Nondestructive testing optimization method based on safety state evaluation precision feedback of explosion-proof equipment

Abstract

The invention relates to the technical field of industrial safety and nondestructive testing, and particularly discloses a nondestructive testing optimization method based on safety state evaluation precision feedback of explosion-proof equipment, which comprises the following steps of: monitoring a beam steering angle and a local temperature gradient of the explosion-proof equipment in real time, and acquiring key data by using a high-precision sensor network; a clustering algorithm, fast Fourier transform and other advanced data analysis technologies are applied to calculate a beam steering angle abnormal characteristic value and a local temperature gradient characteristic value so as to evaluate the ultrasonic propagation stability and the consistency of the internal structure of the equipment, the characteristic values are synthesized to construct a characteristic vector, the characteristic vector is input into a support vector machine model, and the ultrasonic propagation stability is improved. And outputting the safety state score of the equipment to judge whether the current detection process is in an unstable state or not, automatically adjusting the beam steering angle to cover the abnormal area once the system judges that the current detection process is unstable, increasing the scanning density of the abnormal area displayed by the local temperature gradient, and ensuring that potential problems are detected more meticulously.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial safety and non-destructive testing, and particularly to an optimization method for non-destructive testing based on the accuracy feedback of the safety status assessment of explosion-proof equipment. Background Art

[0002] With the increasing requirements for safety and reliability in industrial production, explosion-proof equipment, as a key safety protection facility, plays an indispensable role in industries such as chemical engineering, petroleum, and natural gas. During the long-term operation of these devices, due to reasons such as material aging, environmental corrosion, or improper operation, structural damage or performance degradation may occur, thus affecting their normal functions and safety. Traditional non-destructive testing methods mainly rely on regular manual inspections and limited sensor monitoring. Although this method can detect surface defects of the equipment to a certain extent, its ability to identify internal subtle changes and potential hazards is limited. Therefore, how to achieve real-time and accurate monitoring of the status of explosion-proof equipment and take preventive measures in a timely manner to avoid major accidents has become an important issue that needs to be solved urgently.

[0003] The existing technology has the following deficiencies: When the device to be detected has a complex geometric shape or internal structure, it becomes particularly difficult to ensure that non-destructive testing comprehensively covers all key areas because traditional testing methods may not be able to effectively cope with problems such as signal attenuation, scattering, and poor probe contact in complex paths. For example, deep holes, narrow channels, or parts with uneven thickness in the equipment will cause abnormal propagation of detection signals such as ultrasonic waves, forming detection blind spots; at the same time, interfaces between different internal materials will also interfere with signals, affecting the accuracy of defect identification. The present invention aims to significantly improve the accuracy and response speed of equipment monitoring by integrating advanced sensing technologies and intelligent data analysis means, providing more solid protection for industrial safety. Summary of the Invention

[0004] The purpose of the present invention is to provide an optimization method for non-destructive testing based on the accuracy feedback of the safety status assessment of explosion-proof equipment to solve the problems in the above background.

[0005] The purpose of the present invention can be achieved through the following technical solutions: An optimization method for non-destructive testing based on the accuracy feedback of the safety status assessment of explosion-proof equipment, comprising the following steps: S1: During the monitoring period of the safety status of the explosion-proof equipment, the beam steering angle and the local temperature gradient are monitored in real time; Among them, the beam steering angle is used to dynamically adjust the direction of the ultrasonic beam to adapt to complex geometric shapes, and the local temperature gradient is measured by infrared thermal imaging technology, reflecting the integrity of the internal materials; S2: Determine the abnormal eigenvalue of the beam steering angle according to the change degree of the beam steering angle, and evaluate the stability of ultrasonic wave propagation; S3: Analyze the change amplitude of the local temperature gradient, calculate the local temperature gradient eigenvalue, and evaluate the consistency of the internal structure of the explosion-proof equipment; S4: Conduct a comprehensive analysis of the abnormal characteristics of the beam steering angle and the local temperature gradient eigenvalue to determine whether the current detection process is in an unstable state; S5: If it is determined to be in an unstable state, the system automatically adjusts the beam steering angle and increases the scanning density for the abnormal area shown by the local temperature gradient.

[0006] As a further solution of the present invention: The process of determining the abnormal eigenvalue of the beam steering angle according to the change degree of the beam steering angle and evaluating the stability of ultrasonic wave propagation specifically includes: During the monitoring period of the safe state of the explosion-proof equipment, obtain the beam steering angle data according to the time series. According to the change degree of the beam steering angle, calculate the abnormal eigenvalue of the beam steering angle, and determine whether the abnormal eigenvalue of the beam steering angle is greater than or equal to the preset threshold. If so, the ultrasonic wave propagation is stable; if not, the ultrasonic wave propagation is unstable.

[0007] As a further solution of the present invention: The process of obtaining the abnormal eigenvalue of the beam steering angle is as follows: Obtain the beam steering angle data set of the explosion-proof equipment during the monitoring period; Select the number of clusters And initialize centroids; For each point in the beam steering angle data set, calculate the Euclidean distance between it and each centroid And assign it to the closest cluster, and update the centroid of each cluster to make it equal to the average position of all points in the corresponding cluster; Repeat the assignment and update steps until the centroid reaches the preset maximum number of iterations; Determine whether the Euclidean distance between each point in the data point set and the centroid of the cluster it belongs to is greater than or equal to the preset threshold. If so, it is determined as an abnormal point, and calculate the average Euclidean distance of the abnormal points in the data point set to obtain the abnormal eigenvalue of the beam steering angle.

[0008] As a further solution of the present invention: The process of analyzing the change amplitude of the local temperature gradient, calculating the local temperature gradient eigenvalue, and evaluating the consistency of the internal structure of the explosion-proof equipment specifically includes: During the monitoring period of the safety state of the explosion-proof equipment, obtain the temperature data inside the explosion-proof equipment according to the time series, calculate the local temperature gradient eigenvalue based on the change amplitude of the local temperature gradient, and determine whether the local temperature gradient eigenvalue is greater than or equal to the preset threshold. If so, the internal structure of the explosion-proof equipment is inconsistent; if not, the internal structure of the explosion-proof equipment is consistent.

[0009] As a further solution of the present invention: the process of obtaining the local temperature gradient eigenvalue is as follows: Obtain the temperature data set of the explosion-proof equipment during the monitoring period , where represents the temperature data set, represents the number of samples in the data set, represents the th temperature value at the time point in the time series; Calculate the temperature difference between adjacent time points, and integrate all temperature differences into a difference sequence to obtain the local temperature gradient; Apply the fast Fourier transform to the local temperature gradient to obtain the frequency domain representation, and calculate the ratio of the sum of the squares of all non-zero frequency components to the standard deviation to obtain the local temperature gradient eigenvalue.

[0010] As a further solution of the present invention: the comprehensive analysis of the beam steering angle anomaly feature and the local temperature gradient eigenvalue specifically includes: Obtain the beam steering angle anomaly feature and the local temperature gradient eigenvalue, construct the beam steering angle anomaly feature and the local temperature gradient eigenvalue into a comprehensive feature vector as the input of the machine learning model, and the output of the model is the safety state score of the explosion-proof equipment. The machine learning model is a support vector machine model.

[0011] As a further solution of the present invention: the process of obtaining the safety state score is as follows: Obtain the beam steering angle anomaly feature, the local temperature gradient eigenvalue and the safety state score during the historical monitoring period of the explosion-proof equipment as the training data set, train the support vector machine model, use minimizing the error between the predicted safety state score and the actual safety state score as the training objective, train the support vector machine model, and input the comprehensive feature vector of the current explosion-proof equipment into the trained support vector machine model according to the trained support vector machine model, and the model will output the accurate safety state score.

[0012] As a further solution of the present invention: the judgment of whether the current detection process is in an unstable state specifically includes: Judge whether the safety state score of the current detection process of the explosion-proof equipment is greater than or equal to the preset threshold. If so, the current detection process is in an unstable state; if not, the current detection process is in a stable state.

[0013] As a further solution of the present invention: The system automatically adjusts the beam steering angle and increases the scanning density for the abnormal area shown by the local temperature gradient, specifically including: If the safety status assessment of the explosion-proof equipment determines an unstable state, for the abnormal situation of the beam steering angle, the system determines the angle range to be adjusted according to the abnormal characteristic value of the beam steering angle, and changes the direction of the beam by controlling the mechanical structure; The system first determines whether the local temperature gradient characteristic value is greater than or equal to the preset threshold. If so, the corresponding area is marked. For the marked area, the system adjusts the scanning strategy to increase the scanning frequency of these areas to times of the original, and is an integer greater than 1.

[0014] Advantages of the present invention: (1) By integrating the technologies of real-time monitoring of the beam steering angle and local temperature gradient, and using advanced data analysis means such as clustering algorithms and fast Fourier transforms, the present invention realizes precise monitoring and in-depth analysis of the operating state of explosion-proof equipment. Specifically, a high-precision angle sensor is used to continuously record the changes in the beam steering angle, and the abnormal characteristic value of the beam steering angle is calculated by a clustering algorithm to evaluate the stability of ultrasonic wave propagation; at the same time, a temperature sensor network distributed at key positions of the equipment is used to obtain local temperature data, and the local temperature gradient characteristic value is calculated after being processed by a fast Fourier transform to evaluate the consistency of the internal structure of the equipment. This method not only significantly improves the detection sensitivity and accuracy of potential faults, but also can identify subtle changes that may affect the safety of the equipment at an early stage, thereby providing a scientific basis for taking preventive measures in a timely manner. When the system detects an abnormal situation, it can automatically adjust the beam steering angle to cover the relevant area and increase the scanning density to ensure a more detailed inspection of the potential hazard area. This precise and dynamic safety hazard detection mechanism not only greatly improves the safety and reliability of the operation of explosion-proof equipment, but also provides strong support for optimizing maintenance strategies and reducing operating costs, reflecting the outstanding contribution of the present invention in improving industrial safety levels.

[0015] (2)If it is determined that the current detection process is in an unstable state by comprehensively analyzing the abnormal eigenvalue of the beam steering angle and the local temperature gradient eigenvalue, the present invention can intelligently adjust the beam steering angle to accurately cover the abnormal area, and dynamically increase the scanning density for the abnormal area shown by the local temperature gradient. This adaptive adjustment mechanism not only ensures a more detailed and comprehensive detection of potential problem areas, but also significantly improves the response speed and adaptability of the overall monitoring system. Based on real-time monitoring data, the system can dynamically optimize the detection strategy, which not only ensures key attention to key risk areas, but also avoids unnecessary resource waste, achieving efficient, flexible and accurate equipment monitoring. In addition, with the accumulation of more historical data and the continuous optimization of machine learning models (such as support vector machines), the present invention supports the self-learning and improvement of the system, thereby continuously improving the prediction accuracy and reliability. This feature not only enhances the safety and operating efficiency of explosion-proof equipment, but also provides a solid foundation for future expansion and upgrading, making the present invention show wide applicability and excellent forward-looking in practical applications and becoming an important innovative means to ensure industrial safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below with reference to the accompanying drawings.

[0017] Figure 1 is a specific step flowchart of the non-destructive testing optimization method based on the accuracy feedback of the safety status evaluation of explosion-proof equipment according to the present invention; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Please refer to Figure 1 as shown, the present invention is a non-destructive testing optimization method based on the accuracy feedback of the safety status evaluation of explosion-proof equipment, including the following steps: S1: During the monitoring period of the safety status of the explosion-proof equipment, the beam steering angle and the local temperature gradient are monitored in real time; Among them, the beam steering angle is used to dynamically adjust the direction of the ultrasonic beam to adapt to complex geometries, and the local temperature gradient is measured by infrared thermal imaging technology to reflect the integrity of the internal materials; S2: According to the change degree of the beam steering angle, determine the abnormal eigenvalue of the beam steering angle and evaluate the stability of ultrasonic wave propagation; S3: Analyze the change amplitude of the local temperature gradient, calculate the local temperature gradient eigenvalue, and evaluate the consistency of the internal structure of the explosion-proof equipment; S4: Comprehensively analyze the abnormal characteristics of the beam steering angle and the local temperature gradient eigenvalue to determine whether the current detection process is in an unstable state; S5: If it is determined to be in an unstable state, the system automatically adjusts the beam steering angle and increases the scanning density for the abnormal area shown by the local temperature gradient.

[0020] In S1, during the monitoring period of the explosion-proof equipment's safety status, the beam steering angle and the local temperature gradient are monitored in real time, specifically including: During the monitoring period of the explosion-proof equipment's safety status, the process of monitoring the beam steering angle and the local temperature gradient in real time is a key step to ensure the safe operation of the equipment. First, for the acquisition of beam steering angle data, through the high-precision angle sensors installed on the explosion-proof equipment, the current steering angle of the beam is continuously recorded at fixed time intervals (such as once per second). The angle sensors can provide accurate angle measurement values to ensure that even the slightest angle changes can be captured, and these data are transmitted to the central monitoring system in real time for storage and subsequent analysis. At the same time, to ensure the accuracy and reliability of the data, the system will conduct a preliminary quality check on the collected data and eliminate abnormal readings.

[0021] Meanwhile, the monitoring of the local temperature gradient is achieved through a network of temperature sensors distributed at key positions of the explosion-proof equipment. These sensors collect the temperature information of the surrounding environment at preset time intervals (such as once per minute) and calculate the temperature difference between adjacent time points to reflect the temperature change trend in the local area. To accurately capture rapidly changing temperature patterns, higher-density sensors or higher-frequency data acquisition strategies may be configured in some key areas. All the collected temperature data will also be sent to the central monitoring system, where specialized algorithms are used to process these data and calculate the local temperature gradient eigenvalue to detect potential safety hazards in a timely manner. This process not only helps to understand the working state of the equipment but also provides an important basis for subsequent risk assessment.

[0022] In S2, according to the degree of change of the beam steering angle, determine the abnormal characteristic value of the beam steering angle and evaluate the stability of ultrasonic wave propagation, specifically including: During the monitoring period of the explosion-proof equipment's safety status, obtain the beam steering angle data according to the time series, calculate the abnormal characteristic value of the beam steering angle according to the degree of change of the beam steering angle, and judge whether the abnormal characteristic value of the beam steering angle is greater than or equal to the preset threshold. If so, the ultrasonic wave propagation is stable; if not, the ultrasonic wave propagation is unstable.

[0023] The process of obtaining the abnormal characteristic value of the beam steering angle is as follows: Obtain the beam steering angle data set of the explosion-proof equipment during the monitoring period , where represents the beam steering angle data set, represents the number of samples in the data set, represents the -th beam steering angle at the Select the number of clusters and initialize centroids , where represents the desired number of clusters, represents the -th initial centroid of the cluster; For each point in the beam steering angle data set, calculate the Euclidean distance between it and each centroid and assign it to the nearest cluster, update the centroid of each cluster to be equal to the average position of all points in the corresponding cluster, and the update formula is: ; In the formula, represents the set of data points in the -th cluster, represents the number of data points in cluster , represents the -th beam steering angle, represents the number of beam steering angles; Repeat the assignment and update steps until the centroid reaches the preset maximum number of iterations; Judge whether the Euclidean distance between each point in the data point set and the centroid of the cluster it belongs to is greater than or equal to the preset threshold. If so, it is determined as an outlier, and calculate the average Euclidean distance of the outliers in the data point set to obtain the beam steering angle outlier characteristic value.

[0024] It should be noted that: By monitoring the beam steering angle data of the explosion-proof device in real time during the monitoring period and applying the clustering algorithm to analyze these data to calculate the beam steering angle outlier characteristic value, and then evaluate the stability of ultrasonic wave propagation. Specifically, by quantitatively analyzing the degree of change of the beam steering angle, the outliers deviating from the normal range are identified, and a comprehensive outlier characteristic value is calculated based on these outliers. If the beam steering angle outlier characteristic value is greater than or equal to the preset threshold, it indicates that there may be instability problems in ultrasonic wave propagation; otherwise, it is considered that the ultrasonic wave propagation is stable. The technical effect of this method is to provide an effective means to dynamically monitor and evaluate the safety and reliability of the operation of explosion-proof devices. Its innovation lies in combining time series data analysis and clustering technology, which can accurately capture the subtle outliers in the change of beam steering angle and provide strong support for timely discovery of potential safety hazards.

[0025] In S3, analyze the variation range of the local temperature gradient, calculate the local temperature gradient eigenvalue, and evaluate the consistency of the internal structure of the explosion-proof equipment, specifically including: During the monitoring period of the safe state of the explosion-proof equipment, obtain the temperature data inside the explosion-proof equipment according to the time series. Calculate the local temperature gradient eigenvalue based on the variation range of the local temperature gradient, and determine whether the local temperature gradient eigenvalue is greater than or equal to the preset threshold. If so, the internal structure of the explosion-proof equipment is inconsistent; if not, the internal structure of the explosion-proof equipment is consistent.

[0026] The process of obtaining the local temperature gradient eigenvalue is as follows: Obtain the temperature data set of the explosion-proof equipment during the monitoring period , where represents the temperature data set, represents the number of samples in the data set, represents the th temperature value at the time point in the time series; Calculate the temperature difference between adjacent time points and integrate all temperature differences into a difference sequence to obtain the local temperature gradient; Apply the fast Fourier transform to the local temperature gradient to obtain the frequency domain representation, and calculate the ratio of the sum of the squares of all non-zero frequency components to the standard deviation to obtain the local temperature gradient eigenvalue.

[0027] It should be noted that: by deeply analyzing the temperature change pattern, potential structural inconsistencies or abnormal hot spots can be discovered in a timely manner, which is crucial for preventing failures and ensuring the safe operation of the equipment. In addition, the characteristics of frequency domain analysis make this method sensitive to different types of temperature changes, helping to identify small but important changes that may affect the equipment performance. Evaluate the equipment status through the variation range of the local temperature gradient and its spectral characteristics. This method goes beyond the traditional single-dimensional analysis method and provides a more comprehensive and accurate description of the equipment health status by comprehensively considering the overall intensity and fluctuation of the temperature change.

[0028] In S4, comprehensively analyze the beam steering angle anomaly feature and the local temperature gradient eigenvalue to determine whether the current detection process is in an unstable state, specifically including: Obtain the beam steering angle anomaly feature and the local temperature gradient eigenvalue, construct the beam steering angle anomaly feature and the local temperature gradient eigenvalue into a comprehensive feature vector as the input of the machine learning model, and the output of the model is the safety status score of the explosion-proof equipment. The machine learning model is a support vector machine model.

[0029] The process of obtaining the safety status score is as follows: Obtain the beam steering angle anomaly feature, local temperature gradient eigenvalue, and safety status score within the historical monitoring period of the explosion-proof equipment as the training dataset, and train the support vector machine model. With the goal of minimizing the error between the predicted safety status score and the actual safety status score, train the support vector machine model. According to the trained support vector machine model, input the comprehensive feature vector of the current explosion-proof equipment into the trained support vector machine model, and the model will output the accurate safety status score.

[0030] It should be noted that during the training process, cross-validation technology is adopted to optimize the model parameters, including the penalty coefficient and kernel function parameters, to achieve the best generalization performance. After training, the obtained support vector machine model can receive a new comprehensive feature vector as input and output the corresponding safety status score of the explosion-proof equipment. This score is used to evaluate the current safety condition of the equipment and guide subsequent maintenance decisions.

[0031] In S5, if it is determined to be an unstable state, the system automatically adjusts the beam steering angle and increases the scanning density for the abnormal area shown by the local temperature gradient. Specifically, it includes: If, in the evaluation of the safety status of the explosion-proof equipment, it is determined to be an unstable state, for the abnormal situation of the beam steering angle, the system automatically adjusts the beam steering angle through a built-in algorithm to cover the existing abnormal area. Specifically, it includes: The system determines the angle range that needs to be adjusted according to the beam steering angle anomaly eigenvalue, and changes the direction of the beam by controlling the mechanical structure. The calculation expression for the adjustment is: ; Among them, represents the new beam steering angle, represents the original beam steering angle. Among them, , represents the adjustment coefficient, which is used to adjust the influence of the anomaly eigenvalue on the angle adjustment amount, represents the beam steering angle anomaly eigenvalue, represents the basic adjustment amount, which is used to compensate for system errors or ensure the minimum adjustment requirement, represents the angle adjustment amount; For the abnormal area shown by the local temperature gradient, the system will increase the scanning density of this area. The system first judges whether the local temperature gradient eigenvalue is greater than or equal to the preset threshold. If so, the corresponding area is marked. For the marked area, the system adjusts the scanning strategy to increase the scanning frequency of these areas to times the original, and is an integer greater than 1.

[0032] Working principle of the present invention: During the monitoring period, the beam steering angle and local temperature gradient data of the explosion-proof equipment are collected in real time. The beam steering angle is recorded at fixed intervals by a high-precision angle sensor to ensure that the slightest angle changes are captured; the local temperature gradient is measured by a network of temperature sensors distributed at key positions of the equipment to reflect the integrity of the internal materials. According to the degree of change of the beam steering angle, a clustering algorithm is used to calculate the abnormal eigenvalue of the beam steering angle and evaluate the stability of ultrasonic wave propagation. If the abnormal eigenvalue exceeds the preset threshold, instability is considered to exist. Analyze the change amplitude of the local temperature gradient, use the fast Fourier transform to calculate the local temperature gradient eigenvalue, and evaluate the consistency of the internal structure of the equipment. If the local temperature gradient eigenvalue exceeds the standard, it indicates that there may be inconsistencies in the structure. The abnormal feature of the beam steering angle and the local temperature gradient eigenvalue are constructed into a comprehensive feature vector and input into the support vector machine model to output the safety status score of the equipment, which is used to determine whether the current detection process is in an unstable state. If the system determines an unstable state, the beam steering angle is automatically adjusted to cover the abnormal area, and the scanning density is increased for the abnormal area shown by the local temperature gradient to ensure more detailed detection of potential problem areas. This method can not only accurately identify potential safety hazards during equipment operation, but also improve the overall monitoring efficiency by dynamically adjusting the detection strategy, thus effectively ensuring the safe operation of explosion-proof equipment, and has important practical value and innovation significance.

[0033] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0034] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0035] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0036] It should be understood that in various embodiments of the present application, the order numbers of the above processes do not indicate the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0037] The above has described in detail one embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. Any equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the present invention.

Claims

1. A non-destructive testing optimization method based on the accuracy feedback of the safety status assessment of explosion-proof equipment, characterized in that, It includes the following steps: S1: During the monitoring period of the explosion-proof equipment's safe state, the beam steering angle and local temperature gradient are monitored in real time; Among them, the beam steering angle is used to dynamically adjust the ultrasonic beam direction to adapt to complex geometries, and the local temperature gradient is measured by infrared thermal imaging technology to reflect the integrity of internal materials; S2: According to the degree of change of the beam steering angle, determine the abnormal characteristic value of the beam steering angle and evaluate the stability of ultrasonic wave propagation; S3: Analyze the change amplitude of the local temperature gradient, calculate the local temperature gradient characteristic value, and evaluate the consistency of the internal structure of the explosion-proof equipment; S4: Conduct a comprehensive analysis of the abnormal characteristics of the beam steering angle and the local temperature gradient characteristic value to determine whether the current detection process is in an unstable state; S5: If it is determined to be in an unstable state, the system automatically adjusts the beam steering angle and increases the scanning density for the abnormal area shown by the local temperature gradient.

2. The non-destructive testing optimization method based on the accuracy feedback of the safety status assessment of explosion-proof equipment according to claim 1, characterized in that The process of determining the abnormal characteristic value of the beam steering angle according to the degree of change of the beam steering angle and evaluating the stability of ultrasonic wave propagation specifically includes: During the monitoring period of the explosion-proof equipment's safe state, obtain the beam steering angle data according to the time series. According to the degree of change of the beam steering angle, calculate the abnormal characteristic value of the beam steering angle, and determine whether the abnormal characteristic value of the beam steering angle is greater than or equal to the preset threshold. If so, the ultrasonic wave propagation is stable; if not, the ultrasonic wave propagation is unstable.

3. The non-destructive testing optimization method based on the accuracy feedback of the safety status assessment of explosion-proof equipment according to claim 2, wherein The process of obtaining the abnormal characteristic value of the beam steering angle is as follows: Obtain the beam steering angle data set of the explosion-proof equipment during the monitoring period; Number of clusters selected and initialize centroids; For each point in the beam steering angle dataset, calculate the Euclidean distance between it and each centroid and assign it to the closest cluster, updating the centroid of each cluster to be equal to the average position of all points in the corresponding cluster; Repeat the assignment and update steps until the centroid reaches the preset maximum number of iterations; Determine whether the Euclidean distance between each point in the data point set and the centroid of the belonging cluster is greater than or equal to the preset threshold. If so, it is determined as an abnormal point, and calculate the average Euclidean distance of the abnormal points in the data point set to obtain the abnormal characteristic value of the beam steering angle.

4. The non-destructive testing optimization method based on the accuracy feedback of the safety status assessment of explosion-proof equipment according to claim 1, characterized in that, The process of analyzing the change amplitude of the local temperature gradient, calculating the local temperature gradient characteristic value, and evaluating the consistency of the internal structure of the explosion-proof equipment specifically includes: During the monitoring period of the explosion-proof equipment's safe state, obtain the temperature data inside the explosion-proof equipment according to the time series. According to the change amplitude of the local temperature gradient, calculate the local temperature gradient characteristic value, and determine whether the local temperature gradient characteristic value is greater than or equal to the preset threshold. If so, the internal structure of the explosion-proof equipment is inconsistent; if not, the internal structure of the explosion-proof equipment is consistent.

5. The non-destructive testing optimization method based on the accuracy feedback of the safety status assessment of explosion-proof equipment according to claim 1, characterized in that The process of obtaining the local temperature gradient characteristic value is as follows: Obtain the temperature dataset of the explosion-proof equipment within the monitoring period , where represents the temperature dataset represents the number of samples in the dataset. Among them represents the temperature dataset represents the number of samples in the dataset. By calculating the temperature difference between adjacent time points and integrating all the temperature differences into a difference sequence, the local temperature gradient is obtained Apply the fast Fourier transform to the local temperature gradient to obtain the frequency domain representation, and calculate the ratio of the sum of squares of all non-zero frequency components to the standard deviation to obtain the local temperature gradient characteristic value.

6. The non-destructive testing optimization method based on the accuracy feedback of the safety state assessment of explosion-proof equipment according to claim 1, wherein, The comprehensive analysis of the abnormal characteristics of the beam steering angle and the local temperature gradient characteristic value specifically includes: Obtain the abnormal characteristics of the beam steering angle and the local temperature gradient characteristic value, construct the abnormal characteristics of the beam steering angle and the local temperature gradient characteristic value into a comprehensive feature vector as the input of the machine learning model, and the output of the model is the safety state score of the explosion-proof equipment. The machine learning model is a support vector machine model.

7. The non-destructive testing optimization method based on the accuracy feedback of the explosion-proof equipment safety status assessment according to claim 6, characterized in that, The process of obtaining the safety state score is as follows: Obtain the beam steering angle anomaly feature, local temperature gradient eigenvalue, and safety status score within the historical monitoring period of the explosion-proof device as the training data set, and train the support vector machine model. Take minimizing the error between the predicted safety status score and the actual safety status score as the training objective to train the support vector machine model. According to the trained support vector machine model, input the comprehensive feature vector of the current explosion-proof device into the trained support vector machine model, and the model will output the accurate safety status score.

8. The non-destructive testing optimization method based on the accuracy feedback of the safety status assessment of explosion-proof equipment according to claim 1, wherein, The judgment of whether the current detection process is in an unstable state specifically includes: Judge whether the safety status score of the current detection process of the explosion-proof device is greater than or equal to the preset threshold. If so, the current detection process is in an unstable state; if not, the current detection process is in a stable state.

9. The non-destructive testing optimization method based on the accuracy feedback of the safety status assessment of explosion-proof equipment according to claim 1, characterized in that The system automatically adjusts the beam steering angle and increases the scanning density for the abnormal area shown by the local temperature gradient, specifically including: If the safety status assessment of the explosion-proof device determines an unstable state, for the abnormal situation of the beam steering angle, the system determines the angle range to be adjusted according to the beam steering angle anomaly eigenvalue, and changes the direction of the beam by controlling the mechanical structure; The system first determines whether the local temperature gradient eigenvalue is greater than or equal to a preset threshold. If so, the corresponding area is marked. For the marked areas, the system adjusts the scanning strategy to increase the scanning frequency of these areas to times the original, and is an integer greater than 1.

Images