updating the blending period prediction model on line by using the period learning sample to obtain the updated blending period prediction model.
Optionally, the bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle at the same moment are quantized to the same interval according to a certain shrinkage proportion, and the following steps are specifically executed:
calculating the ratio of the bulk density to the density of the component with the highest density in the components;
calculating the ratio of the rotating speed of the mixing drum to the maximum rotating speed of the mixing drum;
calculating the ratio of the rotating speed of the main propeller to the maximum rotating speed of the main propeller;
and calculating the ratio of the rotating speed of the auxiliary propeller to the maximum rotating speed of the auxiliary propeller.
Optionally, the mixer control system further comprises a mixing degree detection mechanism for the mixture, wherein the mixing degree detection mechanism comprises a sampling device and an off-line detection device; the sampling device is used for acquiring mixture detection samples from different depths of the mixer according to a preset time interval and inputting the mixture detection samples into the off-line detection device, and the off-line detection device is used for measuring the mixing degree of the detection samples at different time intervals to obtain the shortest mixing period;
the blending period prediction model is generated by training a learning machine model and is established according to the following steps:
acquiring N groups of independent mixture parameters and corresponding mixer state parameters, wherein the mixture parameters comprise components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the mixture in a mixing barrel, and the mixer state parameters comprise the rotating speed of the mixing barrel, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle;
taking N groups of independent mixture parameters and corresponding mixer state parameters as the input of N groups of periodic training samples;
according to a preset time interval, obtaining mixture detection samples from different depths of the mixer, performing off-line measurement on the detection samples to obtain the blending degree of the mixture, and obtaining a measured value of the shortest blending period as the output of N groups of period training samples;
training a learning machine model by using the input of the periodic training sample and the output of the periodic training sample and adopting a time back propagation method;
continuously updating the weight parameters, the bias parameters and the learning factors of the learning machine model through iterative training;
and if the predicted value and the measured value of the learning machine model reach the set tolerance range or the learning machine model reaches the set maximum iteration number, finishing the training, and storing the finally updated weight parameter, the offset parameter and the learning factor to obtain the blending period prediction model.
The second aspect of the present application provides a mixer control method based on optimal mixing energy efficiency ratio, the mixer control method including:
the method comprises the steps of obtaining the filling rate of a mixture sent by a feeding and discharging controller, obtaining the components of the mixture sent by a feeding controller, the ratio, bulk density, water content and binder ratio of the components, and obtaining the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle sent by a rotating speed controller;
predicting the mixing time according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the components, the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle to obtain the shortest mixing period;
predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the energy consumption of the mixer;
calculating the production rate of the mixture according to the shortest mixing period, the bulk density and the filling rate of the mixture; establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the production rate of the mixture;
and carrying out global optimization on the mixing energy efficiency ratio model until the mixing machine control parameters when the energy efficiency ratio is optimal are obtained and used as the actual control parameters of the mixing machine, wherein the actual control parameters comprise the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle.
According to the technical scheme, the mixer control system and the method based on the optimal mixing energy efficiency ratio are provided, the mixer control system comprises a mixer and a mixture supply device, and the mixture supply device is connected with a feed inlet of the mixer and is used for supplying a mixture to the mixer; the control system of the mixing machine also comprises a rotating speed controller, a feeding and discharging controller, a feeding controller and a central processing unit, wherein the rotating speed controller and the feeding and discharging controller are connected with the mixing machine, the feeding controller is connected with the mixture supply equipment, and the central processing unit is respectively connected with the rotating speed controller and the feeding controller.
In the practical application process, the central processing unit obtains the filling rate of the mixture through the feeding and discharging controller, obtains the components of the mixture, the proportion, the bulk density, the water content and the binder ratio of each component through the feeding controller, and obtains the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle through the rotating speed controller; predicting the mixing time according to the components of the obtained mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the components, the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle to obtain the shortest mixing period; then predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the energy consumption of the mixer; calculating the production rate of the mixture according to the shortest mixing period, the bulk density and the filling rate of the mixture; establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the production rate of the mixture; finally, carrying out global optimization on the mixing energy efficiency ratio model until a mixing machine control parameter when the energy efficiency ratio is optimal is obtained and is used as an actual control parameter of the mixing machine; the driving rotating speed controller adjusts the rotating speeds of the mixing drum motor, the main paddle motor and the auxiliary paddle motor into actual control parameters.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments are briefly described below, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a front view of a prior art intensive mixer;
FIG. 2 is a top view of an intensive mixer corresponding to FIG. 1;
fig. 3 is a schematic overall structural diagram of a mixer control system provided in an embodiment of the present application;
FIG. 4 is a flowchart illustrating steps performed by a CPU configured according to an embodiment of the present invention;
fig. 5 is a flowchart for predicting a shortest blend cycle by using a blend cycle prediction model according to an embodiment of the present application;
FIG. 6 is a flowchart of online updating of a blending cycle prediction model according to an embodiment of the present disclosure;
FIG. 7 is a flow chart of obtaining predicted energy consumption of a mixer using an energy consumption prediction model according to an embodiment of the present application;
FIG. 8 is a flowchart of generating an energy consumption prediction model using a neural network model according to an embodiment of the present disclosure;
FIG. 9 is a flowchart illustrating an optimization of a hybrid energy efficiency ratio model according to an embodiment of the present disclosure;
fig. 10 is a flowchart of generating a blending cycle prediction model using a learning machine model according to an embodiment of the present application.
Illustration of the drawings:
the mixing machine comprises a 100-mixing machine, a 200-rotating speed controller, a 300-feeding and discharging controller, a 1-mixing barrel, a 2-weighing sensor, a 3-discharging opening, a 4-feeding opening, a 5-mixture supplying device, a 501-feeding controller, a 6-central processing unit and a 7-mixing degree detecting mechanism.
Detailed Description
Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following examples do not represent all embodiments consistent with the present application. But merely as exemplifications of systems and methods consistent with certain aspects of the application, as recited in the claims.
The intensive mixers are continuously rotating cylindrical machines, and are classified into horizontal intensive mixers and vertical intensive mixers, which are slightly different from each other in equipment structure but basically similar in control principle, and hereinafter referred to as mixers. In order to optimize the energy efficiency ratio of the mixer under the condition of meeting the requirement of the set mixing degree, as shown in fig. 3, an embodiment of the present application provides a mixer control system based on the optimal mixing energy efficiency ratio, the mixer control system includes a mixer 100 and a mixture supply device 5, and in the practical application process, the mixture supply device 5 may adopt a disk feeder, and the disk feeder is connected with the feed port 4 of the mixer 100, so as to provide the mixture to the mixer 100; mixer control system is still including being used for control mix the rotary speed controller 200 of the mixing drum rotational speed, main oar rotational speed and the vice oar rotational speed of machine 100, and control the business turn over material controller 300 of 1 feed inlet 4 of mixing drum and discharge opening 3, business turn over material controller 300 can control mix the business turn over material condition of machine 100, and the monitoring the mixture flow of 1 feed inlet of mixing drum and discharge opening 3. The mixer control system further comprises a feed controller 501 connected to the mix supply device 5, the feed controller 501 may be a circular roller rotational speed controller of a circular roller feeder. For controlling the mix feed speed of the mix supply device 5; and the device also comprises a central processing unit 6 which is respectively connected with the rotating speed controller 12, the feeding and discharging controller 300 and the feeding controller 501.
As shown in fig. 4, in order to realize the mixing-energy-ratio-based optimization, the mixer is controlled, and the mixer control system may be configured to perform the following steps S101 to S111.
The feed controller 501 may be configured to perform the following steps 101 and 102.
And step S101, obtaining the filling rate of the mixture.
And S102, sending the filling rate of the mixture to a central processing unit.
The filling rate of the mixed material in the mixing cylinder can be controlled by controlling the feeding amount and the discharging amount of the mixing cylinder, that is, the filling rate of the mixed material in the mixing cylinder can be obtained by the feeding controller 501.
The feed controller 501 may be configured to perform the following steps 103 and 104.
Step S103, obtaining the components of the mixture, and the proportion, bulk density, water content and binder ratio of each component.
And step S104, sending the components of the mixture, the mixture ratio, the bulk density, the water content and the binder ratio of the components to a central processing unit.
The water content and the bulk density of the mixture can be calculated according to the components of the material, because the water content of the mixture can be generally kept at a relatively stable level before mixing, the water content and the bulk density can be obtained through sampling detection, the detection result is stored in the feed controller 501 of the mixture supply device at the upstream of the mixer 100, the mixture with certain mixture ratio components needs to be provided for the mixer 100 before the mixture is mixed, the mixture ratio of each component in the mixture needs to be strictly controlled according to the production requirement, the mixture ratio relation needs to be recorded and input into the feed controller 501 of the mixture supply device, and the production requirement system for producing various mixtures can be recorded or stored in the feed controller 501, so the binder ratio can be obtained from the feed controller 501 of the material. The mixing ratio of the components is substantially the mass ratio of the components.
The rotational speed controller 200 may be configured to perform the following steps 105 and 106:
and step S105, acquiring the rotating speed of the mixing drum, the rotating speed of the main propeller and the rotating speed of the auxiliary propeller.
And step S106, sending the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to the central processing unit 6.
Rotational speed controller 200 can control mixing drum rotational speed, main oar rotational speed and vice oar rotational speed, for rotational speed controller 200 sends and gives central processing unit 6's rotational speed, can rotational speed controller 200 exports the controlled quantity of mixing drum rotational speed, main oar rotational speed and vice oar rotational speed, also can rotational speed controller 200 adopts the sensor to measure the rotational speed through the rotational speed of sensor measurement, and concrete mode can be for installing speed sensor in the drive shaft of mixing drum, main oar and vice oar respectively, acquires the rotational speed of drive shaft through transmission sensor to obtain mixing drum rotational speed, main oar rotational speed and vice oar rotational speed.
The rotation speed sensor is a sensor that converts the rotation speed of a rotating object into electric quantity to be output, and for example, a magnetic-sensing rotation speed sensor or a laser rotation speed sensor is used. In the process of detecting the rotating speed, if the detected rotating speed is in a stable state, the rotating speed of the driving shaft in the stable state is stored and used as subsequent detection data, and if the detected rotating speed of the driving shaft changes, the stored rotating speed of the driving shaft is updated in real time.
The central processor 6 may be configured to perform the following steps 107 to 111:
and step S107, receiving the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of each component, and the rotating speed of the mixing cylinder, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle.
And S108, predicting the mixing time according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the components, the rotating speed of the mixing cylinder, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the shortest mixing period.
As shown in fig. 5, in step S108, step S201 to step S203 are further included.
Step S201, quantifying the bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to the same interval according to a certain shrinkage proportion at the same moment.
The data amount and the data type of the bulk density, the water content, the binder ratio, the filling rate, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle at the same moment are different, so that the data amount cannot be directly calculated. In the embodiment of the application, data and processing are required to be carried out on the bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle.
Namely, calculating the ratio of the bulk density to the density of the component with the highest density in the components, and calculating the ratio of the rotating speed of the mixing drum to the maximum rotating speed of the mixing drum; calculating the ratio of the rotating speed of the main propeller to the maximum rotating speed of the main propeller; and calculating the ratio of the rotating speed of the auxiliary propeller to the maximum rotating speed of the auxiliary propeller. The same interval after quantization is an interval (0, 1).
Wherein, the quantization model of the bulk density is as follows:
Figure BDA0002642986290000091
the quantitative model of the rotating speed of the mixing drum is as follows:
Figure BDA0002642986290000092
the quantitative model of the main propeller rotating speed is as follows:
Figure BDA0002642986290000093
the quantitative model of the rotating speed of the auxiliary propeller is as follows:
Figure BDA0002642986290000094
wherein beta represents the mixture ratio of each component, Norm (rho) represents the bulk density after quantization, rho represents the bulk density,
Figure BDA0002642986290000095
the density of the component with the highest density among the components is expressed; r is a radical of hydrogen1Indicates the water content r2Denotes the binder ratio, r3Represents the fill rate; norm (n)1) Representing the quantified rotational speed of the mixing drum, n1The rotational speed of the mixing drum is indicated,
Figure BDA0002642986290000096
representing the maximum rotational speed of the mixing drum; norm (n)2) Representing the quantized main rotor speed, n2The rotational speed of the main propeller is shown,
Figure BDA0002642986290000097
representing the maximum rotational speed of the main rotor; norm (n)3) Representing the quantized secondary rotor speed, n3The rotational speed of the auxiliary propeller is shown,
Figure BDA0002642986290000098
representing the maximum rotational speed of the secondary paddles.
And S202, generating a period prediction sample according to the quantized bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle, the rotating speed of the auxiliary paddle, the components of the mixture, the mixture ratio of each component, the water content, the binder ratio and the filling rate.
The parameters subjected to scaling quantization are as follows:
X(k)＝(x1(k),x2(k),x3(k),x4(k),x5(k),x6(k),x7(k),x8(k))＝Norm(β,ρ,r1,r2,r3,n1,n2,n3)。
x (k) represents input data for a prediction model, x1(k)，x2(k)，x3(k)，x4(k)，x5(k)，x6(k)，x7(k)，x8(k) Respectively correspond to beta, rho, r1,r2,r3,n1,n2,n3Processed data, wherein x1(k) Contains the information of each component and the proportion of each component, x2(k) Contains the information of each component and the bulk density of each component, and in practical application, each component can be numbered by numbers, x1(k) Wherein the serial numbers of the components correspond to the mixture ratios of the components, and are in x2(k) Wherein the numbering of the components corresponds to the bulk density of the components.
The periodic prediction sample integrates the influence factors of the mixing degree according to a certain rule, for example, for a mixture with three components, the influence factors of the mixing degree are integrated into a set or a characteristic vector according to the following sequence:
Figure BDA0002642986290000099
wherein the first 3 indicates that the raw material types of the mix are three, and the ones after 3
Figure BDA00026429862900000910
Respectively show the mixture ratio of three raw materials with the numbers of 1,4 and 6,
Figure BDA00026429862900000911
respectively, the bulk densities, x, of the three materials numbered 1,4 and 63(k)，x4(k)，x5(k)，x6(k)，x7(k),x8(k) The bulk density, the water content, the binder ratio, the filling rate, the rotation speed of the mixing drum, the rotation speed of the main paddle and the rotation speed of the auxiliary paddle are respectively expressed.
Step S203, inputting the period prediction sample into a pre-established blending period prediction model, and predicting the shortest blending period, wherein the blending period prediction model comprises a mapping relation between the period prediction sample and the shortest blending period.
The mapping relationship can obtain a corresponding shortest mixing period through different mixing parameters and different states of the state parameters of the mixer 100, and the shortest mixing period t (k) can be expressed in the following manner:
T(k)＝fk(X(k))＝fk(x1(k),x2(k),x3(k),x4(k),x5(k),x6(k),x7(k),x8(k))
wherein f iskAnd the mapping relation between the period prediction sample and the shortest blending period at the moment k is shown.
Since the blending period prediction model is pre-established according to actual production data of part of the mixing machines 100, in an application stage, the blending period prediction model is used on all mixing machine 100 devices, actual working conditions of different mixing machines 100 have certain differences, and the working conditions of the same mixing machine 100 change with time in a long-term use process.
The mixer control system also comprises a mixing degree detection mechanism 7 of the mixture, and the mixing degree detection mechanism comprises a sampling device and an off-line detection device; the sampling device is used for obtaining mixture detection samples from different depths of the mixer 100 according to preset time intervals, and inputting the mixture detection samples into the offline detection device, the offline detection device is used for measuring the mixing degree of the detection samples, obtaining the mixing degree of the mixture under different time intervals, comparing the measured mixing degree with the mixing degree value required by production, recording sampling time when the measured mixing degree value meets the production requirement, and starting the working time of the mixer to the sampling time, wherein the experienced time record is the shortest mixing period.
Step S301, a period learning sample which is before the acquisition time point of the period prediction sample and is closest to the period prediction sample is obtained, wherein the period learning sample comprises period learning sample input and a shortest blending period measured value corresponding to the period learning sample input.
The period learning sample not only comprises the mixture parameters of the mixture and the state parameters of the mixing machine 100, but also comprises a corresponding measured shortest mixing period, and the specific acquisition method of the period learning sample comprises the following steps: obtaining a historical period prediction sample in a preset time interval before the acquisition time point of the period prediction sample and closest to the period prediction sample, and measuring the shortest mixing period corresponding to the historical period prediction sample. It should be noted that the parameters of the mixture in the embodiment of the present application include the components of the mixture, the mixture ratio, bulk density, water content, binder ratio, and filling rate of the mixture in the mixing barrel, and the state parameters of the mixer 100 include the rotation speed of the mixing barrel, the rotation speed of the main paddle, and the rotation speed of the auxiliary paddle.
The historical period prediction samples collected here are used as period learning samples, and since the mixing process of the mixer 100 is a long-time continuous process, the mixer 100 is always mixing before the period prediction samples are collected, and the historical period prediction samples in the preset time interval closest to the period prediction samples are collected, the condition of the mixer 100 corresponding to the obtained period learning samples can be ensured to be consistent with the condition of the mixer 100 at the time point of the period prediction sample collection.
And step S302, updating the blending period prediction model on line by using the period learning sample, and acquiring the updated blending period prediction model.
In order to further ensure that the shortest blending period output by the blending period prediction model is more accurate. In the specific updating process, according to the prediction deviation value between the prediction value of the periodic learning sample and the measured shortest blending period (the shortest blending period corresponding to the periodic learning sample), the blending period prediction model has two updating modes, if the prediction deviation value is small and relatively stable and is within the allowable error range of the model quality index, the prediction deviation value is directly added to the prediction value of the prediction model, and the result is used as the updated prediction value. And if the prediction deviation value is large and the mapping relation is judged to be changed according to the model quality index, updating the mapping relation contained in the blending period prediction model according to the period learning sample and the shortest blending period corresponding to the period learning sample.
It should be noted that, generally, the mean square error of the predicted deviation value may be used as the quality index, and then a statistical confidence limit is preset according to the statistical distribution rule of the quality index to determine whether to trigger the update and the required update method. Although the off-line detection result of the mixture mixing degree is not suitable for the closed-loop control problem of the mixing process due to the hysteresis problem, the off-line detection result can be used for the reference of the stable state, namely, when the mixer 100 reaches the stable state under the stable state, the shortest mixing period can be maintained at a certain level, under the normal condition, the distribution of the measured value usually does not deviate from the confidence interval although the measured value fluctuates, and when the confidence interval is exceeded, the model updating mechanism is triggered. If the process characteristics are judged to be gradual change according to the index analysis result, a model recurrence method is selected, and the soft measurement model is updated by using a moving window recurrence method, and the method comprises the following steps:
setting a sample set of an original blending period prediction model as S { [ X ]1,Y1],...,[Xt,Yt]T is totalThe number of samples of (1). When a new measured value [ X ] is obtainedm,Ym]If it is added to the sample set and the oldest sample is eliminated, the new sample set (cycle learning samples) is:
S＝{[X2,Y2],...,[Xt,Yt],[Xm,Ym]}
and then updating the blending period prediction model on line by using the period learning samples to obtain a new blending period prediction model.
And if the process characteristics belong to mutation according to the index analysis result, selecting an instant learning method, selecting data samples similar to the current measurement state in the period prediction samples in the historical period, and reconstructing a prediction model.
And step S109, predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle, so as to obtain the energy consumption of the mixer.
As shown in fig. 7, in step S109, step S401 to step S403 are further included.
And S401, quantizing the bulk density of the mixed material, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to the same interval according to a certain shrinkage proportion.
Wherein, the quantization model of the bulk density is as follows:
Figure BDA0002642986290000111
the quantitative model of the rotating speed of the mixing drum is as follows:
Figure BDA0002642986290000112
the quantitative model of the main paddle rotating speed is as follows:
Figure BDA0002642986290000113
the quantitative model of the rotating speed of the auxiliary propeller is as follows:
Figure BDA0002642986290000114
wherein beta represents the mixture ratio of each component, Norm (rho) represents the bulk density after quantization, rho represents the bulk density,
Figure BDA0002642986290000115
the density of the component with the highest density among the components is expressed; r is1Indicates the water content r2Denotes the binder ratio, r3Represents the fill rate; norm (n)1) Representing the quantified rotational speed of the mixing drum, n1The rotational speed of the mixing drum is indicated,
Figure BDA0002642986290000116
representing the maximum rotational speed of the mixing drum; norm (n)2) Representing the quantized main rotor speed, n2The rotational speed of the main propeller is shown,
Figure BDA0002642986290000117
representing the maximum rotational speed of the main rotor; norm (n)3) Representing the quantized secondary rotor speed, n3The rotational speed of the auxiliary propeller is shown,
Figure BDA0002642986290000118
representing the maximum rotational speed of the secondary paddles.
And S402, obtaining an energy consumption characteristic vector according to the quantized bulk density of the mixed material, the rotating speed of the mixing drum, the rotating speed of the main paddle, the rotating speed of the auxiliary paddle, the water content, the binder ratio, the filling rate and the shortest mixing period.
The energy consumption characteristic vector is used for integrating the influence factors of the energy consumption of the mixer according to a certain rule, for example, for a mixture with three components, the influence factors of the mixing degree are integrated into a set or characteristic vector according to the following sequence:
M(k)＝(x2(k),x3(k),x4(k),x5(k),x6(k),x7(k),x8(k),T(k))
x2(k)，x3(k)，x4(k)，x5(k)，x6(k)，x7(k),x8(k) and T (k) respectively represents the bulk density, the water content, the ratio of the bonding agent, the filling rate, the rotating speed of the mixing drum, the rotating speed of the main paddle, the rotating speed of the auxiliary paddle and the shortest mixing period.
And S403, inputting the energy consumption characteristic vector into a pre-established energy consumption prediction model to obtain the energy consumption of the mixer, wherein the energy consumption prediction model comprises a mapping relation between the energy consumption characteristic vector and the energy consumption of the mixer.
The mixer energy consumption e (k) can be expressed in the following way:
E(k)＝Fk(X(k))＝Fk(x2(k),x3(k),x4(k),x5(k),x6(k),x7(k),x8(k),T(k))
wherein, FkAnd the mapping relation between the energy consumption characteristic vector and the energy consumption of the mixer at the moment k is shown.
The energy consumption prediction model is established by utilizing a plurality of groups of known mixture parameters, the state parameters of the mixer 100 and the corresponding shortest mixing period. The embodiment of the application provides a method for generating the energy consumption prediction model by utilizing a neural network model training mode. The specific operation is that a plurality of groups of known mixture parameters and mixer 100 state parameters are used as the input of a neural network model, the corresponding shortest mixing period is used as the output of the neural network model, and the neural network model is trained, namely, a weight matrix and an offset item corresponding to the middle layer of the neural network model are adjusted, so that the mapping relation between the mixture parameters and the corresponding mixer 100 state parameters and the shortest mixing period is established. As shown in fig. 8, the specific generation step includes:
and S501, acquiring N groups of independent mixing drum rotating speeds, main paddle rotating speeds, auxiliary paddle rotating speeds, mixed material bulk density, water content, binder ratio and filling rate, and corresponding shortest mixing period, and taking the obtained mixture as input of N groups of energy consumption training samples.
Calculating the ratio of the bulk density to the density of the component with the highest density in the components, and calculating the ratio of the rotating speed of the mixing drum to the maximum rotating speed of the mixing drum; calculating the ratio of the rotating speed of the main propeller to the maximum rotating speed of the main propeller; and calculating the ratio of the rotating speed of the auxiliary propeller to the maximum rotating speed of the auxiliary propeller, wherein the same quantized interval is an interval (0, 1).
And integrating the quantized rotating speed of the mixing drum, the rotating speed of the main paddle, the rotating speed of the auxiliary paddle, the bulk density and the water content of the mixed material, the binder proportion, the filling rate and the shortest mixing period into a set or a characteristic vector, and using the set or the characteristic vector as the input of N groups of energy consumption training samples. It should be noted that the shortest blending cycle here is the shortest blending cycle obtained in step 108.
And step S502, acquiring mixer energy consumption corresponding to the N groups of energy consumption training samples, and outputting the mixer energy consumption as the N groups of energy consumption training samples.
In the process of establishing the energy consumption prediction model, instantaneous power of power supply equipment (a mixing drum motor, a main paddle motor and an auxiliary paddle motor) of the mixing machine is detected in real time, and then the instantaneous power in the shortest mixing period is integrated, so that energy consumption of the mixing machine in the shortest mixing period is obtained, and N groups of obtained energy consumption training samples are output.
And S503, training the neural network model by using the input of the energy consumption training sample and the output of the energy consumption training sample and adopting a time back propagation method.
The time back propagation method is a learning algorithm suitable for the multilayer neuron network, and guides the response (output) of the multilayer neuron network to the input to reach a preset target range through excitation propagation and repeated loop iteration of weight updating.
Step S504, the weight parameters, the bias parameters and the learning factors of the neural network model are continuously updated through iterative training.
And step S505, if the predicted value and the measured value of the neural network model reach a set tolerance range or the neural network model reaches a set maximum iteration number, ending the training, and storing the finally updated weight parameter, the offset parameter and the learning factor to obtain the energy consumption prediction model.
And establishing a mapping relation between the period prediction sample and the shortest blending period in the neural network model by continuously updating the weight parameter, the bias parameter and the learning factor of the neural network model until the shortest blending period is accurately predicted according to the mapping relation between the period prediction sample and the shortest blending period. The specific judgment method comprises the steps of judging whether the predicted value and the detected value of the neural network model reach a set tolerance range or not, judging whether the neural network model reaches a set maximum iteration number or not, finishing training if the predicted result and the detected result of the neural network model reach the set tolerance range or the neural network model reaches the set maximum iteration number, and storing the finally updated weight parameter, bias parameter and learning factor to obtain the energy consumption prediction model.
The energy consumption prediction model is generated by utilizing neural network model training. Specifically, a BP neural network model is adopted, wherein the BP neural network model mainly comprises an input layer, a hidden layer and an output layer, each layer is provided with a corresponding connection weight matrix and a corresponding bias item, the multi-layer neuron network is trained through an energy consumption training sample, and weight parameters, bias parameters and learning factors are continuously updated, so that the prediction model is obtained.
In the specific training process of the neural network model in the embodiment of the application, the collected samples are divided into two parts, wherein 2/3 groups of samples are used as training data of the neural network model, and weight parameters, bias parameters and learning factors are continuously updated; 1/3 group samples are used as test data of the neural network model to verify the accuracy and reliability of the model.
Step S110, calculating the production rate of the mixture according to the shortest mixing period, the bulk density of the mixture and the filling rate; and establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the productivity of the mixture.
According to the filling rate and the capacity of the mixing drum, the volume of the mixed materials in the mixing drum can be obtained, the mass of the mixed materials in the mixing drum can be calculated according to the bulk density of the mixed materials, then the time represented by the shortest mixing period is introduced, the mass of the mixed materials produced in unit time can be obtained, the unit time can be set according to actual production, such as every hour or every day, and the technical scheme of the embodiment of the application is to set the unit time to every hour.
Establishing a hybrid energy efficiency ratio model in the following manner;
the mixing energy efficiency ratio of the mixer can be expressed as follows:
Figure BDA0002642986290000141
Figure BDA0002642986290000142
wherein y is the energy efficiency ratio of mixing, E is the energy consumption of the mixer, u is the productivity of the mixture, m is the mass of the mixture completing mixing in the shortest mixing period, rho represents the bulk density of the mixture, and r is3The filling rate of the mixture in the mixing drum is shown, and V represents the capacity of the mixing drum.
And S111, carrying out global optimization on the mixing energy efficiency ratio model until a mixing machine control parameter when the energy efficiency ratio is optimal is obtained and is used as an actual control parameter of the mixing machine, and driving a rotating speed controller to adjust a mixing drum motor, a main paddle motor and an auxiliary paddle motor into the actual control parameter, wherein the actual control parameter comprises the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle.
As shown in fig. 9, the step of performing global optimization on the hybrid energy efficiency ratio model includes:
step S601, setting an N-dimensional feasible solution space of the hybrid energy efficiency ratio model, where N is 3, and the N is a mixing barrel rotation speed, a main paddle rotation speed, and an auxiliary paddle rotation speed.
Since the entire metal sintering process flow needs to be considered during the operation of the mixer, the mixer 100 is generally only allowed to adjust the mixing drum speed, the main paddle speed, and the auxiliary paddle speed, so N is set to 3.
Step S602, a particle group with the size of M is initialized randomly, and the initial position of the particle, the search speed, the individual extreme value and the group extreme value are set.
The initial particle position is an initial control parameter of the mixer, and the initial control parameter comprises initial values of the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle; the search speed is the initial rate of change of the initial control parameter; the individual extreme value is the mixing energy efficiency ratio of the mixer corresponding to the position of a single particle; the population extremum is the minimum value of the energy-mixing ratios corresponding to the M particles.
Step S603, the positions of the particles and the searching speed are updated iteratively according to the following mixed energy efficiency ratio model, and an individual extreme value corresponding to each particle is calculated, so that the individual extreme value and the group extreme value of the mixed energy efficiency ratio model are updated continuously.
Figure BDA0002642986290000143
Figure BDA0002642986290000144
Wherein:
Figure BDA0002642986290000145
is the initial position of the population individual;
Figure BDA0002642986290000146
is the search speed;
Figure BDA0002642986290000147
is an individual extremum;
Pnis a group extremum;
n and n +1 represent the current iteration number; i represents the ith particle in the population; c1And C2Is a non-negative constant and represents a tracking learning factor, in the embodiment of the application, C1And C2Respectively taking 1.5 and 1.6; w is an inertia factor, and in the present embodiment, W is set to 0.5; a is a constraint factor, which is a weight for controlling the search speed; n is a radical of1And N2Represents two independent random numbers with the value range of 0,1]；
Figure BDA0002642986290000151
Is the search speed of particle i in the nth iteration
Figure BDA0002642986290000152
Is the ith iterationIn the generation, the current position of the particle i, n and i are both positive integers greater than or equal to 1.
And step S604, after the optimization of the mixing energy efficiency ratio model is completed, outputting a group extreme value and a particle position corresponding to the group extreme value, wherein the particle position corresponding to the group extreme value is an actual control parameter of the mixer.
Judging two conditions for completing optimization of the hybrid energy efficiency ratio model, wherein one condition is that the iteration frequency reaches the set maximum iteration frequency; and the other is that the global optimum meets the minimum limit, if the minimum limit is met, the optimization is finished, and if the minimum limit is not met, the step S503 is returned, iterative updating is continued, and the optimum value is searched. It should be noted that the minimum limit mentioned here is a globally optimal empirical limit, which in the present embodiment is represented by the minimum requirement that the energy efficiency ratio must meet, said minimum requirement being a value determined from empirical accumulations during long-term operation of a specific mixer device, taking into account the type and model of the mixer actually used, and the age of use.
The blending cycle prediction model is established by utilizing a plurality of groups of known mixture parameters, the state parameters of the mixer 100 and the corresponding measured shortest blending cycle. The embodiment of the application provides a method for generating the blending period prediction model by utilizing a learning machine model training mode. In order to generate the blending period prediction model, a blending degree detection mechanism of the mixture needs to be utilized, wherein the blending degree detection mechanism comprises a sampling device and an off-line detection device; the sampling device is used for acquiring mixture detection samples from different depths of the mixer according to preset time intervals, inputting the mixture detection samples into the off-line detection device, and the off-line detection device is used for measuring the mixing degree of the detection samples at different time intervals to obtain the shortest mixing period.
The concrete operation is that a plurality of groups of known mixture parameters and mixer 100 state parameters are used as the input of a learning machine model, the corresponding blending degree measured value is used as the output of the learning machine model, and the learning machine model is trained, namely, the corresponding weight matrix and offset item between each layer of the learning machine model are adjusted, so that the mapping relation between the mixture parameters and the corresponding mixer 100 state parameters and the blending degree is established. Referring to fig. 10, a flowchart for generating a blending cycle prediction model by using a learning machine model according to the embodiment of the present application includes:
and S701, acquiring N groups of independent mixture parameters and corresponding mixer 100 state parameters, wherein the mixture parameters comprise the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the mixture in the mixing barrel, and the mixer 100 state parameters comprise the rotating speed of the mixing barrel, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle.
The N groups of independent mixture parameters and the corresponding mixer 100 status parameters may be data of the same mixer 100 or data of a plurality of mixers 100, and are divided into one group according to a corresponding relationship, that is, data of the same mixer 100 and at the same time are set as unified group data.
Step S702, using the N groups of independent mixture parameters and the corresponding mixer 100 state parameters as input of the N groups of periodic training samples. The bulk density in the mixture parameters, and the mixing drum rotational speed, the main paddle rotational speed, and the auxiliary paddle rotational speed in the state parameters of the mixer 100 need to be quantized to the interval (0,1), and then other data are integrated as the input of the periodic training sample.
And step S703, acquiring mixture detection samples from different depths of the mixer according to a preset time interval, performing off-line measurement on the detection samples to obtain the blending degree of the mixture, and acquiring a measurement value of the shortest blending period as the output of N groups of period training samples.
Step S704, train the learning machine model by using the input of the periodic training sample and the output of the periodic training sample and using the time back propagation method.
The dynamic prediction training module trains a learning machine model by adopting a time back propagation method by utilizing the input of the periodic training samples and the output of the periodic training samples; the time back propagation method is a learning algorithm suitable for the multilayer neuron network, and guides the response (output) of the multilayer neuron network to the input to reach a preset target range through excitation propagation and repeated iteration of weight updating.
Step S705, continuously updating the weight parameter, the bias parameter, and the learning factor of the learning machine model through iterative training.
Step S706, if the predicted value and the measured value of the learning machine model reach the set tolerance range or the learning machine model reaches the set maximum iteration number, the training is finished, and the finally updated weight parameter, the offset parameter and the learning factor are saved to obtain the blending period prediction model.
The mapping relation between the period prediction sample and the shortest blending period is established in the learning machine model by continuously updating the weight parameter, the bias parameter and the learning factor of the learning machine model until the shortest blending period can be accurately predicted according to the mapping relation between the period prediction sample and the shortest blending period.
The specific judgment method comprises the steps of judging whether the predicted value and the detected value of the learning machine model reach a set tolerance range or not, judging whether the learning machine model reaches a set maximum iteration number or not, finishing training if the predicted result and the detected result of the learning machine model reach the set tolerance range or the learning machine model reaches the set maximum iteration number, and storing the finally updated weight parameter, the offset parameter and the learning factor to obtain the blending cycle prediction model.
The following are embodiments of the method of the present application for implementing embodiments of the system of the present application. For details which are not disclosed in the method embodiments of the present application, reference is made to the system embodiments of the present application.
A mixer control method based on mixing energy efficiency ratio optimization, the mixer control method comprising:
and acquiring the filling rate of the mixture sent by the feeding and discharging controller, the components of the mixture sent by the feeding controller, the ratio, bulk density, water content and binder ratio of the components, and the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle sent by the rotating speed controller.
And predicting the mixing time according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of each component, and the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddles to obtain the shortest mixing period.
And predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder proportion and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the energy consumption of the mixer.
Calculating the production rate of the mixture according to the shortest mixing period, the bulk density and the filling rate of the mixture; and establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the productivity of the mixture.
And carrying out global optimization on the mixing energy efficiency ratio model until a mixing machine control parameter when the energy efficiency ratio is optimal is obtained and is used as an actual control parameter of the mixing machine, wherein the actual control parameter comprises the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle.
According to the technical scheme, the embodiment of the application provides a mixing machine control system and method based on optimal mixing energy efficiency ratio, the mixing machine control system comprises a mixing machine 100 and a mixture supply device 5, and the mixture supply device 5 is connected with a feed port 4 of the mixing machine 100 and is used for supplying mixture to the mixing machine 100; the mixer control system further comprises a rotational speed controller 200 and a feeding and discharging controller 300 connected to the mixer 100, a feeding controller 501 connected to the mix supply device 5, and a central processor 6 connected to the rotational speed controller 200 and the feeding controller 501, respectively.
In the practical application process, the central processing unit obtains the filling rate of the mixture through the feeding and discharging controller, obtains the components of the mixture, the proportion, the bulk density, the water content and the binder ratio of the components through the feeding controller, and obtains the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle through the rotating speed controller; and according to the components of the obtained mixture, the mixture ratio, the bulk density, the water content, the binder proportion and the filling rate of each component, the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle, predicting the mixing time to obtain the shortest mixing period; then predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the energy consumption of the mixer; calculating the mixture production rate according to the shortest mixing period, the bulk density and the filling rate of the mixture; establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the production rate of the mixture; finally, carrying out global optimization on the mixed energy efficiency ratio model until a mixing machine control parameter when the energy efficiency ratio is optimal is obtained and is used as an actual control parameter of the mixing machine; the driving rotating speed controller adjusts the rotating speeds of the mixing drum motor, the main paddle motor and the auxiliary paddle motor into actual control parameters.
The embodiments provided in the present application are only a few examples of the general concept of the present application, and do not limit the scope of the present application. Any other embodiments that can be extended by the solution according to the present application without inventive efforts will be within the scope of protection of the present application for a person skilled in the art.

Claims (10)

1. The mixing machine control system based on the optimal mixing energy efficiency ratio is characterized by comprising a mixing machine and a mixture supply device, wherein the mixture supply device is connected with a feeding hole of the mixing machine and is used for supplying a mixture to the mixing machine; the mixer control system is characterized by further comprising a rotating speed controller, a feeding and discharging controller, a feeding controller and a central processing unit, wherein the rotating speed controller and the feeding and discharging controller are connected with the mixer, the feeding controller is connected with the mixture supply equipment, and the central processing unit is respectively connected with the rotating speed controller and the feeding controller; wherein the central processor is configured to perform the steps of:
receiving the filling rate of the mixture sent by the feeding and discharging controller, receiving the components of the mixture sent by the feeding controller, the mixture ratio, the bulk density, the water content and the binder ratio of each component, and receiving the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle sent by the rotating speed controller;
predicting the mixing time according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the components, the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle to obtain the shortest mixing period;
predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the energy consumption of the mixer;
calculating the production rate of the mixture according to the shortest mixing period, the bulk density and the filling rate of the mixture; establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the productivity of the mixture;
performing global optimization on the mixing energy efficiency ratio model until a mixing machine control parameter when the energy efficiency ratio is optimal is obtained and is used as an actual control parameter of the mixing machine; the driving speed controller adjusts the rotating speed of the mixing drum motor, the main paddle motor and the auxiliary paddle motor into actual control parameters, and the actual control parameters comprise the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle.
2. The mixing machine control system based on mixing energy efficiency ratio optimization according to claim 1, characterized in that in the step of predicting the energy consumption of the mixing machine according to the shortest mixing period, bulk density, water content, binder ratio and filling rate, and the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle, the energy consumption of the mixing machine is obtained, the method further comprises:
quantifying the bulk density of the mixture, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to the same interval according to a certain shrinkage proportion;
obtaining energy consumption characteristic vectors according to the quantized bulk density of the mixed material, the rotating speed of the mixing drum, the rotating speed of the main paddle, the rotating speed of the auxiliary paddle, the water content, the binder ratio, the filling rate and the shortest mixing period;
and inputting the energy consumption characteristic vector into a pre-established energy consumption prediction model to obtain the energy consumption of the mixer, wherein the energy consumption prediction model comprises a mapping relation between the energy consumption characteristic vector and the energy consumption of the mixer.
3. The optimal mixing machine control system based on the mixing energy efficiency ratio is characterized by further comprising a motor power detection device for connecting the mixing drum rotating motor, the main paddle rotating motor and the auxiliary paddle rotating motor;
the energy consumption prediction model is generated based on neural network model training and is established according to the following steps:
acquiring N groups of independent mixing drum rotating speeds, main paddle rotating speeds, auxiliary paddle rotating speeds, bulk density of mixed materials, water content, binder proportion and filling rate, and corresponding shortest mixing periods, and taking the obtained mixture as the input of N groups of energy consumption training samples;
acquiring mixer energy consumption corresponding to the N groups of energy consumption training samples, and outputting the mixer energy consumption as the N groups of energy consumption training samples;
training a neural network model by using the input of the energy consumption training sample and the output of the energy consumption training sample and adopting a time back propagation method;
continuously updating the weight parameters, the bias parameters and the learning factors of the neural network model through iterative training;
and if the predicted value and the measured value of the neural network model reach the set tolerance range or the neural network model reaches the set maximum iteration number, ending the training, and storing the finally updated weight parameter, bias parameter and learning factor to obtain the energy consumption prediction model.
4. The optimal mixing energy efficiency ratio based mixer control system according to claim 1 wherein the model of the mixing energy efficiency ratio is established by;
the mixing energy efficiency ratio of the mixer can be expressed as follows:
Figure FDA0002642986280000021
wherein y is the mixing energy efficiency ratio, E is the mixer energy consumption, and u is the mix productivity.
5. The optimal mixing machine control system based on mixing energy efficiency ratio according to claim 1, wherein the step of performing global optimization on the model of mixing energy efficiency ratio until obtaining the control parameters of the mixing machine when the energy efficiency ratio is optimal comprises:
setting an N-dimensional feasible solution space of the hybrid energy efficiency ratio model, wherein N is 3 and is respectively the rotating speed of a mixing cylinder, the rotating speed of a main propeller and the rotating speed of an auxiliary propeller;
randomly initializing a particle group with the size of M, and setting an initial particle position, a search speed, an individual extreme value and a group extreme value; the initial particle position is an initial control parameter of the mixer, and the initial control parameter comprises initial values of the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle; the search speed is the initial rate of change of the initial control parameter; the individual extreme value is the mixing energy efficiency ratio of the mixer corresponding to the position of a single particle; the group extreme value is the minimum value in the mixed energy efficiency ratios corresponding to the M particles;
iteratively updating the positions of the particles and the searching speed according to the following mixed energy efficiency ratio model, and calculating an individual extreme value corresponding to each particle, so as to continuously update the individual extreme value and the group extreme value of the mixed energy efficiency ratio model;
Figure FDA0002642986280000022
Figure FDA0002642986280000023
wherein, the initial position of the individual in the population
Figure FDA0002642986280000024
Search speed
Figure FDA0002642986280000025
Individual extremum
Figure FDA0002642986280000026
And group extremum Pn(ii) a n and n +1 represent the current iteration number; i tableShowing the ith particle in the population; c1And C2Is a non-negative constant; w is the inertia factor; a is a constraint factor; n is a radical of1And N2Represents two independent random numbers with the value range of 0,1]；
Figure FDA0002642986280000027
Is the search speed of particle i in the nth iteration,
Figure FDA0002642986280000028
is the current position of particle i in the ith iteration;
and after the optimization of the mixed energy efficiency ratio model is completed, outputting a group extreme value and a particle position corresponding to the group extreme value, wherein the particle position corresponding to the group extreme value is an actual control parameter of the mixer.
6. The mixing machine control system based on the optimal mixing energy efficiency ratio is characterized in that the mixing time is predicted according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of each component, the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle, so that the shortest mixing period is obtained; the following steps are specifically executed:
quantifying the bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle at the same moment to the same interval according to a certain shrinkage proportion;
generating a period prediction sample according to the quantized bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle, the components of the mixture, the proportion of each component, the water content, the binder ratio and the filling rate;
inputting the period prediction sample into a pre-established blending period prediction model, and predicting the shortest blending period, wherein the blending period prediction model comprises a mapping relation between the period prediction sample and the shortest blending period.
7. The optimal mixing energy efficiency ratio based mixer control system according to claim 6, further comprising a mix degree detection mechanism of the mix, wherein the mix degree detection mechanism comprises a sampling device and an off-line detection device; the sampling device is used for acquiring mixture detection samples from different depths of the mixer according to preset time intervals, inputting the mixture detection samples into the off-line detection device, and the off-line detection device is used for measuring the uniformity of the detection samples and obtaining the shortest mixing period according to the obtained uniformity of the mixture at different time intervals;
before the step of inputting the period prediction sample into the pre-established blending period prediction model to obtain the shortest blending period, the method further comprises the following steps:
acquiring a period learning sample which is before the acquisition time point of the period prediction sample and is closest to the period prediction sample, wherein the period learning sample comprises period learning sample input and a shortest blending period measured value corresponding to the period learning sample input;
and updating the blending period prediction model on line by using the period learning sample to obtain an updated blending period prediction model.
8. The mixing machine control system based on mixing energy efficiency ratio optimization according to claim 6, characterized in that the bulk density, the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle at the same moment are quantized to the same interval according to a certain shrinkage proportion, and the following steps are specifically executed:
calculating the ratio of the bulk density to the density of the component with the highest density in the components;
calculating the ratio of the rotating speed of the mixing drum to the maximum rotating speed of the mixing drum;
calculating the ratio of the rotating speed of the main propeller to the maximum rotating speed of the main propeller;
and calculating the ratio of the rotating speed of the auxiliary propeller to the maximum rotating speed of the auxiliary propeller.
9. The optimal mixing energy efficiency ratio based mixer control system according to claim 6, further comprising a mix degree detection mechanism of the mix, wherein the mix degree detection mechanism comprises a sampling device and an off-line detection device; the sampling device is used for acquiring mixture detection samples from different depths of the mixer according to preset time intervals and inputting the mixture detection samples into the off-line detection device, and the off-line detection device is used for measuring the mixing degree of the detection samples at different time intervals to obtain the shortest mixing period;
the blending period prediction model is generated by training a learning machine model and is established according to the following steps:
acquiring N groups of independent mixture parameters and corresponding mixer state parameters, wherein the mixture parameters comprise components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the mixture in a mixing barrel, and the mixer state parameters comprise the rotating speed of the mixing barrel, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle;
taking N groups of independent mixture parameters and corresponding mixer state parameters as the input of N groups of periodic training samples;
according to a preset time interval, obtaining mixture detection samples from different depths of the mixer, performing off-line measurement on the detection samples to obtain the blending degree of the mixture, and obtaining a measured value of the shortest blending period as the output of N groups of period training samples;
training a learning machine model by using the input of the periodic training sample and the output of the periodic training sample and adopting a time back propagation method;
continuously updating the weight parameters, the bias parameters and the learning factors of the learning machine model through iterative training;
and if the predicted value and the measured value of the learning machine model reach the set tolerance range or the learning machine model reaches the set maximum iteration number, finishing the training, and storing the finally updated weight parameter, the offset parameter and the learning factor to obtain the blending period prediction model.
10. A mixer control method based on mixing energy efficiency ratio optimization is characterized by comprising the following steps:
obtaining the filling rate of the mixture sent by the feeding and discharging controller, the components of the mixture sent by the feeding controller, the mixture ratio, the bulk density, the water content and the binder ratio of each component, and the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle sent by the rotating speed controller;
predicting the mixing time according to the components of the mixture, the mixture ratio, the bulk density, the water content, the binder ratio and the filling rate of the components, the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle to obtain the shortest mixing period;
predicting the energy consumption of the mixer according to the shortest mixing period, the bulk density, the water content, the binder ratio and the filling rate, as well as the rotating speed of the mixing drum, the rotating speed of the main paddle and the rotating speed of the auxiliary paddle to obtain the energy consumption of the mixer;
calculating the production rate of the mixture according to the shortest mixing period, the bulk density and the filling rate of the mixture; establishing a mixing energy efficiency ratio model according to the energy consumption of the mixer and the production rate of the mixture;
and carrying out global optimization on the mixing energy efficiency ratio model until a mixing machine control parameter when the energy efficiency ratio is optimal is obtained and is used as an actual control parameter of the mixing machine, wherein the actual control parameter comprises the rotating speed of a mixing drum, the rotating speed of a main paddle and the rotating speed of an auxiliary paddle.
CN202010845710.XA 2020-08-20 2020-08-20 Mixing machine control system and method based on optimal mixing energy efficiency ratio Active CN113289542B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010845710.XA CN113289542B (en) 2020-08-20 2020-08-20 Mixing machine control system and method based on optimal mixing energy efficiency ratio

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010845710.XA CN113289542B (en) 2020-08-20 2020-08-20 Mixing machine control system and method based on optimal mixing energy efficiency ratio

Publications (2)

Publication Number Publication Date
CN113289542A CN113289542A (en) 2021-08-24
CN113289542B true CN113289542B (en) 2022-06-07

Family

ID=77318325

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010845710.XA Active CN113289542B (en) 2020-08-20 2020-08-20 Mixing machine control system and method based on optimal mixing energy efficiency ratio

Country Status (1)

Country Link
CN (1) CN113289542B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116550216B (en) * 2023-07-12 2023-09-15 广东工业大学 Control method and related device for multi-paddle mixing vector control kneader

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0587085A2 (en) * 1992-09-11 1994-03-16 Stefan Klaus Alfred Dr. Ihde Method and device for dosing and mixing multicomponent material
EP0927944A1 (en) * 1997-12-30 1999-07-07 Elf Antar France Method for the production of a product mixture comprising an optimal formulation step
CN102641675A (en) * 2012-04-23 2012-08-22 宁德新能源科技有限公司 Intelligent stirring device
CN108107931A (en) * 2017-12-14 2018-06-01 长安大学 A kind of mixture mixes and stirs method of quality control and system
CN108261976A (en) * 2016-12-30 2018-07-10 中冶长天国际工程有限责任公司 A kind of control method and control system of intensive mixer mixed effect
CN109092206A (en) * 2018-09-25 2018-12-28 常州荣创自动化装备股份有限公司 Based on mobile Internet and the intelligentized fertilizer ratio blending bagging system of cloud service and method
CN110105974A (en) * 2019-06-14 2019-08-09 湖南千盟智能信息技术有限公司 Coke making and coal blending intelligence control system
CN209752721U (en) * 2019-04-08 2019-12-10 辽宁科技大学 Control device of vertical intensive mixer for pellet production

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0587085A2 (en) * 1992-09-11 1994-03-16 Stefan Klaus Alfred Dr. Ihde Method and device for dosing and mixing multicomponent material
EP0927944A1 (en) * 1997-12-30 1999-07-07 Elf Antar France Method for the production of a product mixture comprising an optimal formulation step
CN102641675A (en) * 2012-04-23 2012-08-22 宁德新能源科技有限公司 Intelligent stirring device
CN108261976A (en) * 2016-12-30 2018-07-10 中冶长天国际工程有限责任公司 A kind of control method and control system of intensive mixer mixed effect
CN108107931A (en) * 2017-12-14 2018-06-01 长安大学 A kind of mixture mixes and stirs method of quality control and system
CN109092206A (en) * 2018-09-25 2018-12-28 常州荣创自动化装备股份有限公司 Based on mobile Internet and the intelligentized fertilizer ratio blending bagging system of cloud service and method
CN209752721U (en) * 2019-04-08 2019-12-10 辽宁科技大学 Control device of vertical intensive mixer for pellet production
CN110105974A (en) * 2019-06-14 2019-08-09 湖南千盟智能信息技术有限公司 Coke making and coal blending intelligence control system

Also Published As

Publication number Publication date
CN113289542A (en) 2021-08-24

Similar Documents

Publication Publication Date Title
CN113295000B (en) Material distribution control system and method based on material layer thickness prediction
CN113289542B (en) Mixing machine control system and method based on optimal mixing energy efficiency ratio
WO2022037499A1 (en) Control system and control method for pelletizing machine
CN113289541B (en) Mixer control system and method based on uniformity prediction
CN109190226B (en) Soft measurement method for overflow granularity index of ore grinding system
CN103682498A (en) Charging method and electronic device
CN1408081A (en) System and method for tuning raw mix proportioning controller
CN109603617B (en) Mixed homogenate system and application thereof
CN113299352B (en) Material layer thickness dynamic prediction system and method of sintering trolley
CN108629091A (en) A kind of mill load parameter prediction method based on selectivity fusion multiple channel mechanical signal spectrum multiple features subset
CN113299353A (en) Blending degree prediction method and system of mixing machine
CN100394163C (en) Flexible measuring method for overflow particle size specification of ball mill grinding system
CN108549332A (en) A kind of production status prediction technique based on cobalt acid lithium feed proportioning system
CN115238971A (en) Intelligent brain analysis and processing system for coal preparation plant
CN110697448A (en) Screw material proportioning machine controller based on machine learning
CN110202697B (en) Concrete mixing device and control method thereof
CN113447102A (en) Method for controlling discharge flow of weightless scale
CN113247595A (en) High-precision stable discharging device in lithium battery industry and control method thereof
CN110008566B (en) Filling slurry performance index prediction method based on big data
CN107741695B (en) Machine learning-based control method for direct-falling type material blanking machine
CN109551673A (en) A kind of engineering plastics grinding device and its control method
CN112999959B (en) Method and device for automatically controlling filling rate of vertical mixer
RU2812444C1 (en) System and method for controlling material distribution based on predicting material layer thickness
CN107544252B (en) Machine learning-based direct-falling material blanking machine controller
JPH08278188A (en) Quantitative charging devicee

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