KR102618658B1 - Switchboard system and method using energy harvesting - Google Patents

Abstract

The switchboard system and method using energy harvesting according to the embodiment detects energy sources around the switchboard, collects surrounding energy, and supplies power generated through harvesting to the switchboard. In the embodiment, environmental information is collected, and the harvesting rate of each energy source including sunlight, vibration, heat, and kinetic energy is calculated based on the environmental information analysis results. Afterwards, the harvesting device connected to each energy source is controlled according to the calculated harvesting ratio to collect surrounding energy. Additionally, in the embodiment, harvesting efficiency is improved by optimizing the operation of the energy harvesting system and the switchgear system through a deep learning model. For example, it dynamically adjusts the amount of energy collected or consumed according to changes in the surrounding environment, or determines efficient timing between energy collection and use.

Description

Switchboard system and method using energy harvesting {SWITCHBOARD SYSTEM AND METHOD USING ENERGY HARVESTING}

The present disclosure relates to a switchboard system and method, and more specifically, to a system and method for improving the energy efficiency of a switchgear through energy harvesting that collects ambient energy.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and is not admitted to be prior art by inclusion in this section.

Energy harvesting is a technology that collects energy from small energy sources in the surrounding environment and converts it into electrical energy. Energy harvesting collects energy such as vibration, heat, sunlight, and wind power generated in the surroundings and uses it to drive electrical devices or systems. Energy harvesting can be applied to devices that operate independently without relying on traditional battery replacement or external power supply. It is mainly used in low-power consumption devices such as small electronic devices, sensor networks, and portable electronic devices. Small electronic devices operate at low power and can utilize energy harvesting to solve the difficulties of battery replacement or power supply.

Meanwhile, a switchgear is a system that manages the storage and distribution of electrical energy and is mainly used in power systems or electrical networks, and is designed for stable supply of electrical energy and efficient energy management. Switchboards store energy and distribute it to various devices or systems. In addition, the switchgear monitors the flow and usage of energy and detects charging or discharging status for efficient energy management. Additionally, it performs control and adjustment functions to minimize energy loss and maintain system stability.

Since the switchboard must be continuously supplied with power for energy storage and management, the switchboard often receives power from an energy harvesting system. However, in the past, the amount of energy collected from the surroundings through energy harvesting is small, and the amount of energy collected from the surroundings is limited or conversion efficiency is low, making it difficult to supply sufficient power to the switchgear. Additionally, when using energy harvesting, the switchboard supplies power using energy sources in the surrounding environment, and the availability of energy sources varies greatly. In particular, renewable energy such as solar or wind power fluctuates greatly depending on weather conditions, making energy supply unstable.

Additionally, there is a limit to the storage capacity of conventional energy harvesting systems, and it may be difficult to secure sufficient energy storage capacity. In particular, devices with high power consumption or long-term energy needs may require additional energy storage or auxiliary power sources. Additionally, switchboards perform best under specific operating conditions, and environmental factors such as temperature, humidity, and vibration can affect the operation of switchboards. Therefore, if the switchboard operates under non-optimal conditions, energy harvesting and power supply efficiency may be difficult.

In addition, the conventional switchboard has a problem in that it cannot diagnose abnormal situations by distinguishing between cases where temperature and vibration are correlated and cases where there is no correlation. Conventionally, when learning a model for managing and diagnosing switchboards, a problem occurs in which the judgment reliability of the artificial neural network model is lowered because the deep learning model is learned using temperature and vibration data sets from a point in time when there is no correlation between temperature and vibration.

1. US Patent Registration No. 11563328 (2023.01.24) 2. US Patent Registration No. 11552458 (2023.01.10) 3. US Patent Registration No. 11608174 (2023.03.21) 4. US Patent Registration No. 10862277 (2020.12.08) 5. US Patent Registration No. 11209499 (2021.12.28) 6. Korean Patent Registration No. 10-2485079 (2023.01.02)

The switchboard system and method using energy harvesting according to the embodiment detects energy sources around the switchboard, collects surrounding energy, and supplies power generated through harvesting to the switchboard.

In the embodiment, environmental information is collected, and the harvesting rate of each energy source including sunlight, vibration, heat, and kinetic energy is calculated based on the environmental information analysis results. Afterwards, the harvesting device connected to each energy source is controlled according to the calculated harvesting ratio to collect surrounding energy.

Additionally, in the embodiment, harvesting efficiency is improved by optimizing the operation of the energy harvesting system and the switchgear system through a deep learning model. For example, it dynamically adjusts the amount of energy collected or consumed according to changes in the surrounding environment, or determines efficient timing between energy collection and use.

Additionally, in the embodiment, electrical energy leaking from the switchboard is collected and used for energy harvesting.

In addition, in the embodiment, energy is collected through a nano power generation device that extracts energy from the surrounding environment using various characteristics of materials and can be used to operate the switchgear.

Additionally, in the embodiment, the power usage pattern of the switchgear is analyzed, the power usage is predicted, and the energy harvesting rate is adjusted according to the predicted power usage.

Additionally, in the embodiment, the energy harvesting time and energy storage capacity are adjusted according to the remaining power amount of the switchgear power supply source and the predicted power use amount.

A switchgear system using energy harvesting according to an embodiment includes a harvesting device that generates energy from each energy source; Sensors that sense environmental information; A switchboard receiving power from a harvesting device; Includes.

In an embodiment a switchboard; A calculation unit that analyzes environmental information collected from sensors to predict the power generation efficiency of each energy source and calculates the harvesting ratio of each energy source based on the prediction results; An energy collection unit that controls the harvesting device connected to each energy source according to the calculated harvesting ratio and collects energy from the harvesting device; A supply unit that converts the collected energy into electric power and supplies the converted electric power to the switchboard; A switchgear system using energy harvesting, comprising:

The switchgear system using energy harvesting as described above improves the independence of switchboard power supply by utilizing environmentally friendly and sustainable energy sources.

In addition, the embodiment creates effects such as extending the life of the switchboard battery, reducing maintenance costs, and reducing power consumption. In addition, through the embodiment, energy harvesting efficiency can be improved and power use efficiency of the switchgear can be improved.

The effects of the present invention are not limited to the effects described above, and should be understood to include all effects that can be inferred from the configuration of the invention described in the detailed description or claims of the present invention.

Figure 1 is a diagram showing the configuration of a switchgear system using energy harvesting according to an embodiment
Figure 2 is a diagram showing the data processing configuration of the switchgear according to an embodiment
Figure 3 is a diagram showing the data processing configuration of the management server according to an embodiment
Figure 4 is a diagram showing the data processing configuration of a manager terminal according to an embodiment
Figure 5 is an example of visualizing data analysis results
Figure 6 is an output screen to an administrator terminal according to an embodiment
Figure 7 is a diagram showing a nano-power generation device according to an embodiment.
Figure 8 is a signal flow diagram of a switchgear system using energy harvesting according to an embodiment
Figure 9 is a diagram showing a data processing process for acquiring power of a switchgear according to an embodiment
Figure 10 is a diagram showing the energy collection process according to an embodiment

Hereinafter, embodiments disclosed in the present specification will be described in detail with reference to the attached drawings, but identical or similar components will be assigned the same reference numbers regardless of the reference numerals, and duplicate descriptions thereof will be omitted. The suffixes “module” and “part” for components used in the following description are given or used interchangeably only for the ease of preparing the specification, and do not have distinct meanings or roles in themselves. Additionally, in describing the embodiments disclosed in this specification, if it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed in this specification, the detailed descriptions will be omitted. In addition, the attached drawings are only for easy understanding of the embodiments disclosed in this specification, and the technical idea disclosed in this specification is not limited by the attached drawings, and all changes included in the spirit and technical scope of the present invention are not limited. , should be understood to include equivalents or substitutes.

Terms containing ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another.

When a component is said to be "connected" or "connected" to another component, it is understood that it may be directly connected to or connected to the other component, but that other components may exist in between. It should be. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

In this application, terms such as “comprise” or “have” are intended to designate the presence of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, but are not intended to indicate the presence of one or more other features. It should be understood that this does not exclude in advance the possibility of the existence or addition of elements, numbers, steps, operations, components, parts, or combinations thereof.

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware.

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

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

Figure 1 is a diagram showing the configuration of a switchgear system using energy harvesting according to an embodiment.

Referring to FIG. 1, the switchboard system using energy harvesting according to the embodiment includes a harvesting device 100, a sensor 200, a switchgear 300, a management server 400, and an administrator terminal 500. It can be. The harvesting device 100 generates energy from each energy source. In an embodiment, the harvesting device 100 may include, but is not limited to, a nano-power generation device, a solar panel, a wind power generation device, a heat conversion device, a kinetic energy collection device, and a leakage energy collection device.

The nanopower generation device according to the embodiment is a device that extracts energy from the surrounding environment and may include a piezoelectric element made of piezo material that collects vibration or pressure energy. Nano power generation devices are devices that generate power on a small scale using nano technology. The nanopower generation device shown in Figure 7 performs energy harvesting (energy collection) or energy conversion using the characteristics of nanomaterials, and mainly generates small power by utilizing energy captured from the surrounding environment. For example, solar nano power generation devices absorb solar energy and convert it into electrical energy, and nano vibration power generation devices collect vibration energy and convert it into electrical energy.

Among the harvesting devices according to the embodiment, the solar panel collects solar energy, and the wind power generation device collects wind energy. The heat conversion device collects heat energy, and the kinetic energy collection device collects kinetic energy. The leakage energy collection device collects leakage power from the switchboard and allows it to be used as power at the switchboard.

In an embodiment, the leakage energy collection device may collect leakage power of the switchboard through wireless power transfer, electromagnetic field harvesting, and thermal energy harvesting methods. The wireless power reception method according to the embodiment is a method of collecting leakage energy in the process of transmitting and receiving power from a leakage energy collection device. In an embodiment, the leakage energy collection device wirelessly transmits power using a wireless power transmission and reception device, and the receiving side of the wireless power transmission and reception device collects the transmitted power. Electromagnetic field harvesting is a method of collecting energy using electromagnetic fields existing in the surroundings. A leakage energy harvesting device collects electromagnetic fields generated from power lines and wireless communication equipment existing in switchboards and converts them into energy. In addition, the leakage energy collection device collects heat using temperature differences through the thermal energy harvesting method, and can collect leakage energy from the switchgear using a thermoelectric conversion device that converts heat into electrical energy. .

The sensor 200 senses environmental information including temperature, illumination, and humidity. In an embodiment, the sensor 200 generates integrated data that includes temperature and vibration data in one set. For example, the sensor 200 may generate integrated data, which is a data group that groups temperature and vibration data into a set. To this end, the generator 130, the temperature sensing unit 110 and the vibration sensing unit 120 simultaneously collect temperature and vibration data and sample the collected temperature and vibration data. Thereafter, the generator 130 sets the temperature and vibration data to the same time standard, records the temperature and vibration values at each data point together, and integrates the temperature and vibration data as related information. In the embodiment, integrated data is generated from the sensor 200, the correlation between temperature and vibration data is identified, and the integrated data is used as learning data for a deep learning model in addition to individual data for temperature and vibration to manage the distribution panel. It allows to improve the reliability of deep learning models, including models, power usage models, and fault diagnosis models.

The switchboard 300 receives power from the harvesting device 100.

The management server 400 accumulates and collects data generated from the switchgear 300, the harvesting device 100, and the sensor 200 and turns it into big data, and the switchboard 300, the harvesting device 100, and the sensor 200 Monitors and determines abnormal status of each device.

The manager terminal 500 receives and outputs data visualizing the monitoring results and monitoring data of the switchboard 300, the harvesting device 100, and the sensor 200 from the management server 400, and outputs the data visualizing the monitoring data of the switchboard 300, the harvesting device 100, and the sensor 200. When an abnormal condition is detected in at least one of the device 100 and the sensor 200, abnormal condition information is output.

The switchboard system and method using energy harvesting according to the embodiment detects energy sources around the switchboard, collects surrounding energy, and supplies power generated through harvesting to the switchboard.

In the embodiment, environmental information is collected, and the harvesting rate of each energy source including sunlight, vibration, heat, and kinetic energy is calculated based on the environmental information analysis results. Afterwards, the harvesting device connected to each energy source is controlled according to the calculated harvesting ratio to collect surrounding energy.

Additionally, in the embodiment, harvesting efficiency is improved by optimizing the operation of the energy harvesting system and the switchgear system through a deep learning model. For example, it dynamically adjusts the amount of energy collected or consumed according to changes in the surrounding environment, or determines efficient timing between energy collection and use.

Additionally, in the embodiment, electrical energy leaking from the switchboard is collected and used for energy harvesting.

In addition, in the embodiment, energy is collected through a nano power generation device that extracts energy from the surrounding environment using various characteristics of materials and can be used to operate the switchgear.

Additionally, in the embodiment, the power usage pattern of the switchgear is analyzed, the power usage is predicted, and the energy harvesting rate is adjusted according to the predicted power usage.

Additionally, in the embodiment, the energy harvesting time and energy storage capacity are adjusted according to the remaining power amount of the switchgear power supply source and the predicted power use amount.

Figure 2 is a diagram showing the data processing configuration of a switchgear according to an embodiment.

Referring to FIG. 2, the switchgear 300 according to the embodiment includes a collection unit 310, a preprocessing unit 320, a deep learning unit 330, a calculation unit 340, an energy collection unit 350, and a supply unit 360. ), an analysis unit 370, and a management unit 380. The term 'part' used in this specification should be interpreted to include software, hardware, or a combination thereof, depending on the context in which the term is used. For example, software may be machine language, firmware, embedded code, and application software. As another example, hardware may be a circuit, processor, computer, integrated circuit, integrated circuit core, sensor, Micro-Electro-Mechanical System (MEMS), passive device, or a combination thereof.

The collection unit 310 collects environmental information, power usage information of the switchboard, and learning data of the deep learning model. In the embodiment, the collection unit 310 collects environmental information including temperature, illuminance, and humidity from sensors. In an embodiment, the power usage information of the switchboard may include hourly power usage and power distribution. In an embodiment, the deep learning model includes a switchgear management model and a power usage prediction model. In an embodiment, the learning data of the switchboard management model may include information related to the management and operation of the power system and power network of the switchboard, such as power usage history data and power efficiency data of the switchboard. In an embodiment, the learning data of the power usage prediction model may include power usage history data, holidays, events, weather information, etc.

The preprocessing unit 320 preprocesses the collected learning data to remove data with bias or discrimination among the collected artificial intelligence learning data. In the embodiment, the preprocessor 320 preprocesses the collected data and processes it into a form suitable for learning an artificial intelligence model. For example, the preprocessor 320 may perform processes such as noise removal, outlier removal, and missing value processing. In addition, the preprocessor 120 can prevent the model from learning unnecessary patterns by normalizing the data, removing outliers, or adjusting the scale of the data through data preprocessing.

The deep learning unit 330 trains a deep learning neural network with learning data to implement a deep learning model including a switchgear management model, a fault diagnosis model, and a power usage prediction model. In the embodiment, the switchboard management model is a deep learning model that calculates the time of energy collection and distribution and the amount of energy collection and distribution for efficient operation and management of power supplied to the switchgear. In the embodiment, the power use prediction model is a deep learning model that calculates the predicted amount of power use of the switchboard by time based on the power usage history of the switchboard.

In the embodiment, the deep learning unit 330 learns a switchgear management model by distinguishing between data for which correlation is recognized and data for which correlation is not recognized in the collected temperature and vibration data set. To this end, when the deep learning unit 330 collects a temperature and vibration data set, it does not immediately use it as learning data, but extracts a temperature and vibration correlation data set. In the embodiment, the temperature and vibration correlation data set is data in which the correlation between temperature and vibration is identified. In the embodiment, the deep learning unit 330 first extracts the temperature and vibration correlation data at a preset first time (e.g., Accumulate temperature and vibration data sets for 1 hour). Afterwards, the deep learning unit 330 extracts a temperature and vibration correlation data set, which is a data set with a correlation between temperature and vibration, from the accumulated temperature and vibration data set. At this time, the deep learning unit 330 calculates the correlation between temperature and vibration as a data set in which the temperature change rate is greater than the temperature change rate reference value and the vibration change rate is greater than the vibration change rate reference value during the preset second time period (e.g., 10 minutes). It is recognized as a temperature and vibration correlation data set. In the embodiment, the second time is shorter than the first time.

However, since a correlation between the temperature and vibration of the switchgear may occur due to long-term aging, the deep learning unit 330 in the embodiment uses the starting point of the data of the temperature and vibration correlation data set to minimize leaked data. Data sets from before the preset time are recognized as quasi-correlated data sets. In the embodiment, quasi-correlated data refers to unstructured data that is not structured and does not follow certain patterns or rules.

In addition, the deep learning unit 330 can utilize the temperature and vibration correlation data set and the quasi-correlation data set as temperature and vibration data sets for learning a deep learning model including a switchgear management model. Through this, the deep learning unit 330 learns both structured data, which is a temperature and vibration correlation data set, and unstructured data, which is a quasi-correlated data set, and can significantly improve the reliability and accuracy of deep learning models, including the switchgear management model. there is. In addition, in the collected temperature and vibration data sets, the validity of the data can be strengthened and the performance of the model can be improved by learning a fault diagnosis model by distinguishing in advance between data with recognized correlation and data without recognized correlation. .

In addition, the deep learning unit 330 can continuously learn a deep learning model using data sets determined to be temperature and vibration correlation data sets and quasi-correlation data sets.

In an embodiment, the deep learning neural network includes, but is not limited to, at least one of a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and a Bidirectional Recurrent Deep Neural Network (BRDNN).

In the embodiment, the deep learning unit 330 evaluates the learned artificial neural network model and deep learning model. In an embodiment, the deep learning unit 330 may evaluate an artificial neural network model through at least one of accuracy, precision, and recall. Accuracy is an indicator that measures how well the results predicted by an artificial neural network model match the actual results. Precision is an indicator that measures the proportion of results predicted to be positive that are actually positive. Recall rate is an indicator that measures the proportion of actual positives predicted by the model as positive. In an embodiment, the deep learning unit 330 may calculate the accuracy, precision, and recall rate of the artificial neural network model, and evaluate the artificial neural network model based on at least one of the calculated indicators.

Additionally, in the embodiment, the deep learning unit 330 may measure the accuracy of the artificial neural network model using an evaluation dataset. The evaluation dataset consists of data that the model did not use for learning, and is used to objectively evaluate the model's performance. In an embodiment, the feedback unit 160 executes an artificial neural network model using an evaluation dataset and compares the predicted value of the artificial neural network model for each input data with the actual correct answer value of the data. Afterwards, through the comparison results, you can measure how accurately the model predicts. For example, in the feedback unit 160, accuracy may be calculated as the ratio of data correctly predicted by the model among all data.

In addition, the deep learning unit 330 calculates the F1 score, which is an indicator of the balance between precision and recall, which is an indicator calculated as the harmonic average of precision and recall, and creates an artificial neural network model based on the calculated F1 score. You can evaluate and generate an AUC-ROC curve, which is an indicator that visualizes the performance of the classification model in a graph, and evaluate the artificial neural network model based on the generated AUC-ROC curve. In an embodiment, the deep learning unit 330 may evaluate the model's performance as better as the area under the ROC curve (AUC) is closer to 1.

The calculation unit 340 analyzes environmental information from sensors to predict the power generation efficiency of each energy source, and calculates the harvesting ratio for each energy source based on the prediction result. In the embodiment, the calculation unit 340 collects environmental information through a sensor. Environmental information may include elements such as sunlight, temperature, wind speed, humidity, etc. Afterwards, the calculation unit 340 predicts the power generation efficiency of each energy source, such as solar power and wind power, based on the collected environmental information. In an embodiment, the calculation unit 340 may predict the power generation efficiency of each energy source through a power generation efficiency prediction model. For example, when the calculation unit 340 inputs environmental information into power generation efficiency, it can obtain the power generation efficiency of each energy source expected as an output of the power generation efficiency prediction model. Specifically, when the amount of sunlight is above a certain level and the wind speed is below a certain level, the power generation efficiency prediction model predicts the harvesting efficiency through solar power to be higher than the harvesting efficiency through wind power generation devices. In addition, when the amount of sunlight is below a certain level and the wind speed exceeds the standard value, the power generation efficiency of the wind power generator is predicted to be higher than the power generation efficiency through solar power.

Thereafter, the calculation unit 340 calculates the harvesting ratio for each energy source based on the predicted power generation efficiency. The harvesting rate is the proportion of power that the energy source supplies to the entire system. In an embodiment, the calculation unit 340 may calculate the harvesting ratio of each energy source by dividing the expected power generation efficiency by the total expected power generation amount. Afterwards, the calculation unit 340 evaluates the harvesting ratio calculation result and adjusts the harvesting ratio of each energy source according to the evaluation result. This is a process to balance energy sources and meet the power demand of the switchgear. In the embodiment, the calculation unit 340 adjusts the harvesting rate of each energy source if the predicted harvesting rate of each energy source is unbalanced with the power demand. Set the optimal distribution ratio through .

In the embodiment, the calculation unit 340 repeats the rate adjustment process to analyze environmental information in real time, predict power generation efficiency, and calculate the harvesting rate of the energy source. This allows energy to be collected and utilized efficiently.

The energy collection unit 350 controls the harvesting device connected to each energy source according to the calculated harvesting ratio and collects energy to be supplied to the switchgear. For example, the energy collection unit 350 controls the harvesting device of each energy source based on the calculated harvesting ratio. Specifically, the energy collection unit 350 determines whether to operate each harvesting device and the operation time according to the harvesting ratio. For example, in the case of a solar energy source with a high harvesting rate, solar panels and inverters can be activated, and in the case of a wind energy source with a low harvesting rate, the wind generator operation time can be reduced from the standard time.

Thereafter, the energy collection unit 350 collects energy from a plurality of harvesting devices and converts the collected energy into electrical energy. In the case of a solar energy source in an embodiment, a solar panel absorbs sunlight to generate direct current electricity, and an inverter converts direct current to alternating current. In the case of wind energy sources, wind generators use wind power to rotate and convert the rotational motion into electrical energy. Thereafter, the energy collection unit 350 manages to combine the electrical energy generated from various energy sources and supply it to the switchboard. For example, the energy collection unit 350 combines electrical energy collected from each energy source and stores the energy using an energy storage device such as a battery as needed.

In an embodiment, the energy collection unit 350 adjusts the voltage, frequency, and state of the electrical energy to combine the electrical energy collected from each energy source and converts it into one integrated electrical energy. In the embodiment, the energy collection unit 350 controls the harvesting device of each energy source according to the calculated harvesting ratio and collects energy to be supplied to the switchgear, so that energy can be efficiently secured and supplied to the switchboard.

The supply unit 360 converts the collected energy into electric power and supplies the converted electric power to the switchboard. In an embodiment, the supply unit 360 converts the collected energy into electricity. At this time, the supply unit 360 uses an appropriate conversion device according to the characteristics of the collected electrical energy. For example, solar energy collected as direct current is converted to alternating current through an inverter, and in an embodiment, the conversion device adjusts the voltage, frequency, waveform, etc. of the electrical energy and converts it into standard power that can be used in the switchboard. Afterwards, the supply unit 360 supplies the converted power to the switchboard. The supply unit 360 transmits power to the switchboard through a power line or power network. At this time, the supply unit 360 may use appropriate protection devices, switches, and circuit control devices for power stability and safety.

In the embodiment, the supply unit 360 monitors and controls the flow and usage of power. For example, the supply unit 360 continuously monitors monitoring data including power quality, voltage, current, frequency, etc., and adjusts power distribution when the monitoring data is outside the normal range. Additionally, the supply unit 360 may adjust power distribution according to the power supply control signal transmitted from the management unit 380.

Additionally, in the embodiment, the analysis unit 370 accumulates hourly power use information of the switchboard, identifies power use patterns, and calculates hourly power use prediction values. For this purpose, the analysis unit 370 collects power usage information by time from the switchboard. Hourly power usage information includes past power usage, usage patterns, and power demand by time slot. Afterwards, the analysis unit 370 analyzes the collected data to identify power usage patterns. The analysis unit 370 uses statistical analysis techniques or machine learning algorithms to identify power use patterns. For example, the analysis unit 370 may use data mining techniques to find patterns of high power demand at specific times or group similar power use patterns through clustering.

Additionally, the analysis unit 370 updates the hourly power use prediction model based on the power use pattern. To this end, the analysis unit 370 can utilize prediction models such as regression analysis, time series analysis, and artificial neural networks. The model learns the relationship between power usage and time by learning the collected data, and calculates future power usage predictions based on this. The analysis unit 370 uses a power usage prediction model to calculate hourly power usage predictions.

The management unit 380 calculates the optimal energy harvesting amount according to the predicted power usage value and the remaining power amount of the switchboard. The management unit 380 can calculate the optimal energy harvesting amount by using the hourly power usage prediction value calculated by the analysis unit 370. In the embodiment, the hourly power usage predicted value is a value predicting the future hourly power usage and reflects the expected electric power demand in the switchgear. Afterwards, the management unit 380 calculates the remaining amount of power remaining in the switchboard at the current point in time. The remaining amount of power is the amount of energy that can be supplied to the switchboard, and is calculated to determine the amount of power supply remaining. Thereafter, the management unit 380 compares the predicted power usage value with the remaining power amount, and the management unit 380 calculates the optimal energy harvesting amount for smooth power supply to the switchboard. Through this, it is determined how much energy must be harvested to meet the power demand of the switchgear. For example, if the predicted power use value is greater than the remaining power amount, the management unit 380 harvests additional energy to supplement power supply and demand.

The management unit 380 controls the energy harvesting device based on the energy harvesting amount. During the energy harvesting process, the management unit 380 can monitor the power usage status and remaining power amount in real time and control the harvesting device according to the monitoring results. In an embodiment, the management unit 380 optimizes power supply by updating the energy harvesting amount or adjusting the operation of the energy harvesting device.

In addition, the management unit 380 calculates the energy collection point and power use point of the switchboard according to the power use pattern and power use efficiency of the switchboard. To this end, the management unit 380 analyzes past power use patterns of the switchboard. The management unit 380 identifies peak hours, which are the times when power is used the most. In addition, the management unit 380 evaluates the power use efficiency in the switchboard. Power use efficiency refers to minimizing energy loss and using power efficiently to maintain the required power to a minimum. The management unit 380 evaluates the energy usage and production volume. Measure power use efficiency by considering such factors and analyze the measured power use efficiency. Afterwards, the management unit 380 calculates the energy collection point of the switchboard. This determines the optimal time to collect energy from the switchboard. For example, in the case of a solar power generation system, considering the solar illuminance and the position of the sun, the management unit 380 determines the time zone when solar energy collection is most efficient, and when the power consumption in that time zone is below a certain level, the energy harvester It allows you to conduct meetings and collect energy.

Additionally, the management unit 380 calculates the power use time of the switchboard. This determines the optimal time to use power, and the management unit 380 can adjust power use by considering changes in power use patterns and power demand and create a strategy to minimize power use during peak hours. The management unit 380 monitors the power use pattern and power use efficiency of the switchboard in real time and adjusts the energy collection point and power use point as necessary. Through this, power use can be optimized and power supply and demand balanced.

Additionally, in the embodiment, the management unit 380 adjusts the harvesting time and energy storage capacity of each energy source according to the remaining power amount and predicted power use of the switchgear power supply source. To this end, the management unit 380 monitors the remaining amount of power remaining from the power supply of the switchboard. Afterwards, the management unit 380 predicts future power usage using a power usage prediction model. The management unit 380 determines the expected power demand from the switchboard through power usage prediction, and the management unit 380 adjusts the harvesting time of each energy source by comparing the remaining power amount and the predicted power use amount. For example, if the remaining power amount is greater than the predicted power usage, the harvesting time is increased to collect additional energy. Conversely, if the remaining power amount is less than the predicted power usage, energy collection can be limited by reducing the harvesting time. Additionally, the management unit 380 readjusts the energy storage capacity. For example, if the remaining power amount is above a certain level, more energy is stored in an energy storage device (e.g., battery) so that it can be used later. In the embodiment, the management unit 380 monitors the remaining power amount and predicted power use in real time and adjusts the harvesting time and energy storage capacity as needed. This allows the power demand of the switchgear to be met while maximizing the use of energy from the power source.

Figure 3 is a diagram showing the data processing configuration of the management server according to an embodiment. Referring to FIG. 3, the management server 400 according to the embodiment is configured to include a storage unit 410, a monitoring unit 420, a remote control unit 430, an analysis unit 440, and a generation unit 450. You can.

In the embodiment, the management server 400 builds big data by collecting monitoring data from each registered switchgear, environmental information collected from sensors, and monitoring information from harvesting devices. The storage unit 410 collects data generated from switchboards, harvesting devices, and sensors, and converts the collected data into big data. For this purpose, the storage unit 410 collects various data generated from the switchgear. Data collected in the storage unit 410 may mainly include real-time data generated from sensors, harvesting devices, and switchboards. For example, data such as current, voltage, frequency, temperature, and vibration may be collected. In an embodiment, the storage unit 410 may directly collect data or receive it through another device. Afterwards, the storage unit 410 stores the collected data using a database system. The storage unit 410 stores data in a structured form in a database and allows access to the data through queries.

The monitoring unit 420 monitors the status of the switchboard, sensors, and harvesting devices. In an embodiment, the monitoring unit 420 may monitor the status of the switchboard by comparing data collected from each of the switchboard, sensors, and harvesting devices with normal data.

In an embodiment, the monitoring unit 420 determines an abnormal state when the collected data is outside a preset normal data range or when the change pattern is different from normal. In an embodiment, the monitoring unit 420 may detect a device in an abnormal state according to the source of data determined to be in an abnormal state, and determine the type of abnormal state and response process according to the results of analyzing the collected data. In the embodiment, the monitoring unit 420 determines the abnormal state of the monitoring data through a parameter analysis method that determines a process abnormality when the difference between the parameters calculated with normal data and the parameters calculated with actual data is large. You can. In addition, the monitoring unit 320 determines the abnormal state of the monitoring data through the residual analysis method, which determines a process abnormality when the difference between the value predicted by a pattern recognition model made from normal data and the value measured by the actual sensor is large. can be figured out.

Additionally, in the embodiment, the monitoring unit 420 may diagnose a failure of the switchboard according to the correlation between real-time temperature and vibration data sets. For example, the monitoring unit 420 may collect real-time temperature and vibration data sets and diagnose abnormalities based on the similarity between the collected temperature and vibration data sets and the data included in the temperature and vibration correlation data sets. Specifically, if the temperature and vibration correlation of the collected temperature and vibration data set is similar to the temperature and vibration correlation included in the temperature and progress correlation data set at a certain level or more, the monitoring unit 420 collects the collected temperature and vibration data. The set is input into the fault diagnosis model to diagnose any abnormalities.

In addition, the monitoring unit 420 collects a quasi-correlation data set, which is a data set from the start of the data of the temperature and vibration correlation data set to before a preset time, and inputs the collected quasi-correlation data set into the fault diagnosis model. , it is possible to diagnose abnormalities in the switchboard. Additionally, the monitoring unit 420 may diagnose a failure of the switchgear through a separate diagnostic method if the collected temperature and vibration data set does not belong to the temperature, vibration correlation data, or quasi-correlation data set. At this time, the monitoring unit 420 may use a separate temperature diagnosis algorithm or a vibration diagnosis algorithm that is not based on artificial intelligence. The diagnostic algorithm includes an algorithm for piecemeal diagnosis of temperature abnormality and vibration abnormality using temperature threshold and vibration threshold. In embodiments, the temperature threshold and vibration threshold may be preset and may include minimum and maximum values of the steady-state range. For example, the monitoring unit 420 can determine whether the collected temperature and vibration data are within the normal range, and determine whether there is an abnormality in the switchgear depending on the level at which the collected temperature and vibration data are outside the normal range. Specifically, the monitoring unit 420 can determine whether there is an abnormality in the switchboard according to the difference between the minimum value of the normal range and the collected data and the difference between the maximum value of the normal range and the collected data.

The remote control unit 430 remotely controls the switchboard according to the monitoring results of the switchboard. For example, when an abnormal condition is monitored in any one of the switchboard, sensor, and harvesting device, the remote control unit 430 can remotely control the switchboard to resolve the monitored abnormal condition.

Additionally, in the embodiment, the remote control unit 430 generates and transmits control commands for each of the switchboard, sensor, and harvesting device based on the data monitoring results. Control commands include changing the operation mode of each device, adjusting set values, generating warnings/notifications, etc., and can be generated according to monitoring results. For example, the remote control unit 430 may generate a control command to transmit a warning message when the monitoring data is outside the normal range.

Afterwards, the switchboard, sensor, and harvesting device execute the control command received from the remote control unit 430. Through this, the switchboard can change the operating state or perform a specific task. For example, the remote control unit 430 can control the operation/stop of the switchboard, change of setting values, and generation of alarms/notifications.

The analysis unit 440 analyzes the collected data to predict the performance, energy use pattern, and load of the switchboard, sensor, and harvesting device system. To this end, the analysis unit 440 improves the quality of the data by performing purification, outlier processing, missing value processing, and data conversion of the collected data, and scales or normalizes the data as necessary.

Afterwards, the analysis unit 440 analyzes the performance of the switchgear power system based on the collected data. This means monitoring parameters such as voltage, current, and frequency of the power system to evaluate the stability, accuracy, and efficiency of the system. Performance analysis can be performed through statistical analysis of data, frequency spectrum analysis, correlation analysis, etc. Additionally, the analysis unit 440 analyzes the energy use pattern of the switchgear based on the collected data. This means evaluating the characteristics and efficiency of energy use by identifying patterns by hour, day, week, and season. For example, it analyzes peak times, low power times, and changes in energy consumption patterns to help manage and save energy.

Additionally, the analysis unit 440 uses the collected data to predict the load of the switchgear. Load prediction is predicting the expected load situation at a future point in time and can be performed using machine learning algorithms, time series analysis, neural networks, etc. Accurate load prediction plays an important role in power system operation and helps improve the efficiency and stability of energy supply.

The generation unit 450 generates a report on the data analysis results. To this end, the generation unit 450 derives results using various analysis methods and algorithms based on the analyzed data. For example, the generator 450 may derive performance evaluation results of the switchgear, energy use pattern analysis results, load prediction results, etc. as results. Afterwards, the generation unit 450 constructs a report to visually express the derived data analysis results. For example, the generator 450 utilizes visual elements such as graphs, charts, and tables shown in FIG. 5, and the report may include an overview, summary, main features, graphs, and statistical information of the analysis results. Afterwards, the generation unit 450 automatically generates a report using computer software. The generated report is provided to personnel related to the switchgear, such as managers, operators, and technicians. This allows you to easily check the data analysis results and make decisions based on them.

Figure 4 is a diagram showing the data processing configuration of a manager terminal according to an embodiment.

Referring to FIG. 4, the manager terminal 500 according to the embodiment may be configured to include an authentication unit 510, an output unit 520, and an emergency notification unit 530.

The authentication unit 510 transmits administrator personal information or device information to the management server 400 and performs administrator authentication. In the embodiment, the administrator authentication process is a process for controlling and monitoring data viewing of switchboards, sensors, and harvesting devices. In the embodiment, the authentication unit 510 transmits administrator information, pin numbers, etc. to the management server, and Depending on whether (400) is authenticated, authentication of the manager or device can be completed.

The output unit 520 outputs switchboard monitoring data. In the embodiment, the output unit 520 outputs monitoring data including switchboard sensor data according to the type and time of the data. For example, the output unit 420 can output monitoring data by visualizing it in graphs, charts, icons, etc. Additionally, the output unit 520 may change the color or shape of the monitoring data or change the color or form of data related to abnormalities and output the data. Additionally, the output unit 520 may output monitoring data in colors or icons that are previously matched to the health status and fault diagnosis status of the switchboard.

In the embodiment, the output unit 520 processes the collected monitoring data and converts it into a required format for output. For example, as shown in Figure 5, monitoring data is visualized in graphs, charts, tables, etc. or processed to fit a specific format. Afterwards, the output unit 520 outputs the processed data through an appropriate output device or interface. Through this, the monitoring results of the switchboard can be visually displayed or recorded. For example, data can be output using LCD screens, LED lights, printers, data logging devices, etc. Output methods can be configured in various ways depending on system requirements and operator needs.

Additionally, the output unit 520 can control output as needed. For example, you can set the output cycle to output data at regular time intervals, or output a specific signal when an alarm or warning occurs.

If an abnormality is detected in the monitoring data and the emergency notification unit 530 determines that the detected abnormality is an emergency event, it displays this on the administrator terminal. In embodiments, emergency events may include overvoltage, undervoltage, overcurrent, short circuit, fault detection, etc. Overvoltage: An event in which the voltage generated in a switchgear exceeds the normal range. This may occur due to an abnormality or malfunction of the power supply system and may cause damage to electrical equipment. Undervoltage is an event in which the voltage generated in the switchboard becomes lower than the normal range. This may occur due to power supply problems or equipment failure, and may interfere with the normal operation of electrical equipment. Overcurrent: An event in which the current generated in the switchboard exceeds the normal range. Overcurrent can occur due to circuit overload, short circuit, or device failure, and can damage electrical equipment and even cause fire. A short circuit is a condition in an electric circuit where voltage is bypassed through a short path. Short circuits can be caused by incorrect connections in circuits, short circuits in wires, or equipment failures, and can cause serious damage to electrical equipment and pose a fire risk. Fault detection is an event that occurs when a fault in equipment or circuit is detected in the switchboard. Fault detection can occur when certain conditions such as voltage abnormality, current abnormality, or temperature abnormality are met, allowing faults to be detected early and action to be taken.

Figure 6 is a diagram showing an output interface of a manager terminal according to an embodiment.

Referring to FIG. 6, the manager terminal according to the embodiment can check electrical defects, mechanical defects, notification caution information, etc. of the switchgear through the application (a) or the web (b), the number of switchboards in a normal state, and the number of switchboards in an abnormal state. You can check the number of switchboards.

Below, the distribution board diagnosis method will be explained in turn. Since the operation (function) of the switchboard diagnosis method according to the embodiment is essentially the same as the function of the switchboard diagnosis system, descriptions overlapping with FIGS. 1 to 7 will be omitted.

Figure 8 is a signal flow diagram of a switchgear system using energy harvesting according to an embodiment.

Referring to FIG. 8, in step S100, the harvesting device generates energy from each energy source. In step S200, environmental information is sensed by a sensor, and in step S300, power is acquired from a harvesting device in the switchboard. In step S400, the management server collects monitoring data from harvesting devices, sensors, and switchboards and analyzes them to determine abnormal conditions. In step S500, monitoring data and abnormal status information are output from the manager terminal.

Figure 9 is a diagram showing a data processing process for acquiring power of a switchboard according to an embodiment.

Referring to Figure 9, in step S310, the power generation efficiency of each energy source is predicted by analyzing the environmental information collected from the sensor, and in step S320, the harvesting ratio of each energy source is calculated based on the prediction result. In step S330, the harvesting device connected to each energy source is controlled according to the calculated harvesting ratio, and in step S340, energy is collected from the harvesting device. In step S750, the collected energy is converted into power and the converted power is obtained.

Figure 10 is a diagram showing the energy collection process according to an embodiment.

Referring to FIG. 10, in step S341, hourly power usage information is accumulated, power usage patterns are identified, and hourly power usage prediction values are calculated. In step S343, the energy harvesting amount for each energy source is calculated according to the predicted power usage value and the remaining power amount of the switchboard. In step S345, the harvested energy is collected.

The switchgear system using energy harvesting as described above improves the independence of switchboard power supply by utilizing environmentally friendly and sustainable energy sources.

In addition, the embodiment creates effects such as extending the life of the switchboard battery, reducing maintenance costs, and reducing power consumption. In addition, through the embodiment, energy harvesting efficiency can be improved and power use efficiency of the switchgear can be improved.

The disclosed content is merely an example, and various modifications and implementations may be made by those skilled in the art without departing from the gist of the claims, so the scope of protection of the disclosed content is limited to the above-mentioned specific scope. It is not limited to the examples.

Claims (20)

In the switchgear system using energy harvesting,
A harvesting device that generates energy from each energy source;
Sensors that sense environmental information;
A switchboard receiving power from the harvesting device; contains
The switchboard; silver
A calculation unit that analyzes environmental information collected from sensors to predict the power generation efficiency of each energy source and calculates the harvesting ratio of each energy source based on the prediction results;
an energy collection unit that controls a harvesting device connected to each energy source according to the calculated harvesting ratio and collects energy from the harvesting device;
a supply unit that converts the collected energy into electric power and supplies the converted electric power to a switchboard;
An analysis unit that accumulates hourly power use information, identifies power use patterns, and calculates hourly power use forecasts;
Calculate the energy harvesting amount of each energy source according to the predicted power use value and the remaining power amount of the switchboard, calculate the energy collection point and power use time of the switchboard according to the power use pattern and power use efficiency of the switchboard, and calculate the remaining power of the switchboard. A management unit that adjusts the harvesting time and energy storage capacity of each energy source according to the amount of power and predicted power use;
A collection unit that collects environmental information, power usage information from switchboards, and deep learning learning data; and
A deep learning unit that trains a deep learning neural network with deep learning learning data to generate a deep learning model including a switchgear management model and a power usage prediction model; Including,
The deep learning unit; Is
In order to extract a temperature and vibration correlation data set, which is data showing the correlation between temperature and vibration, the temperature and vibration data set is accumulated for a preset first time, and a temperature and vibration correlation data set is collected from the accumulated temperature and vibration data set. Extract ,
The deep learning unit; Is
During the preset second time, the data set in which the temperature change rate is greater than the temperature change rate standard value and the vibration change rate is greater than the vibration change rate standard value is recognized as a temperature and vibration correlation data set with correlation between temperature and vibration,
The second time is shorter than the first time,
The deep learning unit; Is,
The data set from the start of the temperature and vibration correlation data set to before a preset time is recognized as a quasi-correlated data set, which is unstructured and unstructured data that does not follow certain patterns or rules.
Temperature and vibration correlation data sets and quasi-correlation data sets are used as temperature and vibration data sets for training deep learning models,
the harvesting device; Is
Nano power generation devices that extract energy from the surrounding environment; and
solar panels that collect solar energy;
wind turbines that collect wind energy;
A thermal conversion device that collects thermal energy;
A kinetic energy collection device that collects kinetic energy;
A leakage energy collection device that collects leakage power from the switchboard through wireless power transfer, electromagnetic field harvesting, and thermal energy harvesting methods; includes
The nano power generation device; Is
Piezoelectric elements that collect vibration or pressure energy; includes
The calculation unit; Is
A switchgear system using energy harvesting that calculates the harvesting ratio of each energy source by dividing the expected power generation efficiency by the total expected power generation, evaluates the harvesting ratio calculation results, and then adjusts the harvesting ratio of each energy source according to the evaluation results. .
delete delete delete delete delete delete delete delete In a switchgear using energy harvesting,
A calculation unit that analyzes environmental information collected from sensors to predict the power generation efficiency of each energy source and calculates the harvesting ratio of each energy source based on the prediction results;
an energy collection unit that controls a harvesting device connected to each energy source according to the calculated harvesting ratio and collects energy from the harvesting device;
a supply unit that converts the collected energy into electric power and supplies the converted electric power to a switchboard;
An analysis unit that accumulates hourly power use information, identifies power use patterns, and calculates hourly power use forecasts;
Calculate the energy harvesting amount of each energy source according to the predicted power use value and the remaining power amount of the switchboard. Calculate the energy collection time and power use time of the switchboard according to the power use pattern and power use efficiency of the switchboard. The remaining power amount of the switchboard is calculated. A management unit that adjusts the harvesting time and energy storage capacity of each energy source according to the predicted amount of power use;
A collection unit that collects environmental information, power usage information from switchboards, and deep learning learning data; and
A deep learning unit that trains a deep learning neural network with deep learning learning data to generate a deep learning model including a switchgear management model and a power usage prediction model; includes
The deep learning unit; Is
In order to extract a temperature and vibration correlation data set, which is data in which the correlation between temperature and vibration is identified, the temperature and vibration data set is accumulated for a preset first time, and a temperature and vibration correlation data set is collected from the accumulated temperature and vibration data set. Extract ,
The deep learning unit; Is
During the preset second time, the data set in which the temperature change rate is greater than the temperature change rate standard value and the vibration change rate is greater than the vibration change rate standard value is recognized as a temperature and vibration correlation data set with correlation between temperature and vibration,
The second time is shorter than the first time,
The deep learning unit; Is,
The data set from the start of the temperature and vibration correlation data set to before a preset time is recognized as a quasi-correlated data set, which is unstructured and unstructured data that does not follow certain patterns or rules.
Temperature and vibration correlation data sets and quasi-correlation data sets are used as temperature and vibration data sets for training deep learning models,
the harvesting device; Is
Nano power generation devices that extract energy from the surrounding environment; and
solar panels that collect solar energy;
wind turbines that collect wind energy;
A thermal conversion device that collects thermal energy;
A kinetic energy collection device that collects kinetic energy;
A leakage energy collection device that collects leakage power from the switchboard through wireless power transfer, electromagnetic field harvesting, and thermal energy harvesting methods; includes
The nano power generation device; Is
Piezoelectric elements that collect vibration or pressure energy; includes
The calculation unit; Is
Energy harvesting, characterized in that the harvesting ratio of each energy source is calculated by dividing the expected power generation efficiency by the total expected power generation, and after evaluating the harvesting ratio calculation result, the harvesting ratio of each energy source is adjusted according to the evaluation result. Distribution board using .


delete delete delete delete delete delete delete delete delete delete