CN110697448B

CN110697448B - Screw material proportioning machine controller based on machine learning

Info

Publication number: CN110697448B
Application number: CN201910845720.0A
Authority: CN
Inventors: 邹细勇; 朱力; 穆成银
Original assignee: China Jiliang University
Current assignee: China Jiliang University
Priority date: 2017-09-19
Filing date: 2017-09-19
Publication date: 2021-07-02
Anticipated expiration: 2037-09-19
Also published as: CN107640609B; CN110697448A; CN107640609A

Abstract

The invention discloses a screw type material proportioning machine controller based on machine learning, which comprises a signal acquisition module, a processing module, a neural network module, an iterative learning module, a storage module and an output module, wherein the signal acquisition module is used for acquiring a signal; the dynamic recursive Elman neural network is adopted to map the material level of the blanking bin, the air fall, the blanking rate, the material density, the diameter of the helical blade of the screw conveyor, the screw pitch and the maximum rotating speed of the screw to the material air quantity, the iterative learning module adjusts the weight according to the gradient descent method in the off-line training, and the processing module performs the advanced closing control on the screw conveyor through the output module according to the predicted value of the air quantity in the on-line control blanking process. The invention adopts the nonlinear network to model the blanking process, and the trained network can accurately predict the empty space amount under different blanking states, thereby directly and accurately blanking, being suitable for small-batch production, and improving the blanking efficiency because the screw can keep high running speed.

Description

Screw material proportioning machine controller based on machine learning

The application is a divisional application with application number 201710905606.3, application date 2017, 09 and 19 and invention name 'screw material dosing machine controller based on machine learning'.

Technical Field

The invention relates to the field of quantitative blanking, in particular to a screw type material proportioning machine controller based on machine learning.

Background

In industrial and agricultural manufacturing and commodity packaging, a large amount of powder materials, such as iron-making raw materials including coal powder, chemical raw materials including polypropylene, polystyrene, polyvinyl chloride, light methyl cellulose, polyacrylonitrile, epoxy resin powder coating and the like, building material raw materials including quartz sand, cement and the like, daily chemical products including washing powder and the like, grain and bean agricultural products including millet, soybean and the like, or agricultural production materials including powder, slag and granular processed food, feed, chemical fertilizer, pesticide and the like, and granular health care products, Chinese and western medicaments, seasonings and the like need to be automatically quantitatively packaged or prepared by proportioning.

At present, many enterprises in China still adopt manual quantitative batching or packaging, so that on one hand, the labor intensity is high, the speed is low, and the economic benefit is poor; on the other hand, manual quantification of food, medicine and the like often cannot meet the sanitary requirements, toxic and harmful materials are used, and manual quantification is easy to cause harm to human bodies. Therefore, for the manufacturing enterprises, it is urgently needed to provide a cheap multi-component automatic quantitative blanking device or device with higher speed and accuracy, so as to meet the requirements of quantitative packaging of a large amount of materials or manufacturing of ingredients.

At present, two common methods, namely a positive displacement type and a weighing type, are adopted for automatic quantitative powder material feeding devices at home and abroad. The volumetric quantification is used for metering filling or feeding according to the volume of the material, the quantitative feeding is rapid, but the quality of the quantified material is changed by the change of the density of the material. In order to improve the blanking precision, various adjusting methods are provided, for example, in the chinese patent with application number 201320001933.3, the variable frequency speed regulation is adopted for the screw, the feeding speed is gradually reduced when the target value is approached, and the air drop value is reduced; in the Chinese patent with the application number of 201310234280.8, a large screw and a small screw are adopted in a three-speed variable-frequency feeding process of a soda packing machine for feeding materials in multiple stages; the Chinese patent with the application number of 200920248298.2 reduces the influence of the fall of the feeding by a method of first quick and then slow considering that the quantitative control is difficult to control when the fast feeding is carried out; the final blanking value of the non-weighing schemes can only be close to the expected value, and the accuracy is not high.

The weighing type quantitative material feeding device is used for metering, filling or feeding according to the mass of a material, the material needs to be weighed continuously in the feeding process, the feeding amount is controlled in a feedback mode according to the weighing result, and due to the fact that the weighing is greatly influenced by feeding impact and air lag materials, the feeding speed and the feeding precision face a lot of difficulties. In order to compensate the interference of the materials in the air to the metering precision, a technology of closing a valve in advance is adopted in many schemes, for example, the Chinese patent with the application number of 201410230888.8 divides the ingredient weighing process into three stages, and an iterative learning control mode is adopted in the last stage to calculate the closing advance control quantity.

Compared with indirect linear iterative prediction in iterative learning control, if a nonlinear mapping can be constructed by analyzing factors influencing the material empty blanking amount in the blanking process, the blanking process can be described more intuitively, and the material empty blanking amount can be accurately and directly predicted based on the mapping.

Disclosure of Invention

The simple screw feeder belongs to the volumetric quantitative category, the volumetric quantitative filling measures the quantity of filling materials based on the volume, the structure is simple, the cost is low, but the stability and the precision of the quantitative filling speed depend on the stability of the materials according to the specific gravity, and the influence of physicochemical properties such as the loose degree of the materials, the uniform degree of particles, the hygroscopicity and the like is large. Since the ordinary positive displacement type is conversion type in nature and cannot grasp the exact quality of the blanking like a weighing type, although a scheme combining weighing is provided later, the precision can be ensured only by depending on the extremely low feeding speed at the final stage of the blanking because no empty space amount prediction exists.

Therefore, the invention combines dynamic weighing detection with a screw feeder to improve the feeding speed. However, in the case of the gravimetric feeding, the amount of air and its impact need to be estimated. The empty blanking amount in the blanking process is the empty amount, and the influence factors are many, such as the closing speed of the conveying device, the fall between the blanking port and the material surface of the scale bucket, the falling form flow rate of the material and the like, so that the time for closing the blanking conveying device in advance is difficult to determine at one time through an off-line experiment.

According to deep test and analysis of the blanking process, the most main influence factors of the air-to-air quantity of the screw type material batching machine are found to comprise: the material level of the discharging bin, the air drop, the discharging rate, the material density, the diameter of a helical blade of the helical conveyor, the pitch and the maximum rotating speed of a screw. The empty space is a complex non-linear mapping of these physical quantities, and in order to predict the empty space and then accurately feed by closing the screw conveyor in advance, the mapping relationship needs to be identified and expressed.

The method for identifying and correcting parameters of the system based on the linear system theory can be well applied to the linear system, but cannot be applied to a complex nonlinear system. The artificial neural network is a network formed by widely interconnecting a large number of processing units, has large-scale parallel simulation processing capacity and strong self-adaption, self-organization and self-learning capacity, is generally emphasized in system modeling, identification and control, and has a nonlinear transformation characteristic which provides an effective method for system identification, particularly for identification of a nonlinear system.

At present, the most applied in nonlinear system identification is a multilayer forward network which has the capability of approximating any continuous nonlinear function, but the network structure is generally static, and analysis of a material falling process shows that the material level and the air drop of a blanking bin are gradually changed, so that the air content in two continuous sampling periods is also closely related. To this end, the present invention employs a dynamic recurrent neural network to model the system. Unlike static feedforward neural networks, dynamic recursive networks have the function of mapping dynamic features by storing internal states, so that the system has the capability of adapting to time-varying characteristics and is more suitable for identification of nonlinear dynamic systems. Based on a dynamic recursive Elman neural network, the invention is used for measuring the air volume, the material level c of a blanking bin, the air fall h, the blanking rate D, the material density rho, the diameter D of a helical blade of a helical conveyor, the pitch S and the maximum rotating speed v of a screw_RThe mapping relation between the two is identified, and the material distribution in the blanking bin is detected and dynamically adjusted in the blanking process, so that the trained neural network can directly predict the air space amount in different states, and high-precision blanking is realized.

The technical scheme of the invention is to provide a screw type material proportioning machine controller based on machine learning, which comprises the following structures: the device comprises a signal acquisition module, a processing module, a neural network module, an iterative learning module, a storage module, a first connection array, a second connection array and an output module, wherein the signal acquisition module acquires sensing signals of the material level of a discharging bin, the material level of a weighing hopper and the weight of falling materials in real time through a bin level sensor in the discharging bin, a hopper level sensor in the weighing hopper and a weighing module bearing the weighing hopper respectively and transmits the sensing signals to the processing module for data processing and analysis, and a memory is used for data storage;

the neural network module adopts a dynamic recursive Elman neural network, an input layer of the neural network module respectively receives 7 input quantities of material level, air fall, blanking rate, material density of a blanking bin, the diameter and the screw pitch of a helical blade of a screw conveyor and the maximum rotating speed of a screw from the processing module, and the output quantity of an output layer is respectively transmitted to the iterative learning module and the processing module through a first connecting array and a second connecting array;

when the neural network is trained offline, the iterative learning module adjusts the connection weight of the neural network according to the actual value of the material empty space and the network output value which are respectively input by the processing module and the neural network through the first connection array;

when the feeding is controlled on line, the first connection array is disconnected, the neural network predicts the air quantity and outputs the air quantity to the processing module through the second connection array, and the spiral conveyor at the opening at the bottom of the feeding bin is controlled to be shut down through the output module after the air quantity is processed and analyzed by the processing module.

Preferably, the output module is further connected to a blanking valve at the bottom opening of the weighing hopper, and the blanking valve is controlled to be opened and closed according to the instruction of the processing module.

Preferably, the signal acquisition module is further used for acquiring the material level in the mixing hopper through a material level sensor in the mixing hopper positioned below the blanking valve, the output module is further respectively connected to a push plate at the bottom of the mixing hopper and a mixer installed in the mixing hopper, and the start and stop of the push plate and the mixer are respectively controlled according to the instruction of the processing module.

Preferably, the output module is further connected to a feeding pump which is arranged between the storage bin and the discharging bin in series, and controls the start-stop and the operation of the feeding pump according to the instruction of the processing module, wherein the rotating speed of the feeding pump is controlled according to the following formula:

wherein, V_{0 feeding}A set maximum feeding speed, L is the current material level of the feed bin, L_MAnd L_mRespectively the preset highest and lowest feeding bin material positions.

Preferably, the output module is also connected to a rotatable base of a bin level sensor in the blanking bin, and controls the operation of the base according to the instruction of the processing module.

Preferably, the output module is also connected to a vibrating rod arranged on the side wall of the machine frame close to the blanking bin, and controls the starting, stopping and running of the vibrating rod according to the instruction of the processing module.

Preferably, the model of the neural network is:

xc_k(t)＝x_k(t-mod(k，q)-1)，

wherein mod is a remainder function, and f () is a sigmoid function; xc_k(t) is the carry layer output, x_j(t) is the hidden layer output, u_i(t-1) and y (t) are input layer input and output layer output, ω_j、ω_jkAnd ω_jiRespectively, the connection weight from the hidden layer to the output layer, the connection weight from the accepting layer to the hidden layer and the connection weight from the input layer to the hidden layer, theta and theta_jOutput layer and hidden layer thresholds, respectively; m, q is a selected regression delay scale, and is preferably selected according to the sampling period and the blanking rate, and if q is 5, the method is used; j is 1, 2.. m, i is 1, 2.. 7, and the number m of nodes of the hidden layer and the receiving layer can be selected from 11 to 20, such as 16;

the training uses a gradient descent method.

Preferably, the screw conveyer shutdown control is used for compensating the current accumulated blanking error in addition to the empty space amount predicted value.

Preferably, the number of the neural network modules is multiple, and each neural network module corresponds to one screw conveyer of the dispensing machine.

Preferably, the output module controls the running speed of the screw conveyor in the following way:

A. from a stopped state at a rate of mu a_maxStarting at acceleration, when the speed reaches lambda.v_RKeeping the speed unchanged;

B. when the closing time is up, the value is expressed in mu a_maxThe acceleration starts to decelerate until stopping;

wherein, a_maxRated maximum acceleration, v, of the screw conveyor_RThe maximum speed is mu is an acceleration coefficient between 0.5 and 0.9, and the lambda is a speed coefficient between 0.85 and 1.0;

the closing time means that the current baiting weight read from the weighing module is equal to:

wherein Ws and Wa are respectively the predicted values of the current one-time material discharge amount and the empty space amount, d is the discharge rate of the screw conveyer when the screw rotates at the maximum speed, and t is the discharge rate of the screw conveyer when the screw rotates at the maximum speed_sFor the deceleration stop time length: t is t_s＝λ·v_R/μ·a_max。

Compared with the prior art, the scheme of the invention has the following advantages: according to the invention, a nonlinear network is adopted to construct and model a mapping relation between influence factors and the empty space amount in the blanking process, and the network after offline training can accurately predict the empty space amount in different blanking states, so that continuous blanking control can be directly carried out according to a predicted value in online application, the blanking error fluctuation in online iterative learning is avoided, the method is suitable for small-batch production, the total error of batch blanking is reduced by controlling the accumulated error of blanking, and compared with a common screw type blanking device, the spiral conveyor can keep a higher operation speed, and the blanking efficiency is improved.

Drawings

FIG. 1 is a block diagram of a machine learning based screw material dispensing machine controller;

FIG. 2 is a schematic diagram of an Elman neural network structure;

FIG. 3 is a view of the screw type material proportioning machine;

FIG. 4 is a view of the configuration of a screw type material batching machine;

FIG. 5 is a schematic view of a material falling process;

FIG. 6 is a schematic view of a partial structure of a storage silo and a feed silo;

FIG. 7 is a schematic view of a vibrating rod;

FIG. 8 is a schematic view of a laminar flow of the material in the blanking bin;

FIG. 9 is a schematic view showing the distribution of a multicomponent material in a weighing hopper;

fig. 10 is a graph of the change in weighing during the falling of the material.

Wherein: 1. the device comprises a discharging bin 2, a screw conveyor 3, a metering hopper 4, a weighing module 5, a discharging valve 6, a mixing hopper 7, a push plate 8, a conveying pipe 9, a controller 10, a storage bin 11, a feeding pump 12, a bin level sensor 13, a bin level sensor 14, a material level sensor 15, a feeding pipe 16, a material spray head 17, a small hole 18, a vibrating rod 19, a material level surface 20, a stopping point 21, a scanning line 22, a mixer 23 and a discharging pipe

30. Rack

91. The device comprises a signal acquisition module 92, a processing module 93, a neural network module 94, an iterative learning module 95, a storage module 96, a first connection array 97, a second connection array 98 and an output module

101. Drawing plate

181. Pillar 182, cradle head 183, vibrator 184, vibration rod 185, particle protrusion 186, vibration rod track

201. Screw box 202, conveying screw 203, connector 204 and motor

Detailed Description

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but the present invention is not limited to only these embodiments. The invention is intended to cover alternatives, modifications, equivalents and alternatives which may be included within the spirit and scope of the invention.

In the following description of the preferred embodiments of the present invention, specific details are set forth in order to provide a thorough understanding of the present invention, and it will be apparent to those skilled in the art that the present invention may be practiced without these specific details.

The invention is described in more detail in the following paragraphs by way of example with reference to the accompanying drawings. It should be noted that the drawings are in simplified form and are not to precise scale, which is only used for convenience and clarity to assist in describing the embodiments of the present invention.

As shown in fig. 1, the screw material proportioning machine controller based on machine learning of the present invention includes a signal acquisition module 91, a processing module 92, a neural network module 93, an iterative learning module 94, a storage module 95, a first connection array 96, a second connection array 97 and an output module 98. The neural network module 93 adopts an Elman neural network, and the storage module 95, i.e. a memory, is used for storing data.

As shown in fig. 2, the used Elman neural network has a recursive structure, compared with the BP neural network, the Elman neural network further includes a receiving layer in addition to an input layer, a hidden layer and an output layer, and the receiving layer is used for feedback connection between layers, so that the receiving layer can express time delay between input and output and parameter timing characteristics, and the network has a memory function. Referring to fig. 2, the built neural network input layer has 7 units, the number m of nodes of the hidden layer and the accepting layer can be selected from 11 to 20, for example, 16 is selected, and the output layer has only one unit.

The neural network model is:

xc_k(t)＝x_k(t-mod(k，q)-1) (1)，

wherein mod is a remainder function, and f () is a sigmoid function; xc_k(t) is the carry layer output, x_j(t) is the hidden layer output, u_i(t-1) and y (t) are input layer input and output layer output, ω_j、ω_jkAnd ω_jiRespectively from hidden layer to output layerThe connection weights, the connection weights of the bearer layer to the hidden layer and the connection weights, theta and theta, of the input layer to the hidden layer_jOutput layer and hidden layer thresholds, respectively; m, q is a selected regression delay scale, and is preferably selected according to the sampling period and the blanking rate, and if q is 5, the method is used; j is 1, 2.. m, i is 1, 2.. 7.

Referring to fig. 3 and 4, the screw type material dosing machine controller based on machine learning is used for accurately controlling the feeding of the screw type material dosing machine. The screw type material batching machine comprises a discharging bin 1, a spiral conveyor 2, a metering hopper 3, a weighing module 4, a discharging valve 5, a material mixing hopper 6 and a material mixing hopper 9 adopting the invention. The screw type material proportioning machine is used for blanking and proportioning materials with various components, wherein each component of the materials is provided with a group of blanking bins 1 corresponding to the screw conveyor 2.

The bottom of the blanking bin 1 is provided with a drawing plate 101, the drawing plate is opened during blanking, and the material flows out from an opening at the bottom of the blanking bin. The screw conveyor 2 comprises a screw box 201, a conveying screw 202, a connector 203 and a motor 204, wherein the shell of the motor 204 is connected with the screw box 201 through the connector 203, and the conveying screw 202 in the screw box 201 is connected with the shaft of the motor 204 through a shaft sleeve; the upper surface of the screw box 201 is provided with a feeding hole corresponding to the opening at the bottom of the discharging bin 1, the other end of the screw box opposite to the motor is connected to a discharging pipe 23, and the discharging pipe 23 is fixed on the frame 30.

As shown in fig. 3 and 4, during discharging, the control drawing plate 101 is opened, the material falls into the screw box 201 of the screw conveyor 2 from the discharging bin 1, the motor 204 is started, the conveying screw 202 rotates along with the motor, the material is conveyed to the end discharging pipe 23, and falls into the weighing hopper 3 below from the discharging pipe 23.

The housing 30 serves as a frame of the apparatus for fixing and supporting the other respective components. The weighing module 4 is fixed on the frame 30, the weighing hopper 3 is movably buckled and pressed on the weighing module 4, the bottom of the weighing hopper 3 is provided with an opening, and the opening and the closing of the opening are controlled by the blanking valve 5. The weighing hopper 4 is positioned at the lower part of the blanking pipe 23, and a plurality of screw conveyors 2 are distributed in a radial direction relative to the centers of the blanking pipe 23 and the weighing hopper 4.

The mixing hopper 6 is located below the blanking valve 5 and has a push plate 7 at its bottom, below which a feed pipe 8 is connected, which feeds the multicomponent mixture to a packaging bag or a production facility. A level sensor 14 is mounted on the side wall of the mixing hopper 6, and a mixer 22 is also arranged in the mixing hopper 6, and the capacity of the mixing hopper 6 is several times, for example 15 times, that of the weighing hopper 3.

As shown in fig. 1 and 4, the controller of the present invention preferably further includes an input module, such as a touch screen. During operation, the formula and other parameters of the multi-component material can be set through the human-computer interface of the touch screen, and the switching between the first connection array and the second connection array can be realized through the operation of the touch screen, so that the controller works in an off-line training or on-line prediction mode.

As shown in fig. 4 and 5, the controller can dynamically read the current reading of the weighing module in real time, but during the feeding process, the read reading does not really fall to the weight of the material in the weighing hopper, but includes the effect of the impact quantity of the material; and after the motor is switched off, the material from the screw conveyor to the weighing hopper will continue to fall into the weighing hopper. Therefore, the blanking and batching control is generally performed by deducting the empty amount, i.e., closing the screw conveyor when the weighing amount is less than a certain value of the target weight. However, in practice, how to accurately obtain the size of the empty space is a difficult problem which must be solved.

FIG. 5 is a graph showing the change of impact of level drop and falling speed on a weighing hopper during falling of a material at an initial velocity v₀Falling from the screw conveyor 2, the distance between the outlet of the screw conveyor 2 and the bottom of the measuring hopper 3 is H, and the distance is along with the material level H in the measuring hopper₂Increase of (2), air drop h₁It will be smaller.

The mass equivalent change of the material in the hopper can be represented by the following formula:

wherein, at time t, dm is the unit of the outlet of the screw conveyorTime blanking quality (g/s), v₀The initial velocity of the material as it falls, the velocity of the material at Δ m as it falls into the weighing hopper, is determined from the velocity v over the time Δ t₁Becomes 0.

As can be seen from the equation (4), the air fall h is followed₁The impact of the material on the weighing hopper also changes, so that the weight change of the weighing hopper changes with time.

Through carrying out experiment test and analysis repeatedly to the unloading process, conclude to screw rod formula material proportioning machine, the most main influence factor of volume in its unloading process cavity includes: the material level c of the blanking bin, the air drop h, the blanking rate D, the material density rho, the diameter D of a helical blade of the helical conveyor, the pitch S and the maximum rotating speed v of the screw_R. The empty space quantities are complex non-linear mappings of these physical quantities. In order to accurately obtain the predicted values of the empty material quantities in different states, and therefore to accurately discharge materials by closing the screw conveyor in advance, the mapping relationship needs to be identified and expressed.

Based on the mapped complex nonlinear characteristics and considering the close connection existing between the hollow medium in two continuous sampling periods, the invention adopts dynamic recursive Elman neural network modeling to model the hollow medium and the blanking bin material level c, the air fall h, the blanking rate D, the material density rho, the diameter D of the helical blade of the helical conveyor, the pitch S and the maximum rotating speed v of the screw_RThe mapping relationship between the two is identified.

With reference to fig. 1 and 2, the established neural network has an input layer comprising 7 nodes, wherein the material density ρ, the diameter D of the helical blade of the screw conveyor, the pitch S and the maximum rotating speed of the screw are determined values and can be input to the controller through the touch screen; the other 3 quantities need to be acquired dynamically in real time by the signal acquisition module. By introducing a plurality of different delay regression carrying layer nodes into the network, the network structure is more appropriate to the blanking process, and the network training is faster to converge.

With reference to fig. 1 and 2, when the neural network is trained offline, the iterative learning module adjusts the connection weight of the neural network according to the actual value of the material space volume and the network output value, which are input by the processing module and the neural network through the first connection array, respectively.

In order to obtain a training sample, after the feeding is started, when a continuous material flow is formed between a material from a spiral conveyor at the bottom of a feeding bin and a measuring hopper, the feeding is continued for a period of time, a weighing module weight reading W is read in real time when the spiral conveyor is closed, a weighing module weight reading WD is read after the material is completely dropped, the empty space under the state of the moment when the spiral conveyor is closed is A-WD-W, and the empty space is a value which is an actual value of a sample output value y, namely an expected value y_d。

The neural network training adopts a gradient descent method, and the weight and threshold value adjusting method in the training is as follows.

Assuming a total of P training samples, let the error function be:

then the adjustment of the weight from the hidden layer to the output layer is shown as follows:

ω_j(t+1)＝ω_j(t)+Δω_j(t+1) (6)，

wherein the content of the first and second substances,

δ_y＝-(y_d-y)·y·(1-y) (8)，

the adjustment formula of the output layer threshold is as follows:

θ(t+1)＝θ(t)+Δθ(t+1) (9)，

wherein the content of the first and second substances,

similarly, the adjustment formula of the connection weight from the input layer to the hidden layer is:

ω_ji(t+1)＝ω_ji(t)+Δω_ji(t+1) (11)，

wherein the content of the first and second substances,

δ_j＝δ_y·ω_j·x_j(t)·(1-x_j(t)) (13)，

the adjustment formula of the hidden layer threshold is as follows:

θ_j(t+1)＝θ_j(t)+Δθ_j(t+1) (14)，

wherein the content of the first and second substances,

irrespective of xc_k(t) pairs of connection weights ω_jkThe adjustment formula of the connection weight from the bearer layer to the hidden layer is as follows:

ω_jk(t+1)＝ω_jk(t)+Δω_jk(t+1) (16)，

wherein the content of the first and second substances,

the initial value range of each weight is an interval of (-0.1, 0.1), the learning rate eta is a decimal less than 1, and the learning rate eta can be dynamically adjusted by adopting a fixed rate or according to the total error of the current network output.

The training end condition may be set to a total error or a variation thereof smaller than a set value or a number of times of training up to a certain amount.

Preferably, in order to make the training sample cover more cases, each time the auger is turned off may be set to a random value from the moment the auger is started or the moment the weighing module weight reads a certain determined value.

Before network training, normalization preprocessing is performed on 7 input quantities and 1 output quantity:

r′＝r-r_min/r_max-r_min (18)，

wherein r is an untreated physical quantity, and r' is a treatedNormalized physical quantity, r_maxAnd r_minRespectively the maximum and minimum values of the sample data set.

When calculating the predicted value of the air volume, the output volume of the network is converted back to the air volume value by the following formula:

r＝r_min+r′·(r_max--r_min) (19)。

when the blanking is controlled on line, the first connection array is disconnected, the neural network predicts the air quantity yA and outputs the air quantity yA to the processing module through the second connection array, and the screw conveyor at the opening at the bottom of the blanking bin is controlled to be shut down through the output module after the processing module processes and analyzes:

assuming that the one-time feeding amount of the current components is Ws, when feeding is started, the controller obtains the initial weight of the weighing hopper G0 by reading the sensing value of the weighing module; the controller then constantly reads the sensor value of the weighing module and closes the screw conveyor when this value reaches (G0+ Ws-yA).

Preferably, in addition to the predicted empty space amount, the current accumulated feeding error is compensated, that is, when the weight of the measuring hopper is detected to reach (G0+ Ws-yA-E), the screw conveyor is closed, wherein E is the current accumulated feeding error of the component.

Preferably, the controller of the present invention controls the operating speed of the screw conveyor in the following manner:

wherein Ws and Wa are respectively the predicted values of the current one-time material discharge amount and the empty space amount, d is the discharge rate of the screw conveyer when the screw rotates at the maximum speed, and t is the discharge rate of the screw conveyer when the screw rotates at the maximum speed_sFor the length of deceleration stop time, t_s＝λ·v_R/μ·a_max。

When the training sample is obtained off-line and the neural network is applied on-line, the same rotating speed control is adopted for the spiral conveyor. Of the 7 inputs of the training sample, the material density, the screw blade diameter of the screw conveyor, the screw pitch, and the maximum screw speed were preset. The signal acquisition module acquires sensing signals of the material level of the blanking bin, the material level of the measuring hopper and the weight of falling materials in real time through the bin level sensor in the blanking bin, the bin level sensor in the measuring hopper and the weighing module bearing the measuring hopper respectively, transmits the sensing signals to the processing module for data preprocessing, then inputs the signals to the neural network, transmits output values of the neural network and expected output values preprocessed by the processing module to the iterative learning module through the first connecting array, and transmits adjusted weight values back to the neural network by the iterative learning module according to a gradient descent method.

The bin level sensor and the bucket level sensor can adopt distance sensors to respectively detect the material level heights of materials in the blanking bin and the measuring hopper, wherein the bucket level signals of the measuring hopper are processed by the processing module and then converted into material air drops.

Preferably, the bucket level sensor may be arranged like a bin level sensor.

Through the continuous collection of weighing module signal of periodicity, processing module can calculate the falling mass equivalent of material in the unit interval promptly blanking rate.

It can also be analyzed from the formula (4) that the detected blanking rate, i.e. the blanking mass equivalent per unit time, is also influenced by the material form distribution in the blanking bin 1.

The granular materials flow out of the feed bin under the action of gravity mainly in two types of bulk flow and central flow. The whole particle layer in the overall flow type middle storage bin can flow out approximately uniformly, and basically every particle moves; while some particles in the flow pattern of the core stream are stationary, there is a flow channel boundary between the flowing and stationary particles. The integral blanking rate of the integral flow is larger than that of the central flow, the fluctuation of the blanking rate is small, and the flow is stable. In the actual production process, the material in the bin may have a central flow pattern, so that when the material is discharged from the material opening, the material is firm and plate-shaped due to the compaction stress generated by bin pressure.

With reference to fig. 6 to 8, in order to reduce the fluctuation range of the blanking rate in the blanking bin and better perform system modeling and air-to-air volume prediction, the material batching machine applied to the invention adopts a distance sensor type bin position sensor and a rotatable vibrating rod to detect and adjust the material accumulation form in the blanking bin, so that the dynamic material arch is alternately formed and collapsed above the blanking port, and the material compactness and the stability of the blanking form are ensured.

As shown in figure 6, the discharging bin 1 continuously discharges materials, and when the material level in the bin is reduced to a certain value, the materials need to be supplemented. For this purpose, a storage bin 10 is arranged above the lower bin 1, and the material in the storage bin 10 is fed into the lower bin 1 through a feed pump 11 and a feed pipe 15. In order to uniformly feed material particles, a material spray nozzle 16 is arranged at an outlet at the tail end of the feeding pipe 15, the surface of the material spray nozzle 16 is in a spherical shape, round small holes 17 are distributed on the surface of the material spray nozzle, and the aperture of each small hole is optimized according to the granularity of the material. The feed pump 11 is a screw conveyor, and its operation is controlled by a controller.

In the blanking process of the blanking bin 1, along with the reduction of the material level surface 19, the feeding pump 11 acts under the control of the controller, so that the material level of the top surface of the material in the blanking bin is kept near a preset value, and the rotating speed of the feeding pump is controlled according to the following formula:

wherein, V_{0 feeding}A set maximum feeding speed, L is the current material level of the feed bin, L_MAnd L_mAre respectively preset at L_TThe highest and lowest levels nearby.

In fig. 6, the two drawings are respectively observed from the side view and the top view of the lower silo 1, as shown in fig. 6a and 6b, a bin sensor 12 is installed on a vertex angle of the lower silo 1 near the center of the frame, and the bin sensor has a rotatable base capable of pitching and rotating, so that the bin sensor can detect materials in different directions of the stop pointing points 20, and each stop pointing point 20 forms a scanning line 21 close to a concentric circle, thereby judging the distribution of the discharge level surface 19.

As shown in fig. 7, the controller improves the distribution of the material by means of a vibrating rod 18 mounted on the side wall of the lower silo 1 by the batching machine. The vibrating rod 18 comprises a support 181, a holder 182, a vibrator 183 and a vibrating rod 184 which are connected in sequence, a spring buffer is arranged at the bottom of the vibrator 183, particle protrusions 185 are distributed on the surface of the vibrating rod 184, and the holder 182 can pitch and rotate so that the vibrating rod 184 can do curvilinear motion in the lower storage bin 1.

In the blanking process, the controller of the invention judges the distribution of the materials in the blanking bin respectively through the detection of the bin level sensor and the tracking of the blanking rate in unit time, so that the material level in the blanking bin keeps approximate parabolic surface shape. With reference to fig. 6 to 8, when the materials are uniformly distributed, the distance values of the materials detected by the bin sensors in different directions are approximately concentrated in a smaller range after geometric transformation of the detection ray and the inclination angle in the vertical direction. When the material is locally hardened or is arched stably, the detected distance value exceeds the range. Meanwhile, the feeding speed of each feeding bin is tracked in real time through the weighing module. When the distance sensor detects the abnormal state or finds that the fluctuation of the blanking amount in unit time exceeds a set threshold value, such as 5%, the controller commands the vibrating rod to act, the vibrating rod starts to pass through a high-point area of the material level to a low-point area of the material level from a starting point through the operation of the pan-tilt head to perform snake-shaped stirring, and a vibrating rod track 126 of the tail end of the vibrating rod 124 in the blanking bin 1 is shown in fig. 7; meanwhile, the vibrator starts to vibrate, and the particle protrusions on the vibration rod drive peripheral particles, so that hardening or material arch which is occasionally formed is broken, and the material distribution is recovered to be uniform. Through dynamic detection and control of material distribution, fluctuation of material compactness is reduced, and therefore stability of filling amount in unit time is guaranteed. And (5) stopping feeding while the vibrating rod acts, and closing the drawing plate.

As shown in figure 8, the invention greatly weakens the compaction force effect generated by the charging impact by the detection and action coordination of the distance sensor and the vibrating rod, effectively prevents the granularity segregation of the materials in the bin, activates the materials in the lower bin and improves the distribution of the materials.

Preferably, the controller of the invention is used as a control center of the whole screw type material batching machine, the controller sequentially controls the spiral conveyors to act in the multi-component material blanking process, and after one-time formula amount blanking is completed, the blanking valve is opened, and the material falls into the mixing hopper from the metering hopper.

After accomplishing a plurality of one-time baiting, the controller reads the state of material level sensor in the compounding fill, if detect the material level and exceed and set for the threshold value, then through the rotatory stirring of output module control blender, with behind the multiple material misce bene, under the control of controller, the push pedal is opened, and the misce bene is exported from the conveying pipeline.

FIGS. 9 to 10 are supplementary views of the multi-component material feeding process, wherein FIG. 9 is a schematic diagram of the distribution of the materials in the measuring hopper during the feeding of 4 components; fig. 10 is a graph of the change in the weighing module reading during a 900ms long material fall with the abscissa being the delay time after the screw conveyor is turned off. It can be seen that due to the impact force, the weighing reading will overshoot, and then return to the actual weight; and, the material in the air only falls into the weighing hopper completely after the screw conveyor is closed for about 700ms, and the reading of the weighing module tends to be stable.

The controller of the invention is used for controlling the blanking, the blanking behaviors of each screw conveyor are respectively modeled by the off-line, and the blanking of each component material is independently carried out in the process of collecting samples, so that all the materials can be recycled without waste. The material level, the air drop and the blanking rate of the blanking bin are periodically acquired during actual blanking, and the current air quantity can be forecasted in real time, so that accurate blanking can be realized from the first batch, and the blanking error fluctuation in other online iterative learning schemes is avoided.

The above-described embodiments do not limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the above-described embodiments should be included in the protection scope of the technical solution.

Claims

1. A screw material batching machine controller based on machine learning comprises a signal acquisition module, a processing module, a neural network module, an iterative learning module, a storage module and an output module, wherein the signal acquisition module is used for acquiring sensing signals of the material level of a blanking bin, the material level of a measuring hopper and the weight of falling materials in real time through a bin level sensor in the blanking bin, a hopper level sensor in the measuring hopper and a weighing module bearing the measuring hopper respectively and transmitting the sensing signals to the processing module for data processing and analysis, and a memory is used for data storage;

the neural network module adopts a dynamic recursive Elman neural network, an input layer of the neural network module respectively receives 7 input quantities of the material level, the air fall, the blanking rate and the material density of the blanking bin, the diameter and the screw pitch of a helical blade of the screw conveyor and the maximum rotating speed of a screw from the processing module, and the output quantity of the output layer is transmitted to the iterative learning module and the processing module;

when the neural network is trained off line, the iterative learning module adjusts the connection weight of the neural network;

when the blanking is controlled on line, the neural network predicts the air quantity, and the processing module processes and analyzes the air quantity and then controls the shutdown of the screw conveyor at the opening at the bottom of the blanking bin through the output module:

continuously reading the sensing value of the weighing module, and closing the screw conveyor when the value reaches (G0+ Ws-yA), wherein Ws is the once feeding amount of the current component, G0 is the initial weight of the measuring hopper when feeding is started, and yA is the predicted empty amount;

the bin level sensor adopts a distance sensor, and the output module is also connected to a vibrating rod in the discharging bin; and when the distance sensor detects that the material distance value exceeds a smaller range after geometric transformation of the detection ray and the vertical direction inclination angle, or when the fluctuation of the blanking amount in unit time exceeds a set threshold value, the vibrating rod is commanded to act.

2. The machine learning-based screw material dispensing machine controller of claim 1, wherein: the system also comprises a first connection array and a second connection array;

the output quantity of the output layer is transmitted to the iterative learning module and the processing module through the first connection array and the second connection array respectively;

when the neural network is trained offline, the iterative learning module respectively inputs a material empty space actual value and a network output value through the first connection array according to the processing module and the neural network;

when the blanking is controlled on line, the first connection array is disconnected, the trained neural network predicts the space amount and outputs the space amount to the processing module through the second connection array.

3. The machine learning-based screw material dispensing machine controller of claim 1, wherein: the signal acquisition module is still through being arranged in the material level sensor collection mixing hopper of blanking valve below mixing hopper material level in the hopper, output module still is connected to the blanking valve of batch hopper bottom opening part to according to the opening and closing of processing module's instruction control blanking valve, output module still is connected to respectively the push pedal of mixing hopper bottom and the blender of installing in mixing hopper, and according to processing module's instruction respectively control the start-stop of push pedal and blender.

4. The machine learning-based screw material dispensing machine controller of claim 1, wherein: the output module is also connected to a feeding pump which is connected between the storage bin and the discharging bin in series, and controls the start, stop and operation of the feeding pump according to the instruction of the processing module, wherein the rotating speed of the feeding pump is controlled according to the following formula:

wherein，V_{0 feeding}A set maximum feeding speed, L is the current material level of the feed bin, L_MAnd L_mRespectively the preset highest and lowest feeding bin material positions.

5. The machine learning-based screw material dispensing machine controller of claim 1, wherein: the output module is also connected to a rotatable base of a bin level sensor in the blanking bin, and controls the operation of the base according to the instruction of the processing module.

6. The machine learning-based screw material dispensing machine controller of any one of claims 1-5, wherein the neural network model is:

xc_k(t)＝x_k(t-mod(k，q)-1)，

wherein mod is a remainder function, and f () is a sigmoid function; xc_k(t) is the carry layer output, x_j(t) is the hidden layer output, x_k(t) is x_j(t) component of the vector formed, u_i(t-1) and y (t) are input layer input and output layer output, ω_j、ω_jkAnd ω_jiRespectively, the connection weight from the hidden layer to the output layer, the connection weight from the accepting layer to the hidden layer and the connection weight from the input layer to the hidden layer, theta and theta_jOutput layer and hidden layer thresholds, respectively; m and q are selected regression delay scales according to the sampling period and the blanking rate; j is 1, 2.. m, i is 1, 2.. 7, and the number m of nodes of the hidden layer and the receiving layer is selected from 11-20;

the training uses a gradient descent method.

7. The machine learning-based screw material dispensing machine controller of claim 6, wherein: the screw conveyer shutdown control is used for compensating the current accumulated blanking error besides the predicted value of the empty space amount, and the screw conveyer is closed when the weight of the weighing hopper is detected to reach (G0+ Ws-yA-E), wherein E is the current accumulated blanking error of the component.

8. The machine learning-based screw material dispensing machine controller of claim 6, wherein: the neural network module has a plurality of, and every neural network module corresponds a screw conveyer of proportioning machine.