KR102185433B1 - Intelligent utility system piping design apparatus and method - Google Patents

Abstract

The present invention relates to an intelligent utility system piping design device and to a method thereof. The intelligent utility system piping design device comprises: an input unit which receives request information including factory information, equipment information, and process information; a utility system design unit which determines a factory layout and process flow based on at least one of the factory information, the equipment information, and the process information, and designs a utility system based on the factory layout and process flow; a utility system piping design unit which defines piping to correspond to the utility flow by the utility system and generates piping design information optimized for each piping; and a providing unit which provides the piping design information.

Description

Intelligent utility system piping design device his method {INTELLIGENT UTILITY SYSTEM PIPING DESIGN APPARATUS AND METHOD}

The present application relates to an intelligent utility system piping design apparatus and method.

Utility refers to heating steam, cooling water, power, fuel, etc. supplied to production facilities in a factory, or facilities that supply them. In other words, a cooling source, a heating source, a power source, etc. are required to secure an appropriate temperature, pressure, and power in the production process, and this is called a utility. Exemplarily, the cooling source is air or the like, the heating source is fire heat, steam, and the like, and the power source is electric power, steam, or the like.

On the other hand, the building in which the semiconductor is manufactured may be referred to as a line, and the structure of the line is a two-story structure of a fab and a sub fab, or a fab, a clean sub fab. ) And Facility Sub Fab (Facility Sub Fab). Here, Fab means a clean room (C/R) in which a semiconductor manufacturing process is performed. A sub fab is a space in which facilities that provide chemical substances necessary for the process to production facilities and remove (exhaust) residual chemical substances after the process proceeds are arranged, and it can be understood that utility supply facilities are provided. .

In particular, the importance of a utility system that supplies and discharges utilities such as high-purity gas, compressed air, process cooling water, ultrapure water, wastewater, waste liquid, and chemicals in semiconductor processes and semiconductor production facilities that require high precision and cleanliness is said to be of greater importance. can do. On the other hand, utilities such as high purity gas, compressed air, process cooling water, ultrapure water, waste water, waste liquid, and chemicals correspond to fluids, and supply and discharge of fluids are made through piping, so piping design is a key task in utility systems. can do.

In the prior art, semiconductor fab utilities such as pipes and ducts are classified by bay, standardized standards of semiconductor fab utilities, and modularized semiconductor fab utilities are combined for each bay, enabling efficient construction of semiconductor fab utilities. , There is a limitation in that it cannot provide information for the optimal piping design of the utility system for the building, equipment, or process by reflecting the layout of the building to be built in the complex, the layout of the production equipment in the building, and the process flow. do.

The technology behind the present application is disclosed in Korean Patent Publication No. 10-1600068.

The present application is intended to solve the problems of the prior art described above, in consideration of the mid- to long-term plan for factory construction and the linkage between buildings, production equipment, processes, etc., so that an optimized piping design of the utility system for the plant can be performed. An object of the present invention is to provide an intelligent utility system piping design apparatus and method capable of providing optimized piping design information.

The present application is to solve the problems of the prior art described above, and an object thereof is to provide an intelligent utility system piping design apparatus and method capable of providing optimal piping design information analyzed based on big data.

The present application is to solve the problems of the prior art described above, and an object of the present invention is to provide an intelligent utility system piping design apparatus and method capable of providing optimized piping design information based on a user's desired standard.

However, the technical problem to be achieved by the embodiments of the present application is not limited to the technical problems as described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, the intelligent utility system piping design apparatus according to an embodiment of the present application includes: an input unit receiving request information including factory information, equipment information, and process information; A utility system design unit determining a factory layout and a process flow based on at least one of the factory information, the equipment information, and the process information, and designing a utility system based on the factory layout and process flow; A utility system piping design unit defining piping to correspond to the utility flow by the utility system and generating piping design information optimized for each piping; And a providing unit that provides the piping design information.

In addition, the utility system design unit determines the utility-specific capacity of the utility system, determines the type, specification, and number of utility supply equipment based on the utility-specific capacity, and the arrangement of the utility supply equipment and the It is possible to determine the flow of utility supplied to the process from the utility supply equipment.

In addition, the utility system piping design unit, using fluid information including the type and characteristic of fluid flowing along the piping and piping information including the arrangement state and design conditions of the piping, the piping design including the specification information of the piping Can generate information.

In addition, the utility system piping design unit, based on a pre-learned artificial neural network for inputting the fluid information and the piping information and outputting the piping optimum specification information, the piping design including optimum specification information for each piping Can generate information.

In addition, the optimum specification information is quality-based optimum specification information or cost-based optimum specification information, and the artificial neural network receives the fluid information and the piping information as inputs, but outputs the piping quality-based optimum specification information in advance. It may be learned or learned in advance by outputting information on the optimum specification based on the cost of the pipe.

In addition, the optimum specification information is customized optimum specification information evaluated by applying a predetermined weight to quality and cost, and the artificial neural network inputs the fluid information and the piping information, but provides customized optimum specification information of the piping. It can be learned in advance as an output.

Also, the input unit may further receive weight information on quality and cost from a user.

On the other hand, the intelligent utility system piping design method according to an embodiment of the present application, (a) the input unit, receiving input request information including factory information, equipment information, and process information; (b) the utility system design unit, determining a factory layout and process flow based on at least one of the factory information, the equipment information, and the process information, and designing a utility system based on the factory layout and process flow; (c) the utility system piping design unit, defining piping to correspond to the utility flow by the utility system, and generating piping design information optimized for each piping; And (d) the providing unit may include providing the pipe design information.

In addition, step (b) may include: (b1) determining the capacity of the utility system for each utility; (b2) determining the type, specification, and number of utility supply equipment based on the capacity for each utility; And (b3) determining the arrangement of the utility supply equipment and the utility flow supplied to the process from the utility supply equipment.

In addition, in the step (c), the utility system piping design unit uses fluid information including the type and characteristics of fluid flowing along the piping and piping information including the arrangement state and design conditions of the piping, The piping design information including information may be generated.

In addition, in step (c), the utility system piping design unit receives the fluid information and the piping information as inputs, and based on a pre-learned artificial neural network that outputs the piping optimum specification information, the optimum specification for each pipe The piping design information including information may be generated.

In addition, the optimum specification information is quality-based optimum specification information or cost-based optimum specification information, and the artificial neural network receives the fluid information and the piping information as inputs, but outputs the piping quality-based optimum specification information in advance. It may be learned or learned in advance by outputting information on the optimum specification based on the cost of the pipe.

In addition, the optimum specification information is customized optimum specification information evaluated by applying a predetermined weight to quality and cost, and the artificial neural network inputs the fluid information and the piping information, but provides customized optimum specification information of the piping. It can be learned in advance as an output.

In addition, in step (a), the input unit may further receive weight information about quality and cost from a user.

Meanwhile, a computer program according to another aspect of the present application may be stored in a computer-readable recording medium in order to execute an intelligent utility system piping design method according to an exemplary embodiment of the present application.

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

According to the above-described problem solving means of the present application, by designing a utility system using factory information, equipment information, and process information, and providing optimized piping design information for each piping of the utility system, mid- to long-term planning for factory construction and linkage between buildings Considering the production equipment, process, etc., it is possible to design the optimized piping of the utility system for the plant.

According to the above-described problem solving means of the present application, by providing pipe design information including optimum specification information for each pipe based on the artificial neural network learned in advance, it is possible to provide optimal pipe design information analyzed based on big data.

According to the above-described problem solving means of the present application, by providing piping design information including optimum specification information generated using an artificial neural network learned based on piping specification information optimized for a user's desired standard, It can provide optimized piping design information.

However, the effect obtainable in the present application is not limited to the effects as described above, and other effects may exist.

1 is a schematic block diagram of an intelligent utility system piping design apparatus according to an embodiment of the present application.
2 is a diagram illustrating an interface provided by an intelligent utility system piping design apparatus according to an embodiment of the present disclosure in order to receive an optimization criterion from a user.
3 is a diagram illustrating an interface provided by an intelligent utility system piping design apparatus according to an embodiment of the present application to receive a weight for each optimization criterion from a user.
4 is a view for explaining a process of learning the artificial neural network of the intelligent utility system piping design apparatus according to an embodiment of the present application.

Hereinafter, exemplary embodiments of the present application will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art may easily implement the present application. However, the present application may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in the drawings, parts not related to the description are omitted in order to clearly describe the present application, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the present specification, when a part is said to be "connected" with another part, it is not only "directly connected", but also "electrically connected" or "indirectly connected" with another element interposed therebetween. "Including the case.

Throughout this specification, when a member is positioned "on", "upper", "upper", "under", "lower", and "lower" of another member, this means that a member is located on another member. It includes not only the case where they are in contact but also the case where another member exists between the two members.

Throughout the specification of the present application, when a certain part "includes" a certain component, it means that other components may be further included rather than excluding other components unless specifically stated to the contrary.

In order to design the piping of the utility system operated for the production facility or production process in constructing the factory corresponding to the production facility, we design the utility system in consideration of various information about the factory, equipment and process provided from the client. It relates to an intelligent utility system design apparatus and method for generating and providing optimal specification information for each pipe of a pipe connecting the designed utility system and production equipment (or production process).

Users can create drawings and specifications/invoices based on pipe design information optimized for each pipe provided by the present application. Illustratively, the drawings may be Process Flow Diagram (PFD), Utility Flow Diagram (UFD), Process & Instrument Diagram (P&ID), etc., but are not limited thereto.

On the other hand, the role of the utility system in the production process and production equipment is very important. If the supply of utilities, etc. is not smoothly performed by the utility system, a major problem occurs in the safe operation and economics of production facilities. In addition, in supplying utilities, a pipe is one of the essential components. In general, piping design is a generic term for the design process in which devices and devices are connected using appropriate piping parts as specified in the process, and these devices maintain the best operating performance and the plant operates efficiently. It has a very important effect on being. Piping design is also important in that it accounts for 40-50% of the total manpower required among the work volume of the overall plant design, and piping costs require 25-35% of the total plant construction cost. You can check. Taken together, piping design must be managed in both quality and cost aspects. We can make customized piping design for each plant by providing optimized piping design information for each pipe, including information on the optimum specification of piping, for each plant, and reduce manpower and piping costs for piping design. have.

Exemplarily, the present application may be applied to a semiconductor fab or a clean room (C/R) in which semiconductor production equipment is provided, and a utility system therefor, but is not limited thereto, and equipment or It can be applied to the industrial clean room (ICR) and utility system therefor.

1 is a schematic block diagram of an intelligent utility system piping design apparatus 10 according to an embodiment of the present application.

1, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application includes an input unit 100, a utility system design unit 200, a utility system piping design unit 300, and a providing unit 400 do.

The input unit 100 may receive request information including factory information, equipment information, and process information. In other words, the request information input through the input unit 100 may include factory information, equipment information, and process information. In this case, the factory information refers to information on mid- to long-term plans related to the construction and operation of a plant, the arrangement of the factory (or building) in the complex, and the linkage with a factory to be additionally constructed in the future. Equipment information refers to information on types, numbers, and specifications of various equipment including production equipment. Process information means information on all processes carried out in a factory or through a production facility. Specifically, the process information may include a name and classification of a process, an input and output for a process, a process time, and the like. In addition, the process information may include information on an order between a plurality of processes.

The intelligent utility system piping design apparatus 10 according to an embodiment of the present application is implemented in the form of a user terminal, and request information including factory information, equipment information, and process information is transmitted through an input device such as a touch display or a keyboard or a mouse. Can be entered directly. As another example, the intelligent utility system piping design apparatus 10 according to an exemplary embodiment of the present disclosure may be provided with a communication unit (not shown) to receive the request information in a manner of receiving request information from a server storing the request information. In this case, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application may communicate with a server through a network. A network refers to a connection structure that enables information exchange between nodes such as terminals and servers, and examples of such networks include 3GPP (3rd Generation Partnership Project) networks, LTE (Long Term Evolution) networks, and 5G networks. Network, WIMAX (World Interoperability for Microwave Access) network, Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), wifi network, This includes, but is not limited to, a Bluetooth network.

On the other hand, the user terminal that is an embodiment of the intelligent utility system piping design device 10 according to an embodiment of the present application, for example, for example, a smart phone (Smartphone), a smart pad (SmartPad), a tablet PC, etc. Wired communication devices such as wireless communication devices and desktop computers may be included.

The utility system design unit 200 may determine a factory layout and a process flow based on at least one of factory information, equipment information, and process information.

For example, the utility system design unit 200 determines the factory layout by determining the size (area, height, number of acceptable equipment, etc.), type (use), layout and cross-section (cross-sectional shape and cross-sectional area) of the building (factory). I can. The factory layout can represent the overall building layout within the complex (factory complex). At this time, the factory layout may be determined in consideration of the connection between buildings (including factories to be built in the future). In addition, the factory layout may indicate the arrangement of equipment, subrooms, and offices provided inside the factory. In this case, the factory layout may be determined in consideration of the type and number of equipment, an order between a plurality of processes, and the like.

On the other hand, the utility system design unit 200 assigns codes to items corresponding to detailed information of factory information, equipment information, and process information, and compares it with the code results analyzed for a factory designed in advance or a factory designed through simulation. The highest plant layout can be determined. In this case, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application may include a database (not shown) in which code results analyzed for a factory designed in advance or a factory designed through simulation are stored.

In addition, the utility system design unit 200 may determine a process flow based on the factory layout and process information. Specifically, the utility system design unit 200 may determine a process flow on a factory layout in consideration of an order between processes. For example, equipment performing the same process may be arranged separately on a factory layout. In this case, the process flow may be determined so that the process flow from the previous process of the process to the process is separated into both sides, and the process flow from the process to the next process of the process is joined again.

The utility system design unit 200 may determine a process flow by connecting a code assigned to each process according to a code order for the entire process in a manner that matches the code assigned to the equipment performing the process.

In addition, the utility system design unit 200 may design a utility system based on a factory layout and a process flow. Specifically, the utility system design unit 200 may determine a capacity for each utility of the utility system. In addition, the utility system design unit 200 may determine the type, specification, and number of utility supply equipment based on the capacity for each utility. In addition, the utility system design unit 200 may determine an arrangement of utility supply equipment and a utility flow supplied from the utility supply equipment to a process.

The utility system design unit 200 may determine a capacity for each utility based on a process flow. The utility system design unit 200 may classify utilities according to the type of fluid. Types of fluids include, for example, general gas, nitrogen, argon, hydrogen, oxygen, LNG, toxic and explosive gases, and process cooling water and ultrapure water. In other words, the utility system design unit 200 may determine a capacity for each fluid supplied by the utility system for the entire process based on the process flow. Here, the capacity may mean the maximum flow rate.

Meanwhile, the utility system design unit 200 may determine a capacity (maximum flow rate) for each utility (fluid) based on information on the type of utility (fluid) required for each process and the required amount (flow rate). In this case, the type and amount of utilities required for each process may be stored in a database (not shown) of the intelligent utility system piping design apparatus 10 according to an exemplary embodiment of the present disclosure.

The utility system design unit 200 may determine the type, specification, and number of utility supply equipment based on the capacity for each utility. Specifically, the utility system design unit 200 may determine the type and specification of utility supply equipment according to the type of utility, and may determine the number of utility supply equipment of different types and specifications according to the capacity of each utility.

In other words, the utility system design unit 200 determines the number of types and specifications of utility supply equipment capable of covering (accommodating) the capacity of each utility based on information on the utility capacity per unit predetermined for each type and specification of the utility supply equipment. I can. The type and specification information of utility supply equipment and utility capacity information per utility may be stored in a database (not shown) of the intelligent utility system piping design apparatus 10 according to an embodiment of the present disclosure.

For example, when the first utility capacity is 10 LPM (Liter per Minute) and the utility capacity per unit of the first utility supply facility is 4 LPM, the number of first utility supply facilities may be determined as three. In addition, when the utility capacity of the second utility supply facility supplying the first utility is 5LPM, two second utility supply facilities may be determined. In this case, the first utility supply facility and the second utility supply facility may have different types or specifications.

The utility system design unit 200 may determine an arrangement of utility supply equipment and a utility flow supplied from the utility supply equipment to a process. The utility system design unit 200 may arrange each utility supply equipment at an appropriate location based on a factory layout and a process flow. Here, the appropriate location may mean a location set so that the length connecting the utility supply equipment and the production equipment corresponding to each process is shortest, and when multiple production equipment is connected to one utility supply equipment, the connection It may be set to be the shortest sum of all lengths, but is not limited thereto.

In addition, the utility system design unit 200 may determine a flow direction and a movement path for each utility based on a process flow. That is, the utility flow may include a direction and a movement path through which the utility flows.

The utility system piping design unit 300 may define piping to correspond to the utility flow by the utility system. Here, defining a pipe may mean creating a virtual pipe along a direction and a moving path in which the utility flows, and giving an identification code for identifying the virtual pipe.

In this case, different identification codes may be assigned depending on the pipe connected to a process from the utility system, the production equipment involved in the process, and the utility flowing along the pipe.

The utility system piping design unit 300 may generate piping design information optimized for each piping. Specifically, the utility system piping design unit 300 generates piping design information including piping specification information using fluid information including fluid type and characteristics and piping information including piping arrangement status and design conditions. can do.

In other words, the utility system piping design unit 300 may generate piping specification information optimized for each piping by using fluid information and piping information. The fluid information is information on a fluid flowing along a corresponding pipe, and may include the type of fluid (argon, hydrogen, nitrogen, ultrapure water, etc.), state (gas, liquid, etc.), physical properties, and chemical properties. The piping information is information on the piping itself, and may include an arrangement state of the piping and a design condition of the piping, but is not limited thereto. The arrangement state of the piping may mean information on whether the piping is connected to which process or which production equipment is connected. In addition, design conditions for piping include (design) temperature, (design) pressure, and the like.

Optimal piping specification information may be different depending on fluid information and piping information. In this case, the pipe specification information may include a material and a specification. The standard may mean a diameter, but is not limited thereto. An available pipe specification range may be preset according to the fluid information and the pipe information. The range of available piping specifications according to the fluid information and piping information may be stored in a database (not shown) of the intelligent utility system piping design apparatus 10 according to an embodiment of the present disclosure.

In addition, according to an embodiment of the present application, the utility system piping design unit 300 inputs fluid information and piping information, and based on a pre-learned artificial neural network that outputs piping optimum specification information, optimum specifications for each pipe Piping design information including information can be generated.

Accordingly, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application may include a model construction unit (not shown) for constructing an optimized piping design information generation model based on an artificial neural network.

An artificial neural network-based optimized pipe design information generation model may be constructed based on a supervised learning-based classification/prediction algorithm. Supervised learning means learning a model by using pre-built training data. Exemplarily, the classification/prediction algorithm may be at least one of a Random Forest algorithm, a support vector machine (SVM) algorithm, an Extra Tree algorithm, an XG Boost algorithm, and a Deep Learning algorithm.

The model building unit (not shown) may extract piping specification information within an available piping specification range from the database according to the fluid information and piping information. In addition, the model building unit (not shown) may perform optimality evaluation on the extracted specification information according to a predetermined conformity evaluation criterion. In addition, the model building unit (not shown) may link the pipe specification information and the evaluation result and store it in the database as a data set for learning. In addition, the model building unit (not shown) learns the artificial neural network in advance based on the training data set, so that fluid information and piping information are input and the optimum specification information of piping is output, and the previously learned, optimized piping design information. You can build a generative model.

According to an embodiment of the present application, the optimal specification information corresponding to the output of the artificial neural network-based optimized piping design information generation model may be optimal specification information based on quality or optimal specification information based on cost. That is, the artificial neural network may receive fluid information and piping information as inputs, but may be learned in advance by outputting optimum specification information based on quality of piping, or learning in advance by outputting optimum specification information based on piping cost.

In other words, the model construction unit (not shown) uses the artificial neural network as a quality standard and cost standard when performing the optimality evaluation on the pipe specification information within the available pipe specification range extracted from the database according to the fluid information and pipe information. Can be evaluated. That is, the model building unit (not shown) may store the pipe specification information, quality evaluation result, and cost evaluation result in a database as a training dataset, and pre-train an artificial neural network based on the training dataset.

Meanwhile, an optimization criterion for optimal specification information may be input from a user through the input unit 100. Alternatively, the optimization criterion for optimal specification information may be understood as a concept included in request information along with factory information, equipment information, and process information. In this regard, it can be more easily understood with reference to FIG. 2.

2 is a diagram illustrating an interface provided by the intelligent utility system piping design apparatus 10 according to an embodiment of the present application to receive an optimization criterion from a user.

2, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application provides an interface for selecting an optimization criterion of optimized piping design information (optimal specification information) to be provided to the user to the user. I can. This may be provided through the providing unit 400 to be described later. The user may select (input) an optimization criterion of optimized piping design information (optimum specification information) to be provided through the input unit 100. In other words, the input unit 100 may receive an optimization criterion from a user.

Specifically, referring to FIG. 2A, the intelligent utility system piping design apparatus 10 according to an exemplary embodiment of the present disclosure may receive an optimization criterion for piping design information as'quality'. In this case, the utility system piping design unit 300 may generate piping design information optimized based on quality standards. That is, the utility system piping design unit 300 may generate piping design information based on the learned artificial neural network by outputting the optimal quality specification information.

In addition, referring to FIG. 2B, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application may receive an optimization criterion for piping design information as'cost'. In this case, the utility system piping design unit 300 may generate piping design information optimized based on cost. That is, the utility system piping design unit 300 may generate piping design information based on the learned artificial neural network by outputting the cost-based optimum specification information.

According to an embodiment of the present application, the optimum specification information corresponding to the output of the artificial neural network-based optimized pipe design information generation model may be customized optimum specification information evaluated by applying a predetermined weight to quality and cost. That is, the artificial neural network may be learned in advance by receiving fluid information and piping information as inputs, but outputting customized optimal specification information of piping. Here, the customized optimal specification information may mean specification information of a pipe optimized by applying a weight for each optimization criterion desired by a user.

As described above, the model construction unit (not shown) uses the artificial neural network to perform optimality evaluation on the pipe specification information within the available pipe specification range extracted from the database according to the fluid information and the pipe information. Can be evaluated as a standard. At this time, the model building unit (not shown) applies weights to the quality evaluation results and cost evaluation results, and then stores the pipe specification information, quality evaluation results, and cost evaluation results in a database as a training dataset, and stores these training data. Based on the three, artificial neural networks can be trained in advance.

Meanwhile, weights (weights for quality and cost) for each optimization criterion may be input through the input unit 100. In other words, the input unit 100 may further receive weight information on quality and cost from the user.

3 is a diagram illustrating an interface provided by an intelligent utility system piping design apparatus according to an embodiment of the present application to receive a weight for each optimization criterion from a user.

3, the intelligent utility piping design apparatus 10 according to an embodiment of the present application provides a user with an interface for inputting weights for each optimization criterion of optimized piping design information (optimal specification information) to be provided by the user. can do. This may be provided through a providing unit 400 to be described later, and a user may input a weight for each optimization criterion through the input unit 100. In other words, the input unit 100 may receive a weight for each optimization criterion from a user.

Specifically, referring to FIG. 3, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application sets a weight for a quality criterion among optimization criteria for piping design information to 3 and a weight for cost criterion to 7 Can receive input (based on a total of 10). In this case, the utility system piping design unit 300 may generate optimized piping design information by applying a quality-based weight of 3 and a cost-based weight of 7. That is, the utility system piping design unit 300 may generate piping design information based on the learned artificial neural network by outputting customized optimal optimal specification information evaluated by applying a quality-based weight of 3 and a cost-based weight of 7. .

4 is a view for explaining a process of learning the artificial neural network of the intelligent utility system piping design apparatus 10 according to an embodiment of the present application. In addition, FIG. 4 shows a state in which an optimality evaluation is performed based on quality and cost standards for the specification information of the pipe within the available pipe specification range extracted based on the fluid information and the pipe information by the model building unit (not shown). It is a drawing.

The model construction unit (not shown) may extract a ranking of piping specification information within an available piping range based on a result of an optimality evaluation based on quality and cost criteria. In addition, the model building unit (not shown) may determine the specification information extracted as the first priority as the optimum specification information of a corresponding pipe and store it in a database as a data set for learning.

Specifically, referring to FIG. 4, for example, when the'quality' criterion is selected (input) as the optimization criterion, the model building unit (not shown) is based on the quality evaluation result for the specification information of the piping within the available piping range. Thus, it is possible to arrange pipe specification information in the order of the highest quality evaluation score, extract the specification information with the highest quality evaluation score, and determine the optimum specification information based on the quality of the pipe. When applied to the case shown in Fig. 4, NO. 6, NO. 1, NO. 4, NO. 2, NO. 3, NO. 5, NO. Sorted in 7 order, NO. Specification information corresponding to 6 may be extracted and determined as quality standard optimal specification information. The extracted and determined quality standard optimal specification information may be stored in a database as a data set for learning. Accordingly, the model building unit (not shown) can train the artificial neural network by inputting fluid information and piping information and outputting the quality standard optimal specification information.

In contrast, when the'cost' criterion is selected (input) as the optimization criterion, and the'cost' criterion is selected (input), the model building unit (not shown) evaluates the cost for the specification information of the pipe within the available piping range. Based on the results, the specification information of the pipes can be arranged in the order of the highest cost evaluation score, and the specification information with the highest cost evaluation score can be extracted to determine the optimum specification information based on the cost of the pipe. When applied to the case shown in Fig. 4, NO. 7, NO. 6, NO. 3, NO. 5, NO. 4, NO. 1, NO. 2 are arranged in order, NO. Specification information corresponding to 7 may be extracted and determined as cost-based optimal specification information. The cost-based optimal specification information extracted and determined as described above may be stored in a database as a data set for learning. Accordingly, the model building unit (not shown) can train the artificial neural network by inputting fluid information and piping information and outputting the cost-based optimal specification information.

In addition, when the'quality' reference weight is input as 3 and the'cost' reference weight is input as 7, although not shown in FIG. 4, the final evaluation result is exemplarily multiplied by 3 and the'cost' It can be calculated by adding the result of multiplying the standard evaluation result by 7. That is, if this is applied to FIG. 4, NO. 1 is 620 (90 × 3 + 50 × 7 = 620), NO. 2 is 570 (85 × 3 + 45 × 7 = 570), NO. 3 is 722 (75 × 3 + 71 × 7 = 722), NO. 4 is 712 (88 × 3 + 64 × 7 = 712), NO. 5 is 684 (74×3+66×7=684), NO. 6 is 801 (92×3+75×7=801), NO. 7 can be calculated as 791 (56×3+89×7=791). As a result, NO. 6, NO. 7, NO. 3, NO. 4, NO. 5, NO. 1, NO. 2 are arranged in order, NO. The specification information corresponding to 6 may be extracted and determined as customized optimal specification information optimized by applying the quality reference weight 3 and the cost reference weight 7. The extracted and determined quality standard optimal specification information may be stored in a database as a data set for learning. According to this, the model building unit (not shown) can train the artificial neural network by inputting fluid information and piping information and outputting the customized optimal specification information.

The providing unit 400 may provide piping design information. Here, the piping design information means piping design information optimized for each piping generated by the utility system piping design unit 300. As described above, the piping design information may be piping design information optimized on a quality basis, piping design information optimized on a cost basis, or piping design information optimized by applying a predetermined weight to quality and cost.

For example, the providing unit 400 may provide piping design information through a display provided in the intelligent utility system piping design apparatus 10 according to an embodiment of the present disclosure. As another example, the providing unit 400 may provide piping design information by transmitting it to an external user terminal or an external server. In this case, the intelligent utility system piping design apparatus 10 according to an embodiment of the present application may communicate with an external user terminal or an external server through a network.

The intelligent utility system piping design apparatus 10 according to an embodiment of the present application provides piping design information (pipe specification information) optimized as a criterion that users consider important among quality and cost, which are important aspects in piping design of a utility system. By providing or by setting appropriate weights for quality and cost, and providing optimized piping design information based on the set weights, customized piping design information can be provided for the client or each case of the request.

Meanwhile, in the present application, the optimization criteria for piping design information have been described centering on quality and cost, but it may be extended and applied to various criteria required by users in the future.

Hereinafter, based on the details described above, the operation flow of the present application will be briefly described.

5 is a flowchart illustrating an intelligent utility system piping design method according to an embodiment of the present application.

The intelligent utility system piping design method illustrated in FIG. 5 may be performed by the intelligent utility system piping design apparatus 10 described above. Therefore, even if omitted below, the description of the intelligent utility system piping design apparatus 10 may be equally applied to the description of the intelligent utility system piping design method.

Referring to FIG. 5, a method for designing a piping for an intelligent utility system according to an embodiment of the present disclosure may include receiving request information (S510).

In step S510, the input unit 100 may receive request information including factory information, equipment information, and process information.

In addition, in step S510, the input unit 100 may receive optimization criterion (quality or cost) information from the user. Alternatively, the input unit 100 may receive weight (weight for quality and cost) information for each optimization criterion from a user.

Further, referring to FIG. 5, a method for designing an intelligent utility system piping according to an exemplary embodiment of the present disclosure may include designing a utility system (S520).

In step S520, the utility system design unit 200 may determine a factory layout and process flow based on at least one of factory information, equipment information, and process information, and design a utility system based on the factory layout and process flow.

Also, in step S520, the utility system design unit 200 may determine a capacity for each utility of the utility system. In addition, in step S520, the utility system design unit 200 may determine the type, specification, and number of utility supply equipment based on the capacity for each utility. In addition, in step S520, the utility system design unit 200 may determine the arrangement of the utility supply equipment and the utility flow supplied from the utility supply equipment to the process.

In addition, referring to FIG. 5, the intelligent utility system piping design method according to an embodiment of the present application may include generating piping design information (S530).

In step S530, the utility system piping design unit 300 may define piping to correspond to a utility flow for the utility system. In addition, in step S530, the utility system piping design unit 300 may generate piping design information optimized for each piping.

In addition, in step S530, the utility system piping design unit 300 uses the fluid information including the type and characteristics of the fluid flowing along the piping and the piping information including the arrangement state and design conditions of the piping, It is possible to generate the included piping design information.

In addition, in step S530, the utility system piping design unit 300 inputs fluid information and piping information, and includes optimum specification information for each piping based on a pre-learned artificial neural network that outputs piping optimum specification information. Piping design information can be generated.

As an example, the optimum specification information may be quality reference optimum specification information. In this case, the artificial neural network may be learned in advance by receiving fluid information and piping information as inputs, but outputting optimum specification information based on piping quality. As another example, the optimum specification information may be cost-based optimum specification information. In this case, the artificial neural network may be learned in advance by inputting fluid information and piping information, but outputting optimum specification information based on the cost of piping. As another example, the optimum specification information may be customized optimum specification information evaluated by applying a predetermined weight to quality and cost. In this case, the artificial neural network may be learned in advance by inputting fluid information and piping information, but outputting customized optimal specification information of piping.

In addition, the intelligent utility system piping design method according to an embodiment of the present application may include providing piping design information (S540).

In step S540, the providing unit 400 may provide piping design information.

In the above description, steps S510 to S540 may be further divided into additional steps or combined into fewer steps, according to an embodiment of the present disclosure. In addition, some steps may be omitted as necessary, and the order between steps may be changed.

The intelligent utility system piping design method according to various embodiments of the present disclosure may be implemented in the form of a program command that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like alone or in combination. The program instructions recorded in the medium may be specially designed and configured for the present application, or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. -A hardware device specially configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of the program instructions include not only machine language codes such as those produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The above-described hardware device may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa.

In addition, the above-described intelligent utility system piping design method may be implemented in the form of a computer program or application executed by a computer stored in a recording medium.

The foregoing description of the present application is for illustrative purposes only, and those of ordinary skill in the art to which the present application pertains will be able to understand that it is possible to easily transform it into other specific forms without changing the technical spirit or essential features of the present application. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as being distributed may also be implemented in a combined form.

The scope of the present application is indicated by the claims to be described later rather than the detailed description, and all changes or modified forms 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 application.

10: intelligent utility system piping design device
100: input
200: Utility System Design Department
300: Utility system piping design department
400: provision

Claims (15)

As an intelligent utility system piping design device,
Request information including factory information, equipment information, and process information, and the first weight, which is a weight based on quality, and a second weight, which is a weight based on cost, is input through the interface for inputting user-set values for each weight by optimization criteria. Input unit;
Stores the code assignment result for the item corresponding to the detailed information of each of the factory information, the equipment information, and the detailed information associated with the existing factory designed or designed through simulation, and the specification information of the pipe linked to the existing factory And a database for storing the quality evaluation result and the cost evaluation result as a data set for learning;
A utility system design unit determining a factory layout and a process flow based on at least one of the factory information, the equipment information, and the process information included in the request information, and designing a utility system based on the factory layout and process flow;
A utility system piping design unit defining piping to correspond to the utility flow by the utility system and generating piping design information optimized for each piping; And
A providing unit that provides the interface and the piping design information,
Including,
The utility system design unit,
A target code is assigned to an item corresponding to each detailed information of the factory information, the equipment information, and the process information included in the request information, and the similarity between the target code and the code assignment result stored in the database is the highest. The factory layout is determined by referring to the layout of the existing factory determined to be,
The process flow for the entire process is processed in a manner in which the process execution equipment to which the code corresponding to the target code is assigned for each detailed process of the process information included in the request information is matched according to the order of the detailed process. To determine,
The arrangement of utility supply equipment and the utility flow from the utility supply equipment to the process execution equipment are determined based on the factory layout and the process flow, but the sum of the distances between the utility supply equipment and the process execution equipment is minimum Characterized in that the utility supply device is arranged to be,
The utility system piping design unit,
For each pipe specification information including materials and specifications within the range of available pipe specifications extracted based on fluid information including the type and characteristics of the fluid flowing along the pipe, and pipe information including the arrangement state and design conditions of the pipe Generating the pipe design information including customized specification information for each pipe using a pre-learned artificial neural network that outputs the first evaluation result of the quality standard and the second evaluation result of the cost standard,
The artificial neural network is a supervised learning-based algorithm of any one of a Random Forest algorithm, a support vector machine (SVM) algorithm, an Extra Tree algorithm, and an XG Boost algorithm that are pre-trained based on the training dataset,
The above customized specification information,
Within the range of the available pipe specifications based on a ranking between a value obtained by multiplying the first evaluation result of each of the pipe specification information with the first weight value and a value obtained by multiplying the second evaluation result by the second weight value. It is determined, intelligent utility system piping design device. delete delete delete delete delete delete As an intelligent utility system piping design method by an intelligent utility system piping design device,
(a) The input unit provides a first weight and cost, which are quality reference weights, through an interface for inputting user-set values for each user-set value for each optimization criterion provided by the provider and request information including factory information, equipment information, and process information. Receiving a second weight that is a reference weight;
(b) the utility system design unit, determining a factory layout and process flow based on at least one of the factory information, the equipment information, and the process information, and designing a utility system based on the factory layout and process flow;
(c) the utility system piping design unit, defining piping to correspond to the utility flow by the utility system, and generating piping design information optimized for each piping; And
(d) the providing unit, providing the pipe design information,
Including,
Before step (b),
Storing a code assignment result for an item corresponding to the detailed information of each of the factory information, the equipment information, and the process information associated with an existing factory previously designed or designed through simulation in a database,
Including more,
The step (b),
(b1) assigning a target code to an item corresponding to detailed information of each of the factory information, the equipment information, and the process information included in the request information;
(b2) determining the factory layout by referring to the layout of an existing factory determined to have the highest similarity between the target code and the code assignment result stored in the database; And
(b3) The process flow for the entire process by matching the process performance equipment to which the code corresponding to the target code assigned for each detailed process of the process information included in the request information is assigned according to the order of the detailed process Determining in consideration of a process order; And
(b4) determining an arrangement of utility supply equipment and a utility flow from the utility supply equipment based on the factory layout and the process flow,
Including,
In the step (b4), the utility supply device is arranged so that the sum of the distances between the utility supply equipment and the process performing equipment is minimized,
In the step (c), the utility system piping design unit,
For each pipe specification information including materials and specifications within the range of available pipe specifications extracted based on fluid information including the type and characteristics of the fluid flowing along the pipe, and pipe information including the arrangement state and design conditions of the pipe Generating the pipe design information including customized specification information for each pipe using a pre-learned artificial neural network that outputs the first evaluation result of the quality standard and the second evaluation result of the cost standard,
Before step (c),
Storing the specification information, quality evaluation results, and cost evaluation results of pipes linked to the existing factory as a learning dataset in the database,
Including more,
The artificial neural network is a supervised learning-based algorithm of any one of a Random Forest algorithm, a support vector machine (SVM) algorithm, an Extra Tree algorithm, and an XG Boost algorithm that are pre-trained based on the training dataset,
The above customized specification information,
Within the range of the available pipe specifications based on a ranking between a value obtained by multiplying the first evaluation result of each of the pipe specification information with the first weight value and a value obtained by multiplying the second evaluation result by the second weight value. It is determined, intelligent utility system piping design method. delete delete delete delete delete delete A computer-readable recording medium on which a program for executing the method of claim 8 is recorded.

Images