KR20220045538A - Composite energy sensor based on artificial intelligence - Google Patents

Abstract

The present invention relates to a composite energy sensor. More specifically, the present invention supports decision-making by understanding a situation related to energy use ahead through a complex energy sensor, and provides a level of sensor precision which can replace expensive sensors through the combination of low-cost sensor data. The composite energy sensor includes: a composite sensor unit configured to integrate a single sensor pre-installed in a building and a composite sensor which is in a form of artificial intelligence (AI); a learning environment unit configured to lighten a learning engine for providing an online learning function depending on integration of the single sensor and the composite sensor; and a learning inference unit configured to infer state information on energy use using the lightened learning engine.

Description

COMPOSITE ENERGY SENSOR BASED ON ARTIFICIAL INTELLIGENCE

The present invention relates to an artificial intelligence-based complex energy sensor, and more particularly, to a sensor technology for more efficient energy management and optimal operation in an EMS environment.

In general, sensors and sensor-related technologies are utilized in most industries through the stages of a chip, a package, a unit, and a system. The sensor industry includes a material industry for manufacturing sensors, a device industry in which unique functions are implemented using materials, and a sub- and system-type industry assembled using multiple devices. Here, the sensor is a key element that diversifies and modernizes the functions of most set products, and is used as a core part in most industries and plays an important role in enhancing the competitiveness of each industry. It is suitable for nurturing a global specialized company because material technology, design technology, process technology, etc. are different depending on the application field due to multi-variety and small-volume production.

Sensors are core components of electronic devices and automobiles, and are a technology-intensive industry with a large front-to-back linkage effect. As a key item that leads the paradigm change of the 4th industrial revolution, the Trillion Age is expected in 10 years or so. Support.

Despite the optimistic market outlook due to the quantitative increase of the sensor industry, domestic demanding companies mainly procure sensor demand from overseas companies due to the reliability of domestic products and performance problems of advanced sensors. Domestic companies are sandwiched between countries with advanced technologies such as the US, Germany, and Japan and China, which has price competitiveness, due to lack of technology for advanced sensors and weak price competitiveness of general sensors. About 90% of domestic demand is imported and used from overseas, and domestic sensor companies avoid innovation such as small scale and lack of technology, creating a vicious cycle.

Among sensor products, smartphone image sensor (domestic self-sufficiency rate of about 50%), chemical sensor measuring gas and water quality (5-10%), and optical sensor (5-10%) for diagnosing building safety using optical fiber Except for , the remaining sensors (pressure, inertia, magnetism, image, and radar) are almost entirely dependent on imports. Even when developing new products, it is difficult to enter the market due to the lack of a basis for reliability evaluation and lack of marketing capabilities. . The level of domestic sensor technology is low, and in particular, the level of advanced sensor technology is still insufficient.

Accordingly, domestic sensor technology development focuses on developing sensors used in smart home/home appliances, smart factories, smart cities, smart logistics, etc., or production unrelated to energy, IoT devices/products, environment, and security. It is possible to preoccupy domestic related technologies and lead the market by developing an artificial intelligence complex energy sensor system for the purpose of energy reduction specialized for EMS. Domestic sensor companies need to focus on sensor technology that can sustainably grow to the level of importing, packaging, and hatching sensor chips due to lack of technology.

It is necessary to secure global market competitiveness and lead the four seasons sensor market by developing an artificial intelligence complex energy sensor that can recognize additional situations by combining different types of sensor data, moving away from sensor miniaturization technology.

The present invention provides an artificial intelligence-based complex energy sensor technology that combines sensor data measured from heterogeneous or multiple types of sensors to construct big data information for energy reduction of an EMS (Energy Management System).

The present invention generates state information on energy use by combining sensor data, predicts an energy consumption influence factor and an optimal environmental factor that affect energy use according to the state information, and provides the predicted result to the energy management system.

The present invention provides artificial intelligence sensing information that can be directly utilized in a complex sensor system-based application by combining sensor data and performing data learning through big data and artificial intelligence analysis.

A complex energy sensor according to an embodiment of the present invention includes a complex sensor unit that integrates a single sensor and an artificial intelligence complex sensor pre-installed in a building; a learning environment unit to lighten the learning engine for providing an online learning function according to the integration of the single sensor and the complex sensor; and a learning inference unit for inferring state information regarding energy use using the lightweight learning engine.

The complex sensor unit according to an embodiment of the present invention may integrate sensor data collected from a single sensor already installed in the building and sensor data provided by the complex sensor to be used as basic information for a complex sensor function.

The complex sensor unit according to an embodiment of the present invention may integrate a complex sensor that shares at least one sensor data collected from the single sensor through a network.

The complex sensor unit according to an embodiment of the present invention may integrate a complex sensor that provides sensor precision by applying artificial intelligence learning inference to the sensor data collected from the single sensor.

The complex sensor unit according to an embodiment of the present invention may integrate a complex sensor that provides new sensing information through artificial intelligence learning inference using sensor data collected from the single sensor.

The complex sensor unit according to an embodiment of the present invention may integrate a complex sensor that provides necessary information required for energy management in conjunction with a wearable device or an Internet of Things device.

The learning inference unit according to an embodiment of the present invention may detect an influence factor affecting energy use according to the learning engine, and may provide information about each situation according to the sensed influence factor.

An artificial intelligence complex energy sensor system according to an embodiment of the present invention includes a single sensor for collecting sensor data related to energy consumption from a building; and a complex energy sensor device that provides sensing information required for energy management based on artificial intelligence technology by combining the single sensor and the complex sensor.

The complex energy sensor device according to an embodiment of the present invention may perform a physical or logical combination between the sensor data collected from the single sensor and the sensor data provided from the complex sensor.

The complex energy sensor device according to an embodiment of the present invention can reduce the weight of a learning engine for providing an online learning function according to the integrated sensor data of the single sensor and the sensor data of the complex sensor.

The complex energy sensor device according to an embodiment of the present invention may detect an influencing factor affecting energy use according to the learning engine by inferring state information on energy use using the lightweight learning engine.

The complex energy sensor device according to an embodiment of the present invention may include a complex sensor that shares at least one sensor data collected from the single sensor through a network.

The complex energy sensor device according to an embodiment of the present invention may include a complex sensor that provides sensor precision by applying artificial intelligence learning inference to sensor data collected from the single sensor.

The complex energy sensor device according to an embodiment of the present invention may include a complex sensor that provides new sensing information through artificial intelligence learning inference using sensor data collected from the single sensor.

The composite energy sensor device according to an embodiment of the present invention may include a composite sensor that provides necessary information required for energy management in conjunction with a wearable device or an Internet of Things device.

According to an embodiment of the present invention, the complex energy sensor copes with expensive sensors through combination of low-cost sensor data, or indirect and virtual sensing of points that are difficult to sense in harsh environments (high temperature, high pressure, vibration, space narrow, etc.) By providing a physical sensor replacement and cost reduction effect can be obtained.

According to an embodiment of the present invention, the complex energy sensor can provide real-time data monitoring, analysis, and danger alarm service so that sensor data abnormal/control malfunction can be quickly determined and processed, so that safety-related data through convergence sensor data is possible. Through collection and analysis, it may be possible to prevent safety accidents.

According to an embodiment of the present invention, the composite energy sensor may provide a technology for constructing big data information for energy reduction of EMS by combining sensor data measured from heterogeneous or multiple types of sensors.

According to an embodiment of the present invention, the composite energy sensor combines sensor data and generates state information on energy use to predict energy consumption influencing factors and optimal environmental factors affecting energy use according to state information. can provide

According to an embodiment of the present invention, the complex energy sensor provides artificial intelligence sensing information that can be directly utilized in a complex sensor system-based application by combining sensor data and performing data learning through big data and artificial intelligence analysis. can

1 is a technical conceptual diagram of an artificial intelligence-based complex energy sensor according to an embodiment of the present invention.
2 is a view defining a technology of a three-level complex energy sensor according to a technology shape according to an embodiment of the present invention.
3 is a diagram illustrating five service types operating at a sensor level among three levels of a complex energy sensor according to an embodiment of the present invention.
4A and 4B are diagrams illustrating technical components related to an artificial intelligence-based complex energy sensor according to an embodiment of the present invention.

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

1 is a technical conceptual diagram of an artificial intelligence-based complex energy sensor according to an embodiment of the present invention.

Referring to FIG. 1 , the artificial intelligence-based complex energy sensor may perform logical combination or physical combination on single sensors installed in a building and sensor data monitored by the single sensors. The complex energy sensor can provide supplementary sensor information for energy management and optimal operation of buildings by performing artificial intelligence-based data learning based on single sensors and sensor data that have been logically combined or physically combined. . In addition, the composite energy sensor predicts an energy consumption influence factor and an optimal environmental factor required for energy management of a building, thereby reducing the energy use of the building, and it is possible to determine and process a malfunction of the sensor in advance.

As an example, the artificial intelligence-based complex energy sensor according to xEMS combines sensor combination and artificial intelligence learning and reasoning functions in the energy consumption and operation field of xEMS to detect and provide information on factors affecting energy consumption and energy management. It may be an artificial intelligent complex sensor device that enhances.

Here, xEMS collects various types of energy in the entire process of energy production, supply, and consumption to enable efficient management of energy or cost, and is a management target according to EMS, but separate names according to scope and purpose are integrated. It can be a system. For example, the xEMS is a system collectively called for each management technology such as a Factory Energy Management System (FEMS), a Building Energy Management System (BEMS), and a Home Energy Management System (HEMS) according to an energy consumption area.

The present invention defines an artificial intelligence-based complex energy sensor and proposes a technique for combining the complex energy sensor to be applicable according to the management technology of xEMS.

More specifically, the composite energy sensor may be a sensor for the purpose of energy reduction by specializing in xEMS. The complex energy sensor supports decision-making by understanding the situation in the front of energy use through the complex energy sensor, rather than the simple energy usage specific of the existing EMS, and provides a level of sensor precision that can replace expensive sensors through the combination of low-cost sensor data. can provide

To this end, in the present invention, the composite energy sensor can be classified into three layers by combining the combination of the single sensors already installed in the building and the data learning inference function of artificial intelligence. Hereinafter, the three classified layers may be defined as ① complex sensor layer, ② energy device layer, and ③ server layer.

① Composite sensor layer

The complex sensor layer may be a layer that integrates single sensors already installed in a building and sensor data collected from single sensors. In addition, the complex sensor layer may be a layer that integrates sensors that provide artificial intelligence-based services as well as a single sensor. The artificial near-near-based service may be the service type of FIG. 3 .

② Energy device layer

The energy device layer may be a layer that provides an online learning function that can be performed not only in a high-spec computing device but also in a low-spec computing device in consideration of the type and specification of a computing device performing the learning engine. In other words, the energy device layer can provide a low-cost AI learning environment that lightens the learning engine to enable AI learning even on low-spec computing devices.

③ Server layer

The server layer may be a layer that utilizes a learning engine to perform learning and inference about a situation related to energy use forward.

The complex energy sensor can generate new state information through the combination of sensor data measured by various single sensors according to each classified layer, recognize the situation by itself, and generate big data information for energy reduction of EMS.

At this time, the complex energy sensor detects the factors affecting energy use, not the simple energy usage-oriented data required in the energy management system, and generates information at a level that can recognize each situation according to the detected influence factors. can provide

As an example, when the complex energy sensor is used as an occupancy sensor used in BEMS, the complex energy sensor provides not only the presence or absence of users in the building, but also the number of occupants in each space in the building and the state of each user. After making the judgment, the result can be provided. In other words, the complex energy sensor can combine sensor data monitored from a single sensor already installed in a building, and perform AI-based data analysis and learning. The complex energy sensor can recognize each situation related to occupancy and provide it as information by predicting factors affecting energy consumption and optimal environmental factors through artificial intelligence-based data analysis and learning.

In addition, the complex energy sensor may detect factors affecting energy use, rather than simple energy usage-oriented data required in an energy management system, and provide a level of situational awareness. In other words, the complex energy sensor can provide an artificial intelligence convergence technology that is presented at the level required by the application through sensor combination and data learning in order to solve the information extraction limit where the level of the existing single sensor is different.

The complex energy sensor analyzes the level of sensor precision and is low-cost compared to commercial sensors and capable of sensing within the tolerance range. In the case of applications requiring real-time, it is a sensor suitable for the specification of the application to quickly calculate/analyze/process at the edge level. data can be provided.

After all, the complex energy sensor proposed in the present invention can derive new information through the combination of heterogeneous or homogeneous sensors, and enable energy-efficient energy management through big data and AI analysis. In addition, the complex energy sensor can derive artificial intelligence sensing information that can recognize various information or situations based on the complex sensor system compared to the existing sensor system that measures only one value.

2 is a view defining a technology of a three-level complex energy sensor according to a technology shape according to an embodiment of the present invention.

Referring to FIG. 2 , the composite energy sensor may be classified into three levels according to a technology shape utilized in the three layers corresponding to the three layers described in FIG. 1 . Hereinafter, the three levels classified may be defined as ① sensor level, ② H/W product level, and ③ SW product level.

① Sensor level

The sensor level may be a level indicating a service type operating as a complex energy sensor. Here, the service type can be divided into ⓐ multi-functional integration type, ⓑ function fusion type, ⓒ AI inference information-correction type, ⓓ AI convergence virtual sensor type, and ⓔ non-intrusive type. A detailed description thereof will be described with reference to FIG. 3 .

② Hardware (HW: Hardware) product level

The hardware product level may be a level at which a complex sensor hardware device for utilizing a complex energy sensor, an edge computing device for a complex sensor, and the like are derived.

③ Software (SW: Software) product level

The software product level may be a level at which artificial intelligence learning/inference technology operated at the server level and artificial intelligence inference algorithm executed on the complex sensor are derived. In addition, at the software product level, lightweight artificial intelligence learning/inference technology and complex sensor composition service can be derived.

3 is a diagram illustrating five service types operating at a sensor level among three levels of a complex energy sensor according to an embodiment of the present invention.

Referring to FIG. 3, the complex energy sensor is a service type that is divided into ⓐ multi-functional integrated type, ⓑ function fusion type, ⓒ AI inference information-correction type, ⓓ AI convergence virtual sensor type, ⓔ non-intrusive type. can mean Each service type can be defined as follows.

ⓐ Multifunctional integration model is a concept of integration between single sensors and can be defined as a service type in which multiple sensors share processor and network functions to provide efficiency.

ⓑ Function fusion type can be defined as a service type that creates fixed new information through combination of multiple sensor information and artificial intelligence fusion.

ⓒ AI inference information-correction type can be defined as a service type that reinforces the existing imperfect sensor information by adding other information or fusion of artificial intelligence.

ⓓ AI convergence virtual sensor type can be defined as a service type related to a software complex sensor that creates new information by using multiple sensor information.

ⓔ The non-intrusive type can be defined as a service type that creates necessary information by linking wearables or IoT devices without installing a separate new sensor. New information can be generated by using signal information from non-intrusive wearables and IoT devices.

In the complex energy sensor including these five service types, the sensing information inference algorithm learned by machine learning may be executed in the complex sensor itself. In addition, the complex energy sensor may be provided with an online artificial intelligence learning function in conjunction with an edge device or a server.

Furthermore, the complex energy sensor is a user composition service that provides the above-described five services, and may induce a user to directly create sensor information.

In addition, each of the above-described sensors may be defined as shown in Table 1 below.

Sensor classification characteristic single sensor - A sensor that provides simple single information
- Used as a base technology for complex sensor functions
- Example: temperature, humidity, CO2, illuminance, fine dust, gas, wind speed/direction, dust, etc. robes
union
sesen
librarian Multi-function integrated shaping complex sensor - A complex sensor in which multiple sensor signals share a single MCU and network function
- Improved processor and network resource efficiency
- Example: Composite sensor composed of sensors such as temperature, humidity, CO2, illuminance, fine dust, gas, wind speed/direction, occupancy, etc. sharing one MCU artificial intelligence function fusion
complex - A complex sensor that provides single information by fusion of single or multiple physical signals and artificial intelligence functions
- Example: People counter + infrared sensor + occupancy information sensor of artificial intelligence fusion AI inference-based information correction type - A complex sensor that adds other sensor information to the existing sensor information and improves the accuracy, reliability/stability of the existing sensor information by fusing artificial intelligence learning reasoning
- Example: Composite sensor that provides flow information inference type with artificial intelligence of flow sensor + pressure sensor AI fusion virtual sensor type (SW sensor) - A complex sensor that provides new information through artificial intelligence learning inference by fusion of single or multiple sensor information
- Example: virtual sensor, software sensor, rotating machine status/lifetime prediction and maintenance complex sensor, etc. Non-Intrusive Composite Sensor Type - A complex sensor that provides new information in connection with wearable devices such as smartphones and smart watches and IoT devices
- Example: Composite sensor that provides situational awareness information using smartphone sensor information

4A and 4B are diagrams illustrating technical components related to an artificial intelligence-based complex energy sensor according to an embodiment of the present invention.

Referring to FIG. 4 , the artificial intelligence-based complex energy sensor can be stratified into five layers: ① single sensor, ② complex sensor, ③ artificial intelligence edge, ④ artificial intelligence sensor platform, and ⑤ service layer, depending on the technology components. Here, the composite sensor, AI edge, and AI sensor platform may be collectively referred to as a composite energy sensor layer. The composite energy sensor may be defined as shown in Table 1 below.

The sensor device technology performed in the single sensor and the complex sensor secures installation convenience and reliability in harsh environments, and may include hardware technology for single device function improvement and complex sensor.

Artificial intelligence technology performed in the complex energy sensor layer may include edge computing and artificial intelligence learning inference technology in the server. In addition, the artificial intelligence complex sensor management platform may include a sensor management function, firmware, and upgrade technology of an artificial intelligence execution algorithm. In the artificial intelligence learning platform, a customized learning engine is developed according to the driving environment and sensor characteristics of the artificial intelligence complex sensor, and a complex sensor execution algorithm package is created through artificial intelligence learning based on collected data. In addition, the AI learning platform provides an online learning function using the collected data. The edge computing complex sensor and lightweight learning engine do not use server-grade computing power, and enable a low-cost AI learning environment that makes the learning engine lightweight so that AI learning can be performed even on low-spec edge computing devices.

Meanwhile, the method according to the present invention is written as a program that can be executed on a computer and can be implemented in various recording media such as magnetic storage media, optical reading media, and digital storage media.

Implementations of the various techniques described herein may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or combinations thereof. Implementations may be implemented for processing by, or controlling the operation of, a data processing device, eg, a programmable processor, computer, or number of computers, a computer program product, ie an information carrier, eg, a machine readable storage It may be embodied as a computer program tangibly embodied in an apparatus (computer readable medium) or a radio signal. A computer program, such as the computer program(s) described above, may be written in any form of programming language, including compiled or interpreted languages, as a stand-alone program or in parts, components, subroutines, or computing environments. It can be deployed in any form, including as other units suitable for use in A computer program may be deployed to be processed on one computer or multiple computers at one site or distributed across multiple sites and interconnected by a communications network.

Processors suitable for processing a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer. In general, a processor will receive instructions and data from either read-only memory or random access memory or both. Elements of a computer may include at least one processor that executes instructions and one or more memory devices that store instructions and data. In general, a computer may include, receive data from, transmit data to, or both, one or more mass storage devices for storing data, for example magnetic, magneto-optical disks, or optical disks. may be combined to become Information carriers suitable for embodying computer program instructions and data are, for example, semiconductor memory devices, for example, magnetic media such as hard disks, floppy disks and magnetic tapes, Compact Disk Read Only Memory (CD-ROM). ), optical recording media such as DVD (Digital Video Disk), magneto-optical media such as optical disk, ROM (Read Only Memory), RAM (RAM) , Random Access Memory), flash memory, EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), and the like. Processors and memories may be supplemented by, or included in, special purpose logic circuitry.

In addition, the computer-readable medium may be any available medium that can be accessed by a computer, and may include both computer storage media and transmission media.

While this specification contains numerous specific implementation details, they should not be construed as limitations on the scope of any invention or claim, but rather as descriptions of features that may be specific to particular embodiments of particular inventions. should be understood Certain features that are described herein in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments, either individually or in any suitable subcombination. Furthermore, although features operate in a particular combination and may be initially depicted as claimed as such, one or more features from a claimed combination may in some cases be excluded from the combination, the claimed combination being a sub-combination. or a variant of a sub-combination.

Likewise, although acts are depicted in the drawings in a particular order, it should not be construed that all acts shown must be performed or that such acts must be performed in the specific order or sequential order shown to obtain desirable results. In certain cases, multitasking and parallel processing may be advantageous. Further, the separation of the various device components of the above-described embodiments should not be construed as requiring such separation in all embodiments, and the program components and devices described may generally be integrated together into a single software product or packaged into multiple software products. You have to understand that you can.

On the other hand, the embodiments of the present invention disclosed in the present specification and drawings are merely presented as specific examples to aid understanding, and are not intended to limit the scope of the present invention. It will be apparent to those of ordinary skill in the art to which the present invention pertains that other modifications based on the technical spirit of the present invention can be implemented in addition to the embodiments disclosed herein.

Claims (15)

a complex sensor unit that integrates a single sensor already installed in a building and a complex sensor in the form of artificial intelligence;
a learning environment unit to lighten the learning engine for providing an online learning function according to the integration of the single sensor and the complex sensor; and
a learning inference unit for inferring state information about energy use using the lightweight learning engine;
A complex energy sensor comprising a. According to claim 1,
The complex sensor unit
A complex energy sensor that integrates sensor data collected from a single sensor installed in the building and sensor data provided by the complex sensor to be used as basic information for a complex sensor function. According to claim 1,
The complex sensor unit,
A complex energy sensor that integrates a complex sensor that shares at least one sensor data collected from the single sensor through a network. According to claim 1,
The complex sensor unit,
A complex energy sensor incorporating a complex sensor that provides sensor precision by applying artificial intelligence learning inference to sensor data collected from the single sensor. According to claim 1,
The complex sensor unit,
A complex energy sensor that integrates a complex sensor that provides new sensing information through artificial intelligence learning inference using sensor data collected from the single sensor. According to claim 1,
The complex sensor unit,
A complex energy sensor that integrates a complex sensor that provides necessary information for energy management in conjunction with a wearable device or an Internet of Things device. According to claim 1,
The learning inference unit,
A complex energy sensor that detects an influence factor affecting energy use according to the learning engine, and provides information about each situation according to the detected influence factor. a single sensor that collects sensor data related to energy consumption from a building; and
a complex energy sensor device combining the single sensor and the complex sensor to provide sensing information required for energy management based on artificial intelligence technology;
Artificial intelligence complex energy sensor system comprising a. 9. The method of claim 8,
The complex energy sensor device,
An artificial intelligence complex energy sensor system that performs a physical or logical combination between the sensor data collected from the single sensor and the sensor data provided by the complex sensor. 10. The method of claim 9,
The complex energy sensor device,
An artificial intelligence complex energy sensor system that lightens a learning engine for providing an online learning function according to the sensor data of the integrated single sensor and the sensor data of the complex sensor. 11. The method of claim 10,
The complex energy sensor device,
An artificial intelligence complex energy sensor system that detects an influencing factor affecting energy use according to the learning engine by inferring state information about energy use using the lightweight learning engine. 9. The method of claim 8,
The complex energy sensor device,
An artificial intelligence complex energy sensor system comprising a complex sensor that shares at least one sensor data collected from the single sensor through a network. 9. The method of claim 8,
The complex energy sensor device,
An artificial intelligence complex energy sensor system comprising a complex sensor that provides sensor precision by applying artificial intelligence learning inference to sensor data collected from the single sensor. 9. The method of claim 8,
The complex energy sensor device,
An artificial intelligence complex energy sensor system comprising a complex sensor that provides new sensing information through artificial intelligence learning inference using the sensor data collected from the single sensor. 9. The method of claim 8,
The complex energy sensor device,
An artificial intelligence complex energy sensor system including a wearable device or a complex sensor that provides necessary information for energy management in conjunction with an Internet of Things device.

Images