JPH11104511A - Crushing and pulverizing treatment system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To assure the automatic execution of a crushing or pulverizing treatment to the same extent as the treatment by a skilled operator's manual operation by providing a controller of a crushing and pulverizing treatment system with a control means having a learning function and allowing the control means to learn the operating procedures of the skilled operator. SOLUTION: The controller 20 is provided with the control means 22 having a learning function comprising a neural network or fuzzy neural network, etc., The controller 20 is provided with a correcting means 30 which stores a data base and the know-how, etc., of the skilled operator in order to enable the dealing with the seasonal changes, etc., of supplied bulky wastes. The proper correction of the neural network or fuzzy neural network is made possible by the data supplied from the correcting means 30 or the know-how, etc., of the skilled operator. As a result, the automatic operating accuracy to the same extent as that of the manual operation by the skilled operator is assured.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] The present invention relates to a crushing / crushing processing system. More specifically, the present invention relates to a crushing / crushing system including a control device having a control unit having a learning function.

[0002]

2. Description of the Related Art Conventionally, a crusher or a crusher (hereinafter referred to as a crusher) has been used in the treatment of various and miscellaneous garbage such as used refrigerators and chests, so-called oversized garbage, and scrap processing of scrapped cars. Crushing and pulverizing treatment.

However, in the crushing / pulverizing treatment, as described above, it is necessary to treat various kinds of miscellaneous ones. Therefore, the operation of the crusher is performed by a manual operation by a skilled operator. In other words, the operator monitors the monitor television that images the inlet of the crusher, and at the same time, monitors the instrument that indicates the current value of the motor that drives the crusher and monitors the input amount of oversized garbage. Adjustments are being made. For this reason, the operation of the crusher is a considerable labor for the operator, and the fatigue accumulates with the elapse of the operation time. Therefore, if one operator performs the operation for a long time, the work accuracy may be reduced. In order to avoid such a situation, a method of replacing the work by a plurality of operators has been adopted at present.

[0004] However, due to the recent decrease in the number of young workers, it has become difficult to secure skilled operators. For this reason, the appearance of an oversized garbage automatic treatment system that can be automatically operated has been eagerly sought by those concerned.

In order to improve such circumstances, Japanese Patent Laid-Open No.
No. 276138 discloses that, when a crushed object is sent to a crusher / pulverizer by a supply device and crushed / pulverized, not only the load current of the crusher / pulverizer is detected but also the fluctuation amount of the load current, The layer thickness of the object to be crushed in the apparatus, and the crushing sound level of the crushing and crushing machine are respectively detected, and based on the detected values, by fuzzy inference, so that the load of the crushing and crushing machine is constant. There has been proposed a method for controlling fluctuations in the load of the crusher / pulverizer, which comprises controlling the feeding speed of the crushed object from the supply device to the crusher / pulverizer (see FIG. 7).

[0006] However, according to the fluctuation suppressing method according to the above proposal, although the load on the operator is expected to be reduced somewhat, it is not possible to automate the operation of the oversized refuse treatment system.

[0007]

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned problems in the prior art, and is directed to an automatic crushing / pulverizing processing system for processing an object to be processed such as oversized garbage having various and various properties. It is an object of the present invention to provide a crushing and crushing processing system that can be operated at the same level as a manual operation of a skilled operator.

[0008]

A crushing and crushing system according to the present invention is a crushing and crushing processing system having a crushing function or a crushing function, and a control device having a learning function in a control device of the crushing and crushing processing system. Means for causing the control means to learn the operation procedures of a skilled operator and automatically performing crushing or crushing processing.

More specifically, the crushing and pulverizing processing system includes a conveying means for conveying the object to be processed to the processing system, an input port into which the object conveyed by the conveying means is input, Control means comprising: supply means capable of changing an opening degree supplied to a crushing means or a crushing means for crushing or crushing the object to be processed introduced into the input port; and a driving means for driving the crushing means or the crushing means. Learning, the crushing sound or crushing sound generated during crushing or crushing from at least the crushing means or crushing means as input, the transfer speed of the transfer means, the captured image of the input port, and the opening degree can be changed It is performed using the opening degree of the supply unit and the load of the driving unit, and using the opening degree command value of the supply unit that can change the opening degree and the conveyance speed command value of the conveyance unit as outputs. And wherein the door.

[0010] Alternatively, the crushing / crushing processing system may include a conveying means for conveying the object to be processed to the processing system;
An input port into which the object transferred by the transfer unit is input, and a supply unit capable of changing an opening degree to be supplied to a crushing unit or a crushing unit that crushes or crushes the object input into the input port. And driving means for driving the crushing means or crushing means, learning of the control means, crushing sound or crushing sound generated during crushing or crushing from the crushing means or crushing means, the conveying speed of the conveying means, At least two of the captured image of the input port, the opening of the supply unit whose opening can be changed, and the load of the driving unit are used as inputs, and the opening can be changed as an output. It is characterized by using an opening command value of the supply means and a transfer speed command value of the transfer means.

It is preferable that the crushing / crushing processing system of the present invention further comprises a correction means for correcting the learning content of the control means having the learning function. In the crushing / crushing processing system of the present invention, the learning may be performed off-line.

Here, the transfer means is, for example, a supply conveyor, and the transfer speed is the number of rotations of the supply conveyor. The control means having the learning function is constituted by, for example, a neural network or a fuzzy neural network.

[0013]

Since the crushing and crushing system of the present invention is configured as described above, the automatic operation of the crushing and crushing system can be performed by making the control means of the control device learn the operating procedure of the skilled operator. To the same extent.

According to a preferred embodiment of the present invention including a correction means for correcting the learning content, the control means performs learning corresponding to a change in the property of the workpiece during operation even after the crushing / crushing processing system is installed. Since it can be easily performed, it is easy to cope with a change in the property of the object to be processed.

[0015]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described based on embodiments with reference to the accompanying drawings, but the present invention is not limited to these embodiments.

FIG. 1 is a schematic diagram showing a conventional bulky waste disposal system S 'to which the present invention is applied. In this oversized refuse treatment system S ', as shown in FIG.
The bulky waste inlet 1a of the crusher 1 is imaged by the video camera 10 and is displayed on a monitor television (not clearly shown) in the control room R. The crushing sound generated from the crusher 1 The sound is collected by a sound collecting microphone 12 provided on the side of the control room R and flown from a speaker (not clearly shown) in the control room R, and the conveying speed of the conveying means, for example, the rotation speed and the opening of the supply conveyor 2 are changed. Possible supply means, for example, the opening of the feeder 3, the number of revolutions of the crushing means, for example, the number of revolutions of the crusher, the load of the driving means of the crushing means, for example, the motor load, etc., are instruments provided in the control room R (clearly illustrated). Has not been). Then, the operator comprehensively judges the monitor image, the displayed opening degree, the number of revolutions of the feeder 3, the load of the motor, and the like, and determines the feeder 3.
And the number of revolutions of the supply conveyor 2 are adjusted so that the crusher 1 is operated in an optimum state.

For example, regarding the treatment of oversized refuse from home, the processing time in the crusher 1 differs between the refrigerator and the wooden chest. That is, the processing takes a long time when the refrigerator is put in, whereas the processing takes less time when the wooden chest is put in. Therefore, when the refrigerator is loaded, the transport speed of the supply conveyor 2 is reduced, that is, the rotation speed of the supply conveyor 2 is reduced, while when a wooden chest is loaded, the transport speed of the supply conveyor 2 is increased, Increase the number of rotations of the supply conveyor 2. Further, even in the same refrigerator, if the size is different, the time required for processing is different, and the opening of the feeder 3 needs to be changed. That is, when a large refrigerator is loaded, the opening of the feeder 3 is increased and the transport speed of the supply conveyor 2 is reduced, while when a small refrigerator is loaded, the opening of the feeder 3 is reduced. And the transport speed of the supply conveyor 2 is increased. In addition, since the processing speed is different between a metal product and a plastic product, if a metal sound is heard from a speaker, the metal product is processed, so that it takes a long time to process. Therefore, the transport speed of the supply conveyor 2 is reduced. . Further, when it is recognized from the image on the monitor television that the amount of stay at the inlet 1a has increased, the conveying speed of the supply conveyor 2 is reduced or the feeder is stopped in order to prevent the oversized dust from overflowing from the inlet 1a. 3 is increased.

On the other hand, in the scrap processing in which the pre-crushing processing is performed, the conveying speed of the supply conveyor 2 and the feeder 3 depend on the amount of stay in the inlet 1a and the material to be scrapped.
Is adjusted. For example, when the amount of stay in the inlet 1a increases, the transport speed of the supply conveyor 2 is reduced or the opening of the feeder 3 is increased. When a soft material is supplied, the transport speed of the supply conveyor 2 is increased, and the opening of the feeder 3 is increased.

FIG. 2 shows an oversized refuse treatment system S shown in FIG.
'Shows a state of a preparation stage for automating the'. That is, a neural network (hereinafter abbreviated as NN) or a fuzzy neural network (hereinafter FN)
N) is provided with a control device 20 'having a control means 22 having a learning function composed of
At 0 ', the measurement values input to the instruments provided in the control room R are input in parallel. In this case, the image from the video camera 10 is input to the control device 20 'via the image processing device 24, and the crushing sound from the sound collecting microphone 12 is input to the control device 20' via the audio processing device 26. .

The feeder 3 is controlled by the control means 22.
The opening command value and the rotation speed command value of the supply conveyor 2 are
A comparator 28 provided in the control device 20 'compares the command value with an operator's command value, and the deviation is fed back to the NN or FNN. Then, the control means 22 controls the NN or F so that the deviation becomes zero.
Modify each coefficient of the NN network. This correction work is repeated, for example, about 5000 times. That is,
The learning of the NN or FNN constituting the control means 22 is repeatedly performed. Inputs for this learning include, for example, monitor images, crushing sound, feeder opening, crusher rotation speed,
The motor load and supply conveyor speed are used. In this case, learning may be performed using two or more combinations of the inputs as inputs. For example, a combination of a monitor image and a crushing sound, a combination of a feeder opening and a crusher rotation speed, a combination of a monitor image, a crushing sound and a feeder opening, and a combination of a monitor image, a crushing sound, a feeder opening and a motor load. Combination, combination of monitor image, crushing sound, feeder opening, motor load, supply conveyor speed, combination of monitor image, crushing sound, feeder opening, crusher speed, motor load, supply conveyor speed, etc. May be used.

The learning may be performed online or offline. Here, online learning means performing NN or FNN learning while operating the crusher 1, and offline learning means performing NN or FNN learning separately from the operation of the crusher 1. Say.

Next, each example of the NN and the FNN will be described.

FIG. 3 shows a schematic diagram of the NN, which is a network having a hierarchical structure.
The crushing sound, the feeder opening, the crusher rotation speed, the motor load, and the supply conveyor rotation speed are input, and the feeder opening command value and the supply conveyor rotation speed command value are output from the output side.

FIG. 4 shows a schematic diagram of the FNN. This network has a fuzzy rule structure. When a certain input pattern is given, an output pattern corresponding to the input pattern is obtained through a structure called a fuzzy rule. is there. For example, as shown in FIG. 4, a monitor image, crushing sound, feeder opening, crusher rotation speed,
The motor load and the supply conveyor speed are input, and the feeder opening command value and the supply conveyor speed command value are output from the output side.

As shown in FIG. 5, the membership functions in the FNN are triangular (see (a)), differentiable function (see (b)), and Gaussian basis. (See (c)), a sigmoid function (see (d)) and the like. The modification of the membership function is performed by iterative learning using a back propagation method or the like as in the case of the NN.

FIG. 6 is a diagram showing N which has been learned by the above procedure.
It is the schematic of the oversized garbage automatic processing system S provided with N or FNN. As is apparent from FIG. 6, the oversized garbage automatic processing system S basically excludes portions related to manual operation by an operator in FIG. Further, the control device 20 is provided with a correction means 30 in which a database and know-how of a skilled operator are accumulated in order to cope with a seasonal change of the supplied oversized garbage. The NN or FNN can be appropriately modified by data supplied from the modifying means 30 or know-how of a skilled operator.

As described above, according to this embodiment, the control device 20 is provided with the control means 22 composed of NN or FNN having a learning function, and the NN or FNN is operated by a skilled operator to operate the oversized refuse treatment system S. Since the automatic operation of the oversized refuse disposal system S is performed after learning the points, the oversized refuse disposal system S can be automatically operated on the same level as the manual operation by the skilled operator.
In other words, the oversized refuse treatment system S can be automated. Further, since learning of NN or FNN is automatically performed, troublesome parameter adjustment is not required. Furthermore, since the data is supplied from the database of the correction means 30 to the control means 22, it is possible to cope with a change in the type of oversized garbage only by changing the supplied data. In addition, even for a bulky waste disposal system S in a business office where there is no skilled operator, automatic operation can be performed only by supplying data from a database from a similar bulky waste disposal system S.

As described above, the present invention has been described based on the embodiments. However, the present invention is not limited to only the embodiments, and various modifications can be made. For example, the present invention is applicable not only to a bulky waste treatment system but also to various systems using a crusher or a crusher.

[0029]

As described in detail above, according to the present invention,
The control device is provided with a control means having a learning function composed of NN or FNN, and the operation of the crushing / crushing processing system is automatically performed after a trained operator learns the operating procedure of the crushing / crushing processing system by a skilled operator. Therefore, an excellent effect is obtained in that the automatic operation of the crushing / crushing processing system can be performed while ensuring the same operation accuracy as the manual operation by the skilled operator. That is, an excellent effect that the crushing / crushing processing system can not be automated can be obtained. Moreover, since learning of the control means composed of the NN or FNN is automatically performed,
There is also obtained an effect that troublesome parameter adjustment becomes unnecessary.

In a preferred embodiment of the present invention,
Since the NN or FNN is corrected by supplying data from the database of the correction means to the control means, the effect of coping with a change in the type of garbage can be obtained only by changing the supplied data. Further, according to this preferred embodiment, a similar crushing / crushing system is used for a crushing / crushing processing system in a business site where there is no skilled operator.
An excellent effect that automatic operation becomes possible only by supplying data from the database from the crushing processing system can be obtained.

[Brief description of the drawings]

FIG. 1 is a block diagram of a conventional configuration of a bulky waste disposal system to which the present invention is applied.

FIG. 2 is a block diagram showing a state in which the control means learns the operation procedure of a skilled operator in the oversized refuse disposal system having the conventional configuration.

FIG. 3 is a schematic diagram of an example of a neural network constituting the control means of the present invention.

FIG. 4 is a schematic diagram of an example of a fuzzy neural network constituting the control means of the present invention.

5A and 5B are graphs of membership functions used in the fuzzy neural network, wherein FIG. 5A shows a triangular function, FIG. 5B shows a differentiable function type, and FIG. Indicates a Gaussian basis type, and (d) indicates a sigmoid function.

FIG. 6 is a block diagram showing a state where the present invention is applied to the conventional oversized refuse treatment system of FIG. 1;

FIG. 7 is a conceptual diagram related to a control method disclosed in JP-A-8-276138.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Crusher 1a Input port 2 Supply conveyor 3 Feeder 10 Video camera 12 Sound collecting microphone 20 Control device 22 Control means having a learning function 24 Image processing device 26 Audio processing device 28 Comparator 30 Correction means S Crushing / crushing processing system

 ──────────────────────────────────────────────────続 き Continued on the front page (72) Inventor Shiro Nakabayashi 2-4-1, Hamamatsucho, Minato-ku, Tokyo World Trade Center Building Kawasaki Heavy Industries, Ltd., Tokyo Head Office (72) Inventor Takao Kanamaru Futatsuka, Noda-shi, Chiba 118 Kawasaki Heavy Industries, Ltd.Noda Factory (72) Inventor Yoshiaki Kato 1780, Yachiyo-Kamitakano, Chiba Prefecture Kawasaki Heavy Industries, Ltd.Yachiyo Factory

Claims (7)

[Claims] 1. A crusher having a crushing function or a crushing function.
A crushing processing system, wherein the control device of the crushing / crushing processing system includes a control means having a learning function, and the control means learns an operation procedure of a skilled operator to automatically perform the crushing or crushing processing. Characterized crushing and crushing processing system. 2. The crushing and pulverizing processing system includes: a conveying unit that conveys the object to be processed to the processing system; an input port into which the object conveyed by the conveying unit is input; A crushing means for crushing or crushing the input object to be processed or a supply means capable of changing an opening degree to be supplied to the crushing means; and a driving means for driving the crushing means or the crushing means. Crushing sound or crushing sound generated during crushing or crushing from at least the crushing means or crushing means as input, the transfer speed of the transfer means, the captured image of the input port, and the supply means whose opening degree can be changed The opening degree, using the load of the driving means, as an output, the opening degree can be changed using the opening command value of the supply means and the transfer speed command value of the conveying means, characterized in that it is made using You Crushing and grinding processing system of claim 1, wherein. 3. The crushing and pulverizing processing system includes: a conveying unit configured to convey the object to be processed to the processing system; an input port into which the object conveyed by the conveying unit is input; A crushing means for crushing or crushing the input object to be processed or a supply means capable of changing an opening degree to be supplied to the crushing means; and a driving means for driving the crushing means or the crushing means. A crushing sound or a crushing sound generated during crushing or crushing from the crushing means or the crushing means, a conveying speed of the conveying means, a captured image of the inlet, an opening degree of the supply means whose opening degree can be changed, and the driving means Using at least two or more combinations of the loads as inputs, and using as outputs an opening command value of the supply unit whose opening can be changed and a transfer speed command value of the transfer unit. Crushing and grinding processing system according to claim 1, characterized in that it is. 4. The crushing / crushing processing system according to claim 1, further comprising a correction unit for correcting the learning content of the control unit having the learning function. 5. The crushing and crushing system according to claim 2, wherein the transporting means is a supply conveyor, and the transport speed is the number of rotations of the supply conveyor. 6. The crushing / crushing processing system according to claim 2, wherein the learning is performed offline. 7. The control means having the learning function is constituted by a neural network or a fuzzy neural network.
4. The crushing / crushing processing system according to 2 or 3.