Method, system and device for evaluating the abnormal degree of outliers in the redundant object detection signal of a space relay

Abstract

Method, system and device for evaluating the abnormal degree of outliers in the redundant object detection signal of aerospace relays, belonging to the technical field of redundant object detection of aerospace relays. In order to solve the problem of more false judgments and missed judgments based on the pulse occurrence time method caused by the fact that the component signals in the redundant object detection of aerospace relays do not always appear as single-group pulse sequences with continuous and periodic cycles. The present invention first extracts pulses from the PIND signals collected in the redundant object detection of aerospace relays, and frames the extracted pulse signals; then folds the framed signals; uses the coordinates of the peak point of each pulse in the frame where the pulse is located to represent the pulse, and displays the peak points of the pulses on all framed segments on the x-y coordinate axes, with the x-axis being the length direction of each frame of signal and the y-axis being the amplitude direction of each frame of signal; evaluates the abnormal degree of outliers based on the peak point coordinates of the corresponding pulses on all framed segments on the x-y coordinate axes.

Description

Technical Field

[0001] The present invention belongs to the technical field of aerospace relay foreign object detection, and particularly relates to a method, a system and a device for evaluating the abnormal degree of outliers in aerospace relay foreign object detection signals. Background Technique

[0002] As a switching component, an aerospace relay is an extremely important part of a spacecraft system. Before an aerospace relay becomes a qualified product, it needs to undergo multiple mandatory tests, and foreign object detection is an important part of the mandatory tests. Research shows that the foreign object problem is a serious problem faced by aerospace products. Based on existing relevant data estimates, foreign objects account for about 6% of the total number of faults in the aerospace system. A large number of cases show that the foreign object problem cannot be completely avoided, so foreign object detection is currently the only economical and effective solution. Figure 1 are physical diagrams of part of the relay body and foreign object particles, Figure 1 in which (a)-(c) are typical relay I, typical relay II, and typical relay III respectively, Figure 1 in which (d)-(f) are foreign objects, where (d) represents an aluminum fragment, (e) represents solder stuck at the connection, and (f) represents a fragment stuck at the connection.

[0003] Particle Impact Noise Detection (hereinafter referred to as: PIND) equipment is a special equipment for detecting foreign particles in sealed components, and its purpose is to effectively detect loose particles existing in components and semiconductor package cavities, so as to improve the reliability of components, semiconductors and other components. The Particle Impact Noise Detection method (hereinafter referred to as: PIND method) is a standard method in foreign object detection, and the accuracy of the detection results of the Particle Impact Noise Detection system is extremely important. Similarly, the accuracy of the aerospace relay foreign object detection results based on the PIND method is extremely important for the quality and reliability of aerospace relays.

[0004] At present, one of the difficulties in judging the results of aerospace relay foreign object detection is the accurate identification of the foreign object collision signal inside the test piece and the component mechanical vibration signal (referred to as the component signal for short). It should be noted that in many cases, these two signals will appear simultaneously and be mixed together to form a mixed signal. In the mixed signal, how to effectively judge the foreign object signal has always been a difficult problem in this field. Since the foreign object signal is not easy to accurately identify, it is often considered to give priority to judging the component signal. The currently widely used component signal identification method is the pulse occurrence time method, that is, it is considered that component pulses always appear at equal intervals. However, based on long-term aerospace relay foreign object detection results and analysis, the component signal is not always a single group of pulse sequences that appear continuously and at equal intervals. This characteristic leads to many misjudgments and missed judgments based on the pulse occurrence time method, and the recognition credibility is not high, and improvement is urgently needed. Summary of the invention

[0005] The invention aims to solve the problem of many misjudgments and missed judgments based on the pulse generation time method in the detection of redundant objects in aerospace relays, which is caused by the fact that component signals are not always a single group of pulse sequences that appear continuously and periodically.

[0006] A method for evaluating the degree of abnormality of outliers in aerospace relay redundant object detection signals, comprising:

[0007] Pulse extraction is performed on the PIND signal collected in the detection of redundant objects in aerospace relays, and the extracted pulse signal is framed; then the framed signal is folded;

[0008] The pulse is represented by the coordinates of the peak point of each pulse in the sub-frame where the pulse is located, and the peak points of the pulses on all sub-frame segments are displayed on the xy coordinate axis, where the x-axis is the length direction of each frame signal and the y-axis is the amplitude direction of each frame signal;

[0009] The abnormality of the outliers is evaluated based on the peak coordinates of the pulses corresponding to all the frame segments on the xy coordinate axis.

[0010] Furthermore, in the process of framing the extracted pulse signal, the framing is performed using the vibration cycle time length of the vibration table as the length of the framing window.

[0011] Furthermore, before the pulse signal is framed, adjacent pulses whose time interval is less than a set threshold are combined into one pulse.

[0012] Preferably, the AE-LOF algorithm is used to evaluate the abnormality of the outlier based on the peak point coordinates of the pulses corresponding to all the frame segments on the xy coordinate axis. The specific process includes:

[0013] For the peak point coordinates of the pulses corresponding to all the frame segments on the xy coordinate axis, the associated point set A is first obtained. i ; For each data point p i , the set of associated points A i as follows:

[0014] A i ={p j ∈C\{p i}|d(p i , p j )≤R i}

[0015] This set contains all the i The radius R i Other data points within d k(·) represents the k-nearest neighbor distance;

[0016] For each point p in the dataset j , initialize a frequency counter F j = 0; For each data point p i , check each other point p j whether it is in A i , if so then F j = F j + 1; After traversing all points, each F j will represent the total number of times the point p j appears within the radius of all other points as an associated point;

[0017] Then calculate AE-LOF(p j ):

[0018]

[0019] where, N k (·) represents the set of neighbor points, |N k (P)| represents the set capacity; LRD(·) represents the reciprocal of the average reachability distance from a point to its surrounding neighbor points; Z is the internal adjustment coefficient, and w is the external adjustment coefficient;

[0020] Use AE-LOF(p j ) to evaluate the degree of abnormality of the outlier points corresponding to the peak points of the pulses on all framed segments on the x-y coordinate axes.

[0021] Preferably, the w = Z × k, where k is the value k of the k-nearest neighbor distance.

[0022] A system for evaluating the degree of abnormality of outlier points in the redundant object detection signal of a space relay, comprising:

[0023] Pulse extraction module: Extract pulses from the PIND signal collected in the redundant object detection of the space relay;

[0024] Pulse segmentation module: Frame the extracted pulse signal;

[0025] Signal folding and coordinate projection module: Fold the framed signal; then represent each pulse with the coordinates of the peak point of the pulse in the frame where the pulse is located, and display the peak points of the pulses on all framed segments on the x-y coordinate axes; the x-axis is the length direction of each frame of the signal, and the y-axis is the amplitude direction of each frame of the signal;

[0026] Outlier point abnormality degree evaluation module: Evaluate the degree of abnormality of the outlier points based on the peak point coordinates of the pulses corresponding to all framed segments on the x-y coordinate axes.

[0027] Further, during the process of frame - dividing the extracted pulse signal by the pulse division module, the vibration period time length of the vibration table is used as the length of the frame - dividing window for frame - dividing.

[0028] Further, before frame - dividing the pulse signal, the pulse division module combines adjacent pulses with a time interval less than a set threshold into one pulse.

[0029] Preferably, the outlier anomaly degree evaluation module uses the AE - LOF algorithm to evaluate the anomaly degree. The specific process includes:

[0030] For the peak - point coordinates of the pulses corresponding to all frame - divided segments on the x - y coordinate axes, first obtain the associated point set as A i ; for each data point p i , the associated point set A i is as follows:

[0031] A i ={p j ∈C\{p i}∣d(p i , p j )≤R i}

[0032] This set contains all other data points within the radius R of p i ; that is, d k (·) represents the k - nearest neighbor distance;

[0033] For each point p in the dataset j , initialize a frequency counter F j =0; for each data point p j , check whether each other point p i is in A j . If it is, then F i =F j +1; after traversing all points, each F j will represent the total number of times the point p j appears within the radius of all other points as an associated point;

[0034] Then calculate AE - LOF(p j ):

[0035]

[0036]

[0037] where N k (·) represents the set of neighbor points, |N k(P) represents the set capacity; LRD(·) represents the reciprocal of the average reachability distance from a point to its surrounding neighbor points; Z is the internal adjustment coefficient, and w is the external adjustment coefficient;

[0037] Using AE-LOF(p j ) to evaluate the degree of abnormality of the outliers corresponding to the peak points of the pulses on all framed segments based on the x-y coordinate axes.

[0038] An outlier abnormality degree evaluation device for aerospace relay foreign object detection signals, the device includes a processor and a memory, and at least one instruction is stored in the memory, and the at least one instruction is loaded and run by the processor for the outlier abnormality degree evaluation system of the aerospace relay foreign object detection signal.

[0039] Beneficial effects:

[0040] The present invention first transforms the PIND signal collected in the aerospace relay foreign object detection signal, and preprocesses the PIND signal into an object that can be detected by AE-LOF, so it provides the possibility and basis for the evaluation of the degree of abnormality of outliers. Then, the degree of abnormality of the transformed points is evaluated to realize the evaluation of the degree of abnormality of outliers, so that potential foreign object particle signals can be detected from the mixed signal, and it can effectively solve the problem of many false judgments and missed judgments based on the pulse occurrence time method caused by the single-group pulse sequence that the component signals do not always appear continuously and periodically.

[0041] At the same time, the present invention also proposes an AE-LOF algorithm to evaluate the degree of abnormality of outliers for the transformed points. Through this algorithm, outliers can be effectively detected, ensuring the judgment of outliers and the accuracy of detecting potential foreign object particle signals from the mixed signal. Description of the drawings

[0042] Figure 1 is a physical diagram of part of the relay body and foreign object particles;

[0043] Figure 2 Schematic diagram of the pulse extraction and waveform segmentation process;

[0044] Figure 3 is a schematic diagram of the pulse framing and folding steps of the foreign object signal;

[0045] Figure 4 is the original component signal waveform of the mixed signal;

[0046] Figure 5 is the pulse point display diagram after processing the mixed signal;

[0047] Figure 6 is the necessity of density-based local outlier detection;

[0048] Figure 7 Schematic diagram of density-based local outlier detection algorithm;

[0049] Figure 8 Schematic diagram of the outlier degree based on the LOF algorithm;

[0050] Figure 9 Schematic diagram of outliers calculated based on the AE-LOF algorithm;

[0051] Figure 10 Comparison graph of LOF calculated value and AE-LOF calculated value;

[0052] Figure 11 Schematic table of the LOF value calculation process for outlier points;

[0053] Figure 12 Association frequency of outlier points and calculation results of LOF and AE-LOF. Specific implementation manner

[0054] In order to solve the problems existing in the background technology. The present invention first proposes a transformation method for the PIND signal collected in the detection of aerospace relay debris. The PIND signal collected in the aerospace relay debris detection signal is transformed. A very important innovation of the present invention is to preprocess the PIND signal into an object that can be detected by AE-LOF. The present invention first extracts the pulses. Through further research, it is found that both the debris signal and the component signal show a pulse sequence of a damped attenuation oscillation process, which is different from the Gaussian background noise and the instantaneous impact interference signal. Based on this characteristic, the pulses in the debris signal and the component signal can be effectively extracted, and other interference signals are preliminarily filtered to reduce the omission of pulses. Secondly, the preprocessed PIND signal is displayed in the form of pulse merging, segmentation, and folding. Finally, the AE-LOF algorithm is used to evaluate the outlier degree for the peak point coordinates of the pulses corresponding to all segmented segments on the x-y coordinate axes. Specific implementation manner one:

[0056] This implementation manner is a method for evaluating the outlier degree in the aerospace relay debris detection signal, including the following steps:

[0057] I. PIND signal preprocessing:

[0058] S100. Extract the pulses in the PIND signal. In this implementation manner, the three-threshold method is used to extract the effective pulses in the signal. It should be noted that the present invention includes but is not limited to using the three-threshold method to extract the effective pulses in the signal, and it can also be the double-threshold method, etc., as long as it can extract the effective pulses in the signal.

[0059] The process of extracting effective pulses from a signal using the three - threshold method is as follows:

[0060] (a) Determination of reference threshold: First, taking the overall acquired signal as the object, calculate the average energy as the reference for the threshold, and determine the main - pulse energy threshold, start - energy threshold, and end - energy threshold based on the average energy, as shown in Figure 2 (a). The threshold parameters need to be adjusted according to the actual situation and signal characteristics.

[0061] (b) Preliminary search: According to the principle of the search algorithm, process a single - pulse signal, as shown in Figure 2 (b). Determine whether there are pulses exceeding the threshold. When the average energy value or amplitude of a certain segment of signal data reaches the set threshold, it is determined that the main body of the pulse exists. Subsequently, continue to calculate the energy of each subsequent segment until the energy value is lower than the set main - body energy threshold. Count the peak points of the energy values, and obtain the starting time and position coordinates of the segment with the highest energy.

[0062] (c) Detailed search: On the basis of the preliminary search, taking the pulse - energy peak point as the starting point, divide it with the set time length as the step size, and search forward and backward for the exact starting point and exact ending point of the pulse occurrence moment. As shown in Figure 2 (c).

[0063] Thus, the extraction of pulses from the signal is completed, ensuring the accuracy and integrity of the pulses.

[0064] S200. Pulse merging, splitting, and folding:

[0065] For the extracted pulse signal, frame it with the vibration - period time length of the vibration table as the length of the frame - dividing window (i.e., the splitting step size), that is, split it according to the splitting step size, and then fold the split signal, as shown in Figure 2 (d). Before splitting, considering the acoustic reflection characteristics and sensor sensitivity characteristics, merge adjacent pulses with a time interval less than the set value into one pulse, that is, merge adjacent pulses with too close distances.

[0066] (1) Splitting is performed with the period of the vibration - period signal as the step size (or the length of the frame - dividing window).

[0067] (2) The merging of adjacent pulses is completed before the segmentation program is carried out. That is, many pulses are screened out by the three-threshold method. For example, pulses a1, a2, a3, …, an are obtained from a certain signal. If pulses a1 and a2 are very close to each other, and the distance between the end point of pulse a1 and the start point of pulse a2 is less than the set value Δdmin = 500, then a1 and a2 are merged. That is, the end point of pulse a2 is assigned to the end point of pulse a1. Therefore, the actual range of the merged pulse a1-2 is: [the start point of a1, the end point of a2].

[0068] (3) The folding program is carried out after the segmentation program. As Figure 3 shown, specifically, the respective sub-frame data obtained after executing the segmentation program are stacked in a manner parallel to the x-y axis and perpendicular to the z axis in the middle. Finally, the peak points of the pulses in each sub-frame are extracted as the representatives of the pulses and displayed to form Figure 3 the final two-dimensional scatter plot in the middle. Figure 3 In fact, the x-axis is the length direction of each frame of the signal, the y-axis is the amplitude direction of each frame of the signal, and the z-axis is the stacking direction of each frame of the signal. In actual drawing, the range on the x-axis is the vibration period time multiplied by the sampling rate of the detection system (500k in this embodiment) and is used to represent the data position points.

[0069] S300. Pulse display: The peak points of each pulse in the coordinates of the sub-frame where the pulse is located are used to represent the pulse, and the peak points of the pulses on all segmented segments are displayed on the x-y coordinate axes. As

[0070] shown in (e) in the middle are the coordinates of the peak points of the folded pulses. Figure 2

[0071] II. Display of pulse points after preprocessing of the mixed signal:

[0072] Macroeconomic waveforms of the mixed signal and the distribution image of pulse peak points after algorithm processing in the detection of foreign objects in aerospace relays:

[0073] (1) Affected by objective factors such as the shape, mass, material, and collision angle of foreign object particles, the trajectory of the foreign object signal has the randomness similar to that of the free electron collision signal. Therefore, the image of the pulse peak points of the foreign object signal is an irregular scatter plot.

[0074] (2) The image of the pulse peak points of the component signal has the shrinkage of the cluster data set and is shaped like a narrow band-shaped cloud cluster, as Figure 5 shown near the abscissa of 0.4×10 4 in the middle.

[0075] ​(3) The pulse peak point distribution image of the mixed signal has two characteristics, namely: (1) The main part of the pulse peak points is distributed in clusters in the shape of a narrow strip-like cloud cluster, and most of them are distributed inside and around the cluster. (2) A small part of the pulse peak points are randomly distributed in other areas, scattered like stars.

[0076] Actually, the pulse point distribution after the preprocessing of the mixed signal reflects both the periodicity of the component signal and the randomness of the foreign object signal. From Figure 5 it can be seen that the main problem of the present invention is to determine whether there is a foreign object signal in the shape of stars outside the component signal in the shape of a narrow strip-like cloud cluster. Further understood, it is to detect whether there is a foreign object particle signal around the component signal with better periodicity.

[0077] It should be further explained that the component signal in the shape of a narrow strip-like cloud cluster has a certain moving redundancy range, and only the pulse peak points of the foreign object signals far from the "narrow strip-like cloud cluster" range need to be clearly determined.

[0078] Third, the AE-LOF algorithm is used to evaluate the degree of abnormality for the peak point coordinates of the pulses corresponding to all the segmented segments on the x-y coordinate axes.

[0079] Principle of the LOF algorithm (conventional existing algorithm):

[0080] In 2000, Markus M. Breunig et al. proposed the Local Outlier Factor (LOF) method. This method is used to identify abnormal data, and its core idea is to judge whether a point is abnormal by comparing the local density of the point with that of its neighboring points. Therefore, compared with the distance-based anomaly algorithm, density-based outlier detection can detect a type of abnormal data - local outliers. In the LOF algorithm, the degree of abnormality of the data is defined based on the concept of relative density, so it has a strong dependence on the surrounding data.

[0081] Figure 6 is a two-dimensional data set, and the figure contains two clusters C1 = {c 11 , c 12 , …, c 1n} and C2 = {c 21 , c 22 , …, c 2n}, two types of outliers {o1, o3} and {o2, o4}. C1 is a dense morphological cluster, and C2 is a sparse morphological cluster. {o1, o3} are global outliers, and {o2, o4} are local outliers. Generally speaking, global outliers are easy to identify, but local outliers are difficult to detect. If we want to obtain local outliers, we need to adjust the distance parameter Dist(x). If we make Dist(x) less than the minimum distance between C1 and o2, then some data points {c 2i , c 2j} in C2 may be mislabeled as outliers. Based on the above analysis, we need to obtain an algorithm with the ability to identify local outliers, that is, the LOF algorithm. In a given dataset, if for any data point, the points within its local range are very dense, then this data point is considered likely to be a normal data point. Otherwise, it may be an outlier.

[0082] Let there be a sample of a data set C. Suppose there are n samples in total and the data dimension is m. For

[0083]

[0084] The Euclidean distance between any two points can be expressed as:

[0085]

[0086] The k-th nearest point P is the k-th nearest distance point of O, that is, d k (O) is the k-th distance of point O, defined as follows:

[0087] d k (O) = d(O, P)

[0088] If the following conditions are met:

[0089] (1) There are at least k points P′ ∈ C\{O} in the set such that d(O, P′) ≤ d(O, P); where C\{O} represents the difference set of C with respect to {O}, and \ is the difference set symbol;

[0090] (2) There are at most k - 1 points P′ ∈ C\{O} in the set such that d(O, P′) < d(O, P).

[0091] At this time, point P is the k-th nearest point to O.

[0092] For example, as Figure 7 shown, C is a set of points centered at O. Both P6 and P7 are the 6th nearest points. There are 5 points inside the 6th distance, and there are 2 points on the 6th distance.

[0093] RD(P, O) (Reachability Distance of P with respect to Object O) is a custom function to obtain the maximum distance. The reachability distance of point P with respect to data point O can be calculated according to the results of Equations (3)-(4). For example, in Figure 5 , when the parameter k = 6, the reachability distance of P5 is d k＝6 (O), and the reachability distance of P 10 is dist(P 10 , O), where P 10 is outside the k-distance, and in this case, the Euclidean distance dist(P 10 , O) needs to be used to represent it. Therefore, the reachability distance of point P with respect to point O is the maximum value of the k-distance of point O and the Euclidean distance between P and O.

[0094] reach-dist k (P, O) = max(d k (O), dist(P, O)) (3)

[0095] That is:

[0096] RD(P, O) = max(d k (O), dist(P, O)) (4)

[0097] Among them, dist(·) represents the Euclidean distance.

[0098] Local reachability density (LRD) is the reciprocal of the average reachability distance from P to its surrounding neighbor points. Intuitively, according to the LRD formula, the larger the average reachability distance (that is, the farther the surrounding neighbor points are from point P), the smaller the density of the surrounding neighbor points of this point. Therefore, LRD represents the distance of a point from the nearest point cluster. The lower the LRD value, the farther the nearest point cluster is from this point.

[0099]

[0100] Among them, N k (P) represents the set of neighbor points of P, and |N k (P)| represents the set capacity.

[0101] Local outlier factor (LOF) is the ratio of the average value of the LRDs of the k neighbor points of P to the LRD of P:

[0102]

[0103] Furthermore, if point P is not an outlier, the ratio of the average LRD of its neighbor points is approximately equal to the LRD of point P because the density of a point is roughly equal to the density of its adjacent points. In this case, LOF is almost equal to 1. On the other hand, if a certain point is an outlier, the LRD of this point is less than the average LRD of its surrounding neighbor points. Then the LOF value will be very high. Generally, if LOF > 1, it may be considered an outlier value, but this is not always correct. Suppose we know that there is only one outlier in the data, then the point corresponding to the maximum value among all LOF values will be considered an outlier. Obviously, the LOF value of a point directly represents the degree of abnormality of this point.

[0104] Improved LOF algorithm - Attention Enhancement AE - LOF algorithm:

[0105] Taking "attention" as the core word to explain the AE - LOF algorithm. For example, in a social network, assume that A follows many people {B, C, D, E, F,...}. Just because A follows many people does not mean that A has a high attention level. Only when many people {B, C, D, E, F,...} also follow A can it be considered that A has a high attention level.

[0106] Therefore, the AE - LOF algorithm can be explained as follows: Suppose there is a data set C composed of several data points, and the data points in the data set can be mutually related. Data set C = {p1, p2,..., p n}, C contains n data points. The attention radius of data point p i is R i . The Euclidean distance between data points p i and p j is d(p i , p j ).

[0107] The associated point set is A i , for each data point p i , define the associated point set A i as follows:

[0108] A i = {p j ∈ C\{p i} ∣ d(p i , p j ) ≤ R i} (7)

[0109] This set contains all other data points within the radius R i of p i .

[0110] Frequency statistics: For each point p in the data setj , initialize a frequency counter F j = 0. For each data point p i , check every other point p j Is it in A i If p j In A i In, F j Increase by 1. For each i and each j ≠ i, if p j ∈A i , then F j =F j +1. After traversing all the points, each F j

[0111] will represent the point p j As the total number of times the associated point appears within the radius of all other points. In summary, for each point p j The number of occurrences of global association points F j This can be calculated by iterating over the dataset and updating the counter:

[0112]

[0113] Among them, 1 is the indicator function, when p j In A i The value is 1 when it is in, otherwise it is 0.

[0114] In order to adjust the LOF value of each point to a new value that takes into account its "attention", F is integrated on the basis of the original LOF algorithm. j Therefore, the present invention is implemented by adjusting the LRD calculation method of each point. Specifically, assuming F j The smaller the value, the more points p j The more likely it is to be isolated, the higher its abnormality should be. Then, by introducing F j The method of using the value to improve the LOF value of these points in disguised form, thereby improving the abnormality of these points.

[0115] Adjusted AE-LOF(p j ) is defined as:

[0116]

[0117] Wherein, Z is the internal adjustment coefficient, which is usually a positive integer, and is generally 1. w is the external adjustment coefficient, which is usually a positive integer, and can generally be w=Z×k.

[0118] When w = Z × l, there are two main calculation results: (1) When point p j If it is not an outlier, then F j is equal to or close to k, then can be simplified to At this time the calculated value of is approximately equal to 1. Therefore, in this case, AE-LOF(p j ) is almost the same as the calculation result of the original LOF(p j ), ensuring the usability of the result of the original LOF(p j ). (2) When the point p j is an outlier, then F j will be less than k. At this time can be simplified to However, at this time the calculated value will increase significantly. Therefore, in this case, the calculation result of AE-LOF(p j ) will be greater than the calculation result of the original LOF(p j ), ensuring that the calculation result of AE-LOF(p j ) can effectively screen out outliers.

[0119] Through the above steps, the local density of the point p j is adjusted by the number of occurrences of its global associated points, so that those less concerned points are enhanced in the outlier degree evaluation. This not only strengthens the outlier degree analysis of each point, but also provides more flexibility and adaptability to handle different data and scenarios by considering the new value F j (the number of occurrences of associated points) and Z, w (inner and outer adjustment coefficients). Specific Embodiment 2:

[0121] This embodiment is an outlier degree evaluation system for redundant object detection signals of aerospace relays, including:

[0122] Pulse extraction module: Extract pulses from the PIND signals collected in the redundant object detection of aerospace relays;

[0123] Pulse segmentation module: Frame the extracted pulse signals;

[0124] Before framing the pulse signals, the pulse segmentation module merges adjacent pulses with a time interval less than the set threshold into one pulse. During the process of framing the extracted pulse signals, the vibration period length of the vibration table is used as the length of the framing window for framing.

[0125] Signal folding and coordinate projection module: Fold the framed signal; then, represent the pulse by the coordinates of the peak point of each pulse in the frame where the pulse is located, and display the peak points of the pulses on all framed segments on the x-y coordinate axes. The x-axis is the length direction of each frame of the signal, and the y-axis is the amplitude direction of each frame of the signal. In actual drawing, the range on the x-axis is the vibration cycle time multiplied by the sampling rate (500k) of the detection system, which is used to represent the data position points.

[0126] Outlier anomaly degree evaluation module: Evaluate the anomaly degree of outliers based on the peak point coordinates of the pulses corresponding to all framed segments on the x-y coordinate axes.

[0127] The outlier anomaly degree evaluation module uses the AE-LOF algorithm to evaluate the anomaly degree. The specific process includes:

[0128] For the peak point coordinates of the pulses corresponding to all framed segments on the x-y coordinate axes, first obtain the set of associated points as A i ; For each data point p i , the set of associated points A i is as follows:

[0129] A i ={p j ∈C\{p i}}∣d(p i , p j )≤R i}}

[0130] This set contains all other data points within the radius R i of p i ; That is, d k (·) represents the k-nearest neighbor distance;

[0131] For each point p j in the dataset, initialize a frequency counter F j =0; For each data point p i , check whether each other point p j is in A i . If it is, then F j =F j +1; After traversing all points, each F j will represent the total number of times the point p j appears within the radius of all other points as an associated point;

[0132] Then calculate AE-LOF(p j ):

[0133]

[0134] Among them, N k (·) represents the set of neighbor points, and |N k (P)| represents the set capacity; LRD(·) represents the reciprocal of the average reachable distance from a point to its surrounding neighbor points; Z is an internal adjustment coefficient, usually taking a positive integer, generally taking 1; w is an external adjustment coefficient, usually taking a positive integer, and generally w = Z×k can be taken.

[0135] Use AE-LOF(p j ) to evaluate the abnormality degree of the outlier points corresponding to the peak points of the pulses on all framed segments based on the x-y coordinate axes. Specific Embodiment 3:

[0137] This embodiment is an apparatus for evaluating the abnormality degree of outlier points in the redundant object detection signal of an aerospace relay. The apparatus includes a processor and a memory. It should be understood that any device including a processor and a memory described in the present invention, and the device may further include other units and modules for display, interaction, processing, control, etc. through signals or instructions and other functions;

[0138] At least one instruction is stored in the memory, and the at least one instruction is loaded and run by the processor to implement the system for evaluating the abnormality degree of outlier points in the redundant object detection signal of an aerospace relay.

[0139] Those skilled in the art should understand that the stored at least one instruction is a computer program product corresponding to the method or system. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present application can be implemented in various computer languages. For example, object-oriented programming languages such as Java and interpreted scripting languages such as JavaScript.

[0140] The present application is described with reference to the flowcharts and / or block diagrams of methods, systems, and computer program products according to the embodiments of the present application, and can also be used for corresponding devices. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementing in the process Figure 1 one process or multiple processes and / or blocks Figure 1means for the functions specified in one or more boxes.

[0141] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one Figure 1 process or a plurality of processes and / or boxes Figure 1 means for the functions specified in one or more boxes.

[0142] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one Figure 1 process or a plurality of processes and / or boxes Figure 1 means for the functions specified in one or more boxes.

[0143] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0144] Embodiments

[0145] (A), Original LOF algorithm results

[0146] For mixed signal data, the LOF value of each point to be detected can be obtained through the LOF algorithm. By setting the outlier detection threshold, outliers can be screened out. Generally, after obtaining the outliers, it is also necessary to evaluate the degree of abnormality of each outlier, which is beneficial for visual inspection, display, and evaluation of relevant data in the later stage. It should be emphasized that the evaluation of the degree of abnormality of the points to be detected is mainly completed by comparing the LOF values. Therefore, the LOF value is a key parameter. There are defects in the conventional evaluation of the degree of abnormality of outliers based on the LOF algorithm. Taking the data in Figure 8 as a typical object to illustrate the defects. As Figure 8 shown in the schematic diagram of the outlier anomaly score calculated based on the LOF algorithm, the outliers are mainly divided into three regions, and the LOF value of No.1 in region C is the smallest. In fact, compared with the outlier set {No.75, No.40, No.80, No.57, No.60, No.62}, the outlier No.1 is about 4000 points away from the center line. Obviously, the degree of abnormality of outlier No.1 is more obvious. Therefore, there are defects in the evaluation of the degree of abnormality of outliers based on the LOF algorithm.

[0147] First, taking the outlier No. 40 in area A as an example, analyze the reason why the LOF value of this point is relatively large. The LOF algorithm is mainly a density-based outlier detection algorithm. To evaluate the abnormality degree of any data point in the dataset to be measured, it is usually necessary to refer to the abnormality degrees of the k neighbor points of this data point. For the outlier No. 40 in area A, its k neighbor points (k = 10) mainly consist of three parts, namely the outliers {No. 75, No. 80} in area A, the outliers {No. 62, No. 60, No. 57} in area B, and the data points {No. 81, No. 70, No. 74, No. 69, No. 73} in the central yellow area (Center Area) (because Figure 8 and Figure 9 the display space is limited, these points are not marked in Figure 8 and Figure 9 ). The calculation results show that the LRD value orders of magnitude of the data points {No. 81, No. 70, No. 74, No. 69, No. 73} in the central yellow area (Center Area) are all 1×10 -2 , while the LRD value orders of magnitude of the outliers {No. 75, No. 80} and {No. 62, No. 60, No. 57} are all 1×10 -4 . Obviously, due to the large difference in the order of magnitude of the above data points, generally, the average LRD of the k neighbor points (k = 10) of the outlier No. 40 in area A is significantly affected by the 5 data points in the central yellow area (Center Area), resulting in a relatively high LOF calculated value for the outlier No. 40 in area A.

[0148] Secondly, analyze the reason why the LOF value of the outlier No. 1 in area C is relatively small. For the outlier No. 1 in area C, its k neighbor points (k = 10) are all distributed in the central yellow area and concentrated in area C-1. As can be seen from area C-1 in the figure, the data points in area C-1 are relatively far from the surrounding points, and their LRD values are smaller than those of other data points in the central yellow area (Center Area). Therefore, it will result in a relatively low LOF calculated value for the outlier No. 1 in area C.

[0149] Through the above reason analysis, the LOF value of the outlier No. 1 in area C is smaller than that of the outlier No. 40 in area A. By analogy, the LOF values of the outlier sets {No. 75, No. 80, No. 57, No. 60, No. 62} in areas A and B are larger than the LOF value of the outlier No. 1 in area C.

[0150] Figure 11Schematic table of the LOF value calculation process for each outlier in the main area. It should be noted that:

[0151] (1) Magnitude annotation of LRD values: Red represents 1×10 -1 ; Blue represents 1×10 -2 ; Black represents 1×10 -3 ; Green represents 1×10 -4 . (2) The abnormal risk evaluation level is an index customized by the present invention to evaluate the degree of abnormality and explain the risk situation.

[0152] (B), Results of the AE-LOF algorithm

[0153] For mixed signal data, Figure 12 is the statistical situation of the association frequencies of the outliers in regions A, B, and C. Sorting according to the statistical values of the association frequencies: Region C < Region B < Region A. Based on the statistical values of the association frequencies, the LOF values of the outliers recalculated by the AE-LOF algorithm are plotted, as shown in Figure 9 . As can be seen from Figure 9 , compared with the LOF value of the outliers in region A, the LOF value of the outlier No. 1 in region C increases significantly, and the degree of abnormality increases significantly. At the same time, the LOF value of the outliers in region B also decreases significantly compared with the LOF value of the outliers in region A.

[0154] As can be seen from Figure 10 in the local enlarged detail view, for non-outliers, the calculated values of the LOF algorithm and the AE-LOF algorithm are approximately equal, and the overall change trends are the same. For the outlier No. 1, the calculated value based on the AE-LOF algorithm is 80 times higher than that of the LOF algorithm. For the outliers {No. 62, No. 60, No. 57}, it is increased by about 3 times. For the outliers {No. 40, No. 80, No. 75}, it is increased by about 7 times. The detection value range of AE-LOF is wider, and it can capture more significant outliers (such as the 1620.54 corresponding to the outlier No. 1 in Table 2), which indicates that the AE-LOF algorithm is more sensitive in detecting abnormalities, indicating that the AE-LOF algorithm can identify more obvious outliers in anomaly detection.

[0155] In the outlier detection based on the LOF algorithm, the LOF result of any point P is affected by the neighboring points of the point. When some of the neighboring points of point P are slightly abnormal, from a global perspective, the LOF value of P will be smaller to a certain extent, which may cause some outlier anomalies to be ignored or covered up. The local outlier detection algorithm based on enhanced attention density (AE-LOF algorithm) can make up for this problem of the LOF algorithm to a certain extent when the neighboring points are abnormal. Due to the confidentiality of aerospace detection, experimental data cannot be obtained and disclosed in large quantities, and also contains many complex abnormal situations in redundant object detection. The above multiple reasons have led to the current recognition ability of the mixed signal of redundant object detection to be further improved. In the later stage, it is planned to increase the number of field experiments, obtain more experimental data, and further study the outlier value detection of the redundant object detection signal. The experimental results show that, in general, for outliers, the AE-LOF calculation value is several times higher than the LOF calculation value. AE-LOF is more sensitive in detecting anomalies, has a wider range of detection values, and can capture more significant anomalies. The AE-LOF algorithm is effective in detecting and identifying the abnormality of some outliers in the aerospace relay redundant object detection signal.

[0156] The above calculation examples of the present invention are only used to explain the calculation model and calculation process of the present invention in detail, and are not intended to limit the implementation methods of the present invention. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the implementation methods here. All obvious changes or modifications derived from the technical solution of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for evaluating the abnormal degree of outliers in the redundant object detection signal of a space relay, characterized in that, Including: Extract pulses from the PIND signals collected during the detection of foreign objects in aerospace relays, and frame the extracted pulse signals. Then fold the framed signals. Use the coordinates of the peak point of each pulse in the frame where the pulse is located to represent the pulse, and display the peak points of the pulses on all framed segments on the x-y coordinate axes. The x-axis is the length direction of each frame of signal, and the y-axis is the amplitude direction of each frame of signal. Evaluate the abnormality degree of outliers based on the peak point coordinates of the pulses corresponding to all framed segments on the x-y coordinate axes. During the evaluation process, use the AE-LOF algorithm to evaluate the abnormality degree. The specific process includes: For the peak point coordinates of the pulses corresponding to all framed segments on the x-y coordinate axes, first obtain the set of associated points as A i ; For each data point p i , the set of associated points A i is as follows: A i = {p j ∈ C \ {p i} | d(p i , p j ) ≤ R i} This set contains all other data points within the radius R of p i ; that is, d i within; where d k (·) represents the k-nearest neighbor distance; For each point p in the dataset j , initialize a frequency counter F j = 0; For each data point p i , check each other point p j to see if it is in A i . If it is, then F j = F j + 1; After traversing all the points, each F j will represent the total number of times the point p j appears within the radius of all other points as an associated point; Then calculate AE-LOF(p j ): Among them, N k (·) represents the set of neighbor points, and |N k (P)| represents the set capacity; LRD(·) represents the reciprocal of the average reachable distance from a point to its surrounding neighbor points; Z is the internal adjustment coefficient, and w is the external adjustment coefficient; Using AE-LOF(p j ) to evaluate the degree of abnormality of the outliers at the peak points of the pulses corresponding to all segmented frames on the x-y coordinate axes.

2. The method for evaluating the outlier abnormality degree in the redundant object detection signal of an aerospace relay according to claim 1, wherein, During the process of framing the extracted pulse signals, use the vibration cycle time length of the vibration table as the length of the framing window for framing.

3. A method for evaluating the outlier abnormality degree in the redundant object detection signal of an aerospace relay according to claim 1, characterized in that, Before framing the pulse signals, merge adjacent pulses with a time interval less than the set threshold into one pulse.

4. A method for evaluating the abnormal degree of outliers in the redundant object detection signal of an aerospace relay according to any one of claims 1 to 3, characterized in that, Where \(w = Z\times k\), and \(k\) is the value of \(k\) for the \(k\)-nearest neighbor distance.

5. A system for evaluating the abnormal degree of outliers in the redundant object detection signal of a space relay, characterized in that, Including: Pulse extraction module: Extract pulses from the PIND signals collected during the detection of foreign objects in aerospace relays. Pulse segmentation module: Frame the extracted pulse signals. Signal folding and coordinate projection module: Fold the framed signals; then use the coordinates of the peak point of each pulse in the frame where the pulse is located to represent the pulse, and display the peak points of the pulses on all framed segments on the x-y coordinate axes. The x-axis is the length direction of each frame of signal, and the y-axis is the amplitude direction of each frame of signal. Outlier abnormality degree evaluation module: Evaluate the abnormality degree of outliers based on the peak point coordinates of the pulses corresponding to all framed segments on the x-y coordinate axes. The outlier abnormality degree evaluation module uses the AE-LOF algorithm to evaluate the abnormality degree. The specific process includes: For the peak point coordinates of the pulses corresponding to all segmented segments on the x-y coordinate axes, first obtain the set of associated points as A i ; for each data point p i , the set of associated points A i is as follows: A i = {p j ∈ C \ {p i} | d(p i , p j ) ≤ R i} This set contains all other data points within the radius R i of p i ; that is, d k (·) represents the k-nearest neighbor distance; For each point p in the dataset j , initialize a frequency counter F j = 0; For each data point p i , check each other point p j to see if it is in A i . If it is, then F j = F j + 1; After traversing all points, each F j will represent the total number of times the point p j appears within the radius of all other points as an associated point; Then calculate AE-LOF(p j ): Among them, N k (·) represents the set of neighbor points, and |N k (P)| represents the set capacity; LRD(·) represents the reciprocal of the average reachable distance from a point to its surrounding neighbor points; Z is a regulation coefficient, and w is a regulation coefficient; Using AE-LOF(p j ) to evaluate the degree of abnormality of the outliers at the peak points of the pulses corresponding to all the segmented frames on the x-y coordinate axes.

6. The outlier abnormality degree evaluation system for the redundant object detection signal of a space relay according to claim 5, wherein During the process of the pulse segmentation module framing the extracted pulse signals, use the vibration cycle time length of the vibration table as the length of the framing window for framing.

7. An outlier anomaly degree evaluation system for aerospace relay foreign object detection signals according to claim 6, characterized in that Before the pulse segmentation module frames the pulse signals, merge adjacent pulses with a time interval less than the set threshold into one pulse.

8. An outlier abnormality degree evaluation device for redundant object detection signals of a space relay, characterized in that, The device includes a processor and a memory. At least one instruction is stored in the memory, and the at least one instruction is loaded and run by the processor for an outlier abnormality degree evaluation system for aerospace relay foreign object detection signals according to any one of claims 5 to 7.

Images