JPH07290125A - Method for scheduling physical distribution in rolling mill - Google Patents

Abstract

PURPOSE:To control such physical distribution of rolling slabs within processes that enables decision of the optimum rolling order and charging order in a heating furnace. CONSTITUTION:In a rolling process consisting of plural heating furnaces and rolling mills, the information of slabs to be rolled is inputted so as to decide the charging furnace and the rolling order of the slabs, the slabs are then sorted by the width and the like, and the restrictive rolling conditions of the slabs are then represented in matrix. In addition, an evaluation value for difficulty in rolling is preliminarily determined; the number of a charging heating furnace and the rolling order satisfying restrictive conditions of each slab are set in an gene individual; retrieval is made by a genetic algorithm; evaluation is made by such means as the difficulty in rolling, extraction time from the heating furnace and fuel consumption; and the optimum charging furnace and the rolling order are thereby simultaneously decided. Thus, it is possible to decide charging time, extracting time, charging furnace and rolling order, based on their quantitative evaluation; and the optimum physical distribution can be implemented. As a result, improvement in productivity, reduction in cost and stability in quality can be realized.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a distribution system for a rolling process such as a hot rolling mill, and to a method for controlling the distribution of rolling slabs in the process.

[0002]

2. Description of the Related Art When determining the treatment sequence and treatment time in a hot rolling process of a slab carried from an upper process (a continuous casting process or a slab yard placed after that), the steel type, width, and Regarding the attributes such as thickness and temperature, there are many restrictions on rolling and restrictions on heating, and these are arranged as many operation restrictions. Attempts have been made using AI technology to automatically determine the rolling sequence and charging furnace to comply with those rules, but at present it is still insufficient. Attempts have also been made to determine the rolling order from the attributes of two consecutive slabs.

In addition, the slab charging and heating furnace is often determined based on the experience of the operator.

[0004]

As described above, according to the conventional method, In order determination that considers only the attributes of two consecutive slabs (relative position constraint), the constraints on the rolling position of the slab are
(Absolute position constraint: Specified for rolling order after roll exchange for a slab) cannot be satisfied.

2. Consistency between heating furnace capacity and rolling mill capacity (matching extraction time from heating furnace with rolling pitch, rolling order and heating furnace charging order with fuel cost, and difficulty of rolling) is considered. There was a problem saying no.

Japanese Patent Application No. 05-1010 previously filed
In the technology of No. 05, in order to solve the above-mentioned problems, in determining the rolling order, not only the relative position constraint at the time of rolling until now, but also the absolute position constraint is taken into consideration. By introducing the constraint condition formula and the evaluation function related to the required fuel, the rolling order is determined, and then the distribution of the heating furnace is searched. But at this time,
In some cases, the optimal solution was not reached, and the solution remained only the local optimal solution.

The present method solves the problems of Japanese Patent Application No. 05-101005, and makes it possible to determine the optimum rolling order and charging order of the heating furnace that are consistent with the capabilities of the heating furnace and rolling mill. It is an object to provide a logistics scheduling method for a hot rolling mill.

[0008]

[Means for Solving the Problems] In a rolling process composed of a plurality of heating furnaces and rolling mills, in order to determine the charging furnace of material slabs and the rolling order, the material slab information to be rolled is input. The material slabs are sorted by width and the like, then the rolling constraint conditions of the material slabs are expressed in a matrix, and the evaluation value regarding the difficulty of rolling is obtained, and the charging heating furnace number and constraint conditions of each slab are calculated. Set the rolling order to be satisfied for each gene individual, and search with a genetic algorithm,
The problem is solved by determining the optimum charging furnace and rolling sequence at the same time by evaluating the difficulty of rolling, the extraction time of the heating furnace, the fuel consumption, etc.

Further, in this scheduling method, the individual expression of a gene is defined as a furnace number to be heated and a slab number to be rolled, in which two symbols having the same symbol length as the number of slabs to be scheduled are connected. From the solution candidates, multiple individuals that will become the next solution candidate are generated by crossing or mutation, and the solution is further improved by local search, and the solution candidates are individually used by using evaluation functions such as rolling difficulty, extraction time, and fuel. This is solved by determining the optimum charging furnace and rolling sequence by repeating the procedure of selecting, and then returning to the generation of solution candidates by crossing and mutation.

[0010]

Next, the present invention will be described with reference to the drawings. The structure of the hot rolling mill is shown in FIG.

The slab placed in the slab storage area 201 or the slab carried by the freight car 202 is placed on the table 203 in front of the heating furnace, and the heating furnace 204 is composed of three furnaces.
Is charged to. At this time, the charging slab (cold pieces depending on the temperature,
An appropriate furnace is determined and charged (for hot pieces, etc.). The slab in the heating furnace is heated according to the charging slab temperature, given the in-furnace time (time spent in the heating furnace) and the extraction temperature. The slab that has reached the extraction temperature according to the schedule is extracted from the heating furnace after waiting for the time interval necessary for the previous extraction slab and rolling, and is rolled by VSB (slab width control rolling mill), rough rolling mill 206, and finish rolling mill 207. Then, it is water-cooled by an ROT (cooling table) 208 and wound by a coiler 209. The manufactured coils are used for product storage 2
It is transported to 10.

FIG. 3 shows the hardware configuration implemented by the scheduling method used for controlling the physical distribution of this equipment, and FIG. 1 shows the configuration of the processing (software in this example) of this scheduling method.

In this scheduling method, by the processing shown in the following first to sixth steps,
Approximately 80 to 150 slabs are rolled and the charging furnace is determined.

Step 1: keyboard 3 in 101
03, slab information is input by file transfer via the mouse 305 or the network 304. Table 1 below shows an example of slab attribute information.

[0015]

[Table 1]

In step 2: 102, the arrangement order of the input slab attribute information data is sorted for some attributes. For example, sort in order of increasing width. The order of this result is the slab number used in the rolling constraint matrix and the like thereafter.

Step 3: Preprocessing of rolling order calculation is performed.

In step 103, a rolling constraint matrix is obtained for the material slabs sorted in step 2 from the operation rule (rolling constraint) and the slab arrival time. It is an absolute position constraint matrix A that represents the constraint of the absolute position of the rolling sequence (the range of the rolling sequence is specified for each slab, for example, from 1st to 8th), and the relative position that represents the constraint of the relative position of the front and rear slabs. A relative position constraint matrix R representing constraints (specifying that slab 2 can be rolled but slab 3 cannot be rolled after slab 1) is generated.

[0019]

[Equation 1]

In the rolling evaluation value matrix calculating unit 104, an evaluation value matrix e showing the difficulty of rolling two slabs which are continuously rolled.
Generate [i] [j]. It can be expressed by the amount of transition such as width and thickness.

[0021]

[Equation 2]

Step 4: In the determination of the rolling order and charging furnace by GA (genetic algorithm), the genetic algorithm is used to search the rolling order of the input slab and the charging heating furnace. The flow of the genetic algorithm is shown in FIG.

First, corresponding to the generation of the initial population 401 of FIG. 4, at 105, a schedule group in which the rolling order of the material slab and the charging heating furnace is set is generated. There, the rolling order and charging furnace are set at the same time. The rolling order is selected from the feasible solutions that satisfy the rolling constraints, and the charging furnace is set using random numbers or operating work standards.

First, the expression of the gene individual used in the solution is determined as follows. That is, an individual is formed by connecting two symbol strings (α and β, respectively) having a length equal to the number of slabs, and α _i : S _i is the furnace number for heating β _{i is} the slab number for the i-th rolling. . FIG. 5 shows an example of gene individuals.

Here, the partial symbol string α representing the furnace number is randomly generated, for example. In addition, the partial symbol string β representing the rolling order is generated using an executable rolling order generation algorithm described later. At that time, the same rolling order is included in the individual group.

In 106, the schedule group (solution candidates) of the next generation is changed from the initial schedule group (set of solution candidates).
To generate. Therefore, the following genetic operators are used. The following two genetic operators are used.

(1) Crossover: (402 in FIG. 4)
Process) The schedules (individuals) are randomly assembled, the decomposition positions are selected in the part corresponding to the partial symbol string α representing the furnace number (the number of decomposition positions is one or more), and they are exchanged with each other with a preset probability pc. To do. The original schedule (individual) is left as it is. FIG. 6 shows an example of crossover.

(2) Mutation: (40 in FIG. 4)
Processing of 3) For the partial symbol string α that represents the reactor number, each symbol (gene)
, With a probability p _{m, heat} , randomly change to another.

For the partial symbol string β representing the rolling order,
The rolling order is changed with the probability p _{m, press} . At this time, an exchange pair generation algorithm described later is used. FIG. 7 shows an example of mutation.

In 107, the local search method is applied with the schedule represented by the individual as the initial schedule, and the obtained schedule is improved (process 404 in FIG. 4).

In the local search, the rolling order or the vicinity of the charging furnace is searched and searched for the feasible schedule.

The vicinity of the rolling order is a set of schedules having the same heating furnace distribution but different rolling order at only one place.

The vicinity of the heating and charging furnace is a set of schedules in which the rolling order is the same but the charging furnace of the heating furnace is different at only one place.

At this time, for a certain schedule, when a better schedule is obtained in the neighborhood schedule, the procedure of immediately searching the neighborhood for the schedule is repeated until a better individual is not obtained in the neighborhood.

(1) Local Search Procedure for Rolling Order Only the rolling order β of the schedule (individual) is changed.

(A) From the beginning, the slabs whose rolling orders are adjacent to each other can be changed in order. If there is something that can be changed, go to (b). If not, end.

(B) Calculate the evaluation when changed. When the evaluation is good (when both the difficulty of rolling and the extraction time are good), actually change to (a).

If not, go to (c).

(C) Search for a changeable item. If there is something that can be changed, go to (b).

If not, the process ends.

(2) Local search procedure for heating furnace distribution Only the furnace number α is changed.

(A) It is assumed that i = 1 and j = 1.

(B) Go to (c) when the heating furnace for the slab to be rolled i-th is j furnace.

Otherwise, go to (d).

(C) Calculate the evaluation when the heating furnace of the slab to be rolled i-th is changed to a furnace other than the j furnace. If the evaluation is good (both fuel consumption and extraction time are good), change to the best one and go to (a).

If not improved, go to (d).

(D) i = i + 1.

If i> N (N is the number of slabs), i = 1, j
= J + 1.

If j> M (M is the number of heating furnaces), the process ends.

Otherwise, go to (b).

In 108, the schedule group improved in 107 is selected (processing of 405 in FIG. 4). The next-generation schedule group (individual group) is divided into a number of partial schedule groups (individual groups) equal to the evaluation items, and each partial individual group is selected according to each evaluation. At that time, each individual is selected with a probability proportional to the fitness described later. The concept of this parallel selection is shown in FIG. In addition, the elite strategy, that is, the method of always selecting the individual with the best evaluation value is used.

As the fitness of the individual, a value normalized to [0,100] using the upper limit value and the lower limit value for each evaluation is used.

The items used for evaluation of the individual are (1) difficulty of rolling, (2) extraction time, and (3) required fuel. In addition, costs may be considered.

The method of calculating the evaluation items will be described below.

The evaluation value of the rolling order is calculated by the equations (7) and (8).

[0056]

[Equation 3]

The heating furnace charging evaluation value is obtained from the viewpoint of extraction time and required fuel for charging each slab.

The maximum moving speed of each slab when the maximum fuel is supplied to the heating furnace is determined by the heat balance equation of the heating furnace. As the efficiency, the result calculated from the actual operation data is used.

[0059]

[Equation 4]

The minimum value of the moving speed of the slab in the same furnace is defined as the moving speed of the slab in the heating furnace. The heating furnace extraction time interval is obtained from the moving speed of the slab in the heating furnace, the slab width, and the slab interval, and the larger of the rolling time intervals is set as the extraction time interval.

The rolling time interval p [i] [j] in the case of rolling the slab j after the slab i is calculated based on the actual operation data.

The extraction time interval considering the rolling time is as follows.

[0063]

## EQU00005 ## Extraction time interval = max (p [i] [j], w [j] / moving speed of slab in heating furnace) (10) Find the extraction time. Calculate the required fuel from the extraction time of each slab. The extraction time from the start to the end of extraction and the required fuel are used as evaluation values.

[0064]

[Equation 6]

At 109, it is judged whether or not the GA search is completed. It is determined whether the number of generations is less than or equal to a predetermined number or the calculation time is within a predetermined time. If it is not finished, the number of generations is increased by 1 and the process jumps to 106.

At 110, when it is judged to be finished at 109, the optimum schedule is selected from the best evaluation values in the schedule group and output. The coefficients C _t and C _{g in} that case are set according to the purpose of operation.

[0067]

[Equation 7] Evaluation value = C _t x extraction time + C _g x required fuel (12) Step 5: In the physical distribution simulation unit 111, for the slab for which the rolling order, heating furnace number, and extraction time are determined, Fuel required by simulator with detailed model,
The slab temperature and slab retention status are calculated in detail, and a more accurate evaluation value is calculated.

Step 6: The result output unit 112 outputs the rolling order, the charging order, and the simulation result as a result.

Finally, an outline will be given of a method of generating the feasible rolling order used in step 105 of step 4.

When the number of slabs is N, the rolling order is represented by the following decision variable x.

[0071]

[Equation 8]

The feasible solution of the rolling order can be obtained by using a multistage graph.

The absolute position constraint and the relative position constraint expressed in the matrix above are expressed as shown in FIG. 9 using a multistage graph.

The k-th rollable slab number limited by the absolute position constraint is the k-th stage node, and the continuous rollable slab sequence defined by the relative position constraint is the arc between the nodes included in the adjacent stages. When the evaluation value indicating the difficulty of rolling is associated with the weight of the arc, it can be represented by a multistage graph as shown in FIG. Sk is a set of k-stage nodes, Aki (I)
Is a set of k-1 stages of nodes connectable to k stages of i nodes, A
ki (O) is a set of k + 1-stage nodes to which k-stage i nodes are connected. At this time, among the passes from the 1st stage to the Nth stage, the rolling sequence in which the node numbers that do not overlap (effective pass) can be executed is determined by the sum of the arc weights at that time. Give an evaluation value. FIG. 10 shows the procedure for obtaining the feasible rolling order.

0. Set the initial state of the multi-stage graph.

Here, Sk, Aki (I) and Aki (O) of each stage are set.

1. Next, one node is selected from the multistage graph. That is, the rolling order of one slab is determined. As one method, from the smallest stage of the number of nodes included in each stage,
Nodes that are not included in other stages will be selected.

2. Next, in the multistage graph, the above 1. The nodes that belong to the same stage other than the node selected in step 1 and the arc for that node are removed.

3. Next, the nodes selected above are removed from the stage where no nodes have been selected. The arc set for the removal node is also removed.

4. Next, the nodes not connected to the preceding stage and the succeeding stage are removed by selecting and removing the nodes 1 to 3 described above.

This procedure is repeated until there are no more nodes to be removed.

5. Judgment If t = N, end. Otherwise, t = t + 1 is set and the process returns to 1.

When one feasible solution is obtained, a plurality of other feasible solutions can be obtained by using a method of exchanging the order of two slabs. That is, paying attention to two nodes (slab numbers) i ₁ and i ₂ included in the effective path shown in FIG. 11, these nodes can be exchanged if they can be connected to the nodes (slabs) before and after the exchange. Is. That is, as shown in FIG. 12, the path in which these are exchanged becomes another feasible solution.

As described above, many feasible rolling order solutions can be obtained by using paths obtained by exchanging nodes as new effective paths (solution candidates).

Finally, an example of the result of the present invention is shown in FIG. In FIG. 13, F1, F2, and F3 represent heating furnaces,
Mill indicates a rolling mill. (A) is a schedule result by this apparatus, (b) is a schedule of the actual results of the operator. The numbers in the figure indicate slab numbers. It can be seen that the present invention reduces the extraction time.

The present invention can also be applied to the heating and rolling processes for billets such as steel bars and wire rods.
At that time, although there is only one heating furnace, the rolling order is optimally determined.

[0087]

[Effects of the Invention] By searching for the optimum solution of the evaluation value, it becomes possible to determine the charging time, the extraction time, the charging furnace, and the rolling order based on the quantitative evaluation, and the optimum physical distribution can be achieved. Can be implemented. As a result, productivity can be improved, costs can be reduced, and quality can be stabilized.

[Brief description of drawings]

FIG. 1 is a flowchart showing a configuration of a rolling mill physical distribution scheduling method.

FIG. 2 is a block diagram showing a hot rolling mill of an example.

FIG. 3 is a block diagram showing a hardware configuration of an apparatus for implementing the scheduling method of FIG.

FIG. 4 is a flow chart showing an optimization process by GA and local search.

FIG. 5 is a schematic diagram showing an individual example of a gene.

FIG. 6 is a schematic diagram showing an example of gene crossover.

FIG. 7 is a schematic diagram showing an example of gene mutation.

FIG. 8 is a block diagram showing a method of parallel selection.

FIG. 9 is a schematic diagram showing a multi-stage graph representation of a rolling order determination problem.

FIG. 10 is a flow chart showing a rolling sequence feasible solution generation procedure.

FIG. 11 is a schematic diagram showing an effective path indicating one feasible solution.

FIG. 12 is a schematic diagram showing an effective path indicating a feasible solution obtained by exchanging two nodes.

FIG. 13 is a time chart showing an example of a schedule result.

[Explanation of symbols]

101: Input of slab data 102: Sort of slab data 103: Calculation of rolling constraint matrix 104: Calculation of rolling evaluation value matrix 105: Schedule generation 106: Schedule generation by gene manipulation 107: Schedule improvement by local search 108: Evaluation Schedule selection by function 109: End determination 110: Best schedule output 111: Logistics simulation 112: Result output 201: Slab storage 202: Freight car 203: Table in front of heating furnace 204: Heating furnace 205: VSB, 206: Rough rolling mill 207 : Finishing rolling mill 208: RO
T 209: Coiler 210: Product storage area d: Rolled slab e: Coil f: Slab, direction of coil movement 301: Display 302: Workstation 303: Keyboard 304: Mouse 305: Hard disk 306: Network 401: Generation of initial population 402: Crossover 403: Mutation 404: Local search 405: Selection

Continuation of the front page (51) Int.Cl. ⁶ Identification number Internal reference number FI Technical indication G05B 13/02 Q7531-3H G06F 17/60 // C21D 11/00 105 G06F 15/21 L (72) Invention Person Fujii Akira 20-1 Shintomi, Futtsu-shi, Chiba Nippon Steel Co., Ltd.Technology Development Division (72) Inventor Mitsuhiko Araki 80-2 Kamigamoshikatsucho, Kita-ku, Kyoto (72) Inventor Tamaki Hisashi Hisashi 2-1, Horikawa-dori Ichijo, Kamikyo-ku, Kyoto 2-1 Kyoto Horikawa Grand Heights 207 (72) Inventor Masakatsu Mori 12-2 Ishiodai, Ishiodai, Kasugai City, Aichi Prefecture

Claims (2)

[Claims] 1. In a rolling process composed of a plurality of heating furnaces and rolling mills, in order to determine a charging furnace for material slabs and a rolling order, the material slabs to be rolled are input and the material slabs are input. The information is sorted by width, then the rolling constraint conditions of the material slab are expressed in a matrix, and the evaluation value regarding the difficulty of rolling is obtained in advance, and the charging heating furnace number of each slab and the rolling order satisfying the constraint conditions are calculated. It is possible to set an individual gene and search it with a genetic algorithm, and evaluate it with an evaluation function that includes the difficulty of rolling, the extraction time of the heating furnace, and the fuel consumption to determine the optimum charging furnace and rolling sequence at the same time. Characteristic rolling mill logistics scheduling method. 2. The individual expression of a gene according to claim 1, wherein the number of the slab to be heated and the number of the slab to be rolled, in which two symbols having the same symbol length as the number of slabs to be scheduled are connected, are used as the contents, From the initial solution candidate, cross,
Multiple individuals that will be the next solution candidate are generated by mutation, the solution is further improved by local search, and solution candidates are selected by individually using evaluation functions such as rolling difficulty, extraction time, and fuel,
Next, a distribution scheduling method for a rolling mill, characterized in that the optimum charging furnace and rolling sequence are determined by repeating a predetermined number of times of returning to the generation of solution candidates by crossing and mutation.