JP3241714B2 - Plan type inference method and apparatus - Google Patents

Description

Description: BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a planning-type inference apparatus for drafting a plan such as a production plan for producing goods and a layout plan of facilities in a manufacturing industry.

2. Description of the Related Art In recent years, with the technological innovation and changes in the consumer structure, the manufacturing industry has been rapidly changing the form of production activities such as multi-product, small-quantity, short delivery time, and short life cycle. In such high-mix low-volume production, it is very important to respond sensitively to market trends. Therefore, it is required to create a production plan and a facility arrangement plan for producing goods at high speed and with high accuracy. In addition, it is required to respond quickly and dynamically to frequently occurring plan changes, etc., and to constantly correct deviations between plans and actual results.

A conventional technique is disclosed, for example, in Japanese Patent Application Laid-Open No. 62-52666. Hereinafter, the configuration of this conventional technique will be described with reference to FIG. FIG. 35 is a schematic configuration diagram of a conventional calculation plan creation device. In FIG. 35, 101 is a storage device for storing basic data such as type, number, capacity, and layout of production means such as equipment, and 102 is an input device for inputting production data such as the type and quantity of products to be produced. , 103
Is a production plan creation program that creates a production plan using the storage device 104 as a memory for production plan creation work based on the basic data and the production data, 105 is a display device that displays the production plan creation result, 106 is A printing device for printing the production plan creation result, a storage device 107 for storing the production plan creation result, and a central processing unit 108 for comprehensively managing and controlling the devices and programs. In the above configuration, as a means for drafting a production plan, first, the production data is input using the input device 102, and then the storage device 101
The central processing unit 108 automatically creates a production plan by using the production plan creation program 103 and the work storage device 104 by combining the basic data stored in the storage device with the production data.
The result of the creation is stored in the storage device 107, and screen display and printing on paper are performed using the display device 105 and the printing device 106.

Another conventional technique is disclosed in JP-A-63-291166. This prior art facilitates the creation of a plan by enabling a user to interactively create an operation plan for a production facility. In this configuration, a keyboard for setting and inputting operating conditions and a pointing device for separately setting a position on a screen are provided. As means therefor, the operation plan is interactively created by scrolling a plan table on the screen or performing an execution operation such as insertion or shifting by selecting a predetermined operation menu.

Problems to be Solved by the Invention However, in the configuration described in JP-A-62-52666, when the planned result is not preferable,
When the production plan is changed by changing the production data or the basic data, it is necessary to draft all the plans from the beginning again, and there is a problem that processing time is long and efficiency is low. For this reason, when real-time production is collected and real-time production is attempted by changing the plan while correcting the gap between the plan and the result, a quick plan change is required. The first method has a first problem that it cannot follow the processing speed.

Further, in the configuration described in Japanese Patent Application Laid-Open No. 63-291166, it is possible to easily modify a plan, but it is necessary to input all of the plan interactively, and if further modification is made at one place, it may be affected by the modification. The user has to make similar corrections while searching for almost all of the above, and there is a second problem that the efficiency is low and the reliability of the plan is low.

Furthermore, in the prior art, although it is possible to plan for specific data and method, there is no versatility for changing data, planning method, output format, etc.
There is a third problem that the usage range is extremely limited.

The present invention overcomes the above three drawbacks, and inputs change data in the case of specifying a production date for an express product, stopping the operation of an equipment due to unpredictable equipment trouble, or correcting a plan due to a deviation between the plan and the actual results. Since only the portion affected by the change data is searched for and automatically corrected in the already planned result, a high-speed plan can be created. Also, even for interactive correction, by automatically correcting the affected part, it is possible to always create a consistent plan. Furthermore, since the data, the planning method, and the output format can be easily changed, the present invention provides a planning-type inference device having a very wide range of use.

Means for Solving the Problems In order to solve the first problem, a first invention of the present invention provides a production plan for storing production plan data and change data necessary for drafting a production plan. A database, a knowledge base in which the procedures required for creating and changing production plans are represented in a rule format and stored, and a working memory for temporarily storing intermediate results of inference in the process of creating and changing plans. Tentatively determines the equipment to be used for each type of product to be produced, develops the process, calculates the reference value for drafting the production plan, allocates specific working hours to the equipment, and assigns the results The plan is created by the production plan creation means that calculates the evaluation value of the plan quality from the
Changes in operating time due to suspension of equipment operation, or differences between production plans and actual results, or changes in basic data on the number of owned equipment and its capacity, or production volume, production flow,
The change of the created plan caused by the change of the production data related to the production date, etc., is caused by the difference between the lot assigned to the part where the change of the equipment operation time occurs or the production plan and the actual. The assigned results of all the processes of the specified lots, such as the lots that have been assigned, or the lots that are assigned to the equipment where the basic data changes occur, or the lots where the production data changes occur, etc. It is necessary to search from the working memory and have a work start time and a work completion time linked to the work start time and the work completion time of the lot designated to be changed, and to be changed by being affected by the change designation of the lot. A search step for searching a lot having a change from the working memory; and a search step for the change target and the lot designated for change. A change target deletion step of returning the change target lot including the lot that needs to be changed found in the above to the unallocated state, clearing the reference value and the evaluation value to the uncalculated state, and deleting from the plan, Re-calculate the cleared reference value and evaluation value for the deleted portion to be changed, re-allocate unallocated lots, and re-calculate the reference value and evaluation value in the re-allocated state to re-plan. With the production plan creating means,
This is performed in a local range including a portion affected by this change.

In order to solve the above-mentioned problems, a second invention of the present invention is directed to a method for implementing the method of the first invention of the present invention. Due to changes in operating hours due to suspension of production, or differences between production plans and actual results, or changes in basic data on the number of equipment owned and their capabilities, or changes in production data on production volume, production flow, production dates, etc. A database storing change data, a knowledge base storing procedures necessary for creating and changing a plan in a rule type format, an input device for inputting the database and the knowledge base, and creating a plan And a working memory for temporarily storing intermediate results of the inference in the process of change, and a total based on the database, the knowledge base, and the working memory. An inference engine having a local plan creator for performing a re-planning of the created plan in a local area including a portion affected by the change, and a plan result. Display device, a printing device for printing the result of the plan, and a comprehensive management and control of the database, the knowledge base, the input device, the working memory, the inference engine, the display device, and the printing device. Central processing unit, the local plan creation means, in the created plan, allocation to the portion where the change in equipment operating time occurs, or the occurrence of a difference between the production plan and the actual, or Assignment to equipment where changes in basic data occur, or changes that are affected by change designations caused by changes in the production data, etc. A change target search means for searching for a lot having a work start time and a work completion time linked to the work start time and the work completion time of the change designated lot from the working memory; The present invention further comprises a change target deletion unit for deleting the change target, and the plan creation unit for replanning the deleted change target portion.

In order to solve the above-mentioned problem, a third invention of the present invention has a configuration of the second invention of the present invention, and collects production performance data and equipment operation status data obtained from production equipment. And change data generating means for generating change data for a plan change from the production result data and the equipment operation status data and storing the change data in a database.

According to a fourth aspect of the present invention, in order to solve the above-mentioned problems, in the second aspect of the present invention, the quality of the plan result is evaluated based on the intermediate result of the plan stored in the working memory by the plan creating means. In addition, an inference engine with a plan evaluation means that operates the knowledge base for planning when there is a defect in the evaluation result and rebuilds the plan to a more suitable knowledge base Things.

According to a seventh aspect of the present invention, in order to solve the second problem, in the second aspect of the present invention, a plan change procedure for changing a plan based on plan change data input from an input device. And a local plan creator for sequentially searching for a part affected by the change through the working memory and making a change in the result of the change, and an inference engine having an intelligent editor.

In order to solve the third problem, the fifth invention of the present invention is directed to the second invention of the present invention, wherein the matching of the planning data input from the input device with other related planning data is performed. Means for reconstructing as a structured planning database, and means for providing necessary data from the structured planning database to the inference engine in various aspects of the planning process in a required form. It has a data utilization interface.

According to a sixth aspect of the present invention, in order to solve the above-mentioned problem, in the second aspect of the present invention, the planning knowledge inputted from the input device is constructed in a knowledge base as a structured planning knowledge base. And a knowledge utilization interface having means for providing the inference engine with knowledge necessary for the phase to be processed from the structured planning knowledge base in various aspects of the planning process. .

In order to further solve the above problems, an eighth invention according to the second invention, wherein an inference result database storing inference results, an output specification input from an input device, and Data output means for outputting the contents of the database according to the output specifications, inference result graph output means for outputting the contents of the inference result database, and a data output interface comprising the simulation output means.

Operation The operation of the first invention of the present invention is as follows. A database that stores plan data and change data, a knowledge base that stores procedures necessary for creating and changing plans, and an inference process in the process of creating and changing plans. Create a plan based on the working memory that temporarily stores the intermediate results, change the operation time due to the suspension of equipment operation, or the difference between the production plan and the actual, or the number of equipment owned and its capacity The change of the created plan caused by the change of the basic data related to the above, or the change of the production data related to the production volume, the production flow, the production date, etc., is assigned to the lot where the change of the equipment operation time occurs. , Or a lot that has a difference between the production plan and the actual, or a lot that is assigned to the equipment that changes the basic data,
Or, while searching the allocated result of all the processes of the lot designated to be changed, such as a lot whose production data has been changed, from the working memory, the work start time and the work completion of the lot designated to be changed The work memory has a work start time and a work completion time linked to the time, searches the working memory for a lot that needs to be changed by being affected by the lot change designation, deletes the searched change target, and deletes the lot. By re-planning the changed parts that have been changed and recalculating the reference values and evaluation values, based on changes in operating hours, differences between production plans and actual results, changes in basic data on equipment, changes in production data, etc. Because the plan can be changed flexibly and in a local area, including those affected by the change,
Only the part affected by the change is changed, and the processing time is short.

The operation of the second invention of the present invention is as follows: production planning data necessary for drafting a production plan, change of operation time due to suspension of equipment operation, difference between production plan and actual results, or the number of owned equipment A database that stores change data based on changes in basic data on production capacity and production data, or changes in production data on production volume, production flow, production date, etc., and rules-based format for procedures necessary for creating and changing plans A knowledge base represented and stored in the database, an input device for inputting the database and the knowledge base, a working memory for temporarily storing intermediate results of inference in a process of creating and changing a plan, A plan creating means for creating a plan based on the database, the knowledge base and the working memory, and a change of the created plan, An inference engine having a local plan creating means for performing replanning in a local range including a more affected part, a display device for displaying a plan result, a printing device for printing a plan result, A central processing unit that comprehensively manages and controls the database, the knowledge base, the input device, the working memory, the inference engine, the display device, and the printing device,
The local planning procedure comprises:
Allocated to the part where the change of the equipment operation time occurs, or the difference between the production plan and the actual, or the allocation to the equipment where the change of the basic data occurs, or the change of the production data, etc. Searching for a change target, which is a part affected by the change designation, to search for a lot having a work start time and a work completion time linked to the work start time and the work completion time of the change designated lot from the working memory. Change target search means to be performed by, change target deletion means to delete the searched change target, and the plan creation means to re-plan the deleted change target location, change of the operating time,
It is not necessary to make a plan again from the beginning every time a plan is changed due to a difference between the production plan and the actual results, a change in basic data on equipment, a change in production data, etc. Becomes possible. The result of the plan is displayed on a screen or printed on paper by a display device or a printing device.

The operation of the third invention of the present invention is to collect production performance data indicating production output from production equipment (hereinafter referred to as M / C) and equipment operation status data such as equipment trouble and equipment stoppage, and further change the data. The data generation means generates change data based on the production result data and the equipment operation status data, and generates the change data necessary for the plan creation and plan change in the second invention of the present invention. And stored in the same database as the planning data in the invention. Therefore, for example, in a production plan, it is possible to constantly correct the deviation of the actual result of the plan in real time, and it is possible to realize a production activity with high efficiency even for a small change request that cannot be predicted.

The operation of the fourth invention of the present invention is as follows. First, a defect in the planning result in the working memory according to the second invention of the present invention outputted by the planning means in the second invention of the present invention, that is, a plan change is required. And executing a plan evaluating means for generating a change method using the knowledge base in the second invention of the present invention based on the change target state. Here, the generation of the change method is realized by reconstructing the knowledge base used for creating a plan. Using the knowledge base reconstructed by the plan evaluation procedure, the local plan creation procedure according to the second invention of the present invention is automatically followed, so that a defect in the plan drafting result is automatically eliminated.

The operation of the fifth invention of the present invention is as follows. First, the planning data input from the input device in the second invention of the present invention is made consistent with other related planning data through a data use interface. Built as a structured planning database. Further, inconsistency with other related planning data caused by correction, addition, or deletion of the planning data from the input device according to the second invention of the present invention is caused by the function of the data use interface itself. The problem is solved by data exchange with the input device via the data use interface. Next, in various aspects of the planning process, for the inference engine according to the second aspect of the present invention, the data use interface uses the structured planning database to execute a planning process necessary for a target planning process phase. Provide data in the required form.

The operation of the sixth invention of the present invention is as follows. First, the knowledge for planning input from the input device in the first invention of the present invention is converted into a knowledge base for structured planning classified for each aspect of the planning process through a knowledge utilization interface. To build. Further, in various aspects of the planning process, the inference engine according to the second aspect of the present invention is configured such that the knowledge use interface uses the structured planning knowledge base for planning necessary for the target planning process phase. Provide knowledge.

According to the operation of the seventh aspect of the present invention, first, the plan change data is input to the plan change means from the input device according to the second aspect of the present invention. After the input plan change data is interpreted by the plan change means of the intelligent editor, the local plan creator of the intelligent editor searches for a change target from the planning results. Subsequently, the local plan creator deletes the change target stored in the working memory according to the second invention of the present invention, and further performs a series of processes of the local plan creator as the second invention of the present invention. Is executed by the plan creation means in the step (a). If the above-mentioned execution causes inconsistency in the planning result, the state of the planning result is fed back from the intelligent editor, and the second embodiment of the present invention is performed.
The contents of the working memory in the invention of the second aspect are maintained in a state immediately before the plan change processing is performed. Therefore, for a partial plan change, it is possible to automatically correct a portion affected by the change, and high efficiency and high reliability are secured even when the plan is changed.

The operation of the eighth invention of the present invention resides in that the planning data stored in the database input from the input device according to the second invention of the present invention is defined in output specifications by data output means of a data output interface. It is reconstructed into an output format that matches the intended use, and is output to a display device or printing device. Further, based on the data input from the input device in the second invention of the present invention, the inference result data stored in the inference result database storing the planned result is converted into the inference result graph of the data output interface. The output unit and the simulation output unit reconfigure the output format according to the purpose of use defined in the output specification, and output the output format to the display device or the printing device. According to the fifth, sixth, and eighth aspects of the present invention, it is possible to easily cope with changes in data, a planning method, and an output format, thereby enabling a highly versatile plan.

Embodiment An embodiment of the present invention will be described below with reference to FIGS.

FIG. 1 is a basic configuration diagram of a plan-type inference device according to an embodiment of the present invention, FIG. 2 is a basic configuration diagram of a plan-type inference device having a change data generation procedure in the embodiment, and FIG. FIG. 4 is a basic configuration diagram of a planning-type inference device having a plan evaluation procedure in FIG. 4, FIG. 4 is a basic configuration diagram of a planning-type inference device having a data use interface in the embodiment, FIG.
FIG. 6 is a basic configuration diagram of a plan-type inference device having a knowledge use interface in the embodiment, FIG. 6 is a basic configuration diagram of a plan-type inference device having an intelligent editor in the embodiment,
FIG. 7 is a basic configuration diagram of a planning-type inference device having a data output interface in the embodiment, FIG. 8 is a basic configuration diagram of a planning-type inference device having all additional functions in the embodiment, and FIG. FIG. 10 is a basic configuration diagram of hardware of a plan type cone theory device in the embodiment, FIG. 10 is an explanatory diagram showing a print norm mounting process which is a target of a production plan in the embodiment, FIG.
FIG. 11 is an explanatory diagram showing the data and processing flow of an inference engine that performs a production plan in the embodiment. FIG. 12 is the data and processing flow of an inference engine that performs a production plan while performing a production plan evaluation in the embodiment. , FIG. 13 is an explanatory diagram showing basic data in the embodiment, FIG. 14 is an explanatory diagram showing production data in the embodiment, FIG. 15 is an explanatory diagram showing time data in the embodiment, Figures 16 and 17
FIG. 18 is an explanatory diagram showing change data in the embodiment. FIG. 18 is a flowchart of a production plan creation procedure of the inference engine in the embodiment. FIG. 19 is a flowchart of a local production plan creation procedure of the inference engine in the embodiment. FIG. 20 is a flowchart of a production plan evaluation procedure of the inference engine in the embodiment, FIG. 21 is an explanatory diagram showing a production plan creation procedure and a local production plan creation procedure of the inference engine in the embodiment, and FIG. FIG. 23 is an explanatory diagram showing an example of knowledge of the structured planning knowledge base in the embodiment, FIG. 23 is an explanatory diagram showing a data configuration in a working memory in the embodiment, and FIG. 24 is a production plan planning result in the embodiment. FIG. 25 is an explanatory diagram showing the structure of information relating to the present invention, FIG. 25 is an explanatory diagram showing the flow of data and processing of the data use interface in the embodiment, and FIG. Explanatory view showing a flow of data and processing of knowledge available interfaces in the example, Figure 27 is a flow chart of the intelligent editor in accordance with the exemplary embodiment, 28
FIG. 29 and FIG. 29 are explanatory diagrams showing the operation of the intelligent editor in the embodiment. FIG. 30 is an explanatory diagram showing the data and processing flow of the data output interface in the embodiment.
The figure is an explanatory diagram showing the production plan drafting result in the embodiment,
FIG. 32 and FIG. 33 are explanatory diagrams showing production plan evaluation results in the embodiment, and FIG. 34 is an explanatory diagram showing a simulation example of a production plan drafting result in the embodiment.

In FIG. 1, 1 is a database storing plan data and change data, 2 is a knowledge base that expresses and stores procedures necessary for creating and changing a plan in a rule format, and 3 is the database 1 and the knowledge. An input device for inputting the base 2, 6 is an inference engine that performs planning based on the database 1 and the knowledge base 2, 4 and 5 are planning and local planning creating procedures in the inference engine 6, and 7 is a planning A working memory for temporarily storing intermediate results during preparation; 8 a display device for displaying the results of the plan; 9 a printing device for printing the results of the plan; 10 a database 1; the knowledge base 2; A central processing unit that comprehensively manages and controls the input device 3, the inference engine 6, the working memory 7, the display device 8, and the printing device 9; . In FIG. 2, reference numeral 11 denotes an M / C that performs production at a manufacturing site, and 12 automatically collects equipment operation status data such as production performance data and trouble status from the M / C 11, and stores the results in the database 1. This is a change data generation procedure for saving as plan change data. Further, in FIG. 3, reference numeral 13 denotes a plan evaluation procedure added in the inference engine 6.

There are four types of processes as shown in Fig.
And one at an outside company.
FIG. 11 shows data and a processing flow of the inference engine 6 shown in FIG. 1 when a production plan of a printed circuit board mounting process having a different process flow is made. FIG. 12 shows the data and processing flow of the inference engine 6 to which the plan evaluation procedure shown in FIG. 3 is added. In FIGS. 11 and 12, 24
To 29 are specific data of the production plan database 1b for the production plan of the database 1. Reference numeral 24 denotes basic data relating to production means such as the type, number, capacity, and layout of production means such as equipment. FIG. 13 shows, as a specific example, the equipment capacity, which is the number of electronic parts inserted per hour, and the capacity of printed circuit board equipment. This shows the equipment-specific capacity, which is a loading time, which is a supply time, input for each equipment. Reference numeral 25 denotes production data relating to the product, that is, the type and quantity of the product to be produced and the process flow, and FIG. 14 shows a basic schedule for a lot as a specific example of the production as a specific example. The start date, which depends on the number of lots, the availability of parts necessary for production, and the completion date, which must be produced by this date, are entered. 26 is a method of planning a production plan (a method of planning the last process of production from the date of completion and planning the previous process in sequence) and a forward method (planning of the first process of production from the date of commencement). To determine the order of the lots to be planned based on the priority from among the lots. The priority is the lot with the earliest completion date. Is the dispatching criterion, which is the earliest delivery date criterion, etc.), and 27 is the policy data on the factory operation policy of emphasizing the capacity utilization rate, inventory, and lead time, which are the production planning policies. , 28 are time data relating to the daily operation time, and FIG. 15 shows the daily operation time as a specific example. Numeral 29 is the change data on the production date designation, overtime instruction, equipment operation stoppage, production results, etc. as an express product to change the already planned production plan.As an example, Fig. 16 shows equipment operation due to equipment trouble etc. The equipment operation unavailable designation for setting the time during which the production is not possible, and Fig. 17 shows the production results for the daily production situation. 2b is the knowledge base 2
FIG. 22 shows an example of such a knowledge base for production planning, which is a rule having a meaning of if (condition part) and then (result part). Reference numeral 7 denotes a working memory for temporarily storing intermediate results in the production planning.

In Figs. 11 and 12, 30 to 33 are plan creation procedures 4
In the processing step of the production plan creation procedure 4a for the production plan, a daily production plan is created in minutes by using the working memory 7 together with each of the data 24 to 28. The knowledge necessary for the production plan creation procedure 4a is in the production planning knowledge base 2b, and an example thereof is shown in FIG. 30 is a process development step for tentatively determining equipment to be used for each type of product to be produced, 31 is a reference value for calculating the earliest start time, latest completion time, margin time, balance efficiency, etc., which are reference values for drafting a production plan A calculation step, 32 is an equipment allocating step for allocating a specific working time to the equipment, and 33 is an evaluation value calculating step for calculating a facility operation rate, a stock ratio, and a lead time from the allocation result to evaluate the quality of the plan. FIG. 18 is a flowchart of these steps. The process development step 30 determines a process to be manufactured by selecting any one of the three candidates of process A → process R → process U → process M in FIG. 10 for all models (FIG. 10). 39) Then, for all the models, the equipment to be used in all the processes (AH2 or AE1 in case of process A of candidate 1) is provisionally determined (FIG. 40). The reference value calculation step 31 calculates the line balance of all the models (FIG. 41), determines the magnitude of the line balance loss value and the default value (FIG. 42), and the line balance loss value is larger than the predetermined value. In this case, the lot is divided for a process with a long processing time that deteriorates the line balance (FIG. 43), and the process returns to FIG. B for provisionally determining one facility for the divided process. Next, the time at which production can be started earliest (earliest start) and the time at which production can be completed earliest (earliest completion) are calculated for all lots of all models (FIG. 44). For each lot, the latest time at which production can be started (latest start) and the latest time at which production can be completed (latest completion) are calculated for each process (FIG. 45). Next, it is determined whether the earliest start is earlier than the start date in FIG. 14 or the latest completion is later than the completion date in FIG. 14 and the delivery is delayed (FIG. 46). If so, the production data such as the start date and the completion date in FIG. 14 are changed (FIG. 47), and the calculation is returned to FIG. 14C and recalculated. Calculate the margin time such as the difference between the last latest start time and the earliest start time.
48). If the delivery date is delayed even after recalculation after changing the production data, the process returns to FIG. 10A for selecting a process flow other than the three candidates in FIG. In the equipment allocation step 32, the types to be assigned to the equipment with priority are sequentially selected by dispatching (FIG. 49), and a lot is selected by dispatching again from the selected model, the equipment is allocated, and a specific work time is allocated (FIG. 49). 50). Next, when the allocated work start time is earlier than the earliest start time or the work completion time is later than the latest completion time, it is determined whether or not the work can be allocated (step 51 in FIG. 51). The first
The production data such as the start date and completion date in FIG. 14 is changed (FIG. 52), and the process returns to FIG. As shown in step R of FIG. 10, if the RH1 unit was provisionally determined in FIG. 40, the change in FIG. Return first. If the assignment is still impossible, the process returns to FIG. C, and if the assignment is still impossible, the process returns to FIG. B to temporarily determine another type of equipment, the RT1. In the case where allocation is not possible,
Return to In the evaluation value calculation step 33, when the daily production capacity of the equipment is assumed to be infinite, the work time is allocated to the equipment based on the load (equipment load) which is the total work time for each equipment on each day and the actual daily production capacity. The subsequent operation rate (equipment operation rate) is calculated (Fig. 53), the lead time from the start of the production of the first process to the completion of the production of the final process is calculated (Fig. 54), and the in-process inventory for each process time Then, the product inventory amount from the production completion date of the final process to the delivery date (shipping date) is calculated (FIG. 55). Then these figures are worse than the defaults (capacity utilization is low,
It is determined whether the lead time is long and the stock amount is large (FIG. 56), and if it is not good, the production data such as the start date and completion date in FIG. 14 is changed (FIG. 57). Note that, in this case, the process returns to FIGS. A, B, C, and D as in FIG.

In FIG. 11 and FIG.
The processing steps of the local production plan creation procedure 5a for the production plan are the change object search step 34, the change object deletion step 35, the production plan creation procedure 4a, and the change of the result calculated in the production plan creation procedure 4a. In the step of promptly changing the plan when the need arises, the plan is changed while searching for a portion affected by the change data 29 as needed for the change of the production plan. The knowledge required for this local production plan creation procedure 5a is in the production planning knowledge base 2b.
Reference numeral 34 denotes a change target search step for searching all the portions affected by the change data, specifically, a lot to be changed is searched. Reference numeral 35 denotes a change target that clears the plan result of the lot to be changed, that is, the reference value, the equipment allocation, and the evaluation value that are the result of the production plan creation procedure 4a (returns to the state before the production plan creation procedure was performed). This is the deletion step. Thereafter, the production plan creation procedure 4a is performed. These steps are repeated each time there is a plan change. FIG. 19 is a flowchart of these steps. The change target search step 34 searches the working memory 7 for the assigned results of all the processes of the lot designated to be changed (FIG. 58), and is affected by this, that is, the lot which needs to be changed, that is, the lot designated to be changed. Lots that are temporally linked, such as a lot having a work start time equal to the work completion time of the changed lot or a lot having a work completion time equal to the work start time of the similarly designated change lot, are also stored in the working memory 7. (FIG. 59). The change object deletion step 35 recalculates and corrects the equipment load, the capacity utilization rate, the lead time, the in-process stock amount, and the product stock amount, which are the evaluation values when the lot to be changed is excluded (FIG. 60). The lot to be changed is returned to the unallocated state (FIG. 61), and the line balance, the earliest start, the earliest completion, the earliest start, the latest completion, and the spare time, which are the reference values, are cleared to the uncalculated reference values (FIG. 61). FIG. 62). Next, returning to the production plan creation procedure 4a, the cleared uncalculated reference value is calculated again by the reference value calculation 31 (44 to 48), the unallocated lot is reallocated (49 to 52), and the reference value is again calculated. The calculated lot area recalculates the evaluation value of the reallocated lot (53 to 57). The working memory 7 holds the intermediate results of the plan in order to efficiently and quickly determine and process the production plan creation procedure 4a and the local production plan creation procedure 5a. FIG. 23 shows the configuration of data stored in the working memory. FIG. 24 shows the structure of information related to the production plan drafting result 18a of FIG. The production plan drafting result 18a is data structured for each process of a lot, and holds model information, reference time information, process information, time information, equipment information, supplementary information, and the like.

In FIG. 12, reference numerals 36 to 38 denote processing steps of a production plan evaluation procedure 13a for the production plan of the plan evaluation procedure 13, and 43, 4 by the steps of the production plan creation procedure 4a.
If a satisfactory plan could not be made even after changing the data shown in 7, 52, 57, the production planning knowledge database 2b
Is a step of making a satisfactory plan by reconstructing That is, for a problem in the production plan, a lot that needs to be changed and a lot affected accordingly are searched, and the production planning knowledge database 2b is rebuilt so as not to cause a problem. The knowledge required for this production plan evaluation procedure 13a is in the production plan knowledge base. Reference numeral 36 denotes a change target search step for searching for all the parts affected by the change data, which is the same as the above-mentioned 34. Reference numeral 37 denotes a change method selection step of selecting knowledge representing a change method of a lot to be changed from the production planning knowledge base. 38 is a change method generating step of reconstructing the selected knowledge so as to match the lot to be changed. FIG. 20 is a flowchart of these steps. The change target search step 36 is shown in FIGS. In the change method selection step 37, for example, when the work completion time is later than the latest completion time, the size of the spare time of the production scheduled lot immediately before the lot whose delivery time is delayed is checked, and both lots are replaced by replacing the lot. The data such as whether the delivery date is not delayed is analyzed (FIG. 65), and a method for resolving the problem such as the delivery delay is selected from the rules already input in the production planning knowledge base (FIG. 66). The change method generation step 38 is implemented by, for example, adding a designated condition of the lot number to the rule condition section so as to correspond to only the lot for which the previous rule is to be further changed (FIG. 67), and is added to the production planning knowledge base. (Fig. 6
8). As an example of a knowledge base for production planning, FIG. 22 (D) shows a case in which the processing time of one process in the same lot is more than twice the processing time of all other processes in order to achieve line balance. Knowledge to divide. Based on such knowledge, the production plan evaluation procedure 13a adds a condition or the like to generate embodied knowledge.

The operation of the inference engine 6 in FIG. 1 is as shown in FIG. Regarding the equipment allocation step 32 of the production plan creation procedure 4a in FIGS. 11 and 12, forwards for sequentially planning the subsequent steps from the first step are input as the condition data 26 indicating the method of drafting the production plan. When the input of the policy data 27 indicating the planning policy is based on the facility operation rate emphasis and the lead time emphasis respectively, FIG.
FIG. (B) corresponds. In other words, in the case of the facility operation rate center of gravity,
70 is set as the work completion time so that the machine can always be operated at full capacity even though it can be produced from Fig. 69, and equipment is allocated to produce from Fig. 69a which is processing time earlier than Fig. 70, while lead time is In the case of emphasis, the earliest loading (FIGS. 71 and 72) is always performed, and the earliest completion. In addition, the operation of the local production plan creation procedure 5a in FIGS.
(C) in the figure (in this case, there are three lots of white, black, and oblique lines), and the changed portion propagates. That is, if the lot in FIG. 73 increases as shown in FIG. 73a due to the increase in the lot size, it is affected by the increase and FIG.
Is changed to FIG. 75a. FIG. 76 does not change.

In FIG. 2, the equipment operation status data collected from the M / C 11 in the change data generation procedure 12 is specifically described as the equipment operation inability designation and production result data shown in FIGS. Is stored in the application database 1b. Next, the production plan is changed by the above-described local production plan creation procedure 5a. As a result, it is not necessary for a person to input data such as production results, real-time plan changes can be made at the production site, and highly efficient factory operation based on the latest production plan is always realized.

FIG. 4 has an additional function of automatically checking for omission of data in the database, which has been relying on the user, by having a database index indicating the relation of each data of the database 1 and informing the user of the omission. Explain. 1a structuring the various data 24 to 28 shown in FIGS. 11 and 12 necessary for the production planning,
And a data use interface 14 for maintaining the consistency of the structured plan database 1a and providing necessary data to the inference engine 6 in each phase of the planning process. This is an input device for inputting the structured planning database 1a. FIG. 25A is a diagram showing the data and processing flow of the data use interface 14. The data use interface 14 includes a data maintenance unit 77 including a data correction procedure and a related data search procedure, and a data reading and reading process. Data usage department including procedures
It consists of 78. Reference numeral 79 denotes a database index describing the relationship and format of the structured planning database, which is input by the input device. The operation of the data maintenance unit 77 is as follows.
Is corrected by the input device 3, and the data related to the corrected data is searched by the related data search means through the database index 79. The searched data is fed back to the data correction procedure and corrected. For example, if a basic schedule which is production data shown in FIG. 14 is added and its start date or completion date is not set to the operation time which is the time data shown in FIG. After the addition of the schedule, the data use interface 14 automatically prompts the addition of the operation time and reconstructs the structured planning database 1a with consistency. The database index at this time is
This is shown in FIG. The data reading procedure of the data utilization unit 78 provides the inference engine 6 with necessary data. That is, it is a program that accesses the structured planning database 1a in the format indicated by the database index 79 and passes data to the inference engine. The database index
Reference numeral 79 holds a file name in which the data 24 to 28 are stored, a name of each item, the number of bytes as a length, and the like.

FIG. 5 shows that knowledge of all aspects is provided to the inference engine 6 in the knowledge base 2 by adding a knowledge base index indicating an aspect or specification using the knowledge to the knowledge base 2. However, it was sufficient to provide only the necessary knowledge, and there was only one specification, but it explained additional functions that can have multiple specifications. 2a is a knowledge base for structured planning which is different from the knowledge base 2 by structuring each knowledge necessary for the production planning as shown in FIG. 22, and 15 is the structure of the knowledge base 2a for structured planning. A knowledge utilization interface 3 for providing necessary knowledge to the inference engine 6 in each phase of the planning process is an input device 3 for inputting the structured planning knowledge base 2a. FIG. 26 is a diagram showing a flow of data and processing of the knowledge use interface 15. The knowledge use interface 15 has a specification definition unit 83 including a specification definition procedure and a knowledge loading procedure including a specification interpretation procedure and a knowledge extraction procedure. And part 84. Reference numeral 85 denotes a phase (refers to a process step such as a process development 30 or a reference value calculation 31 in FIGS. 11 and 12) or a specification (in a production method) used for each knowledge in the structured planning knowledge base 2a. The input device is used to input a knowledge base index that describes, for example, a lot production that unites a certain production unit in detail or a continuous production that continuously produces the same product. The specification definition procedure of the specification definition unit 83 sets the use phase and specifications of each knowledge, and registers them in the knowledge base index 85. First, the knowledge loading unit 84 uses the knowledge base index 85 in the specification interpretation procedure.
And select knowledge that matches the plan specification. Next, as the inference engine 6 performs inference, the knowledge extraction procedure extracts knowledge to be used for each phase and provides the knowledge to the inference engine. Of course, as the situation progresses, unnecessary knowledge is released. That is, in FIG. 11 and FIG. 12, when the process development 30 is completed and the process proceeds to the reference value calculation 31, the knowledge used in the process development is deleted from the inference engine, and the knowledge used in the reference value calculation is passed to the inference engine. It is. In the example of the knowledge shown in FIG. 22, the meta-rule of FIG. 22A is always provided to the inference engine for the phase development, and the knowledge of FIG. 22B and FIG. This is the knowledge provided in the 32 aspects of equipment allocation, and is the knowledge that makes the dispatching criterion for lot selection and the Johnson algorithm, which is one of the operations research, which is a mathematical method, a rule. (D) of FIG. 22 described above is also knowledge obtained by making the lot division criterion provided in the phase of the reference value calculation 31 of FIGS. 11 and 12 into a rule.

FIG. 6 illustrates an additional function of creating a plan while further interacting with a user while the inference engine 6 automatically makes a plan. 16 is a plan change procedure for setting plan change data, 5 is a local plan creation procedure described in FIG. 1, and 17 is a display while displaying on the display device 8 by the plan change procedure 16 and the local plan creation procedure 5. It is an intelligent editor that interactively makes advanced plan changes, and is configured as a function of the inference engine 6. Reference numeral 3 denotes an input device for a user to make an interactive input in the plan change procedure 16. FIG. 27 is a flowchart showing the operation of the intelligent editor 17. First, in FIG. 86, the production plan drafting result 18a is extracted from the working memory 7 and displayed on the display device 8.
In FIG. 16A, the user instructs a change by inputting from the input device 3 while watching the display. 28 and 29 show specific examples. In FIG. 28, the daily production plan of the production model AAAA01 from January 20 to January 26 is input to the production facilities A1 to A10 by arrows using a pointing device such as a mouse. FIG. 29 temporarily refers to the production plan of another production model AAAA08. 5a in FIG. 27 is a local production plan creation procedure similar to that shown in FIGS. 11 and 12, in which a change is automatically made while searching for a portion affected by the change designation. Next, in FIG. 87, a contradiction such as the order of the production sequence of each process is searched for, for example, due to a change, the work start time of the first process of the same lot is later than the work start time of the next process. The working memory 7, which temporarily stores the planning result, is rewritten (FIG. 88), and if there is any inconsistency, the user is informed of the inconsistency and the working memory is not rewritten. Thereafter, the procedure returns to FIG. 86, and this procedure is repeated until there is no change in the plan.

FIG. 7 illustrates an additional function of outputting to a display device and a printing device in a format according to the user. 18 is an inference result database storing inference results, 20 is a data output procedure for outputting the contents of the database 1, 21 and 22 are inference result graph output procedures for outputting the contents of the inference result database 18, and simulation output procedures. , 23 are the data output procedure 20 and the inference result graph output procedure
21 and a data output interface for performing the simulation output procedure 22, and 3 is an output specification in each output procedure.
It is an input device for inputting 19. FIG. 30 is a diagram showing a flow of data and processing of the data output interface 23. The data output interface 23 is provided with an output specification definition unit 89 including a specification definition procedure and a specification interpretation procedure for each of the output procedures. And an output unit 90 including an output procedure. Reference numeral 19 denotes an output specification in which each output format of the data output procedure 20, the inference result graph output procedure 21, and the simulation output procedure 22 is input by the input device. The specification definition procedure of the output specification definition unit 89 is based on the output specification.
First, the output unit 90 interprets the output specification 19 according to the specification interpretation procedure, forms an output format according to the output procedure, and outputs the output format to the display device 8 or the printing device 9. The output specification 19 specifically describes in which position on the screen a character is to be placed or a line is to be drawn. No. 31
FIG. 33 to FIG. 33 show an example of the inference result graph output procedure 21 in which a Gantt chart display of the production plan on July 3 is shown.
It shows the equipment operation rate of RT1 from 1st to 9th of the month, as well as the in-process inventory of UK 1st. FIG. 34 shows an example of the simulation output procedure 22, in which the production status at the time of 68 minutes after the start of production on July 4 is displayed in an animation. These displays can be easily changed by resetting the character positions and line positions in the output specifications 19 and the arrangement positions of the production equipment such as the AH1 in FIG. 34.

In FIG. 8, 3 is an input device similar to that shown in FIGS. 1 to 7, 8 is a display device, 9 is a printing device, 7 is a working memory, 11 is the M / C in FIG. 6, the change data generation procedure, 6 is the inference engine in FIG. 3, 1a is the structured planning database in FIG. 4, 14 is the data use interface in FIG. 2, 2a is the structuring in FIG. Planning knowledge base, 15 is the knowledge utilization interface in the same figure, 17 is the intelligent editor in FIG. 6, 18 is the inference result database in FIG. 7, 23 is the data output interface in FIG. The output specification 10 is the input device 3, the display device 8, the printing device 9, the working memory 7, the M /
C11, the change data generation procedure 12, the inference engine 6, the structured planning database 1a, the data use interface 14, the structured planning knowledge base 2a, the knowledge use interface 15, and the intelligent editor 17. , A central processing unit that manages and controls the inference result database 18, the data output interface 23, and the output specifications 19 as a whole. In the operation shown in FIG. 8, first, the structured plan database 1a and the structured plan knowledge base 2a are constructed from the input device 3. A part of the data of the structured planning knowledge base 1a is collected from the M / C 11 in the change data generation procedure. Next, the inference engine 6 uses the structured planning database 1a through the data utilization interface 14, and the structured planning knowledge base through the knowledge utilization interface 15.
2a is used, and while the working memory 7 is used, the knowledge base 2a for structured planning is reconstructed as necessary, and a plan is automatically created. Next, the result of the plan is stored in the inference result database from the working memory 7.
The data is passed to 18 and displayed or printed by the display device 8 or the printing device 9 through the data output interface 23 while referring to the output specification 19. At the time of the change, the user performs an interactive change process through the intelligent editor 17.

FIG. 9 is a basic hardware configuration diagram for realizing all the inventions of FIGS. 1 to 7, that is, for realizing FIG. 8, in which an input device 3, a display device 8, a printing device 9, a central The processing device 10 and the M / C 11 are the same as those shown in FIG. 8, and 10a is the changed data generation procedure 12, the inference engine 6, the data use interface 14, the knowledge use interface 15, the intelligent editor in FIG. 17, ROM in which the data output interface 23 resides, 10b is a RAM used as the working memory 7 in FIG. 8, 10c is a structured planning database 1a, a structured planning knowledge base 2 in FIG.
a, an external storage device for storing the inference result database 18 and the output specifications 19; and 10d, a communication interface for communicating with the M / C 11 in FIG.

The present invention has been described above with reference to an embodiment centering on a production plan in the manufacturing industry. According to the present embodiment, a highly accurate plan change can be performed in a short time in response to a change in a production plan, and versatility enough to follow daily changing production activities is realized, and a plan-type inference having an extremely high practical effect. A method and an apparatus thereof can be provided. For example, if the number of production
When planning a one-month production plan when the number of production models is 40 times and there are 100 models, conventional technology requires more than a week of man-hours even for veteran full-time workers, and completely responds to sudden changes in plans could not. Also in the present embodiment, it has been demonstrated that the effect can be achieved in several hours even under such conditions, and that changes can be dealt with in a timely manner.

It should be noted that the present invention can be implemented by configuring each device in hardware in the above embodiment by software.

Effect of the Invention As described above, the first invention of the present invention provides a database that stores plan data and change data, a knowledge base that stores procedures necessary for creating and changing plans, and a plan for creating and changing plans. Create a plan based on the working memory that temporarily stores the results of inference during the process, and change the operation time due to the suspension of equipment operation, or the difference between the production plan and the actual result, or possession of the equipment Allocate the change of the created plan caused by the change of the basic data on the number and its capacity, or the change of the production data on the production volume, the production flow, the production date, etc. to the part where the change of the equipment operation time occurs. Lots, or lots that have a difference between the production plan and the actual, or lots that are assigned to equipment for which changes in basic data occur, or Indicates the lot whose production data has changed,
Search the allocated results of all the processes of the lot designated as the change from the working memory and determine the work start time and the work completion time linked to the work start time and the work completion time of the change designated lot. Mochi,
The working memory is searched for a lot that needs to be changed by being affected by the lot change designation, the searched change target is deleted, the deleted change target portion is re-planned, and a reference value and evaluation are performed. By recalculating the values, it is possible to flexibly change the operation time, the difference between the production plan and the actual result, the basic data of the equipment, and the plan for the production data change. Since the search is performed in a local range including that part, every time the plan is changed, there is no change that changes everything up to the schedule after the necessary change, and only the part affected by the change is changed As a result, it is possible to prevent the change from having an adverse effect on a portion other than a necessary portion, and the processing time is short.

In addition, it is possible to avoid a situation in which a schedule that is not practically executable, which occurs when all schedules after the change necessary period are changed, can be avoided, and a practical change is possible.

Further, the second invention of the present invention relates to production planning data necessary for drafting a production plan, a change in operation time due to suspension of equipment operation, a difference between the production plan and the actual result, or the number of owned equipment. A database that stores change data based on changes in basic data on production capacity and production data, or changes in production data on production volume, production flow, production date, etc., and rules-based format for procedures necessary for creating and changing plans A knowledge base represented and stored in the database, an input device for inputting the database and the knowledge base, a working memory for temporarily storing intermediate results of inference in a process of creating and changing a plan, A plan creating means for creating a plan based on the database, the knowledge base and the working memory, and a change of the created plan, An inference engine having a local plan creating means for performing replanning in a local range including a more affected part, a display device for displaying a plan result, a printing device for printing a plan result, A central processing unit that comprehensively manages and controls the database, the knowledge base, the input device, the working memory, the inference engine, the display device, and the printing device,
The local planning procedure comprises:
Allocated to the part where the change of the equipment operation time occurs, or the difference between the production plan and the actual, or the allocation to the equipment where the change of the basic data occurs, or the change of the production data, etc. Searching for a change target, which is a part affected by the change designation, to search for a lot having a work start time and a work completion time linked to the work start time and the work completion time of the change designated lot from the working memory. , A change target deletion unit that deletes the searched change target, and a plan creation unit that plans the deleted change target portion again, thereby changing the operation time, Differences between planned and actual results, changes in basic data on equipment,
It is not necessary to draft a plan from the beginning each time a plan change occurs due to a change in production data, etc., and a highly efficient plan change can be performed automatically.

In addition to the effects of the second invention of the present invention, the third invention of the present invention further comprises an apparatus for collecting production performance data and equipment operation status data obtained from M / C, By providing a change data generation procedure for creating change data for a plan change from the situation data and storing the change data in a database, it becomes possible to provide detailed feedback of the actual data to the plan, and the accuracy is reflected by reflecting the actual data. It is possible to create and change high-quality plans.

According to a fourth aspect of the present invention, in addition to the effects of the second aspect of the present invention, the pass / fail evaluation of the plan result is performed based on an intermediate result of the plan stored in the working memory by the plan creating means. If there is a problem in the planning, the knowledge base for planning is operated, and the inference engine that has a plan evaluation procedure for rebuilding the plan and rebuilding it to a more suitable knowledge base is provided. Even if a problem occurs as a result of the execution, it is possible to automatically resolve the problem, and a plan with higher accuracy can be created and changed with high efficiency.

According to a seventh aspect of the present invention, in addition to the effects of the second aspect of the present invention, a plan change procedure for changing a plan based on plan change data input from an input device and a result of the change are described. By providing an inference engine with an intelligent editor consisting of a local plan creation procedure for sequentially searching and making changes to the parts affected by the change via the working memory, the effect of the change on the partial plan change is provided. It is possible to automatically modify the plan of the part to be received, and highly efficient plan creation and change can be performed with high efficiency.

According to a fifth aspect of the present invention, in addition to the effects of the second aspect of the present invention, the planning data input from the input device is made consistent with other related planning data, and the structure is structured. A data utilization interface having means for reconstructing as a planning database and means for providing necessary data to the inference engine from the structured planning database in various aspects of the planning process is provided. According to the sixth aspect of the present invention, in addition to the effect of the second aspect of the present invention, means for constructing a planning knowledge input from the input device in a knowledge base as a structured planning knowledge base, And knowledge means having means for providing the inference engine with knowledge necessary for the phase to be processed from the structured planning knowledge base in various aspects of the planning process. By providing the interface, the eighth invention of the present invention further provides, in addition to the effect of the second invention of the present invention, an inference result database storing inference results, an output specification input from an input device, and ,
By providing a data output procedure for outputting the contents of the database in accordance with the output specifications, an inference result graph output procedure for outputting the contents of the inference result database, and a data output interface including the simulation output procedure, each of the data is changed. In addition, it is possible to easily cope with a change in a plan creation method and a plan change method, a change in an output format, and the like, so that an extremely versatile plan can be performed.

A ninth invention of the present invention is the input device, the display device, the printing device, the working memory, and the M / M of the third invention of the second invention. C, the modified data generation procedure, the inference engine according to the fourth aspect of the present invention, the structured planning database according to the fifth aspect of the present invention, the data use interface, and the sixth aspect of the present invention. The knowledge base for structured planning according to the invention, the knowledge utilization interface, the intelligent editor according to the seventh invention of the present invention, and the eighth invention of the present invention capable of bidirectionally exchanging contents with the working memory Inference result database, the same data output interface, the same output specifications, the input device, the display device, the printing device, the working memory, the M /
C, the change data generation procedure, the inference engine, the structured plan database, the data use interface, the structured plan knowledge base, the knowledge use interface, the intelligent editor, the inference result database, By providing a data output interface and a central processing unit that comprehensively manages and controls the output specifications, efficient automatic processing and interactive processing become possible, and a highly reliable plan can be created and changed. In addition, a very versatile plan is realized. Accordingly, in the recent complex multi-product small-lot production in the manufacturing industry, it is possible to improve the equipment operation rate, reduce the stock amount, shorten the lead time, and the like, which is extremely effective practically for production activities.

[Brief description of the drawings]

FIG. 1 is a basic configuration diagram of a plan-type inference device according to an embodiment of the present invention, FIG. 2 is a basic configuration diagram of a plan-type inference device having a change data generation procedure in the embodiment, and FIG. FIG. 4 is a basic configuration diagram of a plan-type inference device having a plan evaluation procedure in the embodiment, FIG. 4 is a basic configuration diagram of a plan-type inference device having a data use interface in the embodiment, and FIG. 5 is a knowledge use interface in the embodiment. FIG. 6 is a basic configuration diagram of a planning-type inference device having an intelligent editor in the embodiment, and FIG. 7 is a planning-type inference having a data output interface in the embodiment. FIG. 8 is a basic configuration diagram of a planned inference device having all additional functions in the embodiment, and FIG. 9 is a basic configuration diagram of hardware of the planned inference device in the embodiment. Figure 10 is an explanatory view showing a printed circuit board mounting process to be production plan in accordance with the exemplary embodiment, first
FIG. 11 is an explanatory diagram showing the data and processing flow of an inference engine that performs a production plan in the embodiment. FIG. 12 is the data and processing flow of an inference engine that performs a production plan while performing a production plan evaluation in the embodiment. , FIG. 13 is an explanatory diagram showing basic data in the embodiment, FIG. 14 is an explanatory diagram showing production data in the embodiment, FIG. 15 is an explanatory diagram showing time data in the embodiment, Figures 16 and 17
FIG. 18 is an explanatory diagram showing change data in the embodiment. FIG. 18 is a flowchart of a production plan creation procedure of the inference engine in the embodiment. FIG. 19 is a flowchart of a local production plan creation procedure of the inference engine in the embodiment. FIG. 20 is a flowchart of a production plan evaluation procedure of the inference engine in the embodiment, FIG. 21 is an explanatory diagram showing a production plan creation procedure and a local production planning procedure of the inference engine in the embodiment, and FIG. FIG. 23 is an explanatory diagram showing an example of knowledge of a structured planning knowledge base in the embodiment. FIG. 23 is an explanatory diagram showing a data configuration in a working memory in the embodiment.
FIG. 24 is an explanatory diagram showing the configuration of information related to the production plan drafting result in the embodiment, FIG. 25 is an explanatory diagram showing data and processing flow of a data use interface in the embodiment, and FIG. FIG. 27 is an explanatory diagram showing the flow of data and processing of the knowledge utilization interface in the example, FIG. 27 is a flowchart of the intelligent editor in the embodiment, and FIGS. 28 and 29 show the operation of the intelligent editor in the embodiment. FIG. 30 is an explanatory view showing data and a processing flow of a data output interface in the embodiment, FIG. 31 is an explanatory view showing a production plan drafting result in the embodiment, FIG.
FIG. 33 and FIG. 33 are explanatory diagrams showing a production plan evaluation result in the embodiment, FIG. 34 is an explanatory diagram showing a simulation example of a production plan drafting result in the embodiment, and FIG. It is a schematic block diagram. 1 ... Database, 1a ... Structured planning database, 1b ... Production planning database, 2 ... Knowledge base, 2a ... Structured planning knowledge base, 2b ... Production planning knowledge base, 3 ... Input device, 4 ... plan creation procedure, 4a
…… Production plan creation procedure, 5 …… Local plan creation means, 5a
... local production plan creation procedure, 6 ... inference engine, 7
... working memory, 8 ... display device, 9 ... printing device, 10 ... central processing unit, 10a ... ROM, 10b ... RAM, 10
c ... external storage device, 10 d ... communication interface, 11 ...
… M / C, 12… Change data generation procedure, 13 …… Plan evaluation procedure, 13a …… Production plan evaluation procedure, 14 …… Data use interface, 15 …… Knowledge use interface, 16 …… Plan change procedure , 17 …… Intelligent editor, 18 …… Inference result database, 19 …… Output specifications, 20 …… Data output procedure, 21
…… Inference result graph display procedure, 22… Simulation output procedure, 23 …… Data output interface

Continuation of the front page (51) Int.Cl. ⁷ identification code FI G06F 17/60 108 G06F 17/60 108 (56) References JP-A-62-198930 (JP, A) JP-A-62-208105 (JP, A) Japanese Patent Application Laid-Open No. 62-70939 (JP, A) Japanese Patent Application Laid-open No. 62-203225 (JP, A) stem, 1984 pp. 205-212 (58) Fields investigated (Int. Cl. ⁷ , DB name) G06F 9/44 G06F 17/60 G05B 19/418 B65G 61/00

Claims (8)

(57) [Claims] 1. A production plan database storing production plan data and change data necessary for drafting a production plan, and a procedure necessary for creating and changing a production plan are expressed and stored in a rule type format. Based on the knowledge base and the working memory that temporarily stores the results of inference during the process of creating and changing the plan, provisionally determine the equipment to be used for each type of product to be produced and develop the process. Calculate the standard values for planning, assign specific working hours to the equipment, and create a plan by the production planning step, which calculates the evaluation value of the plan based on the allocated results. Changes in operating hours due to outages, or differences between production plans and actual results, or changes in basic data on the number of units owned and their capabilities, or production volumes, production flows,
A change in the created plan caused by a change in the production data related to the production date, etc., is caused by a difference between the lot assigned to the part where the equipment operation time changes occur, or the production plan and the actual The assigned results of all the processes of the specified lots, such as the lots that have been assigned, or the lots that are assigned to the equipment where the basic data changes occur, or the lots where the production data changes occur, etc. It is necessary to search from the working memory and have a work start time and a work completion time linked to the work start time and the work completion time of the lot designated to be changed, and to be changed by being affected by the change designation of the lot. A search step for searching a lot having a change from the working memory; and a search step for the change target and the lot designated for change. A change target lot including a lot that needs to be changed and returned to an unallocated state, clearing the reference value and the evaluation value to an uncalculated state, and deleting the change target from the plan; and Re-calculate the cleared reference value and evaluation value for the deleted part to be changed, re-allocate unallocated lots, and re-calculate the reference value and evaluation value in the re-allocated state to re-plan. And (c) performing the production planning in a local range including a portion affected by the change. 2. A production plan data necessary for drafting a production plan, a change in an operation time due to a stoppage of equipment operation, a difference between a production plan and an actual result, or the number of owned equipment and its capacity. Data changes, or production volumes,
A database storing change data based on a production flow, a change in production data on a production date, etc., a knowledge base storing a procedure necessary for creation and change of a plan in a rule type format, the database and the database An input device for inputting a knowledge base, a working memory for temporarily storing a result of inference in the process of creating and changing a plan, and a plan based on the database, the knowledge base, and the working memory An inference engine having a local plan creator for performing a re-planning of the created plan in a local area including a portion affected by the change, and a plan result. A printing device for printing the result of the plan, the database, the knowledge base, and the input device. , The working memory, the inference engine, the display device, and a central processing unit that comprehensively manages and controls the printing device, wherein the local plan creation means changes the equipment operating time in the created plan. Is affected by the assignment to the part where the occurrence occurs, or the occurrence of the difference between the production plan and the actual, or the assignment to the equipment where the change of the basic data occurs, or the change of the production data, etc. Searching for a change target, which is a part to be changed, by searching from the working memory a lot having a work start time and a work completion time linked to the work start time and the work completion time of the designated change lot Means, a change target deletion means for deleting the searched change target, and before re-planning the deleted change target portion Planning reasoning apparatus characterized by comprising a planning unit. 3. The apparatus according to claim 2, wherein:
An apparatus for collecting production performance data and equipment operation status data obtained from production equipment, and change data generating means for generating change data for a plan change from the production performance data and equipment operation status data and storing the change data in a database A planning type inference apparatus characterized by the following. 4. The method according to claim 2, wherein the plan creation means evaluates the pass / fail of the plan result based on an intermediate result of the plan stored in the working memory, and furthermore, if there is a defect in the evaluation result, a plan is prepared. A planning-type inference apparatus comprising an inference engine having a plan evaluation means for operating a knowledge base for use and reconstructing a plan and reconstructing a more suitable knowledge base. 5. A means for reconstructing a structured planning database as claimed in claim 2, wherein the planning data input from the input device is made consistent with other related planning data. A plan-type inference apparatus comprising a data use interface having means for providing necessary data to the inference engine from the structured planning database in a required form in various aspects of the planning process. . 6. A means for constructing a knowledge base for planning input from an input device into a knowledge base as a knowledge base for structured planning, and an inference engine in various aspects of the planning process. On the other hand, a planning-type inference apparatus comprising a knowledge utilization interface having means for providing knowledge necessary for a phase to be processed from the structured planning knowledge base. 7. A plan changing means for changing a plan based on change data of a plan inputted from an input device and a result of said change, wherein the influence of the change is made via a working memory. A planning-type inference apparatus comprising: an inference engine having an intelligent editor including local plan creation means for sequentially searching for and changing a received portion. 8. An inference result database storing an inference result, an output specification input from an input device, and data output means for outputting the contents of the database in accordance with the output specification. A planning-type inference apparatus comprising: an inference result graph output unit that outputs the contents of the inference result database; and a data output interface including the simulation output unit.