KR102411824B1 - Factory energy management system based on artifical intelligence and method thereof - Google Patents

Abstract

The present invention relates to a factory energy management system and method therefor. This factory energy management system receives data necessary for control from the smart sensing unit that collects data related to the manufacturing site at the manufacturing site based on the smart sensor, the smart sensing unit, and according to the set control parameters and operating conditions, the manufacturing site Based on the pattern learned through machine learning using the smart control unit that controls the operation of the air conditioning system of When it is determined that control change is necessary, an integrated server for generating new control parameters and driving conditions for driving control of the air conditioning system is included, wherein the smart control unit reflects the new parameters and driving conditions and adjusted control parameters and driving conditions It is possible to control the operation of the air conditioning system according to the According to the present invention, efficiency of production energy management is possible through intelligent situational awareness-based factory energy optimization management.

Description

Factory energy management system based on artificial intelligence and method thereof

The present invention relates to a factory energy management system and method, and more particularly, to a factory energy management system and method capable of optimized operation of factory energy management through intelligent situational awareness-based energy management.

In general, the factory energy management system (factory energy management system) is a system that supports energy consumption optimization activities, and the distribution is spreading centering on the Energy Service Company (ESCO) of the Korea Energy Agency.

However, the factory energy management system requires high infrastructure construction and operation costs due to various optimization targets and frequently changing site characteristics, and the effect of investment is very low with a simple monitoring solution alone, so most small and medium-sized factories are hesitant to introduce it.

On the other hand, a clean room, which must maintain high cleanliness, constant temperature, and constant humidity throughout the year, is an essential element in high-tech industrial sites that require precision such as the semiconductor industry. It is also used in small high-tech industries, not factories. In addition to industrial clean rooms, it is also used in sterility and harmful bacteria laboratories and in the medical field for special treatment to prevent infection.

However, in the case of the electronics industry, it is reported that 40% of the total power is consumed for the operation of the clean room, and it is reported that heating, cooling and air conditioning and air supply and exhaust account for 50% of the power consumption.

Therefore, it is necessary to consider a method that can dramatically reduce infrastructure construction and operating costs while maximizing the return on investment by applying a new technology to the factory energy management system required for clean room operation.

Accordingly, it is an object of the present invention to provide a factory energy management system and method capable of maximizing investment return while reducing infrastructure construction and operating costs through intelligent situational awareness-based energy management.

The factory energy management system according to the present invention for achieving the above object is a smart sensor-based manufacturing site, a smart sensing unit that collects data related to the manufacturing site, receives data required for control from the smart sensing unit, and sets According to control parameters and driving conditions, a smart control unit that controls the operation of the air conditioning system at the manufacturing site, and data obtained by measuring and analyzing data transmitted from the smart sensing unit in real time, and FBD (Fish Bone Diagram) data An integrated server for generating new control parameters and driving conditions for driving control of the air conditioning system based on a pattern learned through machine learning using, wherein the smart control unit adjusts by reflecting the new parameters and driving conditions The operation of the air conditioning system may be controlled according to the set control parameters and driving conditions.

In addition, by using computational fluid dynamics, it may further include a simulation unit for predicting and diagnosing flow characteristics for each control situation at the manufacturing site and providing it to the integrated server.

In addition, the factory energy management method according to the present invention for achieving the above object includes the steps of installing a smart sensing unit and a smart control unit at a manufacturing site, and collecting data related to the manufacturing site based on a smart sensor in the smart sensing unit. Step, in the smart control unit, receiving data necessary for control from the smart sensing unit, and controlling the operation of the air conditioning system of the manufacturing site according to set control parameters and driving conditions, the smart sensing unit and the smart In the integrated server communicatively connected to the control unit, based on the data obtained by measuring and analyzing the data transmitted from the smart sensing unit in real time and the pattern learned through machine learning using FBD (Fish Bone Diagram) data, the air conditioning Generating new control parameters and driving conditions for driving control of the system, and in the smart controller, controlling the driving of the air conditioning system according to the control parameters and driving conditions adjusted by reflecting the new control parameters and driving conditions includes steps.

And, in order to achieve the above object, in the present invention, it is possible to provide a processor-readable recording medium recording a program for executing the factory energy management method in the processor.

According to the present invention, through intelligent situational awareness-based factory energy optimization management, not only can the efficiency of production energy management be improved, but also quality advancement can be achieved based on the introduction of an advanced smart production system and a clean environment. In addition, by continuously monitoring the factory environment in real time, it is possible to quickly identify and take action on the cause of abnormalities, and it is also possible to secure immediate response to problems occurring throughout the site through dynamic monitoring. And, since the factory energy management system according to the present invention can be operated by installing additional equipment and programs to the previously installed system, infrastructure construction and operating costs can be reduced.

1 to 3 are diagrams showing the configuration of an energy factory management system according to an embodiment of the present invention;
4 is a block diagram of the smart gateway in FIG. 3;
Figure 5 is a block diagram of the integrated server in Figure 1, and
6 is a flowchart provided to explain the operation process of the factory management system according to an embodiment of the present invention.

In this specification, when a certain element is referred to as being “connected” or “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in between. It should be understood that there may be Other expressions describing the relationship between elements, such as "between" or "neighboring", etc., and expressions such as that one element "transmits" a signal to another element, should be interpreted similarly.

Hereinafter, the present invention will be described in more detail with reference to the drawings.

1 to 3 are diagrams showing the configuration of a factory energy management system according to an embodiment of the present invention.

Referring to FIG. 1 , the factory energy management system 100 may include a smart sensing unit 150 , a smart control unit 200 , a simulation unit 250 , and an integrated server 300 .

The energy management system 100 having such a configuration may control the air conditioning system 400 for controlling air conditioning such as a clean room or other factory energy-related devices.

As shown in FIG. 2 , the smart sensing unit 150 may include sensor adapters 160a to 160n and smart sensors 170a to 170n, etc., and is installed in a manufacturing site such as a clean room, manufacturing status Various data related to it can be collected. For example, the smart sensor unit 150 may collect environmental data such as temperature, humidity, dust, and Volatile Organic Composite (VOC), device-related data, process-related data, and the like.

The sensor adapters 160a to 160n may collect various types of monitoring data through wired/wireless communication from sensors previously installed at the manufacturing site.

Smart sensors (170a ~ 170n) are intelligent sensors that combine nanotechnology or MEMS technology with general sensor technology that detects physical and chemical information of a measurement object to provide signals for data processing, automatic correction, self-diagnosis, decision making, communication Processing functions can be built-in.

As shown in FIG. 3 , the smart control unit 200 may include smart gateways 200a to 200n, etc., and receives data required for control from the smart sensor unit 150 , and in the integrated server 300 . According to the provided control parameters and driving conditions, the air conditioning system 400 or other plant energy-related devices may be controlled. In this case, the smart control unit 200 may divide the manufacturing site into several sub-regions, and use each smart gateway 200a to 200n, etc. to control each sub-region with different driving conditions.

The simulation unit 250 predicts and diagnoses flow characteristics for each control situation at the manufacturing site by using computer fluid dynamics, etc. based on data transmitted from the smart sensing unit 150 or virtual sensor data. A simulation result may be calculated and provided to the integration server 300 . In addition, the simulation unit 250 may simulate effects on production schedule changes, facility replacement improvement activities, etc., and may also perform simulations on energy consumption fluctuations.

The integrated server 300 may generate optimized control parameters and driving conditions for energy operation based on a change in a manufacturing site situation and machine learning using fish bone diagram (FBD) data created by field experts or the like. That is, the integrated server 300 can measure and analyze the data transmitted from the smart sensing unit 150 in real time, and based on the measured and analyzed data and intelligent situational awareness and FBD machine learning for the manufacturing site, air conditioning New parameters and driving conditions for optimal driving control of the system 400 may be created, and various information for optimizing other plant energy operations may be provided.

The new parameters and driving conditions generated by the integrated server 300 are transmitted to the smart control unit 200, and the smart control unit 200 controls the air conditioning system 400 according to the control parameters and driving conditions adjusted to the new parameters and driving conditions. can control the operation of

The integrated server 300 also provides a dynamic monitoring function for the manufacturing site, and measures and analyzes data transmitted from the smart sensing unit 150, and related information that enables immediate response according to a specific situation change. It also provides a user-centered UI environment including experts, so that the user can inquire the information accumulated in the integrated server 300 . The integrated server 300 utilizes modeling through FBD machine learning and simulation results provided through the simulation unit 250 to provide information necessary for unit facility analysis or process energy efficiency analysis for various manufacturing sites, etc. It is also possible to provide quality defect prediction information, facility abnormal occurrence prediction information, facility life prediction information, and on-site abnormal occurrence prediction information.

In addition, the integrated server 300 may analyze the data collected through the smart sensing unit 150, monitor the energy use status, and provide various analysis information necessary for decision making for energy optimization. Examples of such analysis information include information for introducing an ESS (Energy Storage System) optimal for facility standards, and information on whether or not to introduce LEDs for office and field lighting. In addition, the integrated server 300 collects and analyzes advanced cases, design of energy use outline (Energy Profile) information, energy management performance analysis, and design of maintenance required information. It can provide information necessary for the design of major monitoring-related functions.

The integrated server 300 may be connected to a cloud system through a communication network, through which it may be connected to an ERP (Enterprise Resource Planning), MES (Manufacturing Execution System), SCADA (Supervisory Control And Data Acquisition) system, etc., and multiple units It is also possible to connect a plurality of integrated servers 300 each disposed in a factory or a partner company. In addition, by such a configuration, unit factories or subcontractors may be managed integrally by the parent company.

The factory energy management system 100 having such a configuration enables constant multivariate energy monitoring and analysis, and for energy problems that cannot be solved by an approach that targets individual process variables independently, based on big data As a result, it is possible to provide a machiner-based energy diagnosis and prediction system that considers multiple variables together.

In addition, the factory energy management system 100 enables remote monitoring of the manufacturing site and access to various devices, so that a variety of people, from maintenance technicians to control technicians and factory managers, can easily access diagnostic information. . In addition, the factory energy management system 100 can provide a pre-diagnosis function through the analysis of information related to the manufacturing status, and it is possible to analyze inefficient energy equipment and improve the existing energy equipment, through which it is possible to produce to realize operational optimization.

Factory energy management system 100, by convergence of production technology and energy management technology, can prepare a basis for facility control and application of new and renewable energy technology, and is an energy-saving type that combines energy management technology with a manufacturing process Production process system technology can be applied, and energy use is actively managed, and through documented planning and control, it is possible to build an infrastructure to improve energy intensity related to production. In addition, the factory energy management system 100 can support manufacturers to recognize energy resources as essential means for securing strategic competitive advantage, effectively monitor energy resources within the factory, and utilize the results in energy management policies. have.

4 is a block diagram of the smart gateway in FIG. 3 .

Referring to FIG. 4 , the smart gateway 210 includes a mobile communication unit 211 , a wireless communication unit 213 , a GPS unit 215 , a memory 217 , a display unit 219 , an interface unit 221 , and a sensor connection unit ( 223 ), a context awareness module 225 , a power supply unit 227 , and a control unit 229 . When these components are implemented in actual applications, two or more components may be combined into one component, or one component may be subdivided into two or more components as needed.

The mobile communication unit 211 may transmit and receive wireless signals to and from a base station, a user terminal, and a server in a mobile communication network. Here, the wireless signal may include a voice call signal, a video call call signal, or various types of data according to text/multimedia message transmission/reception. The wireless communication unit 213 provides a function for wireless Internet access or other wireless communication. The GPS unit 215 receives location information from a plurality of GPS satellites.,

The memory 217 may store a program for processing and control of the controller 229 and may perform a function for temporarily storing input or output data. The display unit 219 displays information or a screen processed or analyzed by the smart gateway 210 .

The interface unit 221 performs an interface role with all external devices connected to the smart gateway 210 . The sensor connection unit 223 serves as an interface through which various sensors or measurement devices are connected.

The context-aware module 225 provides a context-aware messenger function capable of providing a messenger function to the integrated server 300 or a preset person in charge when it is determined that it is necessary by recognizing the situation at the manufacturing site. Context-aware messenger ensures interoperability of heterogeneous devices, provides the same service on heterogeneous operating systems, supports data-based facility predictive diagnosis, and enables the establishment of a collaborative system for intuitive situational awareness.

The power supply unit 227 may supply power required to each component under the control of the control unit 229 and externally apply power. The power supply 227 may include an energy storage system (ESS) for maintaining the power factor, and may include a lithium ion battery (LIB) and a battery monitoring system (BMS) module to overcome the limitations of a general UPS. .

The control unit 229 controls the overall operation of the smart gateway 210 by generally controlling the operation of each unit.

With such a configuration, the smart gateway 210 may measure and analyze data related to the manufacturing status transmitted from the smart sensing unit 150 in real time, and may control the air conditioning system 400 and the like.

The smart gateway 210 is a dynamic networking function based on recognition and judgment according to location and situation, a serial communication function of a traditional method, a TCP/IP and Fieldbus data communication support function, ZigBee, RFID, Bluetooth and W for wireless communication with peripheral devices. -Lan support function, input/output device interface support function of additional sensors and existing control devices, and logic configuration function for data format conversion/processing can be provided.

In addition, the smart gateway 210 may measure the effective values and power factor of the voltage and current of the three-phase (RST) and the power factor through a sensor or a measuring device connected through the sensor connection unit 223, and in addition to power quality, frequency, It can measure active power, reactive power, harmonics, etc. and detect disconnection. In addition, the smart gateway 210 interworks with the ESS (Energy Storage System) to maintain the power factor, control the peak value, and monitor the power quality and amount of power to perform plant power maintenance and power quality stabilization functions, and the ESS's BMS (Battery Monitoring System) ), PCS (Power Conversion System) status diagnosis function, etc. may be performed. The smart gateway 210 may be developed in the form of an open API in order to minimize costs when newly introduced.

The smart gateway 210 may be made portable so that practitioners in the field can carry it. Using such a mobile smart gateway, engineers in the field can easily perform maintenance work such as changes and additions, and some people in charge of each site, such as knowledge of facilities for each process and knowledge of linking facilities and operating systems, It is possible to build an environment in which the knowledge possessed by the company can be shared and exchanged for development, and it can be applied to the development of an inference engine for common production, facility, and quality concepts, and to solve the problem of quality of finished products that arise from abnormalities in the semi-finished product production environment. It makes it possible to develop and apply One Touch UI-based App for the Ubiquitous environment.

5 is a block diagram of the integrated server in FIG. 1 .

Referring to FIG. 5 , the integrated server 300 includes an environment change detection unit 310 , a pollution source detection unit 320 , a situation awareness inference unit 330 , a smart monitoring unit 340 , and an integrated management unit 350 . ) may be included. When these components are implemented in actual applications, two or more components may be combined into one component, or one component may be subdivided into two or more components as needed.

The environmental change detection unit 310 secures an effective range value of data by accumulating measurement data of the same location and time with respect to the data transmitted from the smart sensing unit 150, and performs multiple observations under the same conditions to determine the effective range value. It improves precision, and it is possible to detect changes in the environment at the manufacturing site depending on whether the measured data falls within or out of the effective range.

The pollution source detection unit 320 extracts the worker's work pattern and clustering from the power quality data and IP camera data, and detects the pollution source at the manufacturing site.

The situation awareness inference unit 330 infers the situation of the manufacturing site based on a pattern learned through machine learning using FBD data on the result detected by the environment transformation detection unit 310 and the pollution source detection unit 320 . do.

FBD, or fishbone diagram, is a data analysis tool, named because it looks like a fish bone. FDM is used to identify causes and effects, to identify problems in the early stages of a process, and to analyze predictions and results.

In addition, machine learning or machine learning is a field of artificial intelligence, which can be said to be a series of processes that try to find an appropriate answer to a new input based on the trained knowledge by training the learning data prepared in advance on the computer. have. At this time, when the training data for training the computer is given both a question (training input) and a correct answer (training output), it is said to be labeled.

The FBD machine learning process may consist of generating cause-and-effect data to be used as learning data based on the received FBD data, and identifying patterns through machine learning using the cause-and-effect data.

The smart monitoring unit 340 provides a real-time monitoring function for the manufacturing site, and can establish a method for detecting, correcting, and removing errors of the collected data, thereby deriving an integrated management model through processing and fusion of various unstructured data. make it possible

The integrated management unit 350 may generate new control parameters and driving conditions when it is determined that a control change is necessary based on situational awareness and machine learning for the manufacturing site inferred by the situational awareness inference unit 330 . In addition, the integrated management unit 350 searches for multiple types of energy data through machine learning in an environment such as a clean room, and through this, it is possible to provide similarity of energy use patterns, cost prediction, and information related to energy consumption based on multiple types of energy. have.

6 is a flowchart provided to explain the operation process of the factory management system according to an embodiment of the present invention.

Referring to FIG. 6 , based on a smart sensor in the smart sensing unit 150 installed at a manufacturing site such as a clean room, environmental data such as temperature, humidity, dust, and Volatile Organic Composite (VOC), device-related data, and process-related data Collects data related to the manufacturing site, such as (S500).

The smart control unit 200 controls the air conditioning system 400 according to the set control parameters and driving conditions with reference to data required for control among the data collected by the smart sensing unit 150 (S510).

The integration server 300 determines whether a situation requiring a control change is recognized (S520). The situation in which control change is necessary is when it is determined that control change is necessary based on the situation recognition in which environmental changes or pollution are inferred at the manufacturing site and the pattern learned through machine learning using FBD (Fish Bone Diagram) data. , a case in which it is determined that a control change is necessary based on the monitored value of the control result, a case in which it is determined that a control change is necessary as a result of the simulation performed by the simulation unit 250 .

When the integrated server 300 recognizes a situation requiring a control change ( S520 ), it creates new control parameters and driving conditions for energy optimization ( S530 ).

The generated new control parameters and driving conditions are transmitted to the smart control unit 200, and the smart control unit 200 controls the operation of the air conditioning system by adjusting the new control parameters and driving conditions (S540).

Through this process, the air conditioning system and the like can be controlled according to the AI-based energy operation optimization algorithm.

On the other hand, the factory energy management system and method according to the present invention can not be applied limitedly to the configuration of the described embodiments as described above, but the above embodiments are all or all of the embodiments so that various modifications can be made. Some of them may be selectively combined and configured.

In addition, the present invention can be implemented as a computer program on a programmable computer. Such a computer may include a processor, a storage device, an input device, and an output device. In order to implement the contents described in the present invention, the program code may be input with a mouse or keyboard input device. These programs can be implemented in a high-level language or an object-oriented language. It can also be implemented as a computer system implemented in assembly or machine code.

In addition, the content of the present invention is not limited to the use of hardware or software, and is applicable to any other computing or processing environment. It may be implemented by hardware, software, or a combination of hardware and software described in the present invention. The present invention can be implemented using circuits. That is, it may be implemented as one or more programmable logic circuits, that is, an application specific integrated circuit (ASIC) or logic circuits (AND, OR NAND gates) or a processing device (eg, a microprocessor, a controller).

In addition, although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention belongs without departing from the gist of the present invention as claimed in the claims Various modifications may be made by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

150: smart sensing unit 200: smart control unit
250: simulation unit 300: integrated server

Claims (10)

a smart sensing unit that collects data related to the manufacturing site at the manufacturing site based on the smart sensor;
a smart control unit receiving data necessary for control from the smart sensing unit, and controlling the operation of the air conditioning system of the manufacturing site according to set control parameters and driving conditions; and
Based on the data obtained by measuring and analyzing the data transmitted from the smart sensing unit in real time and the pattern learned through machine learning using FBD (Fish Bone Diagram) data, a new control parameter for driving control of the air conditioning system and create driving conditions,
an integrated server that extracts the facility operation status of the manufacturing site from the electric power quality data of the manufacturing site, extracts the worker's work pattern and cluster degree from the image information of the manufacturing site, and detects the cause of pollution in the manufacturing site; includes,
The smart control unit, factory energy management system, characterized in that for controlling the driving of the air conditioning system according to the control parameters and driving conditions adjusted by reflecting the new control parameters and driving conditions. According to claim 1,
Factory energy management system further comprising a simulation unit for predicting and diagnosing flow characteristics for each control situation of the manufacturing site by using computational fluid dynamics and providing it to the integrated server. According to claim 1,
The integrated server, the factory energy management system, characterized in that it further provides a function of monitoring the environmental conditions for the manufacturing site in real time. delete According to claim 1,
The smart control unit,
1st to nth smart gateways for measuring and analyzing data transmitted from the smart sensing unit in real time,
The smart gateway is installed in a predetermined production line or equipment unit of the manufacturing site, recognizes the situation of the manufacturing site based on the measured and analyzed data, and when it is determined that there is situation information to be notified, the integration Factory energy management system, characterized in that for transmitting the situation information to a server and a preset terminal. Installing a smart sensing unit and a smart control unit at the manufacturing site;
collecting data related to the manufacturing site based on a smart sensor in the smart sensing unit;
receiving, in the smart control unit, data necessary for control from the smart sensing unit, and controlling the operation of the air conditioning system of the manufacturing site according to set control parameters and driving conditions;
In the integrated server communicatively connected to the smart sensing unit and the smart control unit, data obtained by measuring and analyzing data transmitted from the smart sensing unit in real time and FBD (Fish Bone Diagram) data learned through machine learning Based on the pattern, new control parameters and driving conditions for driving control of the air conditioning system are generated, the facility operation status of the manufacturing site is extracted from the power quality data of the manufacturing site, and the operator from the image information of the manufacturing site detecting a cause of pollution in the manufacturing site by extracting the work pattern and clustering of and
and controlling, in the smart control unit, the driving of the air conditioning system according to the adjusted control parameters and driving conditions by reflecting the new control parameters and driving conditions. 7. The method of claim 6,
Factory energy management method further comprising the step of providing a simulation unit, predicting and diagnosing flow characteristics for each control situation of the manufacturing site by using computational fluid dynamics in the simulation unit, and providing it to the integrated server. 7. The method of claim 6,
Factory energy management method further comprising the step of monitoring, in the integrated server, environmental conditions for the manufacturing site in real time. 7. The method of claim 6,
Factory energy management method further comprising the step of recognizing the situation of the manufacturing site in the smart control unit, and providing a messenger function to the integrated server and a preset person in charge. A processor-readable recording medium recording a program for executing the factory energy management method of any one of claims 6 to 9 in the processor.

Images