TW201518920A - Simulation apparatus of production line - Google Patents

Abstract

To provide a simulation apparatus of a production line that enables efficient simulation. To this end, the simulation apparatus of a production line includes: a data storing function that stores operating data and characteristics data acquired by a data acquiring function; a setting calculation function that uses a model of the production line to calculate setting information on the production line based on the operating data and the characteristics data stored in the data storing function; a model learning function that learns the model of the production line based on the setting information calculated by the setting calculation function; a learned value storing function that stores a learned value for the model learned by the model learning function; and an execution timing management function that causes the setting calculation function, when it calculates setting information, to eliminate time that has no effect on the model so as to shorten the time during which the setting calculation function calculates the setting information to be smaller than the time required for acquiring the operating data and the characteristics data by the data acquiring function.

Description

Production line simulator

The present invention relates to a simulation device for a production line.

Patent Document 1 describes a simulation device for a production line. The simulation device uses data collected by an online series of control systems. This data establishes a corresponding association with the actual time. The simulation device is simulated at the same time as the time required to collect the data.

(previous technical literature) (Patent Literature)

Patent Document 1: Japanese Laid-Open Patent Publication No. 2007-133579

However, the simulation has to be performed many times by changing the program, parameters, and the like. Therefore, it takes a lot of time until all the simulation results are obtained.

The present invention has been made in order to solve the above problems. It is an object of the present invention to provide a simulation apparatus that can efficiently perform a simulated production line.

The simulation device of the production line of the present invention has: a data collection function for collecting operation data of the production line and characteristic data of the production object; and a data storage function for storing operation data and characteristic data collected by the foregoing data collection function; The operation data and the characteristic data saved by the data saving function, the model of the production line is used to calculate the setting calculation function of the setting information related to the production line; and the model of the model of the production line is learned according to the setting information calculated by the setting calculation function a learning function; a learning value saving function of the learning value of the model learned by the model learning function; and a time when the setting calculation function calculates the setting information so that the model has no influence, so that the calculation function is performed due to the foregoing setting The calculation time of the set information caused is shorter than the execution timing management function of the time required for the data collection function to collect the operation data and the characteristic data.

According to the present invention, the calculation time of the setting information is shorter than the time required for the data collection function to collect the operation data and the characteristic data. Therefore, the simulation can be performed efficiently.

1‧‧‧heating furnace

2‧‧‧Rough rolling extension

2a, 5a‧‧‧Work rolls

2b, 5b‧‧‧ reinforcing roller

3‧‧‧ rod heater

4‧‧‧Fine rolling extension inlet side thermometer

5‧‧‧Fine rolling extension

6‧‧‧ Thickness gauge

7‧‧‧ board width meter

8‧‧‧Fine rolling extension exit side thermometer

9‧‧‧Sliding out

10‧‧‧Water injection device

11‧‧‧Winner inlet thermometer

12‧‧‧Winding machine

13‧‧‧Rolling material

14‧‧‧Production line

15‧‧‧Pre-update control function

16‧‧‧ data collection function

17‧‧‧ Execution of timing management function before update

18‧‧‧Set calculation function before update

19‧‧‧Pre-update model learning function

20‧‧‧Pre-update learning value retention function

21‧‧‧Set control function

22‧‧‧Data storage function

22a‧‧‧Data conversion function

22b‧‧‧ event data saving function

23‧‧‧Collection data storage function

24‧‧‧Update control function

25‧‧‧Execution of timing management function after update

25a, 39a‧‧‧ Actual time processing function

25b, 39b‧‧‧ speeding function

26‧‧‧Set calculation function after update

27‧‧‧Updated model learning function

28‧‧‧Renewed learning value retention function

29‧‧‧Online control function

30‧‧‧Online data collection function

31‧‧‧Online execution of timing management functions

32‧‧‧ Online setting calculation function

33‧‧‧Online model learning function

34‧‧‧Online learning value retention function

35‧‧‧Online setting control function

36‧‧‧Offline simulation function

37‧‧‧Offline data storage

38‧‧‧Offline data collection function

39‧‧‧Offline execution of timing management functions

40‧‧‧Offline setting calculation function

41‧‧‧Offline model learning function

42‧‧‧Offline learning value retention function

Fig. 1 is a schematic view showing a production line of a simulation apparatus using a production line according to a first embodiment of the present invention.

Fig. 2 is a block diagram showing a simulation apparatus of a production line according to Embodiment 1 of the present invention.

Figure 3 is a view showing the mold of the production line of the first embodiment of the present invention. A diagram of the timing management function performed after the update of the proposed device.

Fig. 4 is a view for explaining an example of the execution timing shortening performed by the simulation device of the production line according to the first embodiment of the present invention.

Fig. 5 is a view for explaining an example of the execution timing shortening performed by the simulation device of the production line according to the first embodiment of the present invention.

Fig. 6 is a block diagram showing a simulation apparatus of a production line according to a second embodiment of the present invention.

Fig. 7 is a view for explaining an offline execution timing management function of the simulation device of the production line according to the second embodiment of the present invention.

Fig. 8 is a view for explaining the data storage function of the simulation device of the production line according to the third embodiment of the present invention.

Fig. 9 is a view for explaining the data relating to the execution timing and the data required for the setting calculation of the simulation apparatus of the production line of the third embodiment of the present invention.

The form for carrying out the invention will be described below in conjunction with the drawings. In the respective drawings, the same symbols are attached to the same or corresponding parts. The repeated description of this part is simplified or omitted as appropriate.

Embodiment 1

Fig. 1 is a schematic view showing a production line of a simulation apparatus using a production line according to a first embodiment of the present invention.

The production line of Fig. 1 is a hot rolled sheet rolling line. A heating furnace 1 is provided on the most upstream side of the hot rolled sheet rolling line. A rough rolling mill 2 is provided on the downstream side of the heating furnace 1. Rough rolling extension 2 is not shown in the figure Supporting mechanism. The support mechanism supports the work roll 2a and the backup roller 2b. The rotating shaft of the work roll 2a is mounted to an electric motor not shown in the drawing. A rod heater 3 is provided on the downstream side of the rough rolling mill 2.

A finish rolling mill inlet side thermometer 4 is provided on the downstream side of the rod heater 3. A finishing rolling mill 5 is provided on the downstream side of the finish rolling inlet side thermometer 4. The finishing rolling mill 5 has a supporting mechanism not shown. The support mechanism supports the work roll 5a and the reinforcing roll 5b. The rotating shaft of the work roll 5a is mounted to an electric motor not shown.

On the downstream side of the finishing rolling mill 5, a plate thickness gauge 6, a plate width gauge 7, and a finishing mill exit side thermometer 8 are provided. A slide table 9 is provided on the downstream side of the plate thickness gauge 6, the plate width gauge 7, and the finish rolling mill exit side thermometer 8. A water injection device 10 is provided on the upper side and the lower side of the slide table 9. A winder inlet side thermometer 11 is provided on the downstream side of the slide table 9. A winder 12 is provided on the downstream side of the winder inlet side thermometer 11.

In the hot rolled sheet rolling line, the rolled material 13 is fed to the heating furnace 1 in a state of a rectangular plate. The rolled material 13 is heated in the heating furnace 1 to about 1200 °C. Then, the rolled material 13 is subjected to rolling of a plurality of passes by the rough rolling mill 2. At this time, the work roll 2a is rotated by the motor while the rolled material 13 is being held. The reinforcing roller 2b suppresses the deflection of the work roll 2a. As a result, the rolled material 13 becomes a thick rod of a predetermined thickness. Then, the rolled material 13 is induction-heated by the rod heater 3.

Thereafter, the rolled material 13 is calendered by the finish rolling mill 5. At this time, the work roll 5a is rotated by the motor in a state where the rolled material 13 is sandwiched. The reinforcing roller 5b suppresses the deflection of the work roll 5a. Resulting in rolled material 13 becomes a predetermined thickness. Then, the rolled material 13 is conveyed on the slide table 9. At this time, the rolled material 13 is water-cooled by the water injection device 10. Thereafter, the rolled material 13 is taken up by the coiler 12. As a result, a roll product can be formed.

The number of installations of each of the above devices may differ depending on the production line 14. In particular, the number of the bases of the rough rolling mill 2 and the finishing rolling mill 5, the presence or absence of the rod heater 3, and the number of sensors such as thermometers may vary depending on the production line 14.

Next, the simulation device of the production line 14 will be described using FIG.

Fig. 2 is a block diagram showing a simulation apparatus of a production line according to Embodiment 1 of the present invention.

As shown in Fig. 2, in the pre-update control function 15 of the production line 14, the data collection function 16 collects the operation data of the production line 14 and the characteristic data of the production object. The pre-update execution timing management function 17 reads information such as the position and speed of the rolled material 13 in the production line 14. The pre-update execution timing management function 17 can also read information such as the position and speed of the rolled material 13 via the data acquisition function 16. The pre-update execution timing management function 17 determines the timing of the setting control of the rolled material 13 based on information such as the position and speed of the rolled material 13.

The pre-update setting calculation function 18 calculates the necessary setting information based on the operation data and the characteristic data collected by the data collection function 16 at the timing determined by the execution of the timing management function 17 before the update. At this time, the pre-update setting calculation function 18 uses the learning value of the model of the production line 14.

For example, the setting calculation of the finish rolling mill 5 is performed based on the result of the setting calculation of the rough rolling mill 2 at the timing measured by the finish rolling mill inlet side thermometer 4 at the tip end of the rolled material 13 . The timing of the setting calculation of the finishing rolling mill 5 is determined by the time interval during which the rolled material 13 is conveyed. Therefore, the time interval is not necessarily. For example, the time interval is 2 to 3 minutes. The time interval is 30 minutes to several hours. In contrast, even if the setting calculation is longer, it will be completed within 1 second.

The pre-update model learning function 19 learns the model based on the results of the calculation of the settings of the pre-update setting calculation function 18. Specifically, the pre-update model learning function 19 calculates the learning value of the model based on the result of the setting calculation of the pre-update setting calculation function 18. The pre-update learning value retention function 20 maintains the learning value of the model learned by the pre-update model learning function 19.

The setting control function 21 transmits the necessary setting information to the lower controller, the sensor, and the like which are not shown in the figure, based on the result of the setting calculation of the pre-update setting calculation function 18. The lower controller, the sensor, and the like are controlled based on the setting information. At this time, feedback control or the like can be performed using the measured value of the sensor. The production line 14 can be stably operated by this control. As a result, the quality of the product can be ensured over the entire length of the rolled material 13.

The data storage function 22 temporarily stores the data collected by the data collection function 16. The data collection function 23 is used to store the data stored by the data storage function 22. This data is stored in association with the position and actual time of the rolled material 13.

In the post-update control function 24 of the production line 14, the update The post-execution timing management function 25 collects the data stored in the collected data storage function 23 via the data storage function 22 and the data collection function 16. The post-update execution timing management function 25 determines the appropriate execution timing of the set calculation based on the data.

The update setting calculation function 26 performs necessary setting calculation based on the data stored in the collected data storage function 23 at the timing determined by the post-update execution timing management function 25. At this time, the post-update setting calculation function 26 uses the learned value of the model of the production line 14.

The updated model learning function 27 learns the model based on the results of the setting calculation of the post-update setting calculation function 26. Specifically, the updated model learning function 27 calculates the learned value of the model based on the result of the setting calculation of the post-update setting calculation function 26. The updated learning value retention function 28 maintains the learning value of the model learned by the updated model learning function 27.

Next, the third embodiment is used to explain the execution of the sequence management function 25 after the update.

Fig. 3 is a view for explaining the execution of the sequence management function after the update of the simulation device of the production line according to the first embodiment of the present invention.

As shown in FIG. 3, after the update, the execution of the sequence management function 25 includes the actual time processing function 25a and the speedup function 25b. The actual time processing function 25a is selected when the calculation function 26 is set after the update is executed in the actual time. At this time, the actual time processing function 25a sends information related to the execution timing according to the actual time to the post-update setting calculation function 26. High-speed function 25b, when the update is executed at high speed The function 26 is selected. At this time, the high speed function 25b sends information related to the execution timing which is shorter than the timing executed by the actual time processing function 25a to the post-update setting calculation function 26.

Next, an example of the execution timing shortening in the setting calculation will be described using FIG.

Fig. 4 is a view for explaining an example of the execution timing shortening performed by the simulation device of the production line according to the first embodiment of the present invention.

For example, the setting calculation of the finishing rolling mill 5 is performed based on the setting calculation result of the rough rolling mill 2. Therefore, in the setting calculation of the finish rolling mill 5, the order and timing of the execution timing cannot be arbitrarily set.

At this time, the speed increasing function 25b shortens the time between the setting calculation performed on the rolled material 13 and the setting calculation performed on the next rolled material 13. The speed up function 25b gradually performs the shortening. For example, the speed up function 25b causes the timer between setting calculations to be fast forwarded. For example, the speed up function 25b eliminates a certain time between setting calculations.

Next, an example of the execution timing shortening in the dynamic control will be described using FIG.

Fig. 5 is a view for explaining an example of shortening of the execution timing by the simulation device of the production line according to the first embodiment of the present invention.

Dynamic characteristics are not considered in setting calculations. Therefore, the execution of the set calculation can be done in a small number of times. On the other hand, in the dynamic control, the execution of the control calculation is performed many times on the entire length of the rolled material 13.

At this time, in the control of the short time interval in which the execution time interval is several ms to several 10 ms, the effect of shortening the execution timing is affected. limit. For example, in the thickness control and the tension control, the shortening effect is limited. Therefore, for these controls, the speedup function 25b is not selected.

The high speed function 25b is selected when the control is performed in a relatively long time interval such as the coil temperature control. For example, the speed-up function 25b is selected at the time of dynamic control with an interval of about 1 second or more. For example, the speedup function 25b is selected when dynamic control is performed at intervals of several m in distance.

The high speed function 25b is to shorten the time between the execution timings of the dynamic control of the rolled material 13. For example, the high speed function 25b causes the timer between the dynamic controls to be fast forwarded. For example, the high speed function 25b eliminates the fixed time between dynamic controls.

At this time, the high speed function 25b takes into consideration the dynamic characteristics of the dynamic control and the futile time. For example, in the coiling temperature control, the reaction time of the water injection valve of the water injection device 10 includes a futile time and a reaction delay of about 1 second. At this time, it takes about 1 second from the time the opening/closing command is issued to the water injection valve until the water injection valve is opened and closed. Therefore, in order to accurately acquire the data, it is difficult to achieve a shortening of one second or more with respect to the timing from the control command to the execution.

According to the first embodiment described above, the post-update setting calculation function 26 calculates the setting information in a shorter time than the time required for the data collecting function to collect the operating data and the characteristic data. Therefore, the simulation can be performed efficiently. As a result, the function update of the production line 14 can be smoothly performed.

At this time, the time that does not affect the model can be omitted. For example, the production object can be shortened without being processed and cooled. The time of being shipped. For example, it is possible to eliminate the time during which the production object is being transported without being processed and cooled. In such cases, the simulation can be performed efficiently without sacrificing the accuracy of the simulation.

Further, if the production line 14 is controlled by the post-update control function 24, a high quality product can be manufactured. This ensures a competitive advantage in the market.

Embodiment 2

Fig. 6 is a block diagram showing a simulation apparatus of a production line according to a second embodiment of the present invention. The same or equivalent portions as those in the first embodiment are denoted by the same reference numerals, and the description thereof will be omitted.

In the line control function 29 of Fig. 6, the line data collecting function 30 is operated in the same manner as the data collecting function 16 of Fig. 2 . The online execution timing management function 31 has the same operation as the pre-update execution timing management function 17 of FIG. The online setting calculation function 32 has the same operation as the pre-update setting calculation function 18 of Fig. 2 . The online model learning function 33 is operated in the same manner as the pre-update model learning function 19 of Fig. 2 . The online learning value holding function 34 is operated in the same manner as the pre-update learning value holding function 20. The line setting control function 35 is operated in the same manner as the setting control function 21 of Fig. 2 .

The offline simulation function 36 of Fig. 6 has functions similar to those of the online control function 29. The offline simulation function 36 is used when implementing a function that cannot be confirmed by the online series or when developing a function different from the online series.

Offline data storage function 36, offline data storage function 37 The operation is performed in the same manner as the data storage function 22 of Fig. 2 . The offline collection data storage function 38 has the same operation as the collected data storage function 23 of Fig. 2 . The offline execution timing management function 39 has the same operation as the post-update execution timing management function 25 of FIG. The offline setting calculation function 40 is operated in the same manner as the post-update setting calculation function 26 of Fig. 2 . The offline model learning function 41 is operated in the same manner as the updated model learning function 27 of Fig. 2 . The offline learning value holding function 42 has the same operation as the updated learning value holding function 28 of Fig. 2 .

The offline simulation function 36 performs timings that are completely independent of the control of the production line 14. When the offline setting calculation function 40 is executed, the offline model learning function 41 is sometimes not required to be executed. The functions of the offline simulation function 36 are distinguished according to the purpose of the offline simulation. The offline data storage function 37 and the offline data collection function 38 are sometimes shared with the online series.

Next, the offline execution timing management function 39 will be described using FIG.

Fig. 7 is a view for explaining an offline execution timing management function of the simulation device of the production line according to the second embodiment of the present invention.

As shown in Fig. 7, the offline execution timing management function 39 includes an actual time processing function 39a and a high speed function 39b. The actual time processing function 39a is selected when the offline setting calculation function 40 is executed at the actual time. At this time, the actual time processing function 39a sends information related to the execution timing according to the actual time to the offline setting calculation function 40. High-speed function 39b, when performing offline setting calculation function at high speed At 40 o'clock, it was chosen. At this time, the high speed function 39b sends information related to the execution timing which is shorter than the timing executed by the actual time processing function 39a to the offline setting calculation function 40.

According to the second embodiment described above, the offline simulation function 36 calculates setting information different from the setting information required for the control of the production line 14. Therefore, the simulation for confirming the effect or the like of the novel function can be efficiently performed. The results fully validate and apply the novel features.

Embodiment 3

Fig. 8 is a view for explaining the data storage function of the simulation device of the production line according to the third embodiment of the present invention. The same or equivalent portions as those in the first embodiment are denoted by the same reference numerals, and the description thereof will be omitted.

As shown in Fig. 8, the data storage function 22 is provided with a data conversion function 22a and an event data storage function 22b.

The data conversion function 22a converts the data of the collected data storage function 23 into data related to the execution timing of the set calculation and the data required for the calculation. For example, before the update, when there is an actual temperature value that is not used in the setting calculation, the data conversion function 22a converts this into data related to the execution timing of the setting calculation and the data required for the setting calculation. The event data saving function 22b stores the data converted by the data conversion function 22a.

After the update, the sequence management function 25 is executed, and the data related to the execution timing held by the event data storage function 22b is sent to the post-update setting calculation function 26.

Consider the following hundreds of simulations and change the update The model parameters of the calculation function 26 are then set, and then the same simulation is performed again. At this time, at the time of the first calculation, the event data saving function 22b holds the data related to the execution timing and the data required for the setting calculation. Therefore, in the second and subsequent simulations, the data can be used to achieve higher speed.

Next, use Figure 9 to explain the data related to the execution timing and the data required to set the calculation.

Fig. 9 is a view for explaining the data relating to the execution timing and the data required for the setting calculation of the simulation apparatus of the production line of the third embodiment of the present invention.

For example, the timing at which the sensor for detecting the position of the rolled material 13 is turned on is set as the execution timing of the setting calculation. For example, the timing at which the acquisition of the data required for the calculation is completed is set as the execution timing of the setting calculation. At this time, the data conversion function 22a sets the data at the time when the signal of the rolled material 13 is detected to be the data related to the execution timing. The data conversion function 22a sets the data at the time of completion of the acquisition of the data required for the calculation to the data related to the execution timing.

When the data required for the calculation is set to temperature, when the measured value of the temperature exceeds the preset threshold, it is only necessary to make the thermometer start. This threshold can be used in conjunction with the baseline of the updated system. For example, when the threshold value of the updated system is set to 1000 ° C, the time when the measured value of the temperature is 1000 ° C or higher can be set as the time when the thermometer is activated. Data collection can then begin after Ss seconds. At this time, the data conversion function 22a sets the average value of the temperature between Sd seconds to the data required for the setting calculation.

According to the third embodiment described above, even if the processing method of the data collected before and after the update is different, the simulation can be performed efficiently. For example, before the update, when the speed of the rolled material 13 and the measured temperature are stored at intervals of the rolled material 13, the temperature must be measured for each time after the update. At this time, it is only necessary to calculate the time based on the information of speed and distance. Further, even if the units used are different, the unit conversion can be performed by the data conversion function 22a. The converted data can be saved in the event data saving function 22b.

The simulation apparatus of the first embodiment to the third embodiment can be applied to a production line of continuous real estate products such as a thick plate rolling line, a cold rolling and rolling line, a production line of paper, pulp, chemicals, petroleum products, and the like. Further, the simulation apparatus of the first embodiment to the third embodiment can be applied to a production line in which a product is manufactured in batches by an automobile, a mechanism, or the like.

[Industry use possibility]

As described above, the simulation apparatus of the production line of the present invention can be utilized in a system in which simulation can be efficiently performed.

14‧‧‧Production line

15‧‧‧Pre-update control function

16‧‧‧ data collection function

17‧‧‧ Execution of timing management function before update

18‧‧‧Set calculation function before update

19‧‧‧Pre-update model learning function

20‧‧‧Pre-update learning value retention function

21‧‧‧Set control function

22‧‧‧Data storage function

23‧‧‧Collection data storage function

24‧‧‧Update control function

25‧‧‧Execution of timing management function after update

26‧‧‧Set calculation function after update

27‧‧‧Updated model learning function

28‧‧‧Renewed learning value retention function

Claims (6)

A production line simulation device has: a data collection function, collecting operation data of a production line and characteristic data of a production object; a data storage function, storing operation data and characteristic data collected by the foregoing data collection function; setting a calculation function, According to the operation data and characteristic data held by the data saving function, the model of the production line is used to calculate setting information related to the production line; the model learning function learns the production line according to the setting information calculated by the setting calculation function The model; the learning value saving function, the learning value of the model learned by the model learning function; and the execution timing management function, when the setting calculation function calculates the setting information, omitting the time without affecting the model, so that the cause The calculation time of the setting information caused by the foregoing setting calculation function is shorter than the time required for the data collection function to collect the operation data and the characteristic data. The simulation device of the production line described in claim 1 is provided with a setting control function for controlling the production line according to the setting information; and the setting calculation function is based on the operation data and the production object collected by the data collection function. The characteristic data of the object is calculated using the learning value of the model saved by the aforementioned learning value saving function. The setting control function controls the setting information used in the aforementioned production line. The simulation device of the production line according to claim 1, wherein the setting calculation function is based on the operation data and the characteristic data held by the data saving function, and the model of the production line is used to calculate the control required for the production line. The setting information is different setting information. The simulation device of the production line according to any one of claims 1 to 3, wherein the execution timing management function is performed by shortening a time during which the production object is not processed and cooled, but is transported. The calculation time of the setting information caused by the foregoing setting calculation function is shorter than the time required for the data collection function to collect the operation data and the characteristic data. The simulation device of the production line according to any one of claims 1 to 3, wherein the execution timing management function is performed by eliminating the time when the production object is not processed and cooled, but is transported. The calculation time of the setting information caused by the foregoing setting calculation function is shorter than the time required for the data collection function to collect the operation data and the characteristic data. The simulation device of the production line according to any one of claims 1 to 3, further comprising: a data conversion function for converting the operation data and characteristic data held by the data storage function into execution of the setting calculation Timing-related information and the information required to set up the calculation; The event data saving function saves the data converted by the data conversion function; the setting calculation function is based on the execution timing of the data saved by the event data saving function, and is used to collect the operation data and the data collection function. The time required for the characteristic data is shorter, and the data stored in the event data saving function is used for setting calculation.