Smart park electric energy monitoring management system

Abstract

The invention discloses a smart park electric energy monitoring and management system, and relates to the technical field of smart power grids and Internet of Things, and the system comprises the following components: a data collection layer, a big data processing and analysis layer, an equipment health degree evaluation layer, a fault early warning and diagnosis layer, and an operation and maintenance decision support layer. The operation data of the equipment is continuously collected, the equipment health degree evaluation layer calculates and updates the equipment health index in real time, the equipment performance reduction or potential fault risk is found in time, and once the equipment health index is lower than the preset threshold value, the system automatically triggers an early warning mechanism to inform related personnel to pay attention to or take corresponding measures, so that the safety of the equipment is improved. Through the real-time monitoring and early warning functions, operation and maintenance personnel can quickly respond to equipment problems, and fault expansion or influence on the whole electric energy supply of the park is avoided, so that the operation and maintenance efficiency and stability of the park are improved.

Description

Technical Field

[0001] The present invention relates to the technical fields of smart grid and Internet of Things, and specifically to a power monitoring and management system for smart parks. Background Art

[0002] With the rapid development of technologies such as Internet of Things, big data, and artificial intelligence, the construction of smart parks has become an important means to improve urban management and service levels. Smart parks integrate multiple intelligent systems to achieve efficient and refined management of various facilities and resources within the park. Among them, electric energy, as the basic energy for park operation, its stable supply and efficient utilization are crucial for the sustainable development of the park. Therefore, establishing a power monitoring and management system for smart parks that can monitor, analyze, and optimize electric energy usage in real time has become an important requirement for current park management.

[0003] In traditional power monitoring and management systems, the assessment of equipment health often relies on manual inspections and regular maintenance. This method is not only inefficient but also difficult to detect potential equipment failures and performance degradation problems in a timely manner. At the same time, most traditional assessment methods are based on single-dimensional data, lacking comprehensiveness and accuracy, and it is difficult to quantitatively evaluate the overall health status of equipment. In addition, traditional systems lack an intelligent fault warning and diagnosis mechanism, unable to achieve early identification and rapid response to faults, increasing the uncertainty and risk of power supply in the park.

[0004] In view of the above situation, it is necessary to optimize the existing power monitoring and management system. Through Internet of Things technology, comprehensive monitoring of key nodes and electrical equipment in the park grid is achieved. Combining the equipment health assessment model and fault warning and diagnosis algorithms, real-time monitoring of the equipment health status and early warning of fault risks are realized. Therefore, it is particularly important to develop a power monitoring and management system for smart parks based on the above functions. Summary of the Invention

[0005] The purpose of the present invention is to make up for the deficiencies of the existing technology and provide a power monitoring and management system for smart parks. The system mainly includes a data acquisition layer, a big data processing and analysis layer, an equipment health assessment layer, a fault warning and diagnosis layer, and an operation and maintenance decision support layer. Each layer collaborates closely to jointly achieve comprehensive monitoring and management of the power supply in the park.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A power equipment fault warning system, which includes a data acquisition layer, a big data processing and analysis layer, an equipment health assessment layer, a fault warning and diagnosis layer, and an operation and maintenance decision support layer;

[0007] The data acquisition layer: Adopting Internet of Things technology, a large number of intelligent sensors and data acquisition terminals are deployed at key nodes and power-consuming equipment of the campus power grid to collect multi-dimensional power data such as voltage, current, power factor, temperature, and vibration in real time. It supports multiple communication protocols to ensure the comprehensive, accurate, and timely upload of data to the data processing center;

[0008] The big data processing and analysis layer: Using a distributed computing framework to efficiently store and process massive power data, applying data mining and machine learning algorithms to deeply analyze the data and extract information and features;

[0009] The equipment health assessment layer: Based on the collected operation data and through fusion processing, an equipment health assessment model is constructed to calculate the equipment health index in real time, quantitatively evaluate the equipment status, and provide data support for fault warning;

[0010] The fault warning and diagnosis layer: Through comparative analysis, potential power supply and equipment fault risks are identified in advance to achieve fault warning. Machine learning algorithms are used to automatically identify fault patterns, classify them, generate detailed fault diagnosis reports, and combined with the historical case library, provide targeted maintenance suggestions to reduce the difficulty and time cost of fault repair;

[0011] The operation and maintenance decision support layer: Provides a visual interface to display the campus power supply status, equipment health distribution, fault warning, and diagnosis result information, and supports operation and maintenance personnel to perform remote monitoring, fault diagnosis, and dispatching command operations through the system platform.

[0012] Furthermore, the data acquisition layer conducts a comprehensive survey and analysis of the campus power grid. Based on the power grid topology structure and equipment importance assessment, the key nodes and power-consuming equipment where sensors and acquisition terminals need to be deployed are determined. According to the type and accuracy requirements of the collected data, intelligent sensors and data acquisition terminals are selected, and the selected intelligent sensors and data acquisition terminals are installed on the determined key nodes and power-consuming equipment. The sensors and acquisition terminals are configured to support multiple communication protocols to achieve effective communication with the data processing center. The collected data is uploaded to the data processing center through the configured communication protocol and data verification is performed. For abnormal data, error correction algorithms are used for processing. The data processing center receives and stores the uploaded data to provide data support for subsequent analysis and processing, and deeply analyzes the collected data through data analysis algorithms and tools.

[0013] Furthermore, the big data processing and analysis layer receives a large amount of power data from the data acquisition layer, integrates and preprocesses data from different sources and formats, evaluates the data scale and processing requirements, and selects a distributed computing framework. It stores the integrated data in a distributed file system and a database, and uses the K-Means clustering algorithm and the association rule mining algorithm to mine the data. In the K-Means clustering algorithm, the distance from the sample point to the cluster center is calculated: where x is the sample point, c is the cluster center, and n is the number of features. Deep analysis is performed using regression analysis and classification algorithms. The linear regression model: y = β 0 + β 1 x 1 + β 2 x 2 + … +, where y is the dependent variable, x i is the independent variable, β i is the coefficient, and is the error term. Valuable information and features are extracted from the analysis results, and the analysis results are evaluated using evaluation metrics. The calculation formula for accuracy: where TP is the true positive, TN is the true negative, FP is the false positive, and FN is the false negative.

[0014] Furthermore, the equipment health assessment layer collects the operation data of the equipment and performs fusion processing, including voltage, current, power, temperature, and vibration. At the same time, it sorts out the standard parameters of the equipment, the historical operation data, and the performance data of similar equipment, determines the key indicators for evaluating the equipment health, including the operation efficiency, failure rate, and repair times of the equipment, and evaluates the equipment.

[0015] Furthermore, the equipment health assessment layer uses a weighted algorithm to perform fusion processing on the operation data of the collected equipment, including voltage X 1 , current X 2 , power X 3 , temperature X 4 , and vibration X 5 , and its calculation formula is: Y = W 1 X 1 + W 2 X 2 + W 3 X 3 + W 4 X 4 + W 5 X 5 , where W 1 , W 2 , W 3 , W 4 , W 5They respectively represent the weight coefficients of voltage, current, power, temperature, and vibration, that is, the importance of the sensor data in the fusion process.

[0016] Furthermore, the device health assessment layer is based on the collected device operation data, and determines the current device performance by calculating the decision function where x is the device operation data feature vector, x i is the support vector, y i is the class label, α i is the Lagrange multiplier, b is the bias term, and K(x i , x) is the selected kernel function to achieve the quantitative assessment and real-time monitoring of the device health status.

[0017] Furthermore, the device health assessment layer calculates the differences in key indicators between the current device and similar devices. The performance difference: ΔP = P current - Psimilar, where ΔP current is the performance difference, P cuvrent is the current device performance, P similar is the performance of similar devices. Considering all the above factors, the device health index is calculated in real time through the evaluation model. The health index HI consists of multiple factors F i and their weights w i The calculation formula is: According to the calculated health index, determine the health status level of the device, including excellent, good, average, poor, and very poor, and provide the device health index and evaluation results to the fault warning and diagnosis layer.

[0018] Furthermore, the fault warning and diagnosis layer compares the device operation data with the threshold of the normal range, identifies potential risks of power supply and device failures in advance, automatically triggers the warning mechanism for abnormal situations, notifies relevant personnel, and generates a fault diagnosis report in combination with the historical case library.

[0019] Furthermore, the fault warning and diagnosis layer gives a targeted maintenance plan according to the historical cases and the specific situation of the current fault, including the required tools, maintenance steps, and estimated maintenance time, and continuously optimizes the warning indicators, thresholds, machine learning algorithms, and maintenance suggestions according to the actual maintenance effect and new fault data.

[0020] Furthermore, the operation and maintenance decision support layer collects data related to the power supply status, equipment health, fault warning, and diagnosis of the park from various monitoring points and systems, cleans and integrates the data, designs the layout of the visualization interface, displays various indicators of power supply using charts, establishes a communication connection with on-site equipment to achieve real-time data transmission, highlights the fault warning and diagnosis results on the interface, and provides the process and guidelines for fault diagnosis to help operation and maintenance personnel quickly locate problems.

[0021] Compared with the prior art, a smart park power monitoring and management system has the following beneficial effects:

[0022] 1. By continuously collecting the operation data of equipment, and the equipment health assessment layer calculates and updates the equipment health index in real time, the system can timely detect the decline in equipment performance or potential fault risks. Once the equipment health index is lower than the preset threshold, the system will automatically trigger the warning mechanism to notify relevant personnel to pay attention or take corresponding measures. This real-time monitoring and warning function enables operation and maintenance personnel to quickly respond to equipment problems, avoid the expansion of faults or the impact on the overall power supply of the park, thereby improving the operation and maintenance efficiency and stability of the park.

[0023] 2. By comparing the equipment operation data with the threshold of the normal range in the fault warning and diagnosis layer, the system can identify potential power supply and equipment fault risks in advance, greatly improving the accuracy and timeliness of fault warning. This enables operation and maintenance personnel to take preventive measures before the occurrence of faults, reducing the impact of faults on the power supply of the park. At the same time, the fault diagnosis report and maintenance suggestions generated in combination with the historical case library can also provide targeted guidance for operation and maintenance personnel, improving the maintenance efficiency and quality, and further reducing the impact of faults on the operation of the park. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0025] Figure 1 An operation flow chart of a smart park power monitoring and management system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0027] Embodiment 1

[0028] Clearly identify which monitoring points and systems data need to be collected from, including but not limited to the data acquisition layer, big data processing and analysis layer, equipment health assessment layer, and fault warning and diagnosis layer. Clean the collected data to remove duplicate, incorrect, incomplete, and abnormal data records to ensure the accuracy and reliability of the data. Integrate the cleaned data to form a unified data format and standard for subsequent analysis and processing, and adopt an efficient data storage solution.

[0029] Design an intuitive and clear visualization interface layout to ensure that operation and maintenance personnel can quickly understand and operate. Use various charts to display various indicators of power supply, including power consumption changes, equipment health distribution, and fault warning and diagnosis results. Increase the interactivity of the interface to ensure that the data displayed on the interface can be updated in real time to reflect the latest status of power supply and equipment operation in the park.

[0030] Establish a stable communication connection with on-site equipment, support multiple communication protocols, ensure real-time data transmission, receive the data uploaded by on-site equipment in real time, and display it on the visualization interface, enabling operation and maintenance personnel to grasp the equipment operation status in real time, realize the remote operation function, improve the flexibility and efficiency of operation and maintenance, and establish a strict security mechanism to ensure the security of remote operations and prevent illegal access and operations.

[0031] The equipment health assessment layer collects the operation data of the equipment and performs fusion processing, including voltage X 1 , current X 2 , power X 3 , temperature X 4 , and vibration X 5 . Its calculation formula is: Y = W 1 X 1 + W 2 X 2 + W 3 X 3 + W 4 X 4 + W 5 X 5 , where W 1 , W 2 , W 3 , W 4 , W 5They respectively represent the weight coefficients of voltage, current, power, temperature, and vibration, that is, the importance of the sensor data in the fusion process. At the same time, the standard parameters of the equipment, historical operation data, and performance data of similar equipment are sorted out to determine the key indicators for evaluating the equipment health, including the operation efficiency, failure rate, and maintenance times of the equipment, and the equipment is evaluated by calculating the decision function to determine the current equipment performance, where x is the characteristic vector of the equipment operation data, x i is the support vector, y i is the class label, α i is the Lagrange multiplier, b is the bias term, K(x i , x) is the selected kernel function to achieve the quantitative evaluation and real-time detection of the equipment health status. According to the calculated current equipment performance parameters, compare them with those of similar equipment in key indicators. The performance difference: ΔP = P current - Psimilar, where ΔP current is the performance difference, P cuvrent is the current equipment performance, and P similar is the performance of similar equipment.

[0032] The fault warning and diagnosis layer compares the equipment operation data with the threshold of the normal range, identifies potential risks of power supply and equipment failures in advance, automatically triggers the warning mechanism for abnormal situations, notifies relevant personnel, and generates a fault diagnosis report in combination with the historical case database.

[0033] Embodiment 2

[0034] Intelligent sensors and data acquisition terminals are deployed at the key nodes and main power-consuming equipment of the campus power grid. These sensors are responsible for real-time collection of key power data such as voltage, current, power factor, temperature, and vibration, and formulating a detailed data collection plan, including collection frequency, data type, and accuracy requirements.

[0035] Multiple communication protocols are configured for the sensors and acquisition terminals to adapt to the data transmission requirements in different scenarios, ensure the real-time, reliable, and secure data transmission, build a stable and reliable data transmission network, and achieve effective connection and data transmission between the sensors and the data processing center.

[0036] Before uploading data to the data processing center, perform real-time verification and cleaning, check the data range and rationality, ensure the integrity and accuracy of the data. For abnormal data, use error correction algorithms for processing. Store the verified data in a distributed file system and a database for subsequent analysis and processing. Adopt efficient data storage and management strategies to ensure the rapidity and security of data access. Use data mining and machine learning algorithms to deeply analyze massive power data, extract valuable information and features. Through clustering analysis and association rule mining methods, in the K-Means clustering algorithm, calculate the distance from the sample point to the cluster center: where x is the sample point, c is the cluster center, and n is the number of features. Linear regression model: y = β 0 + β 1 x 1 + β 2 x 2 + … + ∈, where y is the dependent variable, x i is the independent variable, β i is the coefficient, and ∈ is the error term. Discover the potential laws and trends in the data.

[0037] Develop an intuitive and clear visualization interface to display the operating status of the campus power grid and the real-time data of each device, support operation and maintenance personnel to perform remote monitoring and management through the interface. Set reasonable alarm thresholds according to historical data and empirical values. When the real-time data exceeds the set alarm threshold, automatically trigger the alarm mechanism and notify the operation and maintenance personnel to handle it in a timely manner through various methods such as sound, email, and text message. Combine the historical case library and machine learning algorithms to quickly diagnose and locate faults, provide detailed fault diagnosis reports and repair suggestions, and reduce the difficulty and time cost of fault repair.

[0038] Integrate intelligent scheduling and optimization algorithms. According to the campus electricity demand and equipment status, automatically adjust the power supply strategy, including adjusting the transformer tap position and the output power of distributed power sources, to achieve the optimal allocation of electric energy resources. Establish a communication connection with on-site equipment to achieve remote control and operation. Operation and maintenance personnel can remotely control the switch status of the equipment and adjust parameters through the system platform, comprehensively test and optimize the various functions of the system to ensure the stability and accuracy of the system. Regularly maintain and upgrade the system to adapt to the continuous changes and development of campus power management.

[0039] It is obvious to those skilled in the art that the present invention is not limited to the details of the above-described exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A smart park power monitoring and management system, characterized in that: The system includes a data collection layer, a big data processing and analysis layer, the equipment health assessment layer, the fault warning and diagnosis layer, and the operation and maintenance decision support layer; The data collection layer: adopts the Internet of Things technology, deploys a large number of intelligent sensors and data collection terminals at key nodes and power-consuming equipment in the park power grid, collects multi-dimensional power data such as voltage, current, power factor, temperature, and vibration in real time, supports multiple communication protocols, and enables data to be uploaded to the data processing center in a timely manner; The big data processing and analysis layer: uses a distributed computing framework to efficiently store and process massive amounts of electric energy data, applies data mining and machine learning algorithms to perform in-depth analysis of the data, and extracts information and features; The equipment health assessment layer: based on the collected operation data and fusion processing, builds an equipment health assessment model, calculates the equipment health index in real time, quantitatively evaluates the equipment status, and provides data support for fault warning; The fault warning and diagnosis layer: compares the equipment operation data with the threshold value of the normal range, identifies the potential power supply and equipment failure risks in advance, generates fault diagnosis reports, and provides targeted maintenance suggestions in combination with the historical case library; The operation and maintenance decision support layer provides a visual interface to display the power supply status of the park, equipment health distribution, fault warning and diagnosis result information, and supports operation and maintenance personnel to perform remote monitoring, fault diagnosis, and dispatch command operations through the system platform.

2. According to claim 1, a smart park power monitoring and management system is characterized in that: The data acquisition layer conducts a comprehensive survey and analysis of the park power grid, and based on the power grid topology and equipment importance assessment, determines the key nodes and power-consuming equipment where sensors and acquisition terminals need to be deployed. According to the type and accuracy requirements of the collected data, intelligent sensors and data acquisition terminals are selected, and the selected intelligent sensors and data acquisition terminals are installed on the determined key nodes and power-consuming equipment. The sensor and acquisition terminal configurations support multiple communication protocols to achieve effective communication with the data processing center. The collected data is uploaded to the data processing center through the configured communication protocol, and data verification is performed. For abnormal data, error correction algorithms are used for processing. The data processing center receives and stores the uploaded data to provide data support for subsequent analysis and processing, and conducts in-depth analysis of the collected data through data analysis algorithms and tools.

3. According to claim 1, a smart park power monitoring and management system is characterized in that: The big data processing and analysis layer receives massive electric energy data from the data collection layer, integrates and preprocesses data from different sources and formats, evaluates the data scale and processing requirements, and selects a distributed computing framework to store the integrated data in a distributed file system and database. The K-Means clustering algorithm and the association rule mining algorithm are used to mine the data. In the K-Means clustering algorithm, the distance from the sample point to the cluster center is calculated: Where x is the sample point, c is the cluster center, n is the number of features, and regression analysis and classification algorithms are used for in-depth analysis. The linear regression model is: y = β0 + β1x1 + β2x2 + ... +, where y is the dependent variable, x i is the independent variable, β i is the coefficient, is the error term, extract valuable information and features from the analysis results, use the evaluation index to evaluate the analysis results, and the accuracy calculation formula is: Among them, TP is a true positive example, TN is a true negative example, FP is a false positive example, and FN is a false negative example.

4. According to claim 1, a smart park power monitoring and management system is characterized in that: The equipment health assessment layer collects and integrates the equipment's operating data, including voltage, current, power, temperature and vibration, and organizes the equipment's standard parameters, historical operating data and performance data of similar equipment to determine key indicators for evaluating equipment health, including equipment operating efficiency, failure rate, and number of repairs, and evaluates the equipment.

5. According to claim 4, a smart park power monitoring and management system is characterized in that: The equipment health assessment layer uses a weighted algorithm to fuse the operating data of the collected equipment, including voltage X1, current X2, power X3, temperature X4 and vibration X5. The calculation formula is: Y=W1 X1+W2 X2+W3 X3+W4 X4+W5 X5, where W1, W2, W3, W4, and W5 represent the weight coefficients of voltage, current, power, temperature, and vibration, respectively, that is, the importance of the sensor data in the fusion process.

6. According to claim 4, a smart park power monitoring and management system is characterized in that: The equipment health evaluation layer is based on the collected equipment operation data by calculating the decision function To determine the current device performance, x is the device operation data feature vector, x i is the support vector, y i is the category label, α i is the Lagrange multiplier, b is the bias term, K(x i ,x) is the selected kernel function to achieve quantitative evaluation and real-time monitoring of the equipment health status.

7. The smart park power monitoring and management system according to claim 4, characterized in that: The device health evaluation layer calculates the difference between the current device and similar devices in key indicators, performance difference: ΔP = P current -Psimilar, where ΔP current is the performance difference, P cuvrent is the current device performance, P similar The performance of similar equipment is comprehensively considered. The equipment health index is calculated in real time through the evaluation model. The health index HI is composed of multiple factors F i and its weight w i Composition, the calculation formula is: Based on the calculated health index, the health status level of the equipment is determined, including excellent, good, average, poor and bad, and the equipment health index and evaluation results are provided to the fault warning and diagnosis layer.

8. The smart park power monitoring and management system according to claim 1, characterized in that: The fault warning and diagnosis layer compares the equipment operation data with the threshold value of the normal range, identifies potential power supply and equipment failure risks in advance, and automatically triggers the warning mechanism for abnormal situations, notifies relevant personnel, and generates a fault diagnosis report in combination with the historical case library.

9. The smart park power monitoring and management system according to claim 8, characterized in that: The fault warning and diagnosis layer provides targeted maintenance plans based on historical cases and the specific circumstances of the current fault, including the required tools, maintenance steps and estimated maintenance time. It continuously optimizes the warning indicators, thresholds, machine learning algorithms and maintenance suggestions based on the actual maintenance results and new fault data.

10. The smart park power monitoring and management system according to claim 1, characterized in that: The operation and maintenance decision support layer collects data related to the power supply status, equipment health, fault warning and diagnosis of the park from various monitoring points and systems, cleans and integrates the data, and designs a visual interface layout, using charts to display various indicators of power supply. At the same time, it establishes communication connections with on-site equipment to achieve real-time data transmission, and highlights fault warning and diagnosis results on the interface, and provides fault diagnosis processes and guidelines to help operation and maintenance personnel quickly locate problems.

Images