A test environment abnormality monitoring method and system

Abstract

The present invention discloses a method and system for monitoring abnormalities in a test environment. The abnormality monitoring method adopted by the present invention includes the following steps: real-time collection of test environment data, pre-processing of the collected test environment data, intelligent enhancement processing of the pre-processed test environment data using a multi-scale fractional-order adaptive feedback enhancement algorithm to obtain environmental data after intelligent enhancement processing; feature extraction optimization of the intelligently enhanced test environment data through nonlinear adaptive perturbation mapping and recursive cross optimization algorithm; feature fusion processing of the optimized feature data to obtain fused feature data; and abnormality monitoring analysis based on the fused feature data to obtain abnormality monitoring results. The present invention can capture small fluctuations in environmental changes; make the enhanced data more sensitive and have higher resolution, and provide a high-precision basis for subsequent feature extraction and abnormality detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular to a method and system for monitoring abnormalities in a test environment using multi-sensor fusion. Background Art

[0002] In the current field of environmental monitoring, multi-sensor fusion technology has been widely used to achieve real-time monitoring and precise analysis of environmental conditions. With the development of Internet of Things technology, various sensors can simultaneously obtain data such as temperature, humidity, air pressure, vibration, and light intensity in the environment. However, due to problems such as heterogeneity of sensor data, noise interference, and the high complexity of multi-source data fusion, traditional monitoring methods often struggle to achieve high-precision, low-false-alarm monitoring in complex and dynamic environments. Furthermore, traditional environmental monitoring methods often rely on a single sensor or simple data fusion methods, lacking the ability to deeply analyze multi-dimensional, multi-source data. This often leads to inadequate monitoring sensitivity, especially when minor environmental changes or sudden anomalies occur.

[0003] In addition, sensor data is often mixed with random noise and periodic interference signals. If effective signal enhancement and denoising are not performed, the environmental monitoring system will be easily affected by noise interference, resulting in false alarms or missed alarms. Summary of the Invention

[0004] The present invention provides a multi-sensor fusion test environment anomaly monitoring method and system to solve the defects of the prior art in multi-sensor environment monitoring, such as inaccurate environmental data processing and incomplete feature analysis.

[0005] To this end, the present invention adopts the following technical solutions.

[0006] In a first aspect, the present invention provides a method for monitoring abnormalities in a test environment, comprising the steps of:

[0007] S1. Real-time collection of test environment data, preprocessing of the collected test environment data, and intelligent enhancement processing of the preprocessed test environment data using a multi-scale fractional-order adaptive feedback enhancement algorithm to obtain intelligently enhanced environmental data;

[0008] The multi-scale fractional-order adaptive feedback enhancement algorithm achieves intelligent enhancement processing through multi-scale variational decomposition, fractional-order derivative feature enhancement, multi-variable adaptive feedback mapping and nonlinear incremental weight optimization;

[0009] S2. Perform feature extraction and optimization on the test environment data after intelligent enhancement processing using a nonlinear adaptive perturbation mapping and a recursive cross optimization algorithm; then perform feature fusion processing on the optimized feature data to obtain fused feature data;

[0010] The nonlinear adaptive perturbation mapping and recursive cross optimization algorithm achieves high-complexity data optimization and fusion through multi-step, multi-process nonlinear adaptive perturbation mapping, recursive cross weight optimization, adaptive feedback perturbation processing and recursive fusion;

[0011] S3. Perform anomaly monitoring analysis based on the fused feature data to obtain anomaly monitoring results.

[0012] Furthermore, in S1, the test environment data is collected in real time by a variety of sensors to obtain original test environment data; the original test environment data is preprocessed by time synchronization, denoising, data missing processing and data normalization to obtain preprocessed test environment data.

[0013] Furthermore, in S1, during the implementation of the multi-scale fractional-order adaptive feedback enhancement algorithm, when performing multi-scale variational decomposition on the pre-processed test environment data, the input signal is decomposed into multiple scale components at different frequency scales through multi-scale signal decomposition, thereby capturing subtle changes in the test environment and extracting key information in the environmental changes.

[0014] Furthermore, in S1, during the implementation of the multi-scale fractional-order adaptive feedback enhancement algorithm, fractional-order derivative feature enhancement processing is performed on each scale component obtained through multi-scale variational decomposition to further amplify subtle changes and enhance feature expression.

[0015] Furthermore, in S1, the specific contents of the multivariable adaptive feedback mapping and nonlinear incremental weight optimization are: constructing an adaptive feedback mechanism between multiple sensor data, performing incremental weight optimization through multivariable nonlinear mapping, and realizing dynamic feature enhanced output.

[0016] Furthermore, in S2, the specific process of implementing the nonlinear adaptive perturbation mapping and recursive cross optimization algorithm is as follows: feature extraction is performed on the test environment data after intelligent enhancement processing, and the extracted features are used to form an initial feature matrix. Nonlinear adaptive perturbation mapping is implemented for each feature in the initial feature matrix through the joint action of nonlinear mapping and sinusoidal modulation to improve the robustness and distinguishing ability of the feature; after completing the nonlinear adaptive perturbation mapping, recursive cross weight optimization is performed on the feature data after the perturbation mapping; and the feature data obtained by the recursive cross weight optimization is subjected to adaptive feedback perturbation processing.

[0017] Furthermore, in S2, all feature data after the adaptive feedback perturbation processing are fused to obtain fused initial feature data, and nonlinear feature fusion mapping is further performed on the fused initial feature data to capture higher-level feature associations.

[0018] Furthermore, in S2, after obtaining the fused feature data after the nonlinear feature fusion mapping, the fused feature data is gradually recursively optimized through cross-recursive iterative fusion to obtain the final fused feature data, so that it can achieve comprehensive expression between different sensor features.

[0019] Furthermore, the final fused feature data is standardized, and anomaly detection of single point anomaly, dynamic anomaly and cluster anomaly is performed based on the standardized fused feature data to obtain anomaly detection results.

[0020] In a second aspect, the present invention provides a test environment anomaly monitoring system for implementing the above-mentioned test environment anomaly monitoring method, which comprises:

[0021] Intelligent enhancement processing unit: collects test environment data in real time, preprocesses the collected test environment data, and uses a multi-scale fractional-order adaptive feedback enhancement algorithm to perform intelligent enhancement processing on the preprocessed test environment data to obtain the environmental data after intelligent enhancement processing;

[0022] The multi-scale fractional-order adaptive feedback enhancement algorithm achieves intelligent enhancement processing through multi-scale variational decomposition, fractional-order derivative feature enhancement, multi-variable adaptive feedback mapping and nonlinear incremental weight optimization;

[0023] Feature optimization and fusion unit: The test environment data after intelligent enhancement processing is subjected to feature extraction and optimization through nonlinear adaptive perturbation mapping and recursive cross optimization algorithm; the optimized feature data is then subjected to feature fusion processing to obtain fused feature data;

[0024] The nonlinear adaptive perturbation mapping and recursive cross optimization algorithm achieves high-complexity data optimization and fusion through multi-step, multi-process nonlinear adaptive perturbation mapping, recursive cross weight optimization, adaptive feedback perturbation processing and recursive fusion;

[0025] Abnormal monitoring and analysis unit: performs abnormal monitoring and analysis based on the fused feature data to obtain abnormal monitoring results.

[0026] The present invention has the following beneficial effects:

[0027] 1. A multi-scale fractional-order adaptive feedback enhancement algorithm refines and analyzes test environment data at different frequency scales, capturing subtle fluctuations in environmental changes. Multi-scale variational decomposition and fractional-order derivative feature enhancement not only improve the data's feature representation but also significantly amplify subtle dynamic changes in the test environment data at different scales. This enhanced data is more sensitive and has higher resolution, providing a high-precision foundation for subsequent feature extraction and anomaly detection.

[0028] 2. During the feature extraction and optimization process, the test environment data after intelligent enhancement is further processed using a nonlinear adaptive perturbation mapping and recursive cross-weight optimization algorithm. This algorithm effectively enhances the robustness and discriminability of feature data through nonlinear perturbation mapping and recursive cross-weight optimization. This ensures that each sensor's features are both highly sensitive to external changes and resistant to internal fluctuations, thus ensuring the stability and consistency of feature data.

[0029] 3. Through nonlinear adaptive perturbation mapping, recursive cross-weight optimization, adaptive feedback perturbation processing and recursive fusion steps, multi-sensor feature data are fused into a comprehensive expression. The multi-step fusion process ensures that the correlation of features in multidimensional space is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a flow chart of a multi-sensor fusion test environment abnormality monitoring method of the present invention;

[0031] Figure 2 This is a composition diagram of a multi-sensor fusion test environment anomaly monitoring system of the present invention. DETAILED DESCRIPTION

[0032] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, 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. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0033] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0034] The specific scheme of the test environment abnormality monitoring method using multi-sensor fusion provided by the present invention is described in detail below with reference to the accompanying drawings.

[0035] Refer to the attached Figure 1 , which shows a flowchart of a method for monitoring abnormalities in a test environment using multi-sensor fusion according to an embodiment of the present invention. The method includes the following steps:

[0036] S1. Collect test environment data in real time, pre-process the collected test environment data, and use the multi-scale fractional-order adaptive feedback enhancement algorithm to perform intelligent enhancement processing on the pre-processed test environment data to obtain the intelligently enhanced environment data. Specifically:

[0037] Raw test environment data is collected in real time using a variety of sensors, including temperature, humidity, pressure, vibration, and light intensity sensors. Preprocessing, including time synchronization, noise removal, data loss processing, and data normalization, is performed on the raw test environment data to generate preprocessed environmental data. The techniques used in this preprocessing process are well known in the art and are not detailed here.

[0038] The pre-processed test environment data is intelligently enhanced using a multi-scale fractional-order adaptive feedback enhancement algorithm. This algorithm achieves intelligent enhancement through multi-scale variational decomposition, fractional-order derivative feature enhancement, multi-variable adaptive feedback mapping, and nonlinear incremental weight optimization. The specific implementation process is as follows:

[0039] First, we perform multi-scale variational decomposition on the pre-processed test environment data to extract key information about environmental changes. The core of multi-scale variational decomposition is to decompose the input signal into multiple scale components at different frequency scales through multi-scale signal decomposition, thereby accurately capturing subtle changes in the test environment. The formula is as follows:

[0040]

[0041] in, Indicates that from The signal collected by the sensor, is a time variable; is the scale ordinal of the decomposition, the range , used to indicate that the signal at different frequency scales is decomposed into multi-scale components; is the frequency The next The first-order decomposition component is used to characterize the signal characteristics at this frequency; It is a frequency variable, used to represent the signal characteristics of different frequency bands; is the total number of decomposition scales; in order to better simulate the environmental noise and periodic fluctuations in the sensor data, the noise term is superimposed on the decomposed data , is the amplitude of random noise, simulating the effect of sensor noise; is the frequency of the noise, which represents the frequency component of the sensor noise; It is the phase of the noise, reflecting the position of the noise signal on the time axis.

[0042] Secondly, for each scale component obtained by decomposition Perform fractional derivative feature enhancement processing to further amplify subtle changes and enhance feature expression. Fractional derivatives are used to enhance signal changes in a local range, so that even very small environmental changes can be significantly amplified. The formula for fractional derivatives is as follows:

[0043]

[0044] in, is the result of fractional derivative operation. Decomposition components In frequency The enhancement value under is the order of the fractional derivative, ranging from , represents the degree of local enhancement and is used to control the distribution characteristics of the derivative in the local area; is the normalized gamma function, which is used to normalize the results to ensure that the results of different orders are comparable; is the integrating variable, used for cumulative effects in the frequency domain; is at frequency The next The fractional-order scale component represents the decomposed frequency component. This fractional-order operation can enhance local changes based on global features, extracting subtle dynamic information from the data, making the data information more delicate and laying the foundation for the next step of feedback mapping.

[0045] Finally, after obtaining the multi-scale data enhanced by fractional derivatives After that, multivariable adaptive feedback mapping and nonlinear incremental weight optimization are performed. An adaptive feedback mechanism is constructed between multiple sensor data, and nonlinear incremental weight optimization is performed through multivariable mapping to achieve dynamic feature enhanced output. The specific formula is:

[0046]

[0047] in, It is a sensor In time Output data after intelligent enhancement processing at all times; It is the total number of frequencies after sensor data decomposition, which is used to represent the fusion of multiple frequency components; It is a sensor With sensor In the Feedback weight under the order scale component; It is the frequency Next Decomposition components The result after fractional derivative enhancement; It is the feedback regulator, controlling the feedback intensity; is the bias parameter of the nonlinear mapping, which is used to adjust the response of the nonlinear feedback. The feedback mapping process can dynamically adjust the data enhancement effect according to the changes in the environmental signal.

[0048] After the above processing, the environmental data after intelligent enhancement processing is obtained.

[0049] S2. Perform feature extraction and optimization on the test environment data after intelligent enhancement processing using a nonlinear adaptive perturbation mapping and recursive cross optimization algorithm; then perform feature fusion processing on the optimized feature data to obtain fused feature data. The nonlinear adaptive perturbation mapping and recursive cross optimization algorithm achieves highly complex data optimization through multi-step, multi-process nonlinear adaptive perturbation mapping, recursive cross weight optimization, and adaptive feedback perturbation processing. The specific implementation process is as follows:

[0050] First, the existing feature engineering technology is used to extract features from the environmental data after intelligent enhancement processing, and the extracted features are used to form the initial feature matrix , , where any Indicates the The characteristic data of each sensor, Is the total number of sensors. For the initial feature matrix Each feature in Adaptive nonlinear perturbation mapping is achieved through the combined action of nonlinear mapping and sinusoidal modulation to improve the robustness and distinguishing ability of features. The adaptive nonlinear perturbation mapping function is defined as:

[0051]

[0052] in, is the feature data after perturbation mapping; It is the adaptive disturbance factor for each sensor feature, with an initial value of 1; is a nonlinear perturbation mapping function, including logarithmic amplification and sinusoidal modulation terms; It is a logarithmic nonlinear mapping, which is used to amplify the relative changes of low-value features and enhance the influence of weak signals; The sinusoidal perturbation term is introduced to increase the periodic modulation of the feature, making the feature more sensitive to external changes.

[0053] Secondly, after completing the adaptive nonlinear perturbation mapping, the characteristic data after perturbation mapping is Perform recursive cross-weight optimization. Recursive cross-weight optimization is defined as follows:

[0054]

[0055] in, It is the feature data after recursive cross-weight optimization; It is a cumulative index used to traverse all sensors, with a value range of , is the total number of sensors; is the characteristic attenuation adjustment parameter; is the disturbance factor adjustment parameter, which controls the response speed to other sensor characteristics; is the cross-perturbation amplitude, which regulates the interaction strength between features; It is a nonlinear interaction term based on feature differences, which increases the impact of disturbances; is a small constant that prevents the denominator from being zero and ensures computational stability. The purpose of the recursive cross-weight optimization is to maintain the independence of each feature while ensuring reasonable correlation between sensors, thereby enhancing the recognition of environmental changes.

[0056] Then, the features obtained by recursive cross-weight optimization are Perform adaptive feedback perturbation processing. The adaptive feedback perturbation processing process aims to enhance the expressiveness of features and make them more sensitive to small changes in the environment. The formula for adaptive feedback perturbation processing is:

[0057]

[0058] in, Represents the final optimized feature data, including high sensitivity to environmental changes; is the feedback amplitude control factor, which is used to adjust the intensity of feedback; It is a nonlinear suppression term that suppresses excessive fluctuations in characteristics and ensures stability; is the nonlinear feedback adjustment parameter; is the feedback disturbance intensity control factor; is the feature after recursive cross-weight optimization The standard deviation of , used for adaptive perturbations; It is the inverse enhancement term of the standard deviation, which enhances the recognition of small features.

[0059] Finally, after completing the adaptive feedback perturbation processing, all optimized features Feature fusion is performed to form a comprehensive feature expression to improve the overall expression ability of environmental information. The goal of feature fusion is to achieve mutual complementation and enhancement between different sensor features through reasonable weights, nonlinear mapping and recursive fusion.

[0060] The diagonal weighting matrix is ​​introduced for initial weighting. The calculation formula of the fusion feature matrix is:

[0061]

[0062] in, is the initial feature data after fusion; Represents the final optimized feature matrix; It is a diagonal weighted matrix used to assign different weights to the features of different sensors. Any element Indicates the Adaptive fusion weights for each sensor. The optimized features of each sensor are weighted by a weighting matrix to improve the feature expression weights of important sensors. The initial weights can be preset and adaptively adjusted in subsequent iterations.

[0063] After weighting, further Perform nonlinear fusion mapping to capture higher-level feature associations. The nonlinear fusion mapping formula is as follows:

[0064]

[0065] in, Represents the fused feature data after nonlinear mapping; parameter 、 and Control the influence of first-order, second-order, and third-order nonlinear mapping. The mapping formula transforms the fused features nonlinearly through a combination of polynomials and trigonometric functions, where Expressing nonlinear combinations of first-order and second-order features, Capturing the nonlinear correlation of third-order features. Nonlinear mapping processing is used to enhance the high-order interaction characteristics between features and improve the detection sensitivity of environmental anomalies.

[0066] In getting Finally, the features are gradually optimized through cross-recursive iterative fusion to achieve comprehensive expression between different sensor features. The recursive iterative fusion formula is:

[0067]

[0068] in, It is The fused feature data of the iteration; It is The fused feature data of the iteration; is the eigenvector at index The fusion characteristics of It is the adjustment parameter of nonlinear interaction, which is used to control the nonlinear degree of cross term; It is a disturbance adjustment factor, which is used to enhance the disturbance effect of the fusion feature in the recursive process, prevent the eigenvalues ​​from converging prematurely, and increase the dynamic variability of the fusion feature.

[0069] After iteration, when the fused feature data reaches a stable value during the iteration process, that is, when the difference between the results of two adjacent iterations is less than the convergence threshold preset according to the empirical method or when the preset number of iterations is reached, the iteration is stopped to obtain the final fused feature data. ,The fusion feature contains the comprehensive feature expression of multiple sensors in a complex environment.

[0070] Furthermore, the fused feature data is standardized to eliminate the scale differences between different features, ensure the effectiveness and stability of the detection process, and obtain standardized fused feature data. Based on the standardized fused feature data, anomaly detection of single point anomalies, dynamic anomalies, and cluster anomalies is performed to obtain anomaly detection results, including:

[0071] Based on the standardized fused feature data, a statistical anomaly detection method is used to quickly identify feature changes that significantly deviate from the normal state. The presence of single-point anomalies in the data is determined by calculating the single-point anomaly score of the standardized feature data. The single-point anomaly score is calculated as the mean of the standardized fused feature data. When the single-point anomaly score exceeds the single-point anomaly threshold preset based on empirical methods, it is marked as a single-point anomaly caused by accidental factors.

[0072] To capture sudden changes in the environment, a dynamic detection method based on time series changes is introduced. By analyzing the changing trends of features in the time series, we can identify gradual or sudden anomalies, namely dynamic anomalies. The incremental change rate of the standardized fused feature data at time t is calculated as the dynamic anomaly score. When the dynamic anomaly score exceeds the dynamic anomaly threshold preset based on empirical methods, it is marked as a dynamic anomaly, indicating the presence of a sudden or gradual change trend.

[0073] In order to improve the accuracy of anomaly detection, the existing density-based clustering method is used to identify outliers in data clusters and calculate the cluster anomaly score. When the cluster anomaly score exceeds the dynamic anomaly threshold preset according to the empirical method, it is marked as a cluster anomaly, indicating that there are discrete changes in the environment.

[0074] The above technical solution has the following beneficial effects:

[0075] 1. A multi-scale fractional-order adaptive feedback enhancement algorithm refines and analyzes environmental data at different frequency scales, capturing subtle fluctuations in environmental changes. This multi-scale variational decomposition and fractional-order derivative feature enhancement not only improves the data's feature expression but also significantly amplifies subtle dynamic changes in environmental data at different scales, making the enhanced data more sensitive and having higher resolution, providing a high-precision foundation for subsequent feature extraction and anomaly detection.

[0076] 2. During the feature extraction and optimization process, the environmental data after intelligent enhancement is further processed using a nonlinear adaptive perturbation mapping and recursive cross-weight optimization algorithm. This algorithm effectively enhances the robustness and discriminability of feature data through nonlinear perturbation mapping and recursive cross-weight optimization. This ensures that each sensor's features are both highly sensitive to external changes and resistant to internal fluctuations, thus ensuring the stability and consistency of feature data.

[0077] 3. Through adaptive weighting, nonlinear mapping, and recursive fusion steps, multi-sensor feature data is fused into a comprehensive representation. This multi-step fusion process strengthens the correlation of features in multidimensional space. It also adaptively adjusts sensor weights to amplify the contributions of important sensors to the comprehensive feature representation, ensuring optimal representation of multi-source information in the fused data.

[0078] Refer to the attached Figure 2 , which shows the composition diagram of a multi-sensor fusion test environment anomaly monitoring system of the present invention, which is used to implement the above-mentioned test environment anomaly monitoring method, and is composed of an intelligent enhanced processing unit, a feature optimization and fusion unit, and an anomaly monitoring and analysis unit.

[0079] Intelligent enhancement processing unit: collects test environment data in real time, preprocesses the collected test environment data, and uses a multi-scale fractional-order adaptive feedback enhancement algorithm to perform intelligent enhancement processing on the preprocessed test environment data to obtain the environmental data after intelligent enhancement processing.

[0080] The multi-scale fractional-order adaptive feedback enhancement algorithm achieves intelligent enhancement processing through multi-scale variational decomposition, fractional-order derivative feature enhancement, multi-variable adaptive feedback mapping and nonlinear incremental weight optimization.

[0081] Feature optimization and fusion unit: The test environment data after intelligent enhancement processing is subjected to feature extraction optimization through nonlinear adaptive perturbation mapping and recursive cross optimization algorithm; the optimized feature data is then subjected to feature fusion processing to obtain fused feature data.

[0082] The nonlinear adaptive perturbation mapping and recursive cross optimization algorithm achieves high-complexity data optimization through multi-step, multi-process nonlinear adaptive perturbation mapping, recursive cross weight optimization and adaptive feedback perturbation processing.

[0083] Abnormal monitoring and analysis unit: performs abnormal monitoring and analysis based on the fused feature data to obtain abnormal monitoring results.

[0084] It should be noted that each unit in the above-mentioned multi-sensor fusion test environment anomaly monitoring system can be fully or partially implemented by software, hardware and their combination. The above-mentioned units can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. For the specific definition of a multi-sensor fusion test environment anomaly monitoring system, please refer to the definition of a multi-sensor fusion test environment anomaly monitoring method above. The two have the same functions and effects and will not be repeated here.

[0085] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for monitoring abnormalities in a test environment, characterized in that: Including steps: S1. Real-time collection of test environment data, preprocessing of the collected test environment data, and intelligent enhancement processing of the preprocessed test environment data using a multi-scale fractional-order adaptive feedback enhancement algorithm to obtain intelligently enhanced environmental data; The multi-scale fractional-order adaptive feedback enhancement algorithm achieves intelligent enhancement processing through multi-scale variational decomposition, fractional-order derivative feature enhancement, multi-variable adaptive feedback mapping and nonlinear incremental weight optimization; S2. Perform feature extraction and optimization on the test environment data after intelligent enhancement processing using a nonlinear adaptive perturbation mapping and a recursive cross optimization algorithm; then perform feature fusion processing on the optimized feature data to obtain fused feature data; The nonlinear adaptive perturbation mapping and recursive cross optimization algorithm achieves high-complexity data optimization through multi-step, multi-process nonlinear adaptive perturbation mapping, recursive cross weight optimization and adaptive feedback perturbation processing; S3. Perform anomaly monitoring analysis based on the fused feature data to obtain anomaly monitoring results; In the above S1, the test environment data is collected in real time by a variety of sensors to obtain the original test environment data; the sensor types include temperature sensors, humidity sensors, air pressure sensors, vibration sensors and light intensity sensors; In the above-mentioned S2, all feature data after the adaptive feedback perturbation processing are introduced into the diagonal weighting matrix for initial weighting to obtain the fused initial feature data, and the fused initial feature data is further subjected to nonlinear feature fusion mapping to capture higher-level feature associations; After obtaining the fused feature data after nonlinear feature fusion mapping, the fused feature data is gradually recursively optimized through cross-recursive iterative fusion to obtain the final fused feature data, so that it can achieve comprehensive expression between different sensor features.

2. The test environment abnormality monitoring method according to claim 1, characterized in that: In S1, the original test environment data is preprocessed by time synchronization, noise removal, data missing processing and data normalization to obtain preprocessed test environment data.

3. The test environment abnormality monitoring method according to claim 1, characterized in that: In S1, during the implementation of the multi-scale fractional-order adaptive feedback enhancement algorithm, when performing multi-scale variational decomposition on the pre-processed test environment data, the input signal is decomposed into multiple scale components at different frequency scales through multi-scale signal decomposition, thereby capturing subtle changes in the test environment and extracting key information in the environmental changes.

4. The test environment abnormality monitoring method according to claim 1, characterized in that: In S1, during the implementation of the multi-scale fractional-order adaptive feedback enhancement algorithm, fractional-order derivative feature enhancement processing is performed on each scale component obtained through multi-scale variational decomposition to further amplify subtle changes and enhance feature expression.

5. The test environment abnormality monitoring method according to claim 1, characterized in that: In S1, the specific contents of the multivariable adaptive feedback mapping and nonlinear incremental weight optimization are: constructing an adaptive feedback mechanism between multiple sensor data, performing incremental weight optimization by means of multivariable nonlinear mapping, and realizing dynamic feature enhanced output.

6. The test environment abnormality monitoring method according to claim 1, characterized in that: In S2, the specific process of implementing the nonlinear adaptive perturbation mapping and recursive cross optimization algorithm is as follows: feature extraction is performed on the test environment data after intelligent enhancement processing, and the extracted features are used to form an initial feature matrix, and nonlinear adaptive perturbation mapping is achieved for each feature in the initial feature matrix through the joint action of nonlinear mapping and sinusoidal modulation; after completing the nonlinear adaptive perturbation mapping, recursive cross weight optimization is performed on the feature data after the perturbation mapping; and the feature data obtained by the recursive cross weight optimization is subjected to adaptive feedback perturbation processing.

7. The test environment abnormality monitoring method according to claim 1, characterized in that: The final fused feature data is standardized, and anomaly detection of single point anomaly, dynamic anomaly and cluster anomaly is performed based on the standardized fused feature data to obtain the anomaly detection results.

8. A test environment anomaly monitoring system, used to implement the test environment anomaly monitoring method according to any one of claims 1 to 7, characterized in that: include: Intelligent enhancement processing unit: collects test environment data in real time, preprocesses the collected test environment data, and uses a multi-scale fractional-order adaptive feedback enhancement algorithm to perform intelligent enhancement processing on the preprocessed test environment data to obtain the environmental data after intelligent enhancement processing; The multi-scale fractional-order adaptive feedback enhancement algorithm achieves intelligent enhancement processing through multi-scale variational decomposition, fractional-order derivative feature enhancement, multi-variable adaptive feedback mapping and nonlinear incremental weight optimization; Feature optimization and fusion unit: The test environment data after intelligent enhancement processing is subjected to feature extraction and optimization through nonlinear adaptive perturbation mapping and recursive cross optimization algorithm; the optimized feature data is then subjected to feature fusion processing to obtain fused feature data; The nonlinear adaptive perturbation mapping and recursive cross optimization algorithm achieves high-complexity data optimization through multi-step, multi-process nonlinear adaptive perturbation mapping, recursive cross weight optimization and adaptive feedback perturbation processing; Abnormal monitoring and analysis unit: performs abnormal monitoring and analysis based on the fused feature data to obtain abnormal monitoring results; In the intelligent enhanced processing unit, the test environment data is collected in real time through a variety of sensors to obtain the original test environment data; the sensor types include temperature sensors, humidity sensors, air pressure sensors, vibration sensors and light intensity sensors; In the feature optimization and fusion unit, all feature data after adaptive feedback perturbation processing are introduced into the diagonal weighting matrix for initial weighting to obtain fused initial feature data, and nonlinear feature fusion mapping is further performed on the fused initial feature data to capture higher-level feature associations; After obtaining the fused feature data after nonlinear feature fusion mapping, the fused feature data is gradually recursively optimized through cross-recursive iterative fusion to obtain the final fused feature data, so that it can achieve comprehensive expression between different sensor features.

Images