Turnover machine room feeding control method, device, equipment, medium and product

Abstract

The invention discloses a feeding control method, device and equipment of a dumper room, a medium and a product, and relates to the technical field of feeding control. The method comprises the steps that working data of the dumper room at the current time period are collected; the working data of the current time period comprise the material flow instantaneous quantity on the belt conveyor, the material level height of each stock bin and the working frequency of each vibration feeder; inputting the working data of the current time period into a feeding control model, and outputting the working frequency of each vibration feeder at the next moment; the feeding control model is obtained by training a recurrent neural network; and monitoring the stock bins in real time according to the material level heights of the stock bins collected at all moments, and sending an alarm signal when the stock bins are empty or overflowed. The control precision can be improved, and potential safety hazards are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of feed control, in particular to a dumper room feed control method, device, equipment, medium and product. BACKGROUND

[0002] In the dumper room operation scene of the coal port, the traditional feed control mode relies on workers to manually adjust the vibration feeder frequency according to the belt scale value to maintain the belt conveyor flow stability. However, this mode has significant defects:

[0003] (1) Large labor consumption: manual continuous observation of the belt scale value and constant adjustment of the vibration frequency of 8 vibration feeders are required, which is high in labor intensity.

[0004] (2) Low control accuracy: manual adjustment has a delay, and it is difficult to accurately control the flow within an error of 5%.

[0005] (3) Safety hazards: if the empty or overflow of the silo cannot be found in time, it will affect the production efficiency and even cause safety hazards. SUMMARY

[0006] The purpose of the present application is to provide a dumper room feed control method, device, equipment, medium and product, which can improve the control accuracy and reduce safety hazards.

[0007] To achieve the above purpose, the present application provides the following solutions:

[0008] In a first aspect, the present application provides a dumper room feed control method, comprising:

[0009] Collecting the working data of the current period of the dumper room; the working data of the current period includes the instantaneous amount of the flow on the belt conveyor, the material level height of each silo and the working frequency of each vibration feeder;

[0010] Inputting the working data of the current period into a feed control model to output the working frequency of each vibration feeder at the next time; the feed control model is obtained by training a recurrent neural network;

[0011] Real-time monitoring each silo according to the material level height of each silo collected at each time, and sending an alarm signal when there is an empty or overflow silo.

[0012] Optionally, before collecting the working data of the current period of the dumper room, the dumper room feed control method further comprises:

[0013] Collecting the historical working data of the dumper room;

[0014] Data cleaning and normalization are performed on the historical working data to obtain preprocessed historical working data;

[0015] The historical working data after preprocessing is integrated according to time sequence to obtain a data set;

[0016] The data set is divided into a training set, a validation set and a test set;

[0017] The training set is used to train a recurrent neural network, the validation set is used to adjust hyperparameters of the recurrent neural network during training of the recurrent neural network, and the test set is used to evaluate accuracy of the trained recurrent neural network, thereby obtaining the feeding control model.

[0018] Optionally, the training of the recurrent neural network using the training set specifically comprises:

[0019] During the training of the recurrent neural network using the training set, a mean square error is used as a loss function, and an Adam optimizer is used to update model parameters of the recurrent neural network.

[0020] Optionally, the feeding control method for the tipping floor further comprises:

[0021] The working data collected at each time point is stored in a database to update the data set;

[0022] The test set in the current updated data set is periodically used to test the feeding control model, thereby obtaining an error rate of the feeding control model;

[0023] If the error rate is greater than a set error rate, the training set in the current updated data set is used to train the feeding control model, and the feeding control model with the error rate greater than the set error rate after training is used as a latest feeding control model.

[0024] Optionally, the working data of the current period of the tipping floor is collected, and specifically comprises:

[0025] A belt scale is used to collect instantaneous quantity of a belt feeder in real time;

[0026] A level radar arranged in each silo is used to collect a level height of each silo in real time;

[0027] A frequency sensor of a vibrating feeder is used to collect a working frequency of each vibrating feeder in real time.

[0028] Optionally, when there is an empty silo or a silo with a high level, an alarm signal is sent, and specifically comprises:

[0029] When there is an empty silo or a silo with a high level, an alarm signal is sent to a programmable controller of the belt feeder, and the programmable controller controls the belt feeder to stop after receiving the alarm signal.

[0030] In a second aspect, the present application provides a car dumper room feeding control device, the car dumper room feeding control device applies the car dumper room feeding control method, and the car dumper room feeding control device comprises:

[0031] a data acquisition module, configured to acquire working data of a current period of the car dumper room; the working data of the current period comprises instantaneous flow on a belt conveyor, stock level height of each stock bin, and working frequency of each vibrating feeder;

[0032] a feeding control module, configured to input the working data of the current period into a feeding control model, and output working frequency of each vibrating feeder at a next time; the feeding control model is obtained by training a recurrent neural network;

[0033] a stock bin monitoring module, configured to monitor each stock bin in real time according to the stock level height of each stock bin acquired at each time, and send an alarm signal when there is an empty stock bin or a stock bin with overflowing material.

[0034] In a third aspect, the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the car dumper room feeding control method in any one of the above.

[0035] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the car dumper room feeding control method in any one of the above.

[0036] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the steps of the car dumper room feeding control method in any one of the above.

[0037] According to the embodiments of the present application, the following technical effects are achieved:

[0038] The present application provides a car dumper room feeding control method, device, equipment, medium and product, a recurrent neural network (RNN) is trained to obtain a feeding control model, working data of a current period is input into the feeding control model, and working frequency of each vibrating feeder at a next time is output, thereby solving the problem of delay caused by manual adjustment, improving control efficiency and control accuracy, and enabling the situation of empty stock bin or stock bin with overflowing material to be understood in time, and reducing safety hazards. BRIEF DESCRIPTION OF DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0040] Figure 1 A flowchart of a feeding control method of a tumbler room provided by an embodiment of the present application is shown in the figure.

[0041] Figure 2 An input-output diagram of a feeding control model provided by an embodiment of the present application is shown in the figure.

[0042] Figure 3 A functional module diagram of a feeding control device of a tumbler room provided by an embodiment of the present application is shown in the figure.

[0043] Figure 4 A structural diagram of a feeding control device of a tumbler room provided by another embodiment of the present application is shown in the figure.

[0044] Figure 5 A structural diagram of a computer device provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0045] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0046] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments.

[0047] In an exemplary embodiment, the present application provides a feeding control method of a tumbler room, as shown in the figure. Figure 1 The feeding control method of the tumbler room includes steps 101-103.

[0048] Step 101: collecting working data of the current period of the tumbler room; the working data of the current period includes instantaneous amount of material flow on the belt conveyor, material level height of each material bin and working frequency of each vibrating feeder.

[0049] Step 102: inputting the working data of the current period into a feeding control model to output working frequency of each vibrating feeder at the next time; the feeding control model is obtained by training a recurrent neural network.

[0050] Step 103: Real-time monitoring of each silo according to the material level height of each silo collected at each time, and sending an alarm signal when there is an empty silo or a silo.

[0051] For example, as shown in Figure 2 the working data of the current period is the working data of the period from time T1 to time Tn, and the vibration feeder frequency Tn+1 is the working frequency of the vibration feeder at the next time of time Tn.

[0052] In an exemplary embodiment, before step 101, the car dumper room feeding control method further comprises steps 201-205.

[0053] Step 201: Collecting historical working data of the car dumper room.

[0054] Step 202: Data cleaning and normalization of the historical working data to obtain preprocessed historical working data.

[0055] If the on-site historical working data, the data collection is completed according to the on-site situation (belt scale, material level sensor, frequency sensor), and at least one week of data is collected.

[0056] Data cleaning includes removing outliers and noise in collected data, such as correcting or deleting belt scale values or material level values that deviate significantly from the normal range, to ensure data accuracy.

[0057] Data normalization includes normalizing input data (material flow instantaneous quantity, material level height, working frequency) of different ranges to the interval of 0-1 to facilitate RNN processing. The formula is: Data normalization is performed, where X is the original data, Xmin is the minimum value of this type of data, Xmax is the maximum value of this type of data, and X' is the data after normalization.

[0058] Step 203: Integrating the preprocessed historical working data according to the time sequence to obtain a data set.

[0059] Step 204: Dividing the data set into a training set (about 80%), a validation set (about 10%), and a test set (about 10%), and storing it in a database for model training and real-time inference.

[0060] Step 205: Training a recurrent neural network using the training set, using the validation set to check the model generalization accuracy during the training of the recurrent neural network and adjust the recurrent neural network hyperparameters, and using the test set to evaluate the accuracy of the trained recurrent neural network to obtain the feeding control model.

[0061] The recurrent neural network comprises an input layer, a hidden layer and an output layer, the input layer is used to receive the processed belt scale material flow data, the silo inventory data and the vibration feeder frequency data, the hidden layer is used to adjust the number of neurons according to the actual effect, and the output layer outputs the frequency value to which each vibration feeder needs to be adjusted. Specifically, the input features of the input layer include the current belt conveyor material flow instantaneous quantity, the inventory heights of the four silos and the current frequencies of the eight vibration feeders, a total of 1+4+8=13 features, and the input data dimension of each time step is 13; 2 layers of hidden layers are selected, each layer has 32 neurons, and a tanh activation function or a ReLU activation function is used to enhance the nonlinear expression ability of the model; the output layer outputs the working frequencies to which the eight vibration feeders need to be adjusted, the output dimension is 8, and the linear activation function is used for the output layer. One silo is configured with two vibration feeders.

[0062] The recurrent neural network is trained by using the training set, and specifically includes: in the process of training the recurrent neural network by using the training set, the model parameters are continuously adjusted, so that the frequency value output by the RNN can effectively control the material flow in the target range, the mean square error (MSE) is used as the loss function, and the Adam optimizer is used to update the model parameters of the recurrent neural network.

[0063] The mean square error is specifically the mean square error between the output of the recurrent neural network and the actual target working frequency. The Adam optimizer is used to update the model parameters of the recurrent neural network according to the loss value, and the model performance is evaluated on the validation set after a certain number of training (such as 10 rounds), and the changes of the loss value and the material flow control error are observed.

[0064] Hyperparameter adjustment: through the evaluation on the validation set, the hyperparameters of the model are adjusted, such as the number of hidden layer neurons, the learning rate, the number of training rounds, etc. For example, if the feeding control model appears overfitting (the loss value continuously decreases on the training set, but increases on the validation set) on the validation set, the number of hidden layer neurons can be reduced or the regularization term can be increased.

[0065] The trained model is finally evaluated by using the test set, whether the material flow control error rate is within 5% or not, and the accuracy and response time of the alarm system in the simulation of empty silo and silo overflow are calculated.

[0066] In an exemplary embodiment, the feeding control method of the tripper house further comprises steps 301-303.

[0067] Step 301: store the collected working data at each time in the database to update the data set.

[0068] Step 302: periodically test the feeding control model using the test set in the current updated data set to obtain the error rate of the feeding control model.

[0069] Step 303: if the error rate is greater than the set error rate, train the feeding control model using the training set in the current updated data set, and apply the feeding control model with a training error rate greater than the set error rate as the latest feeding control model. That is, if the error rate does not meet the requirements, optimize the feeding control model structure (such as adding a hidden layer, adjusting the number of neurons) or the training parameters (such as the learning rate, the number of training rounds).

[0070] Collect the working data of the current period of the tripper room, specifically including:

[0071] Real-time collection of instantaneous quantities on the belt feeder using belt scales.

[0072] Real-time collection of the material level height of each silo using the material level radar installed in each silo.

[0073] Real-time collection of the working frequency of each vibrating feeder using the vibrating feeder frequency sensor.

[0074] According to the data of the material level radar, set the threshold values of empty silos and overflowing silos. When the material level reaches or exceeds the threshold value, trigger the alarm system and send an alarm signal to notify relevant personnel through audible and visual alarms or messages.

[0075] When there is an empty or overflowing silo, an alarm signal is sent, specifically including: when there is an empty or overflowing silo, an alarm signal is sent to the Programmable Controllers (PLC) of the belt feeder, and the PLC controls the belt feeder to stop after receiving the alarm signal. The PLC is used to control the belt feeder and the vibrating feeder.

[0076] The present application automatically adjusts the vibrating feeder frequency through the feeding control model, stabilizes the belt feeder flow at a set value (such as 6000t / h), and the error is not more than 5%. Real-time monitoring of the silo material level, timely alarm when there is an empty or overflowing silo, and sending an alarm signal to the PLC for control to stop, can timely control the empty or overflowing silo situation and reduce safety hazards.

[0077] The beneficial effects of the present application are as follows:

[0078] (1) Automation and precise control: through the feeding control model to automatically adjust the vibrating feeder frequency, replacing manual operation, realizing stable control of the material flow, the error can be controlled within 5%, improving the control precision and production efficiency.

[0079] (2) Real-time monitoring and safety assurance: Real-time monitoring of the material level in the silo, timely detection of empty or overflowing silos and alarm, and transmission of the alarm signal to the PLC for control to stop, effectively avoiding safety hazards and ensuring production safety.

[0080] (3) Data-driven optimization: Through the collection, processing and model training of historical data, the model performance is continuously optimized, so that the system can adapt to different production conditions and improve the reliability and stability of the system.

[0081] Based on the same inventive concept, the embodiments of the present application also provide a dumper room feeding control device for implementing the above-mentioned dumper room feeding control method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more dumper room feeding control device embodiments provided below can be referred to the limitations of the dumper room feeding control method in the foregoing, which will not be repeated here.

[0082] In one exemplary embodiment, as shown in Figure 3 A dumper room feeding control device is provided, comprising:

[0083] A data acquisition module for acquiring working data of the current period of the dumper room; the working data of the current period includes the instantaneous amount of material flow on the belt conveyor, the material level height of each silo, and the working frequency of each vibrating feeder.

[0084] A feeding control module for inputting the working data of the current period into a feeding control model and outputting the working frequency of each vibrating feeder at the next time; the feeding control model is obtained by training a recurrent neural network.

[0085] A silo monitoring module for real-time monitoring of each silo according to the material level height of each silo collected at each time, and sending an alarm signal when there is an empty or overflowing silo.

[0086] The implementation plan of the dumper room feeding control device of the present application includes the following four stages.

[0087] First stage: complete data acquisition (belt scale, material level sensor, frequency sensor) according to the field situation, collect at least one week of data, or if there is historical data, it can be used directly.

[0088] Second stage: based on the collected data, perform data cleaning, normalization and other preprocessing work, build an RNN model framework, and complete the preliminary training and hyperparameter adjustment of the model.

[0089] Third stage: optimize and improve the RNN model, test it in a small range in the actual production environment, further optimize the RNN model and system parameters according to the test results, and obtain the feeding control model.

[0090] The fourth stage: fully deploy the feeding control model to the feeding system, train the relevant staff, and ensure the stable operation and daily maintenance of the system.

[0091] In an exemplary embodiment, as shown in Figure 4 A tipping floor feeding control device is provided, which has an architecture of a collection layer (data collection layer), a data processing layer, a model layer, and an application control layer, Figure 4 The structure relationship between each layer is given.

[0092] The data collection layer includes a belt feeder (BF) belt scale, a material level sensor, and a vibrating feeder frequency sensor.

[0093] The present application measures the instantaneous amount of material flow on the belt feeder in real time through the high-precision belt scale installed on the BF line, and transmits the data to the data processing layer.

[0094] The material level sensor: a material level radar is arranged in each bin to monitor the material level height in the bin in real time, and the data is transmitted to the data processing layer.

[0095] The vibrating feeder frequency sensor obtains the working frequency of the current vibrating feeder.

[0096] The data processing layer is used for data cleaning, data normalization, data set division, and data integration and storage of the collected historical working data.

[0097] The model layer is used for RNN construction, training evaluation and optimization.

[0098] The application control layer is used to automatically adjust the working frequency of the vibrating feeder according to the working frequency of the vibrating feeder output by the feeding control model, to realize precise control of the material flow.

[0099] The application control layer includes an alarm module, which sets the threshold values of empty bins and overflowing bins according to the data of the material level sensor. When the material level reaches or exceeds the threshold value, the alarm system is triggered, and the relevant staff is notified through sound and light alarm or message sending.

[0100] The application control layer is also used for PLC control, which specifically includes: transmitting the working frequency of each vibrating feeder output by the feeding control model and the alarm signal to the PLC for control through the OPC communication protocol.

[0101] In an exemplary embodiment, a computer device is provided, which can be a server or a terminal, and its internal structure diagram can be as shown in Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the feeding control data of the tipping room. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with the terminal outside through the network connection. The computer program is executed by the processor to realize a tipping room feeding control method.

[0102] Those skilled in the art can understand that, Figure 5 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps in each of the above method embodiments.

[0103] In an exemplary embodiment, a computer readable storage medium is provided, storing a computer program, which is executed by a processor to realize the steps in each of the above method embodiments.

[0104] In an exemplary embodiment, a computer program product is provided, including a computer program, which is executed by a processor to realize the steps in each of the above method embodiments.

[0105] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0106] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, databases or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0107] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general processor, a central processing unit, a graphics processing unit, a digital signal processor, a data processing logic of programmable logic, etc., without being limited thereto.

[0108] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combinations of the technical features do not exist contradictory, they should be considered as the scope of the present application.

[0109] The principles and implementation modes of the present application are described by applying specific examples in the present application. The above-mentioned embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed. In conclusion, the content of the present application should not be understood as a limitation.

Claims

1. A feeding control method for a dumper room, characterized in that: The feeding control method of the dumper room includes: Collect the working data of the dumper room during the current period; the working data during the current period includes the instantaneous flow of material on the belt conveyor, the material level height of each silo and the working frequency of each vibrating feeder; Inputting the working data of the current period into the feeding control model and outputting the working frequency of each vibrating feeder at the next moment; the feeding control model is obtained by training a recurrent neural network; The system monitors the material level of each silo in real time based on the material level collected at each moment, and sends an alarm signal when a silo is empty or overflowing.

2. The feeding control method for the dumper room according to claim 1, characterized in that: Before collecting the working data of the current period of the dumper room, the feeding control method of the dumper room further includes: Collecting historical working data of the dumping room; Performing data cleaning and normalization on the historical work data to obtain the pre-processed historical work data; Integrating the pre-processed historical work data according to time series to obtain a data set; Dividing the dataset into a training set, a validation set, and a test set; The training set is used to train the recurrent neural network, the validation set is used to adjust the recurrent neural network hyperparameters during the training of the recurrent neural network, and the test set is used to evaluate the accuracy of the recurrent neural network after training to obtain the feeding control model.

3. The feeding control method for the dumper room according to claim 2, characterized in that: The adopting of the training set to train the recurrent neural network specifically includes: In the process of training the recurrent neural network using the training set, the mean square error is used as the loss function, and the Adam optimizer is used to update the model parameters of the recurrent neural network.

4. The feeding control method for the dumper room according to claim 2, characterized in that: The feeding control method for the dumper room further comprises: Storing the collected working data at each moment into a database to update the data set; Regularly test the feed control model using the test set in the current updated data set to obtain the error rate of the feed control model; If the error rate is greater than the set error rate, the feeding control model is trained using the training set in the current updated data set, and the feeding control model with a trained error rate greater than the set error rate is applied as the latest feeding control model.

5. The feeding control method for a dumper room according to claim 1, characterized in that: Collect the working data of the dumper room during the current period, including: Use belt scale to collect instantaneous amount of material flow on belt conveyor in real time; The material level radar installed in each silo is used to collect the material level height of each silo in real time; A vibration feeder frequency sensor is used to collect the operating frequency of each vibration feeder in real time.

6. The feeding control method for a dumper room according to claim 1, characterized in that: When there is a silo empty or overflowing, an alarm signal is sent, including: When the silo is empty or overflowing, an alarm signal is sent to the programmable controller of the belt conveyor. After receiving the alarm signal, the programmable controller controls the belt conveyor to stop.

7. A feeding control device for a dumper room, characterized in that: The feeding control device for the dumper room applies the feeding control method for the dumper room according to any one of claims 1 to 6, and the feeding control device for the dumper room comprises: The data acquisition module is used to collect the working data of the dumper room during the current period; the working data during the current period includes the instantaneous amount of material flow on the belt conveyor, the material level height of each silo and the working frequency of each vibrating feeder; A feeding control module is used to input the working data of the current period into a feeding control model and output the working frequency of each vibrating feeder at the next moment; the feeding control model is obtained by training a recurrent neural network; The silo monitoring module is used to monitor each silo in real time based on the material level height of each silo collected at each moment, and send an alarm signal when a silo is empty or overflowing.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the feed control method for a dumper room according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the feeding control method for the dumper room according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the feeding control method for the dumper room according to any one of claims 1 to 6 is implemented.

Images