A phase-changing equipment site selection, capacity planning and management system and method based on the Internet of Things

Abstract

The present invention discloses a phase-commutation equipment site selection and sizing planning management system and method based on the Internet of Things. The system includes: a data acquisition module, an analysis and decision-making module, and a geographic information system module. The system of the embodiment of the present invention provides accurate data support for the site selection and sizing of trial-operated phase-commutation equipment by acquiring the operating data, environmental data, and geographic location information of the phase-commutation equipment. It also uses a machine learning algorithm to identify the operating status and predict failure trends, which helps to identify potential risk points and optimization opportunities. Therefore, various factors that may affect the performance of trial-operated phase-commutation equipment can be obtained during the site selection and sizing planning stage, the advantages and disadvantages of different site selection schemes can be evaluated, and the accuracy and scientific nature of site selection and sizing planning can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a phase-changing equipment site selection, capacity planning and management system and method based on the Internet of Things. Background Art

[0002] As an emerging technology that has developed rapidly in recent years, the Internet of Things (IoT) technology originates from the integration of traditional automatic identification technology and sensor network technology. Through the combination of sensing devices, communication networks, and information processing systems, it realizes the interconnection between objects. With the continuous advancement of sensor technology, communication technology, and cloud computing technology, the IoT technology has developed rapidly and has been applied in fields such as electricity, communications, and transportation.

[0003] The site selection, sizing, planning, and subsequent management of commutation equipment (such as power transformers and communication base stations) is a complex and important task. Traditional IoT-based commutation equipment site selection, sizing, and management methods often rely on manual experience and limited data analysis, making it difficult to achieve accuracy and efficiency. Summary of the Invention

[0004] The present invention provides a phase-commutation equipment site selection and capacity planning management system and method based on the Internet of Things to solve the problem that the site selection and capacity planning and subsequent management of phase-commutation equipment are not efficient and accurate enough.

[0005] The present invention provides a phase-commutation equipment site selection and capacity planning and management system based on the Internet of Things, the system comprising:

[0006] a data acquisition module, configured to collect initial data of the trial-operation commutation device, wherein the initial data includes operation data of the trial-operation commutation device, environmental data of the target area where the trial-operation commutation device is located, and geographical location information;

[0007] an analysis and decision-making module, configured to mine and analyze the initial data using a machine learning algorithm to obtain an operating status and predicted failure trend of the trial-operated commutation equipment, and optimize alternative site selection and sizing plans based on environmental data in the initial data, the operating status, and the predicted failure trend to obtain an optimized site selection and sizing plan;

[0008] The geographic information system module is used to perform spatial analysis on the optimized site selection and capacity determination plan to obtain fusion information of the optimized site selection and capacity determination plan and the geographical location.

[0009] Optionally, the data acquisition module is specifically configured to collect the initial data through a first sensor and an RFID tag pre-installed in the trial operation commutation device and a second sensor in a target area where the trial operation commutation device is located;

[0010] Among them, the first sensor includes a current sensor, a voltage sensor, a temperature sensor and a vibration sensor, and the second sensor includes a temperature and humidity sensor and an air pressure sensor to obtain environmental data. The operating data in the initial data includes current, voltage, temperature and vibration data, and the environmental data in the initial data includes ambient temperature, humidity and air pressure data.

[0011] Optionally, the system further includes a planning management platform and a data transmission processing module, wherein:

[0012] The data transmission processing module is used to pre-process the initial data before the analysis and decision module uses the machine learning algorithm to mine and analyze the initial data, so as to obtain pre-processed initial data and transmit it to the planning management platform via a wireless network;

[0013] The planning management platform includes:

[0014] a storage and classification unit, configured to store the initial data in a pre-established distributed database, and classify the initial data stored in the distributed database according to data type, timestamp, and sensor identification dimension to obtain classified initial data;

[0015] The index creation and backup unit is used to create an index for the classified initial data and implement a preset data recovery mechanism by backing up the data in the distributed database at preset time intervals.

[0016] Optionally, the system further includes:

[0017] a data set generation module, configured to obtain historical fault records and maintenance logs, perform standardization on the initial data to obtain processed data in a unified format, and then integrate the processed data to obtain a data set, before performing mining and analysis on the initial data using a machine learning algorithm to obtain the operating status of the trial commutation device and predict the fault trend;

[0018] a feature data set generation module, configured to extract target features from the data set and integrate the target features with the fault features in the historical fault records to obtain a feature data set comprising a training set and a test set, wherein the target features include equipment operation features, environmental features, and abnormal fault features;

[0019] An index determination module, configured to determine an equipment operation evaluation index, an environmental interference index, and a fault diagnosis index using the data set;

[0020] A model building module, configured to build an anomaly classification model based on a neural network model using the feature data set and a machine learning algorithm;

[0021] an abnormality level and threshold preset module, configured to determine an abnormality assessment coefficient using the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index, and to preset an abnormal operation level and a corresponding abnormality threshold using the abnormality assessment coefficient and the historical fault records;

[0022] Wherein, the analysis and decision-making module includes:

[0023] a state and trend determination unit, configured to obtain the operation state and predicted fault trend of the trial-operation commutation device based on the abnormal operation level and the abnormal threshold, using the abnormal classification model and performing mining analysis on the initial data;

[0024] A site selection and sizing scheme optimization unit is used to optimize alternative site selection and sizing schemes using the environmental data and operating status in the data set and the predicted failure trend to obtain an optimized site selection and sizing scheme.

[0025] Furthermore, determining the equipment operation evaluation index and the environmental interference index using the data set includes:

[0026] Determine a current deviation index, a voltage deviation index, a temperature deviation index, and a vibration deviation index respectively using the measured values ​​and reference values ​​of the current characteristics, voltage characteristics, temperature characteristics, and vibration characteristics in the data set, and determine an equipment operation evaluation index using the current deviation index, the voltage deviation index, the temperature deviation index, and the vibration deviation index;

[0027] The measured values ​​and reference values ​​of the temperature characteristics, humidity characteristics, and air pressure characteristics in the data set are used to determine the ambient temperature deviation index, humidity deviation index, and air pressure deviation index, respectively, and the ambient temperature deviation index, humidity deviation index, and air pressure deviation index are used to determine the environmental interference index.

[0028] Furthermore, determining a fault diagnosis index using the data set includes:

[0029] Determine the baseline values ​​of the failure time feature, the failure frequency feature, and the maintenance cost feature respectively by using the associated data of the failure time feature, the failure frequency feature, and the maintenance cost feature in the data set;

[0030] The reference values ​​are used to determine a failure time deviation, a failure frequency deviation, and a maintenance cost deviation, respectively, and a failure diagnosis index is determined using the failure time deviation, the failure frequency deviation, and the maintenance cost deviation.

[0031] Furthermore, the determining of an abnormality assessment coefficient using the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index includes:

[0032] An abnormality assessment coefficient is determined by performing a weighted sum operation on the equipment operation assessment index, the environmental interference index, and the fault diagnosis index.

[0033] Optionally, the geographic information system module includes:

[0034] a database generation unit, configured to collect geographic information data related to the optimized site selection and capacity determination plan, and generate a geographic database using the geographic information data, wherein the geographic information data includes topography, land use status, transportation network, and hydrological information;

[0035] A processing unit, configured to clean, convert, standardize, and vectorize the geographic information data in the geographic database to obtain reference geographic data;

[0036] An analysis unit, configured to perform a multi-geographic layer overlay analysis on the optimized site selection and capacity determination plan using a geographic information system (GIS) and reference geographic data in the geographic database to obtain an analysis result;

[0037] A fusion information generating unit is used to determine the fusion information of the optimized site selection and capacity determination plan and the geographical location using the analysis results.

[0038] Furthermore, the abnormal operation level includes a low abnormal operation level, a medium abnormal operation level, and a high abnormal operation level, and the abnormal threshold includes an upper threshold and a lower threshold.

[0039] The present invention provides a method for planning and managing the site selection and capacity determination of phase-changing equipment based on the Internet of Things, the method comprising:

[0040] Collecting initial data of the trial-operation phase-changing device, wherein the initial data includes operation data of the trial-operation phase-changing device, environmental data of a target area where the trial-operation phase-changing device is located, and geographical location information;

[0041] Using a machine learning algorithm to mine and analyze the initial data to obtain the operating status and predicted failure trend of the trial-operated commutation equipment, and optimizing alternative site selection and sizing plans based on environmental data in the initial data, the operating status, and the predicted failure trend to obtain an optimized site selection and sizing plan;

[0042] A spatial analysis is performed on the optimized site selection and capacity determination plan to obtain fusion information of the optimized site selection and capacity determination plan and the geographical location.

[0043] The IoT-based phase-commutation equipment site selection and sizing planning management system and method provided by the present invention provides accurate data support for the site selection and sizing of trial-operation phase-commutation equipment by acquiring operating data, environmental data, and geographic location information of trial-operation phase-commutation equipment. It also utilizes machine learning algorithms to identify operating status and predict failure trends, which helps to identify potential risk points and optimization opportunities. Thus, various factors that may affect the performance of trial-operation phase-commutation equipment can be obtained during the site selection and sizing planning stage, the advantages and disadvantages of different site selection schemes can be evaluated, and the accuracy and scientific nature of site selection and sizing planning can be improved.

[0044] It should be understood that the content described in this section is not intended to identify the key or important features of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 This is a schematic diagram of the structure of a phase-commutation equipment site selection and capacity planning and management system based on the Internet of Things according to the first embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of the structure of a phase-commutation equipment site selection and capacity planning and management system based on the Internet of Things according to the second embodiment of the present invention;

[0048] Figure 3 This is a flowchart of a method for site selection, capacity planning and management of commutation equipment based on the Internet of Things provided according to embodiment three of the present invention. DETAILED DESCRIPTION

[0049] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0050] It should be noted that the terms "first," "second," and the like in the specification and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein. In the description of the present invention, unless otherwise specified, "plurality" refers to two or more. "And / or" describes an association relationship between associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship. In addition, the terms "including" and "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0051] Example 1

[0052] Figure 1 This embodiment of the present invention provides a schematic diagram of the structure of an IoT-based phase-commutation equipment site selection, capacity planning, and management system. This embodiment is applicable to site selection, capacity planning, and management of trial-operated phase-commutation equipment. The system can be implemented in hardware and / or software.

[0053] like Figure 1 As shown, the commutation equipment site selection and capacity planning and management system based on the Internet of Things includes a data acquisition module 101, an analysis and decision module 102, and a geographic information system module 103, wherein:

[0054] The data acquisition module is used to collect initial data of the trial-operation commutation device, wherein the initial data includes operation data of the trial-operation commutation device, environmental data of the target area where the trial-operation commutation device is located, and geographical location information;

[0055] The analysis and decision-making module is configured to mine and analyze the initial data using a machine learning algorithm to obtain the operating status and predicted failure trend of the trial-operated commutation equipment, and optimize alternative site selection and sizing solutions based on the environmental data, the operating status, and the predicted failure trend to obtain an optimized site selection and sizing solution;

[0056] The geographic information system module is used to perform spatial analysis on the optimized site selection and capacity determination plan to obtain fusion information of the optimized site selection and capacity determination plan and the geographical location;

[0057] The emergency response module is used to monitor the operating data of the trial-operation commutation equipment in real time and execute a corresponding preset emergency response mechanism according to the operating data;

[0058] The visualization display module is used to visualize the changes in the operating data of the trial-operation commutation device and the fusion information.

[0059] Specifically, the data acquisition module, the analysis and decision-making module and the geographic information system module are connected by electrical signals.

[0060] The data acquisition module pre-deploys various sensors and RFID tags as data collection terminals to collect initial data from the trial commutation equipment and its surrounding environment. This includes operational data (such as current, voltage, temperature, and vibration), environmental data (such as ambient temperature, humidity, air pressure, and air quality), and geographic location information. This setup enables remote monitoring and real-time data collection, reduces the frequency of manual inspections, improves monitoring efficiency, ensures comprehensiveness and accuracy, and provides a solid foundation for subsequent analysis.

[0061] The analysis and decision-making module is used to integrate the initial data obtained after preprocessing, use machine learning algorithms to mine and analyze the initial data, evaluate the operating status of the trial commutation equipment and predict failure trends, and optimize the site selection and sizing plan based on environmental data, operating status and predicted failure trends, thereby improving the accuracy and scientific nature of site selection and sizing, and reducing planning errors and cost waste caused by environmental factors;

[0062] The geographic information system module is used to integrate geographic information, combine the optimized site selection and capacity determination plan with the geographical location, conduct spatial analysis, assist in the geographical location selection, and improve the accuracy and efficiency of planning.

[0063] Optionally, the IoT-based commutation equipment site selection and capacity planning and management system may also include:

[0064] The emergency response module is used to monitor the operating status of equipment in real time, detect abnormalities and faults, trigger alarm mechanisms, initiate emergency response processes, promptly identify and address potential problems, reduce the impact of faults on system operations, and ensure safe and stable operation of the power grid;

[0065] The visualization display module is used to display the operating status of the trial-run commutation equipment, environmental data changes, and the site selection and capacity planning results in the optimized site selection and capacity planning plan in the form of charts, etc., to facilitate management personnel's understanding and decision-making, improve information transparency, and enhance decision-making support capabilities.

[0066] The IoT-based phase-commutation equipment site selection and sizing planning and management system provided in the embodiment of the present invention provides accurate data support for the site selection and sizing of trial-operation phase-commutation equipment by acquiring the operating data, environmental data, and geographic location information of the trial-operation phase-commutation equipment, and utilizes a machine learning algorithm to identify the operating status and predict failure trends, thereby helping to identify potential risk points and optimization opportunities. Thus, various factors that may affect the performance of the trial-operation phase-commutation equipment can be obtained in the site selection and sizing planning stage, the advantages and disadvantages of different site selection schemes can be evaluated, and the accuracy and scientific nature of the site selection and sizing planning can be improved.

[0067] Example 2

[0068] Figure 2 This is a structural diagram of a phase-changing equipment site selection and sizing planning and management system based on the Internet of Things provided in Example 2 of the present invention. The system of the embodiment of the present invention is further optimized on the basis of the above system, and provides a specific method for site selection, sizing planning and management of trial-operated phase-changing equipment.

[0069] like Figure 2 As shown, the system includes a data acquisition module 201, a data transmission processing module 202, an analysis and decision module 203, a geographic information system module 204, an emergency response module 205 and a visualization display module 206, and a planning management platform 207 that is communicatively connected to the above modules, wherein the geographic information system module 204, the emergency response module 205 and the visualization display module 206 are communicatively connected, and the analysis and decision module 203 and the geographic information system module 204 are communicatively connected.

[0070] Optionally, the data acquisition module is specifically configured to collect the initial data through a first sensor and an RFID tag pre-installed in the trial operation commutation device and a second sensor in a target area where the trial operation commutation device is located;

[0071] Among them, the first sensor includes a current sensor, a voltage sensor, a temperature sensor and a vibration sensor, and the second sensor includes a temperature and humidity sensor and an air pressure sensor to obtain environmental data. The operating data in the initial data includes current, voltage, temperature and vibration data, and the environmental data in the initial data includes ambient temperature, humidity and air pressure data.

[0072] Specifically, current sensors, voltage sensors, temperature sensors, and vibration sensors can be installed on the trial-operation commutation equipment, allowing the data acquisition module to monitor the operating data of the trial-operation commutation equipment in real time. Temperature, humidity, and air pressure sensors can be placed in the surrounding environment of the trial-operation commutation equipment to enable the data acquisition module to obtain environmental data. RFID tags can also be deployed on the trial-operation commutation equipment to enable the data acquisition module to identify the trial-operation commutation equipment. By combining the various sensors installed on the trial-operation commutation equipment, the data acquisition module can obtain the equipment's operating data and location information. The operating data includes current, voltage, temperature, and vibration data, and the environmental data includes ambient temperature, humidity, and air pressure data. The data collected by the sensors is preprocessed, including data verification, filtering, denoising, and data compression.

[0073] Optionally, the system further includes a planning management platform and a data transmission processing module, wherein:

[0074] The data transmission processing module is used to pre-process the initial data before the analysis and decision module uses the machine learning algorithm to mine and analyze the initial data, so as to obtain pre-processed initial data, and transmit the pre-processed initial data to the planning management platform via the wireless network, wherein the pre-processing includes data cleaning, compression and encryption;

[0075] The planning management platform includes:

[0076] a storage and classification unit, configured to store the initial data in a pre-established distributed database, and classify the initial data stored in the distributed database according to data type, timestamp, and sensor identification dimension to obtain classified initial data;

[0077] The index creation and backup unit is used to create an index for the classified initial data and implement a preset data recovery mechanism by backing up the data in the distributed database at preset time intervals.

[0078] Specifically, the data transmission processing module is used to perform preliminary data cleaning, compression, and encryption processing to ensure the security and efficient transmission of data, ensure the stability and security of data transmission, reduce losses and interference during data transmission, and improve data quality and transmission efficiency. The data transmission processing module can decode the data of the RFID tag, read the information recorded in the tag, timestamp the processed data, and synchronize it with the real-time status of the trial-run commutation equipment to ensure the timing and traceability of the data. The data transmission processing module can encapsulate the pre-processed data, specifically including timestamp, sensor identification, and data type information. The encapsulated data is encrypted using an encryption algorithm to ensure the security of the data during transmission, and is transmitted to the planning management platform via a wireless network (such as Wi-Fi, 4G / 5G or LoRa, etc.). Encryption technology is used to ensure the security of the data and prevent data leakage or tampering.

[0079] The planning and management platform can classify, store, and back up the collected data, and provide a data query interface to facilitate the long-term preservation and rapid retrieval of data, facilitating data analysis. The planning and management platform can establish a distributed database to support the rapid storage and retrieval of large-scale data. After the planning and management platform receives the pre-processed data, it stores it in a distributed database. By classifying the data stored in the distributed database according to the data type, timestamp, and sensor identification dimensions, and indexing the classified data, this setting can improve data query efficiency. Regularly backing up data in the distributed database can prevent data loss or damage, and by setting up a data recovery mechanism, it can ensure that data can be quickly restored in the event of data loss or damage;

[0080] Optionally, the system further includes:

[0081] a data set generation module, configured to obtain historical fault records and maintenance logs, perform standardization on the initial data to obtain processed data in a unified format, and then integrate the processed data to obtain a data set, before performing mining and analysis on the initial data using a machine learning algorithm to obtain the operating status of the trial commutation device and predict the fault trend;

[0082] a feature data set generation module, configured to extract target features from the data set and integrate the target features with the fault features in the historical fault records to obtain a feature data set comprising a training set and a test set, wherein the target features include equipment operation features, environmental features, and abnormal fault features;

[0083] An index determination module, configured to determine an equipment operation evaluation index, an environmental interference index, and a fault diagnosis index using the data set;

[0084] A model building module, configured to build an anomaly classification model based on a neural network model using the feature data set and a machine learning algorithm;

[0085] an abnormality level and threshold preset module, configured to determine an abnormality assessment coefficient using the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index, and to preset an abnormal operation level and a corresponding abnormality threshold using the abnormality assessment coefficient and the historical fault records;

[0086] Wherein, the analysis and decision-making module includes:

[0087] a state and trend determination unit, configured to obtain the operation state and predicted fault trend of the trial-operation commutation device based on the abnormal operation level and the abnormal threshold, using the abnormal classification model and performing mining analysis on the initial data;

[0088] A site selection and sizing scheme optimization unit is used to optimize alternative site selection and sizing schemes using the environmental data and operating status in the data set and the predicted failure trend to obtain an optimized site selection and sizing scheme.

[0089] Specifically, the dataset generation module can extract operational and environmental data within a fixed analysis cycle, obtain historical fault records and maintenance logs, convert data from different sources and formats into a unified format, perform standardization, and integrate the acquired data to form a unified dataset for subsequent analysis. Historical fault records include fault type, fault time, fault frequency, and repair cost.

[0090] The feature data set generation module can extract target features for evaluating the operating status of commutation equipment and predicting fault trends from the data set, specifically including equipment operating features and environmental features. The feature data set generation module can mark the (abnormal) fault features in the historical fault records, merge them with the target features to obtain a feature data set for model training, and divide the feature data set into two subsets, namely a training set and a test set. Among them, extracting target features for evaluating the operating status of commutation equipment and predicting fault trends from the data set includes: performing feature analysis on the operating data to obtain equipment operating features such as current features, voltage features, temperature features, and vibration features; performing feature analysis on the environmental data to obtain environmental features such as ambient temperature features, humidity features, and air pressure features. Fault features include fault time features, fault frequency features, and maintenance cost features associated with the fault type.

[0091] The index determination module can analyze the operating data in the data set, calculate the equipment operation evaluation index, analyze the operating status and trend of the commutation equipment, and analyze the environmental data of the same fixed analysis period in the data set to calculate the environmental interference index. It can analyze the changing trend of the environment around the commutation equipment and then calculate the fault diagnosis index based on the operating data, environmental data and fault characteristics.

[0092] The model building module can use machine learning algorithms to combine the equipment operation characteristics, environmental characteristics and fault characteristics in the feature data set to build an anomaly classification model based on the neural network model, and use the relevant data of the test set to test and analyze the anomaly classification model.

[0093] The abnormality level and threshold preset module can use the equipment operation evaluation index, environmental interference index and fault diagnosis index to obtain the abnormality evaluation coefficient, analyze the operating status of the commutation equipment, and preset the abnormal operation level and its corresponding abnormality threshold based on the abnormality evaluation coefficient and historical fault records.

[0094] The analysis and decision-making module can use the trained anomaly classification model to analyze the real-time data of the commutation equipment, assess the current operating status of the commutation equipment, identify early signs of performance degradation and anomalies in the commutation equipment, and predict failure trends. Specifically, this includes: combining collected environmental data to analyze the impact of different environmental data on the operation of the commutation equipment, using the anomaly classification model to assess the operating status of the commutation equipment, analyzing candidate site selection and sizing solutions based on the abnormal operation level and its corresponding anomaly threshold, and comprehensively evaluating the advantages and disadvantages of each solution to optimize the site selection and sizing solution;

[0095] Furthermore, determining the equipment operation evaluation index and the environmental interference index using the data set includes:

[0096] Determine a current deviation index, a voltage deviation index, a temperature deviation index, and a vibration deviation index respectively using the measured values ​​and reference values ​​of the current characteristics, voltage characteristics, temperature characteristics, and vibration characteristics in the data set, and determine an equipment operation evaluation index using the current deviation index, the voltage deviation index, the temperature deviation index, and the vibration deviation index;

[0097] The measured values ​​and reference values ​​of the temperature characteristics, humidity characteristics, and air pressure characteristics in the data set are used to determine the ambient temperature deviation index, humidity deviation index, and air pressure deviation index, respectively, and the ambient temperature deviation index, humidity deviation index, and air pressure deviation index are used to determine the environmental interference index.

[0098] Exemplary methods for determining the equipment operation evaluation index include:

[0099] EA=P C ×PV ×P T ×P R ;

[0100]

[0101] Among them, EA is the equipment operation evaluation index, P C is the current deviation index, P V is the voltage deviation index, P T is the temperature deviation index, P R is the vibration deviation index, C i is the current value of the i-th measurement cycle, V i is the voltage value of the i-th measurement cycle, T i is the temperature value of the i-th measurement cycle, R i is the vibration value of the i-th measurement cycle, C base is the reference value of the current, V base is the reference value of voltage, T base is the reference value of temperature, R base is the vibration baseline value, and n is the total number of measurement cycles. When the commutation device's operating data is close to its baseline value, the EA tends to be smaller, indicating healthy device operation. When the commutation device's operating data deviates significantly from the baseline, the EA tends to be larger, indicating a potential device problem. By calculating the sum of the squares of each data point's deviation from its baseline value, the degree of data deviation is assessed and data deviating from the normal operating range can be identified. The influence of vibration data is introduced as a score. The greater the vibration deviation, the closer the score is to 1, indicating a smaller contribution to the EA.

[0102] The environmental interference index is determined by:

[0103] EI=P E ×P W ×P P ;

[0104]

[0105] Among them, EI is the environmental interference index, P E is the ambient temperature deviation index, P W is the humidity deviation index, P P is the pressure deviation index, E i is the ambient temperature value of the i-th measurement cycle, W i is the ambient humidity value of the i-th measurement cycle, P i is the ambient pressure value of the i-th measurement cycle, E base is the reference value of the ambient temperature, W base is the reference value of ambient humidity, P baseis the reference value of ambient pressure, σ E is the standard deviation of the ambient temperature, σ W is the standard deviation of ambient humidity, and n is the total number of measurement cycles. The EI value range is between 0 and 1. When the ambient data is close to its baseline value, the EI tends to 1, indicating that the ambient interference is small and the environment is stable. When the ambient data deviates significantly from the baseline value, the EI tends to 0, indicating that the ambient interference is large and the environment changes drastically. Use the exponential function By simulating the Gaussian distribution characteristics of humidity deviation from the baseline value, the significance of humidity changes can be evaluated. In this form, the nonlinear effect of air pressure change on the environmental interference index is simulated.

[0106] Furthermore, determining a fault diagnosis index using the data set includes:

[0107] Determine the baseline values ​​of the failure time feature, the failure frequency feature, and the maintenance cost feature respectively by using the associated data of the failure time feature, the failure frequency feature, and the maintenance cost feature in the data set;

[0108] The reference values ​​are used to determine a failure time deviation, a failure frequency deviation, and a maintenance cost deviation, respectively, and a failure diagnosis index is determined using the failure time deviation, the failure frequency deviation, and the maintenance cost deviation.

[0109] Furthermore, the determining of an abnormality assessment coefficient using the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index includes:

[0110] An abnormality assessment coefficient is determined by performing a weighted sum operation on the equipment operation assessment index, the environmental interference index, and the fault diagnosis index.

[0111] Exemplarily, the fault diagnosis index and the abnormality assessment coefficient are determined in the following manner:

[0112]

[0113] Among them, AP is the abnormal assessment coefficient, EA is the equipment operation evaluation index, EI is the environmental interference index, PI is the fault diagnosis index, which reflects the fault condition of the equipment, TF is the fault time, FF is the fault frequency, MC is the maintenance cost, TF is the fault time, FF is the fault frequency, MC is the maintenance cost, TF is the fault time, FF is the fault frequency, MC is the maintenance cost, TF is the fault time, FF is the fault frequency, MC is the maintenance cost, TF is the fault time, TF is the fault frequency, MC is the maintenance cost, TF is the fault frequency, MC is the maintenance cost, TF is the fault time, FF is the fault frequency, MC is the maintenance cost, TF is the fault frequency, MC is the maintenance cost, TF is the fault frequency, TF is the fault frequency, MC is the maintenance cost, TF is the fault time, TF is the fault frequency, MC is the maintenance cost, TF is the fault frequency ... base , FF base and MC base are the baseline values ​​of failure time, frequency and maintenance cost respectively, σ TFis the standard deviation of the failure time, and w1, w2, and w3 are weighting factors used to adjust the relative importance of EA, EI, and PI in the AP calculation. A lower AP value indicates good device operation, a stable environment, and minimal fault characteristics. A higher AP value indicates possible operational issues, significant environmental interference, or significant fault characteristics. EA, EI, and PI are weighted using the weighting factors w1, w2, and w3, respectively, to reflect their relative importance in the overall assessment. PI values ​​range from 0 or greater, with 0 indicating no deviation, meaning the device is operating normally. Larger PI values ​​indicate a greater deviation from the normal baseline and a higher risk of failure.

[0114] Optionally, the geographic information system module includes:

[0115] a database generation unit, configured to collect geographic information data related to the optimized site selection and capacity determination plan, and generate a geographic database using the geographic information data, wherein the geographic information data includes topography, land use status, transportation network, and hydrological information;

[0116] A processing unit, configured to clean, convert, standardize, and vectorize the geographic information data in the geographic database to obtain reference geographic data;

[0117] An analysis unit, configured to perform a multi-geographic layer overlay analysis on the optimized site selection and capacity determination plan using a geographic information system (GIS) and reference geographic data in the geographic database to obtain an analysis result;

[0118] A fusion information generating unit is used to determine the fusion information of the optimized site selection and capacity determination plan and the geographical location using the analysis results.

[0119] Specifically, the database generation unit collects geographic information data from various sources related to optimizing site selection and sizing plans to form a geographic database, providing data support for subsequent spatial analysis. Geographic information data specifically includes topography, land use status, transportation networks, and hydrological information. Sources include satellite remote sensing, drone aerial photography, GPS positioning, and ground measurement data.

[0120] The processing unit can clean, convert and standardize the collected geographic information data to ensure the consistency and accuracy of the data, and vectorize the geographic information data to facilitate subsequent analysis and processing by the geographic information system (GIS).

[0121] The analysis unit can use the geographic information system GIS and the reference geographic data in the geographic database to perform spatial analysis on the geographic location information of the optimized site selection and capacity determination plan, overlay the plan with various layers in the geographic database for analysis, set a buffer zone for the site selection point, analyze the environmental influencing factors within the buffer zone, and combine the site selection and capacity determination plan with the geographic information to obtain fusion information of the optimized site selection and capacity determination plan and the geographic location.

[0122] Furthermore, the abnormal operation level includes a low abnormal operation level, a medium abnormal operation level, and a high abnormal operation level, and the abnormal threshold includes an upper threshold and a lower threshold.

[0123] For example, the abnormal operation level and the abnormal threshold may satisfy the following relationship:

[0124] When AP≤AP MY When , it is a low abnormal operation level;

[0125] When AP MY <AP≤AP HY When , it is the medium abnormal operation level;

[0126] When AP>AP HY When , it is a high abnormal operation level.

[0127] Among them, AP is the abnormal assessment coefficient, AP MY is the upper threshold corresponding to the low abnormal operation level and the lower threshold corresponding to the medium abnormal operation level, AP HY The upper threshold corresponding to the medium abnormal operation level and the lower threshold corresponding to the high abnormal operation level.

[0128] Furthermore, the emergency response module includes:

[0129] an abnormality and fault information determining unit, configured to analyze the operating data of the trial-operation commutation device using the abnormality assessment coefficient to determine abnormality and fault information, and send the abnormality and fault information to the alarm information generating unit, wherein the abnormality and fault information includes a target abnormal operation level;

[0130] an alarm information generating unit, configured to generate and issue an alarm message by triggering a first preset emergency response mechanism upon receiving the abnormality and fault information sent by the abnormality and fault information determining unit;

[0131] The emergency response unit is used to execute a corresponding second preset emergency response mechanism according to the target abnormal operation level and the alarm information.

[0132] Specifically, the abnormality and fault information determination unit can be integrated into various sensors and monitoring devices in the power grid equipment to collect the operating status data of the phase-commutating equipment in real time and transmit the data to the planning and management platform through the Internet of Things. It can also be combined with the abnormality assessment coefficient to analyze the operating status of the phase-commutating equipment, compare the operating data with the corresponding abnormality threshold, and identify abnormality and fault information.

[0133] If the alarm information generating unit receives the abnormality and fault information sent by the abnormality and fault information determining unit, it generates and sends the alarm information by triggering the first preset emergency response mechanism, such as sending it to relevant personnel through text messages and mobile applications.

[0134] The emergency response unit can combine the abnormal operation level to start the emergency response process corresponding to the current target abnormal operation level, and match the corresponding emergency plan according to the alarm information and operation status, and execute the corresponding second preset emergency response mechanism to promptly discover and deal with potential problems.

[0135] The IoT-based phase-changing equipment site selection and sizing planning and management system provided by the embodiment of the present invention deploys various sensors to collect equipment operating data and combines it with machine learning algorithms. It can not only evaluate the current status of the equipment in real time, but also predict potential failure trends and realize predictive maintenance. It can reduce unexpected downtime, reduce maintenance costs, and improve the operating efficiency and life of the equipment. By comprehensively considering equipment operating data, environmental data and historical failure data, it provides the optimal solution for site selection and sizing planning, analyzes the cost-effectiveness of different site selection solutions, and effectively reduces construction and operating costs.

[0136] Example 3

[0137] Figure 3 A flowchart of a method for site selection, sizing, planning and management of phase-commutation equipment based on the Internet of Things is provided for the third embodiment of the present invention. This embodiment is applicable to the site selection, sizing, planning and subsequent management of phase-commutation equipment.

[0138] like Figure 3 As shown, the third embodiment of the present invention provides a method for site selection, capacity planning and management of commutation equipment based on the Internet of Things, which specifically includes the following steps:

[0139] S301. Collect initial data of a trial-operation commutation device, wherein the initial data includes operation data of the trial-operation commutation device, environmental data of a target area where the trial-operation commutation device is located, and geographical location information.

[0140] S302. Use a machine learning algorithm to mine and analyze the initial data to obtain the operating status and predicted fault trend of the trial-operated commutation equipment, and optimize alternative site selection and sizing plans based on the environmental data in the initial data, the operating status and the predicted fault trend to obtain an optimized site selection and sizing plan.

[0141] S303: Perform spatial analysis on the optimized site selection and capacity determination plan to obtain fusion information of the optimized site selection and capacity determination plan and the geographical location.

[0142] The technical solution of the embodiment of the present invention provides accurate data support for the site selection and sizing of the trial operation phase-changing equipment by obtaining the operating data, environmental data and geographical location information of the phase-changing equipment, and uses a machine learning algorithm to identify the operating status and predict the failure trend, which helps to identify potential risk points and optimization opportunities. Therefore, various factors that may affect the performance of the trial operation phase-changing equipment can be obtained in the site selection and sizing planning stage, the advantages and disadvantages of different site selection schemes can be evaluated, and the accuracy and scientific nature of the site selection and sizing planning can be improved.

[0143] Optionally, the collecting of initial data of the trial operation commutation device includes:

[0144] The initial data is collected by a first sensor and an RFID tag pre-installed in the trial operation commutation device and a second sensor in the target area where the trial operation commutation device is located; wherein the first sensor includes a current sensor, a voltage sensor, a temperature sensor and a vibration sensor, and the second sensor includes a temperature and humidity sensor and an air pressure sensor to obtain environmental data, the operating data in the initial data includes current, voltage, temperature and vibration data, and the environmental data in the initial data includes ambient temperature, humidity and air pressure data.

[0145] Optionally, the above method further includes:

[0146] Before mining and analyzing the initial data using a machine learning algorithm, preprocessing the initial data to obtain preprocessed initial data, and transmitting the preprocessed initial data to the planning management platform via a wireless network;

[0147] The planning management platform is used to:

[0148] The initial data is stored in a pre-established distributed database, and the initial data stored in the distributed database is classified according to the data type, timestamp and sensor identification dimension to obtain the classified initial data; an index is established for the classified initial data, and a preset data recovery mechanism is implemented by backing up the data in the distributed database at preset time intervals.

[0149] Optionally, the above method further includes:

[0150] Before using the machine learning algorithm to mine and analyze the initial data to obtain the operating status and predicted fault trend of the trial-operated commutation equipment, historical fault records and maintenance logs are obtained, and the initial data are standardized to obtain processed data in a unified format, and the processed data are then integrated to obtain a data set; target features are extracted from the data set, and the target features and the fault features in the historical fault records are integrated to obtain a feature data set including a training set and a test set, wherein the target features include equipment operating features and environmental features; the data set is used to determine an equipment operation evaluation index, an environmental interference index, and a fault diagnosis index; the feature data set and the machine learning algorithm are used to construct an abnormality classification model based on a neural network model; the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index are used to determine an abnormality evaluation coefficient, and the abnormal operation level and the corresponding abnormality threshold are preset using the abnormality evaluation coefficient and the historical fault records;

[0151] The method of mining and analyzing the initial data using a machine learning algorithm to obtain the operating status and predicted failure trend of the trial-operated commutation equipment, and optimizing alternative site selection and sizing solutions based on the environmental data in the initial data, the operating status, and the predicted failure trend to obtain an optimized site selection and sizing solution, includes:

[0152] Based on the abnormal operation level and the abnormal threshold, the abnormal classification model and the initial data are used to mine and analyze the operating status and predicted fault trend of the trial operation commutation equipment; the environmental data and operating status in the data set and the predicted fault trend are used to optimize the alternative site selection and sizing scheme to obtain the optimized site selection and sizing scheme.

[0153] Furthermore, determining the equipment operation evaluation index and the environmental interference index using the data set includes:

[0154] The current deviation index, voltage deviation index, temperature deviation index and vibration deviation index are determined respectively by using the measured values ​​and reference values ​​of the current characteristics, voltage characteristics, temperature characteristics and vibration characteristics in the data set, and the equipment operation evaluation index is determined by using the current deviation index, the voltage deviation index, the temperature deviation index and the vibration deviation index; the ambient temperature deviation index, humidity deviation index and air pressure deviation index are determined respectively by using the measured values ​​and reference values ​​of the temperature characteristics, humidity characteristics and air pressure characteristics in the data set, and the environmental interference index is determined by using the ambient temperature deviation index, the humidity deviation index and the air pressure deviation index.

[0155] Furthermore, determining a fault diagnosis index using the data set includes:

[0156] Using the associated data of the failure time characteristics, failure frequency characteristics and maintenance cost characteristics in the data set, the baseline values ​​of the failure time characteristics, failure frequency characteristics and maintenance cost characteristics are determined respectively; using the baseline values, the failure time deviation, failure frequency deviation and maintenance cost deviation are determined respectively, and the failure diagnosis index is determined using the failure time deviation, the failure frequency deviation and the maintenance cost deviation.

[0157] Furthermore, the use of the equipment operation evaluation index, the environmental interference index and the fault diagnosis index to determine the abnormality evaluation coefficient includes: determining the abnormality evaluation coefficient by performing a weighted sum operation on the equipment operation evaluation index, the environmental interference index and the fault diagnosis index.

[0158] Optionally, the performing of spatial analysis on the optimized site selection and capacity determination plan to obtain fusion information of the optimized site selection and capacity determination plan and the geographical location includes:

[0159] Collect geographic information data related to the optimized site selection and sizing plan, and use the geographic information data to generate a geographic database, wherein the geographic information data includes topography, land use status, transportation network and hydrological information; clean, format-convert, standardize and vectorize the geographic information data in the geographic database to obtain reference geographic data; use a geographic information system (GIS) and the reference geographic data in the geographic database to perform a multi-geographic layer overlay analysis on the optimized site selection and sizing plan to obtain analysis results; use the analysis results to determine the fusion information of the optimized site selection and sizing plan and the geographic location.

[0160] Furthermore, the abnormal operation level includes a low abnormal operation level, a medium abnormal operation level, and a high abnormal operation level, and the abnormal threshold includes an upper threshold and a lower threshold.

Claims

1. A commutation equipment site selection and capacity planning and management system based on the Internet of Things, characterized by: include: a data acquisition module, configured to collect initial data of the trial-operation commutation device, wherein the initial data includes operation data of the trial-operation commutation device, environmental data of the target area where the trial-operation commutation device is located, and geographical location information; an analysis and decision-making module, configured to mine and analyze the initial data using a machine learning algorithm to obtain an operating status and predicted failure trend of the trial-operated commutation equipment, and optimize alternative site selection and sizing plans based on environmental data in the initial data, the operating status, and the predicted failure trend to obtain an optimized site selection and sizing plan; A geographic information system module is used to perform spatial analysis on the optimized site selection and capacity determination plan to obtain fusion information of the optimized site selection and capacity determination plan and the geographical location; The system further comprises: a data set generation module, configured to obtain historical fault records and maintenance logs, perform standardization on the initial data to obtain processed data in a unified format, and then integrate the processed data to obtain a data set, before performing mining and analysis on the initial data using a machine learning algorithm to obtain the operating status of the trial commutation device and predict the fault trend; a feature data set generation module, configured to extract target features from the data set and integrate the target features with the fault features in the historical fault records to obtain a feature data set comprising a training set and a test set, wherein the target features include equipment operation features and environmental features; An index determination module, configured to determine an equipment operation evaluation index, an environmental interference index, and a fault diagnosis index using the data set; A model building module, configured to build an anomaly classification model based on a neural network model using the feature data set and a machine learning algorithm; an abnormality level and threshold preset module, configured to determine an abnormality assessment coefficient using the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index, and to preset an abnormal operation level and a corresponding abnormality threshold using the abnormality assessment coefficient and the historical fault records; Wherein, the analysis and decision-making module includes: a state and trend determination unit, configured to mine and analyze the initial data using the abnormality classification model based on the abnormal operation level and the abnormality threshold, so as to obtain the operation state and predicted fault trend of the trial-operation commutation device; A site selection and sizing scheme optimization unit is used to optimize alternative site selection and sizing schemes using the environmental data and operating status in the data set and the predicted failure trend to obtain an optimized site selection and sizing scheme.

2. The system according to claim 1, wherein: The data acquisition module is specifically configured to collect the initial data through a first sensor and an RFID tag pre-installed in the trial operation commutation device and a second sensor in a target area where the trial operation commutation device is located; Among them, the first sensor includes a current sensor, a voltage sensor, a temperature sensor and a vibration sensor, and the second sensor includes a temperature and humidity sensor and an air pressure sensor to obtain environmental data. The operating data in the initial data includes current, voltage, temperature and vibration data, and the environmental data in the initial data includes ambient temperature, humidity and air pressure data.

3. The system according to claim 1, wherein: The system also includes a planning management platform and a data transmission processing module, wherein: The data transmission processing module is used to pre-process the initial data before the analysis and decision module uses the machine learning algorithm to mine and analyze the initial data, so as to obtain pre-processed initial data and transmit it to the planning management platform via a wireless network; The planning management platform includes: a storage and classification unit, configured to store the initial data in a pre-established distributed database, and classify the initial data stored in the distributed database according to data type, timestamp, and sensor identification dimension to obtain classified initial data; The index creation and backup unit is used to create an index for the classified initial data and implement a preset data recovery mechanism by backing up the data in the distributed database at preset time intervals.

4. The system according to claim 1, wherein: Determining an equipment operation evaluation index and an environmental interference index using the data set includes: Determine a current deviation index, a voltage deviation index, a temperature deviation index, and a vibration deviation index respectively using the measured values ​​and reference values ​​of the current characteristics, voltage characteristics, temperature characteristics, and vibration characteristics in the data set, and determine an equipment operation evaluation index using the current deviation index, the voltage deviation index, the temperature deviation index, and the vibration deviation index; The measured values ​​and reference values ​​of the temperature characteristics, humidity characteristics, and air pressure characteristics in the data set are used to determine the ambient temperature deviation index, humidity deviation index, and air pressure deviation index, respectively, and the ambient temperature deviation index, humidity deviation index, and air pressure deviation index are used to determine the environmental interference index.

5. The system according to claim 1, wherein: Determining a fault diagnosis index using the data set includes: Determining the baseline values ​​of the failure time feature, the failure frequency feature, and the maintenance cost feature respectively by using the associated data of the failure time feature, the failure frequency feature, and the maintenance cost feature in the data set; The reference values ​​are used to determine a failure time deviation, a failure frequency deviation, and a maintenance cost deviation, respectively, and a failure diagnosis index is determined using the failure time deviation, the failure frequency deviation, and the maintenance cost deviation.

6. The system according to claim 1, wherein: The determining of an abnormality assessment coefficient by using the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index includes: An abnormality assessment coefficient is determined by performing a weighted sum operation on the equipment operation assessment index, the environmental interference index, and the fault diagnosis index.

7. The system according to claim 1, wherein: The geographic information system module includes: a database generation unit, configured to collect geographic information data related to the optimized site selection and capacity determination plan, and generate a geographic database using the geographic information data, wherein the geographic information data includes topography, land use status, transportation network, and hydrological information; A processing unit, configured to clean, convert, standardize, and vectorize the geographic information data in the geographic database to obtain reference geographic data; An analysis unit, configured to perform a multi-geographic layer overlay analysis on the optimized site selection and capacity determination plan using a geographic information system (GIS) and reference geographic data in the geographic database to obtain an analysis result; A fusion information generating unit is used to determine the fusion information of the optimized site selection and capacity determination plan and the geographical location using the analysis results.

8. The system according to claim 1, wherein: The abnormal operation level includes a low abnormal operation level, a medium abnormal operation level, and a high abnormal operation level, and the abnormal threshold includes an upper threshold and a lower threshold.

9. A method for site selection and capacity planning and management of commutation equipment based on the Internet of Things, characterized in that: include: Collecting initial data of the trial-operation phase-changing device, wherein the initial data includes operation data of the trial-operation phase-changing device, environmental data of a target area where the trial-operation phase-changing device is located, and geographical location information; Using a machine learning algorithm to mine and analyze the initial data to obtain the operating status and predicted failure trend of the trial-operated commutation equipment, and optimizing alternative site selection and sizing plans based on environmental data in the initial data, the operating status, and the predicted failure trend to obtain an optimized site selection and sizing plan; Performing spatial analysis on the optimized site selection and capacity determination plan to obtain integrated information of the optimized site selection and capacity determination plan and the geographical location; The method further comprises: Before using a machine learning algorithm to mine and analyze the initial data to obtain the operating status of the trial-operated commutation equipment and predict the fault trend, historical fault records and maintenance logs are obtained, and the initial data are standardized to obtain processed data in a unified format, and the processed data are then integrated to obtain a data set; Extracting target features from the data set, and integrating the target features with fault features in the historical fault records to obtain a feature data set comprising a training set and a test set, wherein the target features include equipment operation features and environmental features; Determining an equipment operation evaluation index, an environmental interference index, and a fault diagnosis index using the data set; Using the feature data set and machine learning algorithm to build an anomaly classification model based on a neural network model; Determine an abnormality assessment coefficient using the equipment operation evaluation index, the environmental interference index, and the fault diagnosis index, and preset an abnormal operation level and a corresponding abnormality threshold using the abnormality assessment coefficient and the historical fault records; The method of mining and analyzing the initial data using a machine learning algorithm to obtain the operating status and predicted failure trend of the trial-operated commutation equipment, and optimizing alternative site selection and sizing solutions based on the environmental data in the initial data, the operating status, and the predicted failure trend to obtain an optimized site selection and sizing solution, includes: Based on the abnormal operation level and the abnormal threshold, the initial data is mined and analyzed using the abnormal classification model to obtain the operating status and predicted fault trend of the trial operation commutation equipment; the environmental data and operating status in the data set and the predicted fault trend are used to optimize the alternative site selection and sizing scheme to obtain the optimized site selection and sizing scheme.

Images