CN108673816B - EPS particulate charge device and its control method - Google Patents

EPS particulate charge device and its control method Download PDF

Info

Publication number
CN108673816B
CN108673816B CN201810467285.8A CN201810467285A CN108673816B CN 108673816 B CN108673816 B CN 108673816B CN 201810467285 A CN201810467285 A CN 201810467285A CN 108673816 B CN108673816 B CN 108673816B
Authority
CN
China
Prior art keywords
case
agitating shaft
eps
discharge
door
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
CN201810467285.8A
Other languages
Chinese (zh)
Other versions
CN108673816A (en
Inventor
王谊
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.)
Hefei Haijing Packaging Product Co Ltd
Original Assignee
Hefei Haijing Packaging Product 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 Hefei Haijing Packaging Product Co Ltd filed Critical Hefei Haijing Packaging Product Co Ltd
Priority to CN201810467285.8A priority Critical patent/CN108673816B/en
Publication of CN108673816A publication Critical patent/CN108673816A/en
Application granted granted Critical
Publication of CN108673816B publication Critical patent/CN108673816B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C44/00—Shaping by internal pressure generated in the material, e.g. swelling or foaming ; Producing porous or cellular expanded plastics articles
    • B29C44/34—Auxiliary operations
    • B29C44/36—Feeding the material to be shaped
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C44/00—Shaping by internal pressure generated in the material, e.g. swelling or foaming ; Producing porous or cellular expanded plastics articles
    • B29C44/34—Auxiliary operations
    • B29C44/3442—Mixing, kneading or conveying the foamable material
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
    • B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
    • B29C44/00—Shaping by internal pressure generated in the material, e.g. swelling or foaming ; Producing porous or cellular expanded plastics articles
    • B29C44/34—Auxiliary operations
    • B29C44/60—Measuring, controlling or regulating
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Mixers Of The Rotary Stirring Type (AREA)

Abstract

The invention discloses EPS particulate charge devices, comprising: cabinet keeps off door with import and discharge gate, and in discharge outlet setting discharge；Case is prestored, the box house is fixed at, and inlet port and outlet port, the feed inlet and the inlet communication is arranged in the case that prestores, discharging gear door is set in the discharge outlet；Agitating shaft extends transversely through setting and prestores inside case described, and one end is rotatably supported on the cabinet and is pierced by the cabinet, and double helix paddle is arranged on the agitating shaft；Motor, input shaft and the stirring axis connection；Wherein, when the agitating shaft rotates clockwise, the EPS particle prestored in case is entered for stirring from the feed inlet；When the agitating shaft rotates counterclockwise, the EPS particle for that will prestore in case is discharged from the discharge port；Batch meter, bottom are arranged discharging and keep off door, and when discharging gear door is opened, the EPS particle can be discharged from discharge port.The invention also discloses the control methods of EPS particulate charge device.

Description

EPS particulate charge device and its control method
Technical field
The present invention relates to polymer material preparation fields, and in particular to EPS particulate charge device and its control method.
Background technique
Polystyrene foam (Expanded Polystyrene abbreviation EPS) is a kind of light polymer, it is Foaming agent is added using polystyrene resin, while heating is softened, and is generated gas, is formed a kind of bubble of rigid closed cell structure Foam plastics.In the prior art, it needs accurately to feed in EPS foaming process, but charging can not be controlled effectively now, and The control method of use is too simple, causes precision low, and error is big, this also influences the quality of product and the economic benefit of enterprise.
Summary of the invention
The present invention has designed and developed EPS particulate charge device, and goal of the invention of the invention is to solve that agitating shaft can be passed through Setting enable to prestore the EPS particle in case and effectively enter in batch meter, and then effectively adjust EPS charging precision.
The present invention has designed and developed the control method of EPS particulate charge device, goal of the invention of the invention first is that passing through The state that the mode of BP neural network controls discharging gear door, discharge gear door and discharging gear door respectively controls EPS charging precision in turn.
Goal of the invention of the invention second is that the initial speed to agitating shaft controls, and then again to EPS particle into Material precision is adjusted.
Technical solution provided by the invention are as follows:
EPS particulate charge device, comprising:
Cabinet with import and discharge gate, and is arranged discharge at the discharge gate and keeps off door；
Case is prestored, the box house is fixed at, and inlet port and outlet port are arranged in the case that prestores, it is described Discharging gear door is arranged in the discharge outlet in feed inlet and the inlet communication；
Agitating shaft extends transversely through setting and prestores inside case described, and one end is rotatably supported at the cabinet The cabinet is gone up and be pierced by, double helix paddle is set on the agitating shaft；
Motor, input shaft and the stirring axis connection；
Wherein, when the agitating shaft rotates clockwise, described prestore in case is entered for stirring from the feed inlet EPS particle；When the agitating shaft rotates counterclockwise, the EPS particle for that will prestore in case is discharged from the discharge port；
Batch meter, bottom are arranged discharging and keep off door, and when discharging gear door is opened, the EPS particle can be from discharging Mouth discharge.
Preferably, described to prestore case the box house is fixedly connected on by connecting rod.
Preferably, further includes:
Temperature sensor, be separately positioned on it is described prestore inside case and the box house, be respectively used to described in monitoring Prestore the temperature inside the box and the case body temperature；
Speed probe is arranged outside the cabinet, for monitoring the agitator shaft speed；
Weight sensor is arranged outside the batch meter, for monitoring the batch meter weight；
Controller keeps off door with the temperature sensor, speed probe, weight sensor, discharge gear door, discharging simultaneously It is connected with discharging gear door.
Preferably, multiple vibrators are set on the bottom of box inner wall；And
Tracheae is set on the batch meter side wall.
The control method of EPS particulate charge device is controlled using the feeding device based on BP neural network, Include the following steps:
Step 1: prestoring the temperature T in case by temperature sensor monitoring according to the sampling period, speed probe monitors The weight M of the revolving speed n of agitating shaft, weight sensor monitoring and metering case；
Step 2: successively the parameter in the step 1 is standardized, the input layer of three layers of BP neural network is determined Vector x={ x1,x2,x3, wherein x1For temperature coefficient, x2For revolving speed coefficient, x3For weight coefficient；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to middle layer, the middle layer vector y={ y1,y2,…,ym}；During m is Interbed node number；
Step 4: obtaining output layer neuron vector o={ o1,o2,o3}；Wherein, o1For the state of discharging gear door, o2For row The state of material gear door, o3The state of door is kept off for discharging, the output layer neuron value isK is output layer neuron sequence Row number, k={ 1,2,3 }, works as okIt is in the open state when being 1, work as okWhen being 0, it is in close state.
Preferably, the middle layer node number m meets:Wherein n is input layer Number, p are output layer node number.
Preferably, in the step 2, temperature T, revolving speed n, weight M carry out specification formula are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter T, n, M, j=1,2,3；XjmaxAnd Xjmin Maximum value and minimum value in respectively corresponding measurement parameter.
Preferably, the excitation function of the middle layer and the output layer is all made of S type function fj(x)=1/ (1+e-x)。
Preferably, the initial speed n of the agitating shaft0For
In formula, ζ is correction coefficient, nmaxFor agitating shaft maximum (top) speed, nminFor agitating shaft minimum speed, L1For agitating shaft away from From prestoring with a distance from bottom portion, L2The distance of box top is prestored for agitating shaft distance, T is the temperature prestored in case, T0For in cabinet Temperature, δ is empirical coefficient, and value is the length that 0.89~1.15, D is paddle, and h is the width of paddle, and M is batch meter Weight, t are monitoring time, and e is the truth of a matter of natural logrithm, and π is pi.
The present invention compared with prior art possessed by the utility model has the advantages that
1, agitating shaft is arranged to prestoring in the present invention in case, when needing to prestoring case and being stirred or be discharged, Neng Goutong It crosses the control to the direction of rotation of agitating shaft and then effectively controls the stirring of EPS particle or the discharge prestored in case；
2, the present invention is carried out by adjusting the state for keeping off door to discharging gear door, discharge gear door and discharging based on BP neural network Control and then control the charging of EPS；
3, the present invention can be configured the initial speed of agitating shaft, and then carry out again to the charging precision of EPS particle It adjusts, improves charging precision again.
Detailed description of the invention
Fig. 1 is structural schematic diagram of the present invention.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text Word can be implemented accordingly.
As shown in Figure 1, the present invention provide EPS particulate charge device, main structure include: cabinet 110, prestore case 120, Batch meter 130, agitating shaft 121 and motor 123；Wherein, cabinet 110 has import and discharge gate, and is arranged at discharge gate Discharge keeps off door 320, prestores case 120 and is fixed inside cabinet 110, and prestores case 120 and feed inlet 111 and discharging is arranged Mouthful, discharging gear door 310 is arranged in discharge outlet in feed inlet 111 and inlet communication, and agitating shaft 121 extends transversely through setting and prestoring Inside case 120, and one end is rotatably supported on cabinet 110 and is pierced by cabinet 110, and double spiral shells are arranged on agitating shaft 121 Paddle is revolved, the input shaft of motor 123 is connect with agitating shaft 121, and is arranged between agitating shaft 121 and motor 123 and is slowed down Motor 122, wherein when agitating shaft 121 rotates clockwise, prestored in case 120 for stirring to enter from feed inlet 111 EPS particle is discharged for that will prestore the EPS particle in case 121 from discharge port, when agitating shaft 121 rotates counterclockwise by stirring The stirring for mixing axis 121 is uniformly mixed different particles, and can control and EPS particle is discharged or is stirred, batch meter 130 Bottom is arranged discharging and keeps off door 330, and when discharging gear door 330 is opened, EPS particle can be discharged from discharge port 160.
In another embodiment, it prestores case 120 and cabinet is fixedly connected on by vertical connecting rod 124 and waling stripe 125 Inside 110.
In another embodiment, feeding device provided by the invention further include: controller 200, temperature sensor 221, 222, speed probe 210 and weight sensor 230；Wherein, the setting of temperature sensor 221 is prestoring inside case 120, for supervising Survey prestores temperature in case 120, and temperature sensor 222 is arranged inside cabinet 110, and for monitoring temperature in cabinet 110, revolving speed is passed Sensor 210 is arranged outside cabinet 110, and for monitoring 121 revolving speed of agitating shaft, weight sensor 230 is arranged outside batch meter 130 Portion is used for 130 weight of monitoring and metering case；Controller 200 simultaneously with temperature sensor 221,222, revolution speed sensing, 210, weight pass Sensor 230, discharge gear door 320, discharging gear door 310 and discharging gear door 330 connect.
In another embodiment, multiple vibrators 140 are set in 110 bottom interior wall of cabinet, when vibrator 140 is opened When, it can be used in all shaking off the EPS particle in cabinet 110 inside batch meter 130,
In another embodiment, tracheae 131 is set on 130 side wall of batch meter, for arranging gas in batch meter 130 Out.
The present invention also provides the control methods of EPS particulate charge device, are controlled using BP neural network, including as follows Step:
Step 1 establishes BP neural network model.
For the BP network architecture that the present invention uses by up of three-layer, first layer is input layer, total n node, corresponding Indicate n monitoring signals of equipment working state, these signal parameters are provided by data preprocessing module.The second layer is hidden layer, Total m node is determined in an adaptive way by the training process of network.Third layer is output layer, total p node, by system Actual needs output in response to determining that.
The mathematical model of the network are as follows:
Input vector: x=(x1,x2,...,xn)T
Middle layer vector: y=(y1,y2,...,ym)T
Output vector: O=(o1,o2,...,op)T
In the present invention, input layer number is n=3, and output layer number of nodes is p=3.Hidden layer number of nodes m is estimated by following formula It obtains:
3 parameters of input signal respectively indicate are as follows: x1For temperature coefficient, x2For revolving speed coefficient, x3For weight coefficient.
Since the data that sensor obtains belong to different physical quantitys, dimension is different.Therefore, people is inputted in data Before artificial neural networks, need to turn to data requirement into the number between 0-1.
Specifically, being advised for using the temperature T in the monitoring region for prestoring the temperature sensor measurement in case After formatting, temperature coefficient x is obtained1:
Wherein, TminAnd TmaxRespectively prestore the minimum temperature and maximum temperature in case.
Likewise, after being standardized, obtaining revolving speed system for the revolving speed n for the agitating shaft for using speed probe to measure Number x2:
Wherein, nminAnd nmaxThe respectively minimum speed and maximum (top) speed of agitating shaft.
Likewise, after being standardized, obtaining weight system for the weight M for the batch meter for using weight sensor to measure Number x3:
Wherein, MminAnd mmaxThe respectively minimum weight and maximum weight of batch meter.
3 parameters of output signal respectively indicate are as follows: output layer vector o={ o1,o2,o3}；o1For the shape of discharging gear door State, o2The state of door, o are kept off for discharge3The state of door is kept off for discharging, the output layer neuron value isK is output layer Neuron sequence number, k={ 1,2,3 }, works as okIt is in the open state when being 1, work as okWhen being 0, it is in close state.
Step 2, the training for carrying out BP neural network.
After establishing BP neural network nodal analysis method, the training of BP neural network can be carried out.It is passed through according to the history of product Test the sample of data acquisition training, and the connection weight w between given input node i and hidden layer node jij, hidden node j and Export the connection weight w between node layer kjk, the threshold θ of hidden node jj, export the threshold θ of node layer kk、wij、wjk、θj、θk It is the random number between -1 to 1.
In the training process, w is constantly correctedijAnd wjkValue, until systematic error be less than or equal to anticipation error when, complete The training process of neural network.
(1) training method
Each subnet is using individually trained method；When training, first have to provide one group of training sample, each of these sample This, to forming, when all reality outputs of network and its consistent ideal output, is shown to train by input sample and ideal output Terminate；Otherwise, by correcting weight, keep the ideal output of network consistent with reality output；
(2) training algorithm
BP network is trained using error back propagation (Backward Propagation) algorithm, and step can be concluded It is as follows:
Step 1: a selected structurally reasonable network, is arranged the initial value of all Node B thresholds and connection weight.
Step 2: making following calculate to each input sample:
(a) forward calculation: to l layers of j unit
In formula,L layers of j unit information weighted sum when being calculated for n-th,For l layers of j units with it is previous Connection weight between the unit i of layer (i.e. l-1 layers),For preceding layer (i.e. l-1 layers, number of nodes nl-1) unit i send Working signal；When i=0, enableFor the threshold value of l layers of j unit.
If the activation primitive of unit j is sigmoid function,
And
If neuron j belongs to the first hidden layer (l=1), have
If neuron j belongs to output layer (l=L), have
And ej(n)=xj(n)-oj(n)；
(b) retrospectively calculate error:
For output unit
To hidden unit
(c) weight is corrected:
η is learning rate.
Step 3: new sample or a new periodic samples are inputted, and until network convergence, the sample in each period in training Input sequence is again randomly ordered.
BP algorithm seeks nonlinear function extreme value using gradient descent method, exists and falls into local minimum and convergence rate is slow etc. Problem.A kind of more efficiently algorithm is Levenberg-Marquardt optimization algorithm, it makes the e-learning time shorter, Network can be effectively inhibited and sink into local minimum.Its weighed value adjusting rate is selected as
Δ ω=(JTJ+μI)-1JTe；
Wherein, J is error to Jacobi (Jacobian) matrix of weight differential, and I is input vector, and e is error vector, Variable μ is the scalar adaptively adjusted, for determining that study is completed according to Newton method or gradient method.
In system design, system model is one merely through the network being initialized, and weight needs basis using The data sample obtained in journey carries out study adjustment, devises the self-learning function of system thus.Specify learning sample and In the case where quantity, system can carry out self study, to constantly improve network performance；
As shown in table 1, given the value of each node in one group of training sample and training process.
Each nodal value of 1 training process of table
Step 3, acquisition sensor operating parameter input neural network obtain the coefficient of regime in feeding device.
Trained artificial neural network is solidificated among chip, hardware circuit is made to have prediction and intelligent decision function Can, to form Intelligent hardware.
BP is obtained by the way that above-mentioned parameter is standardized using temperature sensor, speed probe and weight sensor simultaneously The initial input vector of neural networkInitial output vector is obtained by the operation of BP neural network
Discharging gear door, discharge gear door and the discharging of step 4, monitoring feeding device keep off the state of door to carry out in feeding device The switch-mode regulation of discharging gear door, discharge gear door and discharging gear door.
It is according to output layer neuron valueK is output layer neuron sequence number, k={ 1,2,3 }；Wherein, work as ok It is in the open state when being 1, work as okWhen being 0, it is in close state.
By above-mentioned setting, pass through temperature sensor, speed probe and weight sensor real-time monitoring feeding device Operating status monitors the charging situation of feeding device in real time by using BP neural network algorithm.
In another embodiment, the initial speed n of agitating shaft0For
In formula, ζ is correction coefficient, unit 1/m4, nmaxFor agitating shaft maximum (top) speed, unit r/s, nminFor agitating shaft Minimum speed, unit r/s, L1The distance in bottom portion, unit m, L are prestored for agitating shaft distance2Case is prestored for agitating shaft distance The distance at top, unit m, T are the temperature prestored in case, and unit is DEG C T0For the intracorporal temperature of case, unit is DEG C that δ is warp Coefficient is tested, value is the length that 0.89~1.15, D is paddle, and unit m, h are the width of paddle, and unit m, M are meter Measuring tank weight, unit kg, t are monitoring time, and unit s, e are the truth of a matter of natural logrithm, and π is pi；In this embodiment, δ is empirical coefficient, value 0.93.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited In specific details and legend shown and described herein.

Claims (4)

1. a kind of control method of EPS particulate charge device, which is characterized in that the control method is to be based on using a kind of EPS Grain feeding device is simultaneously controlled based on BP neural network, is specifically comprised the following steps:
Step 1: prestoring the temperature T in case by temperature sensor monitoring according to the sampling period, speed probe monitoring is stirred The weight M of the revolving speed n of axis, weight sensor monitoring and metering case；
Step 2: successively the parameter in the step 1 is standardized, the input layer vector x of three layers of BP neural network is determined ={ x1,x2,x3, wherein x1For temperature coefficient, x2For revolving speed coefficient, x3For weight coefficient；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to middle layer, the middle layer vector y={ y1,y2,…,ym}；M is middle layer Node number；
Step 4: obtaining output layer neuron vector o={ o1,o2,o3}；Wherein, o1For the state of discharging gear door, o2For discharge gear The state of door, o3The state of door is kept off for discharging, the output layer neuron value isK is output layer neuron sequence number, K={ 1,2,3 }, works as okIt is in the open state when being 1, work as okWhen being 0, it is in close state；
Wherein, the initial speed n of the agitating shaft0For
In formula, ζ is correction coefficient, nmaxFor agitating shaft maximum (top) speed, nminFor agitating shaft minimum speed, L1It is pre- for agitating shaft distance Deposit the distance in bottom portion, L2The distance of box top is prestored for agitating shaft distance, T is the temperature prestored in case, T0For the intracorporal temperature of case Degree, δ are empirical coefficient, and value is the length that 0.89~1.15, D is paddle, and h is the width of paddle, and M is batch meter weight Amount, t are monitoring time, and e is the truth of a matter of natural logrithm, and π is pi；
Also, a kind of structure of EPS particulate charge device are as follows: it include: cabinet, with import and discharge gate, and Discharge is set at the discharge gate and keeps off door；Case is prestored, the box house is fixed at, and the case that prestores is arranged Discharging gear door is arranged in the discharge outlet in inlet port and outlet port, the feed inlet and the inlet communication；Agitating shaft, It extends transversely through setting to prestore inside case described, and one end is rotatably supported on the cabinet and is pierced by the cabinet, Double helix paddle is set on the agitating shaft；Motor, input shaft and the stirring axis connection；The agitating shaft is clockwise When rotation, the EPS particle prestored in case is entered for stirring from the feed inlet；The agitating shaft rotates counterclockwise When, the EPS particle for that will prestore in case is discharged from the discharge port；Batch meter, bottom are arranged discharging and keep off door, unload when described When material gear door is opened, the EPS particle can be discharged from discharge port；It is described to prestore case the cabinet is fixedly connected on by connecting rod It is internal；Temperature sensor, be separately positioned on it is described prestore inside case and the box house, be respectively used to prestore described in monitoring The temperature inside the box and the case body temperature；Speed probe is arranged outside the cabinet, turns for monitoring the agitating shaft Speed；Weight sensor is arranged outside the batch meter, for monitoring the batch meter weight；Controller, simultaneously with institute Temperature sensor, speed probe, weight sensor, discharge gear door, discharging gear door is stated to connect with discharging gear door；The cabinet bottom Multiple vibrators are set on portion's inner wall；Tracheae is set on the batch meter side wall.
2. the control method of EPS particulate charge device as described in claim 1, which is characterized in that the middle layer node Number m meets:Wherein n is input layer number, and p is output layer node number.
3. the control method of EPS particulate charge device as described in claim 1, which is characterized in that in the step 2, temperature T, revolving speed n, weight M carry out specification formula are as follows:
Wherein, xjFor the parameter in input layer vector, XjRespectively measurement parameter T, n, M, j=1,2,3；XjmaxAnd XjminRespectively Maximum value and minimum value in corresponding measurement parameter.
4. the control method of EPS particulate charge device as described in claim 1, which is characterized in that the middle layer and described The excitation function of output layer is all made of S type function fj(x)=1/ (1+e-x)。
CN201810467285.8A 2018-05-16 2018-05-16 EPS particulate charge device and its control method Active CN108673816B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810467285.8A CN108673816B (en) 2018-05-16 2018-05-16 EPS particulate charge device and its control method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810467285.8A CN108673816B (en) 2018-05-16 2018-05-16 EPS particulate charge device and its control method

Publications (2)

Publication Number Publication Date
CN108673816A CN108673816A (en) 2018-10-19
CN108673816B true CN108673816B (en) 2019-08-27

Family

ID=63805544

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810467285.8A Active CN108673816B (en) 2018-05-16 2018-05-16 EPS particulate charge device and its control method

Country Status (1)

Country Link
CN (1) CN108673816B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109551673B (en) * 2019-01-24 2021-09-21 江阴市宏丰塑业有限公司 Engineering plastic crushing device and control method thereof

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7004615B2 (en) * 2003-03-24 2006-02-28 Despres Etienne Distributor for dry cement
CN103105777A (en) * 2012-11-14 2013-05-15 山东交通职业学院 Neural network self-adaptation control algorithm applied to tapered double-screw extruder
CN203064688U (en) * 2013-01-29 2013-07-17 谢树海 Spiral mixing and conveying machine
CN106426658A (en) * 2016-08-23 2017-02-22 重庆市盛塑包装制品有限公司 EPS particle auxiliary feeding system
CN106683222A (en) * 2016-12-12 2017-05-17 中国人民解放军装甲兵技术学院 Detection device and detection method for technical performances of engineering vehicle

Also Published As

Publication number Publication date
CN108673816A (en) 2018-10-19

Similar Documents

Publication Publication Date Title
Yuan et al. Prediction of concrete compressive strength: Research on hybrid models genetic based algorithms and ANFIS
CN108932567A (en) A kind of more energy consumption index prediction techniques of cement burning assembly procedure based on convolutional neural networks
CN105699415B (en) The detection method and system of wax deposit in a kind of Simulation of Crude Oil pipe conveying procedure
CN108673816B (en) EPS particulate charge device and its control method
CN112216354A (en) Intelligent dosing system and method based on CFD numerical simulation and machine learning
CN101382801B (en) Optimum soft measuring instrument based on EGA-optimized polymerization of propylene production process and method
CN109190226B (en) Soft measurement method for overflow granularity index of ore grinding system
CN107601083B (en) Straight weight-loss type material baiting method neural network based
CN109165798A (en) A kind of Free Calcium Oxide Contents in Cement Clinker on-line prediction method and system
CN100546791C (en) Asphalt mixture stirring equipment cold aggregate feeding control method
CN109359692A (en) A kind of crude oil water content on-line measurement model and its construction method, application
CN104991037B (en) A kind of data measuring method for cane sugar boiling and crystal and device
CN109062296A (en) A kind of grain storage method based on temperature and humidity monitor
CN109925992A (en) It is a kind of based on multimode stage by stage continuously stir on-line monitoring method
CN103675006B (en) The industrial melt index soft measurement instrument of least square and method
CN105479719B (en) A kind of weightless integral type of weighing squeezes out control system and method
Wang et al. Nonlinear adaptive control of batch styrene polymerization
CN108538301A (en) A kind of intelligent digital musical instrument based on neural network Audiotechnica
CN107330294A (en) The application process of many hidden layer extreme learning machines of online sequential with forgetting factor
CN109551673B (en) Engineering plastic crushing device and control method thereof
CN103675012B (en) The industrial melt index soft measurement instrument of BP particle group optimizing and method
Chadha et al. Optimal dosing of bulk material using mass-flow estimation and DEM simulation
CN107741695A (en) Vertical material blanking machine control method based on machine learning
Mrózek et al. Rough sets in industrial applications
Schwung et al. Actor-critic reinforcement learning for energy optimization in hybrid production environments

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