Intelligent flexible regulation and control terminal loop inspection method

Abstract

The invention relates to the technical field of power system monitoring, and discloses an intelligent flexible regulation and control terminal loop inspection method, which comprises the following steps: collecting related parameter data on a secondary loop in real time, the related parameter data comprising a current signal and environmental data; data preprocessing is carried out on the current signal, the preprocessing comprises filtering processing and data correction, and features of the current signal and the environment data are extracted; determining and outputting an anomaly detection result based on the extracted feature data through a trained machine learning model; and the intelligent flexible regulation and control terminal judges an abnormal state level based on the abnormal detection result and executes a corresponding early warning regulation and control strategy. According to the invention, through fusion of multiple technologies and means such as real-time data acquisition, intelligent analysis and automatic response, intelligent monitoring and regulation of the state of the secondary circuit are realized, and powerful support is provided for safe and stable operation of a power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring, and in particular to an intelligent flexible control terminal loop inspection method. Background Art

[0002] In power systems, the stability and reliability of secondary circuits are crucial to ensuring their safe operation. Secondary circuits primarily control, protect, and measure the status of primary equipment. Therefore, any failure or anomaly in these circuits could impact the normal operation of the entire power system. Traditional inspection methods rely primarily on periodic manual checks and fixed threshold alarms. This approach is not only inefficient but also makes it difficult to detect potential problems in a timely manner, potentially leading to escalation of failures and resulting in greater losses.

[0003] With the development of information technology, intelligent and automated technologies are increasingly being applied to the monitoring and maintenance of power systems. However, existing intelligent inspection solutions mostly focus solely on changes in current signals, ignoring the impact of environmental factors (such as temperature and humidity) on secondary circuits. This can lead to false alarms or missed alarms. Furthermore, traditional methods lack effective data analysis tools when processing complex data, making it difficult to accurately identify anomalies and respond quickly. Summary of the Invention

[0004] In view of this, the present invention proposes an intelligent flexible control terminal circuit inspection method. By integrating multiple technologies and means such as real-time data acquisition, intelligent analysis and automated response, it realizes intelligent monitoring and control of the secondary circuit status, providing strong support for the safe and stable operation of the power system.

[0005] In order to achieve the above objectives, in a first aspect, the present invention provides an intelligent flexible control terminal loop inspection method, comprising:

[0006] Real-time collection of relevant parameter data on the secondary circuit, including current signals and environmental data;

[0007] Performing data preprocessing on the current signal, the preprocessing including filtering and data correction, and extracting features of the current signal and the environmental data;

[0008] Through the trained machine learning model, based on the extracted feature data, the anomaly detection results are determined and output;

[0009] The intelligent flexible control terminal determines the abnormal state level based on the abnormality detection result and executes the corresponding early warning control strategy.

[0010] Preferably, the real-time collection of relevant parameter data on the secondary circuit includes current signals and environmental data, specifically:

[0011] The current signal on the secondary circuit is collected in real time by an external current transformer and a manganese copper sampling resistor installed on the secondary circuit;

[0012] Real-time monitoring and collection of environmental data through sensors, including temperature data and humidity data;

[0013] The collected environmental data and the current signal are recorded synchronously for subsequent comprehensive analysis.

[0014] Preferably, the current signal is subjected to data preprocessing, wherein the preprocessing includes filtering and data correction, and features of the current signal and the environmental data are extracted, specifically:

[0015] Performing filtering processing on the current signal based on the edge computing module, and performing data correction on the filtered current signal;

[0016] Extracting key features of the current signal, including frequency, amplitude, and phase, through digital signal processing technology;

[0017] The features of the environmental data are simultaneously extracted, including temperature change trends and humidity change trends.

[0018] Preferably, the trained machine learning model determines and outputs anomaly detection results based on the extracted feature data, specifically:

[0019] The abnormality detection results include the current fluctuation amplitude, the degree of shunting phenomenon, the degree of magnetic field change, the degree of increase in harmonic components, and the degree of temperature and humidity exceeding the standard;

[0020] Determining the current fluctuation amplitude by comparing the current current signal with a preset safety threshold;

[0021] Monitoring the change in current distribution and determining the extent of the shunting phenomenon by comparing the extent of the change in the current signal at different locations;

[0022] Monitoring the change in magnetic field intensity by a fluxgate sensor to determine the degree of change in the magnetic field;

[0023] Analyzing the harmonic components of the current waveform, extracting harmonic information through Fourier transform, and determining the degree of increase of the harmonic components;

[0024] The degree to which the temperature and humidity exceed the standard is determined by comparing the current temperature and humidity data with the preset range.

[0025] Preferably, the intelligent flexible control terminal determines the abnormal state level based on the abnormality detection result, specifically:

[0026] Any one of the abnormality detection results corresponds to a preset first threshold and a second threshold, and each of the first thresholds is smaller than the second threshold;

[0027] The current abnormality level is determined by comparing the abnormality detection results with their corresponding thresholds. The abnormality levels include slight abnormality, moderate abnormality and severe abnormality.

[0028] Preferably, the current abnormal state level is determined by comparing the abnormal detection results with their corresponding thresholds, specifically:

[0029] If any one of the abnormality detection results does not exceed the corresponding first threshold, then the current abnormality state level is determined to be the slight abnormality;

[0030] If any one of the abnormality detection results exceeds the corresponding first threshold but does not exceed the second threshold, the current abnormality level is determined to be the moderate abnormality;

[0031] If any one of the abnormality detection results exceeds the corresponding second threshold, the current abnormality state level is determined to be the severe abnormality.

[0032] Preferably, the execution of the corresponding early warning and control strategy is specifically:

[0033] When the abnormal state level is the minor abnormality, the first-level early warning strategy is executed, that is, the sound and light alarm is triggered and the abnormal data is recorded;

[0034] When the abnormal state level is the moderate abnormality, the secondary warning strategy is executed, that is, on the basis of the primary warning strategy, the operation and maintenance personnel are notified via SMS and email, and preliminary handling suggestions are provided;

[0035] When the abnormal state level is the serious abnormality, the third-level warning strategy is executed, that is, on the basis of the second-level warning strategy, the automatic protection measures are triggered again, and the automatic protection measures include cutting off the power supply, starting the backup circuit and starting the protection device.

[0036] In a second aspect, the present invention provides an intelligent flexible control terminal loop inspection system, comprising:

[0037] An acquisition module is used to collect relevant parameter data on the secondary circuit in real time, wherein the relevant parameter data includes current signals and environmental data;

[0038] a processing module, configured to perform data preprocessing on the current signal, wherein the preprocessing includes filtering and data correction, and extract features of the current signal and the environmental data;

[0039] The detection module is used to determine and output anomaly detection results based on the extracted feature data using a trained machine learning model;

[0040] An execution module is used for the intelligent flexible control terminal to judge the abnormal state level based on the abnormal detection result and execute the corresponding early warning control strategy.

[0041] Preferably, the acquisition module is specifically:

[0042] The current signal on the secondary circuit is collected in real time by an external current transformer and a manganese copper sampling resistor installed on the secondary circuit;

[0043] Real-time monitoring and collection of environmental data through sensors, including temperature data and humidity data;

[0044] The collected environmental data and the current signal are recorded synchronously for subsequent comprehensive analysis.

[0045] Preferably, the processing module is specifically:

[0046] Performing filtering processing on the current signal based on the edge computing module, and performing data correction on the filtered current signal;

[0047] Extracting key features of the current signal, including frequency, amplitude, and phase, through digital signal processing technology;

[0048] The features of the environmental data are simultaneously extracted, including temperature change trends and humidity change trends.

[0049] The embodiment of the present application discloses an intelligent flexible control terminal loop inspection method. This method uses external current transformers, manganese copper sampling resistors, and various sensors installed in the secondary circuit to collect current signals and environmental data in real time, ensuring the continuity and timeliness of the inspection process and quickly detecting any abnormalities. Using preprocessing steps such as filtering, data correction, and key feature extraction, along with a trained machine learning model, it can accurately identify current fluctuation amplitude, the degree of shunting, magnetic field changes, the increase in harmonic components, and the degree of temperature and humidity exceeding standards, thereby improving the accuracy of anomaly detection. Based on the anomaly detection results, the system intelligently determines the abnormal state level and implements corresponding early warning and control strategies based on the different levels, including audible and visual alarms, notifications to operation and maintenance personnel, provision of treatment suggestions, and even automatic implementation of protective measures, thus achieving intelligent management and response. When a serious anomaly is detected, the system can immediately take action, such as cutting off power, activating backup circuits, or activating protective devices, minimizing the impact of the fault on the power system and improving the overall safety of the system. The simultaneous recording of environmental data and current signals facilitates subsequent comprehensive analysis, helping operation and maintenance personnel to have a more comprehensive understanding of the system status and formulate more scientific and reasonable maintenance plans, thereby improving operation and maintenance efficiency and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0051] Figure 1 A flowchart of an intelligent flexible control terminal loop inspection method provided by an embodiment of the present invention;

[0052] Figure 2 A schematic structural diagram of an intelligent flexible control terminal loop inspection system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0054] like Figure 1As shown, in some embodiments of the present application, this embodiment provides an intelligent flexible control terminal loop inspection method, specifically, the method includes the following steps:

[0055] Step S101: collect relevant parameter data on the secondary circuit in real time, wherein the relevant parameter data includes current signals and environmental data.

[0056] As mentioned above, various sensors and detection devices installed in the secondary circuit enable real-time collection of various parameter data related to the circuit. This parameter data includes not only current signals but also a range of environmental data such as temperature and humidity, ensuring comprehensive monitoring of the secondary circuit's operating status. Furthermore, the collected data needs to be timestamped to synchronize recording across different data sources, facilitating subsequent comprehensive analysis.

[0057] For example, suppose that in the secondary circuit of a substation, multiple current transformers are installed to monitor the current at each key node. For example, current transformers are installed at locations such as circuit breakers, disconnectors, and protective relays, so that the dynamic changes of the current in the entire secondary circuit can be captured. When a short circuit occurs somewhere, the corresponding current transformer will immediately detect the sharp rise in current and transmit this information to the intelligent flexible control terminal. Temperature sensors and humidity sensors are also arranged in important areas such as control rooms and switch cabinets to send the latest temperature and humidity readings to the intelligent flexible control terminal at regular intervals (such as every second or every minute). If the temperature in a certain area suddenly rises or the humidity exceeds the normal range, the system can issue an early warning in time to remind the operation and maintenance personnel to check whether there are problems such as overheating and humidity to prevent aging or failure of secondary circuit components.

[0058] It should be noted that in a specific implementation scenario, a multi-type sensor integration solution can be adopted on the basis of the above solution, that is, in addition to current transformers, manganese copper sampling resistors, temperature sensors and humidity sensors, other types of sensors can also be integrated, such as gas concentration sensors (for detecting SF6 gas leaks), smoke sensors (for fire warnings), light intensity sensors (for monitoring lighting conditions), etc. Through these additional sensors, a more comprehensive monitoring network can be built to further improve the safety and reliability of the system; an edge computing enhancement solution can be adopted, that is, in order to reduce data transmission delays and improve local processing capabilities, edge computing modules are deployed close to the sensors to perform preliminary processing of the raw data on site, such as filtering, compression, feature extraction, etc., and then the processed results are uploaded to the cloud or central control system. Edge computing not only improves the efficiency of data processing, but also reduces the burden on the backbone network. It is particularly suitable for application scenarios that require real-time response. The above optional solutions all fall within the scope of protection of this application.

[0059] Step S102 : performing data preprocessing on the current signal, wherein the preprocessing includes filtering and data correction, and extracting features of the current signal and the environmental data.

[0060] As mentioned above, a series of data preprocessing operations are performed on the current signals and environmental data collected in real time from the secondary circuit to ensure the accuracy and reliability of subsequent analysis. Preprocessing mainly involves two key steps: filtering and data correction. Based on this, key features that reflect the system status are extracted. These extracted features serve as important input for machine learning models for anomaly detection and status assessment.

[0061] For example, due to various interference sources in real-world environments, such as electromagnetic noise and mechanical vibration, raw current signals are often contaminated with significant noise. To remove this unnecessary interference and improve signal quality, appropriate filtering algorithms are required. Common filtering methods include low-pass filtering, high-pass filtering, band-pass filtering, and adaptive filtering. Filtering effectively isolates useful signal components and reduces the impact of noise on subsequent analysis. Due to factors such as temperature fluctuations and sensor aging, the collected data may still exhibit some deviation, necessitating correction to restore its true value. After filtering and correction, the next step is to extract representative features from the processed current signal and environmental data. For current signals, extractable features include, but are not limited to, frequency, amplitude, phase, and harmonic components. For environmental data, we focus on temperature and humidity trends, as well as the fluctuation range of temperature and humidity. These features not only reflect the current state of the system but also provide important information for predicting future changes.

[0062] It should be noted that in a specific implementation scenario, a multi-stage filtering strategy can be adopted on the basis of the above-mentioned scheme, that is, in order to process the complex current signal more finely, a coarse filter is first used to remove most of the high-frequency noise, and then a fine filter is used to further optimize the remaining signal. This can not only improve the filtering effect, but also reduce the workload of a single filter. In addition, the parameters of each level of filters can be flexibly configured according to the needs of different application scenarios to achieve the best processing effect; a multi-source data fusion scheme can be adopted, that is, considering the complexity and diversity of the secondary circuit, more data sources can be integrated, such as voltage signals, power factors, switch states, etc., to form a multi-dimensional data set. By comprehensively analyzing these multi-source data, a more complete and accurate system model can be constructed to improve the accuracy and reliability of anomaly detection. The above optional schemes all fall within the scope of protection of this application.

[0063] Step S103: Determine and output anomaly detection results based on the extracted feature data through the trained machine learning model.

[0064] As described above, a pre-trained machine learning model is used to analyze the current signal and environmental data after preprocessing and feature extraction to identify whether there are any abnormal conditions, and output corresponding abnormality detection results based on the judgment of the model.

[0065] For example, to achieve high-precision anomaly detection, a machine learning algorithm tailored to the characteristics of the power system must be selected and trained using extensive historical data. During the training process, the model learns the characteristic distribution patterns under normal conditions and establishes anomaly detection criteria based on these patterns. After data preprocessing and feature extraction, the resulting feature data is passed as input to the machine learning model. The model analyzes the input feature data and calculates the degree of difference between each feature in the current state and the normal state. If certain features exceed preset safety thresholds or if a combination of features exhibits unusual patterns, the model determines an anomaly and generates a corresponding anomaly detection result. This result can be quantitative (e.g., an anomaly severity score) or qualitative (e.g., "minor anomaly," "moderate anomaly," or "severe anomaly"). Once an anomaly is detected, the system immediately generates an anomaly detection report and sends it to the intelligent flexible control terminal or other related systems via a pre-defined interface or communication protocol.

[0066] It should be noted that in a specific implementation scenario, on the basis of the above scheme, a scheme of integrating multiple machine learning algorithms can be adopted. That is, in order to further improve the accuracy of anomaly detection, a variety of different machine learning algorithms can be integrated. For example, multiple weak classifiers (such as multiple random forest models) can be combined into a strong classifier to improve the overall prediction performance. You can also first use an unsupervised learning algorithm (such as K-means clustering, principal component analysis PCA) to conduct a preliminary exploration of the data, and then use a supervised learning algorithm for fine classification, so as to achieve more comprehensive anomaly detection; adopt an anomaly tracing and root cause analysis scheme, that is, by analyzing the data changes in a period of time before and after the anomaly occurs, as well as the correlation between different devices, find out the root cause of the anomaly. For example, if an anomaly is caused by a failure of a specific device, the system can determine that it is the source of the anomaly by comparing the data of the device with other devices. Anomaly tracing and root cause analysis help prevent the recurrence of similar problems and improve the reliability and stability of the system. The above optional schemes all fall within the scope of protection of this application.

[0067] Step S104: The intelligent flexible control terminal determines the abnormal state level based on the abnormality detection result and executes a corresponding early warning control strategy.

[0068] As described above, the intelligent flexible control terminal evaluates the current state of the secondary circuit based on the anomaly detection results output by the machine learning model and determines its abnormality level. Based on the determined abnormality level, it then implements appropriate warning and control strategies to ensure safe and stable system operation.

[0069] For example, to more precisely manage and respond to different abnormal situations, the system categorizes abnormal conditions into multiple levels, such as minor, moderate, and severe. Each level corresponds to a different severity level. This grading helps operations personnel quickly understand the urgency and importance of the problem and take appropriate action. Multiple thresholds are pre-set for each abnormality detection metric. The severity of the abnormality is determined by comparison with each threshold. This allows the system to flexibly adjust its response level to different abnormality types. Based on the different abnormality levels, the system will implement corresponding warning and control strategies. These strategies are designed to promptly notify relevant personnel, provide handling recommendations, and implement necessary protective measures to prevent further escalation of the fault. In addition to real-time anomaly detection results, the system can also integrate historical data and trend analysis to assist in determining the severity of the abnormality. For example, if the temperature in a certain area continues to rise, or the frequency of current fluctuations in a certain device gradually increases, even if the threshold has not yet been exceeded, the system can issue an early warning, prompting operations personnel to pay attention to the health of the area or device and take preventive maintenance measures.

[0070] It should be noted that in a specific implementation scenario, a dynamic threshold adjustment scheme can be adopted on the basis of the above scheme, that is, in order to improve the flexibility of abnormal state level determination, the thresholds of various abnormality detection indicators are dynamically adjusted according to the real-time operating conditions, historical data and external environmental factors (such as weather, grid load, etc.) of the system. For example, during the high temperature period in summer, the temperature threshold setting can be appropriately relaxed to avoid false alarms due to the natural increase in ambient temperature. During the low temperature period in winter, the temperature threshold can be tightened to ensure that the equipment is not damaged by overcooling. Dynamic threshold adjustment helps to more accurately identify real abnormal situations and reduce unnecessary alarms; an adaptive early warning control strategy scheme is adopted, that is, the system can make real-time adjustments according to specific circumstances. For example, when a minor abnormality is detected, if the abnormality lasts for a long time and has a tendency to worsen, the system can automatically upgrade to a moderate abnormality response level. Conversely, if the abnormal situation is quickly alleviated, the system can be downgraded to a minor abnormality processing method. The adaptive strategy not only improves the timeliness of the response, but also better adapts to different application scenarios. The above optional schemes all fall within the scope of protection of this application.

[0071] In some embodiments of the present application, in order to achieve real-time and accurate collection of current signals and environmental data on the secondary circuit, and ensure the synchronization and integrity of these data, and provide a reliable basis for subsequent abnormality detection and status assessment, the real-time collection of relevant parameter data on the secondary circuit, including current signals and environmental data, is specifically:

[0072] The current signal on the secondary circuit is collected in real time by an external current transformer and a manganese copper sampling resistor installed on the secondary circuit;

[0073] Real-time monitoring and collection of environmental data through sensors, including temperature data and humidity data;

[0074] The collected environmental data and the current signal are recorded synchronously for subsequent comprehensive analysis.

[0075] As mentioned above, the current signal on the secondary circuit is collected in real time through an external current transformer and manganese copper sampling resistor installed in the secondary circuit. The external current transformer is used to convert the large primary current into a proportionally smaller secondary current for easier measurement and processing. Current transformers are typically installed at key nodes such as circuit breakers, disconnectors, and protective relays to capture the dynamic changes in current throughout the secondary circuit. The manganese copper sampling resistor uses its stable resistance and minimal temperature drift to accurately sample current. The manganese copper sampling resistor can be directly connected in series in the circuit, and the current is calculated by measuring the voltage drop across it. Sensors are used to monitor and collect environmental data in real time, including temperature and humidity. Temperature sensors are used to monitor changes in ambient temperature and can be installed in key areas such as control rooms and switchgear, sending the latest temperature readings at regular intervals (such as every second or every minute). Humidity sensors are used to monitor changes in ambient humidity and can also be installed in key locations, working in conjunction with temperature sensors to provide comprehensive environmental information. The collected environmental data is recorded synchronously with the current signal for subsequent comprehensive analysis. To ensure synchronization between different data sources, all collected data is timestamped. This allows accurate matching of current signals and environmental data at the same time point in subsequent analysis, leading to a more comprehensive understanding of the system's operating status. The collected data will be stored in a central database or local storage device for subsequent analysis. The edge computing module can also perform preliminary data processing on-site to reduce transmission delays and data volume.

[0076] In some embodiments of the present application, in order to effectively preprocess and extract features of the collected current signal and environmental data, and provide high-quality data support for subsequent anomaly detection and status assessment, the data preprocessing of the current signal includes filtering and data correction, and extracting features of the current signal and the environmental data, specifically:

[0077] Performing filtering processing on the current signal based on the edge computing module, and performing data correction on the filtered current signal;

[0078] Extracting key features of the current signal, including frequency, amplitude, and phase, through digital signal processing technology;

[0079] The features of the environmental data are simultaneously extracted, including temperature change trends and humidity change trends.

[0080] As described above, the system uses an edge computing module deployed near the sensor to perform preliminary processing of the current signal. This edge computing module can process data in real time on-site, reducing transmission delays and the burden on the backbone network. Appropriate filtering algorithms are used to remove noise from the current signal. This filtering process effectively isolates useful signal components and reduces the impact of noise on subsequent analysis. Even after filtering, the current signal may still contain some deviations, which may be caused by factors such as temperature fluctuations and sensor aging. Therefore, the filtered current signal needs to be corrected to restore its true value. Digital signal processing techniques are used to extract key features from the filtered and corrected current signal. These features include but are not limited to frequency, amplitude, and phase. Frequency reflects the periodic variation of the current signal. For power systems, the power frequency (such as 50Hz or 60Hz) and its harmonic components are typically of interest. Amplitude indicates the strength of the current signal and is used to monitor whether the current exceeds the normal range, such as in a short circuit or overload condition. Phase describes the phase difference between current and voltage, which helps determine the system's power factor and load characteristics. The characteristics of environmental data are extracted synchronously, mainly including temperature change trends and humidity change trends. By analyzing the changes in temperature over time, it is possible to identify whether there are abnormal heating and cooling phenomena; by monitoring the changes in humidity, it is possible to find out whether the humidity is too high or too low.

[0081] In some embodiments of the present application, in order to comprehensively and accurately assess the status of the secondary circuit, timely discover and report various abnormal situations, and provide reliable protection for the safe and stable operation of the power system, the trained machine learning model is used to determine and output the abnormality detection results based on the extracted feature data, specifically:

[0082] The abnormality detection results include the current fluctuation amplitude, the degree of shunting phenomenon, the degree of magnetic field change, the degree of increase in harmonic components, and the degree of temperature and humidity exceeding the standard;

[0083] Determining the current fluctuation amplitude by comparing the current current signal with a preset safety threshold;

[0084] Monitoring the change in current distribution and determining the extent of the shunting phenomenon by comparing the extent of the change in the current signal at different locations;

[0085] Monitoring the change in magnetic field intensity by a fluxgate sensor to determine the degree of change in the magnetic field;

[0086] Analyzing the harmonic components of the current waveform, extracting harmonic information through Fourier transform, and determining the degree of increase of the harmonic components;

[0087] The degree to which the temperature and humidity exceed the standard is determined by comparing the current temperature and humidity data with the preset range.

[0088] As mentioned above, the current fluctuation amplitude reflects the change in the amplitude of the current signal, which is used to determine whether there are faults such as short circuits and overloads. The degree of shunting describes the change in the distribution of current between different locations, which is used to identify problems such as loose joints and aging of insulation materials. The degree of magnetic field change can monitor changes in magnetic field strength and is used to detect whether there are large metal objects approaching or electromagnetic interference sources. The degree of harmonic component increase can analyze the harmonic components in the current waveform and is used to evaluate power quality issues, such as the impact of nonlinear loads. The degree of temperature and humidity exceeding the standard can monitor changes in temperature and humidity to ensure that the equipment operating environment is within a safe range.

[0089] The system sets a preset safety threshold for the amplitude of the current signal, which is determined based on historical data and actual operating conditions. The system compares the currently collected current signal amplitude with the preset safety threshold. If the current amplitude exceeds the threshold, it is determined that the current fluctuation amplitude is abnormal and the degree of excess is recorded. The system uses multiple sensors to monitor the changes in current signals at different locations in real time, capturing the distribution of current in the secondary circuit. By comparing the degree of change in current signals at different locations, the severity of the shunt phenomenon is assessed. If the current at certain locations decreases significantly while the current at other locations increases accordingly, it indicates a shunt problem. The system installs fluxgate sensors at key locations to monitor changes in magnetic field strength in real time. The fluxgate sensors continuously record magnetic field strength data and compare it with historical data. If the magnetic field strength changes drastically, exceeding the preset range, the system will determine that the magnetic field change is abnormal and record the degree of change. The system performs a Fourier transform on the current waveform, decomposing it into harmonic components of different frequencies. The system then extracts the amplitude and phase information of each harmonic component from the Fourier transform result and analyzes the degree of increase in these harmonic components. A significant increase in harmonic components at certain frequencies indicates the presence of nonlinear loads or other issues in the power system. The system sets preset safety ranges for temperature and humidity, determined based on the equipment's operating requirements and environmental conditions. The system compares the currently collected temperature and humidity data with these preset safety ranges. If the temperature or humidity exceeds these ranges, the system determines that the temperature or humidity exceeds the specified limits and records the extent of the excess.

[0090] In some embodiments of the present application, in order to accurately evaluate the current state of the secondary circuit and adopt corresponding early warning and control strategies according to different abnormal state levels, the intelligent flexible control terminal determines its abnormal state level based on the abnormality detection result, specifically:

[0091] Any one of the abnormality detection results corresponds to a preset first threshold and a second threshold, and each of the first thresholds is smaller than the second threshold;

[0092] The current abnormality level is determined by comparing the abnormality detection results with their corresponding thresholds. The abnormality levels include slight abnormality, moderate abnormality and severe abnormality.

[0093] As mentioned above, for each abnormal detection result (such as the current fluctuation amplitude, the degree of shunting phenomenon, the degree of magnetic field change, the degree of increase in harmonic components, and the degree of temperature and humidity exceeding the standard), the system presets two thresholds, namely the first threshold and the second threshold, wherein the first threshold is less than the second threshold. The first threshold is used to mark the boundary of slight abnormalities, and the second threshold is used to mark the boundary of severe abnormalities. The system compares each abnormal detection result with its corresponding preset threshold to determine whether it exceeds the first threshold or the second threshold to determine the current abnormal status level. The abnormal status levels include slight abnormalities, moderate abnormalities, and severe abnormalities. Mild abnormalities indicate that although there are some minor problems, they have not yet posed a major threat to the normal operation of the system; moderate abnormalities indicate that the problem is already relatively obvious and needs to be taken seriously and dealt with in a timely manner to prevent further deterioration; severe abnormalities indicate that the problem is very serious and may have a major impact on the safe and stable operation of the system, and emergency measures must be taken immediately.

[0094] In some embodiments of the present application, in order to accurately evaluate the current state of the secondary circuit and adopt corresponding early warning and control strategies according to different abnormal state levels to ensure the safe and stable operation of the power system, the current abnormal state level is determined by comparing the abnormal detection results with their corresponding thresholds, specifically:

[0095] If any one of the abnormality detection results does not exceed the corresponding first threshold, then the current abnormality state level is determined to be the slight abnormality;

[0096] If any one of the abnormality detection results exceeds the corresponding first threshold but does not exceed the second threshold, the current abnormality level is determined to be the moderate abnormality;

[0097] If any one of the abnormality detection results exceeds the corresponding second threshold, the current abnormality state level is determined to be the severe abnormality.

[0098] As described above, if all abnormality detection results do not exceed their corresponding first thresholds, the system determines the current abnormality level to be a minor abnormality. This means that although some indicators may be close to the first threshold, they have not yet exceeded it, indicating that there are some minor problems with the system, but overall operation remains within controllable limits. If an abnormality detection result exceeds its corresponding first threshold but does not exceed the second threshold, the system determines the current abnormality level to be a moderate abnormality. This indicates that the indicator has exceeded the limit of a minor abnormality but has not yet reached the level of a severe abnormality, requiring attention and timely treatment to prevent further deterioration of the problem. If an abnormality detection result exceeds its corresponding second threshold, the system determines the current abnormality level to be a severe abnormality. This indicates that the indicator has exceeded the safe range and may pose a serious fault or risk. Emergency measures must be taken immediately to prevent accidents. The system compares each abnormality detection result with its corresponding preset thresholds (first threshold and second threshold) one by one. If multiple abnormality detection results are at different abnormality levels, the system determines the final abnormality level based on the most severe one.

[0099] In some embodiments of the present application, in order to be able to take corresponding early warning and control measures according to different levels of abnormal conditions to ensure the safe and stable operation of the secondary circuit and minimize the losses caused by failures, the corresponding early warning and control strategies are specifically:

[0100] When the abnormal state level is the minor abnormality, the first-level early warning strategy is executed, that is, the sound and light alarm is triggered and the abnormal data is recorded;

[0101] When the abnormal state level is the moderate abnormality, the secondary warning strategy is executed, that is, on the basis of the primary warning strategy, the operation and maintenance personnel are notified via SMS and email, and preliminary handling suggestions are provided;

[0102] When the abnormal state level is the serious abnormality, the third-level warning strategy is executed, that is, on the basis of the second-level warning strategy, the automatic protection measures are triggered again, and the automatic protection measures include cutting off the power supply, starting the backup circuit and starting the protection device.

[0103] As mentioned above, when the system determines that the current abnormal state level is a minor abnormality, it first triggers the sound and light alarm device. The sound and light alarm can immediately alert on-site staff so that they can check the relevant equipment in time; at the same time, the system automatically records all abnormal detection results and related data for subsequent analysis. These records include timestamps, specific abnormal indicators (such as current fluctuation amplitude, temperature changes, etc.) and the environmental conditions at the time, which help operation and maintenance personnel understand the specific situation of the problem and make a diagnosis.

[0104] When the system determines that the current abnormal status level is moderate, it will continue to take further measures on the basis of implementing the first-level warning strategy, including notifying the remote operation and maintenance team via SMS and email to ensure that relevant personnel can be informed of the abnormal situation in a timely manner. The content of SMS and email should contain detailed abnormal information, such as the type of abnormality, time of occurrence, and the equipment or area involved. The system will provide preliminary processing suggestions based on the abnormality type to help operation and maintenance personnel make decisions more quickly.

[0105] When the system determines that the current abnormal status level is a serious abnormality, it will automatically initiate a series of protection measures based on the implementation of the secondary warning strategy to prevent the fault from further expanding and ensure the safety of the system, including cutting off the power supply, that is, immediately cutting off the power supply of the relevant circuit to prevent short circuits or other electrical faults from causing larger accidents; starting the backup circuit, that is, the system will automatically switch to the backup circuit to ensure the continuity of power supply; activating protective devices such as circuit breakers and fuses to prevent equipment damage or secondary disasters such as fire; notifying the operation and maintenance team again through SMS and email, providing detailed fault reports and handling suggestions to help quickly restore the normal operation of the system.

[0106] Compared with the prior art, the embodiment of the present application discloses an intelligent flexible control terminal loop inspection method. This method can collect current signals and environmental data in real time through external current transformers, manganese copper sampling resistors and various sensors installed on the secondary loop, ensuring the continuity and timeliness of the inspection process, so that any abnormal situation can be quickly captured; using pre-processing steps such as filtering, data correction and key feature extraction, as well as a trained machine learning model, it can accurately identify the current fluctuation amplitude, the degree of shunting phenomenon, the degree of magnetic field change, the degree of harmonic component increase and the degree of temperature and humidity exceeding the standard, thereby improving the accuracy of abnormality detection; based on the abnormality detection results, intelligent It can judge the level of abnormal status and implement corresponding early warning and control strategies according to different levels, including sound and light alarms, notification of operation and maintenance personnel, provision of processing suggestions, and even automatic implementation of protective measures, realizing intelligent management and response; when a serious abnormality is detected, the system can take immediate action, such as cutting off power supply, starting backup circuits or activating protection devices, minimizing the impact of faults on the power system and improving the overall safety of the system; by synchronously recording environmental data and current signals, it facilitates subsequent comprehensive analysis, helps operation and maintenance personnel to have a more comprehensive understanding of the system status and formulate more scientific and reasonable maintenance plans, thereby improving operation and maintenance efficiency and reducing maintenance costs.

[0107] Based on the same inventive concept as the above method, the embodiment of the present application also proposes an intelligent flexible control terminal loop inspection system, such as Figure 2 The figure shows a schematic diagram of the structure of an intelligent flexible control terminal loop inspection system, which includes:

[0108] An acquisition module is used to collect relevant parameter data on the secondary circuit in real time, wherein the relevant parameter data includes current signals and environmental data;

[0109] a processing module, configured to perform data preprocessing on the current signal, wherein the preprocessing includes filtering and data correction, and extract features of the current signal and the environmental data;

[0110] The detection module is used to determine and output anomaly detection results based on the extracted feature data using a trained machine learning model;

[0111] An execution module is used for the intelligent flexible control terminal to judge the abnormal state level based on the abnormal detection result and execute the corresponding early warning control strategy.

[0112] Preferably, the acquisition module is specifically:

[0113] The current signal on the secondary circuit is collected in real time by an external current transformer and a manganese copper sampling resistor installed on the secondary circuit;

[0114] Real-time monitoring and collection of environmental data through sensors, including temperature data and humidity data;

[0115] The collected environmental data and the current signal are recorded synchronously for subsequent comprehensive analysis.

[0116] Preferably, the processing module is specifically:

[0117] Performing filtering processing on the current signal based on the edge computing module, and performing data correction on the filtered current signal;

[0118] Extracting key features of the current signal, including frequency, amplitude, and phase, through digital signal processing technology;

[0119] The features of the environmental data are simultaneously extracted, including temperature change trends and humidity change trends.

[0120] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or a combination of software and hardware embodiments. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. An intelligent flexible control terminal loop inspection method, characterized in that: include: Real-time collection of relevant parameter data on the secondary circuit, including current signals and environmental data; Performing data preprocessing on the current signal, the preprocessing including filtering and data correction, and extracting features of the current signal and the environmental data; Through the trained machine learning model, based on the extracted feature data, the anomaly detection results are determined and output; The intelligent flexible control terminal determines the abnormal state level based on the abnormality detection result and executes the corresponding early warning control strategy.

2. The method according to claim 1, wherein The real-time collection of relevant parameter data on the secondary circuit, including current signals and environmental data, is specifically: The current signal on the secondary circuit is collected in real time by an external current transformer and a manganese copper sampling resistor installed on the secondary circuit; Real-time monitoring and collection of environmental data through sensors, including temperature data and humidity data; The collected environmental data and the current signal are recorded synchronously for subsequent comprehensive analysis.

3. The method according to claim 1, wherein The data preprocessing of the current signal includes filtering and data correction, and extracting features of the current signal and the environmental data, specifically: Performing filtering processing on the current signal based on the edge computing module, and performing data correction on the filtered current signal; Extracting key features of the current signal, including frequency, amplitude, and phase, through digital signal processing technology; The features of the environmental data are simultaneously extracted, including temperature change trends and humidity change trends.

4. The method according to claim 1, wherein The trained machine learning model determines and outputs anomaly detection results based on the extracted feature data, specifically: The abnormality detection results include the current fluctuation amplitude, the degree of shunting phenomenon, the degree of magnetic field change, the degree of increase in harmonic components, and the degree of temperature and humidity exceeding the standard; Determining the current fluctuation amplitude by comparing the current current signal with a preset safety threshold; Monitoring the change in current distribution and determining the extent of the shunting phenomenon by comparing the extent of the change in the current signal at different locations; Monitoring the change in magnetic field intensity by a fluxgate sensor to determine the degree of change in the magnetic field; Analyzing the harmonic components of the current waveform, extracting harmonic information through Fourier transform, and determining the degree of increase of the harmonic components; The degree to which the temperature and humidity exceed the standard is determined by comparing the current temperature and humidity data with the preset range.

5. The method according to claim 4, wherein The intelligent flexible control terminal determines the abnormal state level based on the abnormality detection result, specifically: Any one of the abnormality detection results corresponds to a preset first threshold and a second threshold, and each of the first thresholds is smaller than the second threshold; The current abnormality level is determined by comparing the abnormality detection results with their corresponding thresholds. The abnormality levels include slight abnormality, moderate abnormality and severe abnormality.

6. The method according to claim 5, wherein The current abnormal state level is determined by comparing the abnormal detection results with their corresponding thresholds, specifically: If any one of the abnormality detection results does not exceed the corresponding first threshold, then the current abnormality state level is determined to be the slight abnormality; If any one of the abnormality detection results exceeds the corresponding first threshold but does not exceed the second threshold, the current abnormality level is determined to be the moderate abnormality; If any one of the abnormality detection results exceeds the corresponding second threshold, the current abnormality state level is determined to be the severe abnormality.

7. The method according to claim 5, wherein The execution corresponding early warning and control strategy is specifically: When the abnormal state level is the minor abnormality, the first-level early warning strategy is executed, that is, the sound and light alarm is triggered and the abnormal data is recorded; When the abnormal state level is the moderate abnormality, the secondary warning strategy is executed, that is, on the basis of the primary warning strategy, the operation and maintenance personnel are notified via SMS and email, and preliminary handling suggestions are provided; When the abnormal state level is the serious abnormality, the third-level warning strategy is executed, that is, on the basis of the second-level warning strategy, the automatic protection measures are triggered again, and the automatic protection measures include cutting off the power supply, starting the backup circuit and starting the protection device.

8. An intelligent flexible control terminal loop inspection system, characterized in that: include: An acquisition module is used to collect relevant parameter data on the secondary circuit in real time, wherein the relevant parameter data includes current signals and environmental data; a processing module, configured to perform data preprocessing on the current signal, wherein the preprocessing includes filtering and data correction, and extract features of the current signal and the environmental data; The detection module is used to determine and output anomaly detection results based on the extracted feature data using a trained machine learning model; An execution module is used for the intelligent flexible control terminal to judge the abnormal state level based on the abnormal detection result and execute the corresponding early warning control strategy.

9. The system according to claim 8, wherein The acquisition module is specifically: The current signal on the secondary circuit is collected in real time by an external current transformer and a manganese copper sampling resistor installed on the secondary circuit; Real-time monitoring and collection of environmental data through sensors, including temperature data and humidity data; The collected environmental data and the current signal are recorded synchronously for subsequent comprehensive analysis.

10. The system according to claim 8, wherein The processing module is specifically: Performing filtering processing on the current signal based on the edge computing module, and performing data correction on the filtered current signal; Extracting key features of the current signal, including frequency, amplitude, and phase, through digital signal processing technology; The features of the environmental data are simultaneously extracted, including temperature change trends and humidity change trends.

Images