Magnet quenching detection method based on individual group independent optimization immune algorithm

Abstract

The invention relates to the technical field of magnet quenching detection, and discloses a magnet quenching detection method based on an individual group independent optimization immune algorithm. The method comprises the following steps: respectively preprocessing an existing sample and a to-be-detected sample; respectively carrying out feature extraction on the existing sample signal frame and the to-be-detected sample signal frame; respectively standardizing the feature vector of the existing sample signal frame and the feature vector of the to-be-tested sample signal frame; initializing the antibody population to generate an initialized antibody population; performing iterative evolution on the initialized antibody population to obtain an iterated antibody population; performing population optimization screening on the iterated antibody population to obtain a screening result; repeating the steps of iterative evolution and population optimization screening until the antibody population does not change any more, and generating an optimization discrimination region for the antibody population which does not change any more; and calculating the distance between the standardized feature vector of the signal frame of the sample to be detected and all antibodies in the antibody group which does not change any more, and judging whether the magnet is quenched or not according to the calculated distance.

Description

Technical Field

[0001] The invention relates to the technical field of magnet quench detection, and in particular to a magnet quench detection method based on an individual group independent optimization immune algorithm. Background Art

[0002] Superconducting magnets are one of the core components of the power modules of maglev trains, electromagnetic sled cars, etc. The main principle is that the superconducting magnets enter the superconducting state after processes such as cooling and excitation, and generate a strong magnetic field with very little loss of electric energy. The system uses this magnetic field to interact with the ground magnetic field to form thrust, suspension force, etc., driving the body to move at high speed. It is one of the efficient ways to replace traditional internal combustion engines and motor drives.

[0003] The stability of superconducting magnets in the superconducting state is one of the basic conditions for normal operation. The maintenance of the superconducting state is related to many factors. Large-scale fluctuations in related conditions will affect the working state of the superconducting magnet, causing the superconducting magnet to lose its superconducting state, that is, the magnet quenches its superconductivity.

[0004] The current methods for superconducting magnet quench detection mainly include threshold method, data analysis method, etc. The main process of the threshold method is to summarize the quench threshold according to the critical parameters or historical data of the superconducting magnet, and use the threshold to judge the various parameters of the superconducting magnet to determine whether the magnet has quenched. The data analysis method mainly uses the superconducting magnet time series data, such as voltage signals, temperature signals, field strength signals, etc., to analyze the correlation and changes in components in the signal, so as to realize the detection of quench faults.

[0005] The threshold-based quench detection method is easily affected by noise. When the signal is disturbed by environmental noise, false detection is prone to occur. At the same time, due to the differences in superconducting magnet structure and sensor installation conditions, the threshold setting of the method for determining superconducting quench conditions based on thresholds is different, resulting in a certain hysteresis in quench determination, affecting its operational safety.

[0006] The quench detection method based on analyzing the correlation of superconducting magnet sequence data and the changes in composition has a certain degree of specialization. For superconducting magnets of different models and standards, the corresponding specific parameters are somewhat different. In addition, due to the specificity of data distribution, the fault detection judgment criteria cannot take into account the data distribution. Therefore, the generalization ability of this method is limited, and it is difficult to improve the overall robustness and detection capability of the method. Summary of the invention

[0007] The present invention provides a magnet quench detection method based on an individual group independent optimization immune algorithm, which can solve the problems in the prior art.

[0008] The present invention provides a magnet quench detection method based on an individual group independent optimization immune algorithm, wherein the method comprises:

[0009] Preprocessing the existing samples and the samples to be tested respectively to obtain an existing sample signal frame and a sample signal frame to be tested, wherein the existing samples include existing superconducting magnet voltage time series data, and the samples to be tested include superconducting magnet voltage time series data to be tested;

[0010] Extracting features from the existing sample signal frame and the sample signal frame to be tested respectively to obtain a feature vector of the existing sample signal frame and a feature vector of the sample signal frame to be tested;

[0011] The feature vector of the existing sample signal frame and the feature vector of the sample signal frame to be tested are respectively standardized to obtain the standardized feature vector of the existing sample signal frame and the standardized feature vector of the sample signal frame to be tested;

[0012] Initializing the antibody group to generate an initialized antibody group;

[0013] Iteratively evolve the initialized antibody group to obtain an iterated antibody group;

[0014] Performing population optimization screening on the iterated antibody group to obtain screening results;

[0015] Repeating the iterative evolution and population optimization screening steps until the antibody population no longer changes, and generating an optimized discrimination region for the antibody population that no longer changes;

[0016] The distance between the standardized feature vector of the signal frame of the sample to be tested and all antibodies in the antibody group that no longer changes is calculated, and whether the magnet is quenched is determined based on the calculated distance.

[0017] Preferably, the preprocessing includes overlapping framing and windowing, and the existing sample signal frame is obtained by the following formula:

[0018] s i =w i ·S,

[0019] Among them, S is the existing superconducting magnet voltage time series data, w i is the ith Hanning framing window, · is the vector dot multiplication operator, s i is the i-th signal frame of existing samples obtained after framing.

[0020] Preferably, the extracted features include extracting root mean square features, kurtosis features and maximum derivative features, and the root mean square features, kurtosis features and maximum derivative features of the existing sample signal frame are expressed by the following formula:

[0021]

[0022]

[0023]

[0024] Ftvec i =[RMS i ,Kurt i ,Jerkpeak i ],

[0025] Where T represents the signal frame s i Length, RMS i Indicates signal frame s i The root mean square characteristic, μ k and σ k Indicates signal frame s i The corresponding mean and standard deviation, E(…) is the expectation operator, Kurt i Indicates signal frame s i The kurtosis characteristic, max is the maximum value operator, Jerkpeak i is the signal frame s i The maximum derivative feature, Ftvec i is the signal frame s i The feature vector of .

[0026] Preferably, the standardized feature vector of the existing sample signal frame is obtained by the following formula:

[0027]

[0028] Among them, SFtvec i is the signal frame s i is the standardized feature vector of , μ and σ are the mean vector and standard deviation vector of the existing samples.

[0029] Preferably, the antibody population is initialized to generate an initialized antibody population by the following formula:

[0030] IAB i (n) = μ n +r×σ n ,

[0031] Among them, IAB i (n) represents the value of the nth feature dimension of the i-th initial antibody, μ n and σ n is the value of the nth dimension of the existing sample mean vector μ and the existing sample standard deviation vector σ, and r is a random number between -1 and 1.

[0032] Preferably, the initialized antibody population is iteratively evolved to obtain an iterated antibody population by the following formula:

[0033] NAB i (n) = (1 + r n)×IAB i (n),

[0034] Among them, r n A random number between -0.5 and 0.5, NAB i (n) represents the value of the nth feature dimension of the ith antibody after iteration.

[0035] Preferably, performing population optimization screening on the iterative antibody population and obtaining the screening results comprises:

[0036] Calculate the distance between each antibody in the iterated antibody group and the existing samples;

[0037] According to the calculated distance, the iterative antibody group is subjected to group optimization screening to obtain the screening result.

[0038] Preferably, the distance between each antibody in the iterated antibody group and the existing sample is calculated by the following formula:

[0039] BGD i,j =||NAB i -SFtvec j ||,

[0040] Among them, ||…|| is the two-norm operator, BGD i,j is the distance between the i-th antibody and the j-th sample after iteration, NAB i is the value of the i-th antibody after iteration, SFtvec j is the signal frame S j The normalized feature vector of .

[0041] Preferably, the optimized discrimination region is generated by the following formula:

[0042]

[0043]

[0044] R i =max{bgd i ,gbd i,j},

[0045] Among them, bgd i Indicates distance from NAB i With the nearest SFtvec j The distance between them, SFtvec i,j Indicated by NAB i For the most recent antibody sample, gbd i,j Indicates that NAB is found i For all samples with the nearest antibody, i The maximum distance betweeni Indicates the final assignment to antibody NAB i The recognition radius.

[0046] Preferably, judging whether the magnet is quenched according to the calculated distance comprises:

[0047] If the distance between the calculated normalized feature vector of the signal frame of the sample to be tested and all antibodies in the antibody group that no longer changes is less than or equal to the radius Rcr i , then the sample to be tested belongs to the i antibody category, otherwise the sample to be tested does not belong to the i antibody category, where if the i antibody is iteratively generated by the superconducting magnet quench signal frame, then the i antibody belongs to the quench category, and if the i antibody is iteratively generated by the non-quench signal frame, then the i antibody belongs to the non-quench category.

[0048] Through the above technical solution, multiple features of the superconducting magnet voltage can be extracted, and based on the sample group in the feature space, antibody group initialization, iterative evolution and antibody group iterative optimization of optimization screening are performed to form a specialized judgment area based on the sample individual, and finally the accurate detection of the sample quench is achieved according to the specialized judgment area. The detection method described in the present invention can ensure accurate quench detection in the case of large sample distribution differences. Compared with the traditional threshold method, it effectively limits the misjudgment and missed judgment problems caused by noise and signal interference. At the same time, compared with the single parameter data analysis method, it has stronger adaptability and generalization ability, and meets the actual high-precision requirements for superconducting magnet quench detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The included drawings are used to provide a further understanding of the embodiments of the present invention, which constitute a part of the specification, are used to illustrate the embodiments of the present invention, and together with the text description, explain the principles of the present invention. Obviously, the drawings in the following description are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A flow chart of a magnet quench detection method based on an individual group independent optimization immune algorithm according to an embodiment of the present invention is shown;

[0051] Figure 2 A schematic diagram showing antibody groups, samples (antigens) and discrimination zone delineation according to an embodiment of the present invention is shown;

[0052] Figure 3 A schematic diagram of quench detection results according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0053] It should be noted that, in the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present invention and its application or use. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] 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.

[0055] Unless otherwise specifically stated, the relative arrangement of the parts and steps described in these embodiments, numerical expressions and numerical values ​​do not limit the scope of the present invention. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the accompanying drawings are not drawn according to the actual proportional relationship. The technology, method and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but in appropriate cases, the technology, method and equipment should be regarded as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once a certain item is defined in an accompanying drawing, it does not need to be further discussed in subsequent drawings.

[0056] Figure 1 A flow chart of a magnet quench detection method based on an individual group independent optimization immune algorithm according to an embodiment of the present invention is shown.

[0057] like Figure 1 As shown, an embodiment of the present invention provides a magnet quench detection method based on an individual group independent optimization immune algorithm, wherein the method comprises:

[0058] Preprocessing the existing samples and the samples to be tested respectively to obtain an existing sample signal frame and a sample signal frame to be tested, wherein the existing samples include existing superconducting magnet voltage time series data, and the samples to be tested include superconducting magnet voltage time series data to be tested;

[0059] Extracting features from the existing sample signal frame and the sample signal frame to be tested respectively to obtain a feature vector of the existing sample signal frame and a feature vector of the sample signal frame to be tested;

[0060] The feature vector of the existing sample signal frame and the feature vector of the sample signal frame to be tested are respectively standardized to obtain the standardized feature vector of the existing sample signal frame and the standardized feature vector of the sample signal frame to be tested;

[0061] Initializing the antibody group to generate an initialized antibody group;

[0062] Iteratively evolve the initialized antibody group to obtain an iterated antibody group;

[0063] Performing population optimization screening on the iterated antibody group to obtain screening results;

[0064] Repeating the iterative evolution and population optimization screening steps until the antibody population no longer changes, and generating an optimized discriminant region for the antibody population that no longer changes (i.e., the final antibody population);

[0065] The distance between the standardized feature vector of the signal frame of the sample to be tested and all antibodies in the antibody group that no longer changes is calculated, and whether the magnet is quenched is determined based on the calculated distance.

[0066] In this way, the category of the sample to be tested can be determined, thereby obtaining the test result.

[0067] Through the above technical solution, multiple features of the superconducting magnet voltage can be extracted, and based on the sample group in the feature space, antibody group initialization, iterative evolution and antibody group iterative optimization of optimization screening are performed to form a specialized judgment area based on the sample individual, and finally the accurate detection of the sample quench is achieved according to the specialized judgment area. The detection method described in the present invention can ensure accurate quench detection in the case of large sample distribution differences. Compared with the traditional threshold method, it effectively limits the misjudgment and missed judgment problems caused by noise and signal interference. At the same time, compared with the single parameter data analysis method, it has stronger adaptability and generalization ability, and meets the actual high-precision requirements for superconducting magnet quench detection.

[0068] According to an embodiment of the present invention, the preprocessing includes overlapping framing and windowing, and the existing sample signal frame is obtained by the following formula:

[0069] s i =w i ·S,

[0070] Among them, S is the existing superconducting magnet voltage time series data, w i is the ith Hanning framing window, · is the vector dot multiplication operator, s iis the i-th signal frame of existing samples obtained after framing.

[0071] For example, the time length of the frame window is 0.1s and it overlaps with the two adjacent frame windows by 0.05s respectively, and the value of the window function outside 0.1s is 0. In other words, the time length of the frame can be 0.1s, the frame overlap is 0.05s, and the window function is a Hanning window, which can ensure the time accuracy of the detection result.

[0072] By framing, the original time series data can be divided into frame segments suitable for processing, ensuring the time accuracy of the detection results, while frame overlap ensures the continuity between signal frames, and windowing can prevent the frequency leakage of the signal during the framing process.

[0073] According to an embodiment of the present invention, the extracted features include extracting root mean square features, kurtosis features and maximum derivative features. The root mean square features, kurtosis features and maximum derivative features of the existing sample signal frame are expressed by the following formula:

[0074]

[0075]

[0076]

[0077] Ftvec i =[RMS i ,Kurt i ,Jerkpeak i ],

[0078] Where T represents the signal frame s i Length, RMS i Indicates signal frame s i The root mean square characteristic (eigenvalue), μ k and σ k Indicates signal frame s i The corresponding mean and standard deviation, E(…) is the expectation operator, Kurt i Indicates signal frame s i The kurtosis characteristic (eigenvalue), max is the maximum value operator, Jerkpeak i is the signal frame s i The maximum derivative feature (eigenvalue), Ftvec i is the signal frame s i The feature vector of .

[0079] According to an embodiment of the present invention, the standardized feature vector of the existing sample signal frame is obtained by the following formula:

[0080]

[0081] Among them, SFtvec i is the signal frame s i The standardized feature vector of the signal frame is Ftvec, μ and σ are the mean vector and standard deviation vector of the existing samples (i.e., the feature vector Ftvec of all signal frames i A vector of means and standard deviations for each column).

[0082] By standardizing the feature vector of the signal frame, it can be ensured that the weights of each dimension in the determination direction are consistent.

[0083] According to one embodiment of the present invention, the antibody population is initialized to generate an initialized antibody population by the following formula:

[0084] IAB i (n) = μ n +r×σ n ,

[0085] Among them, IAB i (n) represents the value of the nth feature dimension of the i-th initial antibody, μ n and σ n is the value of the nth dimension of the existing sample mean vector μ and the existing sample standard deviation vector σ, and r is a random number between -1 and 1.

[0086] In this way, an initialized antibody population can be generated.

[0087] According to an embodiment of the present invention, the initialized antibody group is iteratively evolved to obtain an iterated antibody group using the following formula:

[0088] NAB i (n) = (1 + r n )×IAB i (n),

[0089] Among them, r n A random number between -0.5 and 0.5, NAB i (n) represents the value of the nth feature dimension of the ith antibody after iteration.

[0090] According to one embodiment of the present invention, performing population optimization screening on the iterative antibody population to obtain the screening results includes:

[0091] Calculate the distance between each antibody in the iterated antibody group and the existing samples;

[0092] According to the calculated distance, the iterative antibody group is subjected to group optimization screening to obtain the screening result.

[0093] According to an embodiment of the present invention, the distance between each antibody in the iterative antibody group and the existing sample is calculated by the following formula:

[0094] BGD i,j =||NAB i -SFtvec j ||,

[0095] Among them, ||…|| is the two-norm operator, BGD i,j is the distance between the i-th antibody and the j-th sample after iteration, NAB i is the value of the i-th antibody after iteration, SFtvec j is the signal frame S j The normalized feature vector of .

[0096] Therefore, according to BGD i,j The results screened out the antibody group closest to all individuals in the sample group and became the new initial antibody group, namely IAB.

[0097] According to one embodiment of the present invention, the optimized discrimination region is generated by the following formula:

[0098]

[0099]

[0100] R i =max{bgd i ,gbd i,j},

[0101] Among them, bgd i Indicates distance from NAB i With the nearest SFtvec j The distance between them, SFtvec i,j Indicated by NAB i For the most recent antibody sample, gbd i,j Indicates that NAB is found i For all samples with the nearest antibody, i The maximum distance between i Indicates the final assignment to antibody NAB i The recognition radius.

[0102] In the present invention, the final antibody group (antibody group that does not change) and the sample (antigen) and the discrimination zone are delineated as follows: Figure 2 shown.

[0103] According to an embodiment of the present invention, judging whether a magnet is quenched according to the calculated distance includes:

[0104] If the distance between the calculated normalized feature vector of the signal frame of the sample to be tested and all antibodies in the antibody group that no longer changes is less than or equal to the radius Rcr i , then the sample to be tested belongs to the i antibody category, otherwise the sample to be tested does not belong to the i antibody category, where if the i antibody is iteratively generated by the superconducting magnet quench signal frame, then the i antibody belongs to the quench category, and if the i antibody is iteratively generated by the non-quench signal frame, then the i antibody belongs to the non-quench category.

[0105] For example, if we get the distance BGD between the jth sample to be tested and the i-th antibody i,j , compared with BGD i,j With Rcr i If BGD i,j Less than or equal to Rcr i , then the sample to be tested belongs to antibody category i, otherwise it does not belong to antibody category i.

[0106] In this way, the category of the sample to be tested can be determined, thereby obtaining the test result.

[0107] In the present invention, in the feature extraction step, the existing samples and the samples to be tested share the same feature extraction method; in the sample standardization step, the existing samples and the samples to be tested share the standardization parameters (i.e., the above-mentioned μ and σ); the method for calculating the distance between the standardized feature vector of the signal frame of the sample to be tested and all antibodies in the antibody group that no longer changes can be the same as the method for calculating the distance between each antibody in the antibody group after iteration and the existing sample.

[0108] The magnet quench detection method based on the individual group independent optimization immune algorithm of the present invention is described below with reference to examples.

[0109] Taking the voltage data of a superconducting magnet test platform as an example, the normal antibody group is generated for the normal voltage data according to the corresponding steps of the present invention, and the voltage data during the quench process is selected to generate the quench antibody group according to the corresponding steps, forming an antibody group that can detect normal and quench faults and generating discrimination areas according to the corresponding steps. The new voltage data (test data) is selected and tested according to the corresponding steps, and the quench detection result is as follows: Figure 3 The results show that the magnet quench detection method based on the individual group independent optimization immune algorithm proposed in the present invention can effectively distinguish the normal and quench conditions of the superconducting magnet. In the data obtained from the actual test platform, the quench detection accuracy is higher than 98.5%, which can effectively detect the working state of the superconducting magnet and meet the demand for high-speed detection of superconducting magnets in actual situations.

[0110] It can be seen from the above embodiments that the magnet quench detection method based on the individual group independent optimization immune algorithm described in the present invention effectively reduces the high false detection rate and missed detection rate caused by parameter fluctuations when relying on threshold judgment through the extracted characteristic expressions of multiple parameters of the superconducting magnet. At the same time, the detection method based on the individual group independent optimization immune algorithm constructs a specific identification area based on the individual distribution of samples, avoiding the problems of false detection and missed detection caused by uneven sample distribution or non-convex sample distribution, which is conducive to improving the detection accuracy of superconducting magnet quench detection.

[0111] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom" are usually based on the directions or positional relationships shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the devices or elements referred to must have a specific direction or be constructed and operated in a specific direction. Therefore, they cannot be understood as limiting the scope of protection of the present invention. The directional words "inside and outside" refer to the inside and outside relative to the contours of each component itself.

[0112] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways (rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0113] In addition, it should be noted that the use of terms such as "first" and "second" to limit components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above terms have no special meaning and therefore cannot be understood as limiting the scope of protection of the present invention.

[0114] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A magnet quench detection method based on an individual group independent optimization immune algorithm, It is characterized in that The method includes: Preprocessing the existing samples and the samples to be tested respectively to obtain an existing sample signal frame and a sample signal frame to be tested, wherein the existing samples include existing superconducting magnet voltage time series data, and the samples to be tested include superconducting magnet voltage time series data to be tested; Extracting features from the existing sample signal frame and the sample signal frame to be tested respectively to obtain a feature vector of the existing sample signal frame and a feature vector of the sample signal frame to be tested; The feature vector of the existing sample signal frame and the feature vector of the sample signal frame to be tested are respectively standardized to obtain the standardized feature vector of the existing sample signal frame and the standardized feature vector of the sample signal frame to be tested; Initializing the antibody group to generate an initialized antibody group; Iteratively evolve the initialized antibody group to obtain an iterated antibody group; Performing population optimization screening on the iterated antibody group to obtain screening results; Repeating the iterative evolution and population optimization screening steps until the antibody population no longer changes, and generating an optimized discrimination region for the antibody population that no longer changes; The distance between the standardized feature vector of the signal frame of the sample to be tested and all antibodies in the antibody group that no longer changes is calculated, and whether the magnet is quenched is determined based on the calculated distance.

2. The method according to claim 1, It is characterized in that Preprocessing includes overlapping framing and windowing, and the existing sample signal frame is obtained by the following formula: s i =w i ·S, Among them, S is the existing superconducting magnet voltage time series data, w i is the ith Hanning framing window, · is the vector dot multiplication operator, s i is the i-th signal frame of existing samples obtained after framing.

3. The method according to claim 2, It is characterized in that The extracted features include extracting root mean square features, kurtosis features and maximum derivative features. The root mean square features, kurtosis features and maximum derivative features of the existing sample signal frame are expressed by the following formula: Ftvec i =[RMS i ,Kurt i ,Jerkpeak i ], Where T represents the signal frame s i Length, RMS i Indicates signal frame s i The root mean square characteristic, μ k and σ k Indicates signal frame s i The corresponding mean and standard deviation, E(…) is the expectation operator, Kurt i Indicates signal frame s i The kurtosis characteristic, max is the maximum value operator, Jerkpeak i is the signal frame s i The maximum derivative feature, Ftvec i is the signal frame s i The feature vector of .

4. The method according to claim 3, It is characterized in that The standardized feature vector of the existing sample signal frame is obtained by the following formula: Among them, SFtvec i is the signal frame s i is the standardized feature vector of , μ and σ are the mean vector and standard deviation vector of the existing samples.

5. The method according to claim 4, It is characterized in that The antibody group is initialized by the following formula to generate an initialized antibody group: IAB i (n)=μ n +r×σ n , Among them, IAB i (n) represents the value of the nth feature dimension of the i-th initial antibody, μ n and σ n is the value of the nth dimension of the existing sample mean vector μ and the existing sample standard deviation vector σ, and r is a random number between -1 and 1.

6. The method according to claim 5, It is characterized in that The initialized antibody group is iteratively evolved using the following formula to obtain the iterated antibody group: NAB i (n)=(1+r n )×IAB i (n) Among them, r n A random number between -0.5 and 0.5, NAB i (n) represents the value of the nth feature dimension of the ith antibody after iteration.

7. The method according to claim 6, It is characterized in that The iterated antibody group is subjected to population optimization screening, and the screening results include: Calculate the distance between each antibody in the iterated antibody group and the existing samples; According to the calculated distance, the iterative antibody group is subjected to group optimization screening to obtain the screening result.

8. The method according to claim 7, It is characterized in that The distance between each antibody in the iterated antibody group and the existing samples is calculated by the following formula: BGD i,j =||NAB i -SFtvec j ||, Among them, ||…|| is the two-norm operator, BGD i,j is the distance between the i-th antibody and the j-th sample after iteration, NAB i is the value of the i-th antibody after iteration, SFtvec j is the signal frame S j The standardized feature vector of .

9. The method according to claim 8, It is characterized in that The optimized discrimination region is generated by the following formula: Rcr i =max{bgd i ,gbd i,j }, Among them, bgd i Indicates distance from NAB i With the nearest SFtvec j The distance between them, SFtvec i,j Indicated by NAB i For the most recent antibody sample, gbd i,j Indicates that NAB is found i For all samples with the nearest antibody, i The maximum distance between i Indicates the final assignment to antibody NAB i The recognition radius.

10. The method according to claim 9, It is characterized in that Judging whether a magnet is quenched based on the calculated distance includes: If the distance between the calculated normalized feature vector of the signal frame of the sample to be tested and all antibodies in the antibody group that no longer changes is less than or equal to the radius Rcr i , then the sample to be tested belongs to the i antibody category, otherwise the sample to be tested does not belong to the i antibody category, where if the i antibody is iteratively generated by the superconducting magnet quench signal frame, then the i antibody belongs to the quench category, and if the i antibody is iteratively generated by the non-quench signal frame, then the i antibody belongs to the non-quench category.

Images