Disclosure of Invention
The invention aims to solve the technical problems in the prior art and provides an optimization scheduling method, system, medium and equipment based on data mining and process models.
To solve the above technical problems, an embodiment of the present invention provides an optimization scheduling system based on data mining and process models, including:
the data mining module is used for acquiring historical data of a preset time period, and performing data mining analysis according to the historical data to obtain a historical data analysis result;
the process model module is used for establishing a mathematical physical model of a specific industry by combining the initial model with a process model of the specific industry;
and the plan scheduling module is used for carrying out optimized scheduling according to the historical data analysis result and/or the mathematical physical model of the specific industry.
In order to solve the above technical problems, an embodiment of the present invention further provides an optimization scheduling method based on data mining and process models, including:
acquiring historical data of a preset time period, and performing data mining analysis according to the historical data to obtain a historical data analysis result;
establishing a mathematical physical model of a specific industry by combining the initial model with a process model of the specific industry;
and performing optimization scheduling according to the historical data analysis result and/or the mathematical physical model of the specific industry.
To solve the foregoing technical problems, an embodiment of the present invention provides a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to execute the optimization scheduling method based on data mining and process model according to the foregoing technical solution.
In order to solve the above technical problems, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the data mining and process model-based optimization scheduling method according to the above technical solution when executing the computer program.
The invention has the beneficial effects that: the influence of various change factors on the planning and scheduling, such as processing environment change, market change and the like, is fully considered through historical data mining and analysis, the change conditions of the factors can be effectively predicted through historical data mining, and the predicted data are transmitted to the planning and scheduling module so as to carry out more reasonable planning and scheduling; in addition, the invention combines the process model of the specific industry, thereby being more in line with the specific industrial environment; the three modules are mutually associated, and the data mining module and the process model module are mutually verified and simultaneously serve as input parts of the planning and scheduling module; the invention can effectively improve the precision of planning and scheduling, control specific industrial environment and achieve better application effect.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a block diagram of an optimized scheduling system based on data mining and process models according to an embodiment of the present invention. As shown in fig. 1, the system includes: the system comprises a data mining module, a process model module and a plan scheduling module.
The data mining module is used for acquiring historical data of a preset time period, and performing data mining analysis according to the historical data to obtain a historical data analysis result; the process model module is used for establishing a mathematical physical model of a specific industry by combining the initial model with a process model of the specific industry; and the plan scheduling module is used for carrying out optimized scheduling according to the historical data analysis result and/or the mathematical physical model of the specific industry.
When the planning and scheduling module performs optimized scheduling according to the historical data analysis result and the mathematical physical model of the specific industry, the mathematical physical model in the process model module is modified according to the historical data analysis result of the data mining module to form a gray box model; and the plan scheduling module performs optimized scheduling according to the ash box model.
In the embodiment, the data mining module is used for mining and analyzing the acquired historical data of the specific process in the preset time period, the influence of various change factors on the planning and scheduling, such as the change of a processing environment, the change of a market and the like, is fully considered, the change conditions of the factors can be effectively predicted through the historical data mining, and the predicted data is transmitted to the planning and scheduling module so as to carry out more reasonable planning and scheduling; in addition, the invention combines the process model of the specific industry, thereby being more in line with the specific industrial environment; the three modules are mutually associated, and the data mining module and the process model module are mutually verified and simultaneously serve as input parts of the planning and scheduling module; the invention can effectively improve the precision of planning and scheduling, control specific industrial environment and achieve better application effect.
Optionally, the data mining module is specifically configured to,
acquiring historical data of a preset time period, carrying out data mining analysis by adopting a cluster analysis algorithm, a random forest algorithm or a smooth index prediction model according to actual conditions, predicting order change, equipment fault conditions and product quality conditions in the market, and acquiring historical data analysis results.
Optionally, the process model module is specifically adapted to,
establishing an initial model according to actual engineering experience, carrying out data mining on a process model of a specific industry by adopting a Bayesian network algorithm or a decision tree model algorithm according to actual conditions, and combining model data obtained by mining with the initial model to obtain a mathematical physical model of the specific industry.
It should be noted that a process model for a particular industry may refer to the requirements of a particular process for a plant. For example, boiler serpentine tubes are produced. The welding position is required to be at least 70mm away from the bending part, and a mechanical model needs to be established.
The optimized scheduling scheme provided by the embodiment of the invention is specific to a specific industry, that is, different industries, wherein the processes have great differences. For example, in the semiconductor industry, the existence of test stages needs to be considered in the process of establishing a process model; in the metal plate industry, a test stage is not provided in the process of establishing a process model, but an automatic nesting stage is provided.
Optionally, the process model module is further configured to return model data of the mathematical physical model to the data mining module as historical data.
Optionally, the plan scheduling module is further configured to obtain optimized scheduling result data, determine difference data between the optimized scheduling result data and actual production data, and return the difference data to the data mining module and the process model module for verification and correction.
The purpose of planning production scheduling is to ensure the cooperativity of production links of each workshop, so that the shutdown of the whole production caused by the out-of-position of some parts is avoided, and the market delivery is delayed. However, in practice, the result calculated by the computer planning scheduling has a certain error from the actual production; this error can be expressed in many indicators, such as the order delay rate, and the accurate productivity of certain plants or links. And the like. According to the embodiment of the invention, the difference data between the optimized scheduling result data and the actual production data is calculated and returned to the data mining module and the process model module for verification and correction, so that the accuracy of the data mining module and the process model module is continuously improved, the accuracy of the planning and scheduling module is further improved, and the precision of the planning and scheduling is effectively improved.
Specifically, model modification is a necessary link in computer modeling, and the main reason is that a certain difference exists between the established model and the real model. And correcting to enable the computer model to conform to the application scene at the time. The correction parameters and correction process are determined according to actual conditions.
When optimizing and scheduling, a user selects an operation time period, and the data mining module predicts the market sale condition, the equipment fault operation condition and the supply chain material condition by adopting an algorithm such as a cluster analysis algorithm, a random forest algorithm or a smooth index prediction model according to the past historical data; and planning and scheduling according to the prediction result, such as when more production should be performed, which machine should be produced more, the materials should be configured in advance, and the like.
In addition, when planning and scheduling, besides automatically planning and scheduling according to the prediction result, a planner or an administrator can manually adjust the working time of the dragging process to plan and schedule.
The process model module of the embodiment of the invention selects a specific process model according to specific industry and industrial environment, and the process model comprises the following steps: priority procedures, workshops and material inventory, etc.
And if the emergency insertion occurs, the priority in the process model can be modified first, and then the optimization scheduling is continued.
It should be noted that the three modules may be used in combination, and may also be used in combination as separate modules, or may achieve a relatively good effect. The combined use comprises the following steps: firstly, a data mining module is combined with a plan scheduling module, and the situation needs to rely on a large amount of data and is continuously compared with the actual production situation; secondly, combining the process model module with a planning and scheduling module, wherein the planning and scheduling of the specific process are carried out under the condition of limited accuracy and longer scheduling time; and thirdly, combining the data mining module, the process model module and the planning and scheduling module, wherein the condition refers to that a mathematical physical model in the process model module is corrected according to a historical data analysis result of the data mining module to form a gray box model. The scheduling method has high accuracy and short time consumption for scheduling production.
In addition, the embodiment of the invention can adopt cloud deployment to solve the problem that a large amount of computing resources are required to be consumed in the computing process.
The optimization scheduling system based on data mining and process model provided by the embodiment of the invention is described in detail above with reference to fig. 1. The following describes the optimization scheduling method based on data mining and process model according to the embodiment of the present invention in detail with reference to fig. 2.
As shown in fig. 2, an embodiment of the present invention further provides an optimization scheduling method based on data mining and process models, including:
acquiring historical data of a preset time period, and performing data mining analysis according to the historical data to obtain a historical data analysis result;
establishing a mathematical physical model of a specific industry by combining the initial model with a process model of the specific industry;
and performing optimization scheduling according to the historical data analysis result and/or the mathematical physical model of the specific industry.
In the embodiment, through historical data mining analysis, the influence of various change factors on planning and scheduling, such as processing environment change, market change and the like, is fully considered, the change conditions of the factors can be effectively predicted through historical data mining, and the predicted data is transmitted to the planning and scheduling module so as to plan and schedule more reasonably; in addition, the invention combines the process model of the specific industry, thereby being more in line with the specific industrial environment; the three modules are mutually associated, and the data mining module and the process model module are mutually verified and simultaneously serve as input parts of the planning and scheduling module; the invention can effectively improve the precision of planning and scheduling, control specific industrial environment and achieve better application effect.
Optionally, the obtaining historical data of a preset time period, performing data mining analysis according to the historical data, and obtaining a historical data analysis result includes:
acquiring historical data of a preset time period, carrying out data mining analysis by adopting a cluster analysis algorithm, a random forest algorithm or a smooth index prediction model, predicting order change, equipment fault conditions and product quality conditions in the market, and acquiring historical data analysis results.
Optionally, the establishing an industry-specific mathematical physical model by using the initial model in combination with an industry-specific process model includes:
establishing an initial model according to actual engineering experience, carrying out data mining on a process model of a specific industry by adopting a Bayesian network algorithm or a decision tree model algorithm, and combining model data obtained by mining with the initial model to obtain a mathematical physical model of the specific industry.
The embodiment of the present invention further provides a computer-readable storage medium, which includes instructions, and when the instructions are executed on a computer, the computer executes the optimization scheduling method based on data mining and process model according to the above embodiment.
The embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and when the processor executes the computer program, the processor implements the data mining and process model-based optimization scheduling method described in the above embodiment.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.