Generator, transformer protection setting value automatic generation system and method

Abstract

The invention provides a generator and transformer protection setting value automatic generation system and method, and relates to the technical field of electrical protection parameter setting. By extracting voltage and current signals before a fault and corresponding setting values, a historical data chain is constructed; the real-time data acquisition module provides the real-time sensing capability of the system for the current operation state, a setting data link can be dynamically generated by acquiring voltage and current signals of a generator or a transformer, the current operation state of the system can be reflected in real time, and the signal processing module performs feature extraction on the voltage and current signals to obtain the current operation state of the system. A historical data link closest to the current state can be quickly matched and recognized, a data link matching module finds the historical data link most matched with the current running state in a historical knowledge base by calculating the error degree, and a setting value generation module achieves automatic generation of a protection setting value by referring to the protection setting value of the optimal historical data link.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical protection parameter setting, and in particular to a system and method for automatically generating protection setting values ​​of generators and transformers. Background Art

[0002] As power systems continue to expand and become more complex, the importance of setting protection settings for generators and transformers has become increasingly prominent. Protection settings refer to key parameters that enable protection devices to accurately identify fault types and quickly take appropriate measures in the event of a fault. The accuracy of these values ​​directly affects the safe operation of the equipment and the stability of the entire system.

[0003] In traditional technology, the setting of protection setting values ​​mostly depends on the experience of engineers and historical operating data. Usually, engineers manually set the setting values ​​through static analysis of the power system. However, this method is powerless in the face of dynamic changes in the power system, especially in the case of frequent load fluctuations and complex failure modes, the efficiency and accuracy of manual adjustment are limited.

[0004] Existing manual setting methods face many challenges. First, the manual setting process is complicated and can easily lead to improper parameter settings, which in turn affects the performance of the protection device. Second, as the system state is constantly changing, the fixed setting value cannot reflect the current operating conditions in real time, which may cause the protection device to malfunction or refuse to operate. In addition, the lack of intelligent and automated means makes it difficult for the system to take advantage of big data and algorithms, and cannot achieve rapid response and adaptive adjustment. Therefore, there is an urgent need for a system that can automatically generate and adjust setting values ​​to improve the safety and adaptability of the power system.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The object of the present invention is to provide a system and method for automatically generating protection setting values ​​of generators and transformers to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A system for automatically generating protection setting values ​​of generators and transformers, comprising:

[0009] A historical database construction module is used to extract the fault data that has occurred from the historical data and construct a historical knowledge base, wherein the fault data includes the voltage and current signals at the output end of the generator or transformer within a time interval of T before the fault occurs and the corresponding protection setting values, and the voltage signal, current signal and setting value are associated to form a historical data chain and stored in the historical knowledge base with a number;

[0010] The real-time data acquisition module is used to take the current moment as the end point of the time sequence, trace back the time length T as the start point of the time sequence, respectively obtain the voltage signal and current signal of the output end of the generator or transformer between the start point of the time sequence and the end point of the time sequence, and associate the voltage signal and the current signal to form a setting data chain;

[0011] The signal processing module is used to divide the current signal and voltage signal in the setting data chain and the historical data chain into time windows of equal length, and number the time windows in chronological order to obtain the current signal and voltage signal segments corresponding to multiple time windows, and use Fourier transform to obtain the voltage characteristic data and current characteristic data in each time window;

[0012] The data link matching module is used to traverse all historical data links, generate the error between the setting data link and each historical data link according to the voltage characteristic data and current characteristic data in each time window in the setting data link and the historical data link, and select the best historical data link;

[0013] The setting value generation module is used to obtain the protection setting value in the best historical data chain and set it as the reference protection setting value, and use the reference protection setting value as the automatically generated protection setting value.

[0014] Furthermore, the output end of the generator is a port for transmitting electric energy to the power network or the load, and the output end of the transformer is the secondary side of the transformer. The historical knowledge base stores historical data chain data corresponding to all faults that have occurred in the generator or transformer, and the form of the historical data chain is:

[0015] LS i =[LV(t i -T, t i ), LI(t i -T, t i ), ZD i ]

[0016] Among them, Ls i Indicates the historical data chain numbered i in the historical knowledge base, LV(t i -T, t i ) and LI(t i -T, t i) represent the i-th historical data chain, at t i -T time to t i The output voltage signal data and current signal data at the moment, ZD i The protection setting value data set in the i-th historical data chain, t i is the corresponding fault occurrence event in the i-th historical data chain;

[0017] The form of the setting data link is:

[0018] Zs=[SV(t0-T, t0), SI(t0-T, t0), ZD0]

[0019] Among them, Zs represents the setting data chain, SV(t0-T, t0) and SI(t0-T, t0) respectively represent the output voltage signal data and current signal data of the device to be protected and set from t0-T to t0, t0 is the current moment, and ZD0 is the set of protection setting values ​​to be determined.

[0020] Furthermore, the specific logic of segmenting the current signal and voltage signal in the historical data chain using time windows of equal length is as follows:

[0021] According to the time sequence, n continuous time windows with a width of ω are used to divide the voltage signal data and the current signal data respectively, and n*ω=T, and the voltage signal and current signal segments corresponding to each generated time window are calibrated as follows:

[0022] LV i (1) LV i (2), …, LV i (m),…,LV i (n)

[0023] LI i (1) LI i (2),…,LI i (m),…,LI i (n)

[0024] Among them, LV i (m) and LI i (n) respectively represent the voltage signal and current signal fragments corresponding to the mth time window in the ith historical data chain, m is a positive integer, and 1≤m≤n.

[0025] Furthermore, for the setting data chain, n continuous time windows with a width of ω are also used to divide the setting data chain, and the current signal and voltage signal segments corresponding to each time window of the setting data chain are calibrated as follows:

[0026] SV(1), SV(2),…,SV(m),…,SV(n)

[0027] SI(1), SI(2),…,SI(m),…,SI(n)

[0028] Wherein, SV(m) and SI(m) represent the voltage signal and current signal segments corresponding to the mth time window in the setting data chain, respectively.

[0029] Furthermore, after Fourier transform is performed on the current signal and voltage signal fragments corresponding to the time window, the voltage signal or current signal fragment is transformed into the form of the sum of a series of complex numbers through Fourier transform, the number of complex numbers is represented as the number of frequency components of the corresponding fragments, the imaginary part of the frequency component of each complex number is represented as the phase of the corresponding frequency component, and the real part of the frequency component of each complex number is represented as the amplitude of the corresponding frequency component. The centroid frequency of the voltage and current in each time window is calculated as the voltage characteristic data and the current characteristic data. The logic for calculating the centroid frequency of each time window in the historical data chain is as follows:

[0030]

[0031] in, They represent the centroid frequencies of the voltage signal and current signal fragments in the mth time window in the ith historical data chain, ALV i (m) p and flv i (m) p They represent the amplitude and phase of the pth frequency component of the voltage signal in the mth time window in the ith historical data chain after Fourier transformation, ALI i (m) q and flv i (m) q They respectively represent the amplitude and phase of the qth frequency component of the current signal in the mth time window in the ith historical data chain after Fourier transform, and P and Q respectively represent the number of frequency components of the voltage signal and current signal in the mth time window in the ith historical data chain after Fourier transform.

[0032] Furthermore, the logic for calculating the center of gravity frequency of each time window in the setting data link is:

[0033]

[0034] Among them, F SV(m) and F SV(m) Respectively represent the centroid frequency of the voltage signal and current signal fragment corresponding to the mth time window in the setting data chain, ASV(m) u and fSV(m)u They represent the amplitude and phase of the uth frequency component of the voltage signal in the mth time window after Fourier transformation in the setting data chain, ASI(m) v and fSI(m) v They respectively represent the amplitude and phase of the vth frequency component of the current signal in the mth time window in the setting data chain after Fourier transform. U and V respectively represent the number of frequency components of the voltage signal and current signal in the mth time window in the setting data chain after Fourier transform.

[0035] Furthermore, the formula for generating the error between the set data link and the historical data link is:

[0036]

[0037] Among them, PD i It represents the error between the setting data chain and the i-th historical data chain, α and β are the voltage weight and current weight respectively, 0<α<β, and α+β=1.

[0038] Furthermore, when selecting the best historical data chain, the historical data chain with the smallest error between it and the setting data chain is used as the best historical data chain, and the protection setting value set to be determined is set as the protection setting value data set in the best historical data chain.

[0039] The present invention further provides a method for automatically generating protection setting values ​​of generators and transformers. The method for automatically generating protection setting values ​​of generators and transformers is obtained by executing the above-mentioned automatic generation system for protection setting values ​​of generators and transformers, and the specific steps include:

[0040] Step 1: Extract the fault data that has occurred from the historical data and build a historical knowledge base. The fault data includes the voltage and current signals at the output end of the generator or transformer within the time interval T before the fault occurs and the corresponding protection setting value. The voltage signal, current signal and setting value are associated to form a historical data chain and stored in the historical knowledge base with a number.

[0041] Step 2: Take the current moment as the end point of the time series, trace back T time length as the start point of the time series, obtain the voltage signal and current signal of the output end of the generator or transformer between the start point of the time series and the end point of the time series, and associate the voltage signal and the current signal to form a setting data chain;

[0042] Step 3: Divide the current signal and voltage signal in the setting data chain and the historical data chain into time windows of equal length, and number the time windows in chronological order to obtain the current signal and voltage signal segments corresponding to multiple time windows, and use Fourier transform to obtain the voltage characteristic data and current characteristic data in each time window;

[0043] Step 4: Traverse all historical data chains, generate the error between the setting data chain and each historical data chain according to the voltage characteristic data and current characteristic data in each time window in the setting data chain and the historical data chain, and select the best historical data chain;

[0044] Step 5: Obtain the protection setting value in the best historical data chain and set it as the reference protection setting value, and use the reference protection setting value as the automatically generated protection setting value.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention can effectively accumulate and manage fault data information and form historical knowledge through the use of the historical library construction module. This module constructs a detailed historical data chain by extracting the voltage and current signals before the fault and the corresponding setting values. This method ensures that when the system automatically generates the setting values, it can improve the accuracy and reliability of the setting values ​​based on rich historical cases. The real-time data acquisition module provides the system with the ability to instantly perceive the current operating status. By acquiring the voltage and current signals of the generator or transformer, the module can dynamically generate a setting data chain to reflect the current operating status of the system in real time. This acquisition and analysis of real-time data avoids the problem of the inability to adjust the setting values ​​in a timely manner in traditional methods.

[0047] The present invention also uses Fourier transform to extract features of voltage and current signals through the signal processing module, further improving the accuracy and efficiency of data analysis. By dividing the signal into equal time windows and extracting feature data, when processing a large amount of historical data, it can quickly match and identify the historical data chain closest to the current state. The data chain matching module calculates the error degree and accurately finds the historical data chain that best matches the current operating state in the historical knowledge base. This process ensures the optimality of the selected reference protection setting value under current conditions, thereby improving the response speed and accuracy of the system. The setting value generation module realizes the automatic generation of protection setting values ​​by referring to the protection setting value of the best historical data chain. This automated setting value setting method solves the problem of time-consuming and error-prone manual setting in traditional methods, and significantly improves the safety and stability of the power system.

[0048] In summary, the present invention successfully solves the problems of untimely response and reliance on experience in traditional setting value methods through a modular automatic generation system combined with historical and real-time data analysis, and significantly improves the protection performance of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the overall system structure of the present invention;

[0050] Figure 2 It is a schematic diagram of the overall method flow of the present invention. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0052] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0053] Example:

[0054] See also Figure 1 , the present invention provides a technical solution:

[0055] A generator and transformer protection setting value automatic generation system includes a history library construction module, a real-time data acquisition module, a signal processing module, a data link matching module, and a setting value generation module, wherein:

[0056] The historical database construction module is used to extract the fault data that has occurred from the historical data and construct a historical knowledge base. The fault data includes the voltage and current signals at the output end of the generator or transformer within a time interval of T before the fault occurs and the corresponding protection setting values. The voltage signal, current signal and setting value are associated to form a historical data chain and are numbered and stored in the historical knowledge base.

[0057] The specific logic of building a historical knowledge base is:

[0058] Extract fault data from historical records, including voltage and current signals within a specified time period (T time length) before the fault occurs, and the corresponding protection setting values. Associate the collected voltage and current signals with the protection setting values ​​to form a complete data chain, ensuring that each set of data can reflect the operating conditions and protection settings before the fault, and then number each data chain for subsequent retrieval and analysis. Store the numbered data chains in the historical knowledge base to form a structured database, which provides a basis for fault analysis and future setting optimization. By systematically collecting and organizing historical fault data, it can effectively support subsequent fault analysis and protection strategy optimization.

[0059] The protection setting of generators and transformers is performed separately. Each device has its own specific operating characteristics and protection requirements, so the protection parameters need to be set independently. Generator protection setting includes overcurrent protection, over / undervoltage protection, loss of synchronization protection and differential protection. Transformer protection setting includes differential protection, overcurrent protection, over / undervoltage protection and gas protection.

[0060] In the power system, voltage and current signals are the most direct and critical parameters, which can fully describe the dynamic behavior and state of the system. Voltage and current are not only the core indicators of power transmission and energy efficiency, but also directly reflect the operation of the equipment. Most power faults will show specific abnormal patterns on these signals. Therefore, by analyzing voltage and current, faults can be quickly identified and located to ensure system safety. In addition, the protection mechanism of the power system mostly relies on the changes of these two signals to ensure the accuracy and sensitivity of the protection equipment. Voltage and current signals also simplify the calculation of power and energy, facilitating real-time monitoring and control. Since these signals can provide enough information to meet key needs such as fault diagnosis, system protection and energy management, there is no need to collect other signals to complete these core tasks.

[0061] In this embodiment, the output end of the generator is a port for transmitting electric energy to the power network or the load, and the output end of the transformer is the secondary side of the transformer. The historical knowledge base stores historical data chain data corresponding to all faults that have occurred in the generator or transformer. The form of the historical data chain is:

[0062] LS i =[LV(t i -T, t i ), LI(t i -T, t i ), ZD i ]

[0063] Among them, Ls i Indicates the historical data chain numbered i in the historical knowledge base, LV(t i -T, ti ) and LI(t i -T, t i ) represent the i-th historical data chain, at t i -T time to t i The output voltage signal data and current signal data at the moment, ZD i The protection setting value data set in the i-th historical data chain, t i is the corresponding fault occurrence event in the i-th historical data chain.

[0064] By recording the voltage and current signals before the fault, we can fully understand the system status when the fault occurs. This helps to accurately identify the fault type and its cause, combine the current and voltage signals with the protection setting value, ensure that all relevant factors are taken into account when analyzing the fault, reduce the possibility of misjudgment, and establish a historical knowledge base so that when analyzing new faults, we can compare historical data, quickly identify similar fault modes, and improve analysis efficiency.

[0065] The real-time data acquisition module is used to take the current moment as the end point of the timing sequence, trace back T time length as the start point of the timing sequence, respectively obtain the voltage signal and current signal of the output end of the generator or transformer between the start point of the timing sequence and the end point of the timing sequence, and associate the voltage signal and the current signal to form a setting data chain.

[0066] In this embodiment, the form of the setting data link is:

[0067] Zs=[SV(t0-T, t0), SI(t0-T, t0), ZD0]

[0068] Among them, Zs represents the setting data chain, SV(t0-T, t0) and SI(t0-T, t0) respectively represent the output voltage signal data and current signal data of the device to be protected and set from t0-T to t0, t0 is the current moment, and ZD0 is the set of protection setting values ​​to be determined.

[0069] Tracing back the T time length can capture the dynamic changes before the fault, which is helpful for comprehensive fault analysis, comparison with historical data, enhancing the accuracy of fault identification, reducing misjudgment, and achieving rapid response through real-time analysis and data association, and collecting voltage and current signals within the set time range. The collected data are associated to form a setting data chain, and the formed data chain is used to compare with historical data to determine the protection setting value. Through comprehensive data support, the protection setting value is optimized, misjudgment is reduced, faults are identified more accurately, and the safety and stability of the system are improved. Tracing back the T time length can correspond to the historical data chain. By comparing with historical data, the similarity between the current fault and the previous fault can be identified, so as to more accurately determine the setting value, ensure that the current collected data is consistent with the historical data in time length and format, which is convenient for analysis and comparison. By comparing historical patterns, similar fault patterns can be quickly identified, and the efficiency and accuracy of fault analysis can be improved. This method helps to use historical experience in fault analysis and improve the responsiveness and reliability of the system.

[0070] This embodiment can effectively accumulate and manage fault data information and form historical knowledge through the use of the historical library construction module. This module constructs a detailed historical data chain by extracting the voltage and current signals before the fault and the corresponding setting values. This method ensures that when the system automatically generates the setting value, it can improve the accuracy and reliability of the setting value based on rich historical cases. The real-time data acquisition module provides the system with the ability to instantly perceive the current operating status. By acquiring the voltage and current signals of the generator or transformer, the module can dynamically generate a setting data chain to reflect the current operating status of the system in real time. This acquisition and analysis of real-time data avoids the problem that the setting value cannot be adjusted in time in the traditional method.

[0071] The signal processing module is used to divide the current signals and voltage signals in the setting data chain and the historical data chain into time windows of equal length, and number the time windows in chronological order to obtain current signal and voltage signal segments corresponding to multiple time windows, and use Fourier transform to obtain voltage characteristic data and current characteristic data in each time window.

[0072] In this embodiment, the specific logic of segmenting the current signal and the voltage signal in the historical data chain using time windows of equal length is:

[0073] According to the time sequence, n continuous time windows with a width of ω are used to divide the voltage signal data and the current signal data respectively, and n*ω=T, and the voltage signal and current signal segments corresponding to each generated time window are calibrated as follows:

[0074] LV i (1) LVi (2), …, LV i (m),…,LV i (n)

[0075] LI i (1) LI i (2),…,LI i (m),…,LI i (n)

[0076] Among them, LV i (m) and LI i (n) respectively represent the voltage signal and current signal fragments corresponding to the mth time window in the ith historical data chain, m is a positive integer, and 1≤m≤n.

[0077] Furthermore, for the setting data chain, n continuous time windows with a width of ω are also used to divide the setting data chain, and the current signal and voltage signal segments corresponding to each time window of the setting data chain are calibrated as follows:

[0078] SV(1), SV(2),…,SV(m),…,SV(n)

[0079] SI(1), SI(2),…,SI(m),…,SI(n)

[0080] Among them, SV(m) and SI(m) respectively represent the voltage signal and current signal segments corresponding to the mth time window in the setting data chain. Since both the historical data chain and the setting data chain are divided into n continuous time windows with a width of ω, the time windows are numbered in a sequence from 1 to n for both the historical data chain and the setting data chain.

[0081] The voltage and current signals in the historical data chain and the setting data chain are divided into time windows of equal length to ensure that the length and number of time windows between the historical data chain and the setting data chain are consistent, which is convenient for comparative analysis. By dividing the signal, the change of the signal can be observed at a finer granularity, which is helpful to identify the fault characteristics. The time domain signal is converted to the frequency domain by Fourier transform, which can more clearly identify the frequency characteristics of the signal. Feature extraction in the subdivided time window can more accurately reflect the signal change, improve the analysis accuracy, provide richer feature information, support more comprehensive fault identification and diagnosis, and simplify the data processing process and improve efficiency through consistent segmentation and analysis methods.

[0082] In this embodiment, after Fourier transform is performed on the current signal and voltage signal segments corresponding to the time window, the voltage signal or current signal segment is transformed into the form of the sum of a series of complex numbers through Fourier transform, the number of complex numbers is represented as the number of frequency components of the corresponding segment, the imaginary part of the frequency component of each complex number is represented as the phase of the corresponding frequency component, and the real part of the frequency component of each complex number is represented as the amplitude of the corresponding frequency component. The centroid frequency of the voltage and current in each time window is calculated as the voltage characteristic data and the current characteristic data. The logic for calculating the centroid frequency of each time window in the historical data chain is as follows:

[0083]

[0084] in, They represent the centroid frequencies of the voltage signal and current signal fragments in the mth time window in the ith historical data chain, ALV i (m) p and flv i (m) p They represent the amplitude and phase of the pth frequency component of the voltage signal in the mth time window in the ith historical data chain after Fourier transformation, ALI i (m) q and flv i (m) q They respectively represent the amplitude and phase of the qth frequency component of the current signal in the mth time window in the ith historical data chain after Fourier transform, and P and Q respectively represent the number of frequency components of the voltage signal and current signal in the mth time window in the ith historical data chain after Fourier transform.

[0085] In this embodiment, the voltage and current signal segments are converted into the complex sum of frequency components by Fourier transform, each complex number consisting of amplitude and phase. This conversion can simplify the complex changes of the time domain signal into several basic components in the frequency domain, which is conducive to analyzing the frequency characteristics of the signal. The calculation of the center of gravity frequency is to summarize the comprehensive characteristics of each frequency component, and a frequency reflecting the overall characteristics of the signal is obtained by weighted averaging. The weighted average in the formula uses the amplitude of the frequency component as the weight, because the amplitude reflects the significance of each frequency component in the signal.

[0086] Specifically, the center of gravity frequency and The calculation formula obtains the representative frequency of the signal in the time window by weighted summing the amplitude and frequency of the frequency component and then dividing it by the total amplitude sum. This calculation logic ensures that the contribution of the frequency component to the signal is proportional to its amplitude, that is, the frequency component with larger amplitude has a greater impact on the center of gravity frequency, and can more accurately reflect the overall characteristics of the signal. Through this method, complex frequency domain information can be simplified into a characteristic value that is easy to compare and analyze, thereby improving the efficiency and accuracy of signal processing.

[0087] The centroid frequency can represent the signal characteristics within a window, mainly because it combines the contributions of each frequency component into a single eigenvalue. The Fourier transform decomposes the signal into different frequency components, each with a specific amplitude and phase. The amplitude represents the strength or contribution of the frequency component in the entire signal. The centroid frequency is calculated by weighting the amplitude of each frequency component and averaging it, which is similar to the concept of center of mass in physics. The denominator in the formula is the sum of the amplitudes, ensuring that the weighted average is calculated rather than the simple average. Since the frequency components with large amplitudes contribute more to the centroid frequency, this eigenvalue can effectively highlight the most significant frequency components in the signal and reflect the overall characteristics of the signal. The centroid frequency simplifies the multi-dimensional frequency information into a scalar indicator, making comparison and analysis between different time windows more convenient.

[0088] Furthermore, the logic for calculating the center of gravity frequency of each time window in the setting data link is:

[0089]

[0090] Among them, F SV(m) and F SV(m) Respectively represent the centroid frequency of the voltage signal and current signal fragment corresponding to the mth time window in the setting data chain, ASV(m) u and fSV(m) u They represent the amplitude and phase of the uth frequency component of the voltage signal in the mth time window after Fourier transformation in the setting data chain, ASI(m) v and fSI(m) v They respectively represent the amplitude and phase of the vth frequency component of the current signal in the mth time window in the setting data chain after Fourier transform. U and V respectively represent the number of frequency components of the voltage signal and current signal in the mth time window in the setting data chain after Fourier transform.

[0091] The setting data link and the historical data link use the same logic when calculating the center of gravity frequency because both need to extract the frequency characteristics of the signal for effective comparison and analysis. The same method is used to calculate the center of gravity frequency to ensure that the feature extraction standards of the historical data and the setting data are consistent, which helps to compare the features between different data sets. The main frequency components of the signal are extracted through the center of gravity frequency. Whether it is historical data or setting data, this method can effectively capture signal characteristics and facilitate identification and analysis. In further analysis, the comparison of the center of gravity frequency between historical data and setting data can reveal the changes and trends of the signal, so the same calculation basis is required. In order to ensure the simplicity and efficiency of the signal processing process, a unified feature extraction method is used to reduce calculation complexity and errors. Through this consistent method, it is ensured that the signal characteristics in different time windows and different data links can be accurately and effectively extracted and compared.

[0092] The center of gravity frequencies of voltage and current need to be calculated separately because they have different physical meanings and characteristics in the power system. Voltage and current exhibit different dynamic characteristics and change patterns in the circuit. Analyzing them separately helps to accurately capture their respective characteristics. Voltage and current signals may be affected by different factors, such as load changes, faults, etc., so they need to be analyzed separately to identify specific problems.

[0093] The data link matching module is used to traverse all historical data links, generate the error between the setting data link and each historical data link according to the voltage characteristic data and current characteristic data in each time window in the setting data link and the historical data link, and select the best historical data link.

[0094] The formula for generating the error between the set data link and the historical data link is:

[0095]

[0096] Among them, PD i It represents the error between the setting data chain and the i-th historical data chain, α and β are the voltage weight and current weight respectively, 0<α<β, and α+β=1.

[0097] By traversing all historical data chains and comparing them with the setting data chain, the best historical data chain is selected. Specifically, in each time window, the voltage and current characteristic data of the setting data chain are compared with each historical data chain. Using the error degree formula, the difference between the setting data chain and each historical data chain can be calculated. The error degree in the formula consists of two parts: voltage error and current error, which are weighted and summed separately. The weight is used to adjust the impact of voltage and current errors on the overall error degree, and the importance of current characteristics is slightly higher than that of voltage. The error calculation is the sum of the absolute values ​​of the difference between the characteristic data of the two chains, and normalized by the sum of the characteristic data of the setting data chain.

[0098] PD i Represents the error between the setting data chain and the i-th historical data chain. The larger the value, the greater the difference, and the smaller the value, the more similar the two are. Therefore, by selecting the historical data chain with the smallest error, the chain that best matches the current setting data can be found for further analysis or optimization. The impact of current on the system is usually more direct. For example, excessive current may cause equipment overheating, increased power loss, and electromagnetic interference. Therefore, in many application scenarios, the change in current characteristics is more concerned, so the impact of current changes is more significant, so a higher weight is given in the error calculation to reflect its importance. This setting can more accurately reflect the system's sensitivity to current characteristics. α+β=1 ensures that the weights are normalized so that the sum of the effects of voltage and current is 1. This provides a fixed ratio framework for easy balance adjustment between voltage and current.

[0099] The setting value generation module is used to obtain the protection setting value in the best historical data chain and set it as the reference protection setting value, and use the reference protection setting value as the automatically generated protection setting value.

[0100] In this embodiment, the protection setting of the generator and transformer is processed through independent data links, ensuring the accurate allocation of the setting parameters. The setting parameters of the generator will not be allocated to the transformer. Each device (generator or transformer) has a dedicated historical data link and a setting data link. These data links are stored and processed separately according to the device type, ensuring the independence of the data. During the data acquisition and processing stage, the voltage and current signals will be feature extracted and marked as the characteristics of the generator or transformer. This device identification ensures the specificity of subsequent analysis and setting parameter generation. During the error calculation process, only the historical data link of the corresponding device type will be compared with the current setting data link. Therefore, the real-time data link of the generator will only match the historical data link of the generator, and the same is true for the transformer.

[0101] In addition, from the perspective of voltage and current, the operating characteristics and parameter ranges of generators and transformers are usually significantly different, which can also effectively prevent the incorrect allocation of setting parameters. Generators and transformers are generally designed and operated at different voltage levels. The voltage output of generators is usually low, while transformers may involve higher step-up or step-down voltages. This difference reduces the possibility of mismatching. Generators and transformers also have different characteristics of the current they withstand during operation. Generators usually have higher short-circuit currents, while the current characteristics of transformers are greatly affected by the load. These characteristics will reflect different patterns in signal processing, and the protection setting parameters of each device have specific ranges and setting standards. For example, the setting value of overcurrent protection will be set according to the physical characteristics and safe operation standards of the equipment, so the matching of parameters has strict upper and lower limits. Through these technical features, the system can effectively identify and distinguish the voltage and current characteristics of different devices and avoid the incorrect allocation of setting parameters.

[0102] In this embodiment, when selecting the best historical data chain, the historical data chain with the smallest error between it and the setting data chain is used as the best historical data chain, and the protection setting value set to be determined is set as the protection setting value data set in the best historical data chain.

[0103] In the process of selecting the best historical data chain, the error between the current setting data chain and each historical data chain must first be calculated. This calculation is based on the voltage and current characteristic data, and the contribution of different characteristics to the error is balanced by pre-set weight parameters. The error calculation formula reflects the difference in characteristic data between the current setting data chain and the historical data chain. The smaller the value, the more similar the two are. All calculated errors are compared to identify the historical data chain with the smallest error. The chain with the smallest error is selected because its characteristic data is closest to the current system conditions and can therefore provide the most valuable historical information. This process ensures that the selected historical data chain is the most relevant in the current environment and reflects the performance of the system under similar conditions.

[0104] Finally, the protection setting data set is extracted from the selected best historical data chain and set as the reference protection setting value. These settings are considered to be the most appropriate automatically generated protection settings because they are based on the data chain that historically best matches the current conditions. This process improves the accuracy of protection settings and ensures that the system can maintain the best protection performance under new or changing conditions. This logic ensures that the selected setting value best matches the current system conditions, thereby improving the accuracy and effectiveness of protection settings.

[0105] This embodiment also uses Fourier transform to extract features of voltage and current signals through the signal processing module, further improving the accuracy and efficiency of data analysis. By dividing the signal into equal time windows and extracting feature data, it can quickly match and identify the historical data chain closest to the current state when processing a large amount of historical data. The data chain matching module calculates the error degree and accurately finds the historical data chain that best matches the current operating state in the historical knowledge base. This process ensures the optimality of the selected reference protection setting value under current conditions, thereby improving the response speed and accuracy of the system. The setting value generation module realizes the automatic generation of protection setting values ​​by referring to the protection setting value of the best historical data chain. This automated setting value setting method solves the problem of time-consuming and error-prone manual setting in traditional methods, and significantly improves the safety and stability of the power system.

[0106] In summary, this embodiment successfully solves the problems of untimely response and reliance on experience in traditional setting value methods by using a modular automatic generation system combined with historical and real-time data analysis, and significantly improves the protection performance of the power system.

[0107] See also Figure 2 The present invention also provides a method for automatically generating protection setting values ​​of generators and transformers. The method for automatically generating protection setting values ​​of generators and transformers is obtained by executing the above-mentioned automatic generation system for protection setting values ​​of generators and transformers. The specific steps include:

[0108] Step 1: Extract the fault data that has occurred from the historical data and build a historical knowledge base. The fault data includes the voltage and current signals at the output end of the generator or transformer within the time interval T before the fault occurs and the corresponding protection setting value. The voltage signal, current signal and setting value are associated to form a historical data chain and stored in the historical knowledge base with a number.

[0109] Step 2: Take the current moment as the end point of the time series, trace back T time length as the start point of the time series, obtain the voltage signal and current signal of the output end of the generator or transformer between the start point of the time series and the end point of the time series, and associate the voltage signal and the current signal to form a setting data chain;

[0110] Step 3: Divide the current signal and voltage signal in the setting data chain and the historical data chain into time windows of equal length, and number the time windows in chronological order to obtain the current signal and voltage signal segments corresponding to multiple time windows, and use Fourier transform to obtain the voltage characteristic data and current characteristic data in each time window;

[0111] Step 4: Traverse all historical data chains, generate the error between the setting data chain and each historical data chain according to the voltage characteristic data and current characteristic data in each time window in the setting data chain and the historical data chain, and select the best historical data chain;

[0112] Step 5: Obtain the protection setting value in the best historical data chain and set it as the reference protection setting value, and use the reference protection setting value as the automatically generated protection setting value.

[0113] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0114] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0115] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A system for automatically generating protection setting values ​​for generators and transformers, characterized in that: include: A historical database construction module is used to extract the fault data that has occurred from the historical data and construct a historical knowledge base, wherein the fault data includes the voltage and current signals at the output end of the generator or transformer within a time interval of T before the fault occurs and the corresponding protection setting values, and the voltage signal, current signal and setting value are associated to form a historical data chain and stored in the historical knowledge base with a number; The real-time data acquisition module is used to take the current moment as the end point of the time sequence, trace back the time length T as the start point of the time sequence, respectively obtain the voltage signal and current signal of the output end of the generator or transformer between the start point of the time sequence and the end point of the time sequence, and associate the voltage signal and the current signal to form a setting data chain; The signal processing module is used to divide the current signal and voltage signal in the setting data chain and the historical data chain into time windows of equal length, and number the time windows in chronological order to obtain the current signal and voltage signal segments corresponding to multiple time windows, and use Fourier transform to obtain the voltage characteristic data and current characteristic data in each time window; The data link matching module is used to traverse all historical data links, generate the error between the setting data link and each historical data link according to the voltage characteristic data and current characteristic data in each time window in the setting data link and the historical data link, and select the best historical data link; The setting value generation module is used to obtain the protection setting value in the best historical data chain and set it as the reference protection setting value, and use the reference protection setting value as the automatically generated protection setting value.

2. The automatic generation system of protection setting values ​​of generators and transformers according to claim 1 is characterized in that: The output end of the generator is the port for transmitting electric energy to the power network or load, and the output end of the transformer is the secondary side of the transformer. The historical knowledge base stores historical data chain data corresponding to all faults that have occurred in the generator or transformer. The form of the historical data chain is: Ls i =[LV(t i ―T,t i ),LI(t i ―T,t i ),ZD i ] Among them, Ls i Indicates the historical data chain numbered i in the historical knowledge base, LV(t i ―T, t i ) and LI(t i ―T, t i ) represent the i-th historical data chain, at t i - Time T to t i The output voltage signal data and current signal data at the moment, ZD i The protection setting value data set in the i-th historical data chain, t i is the corresponding fault occurrence event in the i-th historical data chain; The form of the setting data link is: Zs=[SV(t0-T, t0), SI(t0-T, t0), ZD0] Among them, Zs represents the setting data chain, SV(t0-T, t0) and SI(t0-T, t0) respectively represent the output voltage signal data and current signal data of the device to be protected and set from t0-T to t0, t0 is the current moment, and ZD0 is the set of protection setting values ​​to be determined.

3. The automatic generation system of protection setting values ​​of generators and transformers according to claim 2 is characterized in that: The specific logic of segmenting the current signal and voltage signal in the historical data chain using time windows of equal length is: According to the time sequence, n continuous time windows with a width of ω are used to divide the voltage signal data and the current signal data respectively, and n*ω=T, and the voltage signal and current signal segments corresponding to each generated time window are calibrated as follows: LV i (1)、LV i (2)、…、LV i (m)、…、LV i (n) LI i (1)、LI i (2)….LI i (m)、…、LI i (n) Among them, LV i (m) and LI i (n) respectively represent the voltage signal and current signal fragments corresponding to the mth time window in the ith historical data chain, m is a positive integer, and 1≤m≤n.

4. The automatic generation system of protection setting values ​​of generators and transformers according to claim 3 is characterized in that: For the setting data chain, n continuous time windows with a width of ω are also used to divide the setting data chain, and the current signal and voltage signal segments corresponding to each time window of the setting data chain are calibrated as follows: SV(1), SV(2),…,SV(m),…,SV(n) SI(1), SI(2),…,SI(m),…,SI(n) Wherein, SV(m) and SI(m) represent the voltage signal and current signal segments corresponding to the mth time window in the setting data chain, respectively.

5. The automatic generation system of protection setting values ​​of generators and transformers according to claim 4 is characterized in that: After Fourier transform is performed on the current signal and voltage signal fragments corresponding to the time window, the voltage signal or current signal fragment is transformed into the form of the sum of a series of complex numbers through Fourier transform, the number of complex numbers is represented as the number of frequency components of the corresponding fragments, the imaginary part of the frequency component of each complex number is represented as the phase of the corresponding frequency component, and the real part of the frequency component of each complex number is represented as the amplitude of the corresponding frequency component. The centroid frequency of the voltage and current in each time window is calculated as the voltage characteristic data and the current characteristic data. The logic for calculating the centroid frequency of each time window in the historical data chain is as follows: in, and ALV represents the centroid frequency of the voltage signal and current signal fragment corresponding to the mth time window in the i-th historical data chain, i (m) p and flv i (m) p They represent the amplitude and phase of the pth frequency component of the voltage signal in the mth time window in the ith historical data chain after Fourier transformation, ALI i (m) q and flv i (m) q They respectively represent the amplitude and phase of the qth frequency component of the current signal in the mth time window in the ith historical data chain after Fourier transform, and P and Q respectively represent the number of frequency components of the voltage signal and current signal in the mth time window in the ith historical data chain after Fourier transform.

6. The automatic generation system of protection setting values ​​of generators and transformers according to claim 1 is characterized by: The logic for calculating the center of gravity frequency of each time window in the tuning data link is: Among them, F SV(m) and F SV(m) Respectively represent the centroid frequency of the voltage signal and current signal fragment corresponding to the mth time window in the setting data chain, ASV(m) u and fSV(m) u They represent the amplitude and phase of the uth frequency component of the voltage signal in the mth time window after Fourier transformation in the setting data chain, ASI(m) v and fSI(m) v They respectively represent the amplitude and phase of the vth frequency component of the current signal in the mth time window in the setting data chain after Fourier transform. U and V respectively represent the number of frequency components of the voltage signal and current signal in the mth time window in the setting data chain after Fourier transform.

7. The automatic generation system of protection setting values ​​of generators and transformers according to claim 6 is characterized in that: The formula for generating the error between the set data link and the historical data link is: Among them, PD i It represents the error between the setting data chain and the i-th historical data chain, α and β are the voltage weight and current weight respectively, 0<α<β, and α+β=1.

8. The automatic generation system of protection setting values ​​of generators and transformers according to claim 1 is characterized by: When selecting the best historical data chain, the historical data chain with the smallest error between it and the setting data chain is used as the best historical data chain, and the set of protection setting values ​​to be determined is set as the protection setting value data set in the best historical data chain.

9. A method for automatically generating protection setting values ​​for generators and transformers, characterized in that: The method for automatically generating the protection setting values ​​of generators and transformers is obtained by executing the automatic generation system for the protection setting values ​​of generators and transformers according to any one of claims 1 to 8, and the specific steps include: Step 1: Extract the fault data that has occurred from the historical data and build a historical knowledge base. The fault data includes the voltage and current signals at the output end of the generator or transformer within the time interval T before the fault occurs and the corresponding protection setting value. The voltage signal, current signal and setting value are associated to form a historical data chain and stored in the historical knowledge base with a number. Step 2: Take the current moment as the end point of the time series, trace back T time length as the start point of the time series, obtain the voltage signal and current signal of the output end of the generator or transformer between the start point of the time series and the end point of the time series, and associate the voltage signal and the current signal to form a setting data chain; Step 3: Divide the current signal and voltage signal in the setting data chain and the historical data chain into time windows of equal length, and number the time windows in chronological order to obtain the current signal and voltage signal segments corresponding to multiple time windows, and use Fourier transform to obtain the voltage characteristic data and current characteristic data in each time window; Step 4: Traverse all historical data chains, generate the error between the setting data chain and each historical data chain according to the voltage characteristic data and current characteristic data in each time window in the setting data chain and the historical data chain, and select the best historical data chain; Step 5: Obtain the protection setting value in the best historical data chain and set it as the reference protection setting value, and use the reference protection setting value as the automatically generated protection setting value.

Images