KR20220051505A - Server, method and computer program for determining parameter of specific process - Google Patents

Abstract

A server for determining a parameter, which flexibly responds to various situations in each process and changes parameters at the right time, includes: a data collection unit that collects operation data of a specific process; a driving parameter derivation unit that generates a simulation model based on the collected operation data and determines a parameter set which satisfying an objective function by inputting a plurality of input parameters that are preset; and a correction parameter derivation unit that generates an artificial intelligence model based on the collected operation data and derivates at least one specific parameter value included in the plurality of input parameter based on the artificial intelligence model, wherein the parameter set is changed based on an error range between the at least one specific parameter value included in the determined parameter set and the derived at least one specific parameter value.

Description

SERVER, METHOD AND COMPUTER PROGRAM FOR DETERMINING PARAMETER OF SPECIFIC PROCESS

The present invention relates to a parameter determination server, method and computer program for a specific process.

In general, a process process is designed according to the purpose, type, and necessary factors of the process, and the process process achieves the purpose of the process through a plurality of various processes.

In the process of carrying out each process, the manager must determine various variables that make up the process, i.e., parameters (eg, number of workers, conveyor speed, operating time, etc.), according to the given site conditions, in order to more efficiently achieve the purpose of the process. do.

In the conventional case, the parameters of each process are determined depending only on the manager's know-how, or are determined based on simple rules or rules.

However, in the conventional case, it has been difficult to derive optimal parameters for efficiently operating each process by considering complex functions of advanced facilities and control systems for controlling them.

In addition, as in the prior art, when a parameter is determined by relying only on the manager's know-how, there is a problem in that it is difficult to respond when a new situation occurs or the situation changes rapidly. In addition, when determining the parameters of each process based on a simple rule, the rules do not take into account the influence between multiple parameters, so when changing any one parameter in a specific situation, it affects other parameters, resulting in unexpected, such as reduction of equipment life. side effects had occurred.

Korean Patent Publication No. 10-2088697 (Registered on March 9, 2020)

The present invention is to solve the problems of the prior art described above, and a parameter determination server, method and computer for deriving optimal parameters for efficiently operating each process in consideration of the purpose, type, necessary factors, etc. for each process We want to provide a program.

In addition, the present invention is to provide a parameter determination server, method, and computer program for changing parameters in a timely manner by flexibly responding to various situations of each process.

However, the technical problems to be achieved by the present embodiment are not limited to the technical problems described above, and other technical problems may exist.

As a means for achieving the above-described technical problem, an embodiment of the present invention, in the server for determining a parameter for a specific process, a data collection unit for collecting operation data of the specific process; a driving parameter derivation unit that generates a simulation model based on the collected operation data and determines a parameter set satisfying an objective function by inputting a plurality of preset input parameters to the simulation model; and a correction parameter derivation unit for generating an artificial intelligence model based on the collected operation data, and deriving a value of at least one specific parameter included in the plurality of input parameters based on the artificial intelligence model, wherein the determined The parameter determination server may be provided, wherein the parameter set is changed based on an error range between the value of the at least one specific parameter included in the parameter set and the derived value of the at least one specific parameter.

Another embodiment of the present invention provides a method for determining a parameter for a specific process, the method comprising: collecting operational data of a specific process; a driving parameter deriving step of generating a simulation model based on the collected operation data and determining a parameter set satisfying an objective function by inputting a plurality of preset input parameters to the simulation model; and a correction parameter derivation step of generating an artificial intelligence model based on the collected operation data, and deriving a value of at least one specific parameter included in the plurality of input parameters based on the artificial intelligence model, The method may provide a parameter determining method, wherein the parameter set is changed based on an error range between the value of the at least one specific parameter included in the determined parameter set and the derived value of the at least one specific parameter.

Another embodiment of the present invention is a computer program stored in a computer readable recording medium including a sequence of instructions for determining a parameter for a specific process, wherein the computer program is executed by a computing device to operate the specific process Collect data, generate a simulation model based on the collected operational data, input a plurality of preset input parameters to the simulation model to derive driving parameters that determine a parameter set that satisfies an objective function, and the collection Generate an artificial intelligence model based on the operational data, derive a correction parameter for deriving a value of at least one specific parameter included in the plurality of input parameters based on the artificial intelligence model, and include in the determined parameter set A computer program stored in a computer-readable medium comprising a sequence of instructions that causes the value of the at least one specific parameter to be changed and the value of the at least one specific parameter derived from the value of the at least one specific parameter to change the parameter set based on an error range; can provide

The above-described problem solving means are merely exemplary, and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description.

According to any one of the above-described problem solving means of the present invention, a parameter determination server, method and computer program for deriving parameters for efficiently operating each process in consideration of the purpose, type, and necessary factors for each process, etc. are provided. can do.

In addition, it is possible to provide a parameter determination server, a method, and a computer program that flexibly respond to various situations in each process and change parameters in a timely manner.

1 is a block diagram of a parameter determination server according to an embodiment of the present invention.
2A and 2B are exemplary diagrams for explaining the configuration of a parameter determination server according to an embodiment of the present invention.
3 is a flowchart of a method for determining a parameter according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . In addition, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated, and one or more other features However, it is to be understood that the existence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded in advance.

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware.

Some of the operations or functions described as being performed by the terminal or device in this specification may be instead performed by a server connected to the terminal or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal or device connected to the server.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of a parameter determination server according to an embodiment of the present invention, and FIGS. 2A and 2B are exemplary views for explaining the configuration of a parameter determination server according to an embodiment of the present invention.

1 and 2 , the parameter determination server may include a data collecting unit 110 , a driving parameter deriving unit 120 , and a correction parameter deriving unit 130 . Components that can be controlled by the parameter determination server 100 are illustrated by way of example.

Each component of the parameter determination server 100 of FIG. 1 is generally connected through a network. For example, as shown in FIG. 1 , the data collecting unit 110 , the driving parameter deriving unit 120 , and the correction parameter deriving unit 130 may be connected at the same time or at a time interval.

A network refers to a connection structure in which information can be exchanged between each node, such as terminals and servers, and includes a local area network (LAN), a wide area network (WAN), and the Internet (WWW: World). Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television networks, and the like. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), Wi-Fi, Bluetooth communication, infrared communication, ultrasound Communication, Visible Light Communication (VLC), LiFi, and the like are included, but are not limited thereto.

The data collection unit 110 according to an embodiment of the present invention may collect operation data of a specific process. For example, the data collection unit 110 may collect, for example, sensor data of the facility, the speed of the facility, the processing time for each process, the operation time of the process, the environment of the factory, etc. in real time as operation data. . Operation data of a specific process collected by the data collection unit 110 may be utilized to generate the simulation model 121 and the artificial intelligence model 131 .

The driving parameter derivation unit 120 according to an embodiment of the present invention may generate the simulation model 121 based on the collected operation data.

For example, the driving parameter deriving unit 120 may generate the simulation model 121 reflecting the process of a specific process based on the collected operation data. Here, the simulation model 121 may be implemented as a discrete event model. That is, the driving parameter deriving unit 120 may be implemented as the simulation model 121 by combining events that occur discretely in a continuous time period of a specific process.

For example, the driving parameter deriving unit 120 may implement a simulation model 121 by combining a specific process into a generator step, a buffer step, and a processor step. For example, in the case of simulating the engine assembly process, the driving parameter deriving unit 120 generates the engine into a process process according to a predetermined cycle, a predetermined production schedule, or event conditions, before the input engine is moved to the next process. It is possible to implement the simulation model 121 combined with the waiting step and the process processing step in which the process is performed.

Thereafter, referring to FIG. 2A , the driving parameter deriving unit 120 may determine a parameter set B that satisfies the objective function by inputting a plurality of preset input parameters 210 to the simulation model 121 .

For example, the driving parameter derivation unit 120 may determine the parameter set B based on a genetic algorithm so that various elements of a specific process can be considered. One parameter set (B) may be determined by combining a plurality of input parameter values that satisfy the purpose of a specific process through selection, crossbreeding, and mutation search processes of a genetic algorithm.

Specifically, the driving parameter deriving unit 120 generates a candidate parameter set A by combining values of a plurality of preset input parameters 210 , and inputs the candidate parameter set A to the simulation model 121 . Thus, a specific process can be simulated.

That is, the driving parameter deriving unit 120 derives values of each of the plurality of input parameters 210 suitable for the purpose of the specific process by performing simulation while changing the values of each of the plurality of input parameters 210 for a specific process. can do. Here, the value of each of the plurality of input parameters 210 suitable for the purpose of a specific process constitutes the parameter set (B).

For example, in an engine assembly process for the purpose of maximizing the number of daily assembly, the driving parameter derivation unit 120 may set a plurality of input parameter values including the number of workers in the engine assembly process, the conveyor speed, and the equipment speed. . The driving parameter deriving unit 120 may apply the input parameters to the simulation model while changing the input parameter values including the number of workers in the engine assembly process, the conveyor speed, and the equipment speed. The driving parameter derivation unit 120 may derive a plurality of input parameter values including the number of workers in the engine assembly process, the conveyor speed, and the facility speed values that satisfy the maximization of the daily assembly number, based on the simulation result.

The correction parameter derivation unit 130 according to an embodiment of the present invention generates an artificial intelligence model 131 based on the collected operational data, and is included in the parameter set B based on the artificial intelligence model 131. A value b' of at least one specific parameter may be derived. Here, the artificial intelligence model 131 may use a multi-layer perceptron. In general, a multi-perceptron is composed of an input layer, a hidden layer, and an output layer, and a plurality of activation functions present in the hidden layer and the output layer may be formed, and a plurality of weights may be formed accordingly. It is characterized by being able to

Also, the artificial intelligence model 131 may be learned based on a past process pattern for a specific process. For example, the artificial intelligence model 131 is based on the pattern of the engine assembly process according to the engine assembly process variables including hourly, weekday, weekend, holiday period, number of workers, worker placement, and factory internal environment for the engine assembly process. can be learned based on

Specifically, the correction parameter derivation unit 130 may predict a future process parameter value for a specific process through the artificial intelligence model 131 . For example, the correction parameter derivation unit 130 may predict a future process time of the engine assembly process through the previously-learned artificial intelligence model 131 .

The correction parameter derivation unit 130 may predict the value (b') of the specific parameter by inputting future process variables that will affect the specific process in the artificial intelligence model 131 . For example, it is possible to predict the process required time in the future by inputting the process variables of the forecasted date to be predicted (eg, the facility utilization rate on the forecasted day, the number of workers, worker placement, etc.) into the artificial intelligence model 131 .

The driving parameter derivation unit 120 may derive a first value (a) of the specific parameter, and the correction parameter derivation unit 130 may derive a second value (a') of the specific parameter. For example, the driving parameter derivation unit 120 may derive a first value (a) for the facility operation speed of the engine assembly process, and the correction parameter derivation unit 130 may determine the future process time of the engine assembly process. A second value (a') may be derived.

The driving parameter deriving unit 120 may change the value of the specific parameter to the second value b' when the error between the first value b and the second value b' is out of a preset error range. For example, the driving parameter deriving unit 120 compares the first value (b) for the facility operation speed with the second value (b') for the future process time, and when the error is outside the preset error range , the input parameter value for the equipment operating speed of the engine assembly process may be changed to a second value (b') for the future process time.

Thereafter, the driving parameter derivation unit 120 generates a plurality of candidate parameter sets A′ including the specific parameter changed to the second value b′, and stores the set in the simulation model 121 with reference to FIG. 2B . A plurality of candidate parameter sets A' may be input to determine another parameter set B' that satisfies the objective function.

For example, the driving parameter deriving unit 120 may generate a plurality of other candidate parameter sets generated by combining the input parameter value for the facility operation speed of the engine assembly process with the second value b' and the values of other input parameters. (A') may be input to the simulation model 121 . The driving parameter derivation unit 120 may determine a parameter set B′ that satisfies the purpose of the engine assembly process of maximizing the number of daily assemblies, based on the simulation result. Here, the input parameter value for the facility operation speed of the engine assembly process included in the parameter set (B') is the second value (b'), and the value of the other input parameter is different from the value included in the parameter set (B) can do.

That is, the parameter determination server 100 according to an embodiment of the present invention includes a value (b) of at least one specific parameter included in a parameter set (B) including a plurality of input parameters determined based on a simulation model; The parameter set B may be changed based on an error range of the value b′ of the at least one specific parameter derived based on the artificial intelligence model.

In addition, the parameter determination server 100 according to an embodiment of the present invention may compare the parameter set (B') determined based on the simulation model and the artificial intelligence model with sensor data of the process equipment collected in real time. When the error between the parameter set (B') and the real-time sensor data of the process equipment is out of the preset tolerance range, the parameter determination server 100 changes the values of a plurality of input parameters included in the parameter set (B') to change the parameter The set B' may be changed within a preset tolerance range. Alternatively, the parameter determination server 100 may change the parameter set B within a preset tolerance range by adding a constraint condition in the driving parameter derivation unit 120 to execute the algorithm.

3 is a flowchart of a method for determining a parameter according to an embodiment of the present invention. The parameter determination method shown in FIG. 3 includes steps processed in time series according to the embodiment shown in FIGS. 1 to 2 . Therefore, even if omitted below, it is also applied to the method of determining a parameter in the parameter determination server 100 according to the embodiment shown in FIGS. 1 to 2 .

In step S310, the parameter determination server 100 may collect operation data of a specific process.

In step S320, the parameter determination server 100 generates a simulation model based on the collected operational data, and inputs a plurality of preset input parameters to the simulation model to derive driving parameters that determine a parameter set that satisfies the objective function. can

In step S330, the parameter determination server 100 generates an artificial intelligence model based on the collected operational data, and a correction parameter for deriving a value of at least one specific parameter included in a plurality of input parameters based on the artificial intelligence model. can be derived

In step S340, the parameter determination server may change the parameter set based on an error range between the value of the at least one specific parameter included in the determined parameter set and the value of the at least one specific parameter derived.

In the above description, steps S310 to S340 may be further divided into additional steps or combined into fewer steps, according to an embodiment of the present invention. In addition, some steps may be omitted as needed, and the order between the steps may be switched.

The method for determining a parameter in the parameter determination server described through FIGS. 1 to 3 is also implemented in the form of a computer program stored in a computer-readable recording medium executed by a computer or a recording medium including instructions executable by the computer. can be In addition, the method for determining a parameter in the parameter determination server described with reference to FIGS. 1 to 3 may be implemented in the form of a computer program stored in a computer-readable recording medium that is executed by a computer.

A computer-readable recording medium may be any available medium that can be accessed by a computer, and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable recording medium may include a computer storage medium. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention. do.

100: parameter determination server
110: data collection unit
120: driving parameter derivation unit
130: correction parameter derivation unit

Claims (15)

In the server for determining parameters for a specific process,
a data collection unit for collecting operational data of a specific process;
a driving parameter derivation unit that generates a simulation model based on the collected operation data and determines a parameter set satisfying an objective function by inputting a plurality of preset input parameters to the simulation model; and,
A correction parameter derivation unit for generating an artificial intelligence model based on the collected operation data, and deriving a value of at least one specific parameter included in the plurality of input parameters based on the artificial intelligence model
including,
The parameter determination server, wherein the parameter set is changed based on an error range between the value of the at least one specific parameter included in the determined parameter set and the derived value of the at least one specific parameter.
The method of claim 1,
and the driving parameter derivation unit determines the parameter set based on a genetic algorithm.
The method of claim 1,
wherein the driving parameter deriving unit generates a plurality of candidate parameter sets by combining values of each of the plurality of preset input parameters, and inputs the generated plurality of candidate parameter sets to the simulation model.
The method of claim 1,
The driving parameter deriving unit derives a first value of the specific parameter,
wherein the correction parameter derivation unit derives a second value of the specific parameter.
5. The method of claim 4,
The driving parameter deriving unit,
and changing the value of the specific parameter to the second value when the error between the first value and the second value is out of a preset error range.
6. The method of claim 5,
wherein the driving parameter deriving unit determines a parameter set satisfying the objective function by inputting a plurality of candidate parameter sets including the specific parameter changed to the second value into the simulation model.
The method of claim 1,
The parameter determination server, wherein the correction parameter derivation unit predicts the value of the specific parameter by inputting a future process variable that will affect the specific process in the artificial intelligence model.
A method for determining parameters for a particular process, comprising:
collecting operational data of a specific process;
a driving parameter deriving step of generating a simulation model based on the collected operation data and determining a parameter set satisfying an objective function by inputting a plurality of preset input parameters to the simulation model; and
A correction parameter derivation step of generating an artificial intelligence model based on the collected operation data, and deriving a value of at least one specific parameter included in the plurality of input parameters based on the artificial intelligence model
including,
and the parameter set is changed based on an error range between the value of the at least one specific parameter included in the determined parameter set and the derived value of the at least one specific parameter.
9. The method of claim 8,
wherein the step of deriving the driving parameter determines the set of parameters based on a genetic algorithm.
9. The method of claim 8,
The step of deriving the driving parameters may include generating a plurality of candidate parameter sets by combining respective values of the plurality of preset input parameters; and
and inputting the generated plurality of candidate parameter sets into the simulation model.
9. The method of claim 8,
the step of deriving the driving parameter comprises deriving a first value of the specific parameter,
wherein the step of deriving the calibration parameter comprises deriving a second value of the particular parameter.
12. The method of claim 11,
In the step of deriving the driving parameters,
and changing the value of the specific parameter to the second value when the error between the first value and the second value is out of a preset error range.
13. The method of claim 12,
The step of deriving the driving parameter further comprises the step of determining a parameter set satisfying the objective function by inputting a plurality of candidate parameter sets including the specific parameter changed to the second value into the simulation model. Way.
9. The method of claim 8,
The step of deriving the correction parameter comprises predicting the value of the specific parameter by inputting a future process variable that will affect the specific process into the artificial intelligence model.
In a computer program stored on a computer-readable medium comprising a sequence of instructions for determining a parameter for a specific process,
When the computer program is executed by a computing device,
collect operational data of a specific process;
A simulation model is generated based on the collected operational data, and a plurality of preset input parameters are input to the simulation model to derive a driving parameter for determining a parameter set that satisfies an objective function,
generating an artificial intelligence model based on the collected operational data, and deriving a correction parameter for deriving a value of at least one specific parameter included in the plurality of input parameters based on the artificial intelligence model;
and a sequence of instructions that cause the parameter set to be changed based on a margin of error between the value of the at least one specific parameter included in the determined parameter set and the derived value of the at least one specific parameter. A computer program stored on a medium.

Images