Heating pipe breakage detection method and system based on ultrasonic technology

Abstract

The application relates to the technical field of intelligent sensors, in particular to a heating pipeline damage detection method and system based on ultrasonic technology, which comprises the following steps: analyzing the energy distribution of components of multiple scales of a composite ultrasonic signal, combining the energy contribution degree of main characteristic components of the composite ultrasonic signal in a frequency domain to determine a time-frequency defect index; analyzing the difference between the time-frequency defect index of the composite ultrasonic signal and the clustering center of a normal clustering cluster, combining an abnormal probability to determine a defect characteristic value; and based on the defect characteristic value, adjusting the ability of an intelligent sensor array to capture defect echo at a deep layer of a heating pipeline. The application solves the problem of insufficient penetration of high-frequency ultrasonic signals caused by multiple materials and the false alarm of heating pipeline defects caused by differences in pipeline installation conditions, and improves the accuracy and reliability of heating pipeline damage detection.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of intelligent sensors, in particular to a heating pipeline damage detection method and system based on ultrasonic technology. BACKGROUND

[0002] With the acceleration of urbanization, the scale of underground heating pipelines continues to expand. Problems such as pipeline aging, corrosion and third-party construction damage lead to frequent leakage accidents. Traditional detection methods rely on pressure testing, which has defects such as low efficiency, poor positioning accuracy and the need for shutdown detection. In this context, non-intrusive ultrasonic detection technology has emerged. By analyzing the changes in acoustic characteristics of ultrasonic waves propagating in the pipeline, defects such as pipeline cracks, holes and wall thickness thinning can be accurately identified.

[0003] In the detection of heating pipeline damage, ultrasonic waves can stably propagate in metal pipelines and accurately feedback defect information due to the material homogeneity and high acoustic conductivity. However, when facing non-metal or composite material pipelines such as plastic, glass steel and PE, the acoustic impedance difference leads to ultrasonic energy attenuation, and high-frequency signals lack penetration, making it difficult to detect deep and small defects, reducing the accuracy and reliability of heating pipeline damage detection. In addition, multiple reflections, refractions and scattering caused by multi-layer complex structures lead to disordered sound wave paths and energy dispersion, resulting in false positives or false negatives in heating pipeline damage detection, reducing the accuracy and reliability of heating pipeline damage detection. SUMMARY

[0004] To solve the above technical problems, the purpose of the present application is to provide a heating pipeline damage detection method and system based on ultrasonic technology, and the technical solution adopted is as follows:

[0005] In the first aspect, the application provides a heating pipeline damage detection method based on ultrasonic technology, which comprises the following steps:

[0006] In the heating pipeline, an intelligent sensor array is used to obtain a composite ultrasonic signal within a predetermined time period before each time;

[0007] The composite ultrasonic signal is decomposed into components of multiple scales, the energy distribution of the components at each scale is analyzed, and the energy distribution value of the composite ultrasonic signal at each time is determined; based on the energy contribution degree of the main characteristic components of the composite ultrasonic signal in the frequency domain to the energy of the composite ultrasonic signal, the energy contribution value of the composite ultrasonic signal at each time is determined, and the time-frequency defect index of the composite ultrasonic signal at each time is determined in combination with the energy distribution value;

[0008] analyzing the discrete degree of all data of the composite ultrasonic signal in the time domain and the extreme distribution of all peak values in the frequency domain at each time, and combining the time-frequency defect index to evaluate the abnormal probability of the composite ultrasonic signal at each time; clustering the time-frequency defect indexes of all times within a preset time period before the current time to obtain a normal clustering cluster; determining a defect feature value of the composite ultrasonic signal at the current time by analyzing the difference between the clustering center of the normal clustering cluster and the time-frequency defect index of the composite ultrasonic signal at the current time, and combining the abnormal probability;

[0009] Based on the defect feature value, the ability of the intelligent sensor array to capture defect echo at a deep position of the heating pipeline is adjusted.

[0010] Preferably, the method for obtaining the composite ultrasonic signal comprises:

[0011] Various signals of the heating pipeline at each time and within a preset time period before the current time are collected by the intelligent sensor array, and the signal-to-noise ratios of the various signals are obtained. The product of the signal intensity normalization value of the frequency domain signal of each frequency and the signal-to-noise ratio of the various signals is calculated. The products of the frequency domain signals of all kinds of signals at the same frequency are added to obtain the signal intensity of the corresponding frequency of the frequency domain signal of the composite ultrasonic signal. The frequency domain signal of the composite ultrasonic signal is converted to the time domain to obtain the composite ultrasonic signal. The various signals include low-frequency ultrasonic echo of a non-metal pipeline, high-frequency ultrasonic echo of a metal pipeline, environmental noise signal, and pipeline mechanical vibration signal.

[0012] Preferably, the method for determining the energy distribution value of the composite ultrasonic signal at each time comprises:

[0013] The composite ultrasonic signal at each time is taken as the input of wavelet transform, and the components at a preset number of scales are output. The energy mean value of the components at each scale is calculated. The cumulative sum of the energy mean values of the components at the preset number of scales is taken as the energy distribution value of the composite ultrasonic signal at each time.

[0014] Preferably, the method for determining the energy contribution value of the composite ultrasonic signal at each time comprises:

[0015] The composite ultrasonic signal at each time is taken as the input of principal component analysis, and the variance contribution rate of all principal components is output. The sum of the first preset number of variance contribution rates in the descending order arrangement result is taken as the energy contribution value of the composite ultrasonic signal at each time.

[0016] Preferably, the time-frequency defect index of the composite ultrasonic signal at each time is the result of positive fusion of the energy distribution value and the energy contribution value of the composite ultrasonic signal at each time.

[0017] Preferably, the evaluation of the abnormal probability of the composite ultrasonic signal at each time comprises:

[0018] The variance of all data of the composite ultrasonic signal at each time in the time domain, the maximum peak in the frequency domain, and the time-frequency defect index at each time are taken as inputs of a logistic regression algorithm, and the abnormal probability of the composite ultrasonic signal at each time is output.

[0019] Preferably, the normal cluster is a cluster with the minimum mean of the time-frequency defect index among all clusters obtained by clustering the time-frequency defect indexes of all times within a preset time period before the current time.

[0020] Preferably, the defect feature value of the composite ultrasonic signal at the current time is expressed as: In the formula, D represents the difference between the time-frequency defect index of the composite ultrasonic signal at the current time and the cluster center of the normal cluster; P n represents the abnormal probability of the composite ultrasonic signal at time n within a preset time period before the current time; N represents the length of the preset time period; and norm() represents a normalization function.

[0021] Preferably, the adjustment of the ability of the intelligent sensor array to capture the defect echo at the deep layer of the heating pipe includes:

[0022] If the defect feature value of the composite ultrasonic signal at the current time is greater than a preset threshold, the intelligent sensor array is automatically adjusted to a low-frequency mode to capture the defect echo at the deep layer of the heating pipe, otherwise, the intelligent sensor array is not adjusted. In the second aspect, the embodiments of the present application also provide a heating pipe damage detection system based on ultrasonic technology, which comprises a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the heating pipe damage detection method based on ultrasonic technology in any of the above aspects when executing the computer program.

[0023] The present application has at least the following beneficial effects:

[0024] The application is aimed at the problems of large acoustic impedance difference of non-metal pipelines, fast ultrasonic wave attenuation and sound wave scattering caused by multi-layer wrapping structure. By analyzing the energy contribution degree of main characteristic components of composite ultrasonic signals in the frequency domain to the composite ultrasonic signals, and combining the energy distribution value, a time-frequency defect index is constructed, reflecting the defect-related time-domain transient energy intensity and frequency-domain abnormal energy distribution, solving the positioning ambiguity problem caused by the noise covering of the echo of deep small defects in thick-walled non-metal pipelines and the disorder of sound wave path, and improving the accuracy and reliability of the heating pipeline damage detection. Further, the application is aimed at the misjudgment caused by temperature fluctuation and pipeline material difference. The clustering algorithm is used to classify the time-frequency defect index, and the time-domain variance and frequency-domain peak value are combined to supervise the training of the logistic regression model, so as to obtain the defect characteristic value, reflecting the global deviation degree of the current signal from the historical normal mode and the defect accumulation risk, reducing the false alarm of the heating pipeline defects caused by the environmental temperature change and the difference of pipeline installation conditions, and improving the accuracy and reliability of the heating pipeline damage detection. Further, the application optimizes the working mode of the intelligent sensor array based on the defect characteristic value in real time, enhances the detection depth of ultrasonic waves in non-metal pipelines, solves the problem of insufficient penetration of high-frequency ultrasonic signals caused by multiple materials, reduces the probability of false judgment or missed detection of heating pipeline defects, and improves the accuracy and reliability of the heating pipeline damage detection. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0026] Figure 1 The step flow chart of the heating pipeline damage detection method based on ultrasonic technology provided by one embodiment of the application is shown in the figure.

[0027] Figure 2 The abnormal probability extraction process schematic diagram provided by one embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0028] In order to further illustrate the technical means and effects adopted by the application to achieve the predetermined invention purpose, the following will combine the drawings and the preferred embodiments to specifically describe the heating pipeline damage detection method and system based on ultrasonic technology according to the application, its specific implementation, structure, features and effects as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0029] Unless otherwise defined, 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 application belongs.

[0030] The specific scheme of the heating pipeline breakage detection method and system based on ultrasonic technology provided in the application will be specifically described below with reference to the drawings.

[0031] Please refer to Figure 1 which shows the step flowchart of the heating pipeline breakage detection method based on ultrasonic technology provided in an embodiment of the application, and the method comprises the following steps:

[0032] Step S1: In the heating pipeline, a composite ultrasonic signal within a preset time length before each time is acquired by using an intelligent sensor array.

[0033] The heating pipeline breakage detection system based on ultrasonic technology comprises an ultrasonic emission / reception array module, a multi-channel signal acquisition module, an embedded processing unit module, and a dynamic parameter optimization module, and the functions of each module are as follows:

[0034] Ultrasonic emission / reception array module: An array composed of wideband intelligent sensors is adopted, which supports multi-band coverage and adaptive signal emission, can improve the defect resolution of metal pipelines at high frequencies, and can enhance the ultrasonic wave penetration ability of non-metal pipelines through low frequencies.

[0035] Multi-channel signal acquisition module: The multi-channel signal acquisition module integrates a 24-bit high-precision ADC and a 1MHz sampling rate design, can capture ultrasonic echo signals in real time and synchronously record environmental noise and pipeline vibration data, and provides an original data basis for subsequent analysis.

[0036] Embedded processing unit module: Real-time edge processing is realized based on an FPGA chip, and two sub-modules, i.e., a time-frequency domain feature extraction module and a joint risk analysis module, are executed.

[0037] Dynamic parameter optimization module: Based on the analysis results of the two sub-modules, i.e., the time-frequency domain feature extraction module and the joint risk analysis module, the ultrasonic wave parameters are dynamically optimized.

[0038] The ultrasonic emission / reception array composed of the wideband intelligent sensor group realizes multi-band coverage, which can utilize high frequency to improve the defect resolution of metal pipelines and can enhance the ultrasonic penetration ability of non-metal pipelines through low frequency. The intelligent sensor integrates 24-bit high-precision ADC and 1MHz sampling rate design, captures ultrasonic echo signals in real time, and synchronously records environmental noise and pipeline vibration data, providing original data basis for subsequent analysis. The embedded processing unit realizes edge real-time processing based on FPGA chip, performs time-frequency domain feature extraction and joint risk analysis, and dynamically optimizes ultrasonic parameters to adapt to different pipeline materials and working conditions.

[0039] The wideband intelligent sensor array and multi-channel signal acquisition module are installed on the outer wall of the pipeline and at key nodes along the line to collect low-frequency ultrasonic echo signals of non-metal pipelines and high-frequency ultrasonic echo signals of metal pipelines, which are used to enhance the deep penetration of non-metal materials and the defect resolution of metal surfaces. Intelligent environmental noise sensors and intelligent pipeline vibration sensors are synchronously deployed, and the embedded processing unit analyzes noise spectrum and vibration waveform in real time. The distributed network along the pipeline captures environmental noise spectrum and pipeline mechanical vibration waveform data in real time, which is used to construct a background interference feature library and abnormal vibration correlation analysis.

[0040] The intelligent sensor array collects various signals of the heating pipeline at each time and within a preset time period before the time, and obtains the signal-to-noise ratio of each signal. The product of the signal intensity normalization value of the frequency domain signal of each signal at each frequency and the signal-to-noise ratio is calculated. The products of the frequency domain signals of all kinds of signals at the same frequency are added as the signal intensity of the corresponding frequency of the frequency domain signal of the composite ultrasonic signal. The frequency domain signal of the composite ultrasonic signal is converted to the time domain to obtain the composite ultrasonic signal. In this embodiment, the data acquisition frequency is f.

[0041] It should be noted that the values of the preset time period and the data acquisition frequency f are artificially set. In this embodiment, the value of the preset time period is 1ms, and the value of the data acquisition frequency f is 1MHz. In actual application, as other implementation manners, the implementer can also set it according to the specific situation, and this embodiment does not have special restrictions.

[0042] In particular, if there is less than the preset time period before the current time, no signal acquisition is performed at the current time.

[0043] It should be noted that there are many methods for time-frequency conversion of signals. In this embodiment, short-time fast Fourier transform is used for time-frequency conversion of signals. In actual application, as other implementation manners, the implementer can also use other time-frequency conversion algorithms such as fast Fourier transform. The selection of time-frequency conversion algorithm is not limited in this embodiment.

[0044] Wherein, the process of obtaining signal-to-noise ratio and short-time fast Fourier transform algorithm are known technologies, and the specific process of obtaining signal-to-noise ratio and converting time domain signal to frequency domain by using short-time fast Fourier transform algorithm will not be repeated.

[0045] Step S2: decompose the composite ultrasonic signal into components of multiple scales, analyze the energy distribution of the components at each scale, determine the energy distribution value of the composite ultrasonic signal at each time; determine the energy contribution value of the composite ultrasonic signal at each time based on the degree of energy contribution of the main characteristic component of the composite ultrasonic signal in the frequency domain, and determine the time-frequency defect index of the composite ultrasonic signal at each time in combination with the energy distribution value.

[0046] Due to the significant difference in ultrasonic impedance characteristics between non-metallic pipelines and metals, the ultrasonic energy is sharply attenuated during propagation, especially in thick-walled or large-diameter pipelines, the high-frequency signal penetration is insufficient, and the echo of small defects is easily covered by background noise; at the same time, the sound wave multiple reflection and scattering caused by the outer thermal insulation layer, corrosion-resistant layer or buried structure cause the sound wave path to be disorderly and the defect positioning to be fuzzy.

[0047] Therefore, based on the above analysis, by decomposing the composite ultrasonic signal into components of multiple scales, analyzing the energy distribution of the components at each scale, determining the energy distribution value of the composite ultrasonic signal at each time; determining the energy contribution value of the composite ultrasonic signal at each time based on the degree of energy contribution of the main characteristic component of the composite ultrasonic signal in the frequency domain, and determining the time-frequency defect index of the composite ultrasonic signal at each time in combination with the energy distribution value, the specific process is as follows:

[0048] (1) In this embodiment, the composite ultrasonic signal is decomposed into components of multiple scales, the energy distribution of the components at each scale is analyzed, and the energy distribution value of the composite ultrasonic signal at each time is determined, specifically:

[0049] As an implementation, in this embodiment, the composite ultrasonic signal at each time is taken as the input of wavelet transform, wherein the wavelet basis is selected as "db4", the decomposition scale is set to a preset number, and the components at a preset number of scales are output;

[0050] It should be noted that the value of the preset number is artificially set, and in this embodiment, the value of the preset number is 5, and the implementer can also set it himself according to the specific situation, and this embodiment does not make special restrictions.

[0051] Wherein, the wavelet transform is a known technology, and the specific process of using it for multi-scale decomposition of the signal will not be repeated.

[0052] Further, the energy mean value of the components at each layer scale is calculated, and the accumulation of the energy mean values of the components at the preset number of layer scales is taken as the energy distribution value of the composite ultrasonic signal at each time, which is used to represent the local characteristics of the composite ultrasonic signal in different frequency bands and time, and to distinguish the defect signal from the noise interference. The greater the energy distribution value is, the stronger the defect-related energy in the composite ultrasonic signal is, and the greater the possibility of the heating pipeline damage is.

[0053] (2) Further, the energy contribution value of the composite ultrasonic signal at each time is determined based on the degree of energy contribution of the main characteristic component of the composite ultrasonic signal in the frequency domain, specifically as follows:

[0054] As an implementation manner, the composite ultrasonic signal at each time is taken as the input of the principal component analysis, and the variance contribution rate of all principal components is output. The sum of the first preset number of variance contribution rates in the descending order of the results is taken as the energy contribution value of the composite ultrasonic signal at each time, which reflects the abnormal degree of the frequency energy distribution of the composite ultrasonic signal. The key frequency characteristics in the frequency domain are extracted by dimension reduction, the redundant noise is suppressed, and the frequency component related to the defect is highlighted. The greater the value is, the more likely the frequency band with concentrated energy corresponds to the local defect such as the crack or delamination of the heating pipeline.

[0055] It should be noted that the value of the preset number is artificially set, and the value of the preset number in the embodiment is 3. In actual application, the implementer can also set it by himself according to the specific situation, which is not specially limited in the embodiment.

[0056] The principal component analysis is a known technology, and the process of analyzing the energy contribution of the main component in the composite ultrasonic signal will not be described here.

[0057] (3) Further, the time-frequency defect index of the composite ultrasonic signal at each time is determined based on the energy contribution value of the composite ultrasonic signal at each time and in combination with the energy distribution value, specifically as follows:

[0058] In the embodiment, the result of positively fusing the energy distribution value and the energy contribution value of the composite ultrasonic signal at each time is taken as the time-frequency defect index of the composite ultrasonic signal at each time, which is used to represent the global possibility of monitoring the pipeline damage at each time. The greater the time-frequency defect index at the current time is, the more likely the significant time-domain instantaneous energy and frequency-domain concentrated energy exist in the composite ultrasonic signal, that is, the greater the energy distribution value and the energy contribution value are, and the greater the possibility of the heating pipeline damage is. Conversely, the smaller the time-frequency defect index at the current time is, the less likely the significant time-domain instantaneous energy and frequency-domain concentrated energy exist in the composite ultrasonic signal, that is, the smaller the energy distribution value and the energy contribution value are, and the smaller the possibility of the heating pipeline damage is.

[0059] It should be understood that positive fusion refers to combining two or more indicators together through addition or multiplication or the like, so as to obtain a comprehensive indicator, so as to more comprehensively and accurately evaluate a phenomenon or a problem. The fusion method is not limited to simple arithmetic operation, but can also include more complex statistical models and analysis methods, and the implementer can select them according to specific circumstances, and the present embodiment does not make special limitations.

[0060] Preferably, in the present embodiment, the sum of the energy distribution value and the energy contribution value of the composite ultrasonic signal at each time is taken as the time-frequency defect index of the composite ultrasonic signal at each time; in actual application, as another implementation manner, the product of the energy distribution value and the energy contribution value of the composite ultrasonic signal at each time is taken as the time-frequency defect index of the composite ultrasonic signal at each time.

[0061] At this point, by using wavelet transform to decompose the composite ultrasonic signal into multiple scale components, the energy mean value of the components at each scale is calculated and accumulated to obtain the energy distribution value; further, by principal component analysis, the main characteristic components and their variance contribution rates in the frequency domain of the signal are extracted, and the variance contribution rates are accumulated to obtain the energy contribution value, reflecting the abnormal degree of frequency energy distribution; finally, the energy distribution value and the energy contribution value are positively fused to obtain the time-frequency defect index, which comprehensively evaluates the possibility of pipeline damage, effectively fuses the time domain and frequency domain information, suppresses noise interference, highlights the defect characteristics, and improves the accuracy of non-metal pipeline damage detection.

[0062] Step S3: analyzing the discrete degree of all data of the composite ultrasonic signal in the time domain and the extreme distribution of all peak values in the frequency domain at each time, respectively, and combining the time-frequency defect index to evaluate the abnormal probability of the composite ultrasonic signal at each time; clustering the time-frequency defect indexes of all times within a preset time period before the current time to obtain a normal clustering cluster; determining the defect characteristic value of the composite ultrasonic signal at the current time by analyzing the difference between the time-frequency defect index of the composite ultrasonic signal at the current time and the clustering center of the normal clustering cluster, and combining the abnormal probability.

[0063] Due to the insufficient adaptability of the time-frequency defect index at a single time to complex working conditions such as temperature fluctuation and pipeline material difference, the risk of misjudgment is increased, for example, the time-frequency defect index values of normal vibration and slight defects overlap, or different pipe sections present similar time-frequency defect index values due to differences in installation conditions but have different actual states.

[0064] Thus, based on the above analysis, the abnormal probability of the composite ultrasonic signal at each time is evaluated by analyzing the discrete degree of all data of the composite ultrasonic signal in the time domain and the extreme distribution of all peak values in the frequency domain at each time, and combining the time-frequency defect index; the defect feature value of the composite ultrasonic signal at the current time is determined by analyzing the difference between the time-frequency defect index of the composite ultrasonic signal at the current time and the cluster center of the normal cluster, and combining the abnormal probability, and the specific process is as follows:

[0065] (1) In this embodiment, the discrete degree of all data of the composite ultrasonic signal in the time domain and the extreme distribution of all peak values in the frequency domain at each time are analyzed respectively, and the abnormal probability of the composite ultrasonic signal at each time is evaluated by combining the time-frequency defect index, specifically:

[0066] In this embodiment, the variance of all data of the composite ultrasonic signal in the time domain, the maximum peak value in the frequency domain, and the time-frequency defect index at each time are used as the input of the logistic regression algorithm, wherein the regularization coefficient C is set to 1.0 in this embodiment, the Sigmoid function is used for mapping, the time-frequency defect indexes of all times within a preset time period before the current time are randomly divided into a training set and a test set in a ratio of 7:3, the training set is used to fit the logistic regression model, and the test set is used to verify the generalization performance of the model, and the abnormal probability of the composite ultrasonic signal at each time is output.

[0067] It should be noted that the value of the length of the preset time period is artificially set, and the length of the preset time period is 0.1s in this embodiment. In actual application, as other implementation manners, the implementer can also set it himself according to the specific situation, and this embodiment does not make special limitations.

[0068] Among them, the Sigmoid function and the logistic regression algorithm are all known technologies, and the concept of the Sigmoid function and the specific process of evaluating the abnormal probability of the composite ultrasonic signal by using the logistic regression algorithm will not be repeated.

[0069] Preferably, the abnormal probability extraction process schematic diagram provided by the embodiment is as shown in Figure 2 .

[0070] (2) Further, the time-frequency defect indexes of all times within a preset time period before the current time are clustered in this embodiment to obtain a normal cluster, specifically:

[0071] In this embodiment, the time-frequency defect indexes of all times within a preset time period before the current time are used as the input of the clustering algorithm, wherein the absolute value of the difference between the time-frequency defect indexes is used as the metric distance of the clustering algorithm, the number of clustering clusters is set to q, q clustering clusters are output, the mean of the time-frequency defect indexes of each clustering cluster is calculated, and the clustering cluster with the smallest mean of the video defect indexes is used as the normal clustering cluster.

[0072] It should be noted that there are many commonly used clustering algorithms, and in the embodiment, the k-means clustering algorithm is used to cluster the time-frequency defect index. In actual application, as an alternative, the implementer can use other clustering methods such as the DPC density peak clustering algorithm according to the specific circumstances. The selection of the clustering algorithm is not particularly limited in the embodiment.

[0073] The k-means clustering algorithm is a known technology, and the specific process of clustering the time-frequency defect index will not be described again.

[0074] It should be noted that the value of the number of clustering clusters q is artificially set, and in the embodiment, the value of the number of clustering clusters q is 2, and the implementer can set it according to the specific circumstances, and the embodiment does not make special limitations.

[0075] (3) Further, the embodiment determines the defect feature value of the composite ultrasonic signal at the current time by analyzing the difference between the time-frequency defect index of the composite ultrasonic signal at the current time and the cluster center of the normal clustering cluster, and combining the abnormal probability, specifically:

[0076] As an implementation, in the embodiment, the expression of the defect feature value of the composite ultrasonic signal at the current time is: In the formula, D represents the difference between the time-frequency defect index of the composite ultrasonic signal at the current time and the cluster center of the normal clustering cluster; P n represents the abnormal probability of the composite ultrasonic signal at time n in the preset time period before the current time; N represents the length of the preset time period; and norm() represents a normalization function.

[0077] It should be noted that there are many methods for measuring the difference between data, and in the embodiment, the absolute value of the difference between the time-frequency defect index of the composite ultrasonic signal at the current time and the cluster center of the normal clustering cluster is used as the difference between the time-frequency defect index of the composite ultrasonic signal at the current time and the cluster center of the normal clustering cluster. In actual application, as an alternative, the implementer can use other methods for measuring the difference between data such as the square or ratio of the difference according to the specific circumstances. The selection of the method for measuring the difference between data is not particularly limited in the embodiment.

[0078] According to the defect feature value of the composite ultrasonic signal at the current moment, it can be understood that the defect feature value reflects the possibility of defects existing in the heating pipeline. The greater the difference between the time-frequency defect index of the composite ultrasonic signal at the current moment and the cluster center of the normal cluster, the greater the difference between the energy distribution of the current composite ultrasonic signal and the historical normal state. At this time, the heating pipeline is more likely to have a breakage, and the greater the time-frequency defect index, the more similar the signal features corresponding to the composite ultrasonic signal and the historical defect sample, indicating that the heating pipeline at the current moment is more likely to have a defect, and the greater the final defect feature value.

[0079] On the contrary, the smaller the difference between the time-frequency defect index of the composite ultrasonic signal at the current moment and the cluster center of the normal cluster, the smaller the difference between the energy distribution of the current composite ultrasonic signal and the historical normal state. At this time, the possibility of defects existing in the heating pipeline is smaller, and the smaller the time-frequency defect index, the greater the difference between the signal features corresponding to the composite ultrasonic signal and the historical defect sample, indicating that the possibility of defects existing in the heating pipeline at the current moment is smaller, and the smaller the final defect feature value.

[0080] At this point, by comprehensively analyzing the time domain dispersion degree, the frequency domain peak extreme distribution and the time-frequency defect index of the composite ultrasonic signal at each moment, the abnormal probability is evaluated by using the logistic regression model. Further, the time-frequency defect index in the preset period before the current moment is clustered to determine the normal cluster. By calculating the difference between the time-frequency defect index at the current moment and the center of the normal cluster, and combining the abnormal probability, the defect feature value is obtained, which effectively overcomes the problem of insufficient adaptability of the single time-frequency defect index to complex working conditions. By introducing multi-dimensional feature analysis of time domain and frequency domain and historical data clustering comparison, the accuracy and reliability of the heating pipeline breakage detection are improved.

[0081] Step S4: Based on the defect feature value of the composite ultrasonic signal at the current moment, the ability of the intelligent sensor array to capture defect echo signals at the deep layer of the heating pipeline is adjusted.

[0082] Due to the significant difference in acoustic impedance characteristics between non-metallic pipeline materials and metal, and the multi-scattering effect of sound waves caused by the multi-layer wrapping structure of the heating pipeline, the traditional ultrasonic monitoring method has the problem of insufficient penetration of high-frequency ultrasonic waves in non-metallic pipelines, resulting in a sharp drop in the signal strength of small cracks, holes and other defects in the deep layer of thick-walled or large-diameter pipelines, and even being completely covered by background noise, which can cause serious missed detection of heating pipeline breakage.

[0083] Thus, the embodiment is based on the defect characteristic value B, and the numerical change of the defect characteristic value B is calculated in real time to dynamically adjust the hardware parameters and the signal processing strategy of the detection system, specifically including: in the embodiment, the preset threshold is 0.75, when the defect characteristic value B exceeds the preset threshold, the intelligent sensor array automatically switches to the low-frequency mode and adjusts the gain, to realize the dynamic optimization of the penetration depth and the signal sensitivity, specifically, the heating pipeline damage detection system based on the ultrasonic technology automatically triggers the intelligent sensor parameter adaptive mechanism, the intelligent sensor array automatically switches to the low-frequency band, such as 20 kHz-50 kHz, to capture the echo of the deep defects of the heating pipeline, and the gain value of the multi-channel signal acquisition module is increased to enhance the penetration depth of the ultrasonic wave in the non-metal pipeline, compensate the energy attenuation, and ensure the effective capture of the deep defect echo; on the contrary, when the defect characteristic value B is less than or equal to the preset threshold 0.75, the intelligent sensor array is not adjusted.

[0084] The value of the preset threshold is artificially set, and the implementer can also set it according to the specific situation, which is not specially limited in the embodiment.

[0085] So far, the embodiment acquires multi-source signals through the intelligent sensor array, extracts time domain and frequency domain features by using wavelet transform and principal component analysis, calculates the energy distribution value and the energy contribution value, and evaluates the damage probability in combination with the time-frequency defect index; further, the normal state model is established through clustering analysis, the defect characteristic value at the current time is calculated, and the intelligent sensor array parameters are dynamically adjusted to optimize the detection performance, effectively fusing multi-dimensional information, and improving the accuracy and reliability of the non-metal pipeline damage detection.

[0086] Based on the same inventive concept as the above method, the embodiment of the present application also provides a heating pipeline damage detection system based on ultrasonic technology, which comprises a memory, a processor and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the methods in the above heating pipeline damage detection method based on ultrasonic technology.

[0087] It should be noted that the above-mentioned embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. The above description is made for specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or may be advantageous.

[0088] Each embodiment in the specification is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

[0089] The above description is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting a breakage of a heating pipe based on ultrasonic technology, characterized by, The method comprises the following steps: In the heating pipeline, the composite ultrasonic signal in the preset time period before each time point is acquired by using the intelligent sensor array; The composite ultrasonic signal at each time point is taken as the input of wavelet transform, and the components at a preset number of scales are outputted; the energy mean of the components at each scale is calculated, and the accumulation of the energy mean of the components at the preset number of scales is taken as the energy distribution value of the composite ultrasonic signal at each time point; the composite ultrasonic signal at each time point is taken as the input of principal component analysis, and the variance contribution rate of all principal components is outputted; the sum of the first preset number of variance contribution rates in the descending order arrangement result is taken as the energy contribution value of the composite ultrasonic signal at each time point; and the result of the positive fusion of the energy distribution value and the energy contribution value of the composite ultrasonic signal at each time point is taken as the time-frequency defect index of the composite ultrasonic signal at each time point; The variance of all data of the composite ultrasonic signal at each moment in the time domain, the maximum peak value in the frequency domain, and the time-frequency defect index at each moment are taken as inputs of a logistic regression algorithm, and the abnormal probability of the composite ultrasonic signal at each moment is output; the time-frequency defect indexes at all moments within a preset time period before the current moment are clustered to obtain a normal clustering cluster; the defect feature value of the composite ultrasonic signal at the current moment is calculated, and the expression is: ; in the formula, represents the difference between the time-frequency defect index of the composite ultrasonic signal at the current moment and the cluster center of the normal clustering cluster; represents the abnormal probability of the composite ultrasonic signal at moment n within a preset time period before the current moment; N represents the length of the preset time period; and norm() represents a normalization function. Based on the defect characteristic value, the ability of the intelligent sensor array to capture the defect echo at the deep layer of the heating pipeline is adjusted.

2. The ultrasonic technology-based heating pipe breakage detection method according to claim 1, characterized by, The acquisition method of the composite ultrasonic signal is as follows: The signals of the heating pipeline at each time point and in the preset time period before the time point are collected by using the intelligent sensor array, and the signal-to-noise ratios of the signals are acquired; the product of the signal intensity normalization value of the frequency domain signal of each signal at each frequency and the signal-to-noise ratio is calculated; the products of the frequency domain signals of all kinds of signals at the same frequency are added, and taken as the signal intensity of the corresponding frequency of the frequency domain signal of the composite ultrasonic signal; the frequency domain signal of the composite ultrasonic signal is converted to the time domain, and the composite ultrasonic signal is obtained, wherein the signals include the low-frequency ultrasonic echo of the non-metal pipeline, the high-frequency ultrasonic echo of the metal pipeline, the environmental noise signal and the pipeline mechanical vibration signal.

3. The ultrasonic technology-based heating pipe breakage detection method according to claim 1, characterized by, The normal clustering cluster is the clustering cluster with the minimum mean of the time-frequency defect indexes in all clustering clusters obtained by clustering the time-frequency defect indexes of all time points in the preset period before the current time point.

4. The ultrasonic technology-based heating pipe breakage detection method according to claim 1, characterized by, The adjustment of the ability of the intelligent sensor array to capture the defect echo at the deep layer of the heating pipeline comprises: If the defect characteristic value of the composite ultrasonic signal at the current time point is greater than the preset threshold value, the intelligent sensor array is automatically adjusted to the low-frequency mode to capture the echo of the defect at the deep layer of the heating pipeline, otherwise, the intelligent sensor array is not adjusted.

5. A heating pipe breakage detection system based on ultrasonic technology, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor realizes the steps of the heating pipeline damage detection method based on the ultrasonic technology in claim 1-4 when executing the computer program.

Images