Distribution cable operation early warning method and device

Abstract

The invention relates to a power distribution cable operation early warning method and device. The method comprises the steps that current and voltage on a cable are monitored in real time through a current sensor and a voltage sensor; inputting the current and the voltage into a dynamic analysis module based on machine learning, and performing multivariable feature extraction and trend point prediction by adopting a long-short-term memory network model; establishing a baseline model in combination with an adaptive algorithm according to the historical operation data and the environment variables; through model training, the current, voltage and temperature threshold range is adjusted in a self-adaptive mode; when the operation data exceed a confidence interval or exceed a dynamic threshold value, early warning is triggered; performing grading processing on the abnormity through an early warning system based on a multi-stage risk assessment mechanism; and after the early warning is triggered, the accurate positioning of the fault position is realized through the distributed sensor nodes. According to the method and the device, an effective baseline model can be established to monitor and predict the operation state of the power distribution network cable, so that the overload problem can be found and processed in time, and safe and stable operation of a power system is ensured.

Description

Technical Field

[0001] The present invention relates to the field of power distribution cables, and in particular to a power distribution cable operation early warning method and device. Background Art

[0002] With the continuous development of science and technology, and the development of urban power grids, a large number of overhead lines in urban areas have been "upgraded" and replaced with cable lines. Power cables achieve greater transmission capacity and transmission distance, becoming one of the important components of the distribution network system. In order to promote the process of urbanization and ensure people's quality of life and personal safety, people's demand for electricity is increasing, and their dependence on electricity is also increasing. However, cable failures have gradually become the main source of power accidents, which can easily cause personal accidents and equipment failures, leading to significant economic losses.

[0003] In the power distribution system, due to the complex operating environment of the distribution cable, as the operating time increases, the insulation system will gradually age, and local discharge will occur and propagate along the cable body. If it is not discovered in time, as the hidden dangers increase, failures and accidents will occur. Therefore, in order to find the location of the hidden dangers early and avoid the occurrence of faults, it is necessary to monitor the discharge hidden dangers. It is necessary to develop a distribution cable operation early warning method and device to solve the above-mentioned problems. Summary of the invention

[0004] The purpose of the present invention is to provide a distribution cable operation early warning method and device, which can establish an effective baseline model to monitor and predict the operating status of distribution network cables, so as to timely discover and deal with overload problems and ensure the safe and stable operation of the power system.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is: a distribution cable operation early warning method, comprising the following steps:

[0006] Step S1: Monitor the current and voltage on the cable in real time through the installed current and voltage sensors, which are directly installed on the cable, distribution box or centralized monitoring device; preliminarily filter invalid data and mark abnormal data;

[0007] Step S2: input the acquired current and voltage into a dynamic analysis module based on machine learning, and use a long short-term memory network model to perform multivariate feature extraction and trend prediction to identify potential anomalies and risk points that may cause failures;

[0008] Step S3: Establish a baseline model based on historical operation data and environmental variables in combination with an adaptive algorithm;

[0009] Step S4: adaptively adjust the current, voltage and temperature threshold ranges through model training; trigger early warning when the operating data exceeds the confidence interval or exceeds the dynamic threshold;

[0010] Step S5: The early warning system performs graded processing of abnormalities based on a multi-level risk assessment mechanism, including mild alarms, moderate alarms, and severe alarms; the early warning information is sent to maintenance personnel in real time through the Internet of Things platform in the form of sound, light signal, SMS or cloud monitoring interface, and provides specific fault locations and potential causes;

[0011] Step S6: After the warning is triggered, the fault location is accurately located through distributed sensor nodes.

[0012] Furthermore, in step S2, the long short-term memory network model in deep learning is used to predict the current and voltage risks. Assuming that the input data is X'(t), the output is the predicted value at the future moment.

[0013]

[0014] Among them, LSTM() is a long short-term memory network model.

[0015] Furthermore, the implementation method of the long short-term memory network model is:

[0016] f t =σ(W f ·[h t-1 ,X′(t)]+b f )

[0017] i t =σ(W i ·[h t-1 ,X′(t)]+b i )

[0018] C t =f t ·C t-1 +i t tanh(W C ·[h t-1 ,X′(t)]+b C )

[0019] o t =σ(W o ·[h t-1 ,X′(t)]+b o )

[0020] h t =o t tanh(C t )

[0021] Among them, f t It is the forget gate, t is the input gate, C t is the cell state, o t is the output gate, h t is the hidden state and σ is the sigmoid activation function.

[0022] Furthermore, the prediction results of the long short-term memory network model are adaptively adjusted, and the adjustment strategy is:

[0023]

[0024] Furthermore, in step S3, the following indicators are used to establish a baseline model:

[0025] A1. Average value: Calculate the average value of current and voltage data as an indicator of the baseline model. The average value reflects the current and voltage levels under normal operating conditions.

[0026] A2. Standard Deviation: Calculate the standard deviation of current and voltage data to measure the degree of dispersion of data. A standard deviation greater than the set value indicates a large fluctuation, which is an indication of abnormal conditions.

[0027] A3. Extreme values: Determine the extreme values ​​of current and voltage data, including maximum and minimum values. These extreme values ​​serve as references for the baseline model to detect whether there are conditions that exceed the normal range.

[0028] A4. Percentile: Calculate the percentile of current and voltage data to determine the concentration range of most data under normal operating conditions.

[0029] Furthermore, in step S5, the early warning system includes:

[0030] Data acquisition module: collects current and voltage data in real time from smart sensors on distribution network cables;

[0031] Data processing module: preprocessing, filtering and normalization of raw data;

[0032] Threshold setting module: sets current and voltage thresholds according to normal operating conditions and allowed overload levels;

[0033] Comparison module: compares real-time data with preset thresholds and determines whether to trigger an early warning;

[0034] Early warning trigger module: When an overload risk is detected, an early warning is triggered and a notification is sent to relevant personnel.

[0035] Furthermore, in the early warning system, the current threshold is set to 350 amperes and the voltage threshold is set to 11k volts.

[0036] Furthermore, the early warning system compares the prediction result with the set current threshold and voltage threshold to obtain the following status:

[0037] Normal operation: When both the current and voltage values ​​are lower than the threshold, the system will not trigger an early warning;

[0038] Current overload: When the current value exceeds 350 amperes, the system will trigger a current overload warning;

[0039] Voltage overload: When the voltage value exceeds 11k volts, the system will trigger a voltage overload warning;

[0040] Simultaneous overload: When both the current and voltage values ​​exceed their respective thresholds, the system will trigger a simultaneous overload warning.

[0041] Furthermore, the alarm mode of the early warning trigger module is selected according to the urgency of the system, including:

[0042] Audible alarm: for emergency situations that require immediate action;

[0043] Light Alert: For non-emergency situations that require attention but not immediate action;

[0044] SMS alerts: Suitable for situations where remote personnel need to be notified.

[0045] The present invention also provides a distribution cable operation warning device for implementing the above method, including a sensor, a microcontroller and a warning system, wherein the sensor is used to monitor the current, voltage and temperature parameters of the cable; the microcontroller is electrically connected to the sensor and the warning system for processing data and triggering a warning.

[0046] Compared with the prior art, the present invention has the following beneficial effects: the present invention provides a distribution cable operation early warning method and device, which can establish an effective baseline model to monitor and predict the operating status of distribution network cables, so as to timely discover and deal with overload problems and ensure the safe and stable operation of the power system. The early warning system used can ensure that when the cable is overloaded, the relevant personnel can be notified in time and take corresponding measures to prevent potential safety accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the method implementation principle of the embodiment of the present invention. DETAILED DESCRIPTION

[0048] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0049] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0050] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0051] like Figure 1 As shown, this embodiment provides a distribution cable operation early warning method, comprising the following steps:

[0052] Step S1: Data collection:

[0053] Install current and voltage sensors to monitor the current and voltage on the cable in real time. The sensors are directly installed on the cable, distribution box or centralized monitoring device. Data collection has edge computing function to preliminarily filter invalid data and mark abnormal data.

[0054] Step S2: Data processing and dynamic analysis:

[0055] The acquired current and voltage are input into the dynamic analysis module based on machine learning, and the long short-term memory network model is used for multivariate feature extraction and trend prediction to identify potential anomalies and risk points that may cause failures.

[0056] Step S3: Dynamic baseline establishment:

[0057] A baseline model is established based on historical operating data and environmental variables combined with an adaptive algorithm.

[0058] Step S4: Intelligent threshold setting:

[0059] Through model training, the current, voltage and temperature threshold ranges are adaptively adjusted; when the operating data exceeds the confidence interval or exceeds the dynamic threshold, an early warning is triggered.

[0060] Step S5: Design of hierarchical early warning system:

[0061] The early warning system handles abnormalities in a graded manner based on a multi-level risk assessment mechanism, including mild alarms, moderate alarms and severe alarms; the early warning information is sent to maintenance personnel in real time through the Internet of Things platform in the form of sound, light signals, text messages or cloud monitoring interface, and provides the specific fault location and potential causes.

[0062] Step S6: Fault location and self-healing function:

[0063] After the warning is triggered, the fault location is accurately located through distributed sensor nodes.

[0064] Through the above steps, an effective baseline model can be established to monitor and predict the operating status of distribution network cables, so as to timely detect and deal with overload problems and ensure the safe and stable operation of the power system.

[0065] In step S2, the long short-term memory network model in deep learning is used to predict the current and voltage risks. Assuming that the input data is X'(t), the output is the predicted value at the future moment.

[0066]

[0067] Among them, LSTM() is a long short-term memory network model.

[0068] The implementation method of the long short-term memory network model is:

[0069] f t =σ(W f ·[h t-1 ,X′(t)]+b f )

[0070] i t =σ(W i ·[h t-1 ,X′(t)]+b i )

[0071] C t =f t ·C t-1 +i t tanh(W C ·[h t-1 ,X′(t)]+b C )

[0072] o t =σ(W o ·[h t-1 ,X′(t)]+b o )

[0073] h t =o t tanh(C t )

[0074] Among them, f t It is the forget gate, t is the input gate, C tis the cell state, o t is the output gate, h t is the hidden state and σ is the sigmoid activation function.

[0075] The prediction results of the long short-term memory network model are adaptively adjusted, and the adjustment strategy is:

[0076]

[0077] In step S3, the following indicators are used to establish a baseline model:

[0078] A1. Average value: Calculate the average value of current and voltage data as an indicator of the baseline model. The average value reflects the current and voltage levels under normal operating conditions.

[0079] A2. Standard Deviation: Calculate the standard deviation of current and voltage data to measure the degree of dispersion of the data. A larger standard deviation indicates a larger fluctuation, which is an indication of abnormal conditions.

[0080] A3. Extreme values: Determine the extreme values ​​of current and voltage data, including maximum and minimum values. These extreme values ​​serve as a reference for the baseline model to detect whether there are conditions that exceed the normal range.

[0081] A4. Percentile: Calculate the percentile of current and voltage data to determine the range in which most of the data are concentrated under normal operating conditions.

[0082] In step S5, the early warning system includes:

[0083] Data acquisition module: collects current and voltage data in real time from smart sensors on distribution network cables;

[0084] Data processing module: preprocessing, filtering and normalization of raw data;

[0085] Threshold setting module: sets current and voltage thresholds according to normal operating conditions and allowed overload levels;

[0086] Comparison module: compares real-time data with preset thresholds and determines whether to trigger an early warning;

[0087] Early warning trigger module: When an overload risk is detected, an early warning is triggered and a notification is sent to relevant personnel.

[0088] In this embodiment, the current threshold is set to 350 amperes and the voltage threshold is set to 11k volts in the early warning system. The early warning system compares the prediction result with the set current threshold and voltage threshold to obtain the following status:

[0089] Normal operation: When both the current and voltage values ​​are lower than the threshold, the system will not trigger an early warning;

[0090] Current overload: When the current value exceeds 350 amperes, the system will trigger a current overload warning;

[0091] Voltage overload: When the voltage value exceeds 11k volts, the system will trigger a voltage overload warning;

[0092] Simultaneous overload: When both the current and voltage values ​​exceed their respective thresholds, the system will trigger a simultaneous overload warning.

[0093] Specifically, the current threshold mainly depends on the current carrying capacity of the distribution cable:

[0094] Cable current carrying capacity calculation: For example, some common 10kV cable cross-sections and their corresponding current carrying capacity are as follows:

[0095] 3×95mm 2 Aluminum core cable: Maximum current carrying capacity is about 250A

[0096] 3×150mm 2 Aluminum core cable: Maximum current carrying capacity is about 350A

[0097] 3×240mm 2 Aluminum core cable: Maximum current carrying capacity is about 450A

[0098] Depending on the cable specifications, the current threshold can be set. If the system uses 3×150mm 2 For aluminum core cables, the current threshold can be set close to 350A. When the current exceeds this value, an overcurrent warning is triggered.

[0099] For 10kV distribution systems, the voltage variation range is usually limited by national or industry standards. According to relevant power standards in China, the voltage tolerance of a 10kV system is usually ±10% of the rated voltage. Therefore, the voltage threshold is generally set to 11kV.

[0100] The alarm mode of the early warning trigger module is selected according to the urgency of the system, including:

[0101] Audible alarm: for emergency situations that require immediate action;

[0102] Light Alert: For non-emergency situations that require attention but not immediate action;

[0103] SMS alerts: Suitable for situations where remote personnel need to be notified.

[0104] This embodiment also provides a distribution cable operation warning device for implementing the above method, including a sensor, a microcontroller and a warning system, wherein the sensor is used to monitor the current, voltage and temperature parameters of the cable; the microcontroller is electrically connected to the sensor and the warning system to process data and trigger a warning.

[0105] Through such an early warning system solution, it can be ensured that when the cable is overloaded, relevant personnel can be notified in time and take appropriate measures to prevent potential safety accidents.

[0106] 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 adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0107] 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 generate 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.

[0108] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1A step that specifies a function in one or more boxes.

[0110] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

Claims

1. A distribution cable operation early warning method, characterized in that: The following steps are involved: Step S1: Monitor the current and voltage on the cable in real time through the installed current and voltage sensors, which are directly installed on the cable, distribution box or centralized monitoring device; preliminarily filter invalid data and mark abnormal data; Step S2: input the acquired current and voltage into a dynamic analysis module based on machine learning, and use a long short-term memory network model to perform multivariate feature extraction and trend prediction to identify potential anomalies and risk points that may cause failures; Step S3: Establish a baseline model based on historical operation data and environmental variables combined with an adaptive algorithm; Step S4: adaptively adjust the current, voltage and temperature threshold ranges through model training; trigger early warning when the operating data exceeds the confidence interval or exceeds the dynamic threshold; Step S5: The early warning system performs graded processing on the anomaly based on a multi-level risk assessment mechanism, including a mild alarm, a moderate alarm, and a severe alarm; Early warning information is sent to maintenance personnel in real time through the IoT platform in the form of sound, light signals, text messages or cloud monitoring interface, and provides specific fault locations and potential causes; Step S6: After the warning is triggered, the fault location is accurately located through distributed sensor nodes.

2. A distribution cable operation early warning method according to claim 1, characterized in that: In step S2, the long short-term memory network model in deep learning is used to predict the current and voltage risks. Assuming that the input data is X'(t), the output is the predicted value at the future moment. Among them, LSTM() is a long short-term memory network model.

3. A distribution cable operation early warning method according to claim 2, characterized in that: The implementation method of the long short-term memory network model is: f t =σ(W f ·[h t-1 ,X′(t)]+b f ) i t =σ(W i ·[h t-1 ,X′(t)]+b i ) C t =f t ·C t-1 +i t ·tanh(W C ·[h t-1 ,X′(t)]+b C ) o t =σ(W o ·[h t-1 ,X′(t)]+b o ) h t =o t ·tanh(C t ) Among them, f t It is the forget gate, t is the input gate, C t is the cell state, o t is the output gate, h t is the hidden state and σ is the sigmoid activation function.

4. A distribution cable operation early warning method according to claim 2, characterized in that: The prediction results of the long short-term memory network model are adaptively adjusted, and the adjustment strategy is:

5. A distribution cable operation early warning method according to claim 1, characterized in that: In step S3, the following indicators are used to establish a baseline model: A1. Average value: Calculate the average value of current and voltage data as an indicator of the baseline model. The average value reflects the current and voltage levels under normal operating conditions. A2. Standard Deviation: Calculate the standard deviation of current and voltage data to measure the degree of dispersion of data. A standard deviation greater than the set value indicates a large fluctuation, which is an indication of abnormal conditions. A3. Extreme values: Determine the extreme values ​​of current and voltage data, including maximum and minimum values. These extreme values ​​serve as references for the baseline model to detect whether there are conditions that exceed the normal range. A4. Percentile: Calculate the percentile of current and voltage data to determine the concentration range of most data under normal operating conditions.

6. A distribution cable operation early warning method according to claim 1, characterized in that: In step S5, the early warning system includes: Data acquisition module: collects current and voltage data in real time from smart sensors on distribution network cables; Data processing module: preprocessing, filtering and normalization of raw data; Threshold setting module: sets current and voltage thresholds according to normal operating conditions and allowed overload levels; Comparison module: compares real-time data with preset thresholds and determines whether to trigger an early warning; Early warning trigger module: When an overload risk is detected, an early warning is triggered and a notification is sent to relevant personnel.

7. A distribution cable operation early warning method according to claim 6, characterized in that: In the early warning system, the current threshold is set to 350 amperes and the voltage threshold is set to 11k volts.

8. A distribution cable operation early warning method according to claim 7, characterized in that: The early warning system compares the prediction results with the set current threshold and voltage threshold and obtains the following status: Normal operation: When both the current and voltage values ​​are lower than the threshold, the system will not trigger an early warning; Current overload: When the current value exceeds 350 amperes, the system will trigger a current overload warning; Voltage overload: When the voltage value exceeds 11k volts, the system will trigger a voltage overload warning; Simultaneous overload: When both the current and voltage values ​​exceed their respective thresholds, the system will trigger a simultaneous overload warning.

9. A distribution cable operation early warning method according to claim 6, characterized in that: The alarm mode of the early warning trigger module is selected according to the urgency of the system, including: Audible alarm: for emergency situations that require immediate action; Light Alert: For non-emergency situations that require attention but not immediate action; SMS alerts: Suitable for situations where remote personnel need to be notified.

10. A distribution cable operation early warning device for implementing the method according to any one of claims 1 to 9, characterized in that: It includes a sensor, a microcontroller and an early warning system. The sensor is used to monitor the current, voltage and temperature parameters of the cable. The microcontroller is electrically connected to the sensor and the early warning system to process data and trigger an early warning.

Images