Disclosure of Invention
The invention designs and develops an engineering plastic crushing device, and aims to fully crush crushed materials by arranging three layers of crushing cavities in a crushing bin.
The invention designs and develops a control method of an engineering plastic crushing device, and aims to respectively control a discharging stop door and a discharging stop door in a BP neural network mode so as to fully crush crushed materials in a crushing cavity.
The invention also aims to set the preset rotating speed of the crushing shaft so as to set the initial rotating speed, so that the rotating speed of the crushing shaft can be better controlled to fully crush the crushed materials.
The technical scheme provided by the invention is as follows:
an engineering plastic crushing device comprises:
the crushing bin is provided with a feeding hole and a discharging hole, and a discharging baffle door is arranged at the discharging hole;
the first crushing cavity is communicated with the feeding hole and is also provided with a first discharging hole;
the first crushing shaft transversely penetrates through the first crushing cavity, one end of the first crushing shaft is rotatably supported on the first crushing cavity and penetrates out of the first crushing cavity, and double-helix stirring blades are arranged on the first crushing shaft;
a first motor, an output shaft of which is connected with the first crushing shaft;
the second crushing cavity is communicated with the first discharge hole and is also provided with a second discharge hole;
the second crushing shaft transversely penetrates through the second crushing cavity, one end of the second crushing shaft is rotatably supported on the second crushing cavity and penetrates out of the second crushing cavity, and double-helix stirring blades are arranged on the second crushing shaft;
a second motor, an output shaft of which is connected with the second crushing shaft;
the third crushing cavity is communicated with the second discharge hole and is also provided with a third discharge hole;
the third crushing shaft transversely penetrates through the third crushing cavity, one end of the third crushing shaft is rotatably supported on the third crushing cavity and penetrates out of the third crushing cavity, and double-helix stirring blades are arranged on the third crushing shaft;
and the output shaft of the third motor is connected with the third crushing shaft.
Preferably, the method further comprises the following steps:
the first discharging stop gate is arranged at the first discharging opening;
the second discharging stop gate is arranged at the second discharging opening; and
and the third discharging stop door is arranged at the third discharging opening.
Preferably, the method further comprises the following steps:
a first rotation speed sensor connected with the first crushing shaft for monitoring the rotation speed of the first crushing shaft;
a second rotation speed sensor connected with the second crushing shaft and used for monitoring the rotation speed of the second crushing shaft;
a third rotation speed sensor connected with the third crushing shaft and used for monitoring the rotation speed of the third crushing shaft;
the first weight sensor is arranged at the bottom of the first discharging stop door and used for monitoring the weight of the crushed materials in the first crushing cavity;
the second weight sensor is arranged at the bottom of the second discharging stop door and is used for monitoring the weight of the crushed materials in the second crushing cavity;
the third weight sensor is arranged at the bottom of the third discharging stop door and used for monitoring the weight of the crushed materials in the third crushing cavity; and
a controller electrically coupled to the speed sensor, the weight sensor, and the door simultaneously.
Preferably, a plurality of vibrators are arranged at the bottom of the crushing bin.
A control method of an engineering plastic crushing device is controlled based on a BP neural network and comprises the following steps:
step one, measuring a first weight M of the crushed material in the first crushing cavity through a weight sensor according to a sampling periodaA second weight M of the crushed material in the second crushing chamberbThird, aA third weight M of the material to be crushed in the crushing chambercMeasuring the rotational speed omega of the first comminution shaft by means of a rotational speed sensoraSecond crushing shaft rotational speed ωbThird crushing shaft rotational speed ωc;
Step two, normalizing the parameters in sequence, and determining an input layer vector x ═ x of the three-layer BP neural network1,x2,x3,x4,x5,x6}; wherein x is1Is a first weight coefficient, x2Is a second weight coefficient, x3Is the third weight coefficient, x4Is the coefficient of rotation, x, of the first crushing shaft5Is the second crushing shaft speed coefficient x6Is the rotation speed coefficient of the third crushing shaft;
step three, the input layer vector is mapped to a middle layer, and the middle layer vector y is { y ═ y1,y2,…,ym}; m is the number of intermediate layer nodes;
step four, obtaining an output layer vector o ═ o1,o2,o3,o4};o1For the first discharge door aperture regulating coefficient, o2For the second discharge door aperture regulating coefficient o3The opening degree adjustment coefficient and the opening degree of the third discharging stop door are adjusted4The state is a discharging stop door;
fifthly, controlling the opening degree of the first discharging stop door, the second discharging stop door and the third discharging stop door to ensure that
Wherein the content of the first and second substances,
respectively outputting the first three parameters of the layer vector, delta, for the ith sampling period
a_max、δ
b_max、δ
c_maxThe maximum opening degree, delta, set for the first discharge stop door, the second discharge stop door and the third discharge stop door respectively
a(i+1)、δ
b(i+1)、δ
c(i+1)The set opening degrees of the first discharging stop door, the second discharging stop door and the third discharging stop door in the (i + 1) th sampling period are respectively set;
sixthly, judging the running state of the discharging stop door in the (i + 1) th cycle according to the rotating speed and weight sampling signals in the ith cycle, and outputting signals
When the discharging shutter is closed, the signal is output
When the material is discharged, the material discharge stop door is closed.
Preferably, the number m of the intermediate layer nodes satisfies:
wherein n is the number of nodes of the input layer, and p is the number of nodes of the output layer.
Preferably, in the second step, the first weight M is addedaSecond weight MbA third weight McFirst crushing shaft rotation speed omegaaSecond crushing shaft rotation speed omegabThird crushing shaft rotation speed omegacThe formula for normalization is:
wherein x isjFor parameters in the input layer vector, XjRespectively being a measurement parameter Ma、Mb、Mc、ωa、ωb、ωc,j=1,2,3,4,5,6;XjmaxAnd XjminRespectively, a maximum value and a minimum value in the corresponding measured parameter.
Preferably, in the third step, the rotation speeds of the first crushing shaft, the second crushing shaft and the third crushing shaft in the initial motion state satisfy an empirical value:
ωa0=0.85ωa_pre
ωb0=0.93ωb_pre
ωc0=0.88ωc_pre
wherein, ω isa0、ωb0、ωc0Initial rotation speeds, ω, of the first crushing shaft, the second crushing shaft and the third crushing shaft, respectivelya_pre、ωb_pre、ωc_preThe preset rotating speeds of the first crushing shaft, the second crushing shaft and the third crushing shaft are respectively.
Preferably, the preset rotation speed ω of the first pulverizing shafta_preIs composed of
The preset rotating speed omega of the second crushing shaftb_preIs composed of
A preset rotation speed omega of the third crushing shaftc_preIs composed of
In the formula, ζaIs a first correction coefficient; zetabIs a second correction coefficient; zetacIs a third correction coefficient; lambda [ alpha ]aThe number of the first crushing shaft blades; lambda [ alpha ]bThe number of the second crushing shaft blades; lambda [ alpha ]cThe number of the third crushing shaft blades; omegaa_maxThe maximum rotating speed of the first crushing shaft; omegaa_minThe minimum rotation speed of the first crushing shaft; omegab_maxThe maximum rotating speed of the second crushing shaft; omegab_minThe minimum rotation speed of the second crushing shaft; omegac_maxThe maximum rotating speed of the third crushing shaft; omegac_minThe minimum rotating speed of the third crushing shaft; d is the length of the blade on the crushing shaft; l is the length of the crushing shaft; deltaaThe first experimental coefficient is 0.29-0.67; deltabThe value of the second empirical coefficient is 0.31-0.55; deltacThe third empirical coefficient is 0.33-0.71; vaIs the volume of the first crushing chamber; vbIs the volume of the second crushing chamber; vcIs the volume of the third crushing cavity; a is a first empirical constant; b is a second empirical constant; c is a third empirical constant; e is the base number of the natural logarithm; pi is 3.14.
Preferably, the first empirical coefficient δaThe value is 0.33; second empirical coefficient deltabThe value is 0.41; third empirical coefficient deltacThe value is 0.55; the first empirical constant A is 0.119; the second empirical constant B is 0.113; the third empirical constant C is 0.108.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, the three layers of crushing shafts are arranged in the crushing bin, and when the crushed materials in the crushing bin need to be crushed or discharged, the crushing degree and discharge of the crushed materials in the crushing bin can be effectively controlled by controlling the rotating direction of the crushing shafts;
2. the opening degree of a first discharging stop door, the opening degree of a second discharging stop door, the opening degree of a third discharging stop door and the state of a discharging stop door are controlled based on BP neural network adjustment, so that the crushing degree of crushed materials in a crushing bin is controlled;
3. the invention can set the initial rotating speed of the crushing shaft, and then control the crushing shaft based on the BP neural network, and improve the crushing degree of the crushed material in the crushing cavity again.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
As shown in fig. 1, the present invention provides an engineering plastic pulverizing apparatus, the main structure of which comprises a pulverizing bin 100, a first pulverizing chamber, a second pulverizing chamber, a third pulverizing chamber, a first motor 211, a second motor 212, a third motor 213 and a controller 200; wherein the crushing bin 100 has a feed inlet 110 and a discharge outlet, and a discharge gate 170 is provided at the discharge outlet;
the first crushing cavity is communicated with the feed inlet 110, and is also provided with a first discharge hole, a first discharging baffle door 151 is arranged at the first discharging opening, a first weight sensor 141 is arranged at the bottom of the first discharging baffle door 151 and used for monitoring the weight of the crushed materials in the first crushing cavity, a first crushing shaft 121 transversely penetrates through the inside of the first crushing cavity, one end of the first crushing shaft is rotatably supported on the first crushing cavity and penetrates out of the first crushing cavity, the first pulverizing shaft 121 is provided with a double spiral agitating blade, and when the first pulverizing shaft 121 rotates clockwise, for stirring the crushed materials introduced into the first crushing chamber from the feed opening 110, when the first crushing shaft 121 is rotated counterclockwise, the bottom plate 131 of the first crushing cavity is arc-shaped, so that the crushed materials can be smoothly discharged from the first crushing cavity, and residues in the first crushing cavity are prevented;
the second crushing cavity is communicated with the first discharge hole, the second crushing cavity is also provided with a second discharge hole, a second discharge stop door 152 is arranged at the second discharge hole, a second weight sensor 142 is arranged at the bottom of the second discharge stop door 152 and used for monitoring the weight of the crushed materials in the second crushing cavity, a second crushing shaft 122 transversely penetrates through the second crushing cavity, one end of the second crushing shaft is rotatably supported on the second crushing cavity and penetrates out of the second crushing cavity, a double-helix stirring blade is arranged on the second crushing shaft 122, the crushed materials entering the second crushing cavity from the first discharge hole are stirred when the second crushing shaft 122 rotates clockwise, the crushed materials in the second crushing cavity are discharged from the second discharge hole when the second crushing shaft 122 rotates anticlockwise, the bottom plate 132 of the second crushing cavity is arc-shaped, and the crushed materials are conveniently and smoothly discharged from the second crushing cavity, preventing residue in the second crushing cavity;
the third crushing cavity is communicated with the second discharge hole, the third crushing cavity is also provided with a third discharge hole, a third discharge stop door 153 is arranged at the third discharge hole, a third weight sensor 143 is arranged at the bottom of the third discharge stop door 153 and used for monitoring the weight of the crushed materials in the third crushing cavity, a third crushing shaft 123 transversely penetrates through the third crushing cavity, one end of the third crushing shaft is rotatably supported on the third crushing cavity and penetrates out of the third crushing cavity, a double-helix stirring blade is arranged on the third crushing shaft 123, when the third crushing shaft 123 rotates clockwise, the third crushing shaft is used for stirring the crushed materials entering the third crushing cavity from the second discharge hole, when the third crushing shaft 123 rotates anticlockwise, the crushed materials in the third crushing cavity are discharged from the third discharge hole, the bottom plate 133 of the third crushing cavity is arc-shaped, the crushed materials can be conveniently and smoothly discharged from the third crushing cavity, preventing residue in the third crushing cavity;
an output shaft of the first motor 211 is connected to the first pulverizing shaft 121, and an acceleration motor 221 is provided between the first motor 211 and the first pulverizing shaft 121, an output shaft of the second motor 212 is connected to the second pulverizing shaft 122, and an acceleration motor 222 is provided between the second motor 212 and the second pulverizing shaft 122, an output shaft of the third motor 213 is connected to the third pulverizing shaft 123, and an acceleration motor 223 is provided between the third motor 213 and the third pulverizing shaft 123,
in another embodiment, the method further comprises: a first rotational speed sensor 231, a second rotational speed sensor 232, and a third rotational speed sensor 233; wherein, a first rotation speed sensor 231 is arranged outside the crushing bin 100 and connected with the first crushing shaft 121 for monitoring the rotation speed of the first crushing shaft 121, a second rotation speed sensor 232 is arranged outside the crushing bin 100 and connected with the second crushing shaft 122 for monitoring the rotation speed of the second crushing shaft 122, and a third rotation speed sensor 233 is arranged outside the crushing bin 100 and connected with the third crushing shaft 123 for monitoring the rotation speed of the third crushing shaft 123.
In another embodiment, the bottom of the pulverizing bin 100 is provided with a plurality of vibrators 160, when the vibrators 160 are turned on, the pulverized material in the pulverizing bin 100 can be shaken off completely, and finally the pulverized material is discharged from the outlet 180.
In another embodiment, controller 200 is electrically coupled to first rotational speed sensor 231, second rotational speed sensor 232, third rotational speed sensor 233, first output shutter 151, second output shutter 152, third output shutter 153, first weight sensor 141, second weight sensor 142, third weight sensor 143, and shutter dump 170 at the same time.
The invention also discloses a control method of the engineering plastic crushing device, which is based on BP neural network control and comprises the following steps:
step one, establishing a BP neural network model.
The BP network system structure adopted by the invention is composed of three layers, wherein the first layer is an input layer, n nodes are provided in total, n detection signals representing the working state of the equipment are correspondingly provided, and the signal parameters are provided by a data preprocessing module. The second layer is a hidden layer, and has m nodes, and is determined by the training process of the network in a self-adaptive mode. The third layer is an output layer, p nodes are provided in total, and the output is determined by the response actually needed by the system.
The mathematical model of the network is:
inputting a vector: x ═ x1,x2,...,xn)T
Intermediate layer vector: y ═ y1,y2,...,ym)T
Outputting a vector: o ═ O1,o2,...,op)T
In the invention, the number of nodes of the input layer is n-6, and the number of nodes of the output layer is p-4. The number m of hidden layer nodes is estimated by the following formula:
the input signal has 6 parameters expressed as: x is the number of1Is a first weight coefficient, x2Is a second weight coefficient, x3Is the third weight coefficient, x4Is the coefficient of rotation, x, of the first crushing shaft5Is the second crushing shaft speed coefficient x6The rotation speed coefficient of the third pulverizing shaft.
The data acquired by the sensors belong to different physical quantities, and the dimensions of the data are different. Therefore, the data needs to be normalized to a number between 0-1 before it is input into the artificial neural network.
Specifically, for a first weight M measured using a first weight sensoraNormalized to obtain a first weight coefficient x1:
Wherein M isa_minAnd Ma_maxRespectively the minimum and maximum weight of the crushed material in the first crushing chamber.
Likewise, a second weight M measured using a second weight sensorbNormalized to obtain a second weight coefficient x2:
Wherein M isb_minAnd Mb_maxRespectively the minimum weight and the maximum weight of the crushing amount in the second crushing cavity.
Third weight M measured using third weight sensorcNormalized to obtain a third weight coefficient x3:
Wherein M isc_minAnd Mc_maxRespectively the minimum weight and the maximum weight of the crushed material in the third crushing chamber.
Measuring the rotation speed omega of the first crushing shaft by using a first rotation speed sensoraNormalized to obtain a first pulverizing shaft speed coefficient x4:
Wherein, ω isa_minAnd ωa_maxRespectively, the maximum value and the minimum value of the rotation speed of the first pulverizing shaft.
The rotation speed omega of the second crushing shaft is measured by using a second rotation speed sensorbNormalized to obtain a second pulverizing shaft speed coefficient x5:
Wherein, ω isb_minAnd ωb_maxRespectively the maximum value and the minimum value of the rotation speed of the second crushing shaft.
Measuring the rotation speed omega of the third crushing shaft by using a third rotation speed sensorcNormalized to obtain a third pulverizing shaft speed coefficient x6:
Wherein, ω isc_minAnd ωc_maxRespectively, the maximum value and the minimum value of the rotation speed of the third pulverizing shaft.
The 4 parameters of the output signal are respectively expressed as: o1Is the first discharge stop opening degree regulating coefficient o2For the second discharge shutter opening degree adjustment coefficient, o3Is the aperture regulating coefficient of the third discharging stop door o4The state is the material discharging shutter.
First discharge stop opening degree regulating coefficient o
1Expressed as the ratio of the opening of the first discharging stop gate in the next sampling period to the set maximum opening of the first discharging stop gate in the current sampling period, namely, in the ith sampling period, the collected opening of the first discharging stop gate is delta
aiOutputting a first discharging stop door opening degree regulating coefficient of the ith sampling period through a BP neural network
Then, the opening degree of the first discharging stop door in the (i + 1) th sampling period is controlled to be delta
a(i+1)To make it satisfy
Opening degree regulating coefficient o of second discharging stop door
2Expressed as the ratio of the opening of the second discharging baffle in the next sampling period to the set maximum opening of the second discharging baffle in the current sampling period, namely, in the ith sampling period, the collected opening of the second discharging baffle is delta
biOutputting a second discharging stop door opening degree regulating coefficient of the ith sampling period through a BP neural network
Then, the opening degree of a second discharging stop door in the (i + 1) th sampling period is controlled to be delta
b(i+1)To make it satisfy
Regulating coefficient o of opening degree of third discharging stop door
3Expressed as the ratio of the opening of the third discharging stop gate in the next sampling period to the set maximum opening of the third discharging stop gate in the current sampling period, namely, in the ith sampling period, the collected opening of the third discharging stop gate is delta
ciOutputting a third discharging stop door opening degree regulating coefficient of the ith sampling period through a BP neural network
Then, the opening degree of a third discharging stop door in the (i + 1) th sampling period is controlled to be delta
c(i+1)To make it satisfy
Discharge door stop state signal o4Is indicated as currentWhen the output value is 0, the current discharging stop door is in a closed state; when the output value is 1, the current discharging stop door is in an open state.
And step two, training the BP neural network.
After the BP neural network node model is established, the training of the BP neural network can be carried out. Obtaining a training sample according to historical experience data of the product, and giving a connection weight w between an input node i and a hidden layer node jijConnection weight w between hidden layer node j and output layer node kjkThreshold value theta of hidden layer node jjThreshold value theta of output layer node kk、wij、wjk、θj、θkAre all random numbers between-1 and 1.
Continuously correcting w in the training processijAnd wjkUntil the system error is less than or equal to the expected error, the training process of the neural network is completed.
As shown in table 1, a set of training samples is given, along with the values of the nodes in the training process.
TABLE 1 training Process node values
And step three, the controller collects operation parameters and inputs the operation parameters into the neural network to obtain an opening coefficient and a discharging stop signal.
The trained artificial neural network is solidified in a chip, so that a hardware circuit has the functions of prediction and intelligent decision making, and intelligent hardware is formed; after the intelligent hardware is powered on and started, the first crushing shaft, the second crushing shaft and the third crushing shaft are started at a preset rotating speed, and then the initial rotating speed is adjusted, namely the initial rotating speed of the first crushing shaft is omegaa0=0.85ωa_preThe initial rotation speed of the second crushing shaft is omegab0=0.93ωb_preThe initial rotation speed of the third crushing shaft is omegac0=0.88ωc_pre。
While measuring a first weight M using a weight sensor
a0Second weight M
b0A third weight M
c0(ii) a Normalizing the parameters to obtain an initial input vector of the BP neural network
Obtaining an initial output vector through operation of a BP neural network
And step four, controlling the opening degrees of the first discharging stop door, the second discharging stop door and the third discharging stop door.
Obtaining an initial output vector
After, can carry out the regulation and control of aperture, adjust first ejection of compact stop gate, second ejection of compact stop gate, third ejection of compact stop gate, make the aperture of first ejection of compact stop gate, second ejection of compact stop gate, third ejection of compact stop gate in next sampling period do respectively:
obtaining a first weight M of an ith sampling period through a sensor
aSecond weight M
bA third weight M
cFirst crushing shaft rotation speed omega
aSecond crushing shaft rotation speed omega
bThird crushing shaftSpeed of rotation omega
cObtaining the input vector of the ith sampling period by formatting
Obtaining an output vector to the ith sampling period through the operation of a BP neural network
Then the aperture of the first ejection of compact stop door, the second ejection of compact stop door, the third ejection of compact stop door is adjusted in control, makes the aperture of first ejection of compact stop door, the second ejection of compact stop door, the third ejection of compact stop door be respectively when the (i + 1) th sampling cycle:
and step five, monitoring the state of the discharge outlet.
Judging the running state of the discharging stop gate in the (i + 1) th cycle according to the rotating speed and weight sampling signals in the (i) th cycle, and outputting a signal
When the discharging shutter is closed, the signal is output
When the material is discharged, the material stop door is opened.
Through the arrangement, the running state of the crushing shaft is detected in real time through the sensor, and the discharge stop door is regulated and controlled by adopting a BP neural network algorithm, so that the crushing device reaches the nearest running state, and the crushing quality is improved.
In another embodiment, the preset rotation speed ω of the first crushing shafta_preIs composed of
Preset rotation speed omega of second crushing shaftb_preIs composed of
Preset rotation speed omega of third crushing shaftc_preIs composed of
In the formula, ζaIs a first correction coefficient; zetabIs a second correction coefficient; zetacIs a third correction coefficient; lambda [ alpha ]aThe number of the first crushing shaft blades; lambda [ alpha ]bThe number of the second crushing shaft blades; lambda [ alpha ]cThe number of the third crushing shaft blades; omegaa_maxThe maximum rotating speed of the first crushing shaft is in rad/min; omegaa_minThe minimum rotating speed of the first crushing shaft is in rad/min; omegab_maxThe maximum rotating speed of the second crushing shaft is in rad/min; omegab_minThe minimum rotation speed of the second crushing shaft is in rad/min; omegac_maxThe maximum rotating speed of the third crushing shaft is in rad/min; omegac_minThe minimum rotating speed of the third crushing shaft is in rad/min; d is the length of the blades on the crushing shaft and the unit is m; l is the length of the crushing shaft and is m; deltaaThe first experimental coefficient is 0.29-0.67; deltabThe value of the second empirical coefficient is 0.31-0.55; deltacThe third empirical coefficient is 0.33-0.71; vaIs the volume of the first crushing chamber and has the unit of m3;VbIs a second crushing cavityVolume of (d) in m3;VcIs the volume of the third crushing cavity and has the unit of m3(ii) a A is a first empirical constant; b is a second empirical constant; c is a third empirical constant; e is the base number of the natural logarithm; pi is 3.14.
In another embodiment, the first empirical factor δaThe value is 0.33; second empirical coefficient deltabThe value is 0.41; third empirical coefficient deltacThe value is 0.55; the first empirical constant A is 0.119; the second empirical constant B is 0.113; the third empirical constant C is 0.108.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.