CN107601064A - Straight weight-loss type material blanking machine and its controller based on neutral net - Google Patents
Straight weight-loss type material blanking machine and its controller based on neutral net Download PDFInfo
- Publication number
- CN107601064A CN107601064A CN201710863074.1A CN201710863074A CN107601064A CN 107601064 A CN107601064 A CN 107601064A CN 201710863074 A CN201710863074 A CN 201710863074A CN 107601064 A CN107601064 A CN 107601064A
- Authority
- CN
- China
- Prior art keywords
- blanking
- mrow
- module
- neutral net
- bin
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G65/00—Loading or unloading
- B65G65/005—Control arrangements
-
- 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
- G06N3/048—Activation functions
-
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2201/00—Indexing codes relating to handling devices, e.g. conveyors, characterised by the type of product or load being conveyed or handled
- B65G2201/04—Bulk
Abstract
The invention discloses straight the weight-loss type material blanking machine and its controller based on neutral net, the blanking machine includes frame, blanking bin and baiting valve, blending bucket, Weighing module, discharge valve, blending bunker and controller；Position in storehouse sensor and agitator are installed in blanking bin, have blender in blending bucket.Neural network module is used in controller, the material position based on blanking bin, blanking rate, material density and baiting valve hatch bore diameter are predicted to material weightless value, so as to which the shut-in time of baiting valve be adjusted.The present invention is modeled using neutral net to the behavior of weighing in blanking, and the network after training can carry out Accurate Prediction to the falling material weightless value under different blanking states, is produced so as to direct accurate blanking and suitable for small lot；The solid accumulation form in blanking bin is detected and adjusted using position in storehouse sensor and agitator, reduces the fluctuation of blanking rate；Further through the control to blanking accumulated error, the overall error of patch blanking is reduced.
Description
Technical field
The present invention relates to Quantitative dosing field, and in particular to a kind of straight weight-loss type material blanking machine based on neutral net
And its controller.
Background technology
In industrial or agricultural manufacture and commodity packaging, there are substantial amounts of powder grain material, such as iron ore concentrate, coal dust iron-smelting raw material, gather
The industrial chemicals such as propylene, polystyrene, polyvinyl chloride, light methylcellulose, polyacrylonitrile, epoxy powder coating, quartz
The corn bean agricultural products such as daily chemical product, millet, soybean such as the building materials raw material such as sand, cement, washing powder, or it is powder, slag, granular
The agricultural production materials such as processed food, feed, chemical fertilizer, agricultural chemicals, and the health products of granular, Chinese and Western medicine, flavouring etc. are equal
Automatic quantitative packing or dispensing is needed to manufacture.
China has many enterprises still to use manual quantitative ingredient or packaging at present, and one side labor intensity is big, speed
Slowly, deficiency in economic performance；On the other hand, food, medicine etc. quantitatively tend not to meet hygienic requirements, poisonous and hazardous thing by hand
Material, artificial participation is quantitative easily to be damaged to human body.Therefore for manufacturing enterprise, being badly in need of providing inexpensive has higher speed
Rate and more the component automatic ration blanking equipments or device of the degree of accuracy, meet substantial amounts of material dosing packaging or dispensing manufacture
It is required that.
Powder grain material automatic quantitative blanking machine common method has two kinds both at home and abroad at present, positive displacement and Weighing type.Volume
Formula quantitative basis material volume is carried out measuring filling or fed intake, and is quantitatively fed intake rapid, but quantitative quality of material is close by material
Degree changes and changed.When Chinese patent such as Application No. 200920248298.2 considers fast blanking it is unmanageable quantitative and
Reduce the influence of feed drop by method first quick and back slow, but its blanking final value can only be not high close to desired value, the degree of accuracy.
Weighing type quantitative basis quality of material is carried out measuring filling or fed intake, and again may be used from different its of Weighing method
It is divided into two kinds of increment type and weight-loss type.To falling on the material in weighing hopper and weighing under constantly, this mode needs increment type
Constantly weighed in blanking process, according to weighing results feedback control discharge quantity, because material continuously falls, work as baiting valve
When door is closed, still there is partial material in the air.In order to compensate interference of the aerial material to measuring accuracy, many schemes, which use, to shift to an earlier date
The technology of valve is closed, as batching weighing process is divided into three ranks by the Chinese patent of Application No. 201410230888.8
Section, and controlled quentity controlled variable is shifted to an earlier date to calculate to close using iterative learning control mode in the last stage.
Compared to increment type, weight-loss type weighting manner measures the weight of falling material by constantly weighing feed bin weight,
The problem of so as to avoid aerial material.Such as Application No. 200710142591.6,201010108011.3 and
201310178558.4 Chinese patent, the calculating that is reduced by weighing cabin weight are measured to falling material, these
Although scheme need not consider air weighting, due to do not consider material from blanking valve fall when weightlessness effect and have impact on and weigh
The precision of metering, it is impossible to meet the requirement of high-precision blanking, and these schemes can only continuously blanking and be not directly applicable
By the blanking of batch.
Compared to conventional weight-loss metering blanking, if can be by influenceing falling material weightlessness equivalence value various factors
Analyze to construct a kind of Nonlinear Mapping, then can be based on this actual discharge quantity mapped to material in weight-loss type weighing process
Measured.
The content of the invention
Traditional Weightlessness balance is by controlling the principle of weight loss to realize metering at work, to drawing mechanism and title
Heavy burder bucket is weighed, and weightlessness is calculated according to the reduction Δ G/ Δs t of weight of material in time per unit in Weightlessness balance weighing hopper
The feed flow of scale.Conventional weightless Weighing method, although obtaining flow by difference method, difference twice it
Between blanking flow rate variation, materials from bonding and environment such as vibrate the influence of factor, can all influence the accurate of difference result
Property.
Analyzed from cutting mode, common weightless Weighing typically uses conveying worm as drawing mechanism, can only
Blanking speed when dynamic regulation is continuously run, and can not directly carry out discontinuous blanking in batches；The title that weight-loss type is weighed
Accuracy of measurement and dispensing speed the two parameters are two conflicting controlled quentity controlled variables, to improve weighing precision, it is desirable to which scale body is more steady
Fixed better, i.e., rate of feeding is more slow better, but certainly will increase the dispensing time, and efficiency is low；, whereas if rate of feeding is too fast, essence
Degree it is difficult to ensure that.
Weighed the advantage without the concern for air weighting in view of weight-loss type, the present invention program is incorporated into blanking in batches
Control in.But because the whereabouts of material non-zero speed in blanking process can impact to Weighing, so that weighing
Reading is different from static weighing.Dynamic impulsion caused by the whereabouts of this material non-zero speed, i.e. falling material weightless value, its shadow
The factor of sound is a lot, such as conveying device closing velocity, material whereabouts form, flow rate, thus obtains static state by dynamic weighing
The conversion plan of weight is difficult to disposably determine by test experiment.
According to the test and analysis that blanking process of being weighed to weight-loss type is deep, sum up straight weight-loss type material blanking machine its
The most important influence factor of falling material weightless value includes：Blanking bin material position, blanking rate, material density and baiting valve open pore
Footpath.Falling material weightless value is the complex nonlinear mapping of these physical quantitys, in order to be predicted simultaneously to falling material weightless value
And then accurate blanking is carried out, it is necessary to recognize and express the mapping relations by the control valve shut-in time.
Linear system can be preferably applied to by system debate the method for knowledge and corrected parameter based on lineary system theory,
But complicated nonlinear system can not be applied to.Artificial neural network is to interconnect the network formed extensively by a large amount of processing units,
With very strong adaptive, self-organizing, self-learning capability, by most attention in system modelling, identification and control, it is had
Some non-linear conversion characteristics provide effective method for the identification of System Discrimination especially nonlinear system.
At present, it is at most Multilayer Feedforward Neural Networks to be applied in nonlinear eddy viscosity model, and Multilayer Feedforward Neural Networks, which have to approach, appoints
The ability of meaning Continuous Nonlinear function, but this network structure is usually static, be can be seen that from material dropping process analysis
Because blanking bin material position gradually changes, therefore, also have tightly between falling material weightless value in continuous two sampling periods
Close contact.Therefore, system is modeled using Dynamical Recurrent Neural Networks in the controller of the present invention.Feedovered with static state
Type neutral net is different, and dynamic recurrent neural network makes it possess the function of mapping behavioral characteristics by storing internal state, so that
System has the ability for adapting to time-varying characteristics, and knowledge is debated more suitable for nonlinear dynamic system.In the present invention program, based on dynamic
Recurrence Elman neutral nets, to falling material weightless value and blanking bin material position h, blanking rate d, material density ρ and baiting valve opening
Mapping relations between the D of aperture are recognized, and carry out detection and dynamic to the material distribution in blanking bin in blanking process
Adjustment so that housebroken neutral net can carry out Accurate Prediction to the falling material weightless value under different conditions, so as to realize
High-precision blanking.
The technical solution of the present invention is to provide a kind of straight weight-loss type material based on neutral net of following structure
Blanking machine, including：Frame, blanking bin, baiting valve, blending bucket, Weighing module, discharge valve, blending bunker and controller；
The baiting valve is located at the bottom opening of blanking bin, and the blanking bin and baiting valve are 2~6 groups,
The blanking bin, which is arranged on, to be fixed on the Weighing module of frame, has a bin level sensor inside it,
The blending bucket below baiting valve, its bottom opening are controlled by discharge valve, and are provided with one on its inwall
Individual blender；
The blending bunker is located at below discharge valve, and a push pedal is arranged at its bottom；
The controller contains the neural network module using Dynamic Recurrent Elman neutral nets, and each baiting valve
Have that neural network module is corresponding, each neural network module is by the material position of corresponding blanking bin, blanking rate, material density
And 4 input quantities of baiting valve hatch bore diameter are mapped as falling material weightless value；Controller is by neural network module to lower junk
Material weightless value is predicted and based on the shut-in time of baiting valve is adjusted after the predicted value amendment discharge quantity；
Controller controls each blanking valve events successively, after a formula ratio blanking is completed, opens discharge valve, is then examining
Accumulation of material in blending bunker is measured to after setting value, opens push pedal, material discharge that will be well mixed.
Preferably, it also includes a storage bin and feed pump, the outlet of feed pump rear end feed pipe has one
Material shower nozzle, the material shower nozzle are spherical, and its surface distributed has circular aperture.
Preferably, the position in storehouse sensor is arranged on a drift angle of the nearly frame central of blanking bin, and its bottom
There is a rotating base.
Preferably, the position in storehouse sensor uses range sensor.
Preferably, the side wall of the blanking bin is also equipped with an agitator, the agitator includes what is be sequentially connected
Base, two support arms, support arm rotating shaft, cleft hand rotating shaft and the cleft hand for connecting two support arms.
Preferably, a mixing level sensor is installed in the side wall of the blending bunker, its internal also one
Material-homogenating device, the material-homogenating device use helical blade, also have a conveying pipeline below the push pedal.
Preferably, the batch mixing base, two batch mixing support arms and connection two that the blender includes being sequentially connected are mixed
Expect batch mixing support arm rotating shaft, the rotating shaft of batch mixing cleft hand and the batch mixing cleft hand of support arm.
Preferably, the blender includes batch mixing rotating shaft, batch mixing rotating disk and helical blade in batch mixing rotating shaft,
And the batch mixing support of support batch mixing rotating shaft.
Preferably, the model of the neutral net is：
xck(t)=xk(t-mod (k, q) -1),
Wherein, mod is MOD function, and f () function is taken as sigmoid functions；xck(t) exported to accept layer, xj(t) it is
Hidden layer exports, ui(t-1) and y (t) is respectively that input layer input and output layer export, ωj、ωjkAnd ωjiRespectively hidden layer
Connection weight to output layer, layer is accepted to the connection weight and input layer of hidden layer to the connection weight of hidden layer, θ and θjPoint
Wei not output layer and hidden layer threshold value；K=1,2...m, q are selected recurrence delay yardstick, according to sampling period and blanking
Speed is preferred, such as optional q=3；J==1,2...m, i=1,2...4, hidden layer and undertaking node layer number m can be 11~20
Between select, preferably such as 16.
Preferably, except the predicted value of falling material weightless value, current accumulation blanking is also included in when correcting discharge quantity
Error.
Another technical solution of the present invention is to provide the straight weight-loss type material blanking machine control based on neutral net
Device, it include signal acquisition module, processing module, neural network module, iterative learning module, memory module, first connection battle array,
Second connection battle array and output module, the signal acquisition module by position in storehouse sensor in blanking bin and carry blanking bin respectively
Weighing module gather in real time blanking bin material position, blanking bin weight transducing signal and be transferred to processing module carry out data processing with
Analysis, memory preserve for data；
The neural network module uses Dynamic Recurrent Elman neutral nets, and its input layer receives from processing module respectively
4 blanking bin material position, blanking rate, material density and baiting valve hatch bore diameter input quantities, the output quantity of output layer pass through respectively
One connection battle array and the second connection battle array are transmitted to iterative learning module and processing module；
Described in off-line training during neutral net, iterative learning module passes through first respectively according to processing module and neutral net
The falling material weightlessness actual value and network output valve of battle array input are connected, adjusts the connection weight of neutral net；
During On-line Control blanking, the first connection battle array disconnects, and neutral net is predicted to falling material weightless value and through the
Two connection battle arrays exports to processing module, by after processing module Treatment Analysis by output module under blanking bin bottom opening
Material valve carries out closing valve control.
Using the present invention program, compared with prior art, there is advantages below：The present invention is using nonlinear network to falling
Relation between material weightless value and its influence factor is modeled, and can predict static weight according to dynamic weighing reading, so as to
Accurate blanking can be realized by adjusting the shut-in time of baiting valve.Compared with traditional Weightlessness balance scheme, this programme can be used for into
The blanking accurate in batches of row material, produced suitable for small lot；Using position in storehouse sensor and agitator to the thing in blanking bin
Material accumulation form is detected and adjusted, and reduces the fluctuation of blanking rate；Also by the control to blanking accumulated error, reduce and criticize
Measure the overall error of blanking.
Brief description of the drawings
Fig. 1 is the composition structure chart of the straight weight-loss type material blanking machine based on neutral net；
Fig. 2 is the straight weight-loss type material blanking machine shape assumption diagram based on neutral net；
Fig. 3 is material whereabouts weightlessness effect schematic diagram；
Fig. 4 is the composition structural representation of controller；
Fig. 5 is Elman neural network structure schematic diagrames；
Fig. 6 is blanking bin bottom partial structural diagram；
Fig. 7 is agitator structure schematic diagram in blanking bin；
Fig. 8 is storage bin and blanking bin partial structural diagram；
Fig. 9 is Flow of Goods and Materials laminar flow schematic diagram in blanking bin；
Figure 10 is more component material distribution schematic diagrams in blending bucket；
Figure 11 is blending bucket structural representation in embodiment 1；
Figure 12 is blending bucket structural representation in embodiment 2.
Wherein：1st, blanking bin 2, baiting valve 3, blending bucket 4, Weighing module 5, discharge valve 6, blending bunker 7, push pedal
8th, conveying pipeline 9, controller 10, storage bin 11, feed pump 12, position in storehouse sensor 13, blender 14, vibrator 15, enter
Point 21, scan line 22, material-homogenating device are pointed in expects pipe 16, material shower nozzle 17, aperture 18, agitator 19, material position face 20, stop
23rd, level sensor is mixed
30th, frame
91st, signal acquisition module 92, processing module 93, neural network module 94, iterative learning module 95, storage mould
Block 96, first connects battle array 97, second and connects battle array 98, output module
101st, buffer pool 102, fimbriatum 103, damper 104, umbrella crown 105, umbrella stand
131st, batch mixing base 132, batch mixing support arm 133, batch mixing support arm rotating shaft 134, batch mixing cleft hand rotating shaft 135, batch mixing
Cleft hand 136, batch mixing support 137, batch mixing rotating shaft 138, batch mixing rotating disk 139, helical blade
181st, base 182, support arm 183, support arm rotating shaft 184, cleft hand rotating shaft 185, cleft hand
301st, arc voussoir
Embodiment
The preferred embodiments of the present invention are described in detail below in conjunction with accompanying drawing, but the present invention is not restricted to these
Embodiment.The present invention covers any replacement made in the spirit and scope of the present invention, modification, equivalent method and scheme.
Thoroughly understand in order that the public has to the present invention, be described in detail in present invention below preferred embodiment specific
Details, and description without these details can also understand the present invention completely for a person skilled in the art.
More specifically description is of the invention by way of example referring to the drawings in the following passage.It should be noted that accompanying drawing is adopted
Non- accurately ratio is used with more simplified form and, only to convenience, lucidly aid in illustrating the embodiment of the present invention
Purpose.
Embodiment 1：
As depicted in figs. 1 and 2, the straight weight-loss type material blanking machine of the invention based on neutral net, it includes blanking bin
1st, baiting valve 2, blending bucket 3, Weighing module 4, discharge valve 5, blending bunker 6 and controller 9, wherein the material of every kind of component has
One group of blanking bin 1 and the correspondence of baiting valve 2, conventional component classification are 2~6 kinds, can also increase component classification as needed.Make
To be preferred, feed bin shape structure that blanking bin 1 is formed from right-angled trapezium and rectangle, baiting valve 2 can use the switch valves such as gate valve or
Other vertical material valves, valve event part are arranged at the outlet at bottom of blanking bin 1.
Framework of the frame 30 as equipment, for fixing and supporting other all parts.Weighing module 4 is fixed on frame 30
On, blanking bin 1 is arranged on Weighing module 4, and opening is arranged at the bottom of blending bucket 3, and the opening of the opening is with closing by discharge valve 5
Control.Blending bucket 4 is located at the bottom of blanking bin 1, and the center of multiple baiting valves 2 is divided with respect to the center of blending bucket 4 in circular arc
Cloth.One blender 13 for being used for more component materials being well mixed is installed on the inwall of blending bucket 4.
Controller 9 uses touching type operation mode, has the formula that man-machine interface can carry out more component materials on its touch-screen
And the setting of other specification, formula includes the gross weight of a blanking and each component accounts for the percentage of the weight.With reference to Fig. 1 and
Shown in Fig. 4, controller 9 is connected by signal acquisition module 91 and output module 98 with each sensor and action component respectively.
Blending bunker 6 is located at the lower section of discharge valve 5, and a push pedal 7 is arranged at its bottom, and a conveying pipeline is connected with below push pedal
8, the mixed material of more components is transported to packaging bag or production equipment by the latter.
Preferably, a mixing level sensor 23 is installed in the side wall of blending bunker 6, its internal also one
Material-homogenating device 22, the material-homogenating device 22 use helical blade.The capacity of blending bunker 6 is some such as 15 times of blending bucket 3, complete
Into after multiple secondary amounts blankings, controller 9 reads the state of mixing level sensor 23, if detecting, the material position of compound exceedes
Given threshold, then control material-homogenating device 22 rotate by compound be again stirring for uniformly after, under the control of controller 9, push pedal 7 is beaten
Open, mixed material exports from conveying pipeline 8.
Fig. 3 illustrates influence of the material weightlessness effect to weighing in material dropping process, and material is with speed v0From baiting valve 2
In fall, baiting valve 2 is carried on Weighing module 4 together with blanking bin 1, and Weighing module 4 measures the matter of material in blanking bin 1
Amount equivalent change can be represented by the formula：
Wherein, Gs is the initial weight of zero moment, and in t, dm is the unit interval blanking quality (g/ of blanking valve outlet
S), v0Initial velocity when being fallen for material, Δ m material leave baiting valve 2 within the Δ t times.
With reference to shown in Fig. 2 and Fig. 3, controller can dynamically read the current reading of Weighing module in real time, but in blanking process
In, the weight of its reading decreasing value read and non-real whereabouts material into blending bucket, but include material whereabouts
Reverse impact acts on.Therefore, the influence of this percussion is deducted when calculating material discharge quantity.It is but how accurate in practice
The equivalent weight value for really obtaining impact is the problem that must be solved.
From formula (1) as can be seen that the quality of material that detects of Weighing module is not only included in the material i.e. formula that actually falls
Section 2, while its also by material non-zero speed fall caused by momentum reverse impact be that Section 3 is influenceed in formula, its
Middle Section 3 is exactly weightlessness effect item.Therefore, the method for weight being directly read in traditional Weightlessness balance can not obtain certain in blanking bin
Determine the actual weight at moment.
In order to obtain the definite quality of material in current time blanking bin, the influence of this weightlessness effect need to be considered, first
Section 3 value is equivalent falling material weightless value in acquisition formula (1).
By carrying out experiment test and analysis repeatedly to weight-loss type blanking process, sum up to straight weight-loss type material blanking
Machine, the most important influence factor of falling material weightless value includes in its blanking process：Blanking bin material position h, blanking rate d, material are close
Spend ρ and baiting valve hatch bore diameter D.Falling material weightless value is the complex nonlinear mapping of these physical quantitys.For Accurate Prediction
Falling material weightless value under different conditions, so as to carry out accurate blanking, it is necessary to recognize this by the control valve shut-in time
Mapping relations.
Complex nonlinear feature based on the mapping, it is also contemplated that in continuous two sampling periods falling material weightless value it
Between it is existing be closely connected, the present invention uses Dynamic Recurrent Elman neural net model establishings, to falling material weightless value and blanking bin
Mapping relations between material position h, blanking rate d, material density ρ and baiting valve hatch bore diameter D are recognized.
As shown in figure 4, the controller in the present invention includes signal acquisition module 91, processing module 92, neural network module
93rd, iterative learning module 94, memory module 95, first connect battle array 96, second and connect battle array 97 and output module 98.Wherein, it is neural
Mixed-media network modules mixed-media 93 uses Elman neutral nets, and memory module 95 is that memory is used for preserving data.
As shown in figure 5, used Elman neutral nets have recursive structure, compared to BP neural network, Elman nerves
Network is in addition to input layer, hidden layer and output layer, in addition to a undertaking layer, accepts the feedback connection that layer is used for interlayer,
So as to express the delay between input and output in time and parameters time-sequence feature so that network is provided with memory work(
Energy.In Fig. 5, the neural network input layer established has 4 units, hidden layer and accept node layer number m can 11~20 it
Between select, such as selection be 16, output layer only has a unit.
The model of the neutral net is：
xck(t)=xk(t-mod (k, q) -1) (2),
Wherein, mod is MOD function, and f () function is taken as sigmoid functions；xck(t) exported to accept layer, xj(t) it is
Hidden layer exports, ui(t-1) and y (t) is respectively that input layer input and output layer export, ωj、ωjkAnd ωjiRespectively hidden layer
Connection weight to output layer, layer is accepted to the connection weight and input layer of hidden layer to the connection weight of hidden layer, θ and θjPoint
Wei not output layer and hidden layer threshold value；K=1,2...m, q are selected recurrence delay yardstick, according to sampling period and blanking
Speed is preferred, such as optional q=3；J==1,2...m, i=1,2...4.
With reference to shown in Fig. 2 and Fig. 4, preferably, the controller 9 in the present invention, can also be by touch screen operation come real
The switching of existing first connection battle array and the second connection battle array, so that controller is operated in off-line training or on-line prediction pattern.
With reference to shown in Fig. 4 and Fig. 5, the neutral net established, input layer includes 4 nodes, wherein material density ρ and under
Material valve hatch bore diameter D is to determine value, and other 2 amounts then need to gather come dynamic realtime by signal acquisition module.By in net
The undertaking node layer that multiple different delayed times return is introduced in network so that network structure more suits with blanking process, so that net
Network training more rapid convergence.
Described in off-line training during neutral net, iterative learning module passes through first respectively according to processing module and neutral net
The falling material weightlessness actual value and network output valve of battle array input are connected, adjusts the connection weight of neutral net.
In order to obtain training sample, after blanking starts, when material is from blanking bin bottom baiting valve to shape blending bucket
During into continuous material flow, continue blanking for a period of time, read Weighing module dynamic weight reading W in real time when closing valve,
Material is waited to read the static weight reading WD of Weighing module after falling, then the whereabouts in the state of the valve moment is closed
Material weightlessness actual value is L=WD-W, and this value is sample output valve y actual value i.e. desired value yd。
Neural metwork training uses gradient descent method, and weights and threshold adjustment methods are as follows in training.
Assuming that a total of P training sample, the error function is made to be：
Then hidden layer is shown below to the adjustment type of output layer connection weight：
ωj(t+1)=ωj(t)+Δωj(t+1) (6),
Wherein,
δy=-(yd- y) y (1-y) (8),
The adjustment type of output layer threshold value is：
θ (t+1)=θ (t)+Δ θ (t+1) (9),
Wherein,
Similarly, input layer is to the adjustment type of hidden layer connection weight：
ωji(t+1)=ωji(t)+Δωji(t+1) (11),
Wherein,
δj=δy·ωj·xj(t)·(1-xj(t)) (13),
The adjustment type of hidden layer threshold value is：
θj(t+1)=θj(t)+Δθj(t+1) (14),
Wherein,
Do not consider xck(t) to connection weight ωjkDependence, accept layer be to the adjustment type of hidden layer connection weight：
ωjk(t+1)=ωjk(t)+Δωjk(t+1) (16),
Wherein,
The initial codomain of each weights is taken as (- 0.1,0.1) section, and learning rate η is the decimal less than 1, can use and fix
Speed exports overall error dynamically to adjust according to current network.
Training termination condition can be set as overall error or its change reaches certain less than a setting value or frequency of training
Amount.
Preferably, in order that obtaining training sample covers more situations, each closing valve moment can be set as from title
Molality block weight readings are the random value after some determination value moment.
Before network training is carried out, pretreatment is normalized to 4 input quantities and 1 output quantity：
R '=r-rmin/rmax-rmin(18),
Wherein, r is undressed physical quantity, and r ' is the physical quantity after normalization, rmaxAnd rminRespectively sample
The maximum and minimum value of data set.
When calculating falling material weightlessness predicted value, network output quantity is converted back falling material weightless value with following formula：
R=rmin+r′·(rmax-rmin) (19)。
During On-line Control blanking, the first connection battle array disconnects, and neutral net is predicted and passed through to falling material weightless value yL
Second connection battle array is exported to processing module, passes through blanking of the output module to blanking bin bottom opening after being handled by processing module
Valve carries out closing valve control：
Assuming that a discharge quantity of current component be Ws, during beginning blanking, controller is by reading the sensing of Weighing module
Value, the initial static weight for obtaining blanking bin is G0；So, controller constantly reads the sensed values of Weighing module, when dynamic weight
When amount reading reaches (G0-Ws-yL), baiting valve is closed.
Preferably, except falling material weightless value predicted value, also drafting error is currently accumulated to this component material and enter
Row compensation, i.e., when detecting that blanking bin dynamic weight reading reaches (G0-Ws-yL+E), baiting valve is closed, wherein E is this group
The current accumulation drafting error of part, and E is that timing represents that blanking is excessive.
Signal acquisition module is respectively by the Weighing module of position in storehouse sensor, carrying blanking bin in blanking bin come real-time respectively
Collection blanking bin material position, falling material weight transducing signal and be transferred to processing module and carry out data prediction, input afterwards
It is sent to neutral net, neutral net output valve with the desired output through processing module pretreatment by the first connection battle array
Iterative learning module, the weights after adjustment are returned to by neutral net according to gradient descent method by iterative learning module.
The position in storehouse sensor uses range sensor, the controlling level of material in blanking bin is detected, by periodically
Constantly collection Weighing module signal, processing module can calculate material falling mass equivalent i.e. blanking rate in the unit interval.
With reference to shown in Fig. 2 and Fig. 6, preferably, influence to weighing is acted in order to reduce baiting valve 2, at blanking bin bottom
Portion sets a buffer pool 101, and it includes damper 103, fimbriatum 102.Damper 103 can be reduced using the segmentation that is flexible coupling
Baiting valve 2 is delivered to the vibration of Weighing module when acting.Fimbriatum 102 is again including umbrella crown 104 and the umbrella stand 105 for supporting umbrella crown.
It can also be analyzed from formula (1), falling material weightless value is closely related with blanking situation, and it is by blanking bin 1
The influence of middle material fractions distribution.
Particulate matter mainly has bulk flow and center stream two types from blanking bin outflow form under gravity.It is overall
Whole stratum granulosum can substantially evenly flow out in feed bin in the flow problem of stream, and substantially each particle is moving；
And then some particles are static in the flow problem of center stream, a flow channel side be present between flowing and static particle
Boundary.The Whole blanking speed ratio center stream of bulk flow is big, and the fluctuation of blanking speed is smaller, flowing is stable.In actual production
During, material in blanking bin is it is possible that the flow problem of center stream so that when material mouth starts discharging, by institute is pressed in storehouse
It is caused to be compacted stress and cause material solid into plate.
With reference to shown in Fig. 6~8, preferably, in order to reduce the fluctuating range of blanking rate in blanking bin, so as to preferably enter
Row falling material weightless value is predicted, using Distance-sensing type position in storehouse sensor and mechanical hand agitator to blanking in blanking machine
Solid accumulation form in storehouse is detected and adjusted so that the formation of dynamic material arch is alternately present above feed opening with caving in,
Ensure blanking form for stable bulk flow pattern.
As shown in figure 8, blanking bin 1 constantly discharges, when material position is reduced to certain value in storehouse, it is necessary to carry out feed supplement to it.
Therefore, setting a storage bin 10 above blanking bin 1, the material in storage bin 10 is entered by feed pump 11 and feed pipe 15
Blanking bin 1.To cause the uniform blanking of material particles, a material shower nozzle 16, material are provided with the end outlet of feed pipe 15
The surface of shower nozzle 16 is spherical, and its surface distributed has circular aperture 17, and small aperture carries out preferred according to the granularity of material.Charging
Pump 11 uses screw rod conveyor, and its action is controlled by controller.In the blanking process of blanking bin 1, with material position face 19
Reduce, feed pump 11 is acted under the control of the controller so that the material position of material top surface is maintained near preset value in blanking bin.
Two figures are as shown in figs. 8 a and 8b, near in blanking bin 1 respectively from the side view of blanking bin 1 and overlook direction in Fig. 8
Position in storehouse sensor 12 is installed on one drift angle of frame central, it has a Rotatable base to carry out pitching and rotation, makes
Material detection can be carried out on the different directions for stopping sensing point 20 by obtaining position in storehouse sensor, and it is close same respectively to stop the composition of sensing point 20
The scan line 21 of heart circle, so as to judge the distribution in material position face 19.
As shown in fig. 7, a controller agitator 18 being installed by blanking machine in the side wall of blanking bin 1 improves material
Distribution.Agitator 18 includes 181, two support arms 182 of base, the support arm rotating shaft 183 of two support arms of connection, the pawl being sequentially connected
Hand rotating shaft 184 and cleft hand 185, its center base 181 also contain a rotary shaft.
With reference to shown in Fig. 7 and Fig. 6, the fimbriatum in the buffer pool of blanking bin bottom, top storehouse pressure can be undertaken, weakens discharging opening
The effect of neighbouring larger compaction force, the storehouse pressure below umbrella crown is substantially reduced, while a ring-type stream mouth is formed on its periphery,
So that material tends to overall flow form in storehouse, it can further prevent the knot of material from encircleing to block.
In blanking process, controller is sentenced by the detection of position in storehouse sensor and the tracking to unit interval blanking rate respectively
The distribution of material in disconnected blanking bin so that the material position face in blanking bin keeps near parabolic face shape.With reference to shown in Fig. 8~9, when
When material is uniformly distributed, material distance value that position in storehouse sensor is detected in different azimuth is several through ray and vertical direction inclination angle
What is approximately centered in a less scope after converting.When hardened or stable material arch locally occurs for material, detect
Distance value exceeds this scope.Meanwhile real-time tracking is carried out by blanking speed of the Weighing module to each blanking bin.Work as Distance-sensing
After device detects above-mentioned abnormality or finds that the fluctuation of unit interval discharge quantity exceedes given threshold such as 5%, control order
Agitator is acted, and by the rotation of rotating shaft, its cleft hand is spinned from the off through material position high point region to material position low spot region
Shape is overturn, and so as to abolish the hardened or material arch formed once in a while, material is recovered flowing, is kept the laminar flow regime of bulk flow.
As shown in figure 9, the present invention is coordinated by the detection of range sensor and agitator with action, significantly reduce
Compaction force effect, effectively prevent the size segregation of material in storehouse, makes the material in the magazine of bottom caused by charging impact
Activation, improves the flowing of material.In continuous charging and blanking process, all particles are all flowing in an orderly manner, with
The outflow of storehouse endoparticle, the laminar flow regime of bulk flow is presented in particle swarm.
Figure 10 supplements the record of more component material blanking process, wherein when showing 4 kinds of component blankings in blending bucket
Material distribution schematic diagram.
With reference to shown in Fig. 2 and Figure 11, after blending bucket 3 are fallen under more component materials, the blender action in blending bucket 3,
Material is mixed.As shown in figure 11, blender 13 include 131, two batch mixing support arms 132 of batch mixing base for being sequentially connected and
Connect batch mixing support arm rotating shaft 133, batch mixing cleft hand rotating shaft 134 and the batch mixing cleft hand 135 of two batch mixing support arms 132, wherein batch mixing bottom
Seat 131 also contains a rotary shaft.
There is an arc voussoir 301 on the inside of the bottom of retractable component at the bottom opening of blending bunker 3, batch mixing cleft hand 135 is adopted
With the flexible material of semi-rigid.In the presence of controller, the batch mixing cleft hand 135 of blender 13 from the left of blending bucket through bottom side to
Right side, arrives height again from high to low, shape of spinning repeatedly upset, mixes more component materials.In the non-opening side of blending bucket
Outside, also a vibrator 14, controller also controls the starting of oscillation of vibrator 14 while blender 13 acts, in blending bucket
More component materials fully can be mixed uniformly in the presence of blender 13 and vibrator 14.
Blanking is carried out using blanking machine of the present invention, the first blanking behavior offline to each baiting valve is modeled respectively, is gathered
The blanking per component material is individually carried out during sample, is wasted so as to reclaim all materials without causing.It is actual
Blanking bin material position and blanking rate are periodically gathered during blanking, current falling material weightless value can be forecast in real time, thus from
First batch starts, and other are avoided such as the drafting error fluctuation in online iterative learning scheme with regard to the accurate blanking of energy.
Embodiment 2：
With reference to shown in Fig. 2 and Figure 12, after blending bucket 3 are fallen under more component materials, the blender action in blending bucket 3,
Material is mixed.As shown in figure 12, blender 13 includes being fixed on batch mixing rotating shaft 137 in blending bucket, installed in batch mixing rotating shaft
Batch mixing rotating disk 138 and helical blade 139 on 137, the batch mixing support 136 being fixed on the inwall of blending bucket 3 are used for supporting batch mixing
Rotating shaft 137.Batch mixing rotating disk 138 is similar to the ring-type of water wheeler, and it is in substantially vertical rectangular paddle to have on its outer shroud with circumference, blade
On can perforate.Helical blade 139 uses irregular spiral vane, and hole is distributed on blade.
There is an arc voussoir 301 on the inside of the bottom of retractable component at the bottom opening of blending bunker 3, in the effect of controller
Under, the batch mixing rotating shaft 137 of blender 13 is rotated, and its internal rectangular paddle is overturn together with helical blade 139 to material.
In the outside of the non-opening side of blending bucket, an also vibrator 14, controller while blender 13 acts
The starting of oscillation of vibrator 14 is also controlled, more component materials in blending bucket are in the presence of blender 13 and vibrator 14, by fully
Uniformly mixing.
Embodiment 3：
With reference to shown in Fig. 2, to carry out weight-loss metering to blanking bin 1, two horizontal supports can be drawn from blanking bin lateral wall
Portion；Weighing module is horizontal positioned, and Weighing module supports blanking bin in vertical direction from both sides.Or draw from the top of blanking bin 1
Go out two suspention portions, Weighing module is horizontal positioned, and Weighing module supports blanking bin in vertical direction from both sides.
Embodiments described above, the restriction to the technical scheme protection domain is not formed.It is any in above-mentioned implementation
Modifications, equivalent substitutions and improvements made within the spirit and principle of mode etc., should be included in the protection model of the technical scheme
Within enclosing.
Claims (10)
1. the straight weight-loss type material blanking machine based on neutral net, it includes frame, blanking bin, baiting valve, blending bucket, weighed
Module, discharge valve, blending bunker and controller；
The baiting valve is located at the bottom opening of blanking bin, and the blanking bin and baiting valve are 2~6 groups,
The blanking bin, which is arranged on, to be fixed on the Weighing module of frame, has a bin level sensor inside it,
The blending bucket below baiting valve, its bottom opening are controlled by discharge valve, and one is provided with its inwall and is mixed
Glassware；The blending bunker is located at below discharge valve, and a push pedal is arranged at its bottom；
The controller contains the neural network module using Dynamic Recurrent Elman neutral nets, and each baiting valve has
One neural network module is corresponding, each neural network module by the material position of corresponding blanking bin, blanking rate, material density and under
Material valve 4 input quantities of hatch bore diameter are mapped as falling material weightless value；Controller is lost by neural network module to falling material
Weight values are predicted and based on the shut-in time of baiting valve are adjusted after the predicted value amendment discharge quantity；
Controller controls each blanking valve events successively, after a formula ratio blanking is completed, opens discharge valve, is then detecting
Accumulation of material in blending bunker opens push pedal to after setting value, material discharge that will be well mixed.
2. the straight weight-loss type material blanking machine according to claim 1 based on neutral net, it is characterised in that：It is also wrapped
A storage bin and feed pump are included, there is a material shower nozzle outlet of feed pump rear end feed pipe, and the material shower nozzle is
Spherical, its surface distributed has circular aperture.
3. the straight weight-loss type material blanking machine according to claim 1 based on neutral net, it is characterised in that：The storehouse
Level sensor is arranged on a drift angle of the nearly frame central of blanking bin, and a rotating base is arranged at its bottom.
4. the straight weight-loss type material blanking machine according to claim 1 based on neutral net, it is characterised in that：Under described
The side wall of feed bin is also equipped with an agitator, and the agitator includes two base, two support arms, connection branch being sequentially connected
Support arm rotating shaft, cleft hand rotating shaft and the cleft hand of arm.
5. the straight weight-loss type material blanking machine according to claim 1 based on neutral net, it is characterised in that：It is described mixed
Close and a mixing level sensor is installed in the side wall of feed bin, its internal also a material-homogenating device, described material-homogenating device use spiral shell
Shape blade is revolved, also has a conveying pipeline below the push pedal.
6. the straight weight-loss type material blanking machine according to claim 1 based on neutral net, it is characterised in that：It is described mixed
Batch mixing base that glassware includes being sequentially connected, two batch mixing support arms and the batch mixing support arm rotating shaft, mixed for connecting two batch mixing support arms
Expect cleft hand rotating shaft and batch mixing cleft hand.
7. the straight weight-loss type material blanking machine according to claim 1 based on neutral net, it is characterised in that：It is described mixed
Glassware includes batch mixing rotating shaft, batch mixing rotating disk and helical blade in batch mixing rotating shaft, and the batch mixing of support batch mixing rotating shaft
Support.
8. the straight weight-loss type material blanking machine based on neutral net according to claim 1~7 any one, its feature
It is, the model of the neutral net is：
xck(t)=xk(t-mod (k, q) -1),
<mrow>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>f</mi>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>&omega;</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mi>xc</mi>
<mi>k</mi>
</msub>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>5</mn>
</munderover>
<msub>
<mi>&omega;</mi>
<mrow>
<mi>j</mi>
<mi>i</mi>
</mrow>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mi>u</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>&theta;</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
<mo>,</mo>
</mrow>
<mrow>
<mi>y</mi>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>f</mi>
<mrow>
<mo>(</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>&omega;</mi>
<mi>j</mi>
</msub>
<mo>&CenterDot;</mo>
<msub>
<mi>x</mi>
<mi>j</mi>
</msub>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<mi>&theta;</mi>
<mo>)</mo>
<mo>,</mo>
</mrow>
Wherein, mod is MOD function, and f () function is taken as sigmoid functions；xck(t) exported to accept layer, xj(t) it is implicit
Layer output, ui(t-1) and y (t) is respectively that input layer input and output layer export, ωj、ωjkAnd ωjiRespectively hidden layer is to defeated
Go out the connection weight of layer, the connection weight of undertaking layer to hidden layer and input layer to the connection weight of hidden layer, θ and θjRespectively
Output layer and hidden layer threshold value；K=1,2...m, q are selected recurrence delay yardstick, according to sampling period and blanking speed
It is preferred that such as optional q=3；J==1,2...m, i=1,2...4, hidden layer and undertaking node layer number m can be between 11~20
Selection, preferably such as 16.
9. the straight weight-loss type material blanking machine according to claim 1 based on neutral net, it is characterised in that：Except under
The predicted value of junk material weightless value, current accumulation drafting error is also included in when correcting discharge quantity.
10. the straight weight-loss type material blanking machine controller based on neutral net, it include signal acquisition module, processing module,
Neural network module, iterative learning module, memory module, the first connection battle array, the second connection battle array and output module, the signal are adopted
Collection module gathers blanking bin material position, blanking in real time by the Weighing module of position in storehouse sensor in blanking bin and carrying blanking bin respectively
The transducing signal of storehouse weight is simultaneously transferred to processing module progress data process＆analysis, and memory preserves for data；
The neural network module uses Dynamic Recurrent Elman neutral nets, and its input layer receives blanking from processing module respectively
4 storehouse material position, blanking rate, material density and baiting valve hatch bore diameter input quantities, the output quantity of output layer connect by first respectively
Connect battle array and the second connection battle array is transmitted to iterative learning module and processing module；
Described in off-line training during neutral net, iterative learning module passes through the first connection respectively according to processing module and neutral net
The falling material weightlessness actual value and network output valve of battle array input, adjust the connection weight of neutral net；
During On-line Control blanking, the first connection battle array disconnects, and neutral net is predicted to falling material weightless value and connected through second
Connect battle array to export to processing module, by the baiting valve after processing module Treatment Analysis by output module to blanking bin bottom opening
Carry out closing valve control.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910836277.0A CN110697438B (en) | 2017-09-19 | 2017-09-19 | Controller of direct falling weight loss type material blanking machine based on neural network |
| CN201710863074.1A CN107601064B (en) | 2017-09-19 | 2017-09-19 | Straight weight-loss type material blanking machine and its controller neural network based |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710863074.1A CN107601064B (en) | 2017-09-19 | 2017-09-19 | Straight weight-loss type material blanking machine and its controller neural network based |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910836277.0A Division CN110697438B (en) | 2017-09-19 | 2017-09-19 | Controller of direct falling weight loss type material blanking machine based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107601064A true CN107601064A (en) | 2018-01-19 |
| CN107601064B CN107601064B (en) | 2019-09-24 |
Family
ID=61060399
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910836277.0A Active CN110697438B (en) | 2017-09-19 | 2017-09-19 | Controller of direct falling weight loss type material blanking machine based on neural network |
| CN201710863074.1A Active CN107601064B (en) | 2017-09-19 | 2017-09-19 | Straight weight-loss type material blanking machine and its controller neural network based |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910836277.0A Active CN110697438B (en) | 2017-09-19 | 2017-09-19 | Controller of direct falling weight loss type material blanking machine based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN110697438B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110577091A (en) * | 2019-04-03 | 2019-12-17 | 上海宝信软件股份有限公司 | method, system and medium for stabilizing quality of blended ore based on artificial intelligence |
| CN110615293A (en) * | 2018-06-19 | 2019-12-27 | 佛山市顺德区美的电热电器制造有限公司 | Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115321209B (en) * | 2022-09-15 | 2023-12-22 | 中煤科工智能储装技术有限公司 | Chute height control method based on machine learning |
| CN115879247B (en) * | 2023-03-02 | 2023-06-30 | 中国航发四川燃气涡轮研究院 | Wheel disc key part stress calculation method based on system identification |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2505920Y (en) * | 2001-11-14 | 2002-08-14 | 西安交通大学 | Network intelligent dosing controller |
| CN101271016A (en) * | 2008-05-15 | 2008-09-24 | 山西万立科技有限公司 | Dynamic weighing method and weighing system based on velocity compensation |
| CN102636245A (en) * | 2012-04-23 | 2012-08-15 | 中联重科股份有限公司 | Material weighing and measuring method, device and system |
| CN105734703A (en) * | 2016-02-26 | 2016-07-06 | 常州灵达特种纤维有限公司 | Loss-in-weight batching system |
| KR101680055B1 (en) * | 2015-08-27 | 2016-11-29 | 서울대학교산학협력단 | Method for developing the artificial neural network model using a conjunctive clustering method and an ensemble modeling technique |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS574829A (en) * | 1980-06-09 | 1982-01-11 | Iseki & Co Ltd | Grain charge hopper in grain regulating and processing device |
| JPS6357433A (en) * | 1986-08-25 | 1988-03-12 | Sumitomo Heavy Ind Ltd | Device for compacting and supplying coal in coal charging vehicle |
| DE19919206A1 (en) * | 1999-04-28 | 2000-11-02 | Buehler Ag | Process for the production of pasta |
| CN2589427Y (en) * | 2002-11-10 | 2003-12-03 | 吕荣兴 | Even discharge leaf wheel loader |
| DE102004020790A1 (en) * | 2004-04-28 | 2005-11-24 | Maschinenfabrik Gustav Eirich Gmbh & Co. Kg | Process and apparatus for the continuous controlled discharge of solids |
| CN101226377B (en) * | 2008-02-04 | 2010-11-24 | 南京理工大学 | Robust control method for asphalt mixing plant batching error |
-
2017
- 2017-09-19 CN CN201910836277.0A patent/CN110697438B/en active Active
- 2017-09-19 CN CN201710863074.1A patent/CN107601064B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2505920Y (en) * | 2001-11-14 | 2002-08-14 | 西安交通大学 | Network intelligent dosing controller |
| CN101271016A (en) * | 2008-05-15 | 2008-09-24 | 山西万立科技有限公司 | Dynamic weighing method and weighing system based on velocity compensation |
| CN102636245A (en) * | 2012-04-23 | 2012-08-15 | 中联重科股份有限公司 | Material weighing and measuring method, device and system |
| KR101680055B1 (en) * | 2015-08-27 | 2016-11-29 | 서울대학교산학협력단 | Method for developing the artificial neural network model using a conjunctive clustering method and an ensemble modeling technique |
| CN105734703A (en) * | 2016-02-26 | 2016-07-06 | 常州灵达特种纤维有限公司 | Loss-in-weight batching system |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110615293A (en) * | 2018-06-19 | 2019-12-27 | 佛山市顺德区美的电热电器制造有限公司 | Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system |
| CN110615293B (en) * | 2018-06-19 | 2021-09-14 | 佛山市顺德区美的电热电器制造有限公司 | Automatic image data acquisition system, automatic image data acquisition method and automatic image data identification system |
| CN110577091A (en) * | 2019-04-03 | 2019-12-17 | 上海宝信软件股份有限公司 | method, system and medium for stabilizing quality of blended ore based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107601064B (en) | 2019-09-24 |
| CN110697438A (en) | 2020-01-17 |
| CN110697438B (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107601083B (en) | Straight weight-loss type material baiting method neural network based | |
| CN107720311B (en) | Screw rod weight-loss type material blanking machine and its controller neural network based | |
| CN107640609B (en) | Screw proportioning materials machine controller based on machine learning | |
| CN107673083B (en) | Screw material blanking device and its controller based on variable Rate study | |
| CN107601064B (en) | Straight weight-loss type material blanking machine and its controller neural network based | |
| CN107684846B (en) | Vertical multiple groups part material baiting method | |
| CN107715727B (en) | Screw multiple groups part proportioning materials device and its controller | |
| CN107512597B (en) | Screw multiple groups part material baiting method based on variable Rate study | |
| CN107694469B (en) | Vertical multiple groups part proportioning materials method based on variable Rate study | |
| CN107572016A (en) | The more component material blanking devices of vertical and its controller | |
| CN107661728B (en) | Vertical proportioning materials device and its controller based on variable Rate study | |
| CN107697660B (en) | Screw material disperser control method based on machine learning | |
| CN107684847B (en) | Screw multiple groups part proportioning materials method | |
| CN108002062B (en) | Screw rod weight-loss type material baiting method neural network based | |
| CN204137341U (en) | A kind of rotating disc type many scales gauging device | |
| CN105600500B (en) | A kind of automatic weight calculation drawing-in device | |
| CN107741695A (en) | Vertical material blanking machine control method based on machine learning | |
| CN203227462U (en) | Dosing mixing unit | |
| CN107544252A (en) | Vertical material blanking machine controller based on machine learning | |
| CN103587737B (en) | A kind of high-speed quantitative packing scale | |
| CN104340386B (en) | A kind of rotating disc type many scales metering device | |
| CN205893871U (en) | Intelligence heat -transmission is gathered materials and is saved measurement system | |
| CN203638124U (en) | High-speed quantitative packing balance |
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 |