JP2013176804A - Method, device and program for supporting update of discrete model of manufacturing process - Google Patents

Abstract

PROBLEM TO BE SOLVED: To support update so as to reflect contents described in a trouble report on a discrete model.SOLUTION: A proposition graphic display 192 (not shown in the figure) is prepared in which texts of a trouble report 191 are sectioned into propositions which are connected by arrows to be expressed in a flow chart, and then a summarized proposition graphic display 193 (not shown in the figure) is prepared in which the propositions described in the proposition graphic display 192 (not shown in the figure) are summarized as an expression made to correspond to a continuous casting model 16. An update support device 10 of the continuous casting model acquires the summarized proposition graphic display 193 (not shown in the figure), and prepares a state transition diagram 194 (not shown in the figure) expressing state transition in a trouble using only states defined in the continuous casting model 16 on the basis of the summarized proposition graphic display 193 (not shown in the figure). Then, information is supplemented from the continuous casting model 16 to the state diagram 104 (not shown in the figure) to prepare a supplemented state diagram 195 (not shown in the figure).

Description

  The present invention relates to a discrete model update support method, apparatus and program suitable for supporting the update of a discrete model representing a production process in which a continuous product continuously flows, such as a continuous casting process. About.

  In order to realize the stable operation of continuous casting, it is necessary for the operator to always judge and select an appropriate operation. To that end, it is important to accurately predict the state of products (products) and equipment. is there.

  For the above prediction, operators, particularly experts, have constructed a cognitive model of the continuous casting process by integrating piecewise information about the state of steel in the continuous casting process through causal relationships. And since operators have knowledge of the cognitive model of the continuous casting process in their heads, they have avoided trouble by estimating the state of the steel, predicting the future state, and performing appropriate operations.

  On the other hand, in recent years, productivity decline due to a decrease in skilled workers, operation trouble occurrence, and the like are increasing, and it is demanded to support appropriate operations even if they are not skilled workers.

Japanese Patent Laid-Open No. 07-028862 JP 2001-022566 A JP 2000-339149 A

Tadao Murata: Petri net analysis and application, Modern Science (1992)

In general, in a continuous process, the state of a product as a substance takes various forms depending on temperature and components, the state changes depending on time and facility operation, and the state of the product changes the state of the facility. There are also complex mutual interferences that also affect the state of the product.
Therefore, it is important to note that the cognitive model in the expert's head takes into account the complex mutual interference of the product and equipment states as described above. In order to make the cognitive model of the continuous casting process objective, it is possible to discretely model the causal relationship in the state transition of products and equipment. If the causal relationship in the state transition of products and equipment is discretely modeled, it is possible to use the discrete model to support the operation of the manufacturing process, for example, guidance on actions when operation troubles occur or when troubles occur. Become.

In the operation of the manufacturing process, the state of the equipment changes from moment to moment, and the discrete model is always required to be updated accordingly.
For example, as a technology related to a state transition model or a state transition diagram, Patent Document 1 describes heater control in a vending machine using a state transition model (hierarchical model) that causes a state transition according to an event from the outside and the outside world. ing. Further, Patent Document 2 describes a method of using a table input to improve the efficiency of a state transition diagram that is very important when designing a program for communication control. Further, Patent Document 3 describes a development support system having means for describing a state transition table in software development.

  However, each technique only presents a method for creating a state transition model or state transition diagram, and a method for quickly and efficiently updating a model in response to changes in the state of equipment and operations that change from moment to moment. Is not described.

  By the way, when any trouble occurs in the actual continuous casting process, a trouble report describing the occurrence status and cause of the trouble is created. This trouble report is expressed as a document of the operator's tacit knowledge, and it is useful to update the contents described in the trouble report to reflect them in the discrete model.

  The present invention has been made in view of the above points, and an object of the present invention is to assist in updating the content described in the trouble report so as to be reflected in the discrete model.

The method for supporting update of a discrete model of a manufacturing process according to the present invention creates a state transition model of an attribute of the product and a state transition model of equipment for a manufacturing process in which a continuous product continuously flows, and the product A method for supporting the update of a discrete model of a manufacturing process, which supports the update of a discrete model created by defining an influence relationship between the state of an attribute of the equipment and the state of the equipment, and a trouble has occurred in the manufacturing process At least information about the trouble occurrence status, the cause of the trouble, the countermeasures for the trouble, the product processed at the time of the trouble, the findings about the trouble of the manufacturing operator A procedure to obtain an aggregate proposition-related diagram created based on a trouble report that is a sentence including State transition diagram representing the state transition of the manufacturing process in trouble using only the attribute state and the facility state of the product defined in the discrete model based on the acquired aggregate proposition relation diagram And the created state transition diagram, from the discrete model, information about the state of the attribute of the product, information about the state of the equipment, the state of the attribute of the product and the equipment A procedure for creating a complemented state transition diagram by complementing at least one of the information on the influence relation between the states of the current state, a procedure for outputting the created complemented state transition diagram, and the created complemented state transition diagram And a procedure for updating a discrete model of the manufacturing process, which is addition or correction of a state and a causal relationship, The sentence of the book is divided into propositions corresponding to the expression of the discrete model, expressed by a flowchart connecting the propositions, and these propositions are aggregated as an expression corresponding to the discrete model, To do.
Another feature of the discrete model update support method according to the present invention is that the discrete model divides the manufacturing process into a plurality of stages in the flow direction of the product, and the product for each stage. A discrete model created by defining a state transition model of an attribute and a state transition model of an equipment, and defining an influence relationship between the state of the attribute of the product and the state of the equipment in each stage There is a point.
Another feature of the discrete model update support method of the present invention is that the discrete model is constructed using a Petri net model.
Another feature of the discrete model update support method according to the present invention is that when the user connects propositions in which the trouble report text is divided, creation support means is described in the discrete model. The method further includes a procedure for searching and presenting a relationship between propositions based on a relationship and a relationship between propositions that are not described in the discrete model but are defined in advance.
Another feature of the discrete model update support method according to the present invention is that when the user connects the propositions in which the trouble report text is divided, the creation support means uses the proposition according to a predetermined rule. It is characterized in that it further comprises a procedure for limiting the relationship between them.
Another feature of the discrete model update support method according to the present invention is that when the user connects propositions in which the trouble report text is divided, creation support means is described in the discrete model. The method further includes a procedure for searching and presenting a path between propositions based on a relationship and a relationship between propositions that are not described in the discrete model but are defined in advance.
Further, another feature of the discrete model update support method of the present invention is that the creation support means interpolates a proposition that is based on the discrete model with a proposition as a start point and an end point connected to the proposition. It is in the point which further has the procedure to search and present.
The discrete model update support apparatus according to the present invention creates a state transition model of the product attribute and a state transition model of the facility for a manufacturing process in which a continuous product continuously flows. An update support device for a discrete model of a manufacturing process that supports updating of a discrete model created by defining an influence relationship between a state and a state of the facility, and is created when a trouble occurs in the manufacturing process A trouble report that contains at least information on the status of the trouble, the cause of the trouble, the countermeasures for the trouble, the product processed at the time of the trouble, and the findings about the trouble of the manufacturing operator Aggregate proposition relevant diagram acquisition means for obtaining an aggregate proposition relevant diagram created based on a trouble report Based on the aggregate proposition relation diagram acquired by the aggregate proposition relation diagram acquisition means, the state transition of the manufacturing process in trouble is determined using only the attribute state of the product and the state of equipment defined in the discrete model. State transition diagram creating means for creating a state transition diagram that is a representation of the figure, state transition diagram created by the state transition diagram creating means, from the discrete model, information about the state of the attribute of the product, Complementary state transition diagram creation for creating a supplementary state transition diagram by complementing at least one of information on the state of equipment and information on the influence relationship between the state of the attribute of the product and the state of the equipment Means for outputting the complementary state transition diagram created by the complementary state transition diagram creating means, and the complementary state transition diagram created by the complementary state transition diagram creating unit. Update means for updating the discrete model of Seth, which is addition or correction of the state and the causal relationship, and the aggregation proposition associated diagram associates the text of the trouble report with the expression of the discrete model. The propositions are divided into the propositions and expressed by a flowchart connecting the propositions, and these propositions are aggregated as expressions corresponding to the discrete model.
In addition, another feature of the discrete model update support apparatus according to the present invention is that the discrete model divides the manufacturing process into a plurality of stages in the flow direction of the product, and the product for each stage. A discrete model created by defining a state transition model of an attribute and a state transition model of an equipment, and defining an influence relationship between the state of the attribute of the product and the state of the equipment in each stage There is a point.
Another feature of the discrete model update support apparatus according to the present invention is that the discrete model is constructed using a Petri net model.
In addition, another feature of the discrete model update support apparatus according to the present invention is that when the user connects propositions in which sentences of the trouble report are separated, the relationship described in the discrete model and the discrete It is further provided with a creation support means for searching for and presenting a relationship between propositions based on a relationship between propositions that are not described in the model but defined in advance.
Another feature of the discrete model update support apparatus according to the present invention is that when the user connects the propositions in which the trouble report sentences are separated, the relationship between the propositions is limited according to a predetermined rule. It is the point which further provided the creation assistance means to do.
In addition, another feature of the discrete model update support apparatus according to the present invention is that when the user connects propositions in which sentences of the trouble report are separated, the relationship described in the discrete model and the discrete It is further provided with a creation support means for searching for and presenting a route between propositions based on a relationship between propositions that are not described in the model but are defined in advance.
Another feature of the discrete model update support apparatus according to the present invention is that, based on the discrete model, a proposition which starts from a certain proposition as a start point and searches for a proposition serving as an end point is searched and presented while interpolating the proposition. The creation support means is further provided.
The program of the present invention creates a state transition model of an attribute of the product and a state transition model of an equipment for a manufacturing process in which continuous products continuously flow, and the state of the attribute of the product and the state of the equipment A program for supporting the update of a discrete model created by defining the influence relationship between states, and a trouble report created when a trouble occurs in the manufacturing process, and the occurrence of trouble Aggregated proposition created based on the trouble report, which is a sentence containing at least information about the situation, the cause of the trouble, countermeasures for the trouble, the product processed at the time of the trouble, and the findings about the trouble of the manufacturing operator Aggregate proposition relevant diagram acquisition means for obtaining a related diagram, and an aggregate proposition relevant diagram obtained by the aggregate proposition relevant diagram acquisition means Based on the state of the product attribute defined in the discrete model and the state of the equipment, the state transition diagram creating means for creating a state transition diagram representing the state transition of the manufacturing process in trouble And the state transition diagram created by the state transition diagram creating means, from the discrete model, information about the state of the attribute of the product, information about the state of the equipment, and the state of the attribute of the product, Complementary state transition diagram creating means for creating a supplementary state transition diagram by complementing at least one of the information on the influence relation with the state of the equipment, and complementary state transition created by the complementary state transition diagram creating means Using the output means for outputting a diagram and the complementary state transition diagram created by the complementary state transition diagram creating means, the state and causal relationship can be added to the discrete model of the manufacturing process, or The computer functions as an updating means for performing a positive update, and the aggregated proposition relevant diagram is a flowchart in which sentences of the trouble report are divided into propositions corresponding to the representation of the discrete model, and the propositions are connected. It is characterized in that these propositions are aggregated as an expression corresponding to the discrete model.

  According to the present invention, a state transition diagram is created based on a trouble report created when a trouble occurs in the manufacturing process, and information from the discrete model is supplemented to the state transition diagram. Can be compared with discrete models. As a result, it is possible to support updating the contents described in the trouble report so as to be reflected in the discrete model.

It is a figure which shows the outline | summary of a continuous casting process. It is a flowchart which shows the procedure of the discrete modeling of a continuous casting process. It is a figure explaining the attribute of the product of each stage. It is a figure explaining a Petri net. It is a figure which shows the state transition model of the attribute of the product in a TD stage, and the state transition model of an installation. It is a figure which shows the state transition model of the temperature and hot_water | molten_metal surface level of the product in a casting_mold | template stage, and the state transition model of the bulging of the product in a vertical area | region stage. It is a figure which shows the state transition model of the flow volume of the product in a nozzle stage, and the state transition model of the hot_water | molten_metal surface level of the product in a casting_mold | template stage. It is a figure which shows the structural example of the operation support apparatus of a continuous casting process. It is a flowchart which shows the procedure of the operation support by the operation support apparatus. It is a figure which shows the reachable tree created from the state transition model of the TD stage. It is a figure which shows the reachable tree produced from the state transition model of the temperature of a product in a casting_mold | template stage and a hot_water | molten_metal surface level, and the reachable tree created from the state transition model of the bulging of the product in a vertical area | region stage. It is a figure which shows the reachable tree of the casting_mold | template stage and vertical area | region stage corresponding to FIG. It is a figure which shows the state transition model of the temperature and hot_water | molten_metal surface level of the product in a casting_mold | template stage, and the state transition model of the bulging of the product in a vertical area | region stage. It is a figure which shows the reachable tree of the casting_mold | template stage and vertical area | region stage corresponding to FIG. It is a figure which shows the example of a risk matrix. It is a figure which shows the example of a risk matrix. It is a flowchart which shows the procedure of the operation support by the operation support apparatus. It is a figure which shows the example of a risk matrix. It is a figure which shows the outline | summary of the update support method of a continuous casting model, and the apparatus used for it. It is a figure which shows the example of a trouble report. It is a figure which shows the result of having divided the sentence of the trouble report into the proposition. It is a figure which shows the example of a proposition relevant figure. It is a figure which shows the example of an aggregation proposition relevant figure (before state transition arrangement | positioning). It is a figure which shows the example of an aggregation proposition relevant figure (after state transition arrangement | positioning). It is a figure which shows the example of the list of propositions. It is a figure which shows the example of a state transition diagram. It is a figure which shows the example of a complementation state transition diagram. It is a figure which shows the example of the correspondence of the causal relationship which is a relationship between the propositions represented by the arrow in a state transition diagram, and a continuous casting model. It is a figure which shows the example of the correspondence of the causal relationship which is a relationship between the propositions represented by the arrow in a state transition diagram, and a continuous casting model. It is a figure which shows the example of the correspondence of the causal relationship which is a relationship between the propositions represented by the arrow in a state transition diagram, and a continuous casting model. It is a figure which shows the example of the correspondence of the causal relationship which is a relationship between the propositions represented by the arrow in a state transition diagram, and a continuous casting model. It is a figure which shows the example of the correspondence of the causal relationship which is a relationship between the propositions represented by the arrow in a state transition diagram, and a continuous casting model. It is a figure which shows the example of the correspondence of the causal relationship which is a relationship between the propositions represented by the arrow in a state transition diagram, and a continuous casting model. It is a figure which shows the example of an aggregation proposition relevant figure. It is a figure which shows the example of a state transition diagram. It is a figure which shows the example of a complementation state transition diagram. It is a figure which shows the Petri net to be updated. It is a figure which shows the structure of the preparation assistance apparatus of a proposition relevant figure. It is a figure which shows the example of a trouble report. It is a figure which shows the example of the creation assistance screen displayed on the display apparatus of the creation assistance apparatus of a proposition relevant figure. It is a figure which shows the example of the creation assistance screen displayed on the display apparatus of the creation assistance apparatus of a proposition relevant figure. It is a figure which shows the example of the creation assistance screen displayed on the display apparatus of the creation assistance apparatus of a proposition relevant figure. It is a figure which shows the example of the creation assistance screen displayed on the display apparatus of the creation assistance apparatus of a proposition relevant figure. It is a figure which shows the example of the creation assistance screen displayed on the display apparatus of the creation assistance apparatus of a proposition relevant figure. It is a figure for demonstrating the state with a several path | route between propositions. It is a figure for demonstrating the relationship between the propositions restrict | limited. It is a figure for demonstrating the relationship between the propositions restrict | limited. It is a figure for demonstrating the relationship between the propositions restrict | limited.

Preferred embodiments of the present invention will be described below with reference to the accompanying drawings.
[Outline of continuous casting process]
In the continuous casting process, as shown in FIG. 1, molten steel made in a converter (not shown) is put into a ladle 100 through secondary refining and is transported to the top of a continuous casting facility. Molten steel is poured from the bottom of the ladle 100 to the lower tundish 200. The molten steel poured into the tundish 200 is poured from the bottom of the tundish 200 into the mold 400 via the nozzle 300. The molten steel that has contacted the mold 400 is cooled while being precisely adjusted and solidified to form a steel slab, which is cut to an appropriate length by a gas cutting machine (not shown) at the end of the roll row while being transported by a roll (not shown). The

[Operation support for continuous casting process]
Below, the example of the operation support method using the discrete model of a continuous casting process and the apparatus used for it is demonstrated.
(Discrete modeling of continuous casting process)
First, discrete modeling of the continuous casting process as shown in FIG. 1 will be described. In the continuous casting process, a continuous (physically linked) product (molten steel, billet) flows continuously (moves). Discrete modeling of a continuous casting process having the feature of “continuous” in this way is equivalent to extracting the causal relationship recognized in “continuous” and defining it as a discrete model. Therefore, the state of the product is defined for each stage and discretized.

  FIG. 2 shows a procedure for discrete modeling of the continuous casting process. First, the continuous casting process is divided into a plurality of stages in the direction in which the product flows (step S101). In this embodiment, as shown in FIG. 3, the tundish stage (TD stage), the nozzle stage, the mold stage, and the vertical region stage are divided from the upstream side.

  Next, the attribute of the product and its state are defined for each stage (step S102). In the present embodiment, as shown in FIG. 3, temperature (high / common / low) and viscosity (high / common) are defined as the attributes and states of the product in the TD stage. Moreover, the temperature (high / normal / low), the flow rate (appropriate / low), and the flow (rectification / diffusion) are defined as attributes and states of the product in the nozzle stage. In addition, the attributes of the product at the mold stage and its state include temperature (high, ordinary, low), temperature uniformity (uniform / non-uniform), shell thickness (appropriate / thin), shell uniformity (uniform / non-uniform). ), Inclusions (with / without), surface tensile stress (strong / weak), and level (appropriate / low). In addition, as attributes and states of the product in the vertical region stage, temperature (high / normal / low), shell thickness (appropriate / thin), and presence / absence of bulging (presence / absence) are defined. In addition, the attribute of the product mentioned here and its state are examples, and are not limited to this.

  Next, a transition path of the attribute state of the product is defined for each stage (step S103). For example, in each stage, for the temperature of the product, a transition path is defined such that the movement between the high temperature and low temperature always moves after passing through the temperature.

  Next, a state transition model M1 of product attributes is created for each stage (step S104). In the present embodiment, the state transition model M1 of the product attribute is created by a Petri net. A Petri net is a graphical and executable mathematical model that expresses a discrete event system consisting of multiple processes that run in parallel and asynchronously simultaneously. As shown in FIG. 4, a state is described as a place P and a transition as a transition T. By firing T, the token moves from the input-side places P1 and P2 to the output-side place P3, thereby expressing the target behavior. The Petri net is described in detail in Non-Patent Document 1 and the like.

  FIG. 5 shows a state transition model TD-M1 of product attributes at the TD stage. Regarding the temperature, a place where the temperature is high, a place where the temperature is normal, and a place where the temperature is low are connected via transitions T9 to T12. If there is a token in the place where the temperature is low, the transition T11 can be ignited, and when it is ignited, the token moves to a place where the temperature is normal. In addition, when there is a token at a place where the temperature is normal, the transition T9 can be ignited, and when it is ignited, the token moves to a place where the temperature is high. In addition, when there is a token in a place where the temperature is high, the transition T10 can be ignited, and when it is ignited, the token moves to a place where the temperature is normal. In addition, when there is a token in a place where the temperature is normal, the transition T12 can be ignited, and when ignited, the token moves to a place where the temperature is low.

  In addition, with regard to viscosity, a place with high viscosity and a place with high viscosity are connected via transitions T13 and T14. When there is a token in a place with high viscosity, the transition T14 can be ignited, and when ignited, the token moves to a place where the viscosity is normal. In addition, when there is a token in the viscous place, the transition T13 can be ignited, and when ignited, the token moves to a viscous (high) place.

  Here, the state transition model TD-M1 of the product attribute at the TD stage has been described in detail. However, the state transition model NOZ-M1 of the product attribute is also respectively applied to the nozzle stage, the mold stage, and the vertical region stage. MD-M1 and V-M1 are created.

  If the state transition model M1 of the product attribute is created for all stages (step S105), the equipment and its state are defined for each stage (step S106). In this embodiment, a plasma heating device (ON / OFF / failure) and bubbling (ON / OFF / failure) are defined as equipment and its state on the TD stage. In addition, nozzles (stationary (non-clogging), non-stationary, failure (uneven clogging), failure (clogging)), slide (stationary / non-stationary (wide), failure) ) Is defined. In addition, the equipment and conditions at the mold stage include powder feeders (steady / unsteady (separate pattern) / failure), sprinklers (steady / unsteady (strong) / failure), rollers (steady / Non-stationary use (slow withdrawal speed / failure) is defined. In addition, the facilities mentioned here and the state are examples, and are not limited to this.

  Next, a transition path of equipment state is defined for each stage (step S107). For example, in the TD stage, for the plasma heating device (ON / OFF / failure), a transition path is defined such that the plasma heating device (failure) always moves from the plasma heating device (OFF).

  Next, an equipment state transition model M2 is created for each stage (step S108). In the present embodiment, the equipment state transition model M2 is also created by a Petri net.

  FIG. 5 shows a state transition model TD-M2 of the equipment at the TD stage. In the plasma heating apparatus, an ON place, an OFF place, and a failure place are connected via transitions T1 to T3. When there is a token in the OFF place, the transition T1 can be ignited, and when ignited, the token moves to the place of failure. Further, when there is a token in the OFF place, the transition T3 can be fired, and when fired, the token moves to the ON place. In addition, when there is a token in the ON place, the transition T2 can be ignited, and when ignited, the token moves to the OFF place.

  For bubbling, an ON place, an OFF place, and a failure place are connected via transitions T5 to T7. If there is a token in the OFF place, the transition T5 can be ignited, and when ignited, the token moves to the place of failure. Further, when there is a token in the OFF place, the transition T7 can be fired, and when fired, the token moves to the ON place. Further, when there is a token in the ON place, the transition T6 can be fired, and when fired, the token moves to the OFF place.

  Here, the equipment state transition model TD-M2 at the TD stage has been described in detail. However, the equipment state transition models NOZ-M2, MD-M2, and V for the nozzle stage, the mold stage, and the vertical region stage, respectively. -Create M2.

  If the equipment state transition model M2 is created for all stages (step S109), the influence relationship within the stage is defined for each stage (step S110). Table 1 shows the contents defining the influence relationship between the state of the equipment in the TD stage and the state of the attribute of the product. As shown in Table 1, when the plasma heating device is ON, the temperature of the product attribute changes to a normal temperature if the temperature is low, and to a high temperature if the temperature is normal. Defined. Further, when bubbling is ON, it is defined that, among the attributes of the product, the temperature transitions to a normal temperature when the temperature is high and transitions to a low temperature when the temperature is normal.

  Next, the influence relationship between the state of the equipment and the state of the product attribute defined in step S110 is incorporated into the state transition model (the state transition model M1 of the product attribute and the state transition model M2 of the equipment) (step S111). ). As shown in FIG. 5, when there is a token at the ON place in the state transition model of the plasma heating apparatus, the transition T4 is ignited via the conditional arc. As a result, when there is a token at a place where the temperature is low in the temperature state transition model, the transition T11 connected with the transition T4 by the permission synchronization arc is ignited, and the token moves to the place where the temperature is normal. In addition, when there is a token at a place where the temperature is normal, the transition T9 connected to the transition T4 by the permission synchronization arc is ignited, and the token moves to the place where the temperature is high. Further, when there is a token in the ON place in the bubbling state transition model, the transition T8 is ignited via the conditional arc. As a result, when there is a token at a place where the temperature is high in the temperature state transition model, the transition T10 connected with the transition T8 by the permission synchronization arc is ignited, and the token moves to the place where the temperature is normal. In addition, when there is a token in a place where the temperature is normal, the transition T12 connected with the transition T8 by the permission synchronization arc is ignited, and the token moves to the place where the temperature is high. The permitted synchronization arc indicates that the end point transition always fires when the start point transition fires. The conditional arc indicates that the token can be ignited when a token is present at the starting place.

  Here, the state transition model TD-M1 of the attribute of the product in the TD stage and the equipment state transition model TD-M2 are described in detail. However, the nozzle stage, the mold stage, and the vertical region stage are also staged respectively. The influence relationship between the state of the equipment and the state of the product attribute is incorporated into the state transition model (the state transition model M1 of the product attribute and the state transition model M2 of the equipment).

  Further, here, the influence relationship between the state of the equipment in the stage and the state of the product attribute has been described. However, for example, the influence relationship between the product attributes in the stage may be defined. For example, the temperature uniformity affects the shell uniformity in the mold stage (if the temperature is uniform, the shell is uniform, and if the temperature is not uniform, the shell is not uniform), the state transition model (state of the product attribute) It may be incorporated in the transition model M1).

  If the influence relationship within the stage is taken in for all stages (step S112), the influence relationship between the attributes of the product between the stages is defined (step S113). The influence relationship between the attributes of the product between the stages is an effect received from the product existing in another stage at substantially the same time. For example, it is known that when bulging occurs in the vertical region, the molten metal surface vibration is generated in the upstream mold at approximately the same time, affecting the molten metal surface level. Therefore, as indicated by the broken line arrow 31 in FIG. 3, the presence or absence of bulging in the vertical region stage is defined as affecting the level of the molten metal surface in the upstream mold stage. That is, when there is bulging in the vertical region stage, it is defined that the level shifts to low if the molten metal level at the mold stage is appropriate. Further, it is defined that when there is no bulging on the vertical region stage, an appropriate transition is made if the molten metal level at the mold stage is low.

  Next, the influence relationship between the product attributes between the stages (arrow 31 in FIG. 3) defined in step S113 is expressed as a state transition model (the product attribute state transition model M1 and the equipment state transition model M2). (Step S114). FIG. 6 shows part of the state transition model MD-M1 of the product attribute at the mold stage (temperature and hot water level) and one of the state transition model V-M1 of the product attribute at the vertical region stage. Part (bulging). These state transition models M1 are created in step S104. Regarding the temperature at the mold stage, if there is a token in a place where the temperature is low, the transition T301 can be ignited, and when ignited, the token moves to a place where the temperature is high. In addition, when there is a token in a place where the temperature is high, the transition T302 can be ignited, and when the token is ignited, the token moves to a place where the temperature is low. Although it has been described that (high / normal / low) is defined as the temperature state, only the (high / low) state is illustrated in FIG. 6 in order to simplify the description. With respect to the level of the molten metal surface at the mold stage, when there is a token in an appropriate place, the transition T303 can be ignited, and when ignited, the token moves to a place where the token is low. In addition, when there is a token in a low place, the transition T304 can be fired, and when fired, the token moves to an appropriate place. As for bulging in the vertical region stage, when there is a token in a place without bulging, the transition T401 can be fired, and when fired, the token moves to a place with bulging. In addition, when there is a token in a place where there is a token, the transition T402 can be ignited, and when it is ignited, it moves to a place where there is no token.

  As shown in FIG. 6, when there is a token at a place in the state transition model for bulging in the vertical region stage, a transition T501 is ignited via a conditional arc. As a result, when there is a token at an appropriate place in the state transition model at the molten metal level at the mold stage, the transition T303 connected with the transition T501 by the permission synchronization arc is ignited, and the token moves to a place with a low token. Further, when there is a token in a place where there is no bulging state transition model in the vertical region stage, the transition T502 is ignited via a conditional arc. As a result, when there is a token in a low place in the state transition model of the molten metal level at the mold stage, the transition T304 connected to the transition T501 by the permission synchronization arc is ignited, and the token moves to an appropriate place.

  In the present embodiment, the example in which the attribute of the product at the downstream stage affects the attribute of the product at the upstream stage, but the opposite, that is, the product at the upstream stage. Can affect the attributes of the product at the downstream stage.

  Next, a relationship is defined in which the attribute state of the product in the upstream stage is transferred to the downstream stage as the product moves (step S115). As shown by the solid line arrow 32 in FIG. 3, for example, the temperature at the TD stage is defined as being transferred to the temperature at the nozzle stage on the downstream side. That is, if the temperature at the TD stage increases, the temperature at the downstream nozzle stage also increases, and if the temperature at the TD stage becomes normal, the temperature at the downstream nozzle stage also becomes normal, If the temperature at the TD stage decreases, the temperature at the nozzle stage on the downstream side also decreases. Similarly, it is defined that the temperature at the nozzle stage is transferred to the temperature at the mold stage, and the temperature at the mold stage is transferred to the temperature at the vertical region stage.

  Further, it is defined that the flow rate at the nozzle stage is transferred to the molten metal level at the downstream mold stage. That is, if the flow rate at the nozzle stage is appropriate, the level of the molten metal level at the downstream mold stage is also appropriate, and if the flow rate at the nozzle stage is reduced, the molten metal level at the downstream mold stage. Also lower.

  Further, it is defined that the flow at the nozzle stage is transferred to the temperature uniformity at the downstream mold stage. That is, if the flow at the nozzle stage is rectified, the temperature uniformity at the downstream mold stage is also uniform, and if the flow at the nozzle stage is uneven, the temperature is uniform at the downstream mold stage. The characteristics are also uneven.

  Next, the state transition model defines the relationship (arrow 32 in FIG. 3) in which the state of the product attribute at the upstream stage defined in step S115 is transferred to the downstream stage as the product moves. They are incorporated into (attribute state transition model M1 and facility state transition model M2) (step S116). FIG. 7 shows a part (flow rate) of the state transition model NOZ-M1 of the product attribute at the nozzle stage and a part (water surface level) of the state transition model MD-M1 of the product attribute at the mold stage. ). These state transition models M1 are created in step S104. As for the flow rate at the nozzle stage, when there is a token in an appropriate place, the transition T201 can be ignited, and when ignited, the token moves to a place with few tokens. In addition, when there are tokens in a small number of places, the transition T202 can be fired, and when fired, the tokens move to an appropriate place. The hot water level on the mold stage is as described with reference to FIG.

  Then, as shown in FIG. 7, an appropriate place of the state transition model of the flow rate at the nozzle stage and an appropriate place of the state transition model of the molten metal level at the downstream mold stage are transferred via the transition T601. Further, a small number of places in the state transition model of the flow rate at the nozzle stage and a low place in the state transition model at the molten metal level at the downstream mold stage are connected via the transition T602. Hereinafter, the transition defined in step S116 is referred to as a transfer transition. If there is a token at an appropriate place in the state transition model of the flow rate at the nozzle stage, the transfer transition 601 can be ignited, and when ignited, the state transition model at the molten metal level at the mold stage on the downstream side is ignited. The token moves. In addition, when there are tokens in a small number of places in the state transition model of the flow rate at the nozzle stage, the transfer transition 602 can be ignited. The token moves to the place.

  In addition, when connecting to the downstream stage, the corresponding place is connected via a transfer transition. In the example of FIG. 7, since the hot water level does not connect to the downstream stage, delivery transitions T603 and T604 in which no place is connected to the outlet side are defined.

  The transfer transitions defined in step S116 (the transfer transitions T601 to T604 in the example of FIG. 7) are not ignited alone, and all of them are ignited simultaneously when the state of the product attribute changes in any stage. . For example, in the state shown in FIG. 7 (a token is in an appropriate place in the state transition model of the flow rate at the nozzle stage and a token is in an appropriate place in the state transition model of the mold level at the mold stage) When the flow rate is low (when a token moves to a place with a low flow rate), all transfer transitions fire simultaneously. As a result, the token of the place with a small flow rate moves to a place with a low hot water level due to the firing of the transfer transition T602, and the token of the appropriate place at the hot water level disappears due to the firing of the passing transition T603. Again, when the product attributes change at any stage, all delivery transitions fire simultaneously.

  Further, for example, in the state shown in FIG. 7, if the temperature of the product of any stage changes, all the transfer transitions are ignited simultaneously. As a result, the token of the place with the appropriate flow rate moves to the appropriate place of the hot water level due to the ignition of the transfer transition T601, and the token of the appropriate place of the hot water level disappears due to the ignition of the transfer transition T603. In this arrangement, the flow rate of the nozzle stage and the state of the mold surface level of the mold stage are not affected by the change in temperature and do not change from the previous state.

  The discrete modeling described above can be performed using a computer device that can execute an algorithm of discrete modeling. That is, when an operator inputs through a stage dividing method, a product attribute and its state for each stage, and a transition path of a product attribute state (steps S101 to S103), the computer apparatus automatically performs the stage. A state transition model for each product attribute is created (step S104). Similarly, when the operator inputs the equipment for each stage and its state, and the transition path of the equipment state (steps S106 to S107), the computer apparatus automatically creates the equipment state transition model for each stage (step S106). S108). When the operator inputs an influence relationship within the stage (step S110), the computer apparatus automatically incorporates the influence relationship into the state transition model (step S111). When the operator inputs the influence relationship between the attributes of the product between the stages (step S113), the computer apparatus automatically incorporates the influence relationship into the state transition model (step S114). Further, when the operator inputs a relationship in which the attribute state of the product at the upstream stage is transferred to the downstream stage as the product moves (step S115), the computer device automatically The relationship is incorporated into the state transition model (step S116).

  Although the Petri net has been described in this embodiment, the present invention is not limited to this as long as it models a discrete event system, and the present invention is applied to other graph models such as a directed graph and an undirected graph. Is also possible. For example, in a directed graph, a place in a Petri net model is represented by a point, and a transition is represented by a line with an arrow. A line with an arrow is a moving operation end for moving a product, that is, a token from point to point, and serves as a moving path. The arrow indicates the direction in which the token moves from line to point or from point to line. Even when the present invention is applied to a graph model having such characteristics, a series of operations are the same as the operations in the above-described Petri net model, and detailed description thereof is omitted.

(Operation support using discrete models created by discrete modeling 1)
FIG. 8 is a diagram illustrating a configuration example of an operation support apparatus for a continuous casting process. 1 is a discrete modeling unit, and as described above, the continuous casting process is divided into a plurality of stages in the product flow direction, and a state transition model of product attributes and a state transition model of equipment are created for each stage. A discrete model created by defining the influence relationship in each stage is created. In addition, if necessary, the influence relationship between the attributes of the product between the stages (arrow 31 in FIG. 3), which is an influence received from the product existing in another stage at the same time, the above-mentioned relationship in the upstream stage. The state of the attribute of the product defines a relationship (arrow 32 in FIG. 3) that is transferred to the downstream stage as the product moves.

  Reference numeral 2 denotes a reachable tree creation unit which is a first state transition diagram creation unit, which uses the discrete model created by the discrete modeling unit 1 to set an initial state for each stage, and is reachable from the initial state A reachable tree that is a state transition diagram of each stage showing is generated. 3 is an overall reachable tree creation unit which is a second state transition diagram creation unit, and is a state transition diagram of the entire continuous casting process using reachable trees of all stages created by the reachable tree creation unit 2. Create a reachable tree.

  4 is a risk matrix creation unit, which uses the reachable tree of the entire continuous casting process created by the overall reachable tree creation unit 3 to represent a risk assessment matrix that represents the relationship between the occurrence accuracy and the risk level (in this application, simply the risk matrix). To create). Reference numeral 5 denotes an input device. For example, the discrete modeling unit 1 inputs and sets various definitions when creating a discrete model, and the initial state when the reachable tree creating unit 2 creates a reachable tree is input and set. To do. An output device 6 corresponds to, for example, a display device that displays a risk matrix created by the risk matrix creation unit 4 on the screen.

  Although illustrated as one device in FIG. 8, the functional configuration shown in FIG. 8 may be realized by cooperation of a plurality of devices, for example, discrete modeling is performed by another device. .

  FIG. 9 shows a procedure for operation support by the operation support apparatus. First, a discrete model is created by the above-described discrete modeling (step S201). In the case of this example, the purpose is to present to the operator in detail the risks that may occur in the near future, including the risks that are unlikely to occur. I don't think. That is, a discrete model is created in steps S101 to S114 in FIG. 2, and steps S115 and S116 in FIG. 2 are not performed. That is, the state of the attribute of the product in the upstream stage changes with the movement of the product. A discrete model is created without incorporating the relationship (arrow 32 in FIG. 3) passed to the downstream stage.

  Next, using the discrete model created in step S201, an initial state is set for each stage, for example, the current state of each stage, and a reachable tree that can be transitioned (reachable) from the initial state is created (step) S202). As shown in FIG. 10, the reachable tree is obtained by connecting “states” (ellipses describing the states) via “transitions (corresponding to the contents of the operation)” (ellipses with dots). . FIG. 10 shows a reachable tree created from the state transition model of the TD stage (see FIG. 5). Here, the initial state is “low temperature, high viscosity, plasma heating device OFF, bubbling failure”, and the next “state” that can be reached is “low temperature, high viscosity, plasma heating when transition T1 ignites. “Device failure, bubbling failure” or “Temperature normal, high viscosity, plasma heating device ON, bubbling failure” when transition T3 is ignited (accordingly, transitions T4, T11 are also ignited). In this way, the “state” that can be reached next is sequentially obtained to create a reachable tree.

  Although the reachable tree in the TD stage has been described in detail here, the initial state is set for each of the nozzle stage, the mold stage, and the vertical region stage, and a reachable tree is created. FIG. 11 shows a reachable tree created from a state transition model (see FIG. 6) of the product temperature and the molten metal level at the mold stage, and a state transition model (FIG. 11) of the product bulging at the vertical region stage. 6)). In the mold stage, when the initial state is “low temperature, appropriate level of molten metal level”, the “state” that can be reached next is “high temperature, appropriate level of molten metal level” when transition T301 ignites, or transition T303. "Low temperature, low water level" when the fire ignites. In the vertical region stage, when the initial state is “no bulging”, the next “state” that can be reached is “with bulging” when the transition T401 is ignited. In this way, the “state” that can be reached next is sequentially obtained to create a reachable tree.

  In the meantime, the reachable tree of the TD stage in FIG. 10 is a state transition diagram in which the state transitions only in one direction (cannot return to the original state), whereas the mold stage and the vertical region stage in FIG. The reachable tree is a state transition diagram that can be freely returned to the original state. This is a state transition diagram in which the transition state T12 cannot be fired even if the state transitions due to the firing of the transition T11 because the “bubble failure” is the initial state in the TD stage, and the transition is only in one direction. . Thus, the reachable tree differs depending on how the initial state is given.

  Next, a reachable tree (one reachable tree) of the entire continuous casting process is created using the reachable trees of all stages created in step S202 (step S203).

  Here, depending on the stage, there may be a case where the influence relationship (the arrow 31 in FIG. 3) between the attributes of the product is defined between the stages, and a case where it is not defined. First, with reference to FIG. 11, a description will be given of how to create reachable trees for both stages when an influence relationship between product attributes is defined between stages. FIG. 11 uses a reachable tree created from the state transition model of the product temperature and the molten metal level at the mold stage and a reachable tree created from the state transition model of the product bulging at the vertical region stage. This shows how to create reachable trees for both stages.

  As described above with reference to FIG. 6, when there is a token at a certain place in the bulging state transition model in the vertical region stage, the transition T501 is ignited via the conditional arc. As a result, when there is a token at an appropriate place in the state transition model at the molten metal level at the mold stage, the transition T303 connected with the transition T501 by the permission synchronization arc is ignited, and the token moves to a place with a low token. Further, when there is a token in a place where there is no bulging state transition model in the vertical region stage, the transition T502 is ignited via a conditional arc. As a result, when there is a token in a low place in the state transition model of the molten metal level at the mold stage, the transition T304 connected to the transition T501 by the permission synchronization arc is ignited, and the token moves to an appropriate place.

  In this case, as shown in FIG. 11, the “state” of the mold stage and the vertical region stage is regarded as a place, “transition” is regarded as a transition, and transitions T501 and T502 that connect the stages are regarded as transitions T700 to T703. Transition ”and places P701 and P702. Modeling the “switching” where the hot water level transitions from “appropriate” to “low” only when bulging is “present” and the hot water level transitions from “low” to “appropriate” only when bulging is not present Yes. Although it does not exist in this example, the hot water level changes from “low” to “appropriate” only when the bulging is changed from “present” to “other” (for example, “somewhat present”). do not do. In order to make the transition to the “appropriate” level, the bulging state must always transit to “none”. In order to express this, modeling as shown in FIG. 11 is performed. The transition T501 is a transition that always fires when a token exists with bulging, and the transition T502 is a transition that always fires when a token exists without bulging. The place P701 is a place that becomes a condition for firing the transition T700, and the place P702 is a place that becomes a condition for firing the transition T701. The transition T700 is a transition that always fires when a token exists in the place P701, and the transition T701 is a transition that always fires when a token exists in the place P702. Further, when there is a token in the place P701, the transition T702 is ignited via the conditional arc, and as a result, the transition T304 connected to the transition T702 by the permission synchronization arc is ignited. Further, when there is a token in the place P702, the transition T703 is ignited via the condition arc, and as a result, the transition T303 connected to the transition T703 by the permission synchronization arc is ignited.

  Thereby, as shown in FIG. 12, reachable trees of both stages having the initial state “low temperature, appropriate level of molten metal level, no bulging” are created.

  Next, with reference to FIG. 13 and FIG. 14, a description will be given of how to create reachable trees of both stages when the influence relationship between the attributes of the product between the stages is not defined. Here, including the meaning of the comparison, as shown in FIG. 13, it is assumed that the influence relationship between the attributes of the product is not defined between the mold stage and the vertical region stage, and the reachable trees of both stages are defined. The case of creating will be described. In this case, the reachable tree is created with all combinations of the “state” of the mold stage and the “state” of the vertical area stage as “states”, respectively. That is, in the case of the example of FIG. 14, a reachable tree having eight “states” that are all combinations of the four “states” of the mold stage and the two “states” of the vertical region stage is created. Thereby, as shown in FIG. 14, reachable trees of both stages having the initial state “low temperature, appropriate level of molten metal level, no bulging” are created.

  As shown in FIG. 12, when the influence relationship between product attributes is defined between stages, transition is possible among all combinations of “state” of the mold stage and “state” of the vertical area stage. Only “state” will be selected. That is, the combination of “states” is limited, and the number of “states” is reduced as compared with the case where the influence relationship between the attributes of the product between the stages is not defined as shown in FIG.

  According to the above algorithm, the reachable tree of the entire continuous casting process is created using the reachable trees of all stages. This single reachable tree means a set of states in which the products and equipment of the entire continuous casting process can transition from an initial state.

  Next, using the reachable tree of the entire continuous casting process created in step S203, a risk matrix representing the relationship between the occurrence probability and the risk is created (step S204). FIG. 15 shows an example of the risk matrix. In the illustrated example, for simplicity of explanation, an example is shown in which a risk matrix is created using reachable trees of the mold stage and the vertical region stage. Create a matrix.

  The horizontal axis of the risk matrix represents the probability of occurrence, and the vertical axis represents the degree of risk. The “state” of the reachable tree of the entire continuous casting process (the reachable tree of the mold stage and the vertical area stage in the example of FIG. 15) is rearranged. It is a thing. In the horizontal axis direction, an initial state is first positioned, and then a “state” that can be reached from the initial state is positioned. The minimum number of transitions required to reach each “state” from the initial state is defined as the “distance” from the “initial state” to each “state”. The smaller the “distance”, the lower the probability of occurrence. Position to be. Here, the number of executions of transitions from the initial state is defined as “distance”. However, considering the probability of each “transition” being executed (probability of firing), etc., each “state” from the initial state is You may make it prescribe | regulate a distance.

  In the transitions connecting the initial state and each “state” in FIG. 12, transitions other than the transition of the minimum distance are removed, and the “state” is generated with a lower probability of occurrence as the “distance” from the initial state is smaller. To do.

  Further, a risk level is determined in advance for each attribute of the product, and the risk level is determined according to the combination. Here, the “state” of “high temperature, appropriate level of hot water level, no bulging” is the safest state of operation, whereas “state” of “low temperature, low hot water level, with bulging” is It becomes the most dangerous state in operation.

  By displaying and presenting such a risk matrix on the screen, it is possible to present information that is effective in operator decision making, such as estimation of trouble occurrence. In the reachable tree mapped to the risk matrix, “state of high occurrence accuracy and low risk”, “state of low occurrence accuracy and low risk”, etc. are shown, and any “state” Is comprehensively visualized, it is easy to look down on the cause of the trouble. For example, it can be recognized that the “state” located at the lower left of the risk matrix is “a state where the occurrence probability is high and the degree of danger is high”, and that attention should be paid together with the route to that state. In other words, “transition” in which the degree of danger is reduced from the initial state “low temperature, appropriate level of molten metal level, no bulging” means an operation to be performed.

  When the risk matrix is displayed on the screen, for example, the “highest occurrence probability and high risk state” may be displayed prominently. Further, as indicated by a box 1501 in FIG. 15, a route (scenario) leading to a dangerous state (or a route leading to a safe state (scenario) conversely) may be surrounded and displayed.

  Although the number of “states” is large as described above, the reachable tree of the entire continuous casting process can be obtained without defining the influence relationship between the attributes of the product between the stages (arrow 31 in FIG. 3). Can be created. That is, based on the discrete model created only in steps S101 to S112 in FIG. 2, a reachable tree for each stage is created, and a reachable tree for the entire continuous casting process is created using them to create a risk matrix. You may make it do. For reference, FIG. 16 shows an example of creating a risk matrix using reachable trees of the mold stage and the vertical region stage when the influence relationship between product attributes between stages is not defined.

(Operation support using a discrete model created by discrete modeling 2)
In the operation support 1 described above, an example in which a reachable tree indicating a state transition that can be reached from the initial state is created and presented as a risk matrix has been described. In other words, Operation Support 1 is used when it is desired to grasp the danger in the near future. A risk matrix is created under the condition that the steel remains at the same stage, and there is a possibility that a risk in the near future can occur. The purpose was to present it to the operator in detail, including the low risk. On the other hand, in the operation support 2, an example in which state transitions accompanying the progress of the continuous casting process are presented as a risk matrix will be described. This operation support 2 is used when it is desired to grasp the danger in the far future, and a risk matrix including the far future can be created in consideration of moving to the stage where the steel follows. That is, the operation support 2 does not present risks that are unlikely to occur in the near future, but can present risks to the operator in the distant future, that is, when the product moves to the subsequent stage.

  The configuration example of the operation support device for the continuous casting process is the same as that of FIG. 8, but in the case of this example, the discrete modeling unit 1 shows that the state of the product attribute at the upstream stage is accompanied by the movement of the product. Therefore, the relationship (arrow 32 in FIG. 3) to be transferred to the downstream stage is always defined.

  Then, after giving the initial state and creating the reachable tree of the entire continuous casting process by the overall reachable tree creating unit 3, the state is obtained from the reachable tree of the entire continuous casting process created by the overall reachable tree creating unit 3 ”And the“ transition ”leading to it, and the reachable tree creation unit 2 reaches the reach of each stage with the initial state as the state in which the extracted“ state ”and the“ transition ”leading to it are reflected in the discrete model The step of creating a tree and the step of creating the reachable tree of the entire continuous casting process by using the reachable trees of all stages created by the reachable tree creating unit 2 by the overall reachable tree creating unit 3 .

  FIG. 17 shows a procedure for operation support by the operation support apparatus. First, a discrete model is created by the above-described discrete modeling (step S301). In the case of this example, steps S115 and S116 in the figure are also performed, and the state of the product attribute at the upstream stage is transferred to the downstream stage as the product moves (arrow 32 in FIG. 3). ) To create a discrete model. In the operation support 2 as well, as in the operation support 1, it is preferable to define the influence relationship between the attributes of the product between the stages (arrow 31 in FIG. 3), but it is not always necessary to define it.

  Next, the initial state, for example, the current state of each stage, is set for each stage using the discrete model created in step S301, and a reachable tree for each stage is created (step S302). Next, a reachable tree (one reachable tree) for the entire continuous casting process is created using the reachable trees of all stages created in step S302 (step S303). Then, a risk matrix is created using the reachable tree of the entire continuous casting process created in step S303 (step S304). In addition, the process of step S302-S304 is the same as that of step S202-S204 of the operation support 1, The detailed description is abbreviate | omitted here.

  Next, it is determined whether or not the necessary number of times (necessary operation time) has been completed (step S305). If the required number of times has not been completed, the “state” on the risk matrix created in step S304 based on the occurrence accuracy and the risk (for example, the occurrence accuracy and the risk are quantified and the product thereof is the highest), Alternatively, the “state” artificially selected by the operator is extracted, and “transition” leading to the extracted “state” is also extracted (step S306). The “transition” and “state” not extracted here are not presented to the operator. The “state” extracted here and the “transition” leading to it need not be one, and a plurality of “states” may be extracted.

  Then, the state of the discrete model created in step S301 is changed based on the “state” extracted in step S306 and the “transition” leading to it. When the state changes, the state of the product attribute in the upstream stage is transferred to the downstream stage as the product moves (arrow 32 in FIG. 3), and the state at this time is initialized. A reachable tree for each stage is created as a state (step S307).

  Thereafter, returning to step S303, the reachable tree (one reachable tree) of the entire continuous casting process is created using the reachable trees of all the stages created in step S307 (step S303). Then, a risk matrix is created using the reachable tree of the entire continuous casting process created in step S303 (step S304). If a plurality of “states” and “transitions” leading to them are extracted in step S306, the processes of steps S307, S303, and S304 are executed for each. Although it has been described that the risk matrix is created in step S304, it is not always necessary to create the risk matrix, and “state” and “transition” leading to it are extracted from the reachable tree of the entire continuous casting process created in step S303. You may do it.

  Until the required number of times is completed in this manner, the creation of reachable trees for each stage, the creation of reachable trees for the entire continuous casting process, and the creation of the risk matrix are repeated. A risk matrix representing the relationship with the index is created (step S308). FIG. 18 shows an example of the risk matrix. The horizontal axis of the risk matrix represents the casting time, and the vertical axis represents the occurrence accuracy and the risk. On the vertical axis, A means high risk, B means high risk, C means low risk, a means high occurrence accuracy, b means high occurrence accuracy, and c means low occurrence accuracy. In FIG. 18, a state 1801 is the initial state set in step S302, and a state 1802 is the “state” extracted in step S306. States 1803 and 1804 are “states” extracted in step S306 through a single loop of steps S307, S303, and S304.

  As described above, it is possible to predict the action to be taken for each cause and the phenomenon that will occur as a result, or to predict the phenomenon that will occur if no action is taken. It is possible to support the operation of the continuous casting process, for example, by guiding the actions.

[Support for updating discrete models of continuous casting process]
Below, the update support method of the discrete model (henceforth a continuous casting model) of the continuous casting process mentioned above and the example of the apparatus used for it are demonstrated.

  FIG. 19 is a diagram showing an outline of a continuous casting model update support method and an apparatus used therefor. Reference numeral 10 denotes a continuous casting model update support device. As described below, the state transition diagram 194 created based on the trouble report 191 shows the connection with the continuous casting model 16 from the continuous casting model 16. The supplemented state transition diagram 195 is created by complementing the information. Thereby, the information required for updating the continuous casting model 16 can be presented, and the updating of the continuous casting model 16 can be supported. The update support device 10 may be configured integrally with the operation support device of the continuous casting process described above, or may be configured separately from the operation support device and connected to the operation support device.

(Trouble report)
Reference numeral 191 denotes a trouble report, which is created manually (operator) when trouble occurs in the continuous casting process. FIG. 20A shows an example of a trouble report. The trouble report 191 describes a sentence including information on the occurrence state of the trouble, the cause of the trouble, the countermeasure for the trouble, the product processed at the time of the trouble occurrence, the findings about the trouble of the manufacturing operator, and the like. . For example, in the occurrence status column, “Nozzle cross occurred immediately after the start of casting. After the start of the 3rd channel, as a result of the nozzle sticking, the speed could be increased to Vc = 1.1 m / min. An IN cross has occurred. Although the sticking is carried out but only recovers to Vc = 0.73, the cast cut is made with the remaining hot pot 50t left. In the cause column, a description such as “the nozzle was clogged because the temperature of the steel was low (Δt = + 3 ° C.)” is made. In addition, nozzle sticking is the operation | work which literally pricks a nozzle in order to eliminate the state where the nozzle was clogged with solidification of molten steel.

  The trouble report 191 is expressed as a document by the operator's tacit knowledge. The trouble report 191 is compared with the continuous casting model 16 and the content described in the trouble report 191 is compared with the continuous casting model 16. It is useful to update it to reflect it.

Here, while the trouble report 191 is a sentence mainly described in a natural sentence, the continuous casting model 16 is expressed in a Petri net form. Therefore, the trouble report 191 and the continuous casting model 16 cannot be simply compared, and there are gaps to be solved as follows when comparing the two.
1. Difference in Causal Relationship / State Transition Description Format In the trouble report 191, for example, it is expressed in words and sentences such as “I was overheated”. On the other hand, in the continuous casting model 16, for example, it is expressed as a relationship between states such as “heating → burning”.
2. Difference in state detail level In the trouble report 191, the state can be expressed in detail, for example, “the temperature is high and the upper limit value is exceeded”. In contrast, the continuous casting model 16 expresses a discrete and determined state such as “temperature (high, normal, low)”.
3. Difference in granularity of expression Here, the granularity of expression is considered to be large when the number of states included in the proposition is large. In the trouble report 191, for example, there is an expression that summarizes a plurality of states such as “I have a cold”. This is considered to be a large granularity of expression. On the other hand, in the continuous casting model 16, for example, the state is expressed by being decomposed into individual states such as “head hurts + throat hurts + fever”. This individual state is considered to have a small granularity of expression.
4). Difference in definable categories In the trouble report 191, for example, “after 3 o'clock, after going to the toilet ...” describes the person's action + time / judgement. On the other hand, in the continuous casting model 16, for example, only the state of the product (steel) and equipment is expressed as “high temperature, equipment failure”.
5. Differences of described states In the trouble report 191, only the state relating to the trouble is described, for example, “burn, heating”. On the other hand, in the continuous casting model 16, all the states of the continuous casting model are defined.

  In order to compare the trouble report 191 and the continuous casting model 16 in the same dimension, it is necessary to eliminate the gap described above. Therefore, as shown in FIG. 19, based on the trouble report 191, three intermediate processes, that is, a proposition relation diagram 192, an aggregate proposition relation diagram 193, and a state transition diagram 194 are sandwiched between the continuous casting model 16. I am doing so.

(Proposition related diagram)
The propositional related diagram 192 is a flowchart in which sentences of the trouble report 191 are divided into propositions and connected by arrows, and are created manually by handwriting or using a creation support device as described later. In the propositional related diagram 192, in order to eliminate the above-mentioned “1. Difference in description format of causal relations / state transitions”, sentences described in the trouble report 191 are represented as a set of meanings (representing one meaning). Units) are divided into propositions, which propositions are connected to which propositions, and the relationship is determined. For example, if it is a sentence that says “I was overheated”, I divided it into a proposition, such as “I overheated / it was overheated,” and “I overheated” → (Causal) Define the relationship between the propositions as follows.

  In the trouble report column 191, “Nozzle cross occurred immediately after casting started. As a result of nozzle sticking after starting the 3rd channel, the speed was increased to Vc = 1.1 m / min. After that, IN crossing occurred again, but it was recovered only until Vc = 0.73, so the cast cut was made with the remaining hot pot of 50t left in the cause column. When there is a description that “the nozzle is clogged because of (Δt = + 3 ° C.)”, it is divided into propositions as shown in FIG. 20B.

  As a result of analyzing past trouble reports, when the sentences described in the trouble report are divided into propositions, almost all the propositions are `` state '', `` work process '', `` work judgment '', `` product specification '', `` It was found that it was classified into six types, “insufficiency of equipment” and “others (time zone)”. Therefore, when a sentence is divided into propositions, the sentence is divided into units applicable to these six types of classification.

  FIG. 21 shows a proposition relation diagram 192 in this example. In the proposition relation diagram 192, the propositions are connected by arrows to define the relationship. As a result, a so-called scenario of trouble occurrence can be expressed. By using relationships such as “causal relationship”, “work determination”, “time progress / work progress”, “timing”, and “detailed explanation” as the relationship between propositions, the contents of the trouble can be expressed. The “causal relationship” arrow is used when the proposition behind the arrow causes the proposition ahead of the arrow. The “work judgment” arrow is used when the result of the situation determination by the operator or the operation performed by the operator is the proposition at the end of the arrow with respect to the state represented by the proposition after the arrow. The arrow of “time progress / work progress” is used to connect between tasks that proceed in a normal flow, and propositions that are temporally related but have no causal relationship. The “timing” arrow is used to connect a proposition to a proposition that explains when the proposition occurred. The “detailed explanation” arrow is used to connect a proposition to a proposition explaining details of the contents of the proposition.

  Furthermore, regarding the “causal relationship”, “(1) a condition where a certain state transition occurs (referred to as“ condition ”in FIG. 21)”, “(2) a state transition transmitted by the steel flow”, “(3) operation” Expected state transition (referred to as “operation effect” in FIG. 21) ”,“ (4) When there was no operation effect (indicated as “no operation effect” in the figure) ”,“ (5) Suppressing state change And “(6) State transitions that occur at the same time”. “(1) A condition under which a certain state transition occurs” is used when the proposition after the arrow represents a condition in which the state of the proposition after the arrow becomes a state. “(2) State transition transmitted by steel flow” is used when the state represented by the proposition after the arrow becomes the state represented by the proposition at the end of the arrow when transmitted to the next stage by the steel flow. “(3) Operation and expected state transition” is used when the proposition after the arrow represents the operation, and the proposition after the arrow represents the state change expected by the operation. In “(4) When the operation has no effect”, the proposition after the arrow indicates the operation, and the proposition after the arrow does not indicate the state change expected by the operation (that is, the state changes). Not used). “(5) Condition for suppressing state change” is used when the state represented by the proposition after the arrow is represented and the state represented by the proposition after the arrow is suppressed. In this case, the proposition at the end of the arrow clearly states that no state change has occurred, such as “temperature did not rise”. “(6) State transition occurring simultaneously” is used when the state transition represented by the proposition after the arrow and the state transition represented by the proposition after the arrow occur simultaneously.

  In the example of FIG. 21, for example, the proposition “immediately after casting” and the proposition “nozzle cross has occurred” are related by “timing”. In addition, the proposition “nozzle cross has occurred” and the proposition “result of performing nozzle sticking” are related by “work determination”. In addition, the proposition “the result of the nozzle sticking” and the proposition “the speed could be increased to Vc = 1.1 m / min” are related by “causal relationship (operation effect)”.

  It should be noted that the expression is unified when the proposition relation diagram 192 is created. For example, “IN cross” described in the trouble report 191 is a nozzle cross (IN has the same meaning as a nozzle), and the expression is unified to “nozzle cross”.

(Consolidated proposition-related diagram)
The aggregated proposition relation diagram 193 is obtained by manually combining the propositions in the proposition relation diagram 192 and expressing the occurrence of trouble by concatenation of the propositions. The consolidated proposition relation diagram 193 is created by converting the proposition relation chart 192 in order to express the contents of the trouble report 191 on a computer in a form that can be understood by a person. When creating the aggregate proposition relation diagram 193, the propositions representing the same contents are aggregated into one expression. At this time, the contents described in the trouble report 191 are expressed in a format that can be understood by the computer by making the expression to be aggregated into an expression corresponding to the continuous casting model. That is, in the continuous casting model 16, the state transition is expressed as a phenomenon in which the token moves between places, and is described in the trouble report 191 in a form that can be understood by a computer by associating each proposition with a place or token. Can be expressed.

  The aggregated proposition relevant diagram acquisition unit 11 of the update support apparatus 10 acquires the aggregated proposition relevant diagram 193. The aggregated proposition relation diagram 193 may be created on the update support apparatus 10, or the aggregated proposition relation chart 193 created on another computer may be input to the update support apparatus 10.

  FIG. 22 shows an aggregate proposition relation diagram (before state transition arrangement). In the proposition relation diagram 192 of FIG. 21, the proposition “nozzle clogged” described in the cause and the proposition “nozzle cross has occurred” described at the top of the occurrence situation are the same proposition, Can be aggregated.

  In addition, in order to eliminate the above-described “2. Difference in level of detail”, propositions related in “detailed explanation” are summarized. The propositions related in the “detailed explanation” are that one is abstract and the other is concretely expressed, but only the same phenomenon is expressed in different words. In the proposition relation diagram 192 of FIG. 21, since the proposition “because the temperature of the steel was low” and the proposition “Δt = + 3 ° C.” are related by “detailed explanation”, a discrete and determined state is expressed. Summarize the proposition that “the temperature of steel is low”.

  Further, the propositions in which the states are expressed in detail are aggregated into the propositions in which discrete and determined states are expressed. The proposition “nozzle cross has occurred” and the proposition “nozzle cross has occurred again” described in the proposition relation diagram 192 of FIG. 21 are collected into the proposition “nozzle cross”. Similarly, the proposition “Vc = 1.1 m / min” in the proposition relation diagram 192 of FIG. 21, for example, is the proposition “ordinary casting speed” and the proposition “recovers only up to Vc = 0.73” Are summarized in the proposition “No casting speed increased”, and the proposition “Cast cut with remaining hot pot 50t” and “Cast cut”.

  The state transitions are arranged for the aggregated proposition relevant diagrams (before state transition rearrangement) created so far, and the aggregated proposition relevant diagram (after state transition rearrangement) 193 is completed as shown in FIG. In the aggregated proposition relation diagram of FIG. 22 (before state transition arrangement), the proposition “steel temperature is low” is related only to the proposition “nozzle cross” which means the first nozzle cross. It is thought that the low is the cause of the second nozzle cross. Therefore, as shown in FIG. 23, the proposition “the temperature of the steel is low” is also related to the proposition “nozzle cross” which means the second nozzle cross.

  Further, in order to eliminate the above-mentioned “3. Difference in granularity of expression”, intermediate states not described in the trouble report 191 are complemented, and the relationship between propositions is arranged. As a result of the nozzle sticking, the clogging of the nozzle was eliminated and the flow rate of steel was increased, so it is considered that the casting speed was increased. Therefore, as shown in FIG. 23, between the proposition “Implement nozzle nozzle” and the proposition “Normal casting speed”, the proposition “Nozzle normal” which means an intermediate state and the proposition “Normal steel flow rate” are complemented. To do. Similarly, as a result of nozzle tack, the nozzle cross was not eliminated, so it is considered that the casting speed did not increase. Therefore, as shown in FIG. 23, the proposition “No nozzle cross recovery” meaning an intermediate state is complemented between the proposition “Implement nozzle nozzle” and the proposition “No increase in casting speed”. At this time, it goes without saying that the relationship between the complemented proposition and other propositions is defined.

Here, in order to eliminate the fluctuation of the expression existing in the natural sentence from the trouble report 191 and the proposition related diagram 192 and to make the contents of the trouble comprehensible by the aggregated proposition related diagram 193, the proposition is displayed on the update support apparatus 10. Prepare a list of For a list of propositions,
[A] A list of propositions representing states that are defined in the continuous casting model, or not defined at the present stage but need to be defined by the operator (see FIG. 24A)
For example, the proposition “Bubbling on” in the first line refers to an operation of blowing argon gas to lower the temperature of the steel (liquid) as “Bubbling”, and the proposition “Bubbling on” starts the operation of blowing this argon gas. Means that.
[B] A list of propositions (see FIG. 24B) that are not defined in the continuous casting model and that are not defined but represent a state necessary for expressing the content of the trouble is created. When describing the aggregated proposition relation diagram 193, by selecting a proposition from the list [a] and [b] of these propositions, the contents of the trouble occurrence in the form corresponding to the state defined in the continuous casting model 16 are displayed. Can be described.

  If the propositions described in the proposition relation diagram 192 do not exist in the proposition lists [a] and [b], they are described as new propositions in the proposition lists [a] and [b], and then in the aggregate proposition relation diagram 193. Describe. As a result, the proposition lists [a] and [b] are updated every time the aggregated proposition relation diagram 193 is created. When the proposition list [a] “proposition representing a state that is not defined at the current stage but needs to be defined by the operator” is newly set, the proposition is updated to the continuous casting model 16. It becomes contents to do.

  The aggregated proposition relation diagram 193 created in this way is used for the conversion to the state transition diagram 194 as described below. However, the trouble is represented by a diagram and can be understood by humans. Therefore, by storing it in the update support device 10 as it is, it can be used for the purpose of the operator obtaining past trouble information when necessary.

(State transition diagram)
The state transition diagram 194 represents the state transition in trouble using only the state of the product or equipment defined in the continuous casting model based on the aggregate proposition relation diagram 193, and the state transition diagram of the update support apparatus 10 It is created by the creation unit 12. The state transition diagram 194 is created so that the trouble report 191 and the continuous casting model 16 can be compared, and the contents described in the trouble report 191 are the products and equipment defined in the continuous casting model 16. It is expressed on a computer corresponding to the state. Therefore, the state transition diagram 194 is described only with a proposition representing a state existing in the continuous casting model 16 or to be updated.

  In the state transition diagram 194, only the state of the product or equipment is described in order to eliminate the above described “4. FIG. 25 shows a state transition diagram 194 in this example. The propositions “immediately after the start of casting”, the propositions “after the start of the third channel”, and the propositions “after the start of the fifth channel” described in the aggregated proposition related diagram 193 in FIG. It is not a proposition that represents the state of things or equipment. Therefore, as shown in FIG. 25, these propositions “immediately after the start of casting”, propositions “after the start of the third channel”, and propositions “after the start of the fifth channel” are excluded.

  Further, the proposition “cast cut” described in the consolidated proposition relation diagram 193 of FIG. 23 is a proposition representing a state that is not defined in the continuous casting model and is not defined. Therefore, as shown in FIG. 25, this proposition “cast cut” is excluded. Whether a proposition represents a state that is not defined in the continuous casting model and that is not defined can be determined by referring to the list [b] of the proposition shown in FIG.

(Complementary state transition diagram)
The state transition diagram 194 is created for the purpose of comparing the trouble report 191 and the continuous casting model 16. Therefore, the supplementary state transition diagram creation unit 13 of the update support apparatus 10 creates the supplemental state transition diagram 195 by supplementing the information from the continuous casting model 16 in the state transition diagram 194 so that the connection with the continuous casting model 16 can be understood. To do. The output unit 14 of the update support apparatus 10 outputs the complementary state transition diagram 195 and presents it through, for example, a display device (not shown). FIG. 26 shows a complementary state transition diagram 195 in this example.

  When information is supplemented from the continuous casting model 16 in the state transition diagram 194, the relationship between propositions represented by arrows in the state transition diagram 194 and the correspondence relationship with the continuous casting model 16 are used. As described above, the propositions are connected by arrows indicating five kinds of relations, and the state transition diagram 194 uses three kinds of "causal relation", "work judgment", and "time progress / work progress". is there. Hereinafter, the correspondence between these relationships and the continuous casting model 16 will be described.

  What is represented by an arrow of “work judgment” is an operation performed by judging the situation, the state behind the arrow represents the state, and the tip of the arrow represents the operation.

  What is expressed by an arrow of “time progress / work progress” is a state transition which is not directly related to the causal relationship but is temporally related. Therefore, the state expressed by the propositions before and after this arrow is not related on the continuous casting model 16.

  As described above, the “causal relationship” arrows are expected to be “(1) conditions under which a state transition occurs”, “(2) state transition transmitted by steel flow”, and “(3) operation”. "(4) When there is no effect of operation", "(5) Condition for suppressing state change", and "(6) State transition that occurs simultaneously".

(1) Conditions under which a certain state transition occurs This represents a condition under which a state transition occurs in which the proposition after the arrow is expressed by the proposition after the arrow. An example of this correspondence is shown in FIG. In the continuous casting model 16, it is expressed by a combination of a conditional arc and a permission synchronous arc.

(2) State transition transmitted by the steel flow This indicates that the state behind the arrow becomes the state of the tip of the arrow when transmitted to the next stage by the steel flow. An example of this correspondence is shown in FIG. In the continuous casting model 16, it is expressed using a normal arc. In this case, when the transition is ignited, the “high steel viscosity” state of the mold stage is directly transmitted to the lower nozzle stage to indicate the “low steel flow rate” state.

(3) Operation and Expected State Transition The operation after the arrow indicates the state change expected by the operation. An example of this correspondence is shown in FIG. In the continuous casting model 16, a place represents a static state, and a transition represents a state transition therebetween. The action that the operator performs on the equipment is expressed as a transition that connects the states. This shows that nozzle clogging has been eliminated as a result of nozzle sticking.

(4) When there is no effect of operation The operation after the arrow indicates that the state transition expected by the operation does not occur. An example of this correspondence is shown in FIG. When there is a possibility that the expected state change may not be obtained by the operation, two transitions representing the same operation are connected from the place, and one of them is connected to the place representing the expected operation. In this example, there are cases where the nozzle does not become normal by performing the operation “nozzle tack” from the state of “nozzle is clogged”, so if “nozzle tack” is represented from the place representing the clogging, the transition Keep two. Then, one side is connected to a place representing a state where the “nozzle is normal”. When there is a token in “nozzle clogging”, one of the two “nozzle tacks” at the top and bottom ignites. When the upper transition fires, the nozzle is normal, and when the lower transition fires, the state of the nozzle does not change. By setting the establishment of which transition is fired, the probability that the operation will be effective can be expressed on the Petri net.

(5) Conditions for inhibiting state change The state after the arrow indicates that the state change represented by the tip of the arrow is inhibited. An example of this correspondence is shown in FIG. In the continuous casting model 16, an arrow indicating a condition for suppressing the state change is expressed by a suppression arc.

(6) State transitions that occur at the same time The state transition that follows the arrow and the state transition that precedes the arrow occur simultaneously. An example of this correspondence is shown in FIG. In the continuous casting model 16, it is expressed by a synchronous arc expressing that one transition is ignited simultaneously. However, state transitions occur at the same time, but when the causal relationship is one-way, it is expressed not by a synchronous arc but by a permitted synchronous arc. When the state transition expressed by the proposition after the arrow occurs, the state transition expressed by the proposition after the arrow occurs, but conversely, the causal relationship is expressed by the proposition after the arrow. This means that the state transition represented by the proposition after the arrow does not necessarily occur.

  In the case of this example, from the continuous casting model 16, as shown in FIG. 26, the information about the influence relationship between the attribute state of the product and the state of the equipment, that is, the causal relationship information is complemented, and the complementary state transition diagram Have created. In addition, a complementary state transition diagram may be created by supplementing the state transition diagram with information about the attribute state of the product, that is, information about the state of the attribute, from the continuous casting model 16. In addition, a supplementary state transition diagram may be created by supplementing the state transition diagram with information on the state of the equipment, that is, information on the state of the equipment, from the continuous casting model 16.

  Thus, using the relationship between the propositions represented by the arrows in the state transition diagram 194 and the correspondence relationship of the continuous casting model 16, the state transition diagram 194 is supplemented with information from the continuous casting model 16 to complement the state transition diagram. 195 can be created, so that information on how the relationship between the states related to the occurrence of the trouble is defined on the continuous casting model 16 can be presented to the operator in an easily understandable manner.

  In addition, the update unit 15 of the update support apparatus 10 uses the state, arc, and transition defined by the place for the continuous casting model 16 based on the complementary state transition diagram 195 created by the complementary state transition diagram creation unit 13. The continuous casting model 16 is updated by adding or correcting the represented causal relationship.

  FIG. 33 is a diagram showing an aggregate proposition relation diagram 193 created from a proposition relation chart 192 created from a trouble report. The propositions “7:20”, “nozzle set”, and “cast start”, which are propositions representing state change timings, are excluded from this aggregated proposition relevant diagram 193. Also, “IN residual heat start”, “IN residual heat end”, “cast knitting change”, and “secondary trouble concerns” are excluded that are not defined in the continuous casting model 16 and represent undefined states. As a result, a state transition diagram 194 is created as shown in FIG.

  Then, the information is supplemented from the continuous casting model 16 in the state transition diagram 194 of FIG. 34, and a complemented state transition diagram 195 is created as shown in FIG. The regions on the left and lower sides of the dotted line in FIG. 35 are information supplemented from the continuous casting model 16. In this complementary state transition diagram 195, the propositions “nozzle normal”, “nozzle uneven clogging”, and “flow drift” originally existed in the continuous casting model 16, whereas the proposition “powder molten layer” surrounded by a one-dot chain line Is a proposition that expresses the state that the operator has determined that it needs to be defined, although it is not defined at this stage. The update unit 15 of the update support device 10 expresses the propositions “powder melt layer is enlarged”, “pump melt layer” and the relationship in a Petri net format, and updates to the continuous casting model 16. Specifically, as shown in FIG. 36, a Petri net is added to the mold stage of the continuous casting model 16 to connect the place where the molten layer is enlarged and the place where the molten layer is normal via the transition. .

  As described above, the state transition diagram 194 is created based on the trouble report 191 created when trouble occurs in the continuous casting process, and the state transition diagram 194 is supplemented with information from the continuous casting model 16. Therefore, the trouble report 191 and the continuous casting model 16 can be compared. As a result, it is possible to assist the updating so that the content described in the trouble report 191 is reflected in the continuous casting model 16.

(Support for creating proposition-related diagrams)
As described above, the proposition relation diagram 192 is created by connecting the propositions obtained by dividing the sentence of the trouble report 191. Hereinafter, support for the creation of the proposition relation diagram 192 will be described.

FIG. 37 is a diagram illustrating a configuration of a proposition relation diagram creation support apparatus 370. The proposition relevant figure creation support apparatus 370 is configured by a computer including a CPU, a ROM, a RAM, and the like. On this creation support apparatus 370, the user can create a proposition relevant diagram 192 by connecting propositions obtained by dividing sentences of the trouble report 191.
Reference numeral 371 denotes a relationship search unit. When the user connects propositions on the creation support apparatus 370, the relationship described in the continuous casting model 16 and the proposition interval that is not described in the continuous casting model 16 but is defined in advance. Based on the relationship, the relationship between propositions is searched and presented.
Reference numeral 372 denotes a route search unit, and when the user connects the propositions on the creation support apparatus 370, the relationship described in the continuous casting model 16 and between the propositions that are not described in the continuous casting model 16 but are defined in advance. Based on the relationship, the path between propositions is searched and presented.
Reference numeral 373 denotes a restricting unit that restricts the relationship between propositions according to a predetermined rule when the user connects propositions on the creation support apparatus 370.
Reference numeral 374 denotes a proposition search unit that searches and presents a proposition as a starting point based on the continuous casting model 16 while interpolating the proposition.
Reference numeral 375 denotes an input device such as a keyboard and a mouse, and 376 denotes a display device.

An example of a procedure for creating the proposition relevant diagram 192 using the creation support apparatus 370 will be described with reference to FIGS. 38 and 39A to 39E.
FIG. 38 shows an example of a trouble report. In this trouble report 191, in the column of occurrence status, “Start thin cast double casting. Cast at Vc × for higher temperature (ΔT + ○). Lower upper nozzle Ar flow rate □□, back pressure is less ◇◇ was low (no Ar leak), but the TD-SN opening gradually started to open from the middle to the end of the pot injection, but the temperature after the 2nd channel treatment was higher at + △ ° C, and the second series was cast. Although it was judged that it was possible to continue casting, the TD-SN opening opened after the 2nd injection, so it did not recover, but the pot injection was stopped with the hot pot remaining hot water for TD relief. "Cast cut". In the cause column, there is a description “squeezing by TD re-preheating / reoxidation, and squeezing is promoted by low speed casting by increasing the first channel ΔT”.

The creation support screens illustrated in FIGS. 39A to 39E are displayed on the display device 376 of the creation support device 370. The user creates a proposition relevant figure 192 from the trouble report 191 on the creation support screen.
As shown in FIG. 39A, the creation support screen has a proposition relevant diagram creation screen 391. Further, the creation support screen has a list display column 392 for displaying a list of propositions, and a list up column 393 for listing the propositions selected from the list display column 392. The list display column 392 displays a list of propositions that have been input in the past. If the trouble report 191 for which the proposition relation diagram 192 is to be created does not include a proposition already input in the past, the user needs to define a new proposition in the list display field 392.
When the user selects a proposition from the list display column 392, the proposition is listed in the list-up column 393 and displayed on the proposition relevant diagram creation screen 391.
Taking the trouble report 191 in FIG. 38 as an example, the proposition “cast start” corresponding to the proposition “start thin-sheet cast double casting” is selected from the list display column 392. As a result, as shown in FIG. 39A, the proposition “cast start” 394a is displayed on the proposition relevant diagram creation screen 391.
Next, the proposition “continuous” is displayed on the proposition relevant diagram creation screen 391 by selecting the proposition “high temperature of steel in the continuous casting part” corresponding to the proposition “for temperature increase (ΔT + ○)” from the list display column 392. “High temperature of steel in casting part” 394b is displayed.
Similarly, the propositions 394c to 394o are selected from the list display column 392 in the order in which they appear in the trouble report 191 and displayed on the proposition relevant diagram creation screen 391. In other words, the proposition “slow extraction speed” 394c corresponding to the proposition “casting with Vc ×”, the proposition “low upper nozzle Ar amount” 394d, “the upper nozzle Ar flow rate is low with □□”, “ Proposition corresponding to the proposition “the back pressure was low as ◇◇” “upper nozzle Ar back pressure is low” 394e, proposition corresponding to the proposition “middle pot to late pot injection” 394f, “pan pot injection” 342g, “proposed end of injection” 394g, proposition “sliding nozzle opening large” 394h corresponding to the proposition “TD-SN opening has begun to open”, “proposed after second channel processing” 394i , Corresponding to the proposition “Temperature is high at + Δ ° C.”, the proposition “High temperature of steel in the continuous casting part” 394j, “The TD-SN opening has opened” Ride nozzle opening large 394k, the proposition “nozzle pecking” 394l corresponding to the proposition “performs sticking”, the proposition “sliding nozzle opening large” 394m, “TD relief” Therefore, the proposition “cast cut” 394n corresponding to the proposition “Remaining hot pot hot water is left and cast cut” is selected from the list display column 392 and displayed on the proposition relevant diagram creation screen 391. Also, from the list column 392, select the proposition “nozzle narrow” 394o corresponding to the proposition “squeezing by TD re-preheating / reoxidation and squeezing aid by low-speed casting by increasing the first channel ΔT” in the cause column. It is displayed on the diagram creation screen 391.
In the example shown in the figure, an example in which a circle is displayed on the proposition relevant diagram creation screen 391 is shown. However, the display method is not limited. For example, the proposition is displayed so as to be surrounded by a square as shown in FIG. It does not matter even if it is in a form.

  In the proposition relation diagram creation screen 391, the propositions 394a to 394o are arranged downward in the order selected by the user from the list display field 392. However, the user may change the arrangement via the input device 375. Is possible. For example, a rule is set such that a proposition classified as “work process” is arranged on the left side and a proposition in the countermeasure column of the trouble report 191 is arranged on the right side, and the user changes the arrangement accordingly. In the example of FIG. 39A, the proposition “cast start” 394a classified as a work process, the proposition “middle pot injection” 394f, “late pot injection end” 394g, and “after second channel processing” 394i are rearranged. Yes. In addition, the proposition “nozzle narrow” 394o in the cause column of the trouble report 191 is rearranged on the right side.

If the propositions 394a to 394o are arranged on the proposition relevant diagram creation screen 391 as shown in FIG. 39A, the user connects the propositions with arrows via the input device 375 as shown in FIG. 39B.
At this time, the relationship search unit 371 presents a relationship between propositions based on a relationship described in the continuous casting model 16 and a relationship between propositions that are not described in the continuous casting model 16 but are defined in advance. The relationship described in the continuous casting model 16 and the relationship between propositions have correspondence relationships as shown in FIGS. 27 to 32 and FIGS. 41A to 41C, for example.
As shown in FIG. 41A, in the relationship between propositions “causal relationship (condition, condition for suppressing state change, simultaneous state transition)”, if the proposition as the starting point is “steel state”, the end point The proposition is "steel condition" or "equipment condition". If the proposition as the starting point is “equipment state”, the proposition as the end point is “steel state”. Further, if the proposition as the starting point is “operation variable”, the proposition as the end point is “steel state” or “equipment state”. Further, as shown in FIG. 41B, in the relation “work judgment” between propositions, if the proposition as the starting point is “steel state”, the proposition as the end point is “operation variable” or “operation change”. . Further, if the proposition as the starting point is “equipment state”, the proposition as the end point is “operation variable”. If the proposition as the starting point is “operation variable”, the proposition as the end point is “operation variable” or “operation change”. If the proposition as the starting point is “change operation”, the proposition as the end point is “operation variable” or “change operation”. As shown in FIG. 41C, in the relationship “timing” between propositions, if the proposition as the starting point is “time or work process”, the proposition as the end point is “other than time”. In this way, rules are defined in advance for the relationship between propositions. 41A to 41C show relations between propositions such as “causal relation”, “work judgment”, and “timing” between propositions, but “time progress / work progress” and “detailed explanation”. However, although the explanation is omitted, a rule is set in advance in the same manner.
Thus, as shown in FIG. 39B, for example, when the proposition “cast start” 394a and the proposition “high temperature of steel in the continuous casting portion” 394b are connected by an arrow, the interval between the propositions can be understood from FIG. 41C. It is automatically presented that there is a “timing” relationship.

The path search unit 372 also connects paths between propositions connected by the user based on the relationships described in the continuous casting model 16 and the relationships between the propositions that are not described in the continuous casting model 16 but are defined in advance. If there are a plurality of routes, the plurality of routes are presented. As shown in FIG. 40, it is assumed that the trouble report 191 describes a state change from state C to state B. In this case, referring to the relationship described in the continuous casting model 16 and the relationship between propositions that are not described in the continuous casting model 16 but are defined in advance, the state B from the state C through the state E and the state D If there is a route that changes state, the route is also presented. Although not described in the trouble report 191, if there is a route that changes from state C to state B via state A and operation D, the route is also presented. Although it is not in the trouble report 191, there is a possibility that the operation D is actually performed.
In this way, when there are a plurality of routes between propositions, the list may be displayed and the user may select from there.
As a result, as shown in FIG. 39B, the relationship between propositions displayed on the proposition relevant diagram creation screen 391 can be easily and reliably defined.

Here, in FIG. 39B, the relationship between the proposition “large slide nozzle opening” 394k and the proposition “nozzle pecking” 394l is not automatically presented by the relationship search unit 371 and the route search unit 372, and the user A relationship needs to be defined.
At this time, the restricting unit 373 restricts the relationship between propositions according to a predetermined rule. As shown in FIGS. 41A to 41C, rules are set in advance for the relationship between propositions.
Returning to FIG. 39B, since the relationship between the proposition “large slide nozzle opening” 394k and the proposition “nozzle pecking” 394l is “equipment state” → “operation variable”, the relationship is “work determination”. It becomes only. Therefore, the restriction unit 373 restricts the relationship between the proposition “large slide nozzle opening” 394k and the proposition “nozzle pecking” 394l to “work determination”.
The method of restriction is not particularly limited. For example, a relationship according to the rule may be presented to the user. Alternatively, when the user tries to define a relationship that does not follow the rule, the user may be notified that the relationship does not follow the rule. For example, if the user attempts to define the relationship between the proposition “large slide nozzle opening” 394k and the proposition “nozzle pecking” 394l as “causal relationship”, the user is notified that the relationship does not conform to the rules.
As a result, as shown in FIG. 39C, it can be easily and reliably defined that the relationship between the proposition “large slide nozzle opening” 394k and the proposition “nozzle pecking” 394l is “work determination”.

Here, in FIG. 39C, the user does not know which proposition “nozzle narrow” 394o should be connected with an arrow.
At this time, the proposition search unit 374 interpolates the proposition based on the continuous casting model 16 with a proposition (proposition “nozzle narrow” 394o in the example of FIG. 39C) as a start point and an end point connected thereto. Explore. If there are a plurality of routes, a list of the routes may be displayed, and the user may select from the list.
In FIG. 39D, the proposition “nozzle narrow” 394o passes through the interpolated proposition “nozzle flow rate low” 39p and the user has selected a path leading to the proposition “sliding nozzle opening large” 394k.

The proposition relation diagram 192 is created as described above. For example, after the state shown in FIG. 39D is reached, the user may notice a relationship between new propositions. In this case, the user can newly define a relationship. FIG. 39E shows a state in which the user connects the proposition “slow extraction speed” 394c to the proposition “nozzle narrow” 394o with an arrow and defines the relationship “causal relationship”.
As described above, when the proposition relevant figure 192 is created from the trouble report 191, the creation can be supported.

  The present invention supplies software (program) for realizing the function of the discrete model update support method or apparatus of the continuous casting process of the present invention to a system or apparatus via a network or various storage media. It can also be realized by a computer (or CPU, MPU, etc.) reading and executing a program.

  In the above embodiment, the continuous casting process has been described as an example. However, the present invention is applicable to any manufacturing process in which a continuous product flows continuously. For example, hot rolling (a steel plate flows continuously) or petroleum It can also be applied to plants (liquid flows continuously).

  10: Continuous casting model update support device, 11: Aggregate proposition relevant diagram acquisition unit, 12: State transition diagram creation unit, 13: Complementary state transition diagram creation unit, 14: Output unit, 15: Update unit, 16: Continuous casting Model, 191: Trouble report, 192: Proposition related diagram, 193: Aggregate proposition related diagram, 194: State transition diagram, 195: Complementary state transition diagram, 370: Creation support device, 371: Relationship search unit, 372: Route search Part, 373: restriction part, 374: proposition search part, 375: input device, 376: display device

Claims (15)

For a manufacturing process in which a continuous product flows continuously, a state transition model of the product attribute and a state transition model of the facility are created, and the influence between the state of the product attribute and the state of the facility A method for supporting an update of a discrete model of a manufacturing process, which supports an update of a discrete model created by defining a relationship,
It is a trouble report created when trouble occurs in the manufacturing process, the trouble occurrence status, the cause of trouble, countermeasures for trouble, the product processed at the time of trouble occurrence, trouble of the manufacturing operator A procedure to obtain an aggregate proposition-related diagram created based on a trouble report, which is a sentence containing at least information about the findings of
State transition diagram representing state transition of the manufacturing process in trouble using only the attribute state of the product and the state of equipment defined in the discrete model based on the acquired aggregate proposition relation diagram With steps to create
In the created state transition diagram, from the discrete model, information about the state of the product attribute, information about the state of the equipment, and between the state of the product attribute and the state of the equipment A procedure for creating a complementary state transition diagram by complementing at least one of the information on the influence relationship;
A procedure for outputting the created complementary state transition diagram;
Using the created complementary state transition diagram, the discrete model of the manufacturing process has an update procedure that is addition or correction of state and causal relationship,
The aggregate proposition relation diagram is a representation in which the trouble report text is divided into propositions corresponding to the representation of the discrete model, and is represented by a flowchart connecting the propositions, and these propositions are associated with the discrete model. An update support method for a discrete model, characterized by being summarized as   The discrete model divides the manufacturing process into a plurality of stages in the flow direction of the product, creates a state transition model of the attribute of the product and a state transition model of equipment for each stage, and each stage The discrete model update support method according to claim 1, wherein the model is a discrete model created by defining an influence relationship between an attribute state of the product and a state of the facility.   3. The discrete model update support method according to claim 1, wherein the discrete model is constructed using a Petri net model.   When the user connects the propositions in which the trouble report sentences are separated, the creation support means includes a relationship described in the discrete model and a relationship between propositions that are not described in the discrete model but are defined in advance. 4. The method for supporting the update of a discrete model according to any one of claims 1 to 3, further comprising a procedure for searching and presenting a relationship between propositions on the basis of.   5. The creation support means further includes a procedure for restricting a relationship between propositions according to a predetermined rule when a user connects propositions in which sentences of the trouble report are separated. The discrete model update support method according to any one of the above.   When the user connects the propositions in which the trouble report sentences are separated, the creation support means includes a relationship described in the discrete model and a relationship between propositions that are not described in the discrete model but are defined in advance. 6. The method for supporting the update of a discrete model according to claim 1, further comprising a procedure for searching for and presenting a route between propositions based on.   7. The method according to claim 1, wherein the creation support means further includes a procedure for searching and presenting a proposition as a start point connected to a proposition based on the discrete model while interpolating the proposition. The discrete model update support method according to any one of the preceding claims. For a manufacturing process in which a continuous product flows continuously, a state transition model of the product attribute and a state transition model of the facility are created, and the influence between the state of the product attribute and the state of the facility An update support device for a discrete model of a manufacturing process that supports an update of a discrete model created by defining a relationship,
It is a trouble report created when trouble occurs in the manufacturing process, the trouble occurrence status, the cause of trouble, countermeasures for trouble, the product processed at the time of trouble occurrence, trouble of the manufacturing operator An aggregated proposition relevant diagram acquisition means for acquiring an aggregated proposition relevant diagram created based on a trouble report that is a sentence including at least information about
Based on the aggregate proposition relation diagram acquired by the aggregate proposition relation diagram acquisition means, the state transition of the manufacturing process in trouble is expressed by using only the attribute state of the product and the state of equipment defined in the discrete model. State transition diagram creation means for creating a state transition diagram that is
In the state transition diagram created by the state transition diagram creating means, from the discrete model, information about the attribute state of the product, information about the state of the facility, state of the attribute of the product and the facility A complementary state transition diagram creating means for creating a complementary state transition diagram by complementing at least one of the information on the influence relationship between the state and the state;
Output means for outputting the complementary state transition diagram created by the complementary state transition diagram creating means;
Using the complementary state transition diagram created by the complementary state transition diagram creating means, an update means for performing an update that is addition or correction of the state and causal relationship to the discrete model of the manufacturing process,
The aggregate proposition relation diagram is a representation in which the trouble report text is divided into propositions corresponding to the representation of the discrete model, and is represented by a flowchart connecting the propositions, and these propositions are associated with the discrete model. An update support apparatus for discrete models, characterized in that it is integrated as   The discrete model divides the manufacturing process into a plurality of stages in the flow direction of the product, creates a state transition model of the attribute of the product and a state transition model of equipment for each stage, and each stage The discrete model update support apparatus according to claim 8, wherein the discrete model update support apparatus is a discrete model created by defining an influence relationship between an attribute state of the product and a state of the facility.   10. The discrete model update support apparatus according to claim 8, wherein the discrete model is constructed using a Petri net model.   When the user connects the propositions in which the trouble report sentences are separated, the proposition is based on the relationship described in the discrete model and the relationship between propositions that are not described in the discrete model but are defined in advance. 11. The discrete model update support apparatus according to claim 8, further comprising creation support means for searching for and presenting a relationship between the discrete models.   12. The method according to claim 8, further comprising creation support means for restricting a relationship between propositions according to a predetermined rule when the user connects propositions obtained by dividing the trouble report text. The discrete model update support apparatus according to claim 1.   When the user connects the propositions in which the trouble report sentences are separated, the proposition is based on the relationship described in the discrete model and the relationship between propositions that are not described in the discrete model but are defined in advance. 13. The discrete model update support apparatus according to claim 8, further comprising creation support means for searching for and presenting a route between them.   14. The method according to claim 8, further comprising creation support means for searching and presenting a proposition as a start point connected to a proposition based on the discrete model while interpolating the proposition. The discrete model update support apparatus according to Item 1. For a manufacturing process in which a continuous product flows continuously, a state transition model of the product attribute and a state transition model of the facility are created, and the influence between the state of the product attribute and the state of the facility A program for supporting the updating of discrete models created by defining relationships,
It is a trouble report created when trouble occurs in the manufacturing process, the trouble occurrence status, the cause of trouble, countermeasures for trouble, the product processed at the time of trouble occurrence, trouble of the manufacturing operator An aggregated proposition relevant diagram acquisition means for acquiring an aggregated proposition relevant diagram created based on a trouble report that is a sentence including at least information about
Based on the aggregate proposition relation diagram acquired by the aggregate proposition relation diagram acquisition means, the state transition of the manufacturing process in trouble is expressed by using only the attribute state of the product and the state of equipment defined in the discrete model. State transition diagram creation means for creating a state transition diagram that is
In the state transition diagram created by the state transition diagram creating means, from the discrete model, information about the attribute state of the product, information about the state of the facility, state of the attribute of the product and the facility A complementary state transition diagram creating means for creating a complementary state transition diagram by complementing at least one of the information on the influence relationship between the state and the state;
Output means for outputting the complementary state transition diagram created by the complementary state transition diagram creating means;
Using the complementary state transition diagram created by the complementary state transition diagram creating means, the discrete model of the manufacturing process is made to function as an update means for performing update that is addition or correction of the state and causal relationship,
The aggregate proposition relation diagram is a representation in which the trouble report text is divided into propositions corresponding to the representation of the discrete model, and is represented by a flowchart connecting the propositions, and these propositions are associated with the discrete model. A program characterized by being aggregated as

Images