District intelligent sensing digital evaluation method based on fractal theory

Abstract

The invention discloses an intelligent sensing digital evaluation method for a transformer area based on a fractal theory. The method comprises the following steps: S1, collecting power network data of the transformer area; s2, according to the self-similarity and the dynamic change characteristic of the power network data of the transformer area, calculating the fractal dimension of the power network data of the transformer area; and S3, identifying the transformer area fault type based on the obtained fractal dimension. Based on the fractal theory, accurate fault prediction and real-time diagnosis are achieved, comprehensive, accurate and real-time monitoring and evaluation of the power system in the transformer area are achieved, and powerful support is provided for intelligent and fine management of the power system.

Description

Technical Field

[0001] The present invention relates to intelligent management and evaluation technology of electric power system, and in particular to an intelligent perception digital evaluation method of substation based on fractal theory. Background Art

[0002] At present, the operation status evaluation of the power system in the substation mainly relies on traditional physical measurement technology and static model evaluation methods. Although these methods can reflect the operation status of the system to a certain extent, they have certain limitations when dealing with the complexity, dynamics and changing external environment of the power network. With the expansion of the scale of the power system and the integration of multi-dimensional information, grid management requires more intelligent, real-time and refined evaluation methods. Therefore, existing technologies are difficult to meet the growing demand for monitoring and management of substation power networks.

[0003] Grid monitoring based on physical measurement and static evaluation: Traditional power substation monitoring mainly collects voltage, current, load and other data through physical sensors, and then analyzes them in combination with static models. Common methods include voltage stability analysis, load balancing analysis, power flow analysis, etc. These methods can work effectively in a relatively simple grid environment with obvious linear characteristics.

[0004] Time series data analysis and prediction models: In recent years, with the advancement of data acquisition technology, time series data analysis has gradually become an important tool for power grid monitoring. This technology collects and analyzes historical data to predict the load and voltage fluctuations of the power system, and is used for fault detection and trend analysis. Commonly used models include the autoregressive moving average model (ARIMA).

[0005] Grid status assessment based on intelligent algorithms: With the development of artificial intelligence, more and more intelligent algorithms (such as neural networks, support vector machines, etc.) have been introduced into the field of grid status monitoring for optimization prediction and fault detection. These algorithms can use big data to provide more dimensional status information and make intelligent assessments of the grid operation status.

[0006] Distributed monitoring of power systems and application of Internet of Things technology: Internet of Things (IoT) technology is gradually being applied to power systems. Large amounts of real-time data are collected through distributed sensors, and the operating status of power substations is analyzed with the help of cloud computing and big data technologies to achieve remote monitoring and intelligent operation and maintenance.

[0007] Although existing technologies have achieved monitoring and evaluation of power distribution areas to a certain extent, the following problems still exist:

[0008] Lack of dynamics and real-time performance:

[0009] Existing power system assessment methods are mainly based on static data analysis, which can usually only reflect the state of the power grid at a certain moment, but lack the effective capture of the dynamic changes of the system. Since the state of the power grid is dynamic and is often affected by external factors (such as weather, changes in electricity demand, etc.), static assessment is difficult to timely reflect the actual operating status of the power system.

[0010] Insufficient description of complex systems:

[0011] As a complex network system, the distribution substation has multi-level and multi-dimensional characteristics (such as spatial distribution, electrical characteristics, equipment status, etc.). Existing evaluation methods are mostly limited to a single or a few physical indicators, which are difficult to fully reflect the complexity of the system, especially in the analysis of nonlinear behavior and self-similar structure.

[0012] The complexity and diversity of power system data increase the difficulty of modeling and evaluating it. Traditional models and methods are limited to linear analysis methods and are difficult to describe the complex coupling and nonlinear characteristics of the power grid.

[0013] Strong data dependency and inability to handle uncertainty:

[0014] Existing intelligent sensing and monitoring systems rely on a large amount of high-quality data input, but in actual applications, the accuracy and coverage of data acquisition equipment are limited, and some areas may even have missing or erroneous data. This makes the evaluation results susceptible to data quality, resulting in a decrease in the reliability of system monitoring.

[0015] Traditional models fail to fully consider the problem of data uncertainty in their design, and most existing intelligent algorithms are highly dependent on input data and find it difficult to handle abnormal or missing data.

[0016] Insufficient integration and coordination of distributed monitoring:

[0017] Although IoT technology can realize distributed monitoring of the substation area, the integration and communication protocols between various devices may lead to data collection delays, loss or incompatibility issues. This lack of a coordinated monitoring system may affect the overall monitoring effect.

[0018] Different equipment manufacturers use different data collection protocols and standards, resulting in poor interoperability between intelligent sensing devices in the substation area. At the same time, problems such as transmission delays and network bandwidth limitations of IoT devices will also affect the real-time transmission and processing of data. Summary of the invention

[0019] The objective of the present invention is to provide a digital evaluation method for intelligent perception of a power distribution area based on fractal theory. Based on fractal theory, accurate fault prediction and real-time diagnosis are realized, and comprehensive, accurate, and real-time monitoring and evaluation of the power distribution area power system are achieved, providing strong support for the intelligent and refined management of the power system.

[0020] In order to achieve the above objectives, the present invention is realized through the following technical solutions:

[0021] A digital evaluation method for intelligent perception of a power distribution area based on fractal theory is characterized by including the following steps:

[0022] Step S1: Collect power network data of the power distribution area;

[0023] Step S2: Calculate the fractal dimension according to the self-similarity and dynamic change characteristics of the power network data of the power distribution area;

[0024] Step S3: Identify the fault types of the power distribution area based on the obtained fractal dimension.

[0025] The specific content of the above-mentioned step S1 includes: collecting the operation data of the intelligent fusion terminal of the power distribution area and its related acquisition devices.

[0026] The specific content of the above-mentioned step S2 includes:

[0027] According to the self-similarity and dynamic change characteristics of the online status of the devices and the data acquisition status of the intelligent fusion terminal of the power distribution area and its related acquisition devices, calculate the fractal dimensions of the device online rate and the device data acquisition success rate.

[0028] The fractal number D of the device online rate is calculated by the box dimension method. The higher D is, the higher the fluctuation of the online rate is. On the contrary, the lower the online rate is.

[0029] The fractal dimension Dc of the device data acquisition success rate is calculated by the correlation dimension. The higher Dc is, the more剧烈 the fluctuation of the data acquisition success rate is. On the contrary, it means that the data acquisition success rate is monotonically low.

[0030] If D < 1.2 and Dc < 1.1, there is an incompatibility between the intelligent fusion terminal and the related acquisition devices.

[0031] If 1.5 < D < 1.8 and 1.6 < Dc < 2.0, the transmission power of the intelligent fusion terminal is small, the signal attenuation is serious, and it cannot cover the entire power distribution area.

[0032] If 1.3 < D < 1.6 and 1.5 < Dc < 1.8, the signal frequency band of the intelligent fusion terminal does not match the frequency band of the related acquisition devices, and normal communication cannot be carried out.

[0033] If 1.4 < D < 1.7 and 1.6 < Dc < 1.9, the power of the relevant acquisition device is too small.

[0034] If D > 1.6 and Dc > 1.8, it indicates that the power supply radius of the substation area is large and the signal is interfered.

[0035] If D tends to 0 and Dc also tends to 0, the device software runs abnormally.

[0036] If D < 1.1 and Dc < 1.0, it indicates a hardware failure of the device.

[0037] Compared with the prior art, the present invention has the following advantages:

[0038] 1. Through the abnormal detection and evaluation function of the present invention, problems of the substation area integration terminal and related acquisition devices can be discovered and solved in a timely manner, power outages caused by equipment failures can be reduced, and the reliability and safety of power supply can be improved.

[0039] 2. Through the abnormal detection and evaluation function provided by the present invention, maintenance personnel can perform equipment maintenance and troubleshooting more efficiently, reduce unnecessary inspections and maintenance work, and significantly reduce the operation and maintenance costs.

[0040] 3. The present invention significantly reduces the debugging workload of the substation area integration terminal and related acquisition devices through an automated abnormal detection and evaluation method.

[0041] 4. The present invention proposes a detection method of joint debugging and immediate measurement, which can perform performance evaluation and abnormal detection in real time during the equipment debugging process to ensure that the equipment reaches the best state before being put into use. Description of the Drawings

[0042] Figure 1 It is a flowchart of a digital evaluation method for intelligent perception of substation areas based on fractal theory of the present invention. Detailed Embodiment

[0043] The following further elaborates the present invention by describing in detail a preferred specific embodiment in conjunction with the drawings.

[0044] As Figure 1 shown, a digital evaluation method for intelligent perception of substation areas based on fractal theory includes the following steps:

[0045] Step S1, collect power network data of the substation area;

[0046] Step S2, calculate the fractal dimension according to the self-similarity and dynamic change characteristics of the power network data of the substation area;

[0047] Step S3, identify the fault type of the substation area based on the obtained fractal dimension.

[0048] The step S1 specifically includes: collecting the operation data of the area intelligent fusion terminal (CCO) and its related collection device (SAT module).

[0049] For the fault type, online rate characteristics, and data collection success rate characteristics, please see Table 1

[0050] Table 1

[0051]

[0052] The step S2 specifically includes:

[0053] According to the self-similarity and dynamic change characteristics of the equipment online status and data collection status of the intelligent fusion terminal and related collection devices in the substation area, the fractal dimension of the equipment online rate and the equipment data collection success rate is calculated. The fractal dimension is a parameter used to describe the self-similarity of the fractal structure.

[0054] The online rate fractal number D of the computing device is calculated by the box dimension method. The higher D is, the higher the online rate fluctuation is. On the contrary, the online rate is stable and low.

[0055] The fractal dimension Dc of the data collection success rate of the computing device is calculated by the correlation dimension. The higher the Dc, the more drastic the fluctuation of the data collection success rate. On the contrary, the data collection success rate is monotonically low.

[0056] The online rate fractal dimension calculation includes:

[0057] Take the equipment online rate sequence {x1, x2, …, xN} as input (for a period of time) and calculate its fractal dimension.

[0058] Box counting method steps:

[0059] Map the online rate sequence to the time-amplitude two-dimensional space. (Each data point corresponds to a (x,y)(x,y)(x,y), where x is the time and y is the online rate value)

[0060] Count the number of box fillings N(∈) at different scales (divide the data distribution space into a grid, and each unit of the grid is called a "box"; the scale represents the side length of the box. The larger the box, the sparser the grid; the smaller the box, the denser the grid);

[0061] Calculating fractal dimension

[0062] The data acquisition success rate fractal dimension calculation includes:

[0063] Take the success rate sequence {y1,y2,…,yN} as input and calculate its fractal dimension.

[0064] Calculation of correlation dimension:

[0065] Construct delay embedding: Using the delay time τ and the embedding dimension m, convert the time series into a sequence of m-dimensional vectors.

[0066] Calculate the correlation integral C(r): Count the number of point pairs whose distance is less than the threshold r.

[0067] Fit the relationship between log C(r) and log r to obtain the fractal dimension:

[0068] If D < 1.2 and Dc < 1.1, there is an incompatibility between the intelligent fusion terminal and the relevant acquisition device, resulting in communication failure or instability.

[0069] If 1.5 < D < 1.8 and 1.6 < Dc < 2.0, the transmission power of the intelligent fusion terminal is small, the signal attenuation is serious, and it cannot cover the entire substation area.

[0070] If 1.3 < D < 1.6 and 1.5 < Dc < 1.8, the signal frequency band of the intelligent fusion terminal does not match the frequency band of the relevant acquisition device, and normal communication cannot be carried out.

[0071] If 1.4 < D < 1.7 and 1.6 < Dc < 1.9, the power of the relevant acquisition device is too small to transmit data stably.

[0072] If D > 1.6 and Dc > 1.8, it indicates that the power supply radius of the substation area is large, the signal is interfered, attenuated seriously, and the communication quality deteriorates.

[0073] If D tends to 0 and Dc also tends to 0, the device software runs abnormally and the device cannot work properly;

[0074] If D < 1.1 and Dc < 1.0, it indicates that there is a hardware failure in the device and the device cannot work properly.

[0075] For the specific determination of relevant fault types, please refer to Table 2:

[0076] Table 2

[0077]

[0078] In summary, a digital evaluation method for intelligent perception of substation areas based on fractal theory according to the present invention, based on fractal theory, realizes accurate fault prediction and real-time diagnosis, realizes comprehensive, accurate and real-time monitoring and evaluation of the substation area power system, and provides strong support for the intelligent and refined management of the power system.

[0079] It should be noted that, in the embodiments of the present invention, the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0080] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0081] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.

Claims

1. A digital evaluation method for intelligent perception of substations based on fractal theory, characterized in that: It includes the following steps: Step S1, collect the power network data of the substation area; Step S2, calculate its fractal dimension according to the self-similarity and dynamic change characteristics of the power network data in the substation area; Step S3, identify the fault type of the substation area based on the obtained fractal dimension.

2. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 1, characterized in that: The specific content of the said Step S1 includes: collect the operation data of the intelligent fusion terminal in the substation area and its related collection devices.

3. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 2, characterized in that: The specific content of the said Step S2 includes: According to the self-similarity and dynamic change characteristics of the online status of the equipment and the data collection status of the intelligent fusion terminal in the substation area and related collection devices, calculate the fractal dimensions of the equipment online rate and the equipment data collection success rate.

4. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 2, characterized in that: The fractal number D of the calculated equipment online rate is calculated by the box dimension method. The higher D is, the higher the fluctuation of the online rate is. On the contrary, the online rate is stably low.

5. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 4, characterized in that: The fractal dimension Dc of the calculated equipment data collection success rate is calculated by the correlation dimension. The higher Dc is, the more剧烈 the fluctuation of the data collection success rate is. On the contrary, it means that the data collection success rate is monotonously low.

6. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 5, characterized in that: If D < 1.2 and Dc < 1.1, there is an incompatibility between the intelligent fusion terminal and the related collection devices.

7. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 5, characterized in that: If 1.5 < D < 1.8 and 1.6 < Dc < 2.0, the transmission power of the intelligent fusion terminal is small, the signal attenuation is serious, and it cannot cover the entire substation area.

8. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 5, characterized in that: If 1.3 < D < 1.6 and 1.5 < Dc < 1.8, the signal frequency band of the intelligent fusion terminal does not match the frequency band of the related collection devices, and normal communication cannot be carried out.

9. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 5, characterized in that: If 1.4 < D < 1.7 and 1.6 < Dc < 1.9, the power of the related collection device is too small.

10. The method for digital evaluation of intelligent perception of a station area based on fractal theory as claimed in claim 5, characterized in that: If D > 1.6 and Dc > 1.8, it indicates that the power supply radius of the substation area is large and the signal is interfered; If D tends to 0 and Dc also tends to 0, the equipment software runs abnormally; If D < 1.1 and Dc < 1.0, it indicates that there is a hardware fault in the equipment.

Images