Multilayer material thickness detection system and method based on TM sensor, electronic equipment and storage medium

Abstract

The invention relates to the technical field of material thickness detection, and discloses a multilayer material thickness detection system and method based on a TM sensor, electronic equipment and a storage medium, and the system comprises an ultrasonic detection module which is internally provided with a transmitting unit and a receiving unit; the feature extraction module is configured to obtain the ultrasonic signals and perform feature extraction on the ultrasonic signals; the control module is electrically connected with the ultrasonic detection module and the feature extraction module, and the control module comprises an acquisition unit, an algorithm generation unit, an analysis unit, an adjustment unit and a storage unit; the acquisition unit is configured to acquire amplitude characteristic data, waveform characteristic data and spectrum characteristic data; and the algorithm generation unit is configured to generate a layered measurement algorithm by taking the amplitude characteristic data, the waveform characteristic data and the frequency spectrum characteristic data as input signals, and calculate the measurement thickness of each layer of material according to the layered measurement algorithm. The measurement algorithm can be automatically adjusted, and the accuracy and reliability of the measurement result are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of material thickness detection, and in particular to a multi-layer material thickness detection system, method, electronic device and storage medium based on a TM sensor. Background Art

[0002] In modern industrial production, thickness detection of multi-layer materials is an important quality control link. Multi-layer materials are widely used in aviation, automobiles, construction and other fields, and the uniformity and consistency of their thickness directly affect the performance and safety of the products. Traditional thickness detection methods mainly rely on manual measurement or mechanical measuring equipment, which are not only inefficient, but also easily affected by human factors, resulting in inaccurate measurement results.

[0003] With the development of science and technology, sensor-based thickness detection technology has gradually become mainstream. Among them, TM (Time-of-Fl ight Measurement) sensors have been widely used in the field of multi-layer material thickness detection due to their high precision, high efficiency and non-contact measurement characteristics. TM sensors calculate the thickness of materials by measuring the propagation time of ultrasonic waves in materials, with high measurement accuracy and repeatability.

[0004] However, the existing TM sensor-based thickness detection system still has some problems in practical applications. For example, environmental factors such as changes in temperature, humidity and pressure will affect the propagation speed of ultrasound, thereby affecting the accuracy of the measurement results. In addition, the density inhomogeneity inside the multi-layer material will also affect the thickness measurement. Therefore, how to achieve high-precision multi-layer material thickness detection under the condition of environmental factors and material density changes has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, the present invention proposes a multi-layer material thickness detection system, method, electronic device and storage medium based on a TM sensor, aiming to solve the problem of low accuracy of measurement results for multi-layer materials in current technology.

[0006] In one aspect, the present invention provides a multi-layer material thickness detection system based on a TM sensor, comprising:

[0007] The ultrasonic detection module is provided with a transmitting unit and a receiving unit inside, wherein the transmitting unit is used to transmit ultrasonic waves into the multi-layer material, and the receiving unit is used to receive the echo of the ultrasonic waves transmitted by the transmitting unit on each layer of material to form an ultrasonic signal;

[0008] A feature extraction module is configured to obtain the ultrasonic signal and perform feature extraction on the ultrasonic signal to obtain amplitude feature data, waveform feature data and spectrum feature data of the ultrasonic signal corresponding to each layer of material;

[0009] A control module, electrically connected to the ultrasonic detection module and the feature extraction module, the control module comprising an acquisition unit, an algorithm generation unit, an analysis unit, an adjustment unit and a storage unit;

[0010] The acquisition unit is configured to acquire the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data;

[0011] The algorithm generating unit is configured to generate a layered measurement algorithm using the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data as input signals, and calculate the measured thickness of each layer of material according to the layered measurement algorithm;

[0012] The analysis unit is configured to compare the measured thickness with a standard thickness value, and determine whether to adjust the layer measurement algorithm according to the comparison result:

[0013] When it is determined that the layered measurement algorithm is to be adjusted, the analysis unit controls the acquisition unit to acquire first environmental data of the external environment and second environmental data inside the multilayer material, and establishes an environmental data set according to the first environmental data and the second environmental data, calculates an environmental impact index according to the environmental data set, compares the environmental impact index with historical data, and adjusts the layered measurement algorithm according to the comparison result;

[0014] The adjustment unit is configured to control the acquisition unit to acquire density data corresponding to each layer of material when the environmental impact index is different from the historical data, and calculate a comprehensive compensation coefficient according to the density data, the first environmental data and the second environmental data, and adjust the layered measurement algorithm;

[0015] The storage unit is configured to store the comprehensive compensation coefficient.

[0016] Furthermore, when obtaining the amplitude characteristic data, waveform characteristic data and spectrum characteristic data of the ultrasonic signal corresponding to each layer of material, it includes:

[0017] The amplitude characteristic data is the maximum amplitude of the ultrasonic signal measured for each layer of material;

[0018] The waveform characteristic data is the rising edge time and falling edge time of the ultrasonic signal measured for each layer of material;

[0019] The frequency spectrum characteristic data is the frequency distribution of the ultrasonic signal measured for each layer of material.

[0020] Furthermore, when the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data are used as input signals to generate a hierarchical measurement algorithm, it includes:

[0021] Performing data cleaning on the amplitude characteristic data, waveform characteristic data and spectrum characteristic data to remove noise in the ultrasonic signal, and using wavelet transform to eliminate interference signals;

[0022] Normalizing the amplitude characteristic data, waveform characteristic data, and spectrum characteristic data to obtain normalized amplitude characteristic data, normalized waveform characteristic data, and normalized spectrum characteristic data;

[0023] The normalized amplitude feature data, the normalized waveform feature data and the normalized spectrum feature data are fused to obtain fused feature data;

[0024] The fused feature data is used as input data, and a machine learning algorithm is used to train the fused feature data to generate the hierarchical measurement algorithm.

[0025] Furthermore, the measured thickness is compared with a standard thickness value, and judging whether to adjust the layered measurement algorithm according to the comparison result includes:

[0026] Subtracting the measured thickness from the standard thickness to obtain a thickness difference;

[0027] Comparing the thickness difference with a thickness difference threshold, and determining whether to adjust the layer measurement algorithm according to the comparison result;

[0028] When the thickness difference is less than or equal to the thickness difference threshold, the analysis unit determines not to adjust the layer measurement algorithm;

[0029] When the thickness difference is greater than the thickness difference threshold, the analyzing unit determines to adjust the layer measurement algorithm.

[0030] Further, when it is determined that the layered measurement algorithm is to be adjusted, the analysis unit controls the acquisition unit to acquire first environmental data of the external environment and second environmental data inside the multilayer material, and establishes an environmental data set according to the first environmental data and the second environmental data, and calculates the environmental impact index according to the environmental data set, including:

[0031] The first environmental data includes external environmental temperature, external environmental humidity and external environmental pressure;

[0032] The second environmental data includes the temperature inside the material, the humidity inside the material and the pressure inside the material;

[0033] The environmental impact index is obtained by the following formula:

[0034]

[0035] Among them, C represents the environmental impact index, k represents the weight coefficient, Te represents the external environment temperature, Ti represents the internal temperature of the material, Tr represents the reference temperature, He represents the external environment humidity, Hi represents the internal humidity of the material, Hr represents the reference humidity, Pe represents the external environment pressure, Pi represents the internal pressure of the material, Pr represents the reference pressure, t represents the time variable, t0 and t1 respectively represent the start time and end time of the ultrasonic signal acquisition.

[0036] Furthermore, the environmental impact index is compared with historical data, and the hierarchical measurement algorithm is adjusted according to the comparison result, including:

[0037] When there is a historical environmental impact index identical to the environmental impact index in the historical data, adjusting the hierarchical measurement algorithm with a historical compensation coefficient corresponding to the historical environmental impact index;

[0038] When there is no historical environmental impact index corresponding to the environmental impact index in the historical data, the environmental impact index is stored.

[0039] Further, when calculating the comprehensive compensation coefficient according to the density data, the first environment data and the second environment data and adjusting the layered measurement algorithm, it includes:

[0040] Subtract the density value corresponding to the density data of each layer of material from the density standard value corresponding to each layer of material to obtain the density difference value;

[0041] Compare the density difference with a first density difference threshold and a second density difference threshold, and determine whether there is a density anomaly in the current layer material and the type of anomaly according to the comparison result; wherein the first density difference threshold is less than 0 and the second density difference threshold is greater than 0;

[0042] When the density difference is less than or equal to the first density difference threshold, it is determined that the current layer of material has a density anomaly, and the anomaly type is material damage;

[0043] When the density difference is greater than a first density difference threshold and less than or equal to a second density difference threshold, it is determined that there is no density anomaly in the current layer of material;

[0044] When the density difference is greater than a second density difference threshold, it is determined that a density anomaly exists in the current layer of material, and the anomaly type is material surface contamination.

[0045] Further, when determining whether the current layer of material has no density anomaly according to the comparison result, it includes:

[0046] The comprehensive compensation coefficient is calculated according to the density data, the first environment data and the second environment data, and the comprehensive compensation coefficient is obtained by the following formula:

[0047]

[0048] Wherein, Zi represents the comprehensive compensation coefficient of the current layer material, α and β represent weight coefficients, D represents the normalized value of the density difference, Te represents the normalized value of the external environment temperature, He represents the normalized value of the external environment humidity, Pe represents the normalized value of the external environment pressure, Ti represents the normalized value of the internal temperature of the material, Hi represents the normalized value of the internal humidity of the material, Pi represents the normalized value of the internal pressure of the material, and ρi represents the normalized value of the density of the current layer material;

[0049] The layered measurement algorithm is adjusted using the comprehensive compensation coefficient, and the comprehensive compensation coefficient is stored in the storage unit.

[0050] Compared with the prior art, the beneficial effect of the present invention is that the multilayer material thickness detection system based on TM sensor provided by the present invention is suitable for multilayer material thickness measurement in various complex environments. By real-time acquisition and analysis of external environment data and material internal data, the system can automatically adjust the measurement algorithm to ensure the accuracy and reliability of the measurement results. The ultrasonic detection module of the present invention is used to transmit and receive ultrasonic signals; the feature extraction module is used to extract key information from these signals for subsequent analysis and processing; the control module is used to coordinate the work of each module and perform operations such as algorithm generation, analysis, adjustment and storage; the algorithm generation unit can dynamically adjust the parameters of the layered measurement algorithm according to different material properties and detection environments to adapt to various detection scenarios; the analysis unit can predict the change trend of material thickness according to historical data and real-time data in addition to thickness comparison and environmental impact index calculation; the adjustment unit can select appropriate compensation models and algorithms according to different material types and thickness ranges when adjusting the layered measurement algorithm to ensure the accuracy of the measurement results; the storage unit can record the data and results of each detection in addition to storing the comprehensive compensation coefficient, which is convenient for subsequent data analysis and quality control.

[0051] In another aspect, the present invention also proposes a method for detecting the thickness of a multilayer material based on a TM sensor, the method comprising:

[0052] S100: transmitting ultrasonic waves into the multilayer material, and receiving echoes of the ultrasonic waves on each layer of the material to form ultrasonic signals; acquiring the ultrasonic signals, and performing feature extraction on the ultrasonic signals to obtain amplitude feature data, waveform feature data, and spectrum feature data of the ultrasonic signals corresponding to each layer of the material;

[0053] S200: collecting the amplitude characteristic data, waveform characteristic data and spectrum characteristic data; generating a layered measurement algorithm using the amplitude characteristic data, waveform characteristic data and spectrum characteristic data as input signals, and calculating the measured thickness of each layer of material according to the layered measurement algorithm;

[0054] S300: comparing the measured thickness with a standard thickness value, and judging whether to adjust the layered measurement algorithm according to the comparison result: when it is determined that the layered measurement algorithm is to be adjusted, collecting first environmental data of an external environment and second environmental data inside the multilayer material, and establishing an environmental data set according to the first environmental data and the second environmental data, calculating an environmental impact index according to the environmental data set, comparing the environmental impact index with historical data, and adjusting the layered measurement algorithm according to the comparison result;

[0055] S400: When the environmental impact index is different from the historical data, density data corresponding to each layer of material is collected, and a comprehensive compensation coefficient is calculated according to the density data, the first environmental data and the second environmental data, and the layered measurement algorithm is adjusted;

[0056] S500: Storing the comprehensive compensation coefficient.

[0057] It is understandable that the above-mentioned multi-layer material thickness detection method and system based on TM sensor have the same beneficial effects, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0059] Figure 1 A flow chart of a multi-layer material thickness detection method based on a TM sensor provided in an embodiment of the present invention;

[0060] Figure 2 A structural block diagram of a multi-layer material thickness detection system based on a TM sensor provided in an embodiment of the present invention;

[0061] Figure 3It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0063] See also Figure 1 As shown, in some embodiments of the present application, this embodiment provides a multi-layer material thickness detection system based on a TM sensor, comprising:

[0064] The ultrasonic detection module is provided with a transmitting unit and a receiving unit inside, wherein the transmitting unit is used to transmit ultrasonic waves into the multi-layer material, and the receiving unit is used to receive the echo of the ultrasonic waves transmitted by the transmitting unit on each layer of material to form an ultrasonic signal;

[0065] A feature extraction module is configured to obtain the ultrasonic signal and perform feature extraction on the ultrasonic signal to obtain amplitude feature data, waveform feature data and spectrum feature data of the ultrasonic signal corresponding to each layer of material;

[0066] A control module, electrically connected to the ultrasonic detection module and the feature extraction module, the control module comprising an acquisition unit, an algorithm generation unit, an analysis unit, an adjustment unit and a storage unit;

[0067] The acquisition unit is configured to acquire the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data;

[0068] The algorithm generating unit is configured to generate a layered measurement algorithm using the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data as input signals, and calculate the measured thickness of each layer of material according to the layered measurement algorithm;

[0069] The analysis unit is configured to compare the measured thickness with a standard thickness value, and determine whether to adjust the layer measurement algorithm according to the comparison result:

[0070] When it is determined that the layered measurement algorithm is to be adjusted, the analysis unit controls the acquisition unit to acquire first environmental data of the external environment and second environmental data inside the multilayer material, and establishes an environmental data set according to the first environmental data and the second environmental data, calculates an environmental impact index according to the environmental data set, compares the environmental impact index with historical data, and adjusts the layered measurement algorithm according to the comparison result;

[0071] The adjustment unit is configured to control the acquisition unit to acquire density data corresponding to each layer of material when the environmental impact index is different from the historical data, and calculate a comprehensive compensation coefficient according to the density data, the first environmental data and the second environmental data, and adjust the layered measurement algorithm;

[0072] The storage unit is configured to store the comprehensive compensation coefficient.

[0073] In some embodiments of the present invention, a TM (Time-of-Fl ight Measurement) sensor is a sensor based on time-of-flight measurement, which can accurately measure the propagation time of ultrasound in different media and obtain the thickness information of each layer of material by calculating the propagation time of ultrasound in each layer of material.

[0074] It can be understood that the ultrasonic detection module is used to transmit and receive ultrasonic signals; the feature extraction module is used to extract key information from these signals for subsequent analysis and processing; the control module is used to coordinate the work of each module and perform operations such as algorithm generation, analysis, adjustment and storage; the algorithm generation unit can dynamically adjust the parameters of the layered measurement algorithm according to different material properties and detection environments to adapt to various detection scenarios; in addition to thickness comparison and environmental impact index calculation, the analysis unit can also predict the change trend of material thickness based on historical data and real-time data; the adjustment unit adjusts the layered measurement algorithm to ensure the accuracy of the measurement results; in addition to storing the comprehensive compensation coefficient, the storage unit can also record the data and results of each detection to facilitate subsequent data analysis and quality control.

[0075] In some embodiments of the present invention, the historical data includes historical external environment temperature, historical external environment humidity, historical external environment pressure, historical material internal temperature, historical material internal humidity and historical material internal pressure.

[0076] It is understandable that the multi-layer material thickness detection system based on the TM sensor of the present invention can provide a high-precision and high-stability detection method, which is suitable for measuring the thickness of multi-layer materials in a variety of complex environments. By real-time acquisition and analysis of external environmental data and internal material data, the system can automatically adjust the measurement algorithm to ensure the accuracy and reliability of the measurement results.

[0077] Specifically, when obtaining the amplitude characteristic data, waveform characteristic data and spectrum characteristic data of the ultrasonic signal corresponding to each layer of material, it includes:

[0078] The amplitude characteristic data is the maximum amplitude of the ultrasonic signal measured for each layer of material;

[0079] The waveform characteristic data is the rising edge time and falling edge time of the ultrasonic signal measured for each layer of material;

[0080] The frequency spectrum characteristic data is the frequency distribution of the ultrasonic signal measured for each layer of material.

[0081] In some embodiments of the present invention, the maximum amplitude of the ultrasonic signal of each layer of material is obtained by measurement, and the rising edge time and falling edge time reflect the propagation speed and attenuation of the ultrasonic signal in each layer of material. The frequency distribution reveals the structural characteristics inside the material, and the spectrum characteristic data specifically includes the main frequency, frequency bandwidth, spectrum centroid, spectrum entropy, spectrum roll-off point and harmonic components. The main frequency is the frequency component with the strongest energy in the ultrasonic signal, the frequency bandwidth is the range of signal energy distribution in the ultrasonic signal, the spectrum centroid is the center position of the signal frequency in the ultrasonic signal, the spectrum entropy is the complexity of the signal frequency distribution in the ultrasonic signal, the spectrum roll-off point is the frequency point where the signal energy in the ultrasonic signal drops to a certain value, and the harmonic component is whether there are other integer multiple frequency components other than the fundamental frequency inside the multilayer material.

[0082] Specifically, when the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data are used as input signals to generate a hierarchical measurement algorithm, it includes:

[0083] Performing data cleaning on the amplitude characteristic data, waveform characteristic data and spectrum characteristic data to remove noise in the ultrasonic signal, and using wavelet transform to eliminate interference signals;

[0084] Normalizing the amplitude characteristic data, waveform characteristic data, and spectrum characteristic data to obtain normalized amplitude characteristic data, normalized waveform characteristic data, and normalized spectrum characteristic data;

[0085] The normalized amplitude feature data, the normalized waveform feature data and the normalized spectrum feature data are fused to obtain fused feature data;

[0086] The fused feature data is used as input data, and a machine learning algorithm is used to train the fused feature data to generate the hierarchical measurement algorithm.

[0087] In some embodiments of the present invention, machine learning algorithms include support vector machines, random forests, neural networks, and gradient boosting decision trees. Through the training of these algorithms, the characteristics of different material layers can be effectively identified and classified, thereby improving measurement accuracy and reliability.

[0088] In some embodiments of the present invention, the fused feature data is used as input data, and a machine learning algorithm is used to train the fused feature data to generate the hierarchical measurement algorithm, including:

[0089] First, feature selection is performed on the fused feature data to determine the feature subset that has the greatest impact on the stratified measurement results. This step can be achieved through recursive feature elimination or model-based feature selection methods. Feature selection can reduce the complexity of the model, increase the training speed, and avoid overfitting.

[0090] Next, the cross-validation technique is used to optimize the parameters of the machine learning algorithm.

[0091] Then, the optimized machine learning algorithm is applied to the fused feature data for model training. During the training process, different optimization algorithms, such as gradient descent, Newton method or quasi-Newton method, can be used to accelerate the convergence of the model. After the training is completed, the generated hierarchical measurement algorithm is tested and verified.

[0092] Finally, the verified layered measurement algorithm is integrated into the multi-layer material thickness detection system. The system will automatically call the corresponding layered measurement algorithm based on the real-time collected external environment data and material internal data to achieve high-precision and high-stability thickness measurement.

[0093] It can be understood that using the fused feature data as input data, training the machine learning algorithm using the fused feature data, and generating a layered measurement algorithm can better adapt to complex and changeable detection environments and material properties.

[0094] Specifically, comparing the measured thickness with the standard thickness value and determining whether to adjust the layered measurement algorithm according to the comparison result includes:

[0095] Subtracting the measured thickness from the standard thickness to obtain a thickness difference;

[0096] Comparing the thickness difference with a thickness difference threshold, and determining whether to adjust the layer measurement algorithm according to the comparison result;

[0097] When the thickness difference is less than or equal to the thickness difference threshold, the analysis unit determines not to adjust the layer measurement algorithm;

[0098] When the thickness difference is greater than the thickness difference threshold, the analyzing unit determines to adjust the layer measurement algorithm.

[0099] In some embodiments of the present invention, the standard thickness is obtained by a known calibration sample or a standard value certified by an authoritative organization.

[0100] In some embodiments of the present invention, the thickness difference threshold is pre-set according to the actual application scenario and precision requirements. For example, in the case of high precision requirements, the thickness difference threshold is set to 0.1 mm, and in the case of relatively low precision requirements, the thickness difference threshold is set to 0.5 mm.

[0101] It can be understood that by setting a reasonable thickness difference threshold, the accuracy and reliability of the measurement results can be ensured, while avoiding frequent adjustments to the layered measurement algorithm, thereby improving the stability and efficiency of the system.

[0102] Specifically, when it is determined that the layered measurement algorithm is to be adjusted, the analysis unit controls the acquisition unit to acquire first environmental data of the external environment and second environmental data inside the multilayer material, and establishes an environmental data set according to the first environmental data and the second environmental data, and calculates the environmental impact index according to the environmental data set, including:

[0103] The first environmental data includes external environmental temperature, external environmental humidity and external environmental pressure;

[0104] The second environmental data includes the temperature inside the material, the humidity inside the material and the pressure inside the material;

[0105] The environmental impact index is obtained by the following formula:

[0106]

[0107] Among them, C represents the environmental impact index, k represents the weight coefficient, Te represents the external environment temperature, Ti represents the internal temperature of the material, Tr represents the reference temperature, He represents the external environment humidity, Hi represents the internal humidity of the material, Hr represents the reference humidity, Pe represents the external environment pressure, Pi represents the internal pressure of the material, Pr represents the reference pressure, t represents the time variable, t0 and t1 respectively represent the start time and end time of the ultrasonic signal acquisition.

[0108] In some embodiments of the present invention, the weight coefficient k is pre-set according to the actual measurement environment and material properties to ensure that the environmental impact index C can accurately reflect the impact of environmental changes on the propagation characteristics of ultrasonic signals. For example, in an environment with large temperature changes, the k value needs to be set higher to ensure that the temperature factor is given enough attention; while in an environment with large humidity or pressure changes, the k value needs to be adjusted accordingly.

[0109] It is understandable that the reference temperature, reference humidity and reference pressure are the reference values ​​for calibrating the environmental impact index C to ensure the accuracy and reliability of the calculation of the environmental impact index C. In practical applications, the reference temperature, reference humidity and reference pressure can be set according to the specific measurement environment and material properties to meet different detection needs. For example, in an environment with small temperature fluctuations, the reference temperature can be set to the average value of the ambient temperature; while in an environment with large humidity changes, the reference humidity needs to be reasonably set according to the hygroscopicity of the material and the change in ambient humidity. By reasonably setting the reference temperature, reference humidity and reference pressure, the measurement accuracy and stability of the multi-layer material thickness detection system can be further improved.

[0110] It can be understood that the combined impact of external environmental temperature and humidity, external environmental pressure, material internal temperature and humidity, and material internal pressure on the propagation characteristics of ultrasonic signals can be quantified by calculating the environmental impact index C. The calculation of this index helps the system to more accurately determine when the layered measurement algorithm needs to be adjusted, as well as the degree and direction of the adjustment.

[0111] Specifically, the environmental impact index is compared with historical data, and the hierarchical measurement algorithm is adjusted according to the comparison result, including:

[0112] When there is a historical environmental impact index identical to the environmental impact index in the historical data, adjusting the hierarchical measurement algorithm with a historical compensation coefficient corresponding to the historical environmental impact index;

[0113] When there is no historical environmental impact index identical to the environmental impact index in the historical data, the environmental impact index is stored.

[0114] In some embodiments of the present invention, historical data is stored in a database, which is connected to an analysis unit. The analysis unit periodically analyzes the historical data in the database to identify trends and patterns in environmental changes. Through this analysis, the impact of future environmental changes on the measurement algorithm can be predicted and adjusted in advance, thereby further improving the prediction ability and response speed of the measurement system.

[0115] In some embodiments of the present invention, the historical compensation coefficient is calculated based on historical measurement data, environmental factors and material properties, and is used to compensate for the impact of environmental changes on measurement results. The historical compensation coefficient can also be a comprehensive compensation coefficient corresponding to an environmental impact index, and the comprehensive compensation coefficient is the same as the first environmental data and the second environmental data corresponding to the environmental impact index, or the environmental impact index is used as the historical compensation coefficient to adjust the hierarchical measurement algorithm.

[0116] Specifically, when calculating the comprehensive compensation coefficient according to the density data, the first environment data and the second environment data and adjusting the layered measurement algorithm, it includes:

[0117] Subtract the density value corresponding to the density data of each layer of material from the density standard value corresponding to each layer of material to obtain the density difference value;

[0118] Compare the density difference with a first density difference threshold and a second density difference threshold, and determine whether there is a density anomaly in the current layer material and the type of anomaly according to the comparison result; wherein the first density difference threshold is less than 0 and the second density difference threshold is greater than 0;

[0119] When the density difference is less than or equal to the first density difference threshold, it is determined that the current layer of material has a density anomaly, and the anomaly type is material damage;

[0120] When the density difference is greater than a first density difference threshold and less than or equal to a second density difference threshold, it is determined that there is no density anomaly in the current layer of material;

[0121] When the density difference is greater than a second density difference threshold, it is determined that a density anomaly exists in the current layer of material, and the anomaly type is material surface contamination.

[0122] In some embodiments of the present invention, the density difference threshold is pre-set according to the actual application scenario and accuracy requirements. For example, in the case of high requirements for material damage detection, the first density difference threshold is set to -0.05 g / cm3 and the second density difference threshold is set to 0.1 g / cm3; and in the case of high requirements for material surface contamination detection, the first density difference threshold is set to -0.03 g / cm3 and the second density difference threshold is set to 0.08 g / cm3.

[0123] It can be understood that by setting a reasonable density difference threshold, it is possible to ensure accurate judgment of material density anomalies, so that corresponding maintenance measures can be taken in time to improve the quality and life of the material. When it is determined that the current layer of material has a density anomaly, the analysis unit will adjust the layered measurement algorithm according to the type of anomaly to ensure the accuracy of the measurement results. The specific adjustment method is: when it is determined that the material is damaged, the amplitude characteristic data of the ultrasonic signal is corrected to compensate for the impact of damage on the signal propagation characteristics; when it is determined that the material surface is contaminated, the ultrasonic waveform characteristic data is corrected to compensate for the impact of contamination on the signal propagation speed and attenuation; through the above adjustments, the layered measurement algorithm can adapt to the measurement requirements under different density anomalies, thereby improving the adaptability and robustness of the measurement system.

[0124] Specifically, when it is determined according to the comparison results that the current layer material has density anomaly, it includes:

[0125] If the abnormal type of the current layer material is material damage, analyze the size and position of the damaged area and correct the measurement results according to the degree of damage;

[0126] If the abnormal type of the current layer of material is material surface contamination, remove the contaminants on the material surface and then perform ultrasonic testing again.

[0127] In some embodiments of the present invention, when correcting the measurement results according to the degree of damage, it includes: first, determining the boundary of the damaged area through the waveform characteristic data of the ultrasonic signal, and then calculating the corresponding correction coefficient according to the ratio of the area of ​​the damaged area to the area of ​​the entire measurement area. Next, the correction coefficient is applied to the amplitude characteristic data of the ultrasonic signal to correct the influence of the damage on the signal propagation characteristics. In this way, it can be ensured that the measurement results more accurately reflect the actual state of the material. After removing the contaminants on the surface of the material, when ultrasonic testing is performed again, the analysis unit will guide the acquisition unit to collect ultrasonic signals for the same layer of material multiple times to ensure the stability and reliability of the test results. By collecting multiple times and taking the average value, the influence of random errors can be effectively reduced and the measurement accuracy can be improved.

[0128] It can be understood that by accurately analyzing the size and position of the damaged area, the interference of the damaged area on the thickness detection can be eliminated in the ultrasonic signal processing, avoiding the erroneous measurement results caused by material damage, and ensuring that the final thickness measurement data is closer to the actual situation of the material; during the detection process, material damage will cause abnormal reflection and attenuation of the ultrasonic signal, thereby affecting the thickness measurement. Correcting the damaged area can effectively reduce the measurement error caused by the damage and ensure the reliability of the thickness measurement results.

[0129] Specifically, when determining whether the current layer of material has no density anomaly based on the comparison result, it includes:

[0130] The comprehensive compensation coefficient is calculated according to the density data, the first environment data and the second environment data, and the comprehensive compensation coefficient is obtained by the following formula:

[0131]

[0132] Wherein, Zi represents the comprehensive compensation coefficient of the current layer material, α and β represent weight coefficients, D represents the normalized value of the density difference, Te represents the normalized value of the external environment temperature, He represents the normalized value of the external environment humidity, Pe represents the normalized value of the external environment pressure, Ti represents the normalized value of the internal temperature of the material, Hi represents the normalized value of the internal humidity of the material, Pi represents the normalized value of the internal pressure of the material, and ρi represents the normalized value of the density of the current layer material;

[0133] The layered measurement algorithm is adjusted using the comprehensive compensation coefficient, and the comprehensive compensation coefficient is stored in the storage unit.

[0134] In some embodiments of the present invention, each layer of material has a different density compensation coefficient corresponding to the density thereof, thereby ensuring that the measurement system has higher accuracy and consistency between different material layers.

[0135] In some embodiments of the present invention, after obtaining the comprehensive compensation coefficient, the layered measurement algorithm needs to be adjusted to adapt to the measurement requirements under different environmental conditions. The specific adjustment method includes: adjusting the amplitude characteristic data of the ultrasonic signal according to the comprehensive compensation coefficient to compensate for the influence of environmental parameters on the signal propagation characteristics; adjusting the ultrasonic waveform characteristic data according to the comprehensive compensation coefficient to compensate for the influence of environmental parameters on the signal propagation speed and attenuation; adjusting the acquisition frequency and sampling time of the ultrasonic signal according to the comprehensive compensation coefficient to adapt to the signal acquisition requirements under different environmental conditions. Through the above adjustments, the layered measurement algorithm can maintain high measurement accuracy and stability under different environmental conditions. In addition, the model can be further optimized and improved according to the needs of actual application scenarios to improve the adaptability and robustness of the measurement system.

[0136] See also Figure 2 As shown, in some embodiments of the present application, this embodiment provides a multi-layer material thickness detection method based on a TM sensor, comprising the following steps:

[0137] S100: transmitting ultrasonic waves into the multilayer material, and receiving echoes of the ultrasonic waves on each layer of the material to form ultrasonic signals; acquiring the ultrasonic signals, and performing feature extraction on the ultrasonic signals to obtain amplitude feature data, waveform feature data, and spectrum feature data of the ultrasonic signals corresponding to each layer of the material;

[0138] S200: collecting the amplitude characteristic data, waveform characteristic data and spectrum characteristic data; generating a layered measurement algorithm using the amplitude characteristic data, waveform characteristic data and spectrum characteristic data as input signals, and calculating the measured thickness of each layer of material according to the layered measurement algorithm;

[0139] S300: comparing the measured thickness with a standard thickness value, and judging whether to adjust the layered measurement algorithm according to the comparison result: when it is determined that the layered measurement algorithm is to be adjusted, collecting first environmental data of an external environment and second environmental data inside the multilayer material, and establishing an environmental data set according to the first environmental data and the second environmental data, calculating an environmental impact index according to the environmental data set, comparing the environmental impact index with historical data, and adjusting the layered measurement algorithm according to the comparison result;

[0140] S400: When the environmental impact index is different from the historical data, density data corresponding to each layer of material is collected, and a comprehensive compensation coefficient is calculated according to the density data, the first environmental data and the second environmental data, and the layered measurement algorithm is adjusted;

[0141] S500: Storing the comprehensive compensation coefficient.

[0142] It is understandable that the multi-layer material thickness detection method based on TM sensor has high flexibility and adaptability, and can cope with a variety of complex detection environments and material characteristics. By adopting TM sensor, accurate measurement of multi-layer material thickness can be achieved to ensure the reliability of product quality and performance. TM sensor has high sensitivity and stability, and can capture small thickness changes, thereby providing more accurate measurement data.

[0143] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 3 As shown, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of processors 410 in the device can be one or more. Figure 3 A processor 410 is taken as an example; the processor 410, memory 420, input device 430 and output device 440 in the device can be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0144] The memory 420 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to a multi-layer material thickness detection method based on a TM sensor in an embodiment of the present invention. The processor 410 executes various functional applications and data processing of the device by running the software programs, instructions and modules stored in the memory 420.

[0145] The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 420 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 420 may further include a memory remotely arranged relative to the processor 410, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0146] The input device 430 may be used to receive input digital or character information and generate signal input related to user settings and function control of the device. The output device 440 may include a display device such as a display screen.

[0147] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0148] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-layer material thickness detection system based on TM sensor, characterized in that: include: The ultrasonic detection module is provided with a transmitting unit and a receiving unit inside, wherein the transmitting unit is used to transmit ultrasonic waves into the multi-layer material, and the receiving unit is used to receive the echo of the ultrasonic waves transmitted by the transmitting unit on each layer of material to form an ultrasonic signal; A feature extraction module is configured to obtain the ultrasonic signal and perform feature extraction on the ultrasonic signal to obtain amplitude feature data, waveform feature data and spectrum feature data of the ultrasonic signal corresponding to each layer of material; A control module, electrically connected to the ultrasonic detection module and the feature extraction module, the control module comprising an acquisition unit, an algorithm generation unit, an analysis unit, an adjustment unit and a storage unit; The acquisition unit is configured to acquire the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data; The algorithm generating unit is configured to generate a layered measurement algorithm using the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data as input signals, and calculate the measured thickness of each layer of material according to the layered measurement algorithm; The analysis unit is configured to compare the measured thickness with a standard thickness value, and determine whether to adjust the layer measurement algorithm according to the comparison result: When it is determined that the layered measurement algorithm is to be adjusted, the analysis unit controls the acquisition unit to acquire first environmental data of the external environment and second environmental data inside the multilayer material, and establishes an environmental data set according to the first environmental data and the second environmental data, calculates an environmental impact index according to the environmental data set, compares the environmental impact index with historical data, and adjusts the layered measurement algorithm according to the comparison result; The adjustment unit is configured to control the acquisition unit to acquire density data corresponding to each layer of material when the environmental impact index is different from the historical data, and calculate a comprehensive compensation coefficient according to the density data, the first environmental data and the second environmental data, and adjust the layered measurement algorithm; The storage unit is configured to store the comprehensive compensation coefficient.

2. The multi-layer material thickness detection system based on TM sensor according to claim 1 is characterized in that: When obtaining the amplitude characteristic data, waveform characteristic data and spectrum characteristic data of the ultrasonic signal corresponding to each layer of material, it includes: The amplitude characteristic data is the maximum amplitude of the ultrasonic signal measured for each layer of material; The waveform characteristic data is the rising edge time and falling edge time of the ultrasonic signal measured for each layer of material; The frequency spectrum characteristic data is the frequency distribution of the ultrasonic signal measured for each layer of material.

3. The multi-layer material thickness detection system based on TM sensor according to claim 2 is characterized in that: When the amplitude characteristic data, the waveform characteristic data and the spectrum characteristic data are used as input signals to generate a hierarchical measurement algorithm, the method includes: Performing data cleaning on the amplitude characteristic data, waveform characteristic data and spectrum characteristic data to remove noise in the ultrasonic signal, and using wavelet transform to eliminate interference signals; Normalizing the amplitude characteristic data, waveform characteristic data, and spectrum characteristic data to obtain normalized amplitude characteristic data, normalized waveform characteristic data, and normalized spectrum characteristic data; The normalized amplitude characteristic data, the normalized waveform characteristic data and the normalized spectrum characteristic data are fused to obtain fused characteristic data; The fused feature data is used as input data, and a machine learning algorithm is used to train the fused feature data to generate the hierarchical measurement algorithm.

4. The multi-layer material thickness detection system based on TM sensor according to claim 3 is characterized in that: The measured thickness is compared with the standard thickness value, and judging whether to adjust the layer measurement algorithm according to the comparison result includes: Subtracting the measured thickness from the standard thickness to obtain a thickness difference; Comparing the thickness difference with a thickness difference threshold, and determining whether to adjust the layer measurement algorithm according to the comparison result; When the thickness difference is less than or equal to the thickness difference threshold, the analysis unit determines not to adjust the layer measurement algorithm; When the thickness difference is greater than the thickness difference threshold, the analyzing unit determines to adjust the layer measurement algorithm.

5. The multi-layer material thickness detection system based on TM sensor according to claim 4 is characterized in that: When it is determined that the layered measurement algorithm is to be adjusted, the analysis unit controls the acquisition unit to acquire first environmental data of the external environment and second environmental data inside the multilayer material, and establishes an environmental data set according to the first environmental data and the second environmental data, and calculates the environmental impact index according to the environmental data set, including: The first environmental data includes external environmental temperature, external environmental humidity and external environmental pressure; The second environmental data includes the temperature inside the material, the humidity inside the material and the pressure inside the material; The environmental impact index is obtained by the following formula: Among them, C represents the environmental impact index, k represents the weight coefficient, Te represents the external environment temperature, Ti represents the internal temperature of the material, Tr represents the reference temperature, He represents the external environment humidity, Hi represents the internal humidity of the material, Hr represents the reference humidity, Pe represents the external environment pressure, Pi represents the internal pressure of the material, Pr represents the reference pressure, t represents the time variable, t0 and t1 respectively represent the start time and end time of the ultrasonic signal acquisition.

6. The multi-layer material thickness detection system based on TM sensor according to claim 5, characterized in that: Comparing the environmental impact index with historical data and adjusting the hierarchical measurement algorithm according to the comparison result includes: When there is a historical environmental impact index identical to the environmental impact index in the historical data, adjusting the hierarchical measurement algorithm with a historical compensation coefficient corresponding to the historical environmental impact index; When there is no historical environmental impact index corresponding to the environmental impact index in the historical data, the environmental impact index is stored.

7. The multi-layer material thickness detection system based on TM sensor according to claim 6, characterized in that: When calculating the comprehensive compensation coefficient according to the density data, the first environment data and the second environment data and adjusting the layered measurement algorithm, it includes: Subtract the density value corresponding to the density data of each layer of material from the density standard value corresponding to each layer of material to obtain the density difference value; Compare the density difference with a first density difference threshold and a second density difference threshold, and determine whether there is a density anomaly in the current layer material and the type of anomaly according to the comparison result; wherein the first density difference threshold is less than 0, and the second density difference threshold is greater than 0; When the density difference is less than or equal to the first density difference threshold, it is determined that the current layer of material has a density anomaly, and the anomaly type is material damage; When the density difference is greater than a first density difference threshold and less than or equal to a second density difference threshold, it is determined that there is no density anomaly in the current layer of material; When the density difference is greater than a second density difference threshold, it is determined that a density anomaly exists in the current layer of material, and the anomaly type is material surface contamination.

8. The multi-layer material thickness detection system based on TM sensor according to claim 7, characterized in that: When the density of the current layer material is determined to be abnormal according to the comparison results, it includes: If the abnormal type of the current layer material is material damage, analyze the size and position of the damaged area and correct the measurement results according to the degree of damage; If the abnormal type of the current layer of material is material surface contamination, remove the contaminants on the material surface and then perform ultrasonic testing again.

9. The multi-layer material thickness detection system based on TM sensor according to claim 8, characterized in that: When determining whether the current layer of material has density anomaly based on the comparison result, it includes: The comprehensive compensation coefficient is calculated according to the density data, the first environment data and the second environment data, and the comprehensive compensation coefficient is obtained by the following formula: Wherein, Zi represents the comprehensive compensation coefficient of the current layer material, α and β represent weight coefficients, D represents the normalized value of the density difference, Te represents the normalized value of the external environment temperature, He represents the normalized value of the external environment humidity, Pe represents the normalized value of the external environment pressure, Ti represents the normalized value of the internal temperature of the material, Hi represents the normalized value of the internal humidity of the material, Pi represents the normalized value of the internal pressure of the material, and ρi represents the normalized value of the density of the current layer material; The layered measurement algorithm is adjusted using the comprehensive compensation coefficient, and the comprehensive compensation coefficient is stored in the storage unit.

10. A method for detecting thickness of a multilayer material based on a TM sensor, applied to a multilayer material thickness detection system based on a TM sensor as claimed in any one of claims 1 to 9, characterized in that: include: Transmitting ultrasonic waves into the multi-layer material, and receiving the echo of the ultrasonic waves on each layer of material to form ultrasonic signals; acquiring the ultrasonic signals, and performing feature extraction on the ultrasonic signals to obtain amplitude feature data, waveform feature data, and spectrum feature data of the ultrasonic signals corresponding to each layer of material; Collecting the amplitude characteristic data, waveform characteristic data and spectrum characteristic data; generating a layered measurement algorithm using the amplitude characteristic data, waveform characteristic data and spectrum characteristic data as input signals, and calculating the measured thickness of each layer of material according to the layered measurement algorithm; The measured thickness is compared with the standard thickness value, and it is determined whether to adjust the layered measurement algorithm according to the comparison result: when it is determined that the layered measurement algorithm is to be adjusted, first environmental data of the external environment and second environmental data inside the multilayer material are collected, and an environmental data set is established according to the first environmental data and the second environmental data, an environmental impact index is calculated according to the environmental data set, the environmental impact index is compared with historical data, and the layered measurement algorithm is adjusted according to the comparison result; When the environmental impact index is different from the historical data, density data corresponding to each layer of material is collected, and a comprehensive compensation coefficient is calculated according to the density data, the first environmental data and the second environmental data, and the layered measurement algorithm is adjusted; The comprehensive compensation coefficient is stored.

11. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the multi-layer material thickness detection method based on the TM sensor as claimed in claim 10.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for detecting thickness of multi-layer materials based on a TM sensor as claimed in claim 10 is implemented.

Images