Method and device for calculating thickness of oxide layer of boiler

Abstract

The invention relates to the technical field of boilers, in particular to a boiler oxide layer thickness calculation method and device, and the method comprises the steps: collecting the actual ultrasonic data of a to-be-measured oxide layer in a boiler and the actual operation data of the boiler; extracting features to obtain corresponding actual ultrasonic echo signal features; and inputting the actual ultrasonic echo signal characteristics and the actual operation data into a pre-trained oxidation thickness calculation model to calculate an initial thickness value and a thickness correction coefficient of the to-be-measured oxidation layer, and correcting the initial thickness value according to the thickness correction coefficient to obtain a final thickness value. Therefore, the problems that in the related technology, an off-line sampling measurement method can cause damage to a reheater, the measurement period is long, the thickness change of an oxide layer cannot be reflected in real time, and the requirement for high-precision measurement is difficult to meet are solved; and an on-line nondestructive detection method is high in equipment requirement, high in cost and poor in environmental adaptability, so that the error of a measurement result is relatively large, and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of boilers, in particular to a method and device for calculating the thickness of an oxide layer of a boiler. BACKGROUND

[0002] In related technologies, common methods for measuring the thickness of an oxide layer of a boiler reheater mainly include offline sampling measurement and online nondestructive detection. The offline sampling measurement obtains an oxide layer sample by destructive sampling, and then measures the thickness of the oxide layer in combination with microscopic analysis technology. The online nondestructive detection mainly includes ultrasonic detection, electromagnetic induction detection, etc. The ultrasonic detection mainly utilizes the propagation characteristics of ultrasonic waves in materials, and then calculates the thickness of the oxide layer by analyzing the time delay and amplitude change of the reflected signal. The electromagnetic induction detection is based on electromagnetic induction effect, and indirectly calculates the thickness of the oxide layer by measuring the induced current or magnetic field change.

[0003] However, in related technologies, the offline sampling measurement causes damage to the reheater, has a long measurement period, and cannot reflect the thickness change of the oxide layer in real time, which is difficult to meet the requirement of high-precision measurement. The online nondestructive detection has high requirements for equipment and high cost, and the measurement result often has a large error, which does not have the universality of adapting to multiple scene applications, and needs to be improved. SUMMARY

[0004] The present application provides a method and device for calculating the thickness of an oxide layer of a boiler, to solve the problems in related technologies that the offline sampling measurement causes damage to the reheater, has a long measurement period, and cannot reflect the thickness change of the oxide layer in real time, which is difficult to meet the requirement of high-precision measurement; the online nondestructive detection has high requirements for equipment and high cost, and poor environmental adaptability, resulting in a large error of the measurement result.

[0005] The first aspect embodiment of the present application provides a method for calculating the thickness of an oxide layer of a boiler, including the following steps: collecting actual ultrasonic wave data of a to-be-measured oxide layer in a boiler and actual operation data of the boiler; extracting time domain features and / or frequency domain features in the actual ultrasonic wave data to obtain corresponding actual ultrasonic wave echo signal features; inputting the actual ultrasonic wave echo signal features and the actual operation data into a pre-trained oxide thickness calculation model, respectively calculating an initial thickness value of the to-be-measured oxide layer and a thickness correction coefficient of the to-be-measured oxide layer by using the oxide thickness calculation model, and correcting the initial thickness value according to the thickness correction coefficient to obtain a final thickness value of the to-be-measured oxide layer.

[0006] The above technical solution can collect actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler, and extract the signals from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal characteristics. Then, the actual ultrasonic echo signal characteristics and actual operating data are input into a pre-trained oxide thickness calculation model to obtain the initial thickness value and thickness correction coefficient of the oxide layer to be tested, and finally obtain the final thickness value of the oxide layer to be tested. This method can fully explore the nonlinear relationship between ultrasonic echo signals and oxide thickness. At the same time, through operating condition parameter correction and abnormal signal processing, the accuracy and efficiency of oxide thickness calculation are significantly improved. The method is simple to operate, has a wide range of applications, and provides a reliable basis for the safe operation and maintenance of equipment.

[0007] Optionally, in one embodiment of this application, before inputting the actual ultrasonic echo signal features into the pre-trained oxidation thickness calculation model, the method further includes: acquiring ultrasonic data of the target oxide layer to be measured in the target boiler and the operating data of the target boiler, and obtaining the actual thickness value of the target oxide layer to be measured; extracting time-domain features and / or frequency-domain features from the ultrasonic data to obtain the corresponding ultrasonic echo signal features; and determining the network structure, network parameters, training parameters, and validation function of the oxidation thickness calculation model based on the ultrasonic echo signal features and the actual thickness value, so as to construct the oxidation thickness calculation model.

[0008] The above technical solution allows for the extraction of ultrasonic data and operational parameters of the target oxide layer in the target boiler before inputting the actual ultrasonic echo signal characteristics into the oxide thickness calculation model. This yields the corresponding ultrasonic echo signal characteristics. Based on these characteristics and the actual thickness of the target oxide layer, the network structure, network parameters, training parameters, and validation function of the oxide thickness calculation model are determined. This constructs the corresponding oxide thickness calculation model, eliminating biases in general models, achieving deep model adaptation to operating conditions, improving detection accuracy, dynamically optimizing the model structure, enhancing adaptability, and ensuring the model's stability and reliability through verification with measured data. This provides a more economical and reliable technical guarantee for the safe operation of boilers.

[0009] Optionally, in one embodiment of this application, the step of determining the network structure, network parameters, training parameters, and validation function of the oxide thickness calculation model based on the ultrasonic echo signal features and the actual thickness value to construct the oxide thickness calculation model includes: inputting the ultrasonic echo signal features into an initial oxide thickness calculation model using the network structure and the network parameters to calculate the predicted thickness value of the target oxide layer to be tested using the initial oxide thickness calculation model; calculating the difference between the predicted thickness value and the actual thickness value; and training and validating the initial oxide thickness calculation model based on the training parameters and the validation function until the difference is less than a preset threshold to obtain a trained oxide thickness calculation model.

[0010] The above technical solution allows the ultrasonic echo signal characteristics to be input into an initial oxidation thickness calculation model using a network structure and network parameters. This yields a predicted thickness value for the target oxide layer and calculates the difference between the predicted and actual thickness values. The initial oxidation thickness calculation model is then trained and validated until the difference is less than a certain threshold, resulting in a well-trained oxidation thickness calculation model. This difference feedback mechanism, driven by measured data, gradually approximates the actual thickness value, eliminating the deviation between the theoretical model and actual operating conditions, improving detection accuracy, dynamically optimizing the model structure, accelerating convergence, and enhancing the model's generalization ability. This enables the model to adapt to more complex operating conditions, providing a more intelligent and reliable solution for boiler safety monitoring.

[0011] Optionally, in one embodiment of this application, the step of collecting actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler includes: acquiring temperature data of the boiler based on the actual operating data; determining a correction value for the actual ultrasonic data based on the temperature data, so as to correct the actual ultrasonic data according to the correction value, and obtaining corrected actual ultrasonic data.

[0012] The above technical solution can determine the correction values ​​of the actual ultrasonic data and the actual operating data of the boiler based on the boiler's temperature data, thereby correcting the actual ultrasonic data and the actual operating data of the boiler to obtain the corrected actual ultrasonic data. This eliminates the interference of temperature on ultrasonic propagation, improves data accuracy, dynamically adapts to changes in operating conditions, enhances the model's generalization ability, suppresses nonlinear errors, ensures long-term stability, and supports real-time monitoring and closed-loop control.

[0013] Optionally, in one embodiment of this application, the step of collecting actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler includes: detecting whether the actual ultrasonic data meets preset data conditions; if the actual ultrasonic data does not meet the preset data conditions, generating a repair instruction for the actual ultrasonic data according to the preset data conditions, and repairing the actual ultrasonic data according to the repair instruction until actual ultrasonic data that meets the preset data conditions is obtained.

[0014] The above technical solution can first detect whether the actual ultrasonic data and the actual operating data of the boiler meet certain data conditions. If not, a repair instruction for the actual ultrasonic data is generated based on the certain data conditions to repair the actual ultrasonic data and the actual operating data of the boiler until the actual ultrasonic data and the actual operating data of the boiler that meet the certain data conditions are obtained. This avoids deviations in oxide layer thickness calculation due to missing data, improves data accuracy, optimizes model training efficiency, reduces iteration costs, enhances adaptability to operating conditions, covers extreme scenarios, achieves a fully automated closed loop, reduces manual intervention, and provides higher quality and more stable input data for the boiler oxide layer thickness detection model, significantly improving the overall performance and reliability of the model.

[0015] A second aspect of this application provides a device for calculating the thickness of a boiler oxide layer, comprising: an acquisition module for acquiring actual ultrasonic data of the oxide layer to be measured in the boiler and actual operating data of the boiler; an extraction module for extracting time-domain features and / or frequency-domain features from the actual ultrasonic data to obtain corresponding actual ultrasonic echo signal features; and a calculation module for inputting the actual ultrasonic echo signal features and the actual operating data into a pre-trained oxide thickness calculation model, calculating an initial thickness value of the oxide layer to be measured and a thickness correction coefficient of the oxide layer to be measured using the oxide thickness calculation model, and correcting the initial thickness value according to the thickness correction coefficient to obtain the final thickness value of the oxide layer to be measured.

[0016] The above technical solution can collect actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler, and extract the signals from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal characteristics. Then, the actual ultrasonic echo signal characteristics and actual operating data are input into a pre-trained oxide thickness calculation model to obtain the initial thickness value and thickness correction coefficient of the oxide layer to be tested, and finally obtain the final thickness value of the oxide layer to be tested. This method can fully explore the nonlinear relationship between ultrasonic echo signals and oxide thickness. At the same time, through operating condition parameter correction and abnormal signal processing, the accuracy and efficiency of oxide thickness calculation are significantly improved. The method is simple to operate, has a wide range of applications, and provides a reliable basis for the safe operation and maintenance of equipment.

[0017] Optionally, in one embodiment of this application, it further includes: an acquisition module, configured to acquire ultrasonic data of the target oxide layer to be tested in the target boiler and the operating data of the target boiler before inputting the actual ultrasonic echo signal features into the pre-trained oxide thickness calculation model, and to acquire the actual thickness value of the target oxide layer to be tested; a generation module, configured to extract time-domain features and / or frequency-domain features from the ultrasonic data to obtain the corresponding ultrasonic echo signal features; and a construction module, configured to determine the network structure, network parameters, training parameters, and validation function of the oxide thickness calculation model based on the ultrasonic echo signal features and the actual thickness value, so as to construct the oxide thickness calculation model.

[0018] The above technical solution allows for the extraction of ultrasonic data and operational parameters of the target oxide layer in the target boiler before inputting the actual ultrasonic echo signal characteristics into the oxide thickness calculation model. This yields the corresponding ultrasonic echo signal characteristics. Based on these characteristics and the actual thickness of the target oxide layer, the network structure, network parameters, training parameters, and validation function of the oxide thickness calculation model are determined. This constructs the corresponding oxide thickness calculation model, eliminating biases in general models, achieving deep model adaptation to operating conditions, improving detection accuracy, dynamically optimizing the model structure, enhancing adaptability, and ensuring the model's stability and reliability through verification with measured data. This provides a more economical and reliable technical guarantee for the safe operation of boilers.

[0019] Optionally, in one embodiment of this application, the construction module includes: a first calculation unit, configured to input the ultrasonic echo signal features into an initial oxide thickness calculation model using the network structure and the network parameters, so as to calculate the predicted thickness value of the target oxide layer to be tested using the initial oxide thickness calculation model; a second calculation unit, configured to calculate the difference between the predicted thickness value and the actual thickness value; and a first generation unit, configured to train and verify the initial oxide thickness calculation model based on the training parameters and the verification function until the difference is less than a preset threshold, so as to obtain a trained oxide thickness calculation model.

[0020] The above technical solution allows the ultrasonic echo signal characteristics to be input into an initial oxidation thickness calculation model using a network structure and network parameters. This yields a predicted thickness value for the target oxide layer and calculates the difference between the predicted and actual thickness values. The initial oxidation thickness calculation model is then trained and validated until the difference is less than a certain threshold, resulting in a well-trained oxidation thickness calculation model. This difference feedback mechanism, driven by measured data, gradually approximates the actual thickness value, eliminating the deviation between the theoretical model and actual operating conditions, improving detection accuracy, dynamically optimizing the model structure, accelerating convergence, and enhancing the model's generalization ability. This enables the model to adapt to more complex operating conditions, providing a more intelligent and reliable solution for boiler safety monitoring.

[0021] Optionally, in one embodiment of this application, the acquisition module includes: an acquisition unit, configured to acquire temperature data of the boiler based on the actual operating data; and a second generation unit, configured to determine a correction value for the actual ultrasonic data based on the temperature data, so as to correct the actual ultrasonic data according to the correction value to obtain corrected actual ultrasonic data.

[0022] The above technical solution can determine the correction values ​​of the actual ultrasonic data and the actual operating data of the boiler based on the boiler's temperature data, thereby correcting the actual ultrasonic data and the actual operating data of the boiler to obtain the corrected actual ultrasonic data. This eliminates the interference of temperature on ultrasonic propagation, improves data accuracy, dynamically adapts to changes in operating conditions, enhances the model's generalization ability, suppresses nonlinear errors, ensures long-term stability, and supports real-time monitoring and closed-loop control.

[0023] Optionally, in one embodiment of this application, the acquisition module includes: a detection unit, configured to detect whether the actual ultrasonic data meets preset data conditions; and a repair unit, configured to, when the actual ultrasonic data does not meet the preset data conditions, generate a repair instruction for the actual ultrasonic data according to the preset data conditions, and repair the actual ultrasonic data according to the repair instruction until actual ultrasonic data that meets the preset data conditions is obtained.

[0024] The above technical solution can first detect whether the actual ultrasonic data and the actual operating data of the boiler meet certain data conditions. If not, a repair instruction for the actual ultrasonic data is generated based on the certain data conditions to repair the actual ultrasonic data and the actual operating data of the boiler until the actual ultrasonic data and the actual operating data of the boiler that meet the certain data conditions are obtained. This avoids deviations in oxide layer thickness calculation due to missing data, improves data accuracy, optimizes model training efficiency, reduces iteration costs, enhances adaptability to operating conditions, covers extreme scenarios, achieves a fully automated closed loop, reduces manual intervention, and provides higher quality and more stable input data for the boiler oxide layer thickness detection model, significantly improving the overall performance and reliability of the model.

[0025] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the boiler oxide layer thickness calculation method as described in the above embodiments.

[0026] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for calculating the thickness of the boiler oxide layer.

[0027] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, implements the above-described method for calculating boiler oxide layer thickness.

[0028] This application embodiment can collect actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler, and extract the signal from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal characteristics. Then, the actual ultrasonic echo signal characteristics and the actual operating data are input into a pre-trained oxide thickness calculation model to obtain the initial thickness value and thickness correction coefficient of the oxide layer to be tested, and finally obtain the final thickness value of the oxide layer to be tested. It can fully explore the nonlinear relationship between ultrasonic echo signal and oxide thickness. At the same time, through operating condition parameter correction and abnormal signal processing, it significantly improves the accuracy and efficiency of oxide thickness calculation. It is easy to operate, has a wide range of applications, and provides a reliable basis for the safe operation and maintenance of equipment. Thus, it solves the problems in related technologies, such as offline sampling measurement methods causing damage to reheaters, long measurement cycles, inability to reflect oxide layer thickness changes in real time, and difficulty in meeting the requirements of high-precision measurement; and online non-destructive testing methods having high equipment requirements, high costs, poor environmental adaptability, and large measurement error.

[0029] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0030] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a method for calculating the thickness of a boiler oxide layer according to an embodiment of this application; Figure 2 A flowchart illustrating the working principle of a boiler oxide layer thickness calculation method according to an embodiment of this application; Figure 3 This is a block diagram of a device for calculating the thickness of boiler oxide layer according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0031] Figure label: Among them, 10-Calculation device for boiler oxide layer thickness; 100-Acquisition module, 200-Extraction module, 300-Calculation module; 401-Memory, 402-Processor, 403-Communication interface. Detailed Implementation

[0032] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0033] The following describes a method and apparatus for calculating boiler oxide layer thickness according to embodiments of this application, with reference to the accompanying drawings. Addressing the issues mentioned in the background art, such as the damage to reheaters caused by offline sampling measurement methods, long measurement cycles, inability to reflect oxide layer thickness changes in real time, and difficulty in meeting high-precision measurement requirements; and the high equipment requirements, high cost, and poor environmental adaptability of online non-destructive testing methods leading to large measurement errors, this application provides a method for calculating boiler oxide layer thickness. In this method, actual ultrasonic data of the oxide layer to be measured and actual boiler operating data can be collected from the boiler. Signals from the actual ultrasonic data are extracted to obtain the corresponding actual ultrasonic echo signal characteristics. These characteristics and operating data are then input into a pre-trained oxide thickness calculation model to obtain the initial thickness value and thickness correction coefficient of the oxide layer to be measured, ultimately yielding the final thickness value. This method fully exploits the nonlinear relationship between ultrasonic echo signals and oxide thickness. Furthermore, through operating parameter correction and abnormal signal processing, it significantly improves the accuracy and efficiency of oxide thickness calculation. The method is simple to operate, has a wide range of applications, and provides a reliable basis for the safe operation and maintenance of equipment. This solves the problems in related technologies, such as offline sampling measurement methods causing damage to reheaters, long measurement cycles, inability to reflect oxide layer thickness changes in real time, and difficulty in meeting the requirements of high-precision measurement; while online non-destructive testing methods have high equipment requirements, high costs, poor environmental adaptability, and large measurement error.

[0034] Specifically, Figure 1 This is a flowchart illustrating a method for calculating the thickness of a boiler oxide layer according to an embodiment of this application.

[0035] like Figure 1 As shown, the method for calculating the oxide layer thickness of this boiler includes the following steps: In step S101, the actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler are collected.

[0036] It is understood that, in the embodiments of this application, the oxide layer to be tested can be the oxide layer of a boiler reheater, the oxide layer of a boiler economizer, the oxide layer of a water-cooled wall, or the oxide layer of a high-temperature pressure heating tube in the chemical industry. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose any specific limitations.

[0037] As one possible approach, embodiments of this application can collect actual ultrasonic data of the oxide layer to be tested in the boiler and actual operating data of the boiler.

[0038] For example, in this application embodiment, a high-frequency ultrasonic probe with a frequency of 15-20MHz can be used to detect the oxide layer of the boiler. For instance, in this application embodiment, the high-frequency ultrasonic probe can be installed at the detection point of the boiler reheater and a comprehensive scan of the reheater can be performed to collect the actual ultrasonic data of the oxide layer to be tested and the actual operating data of the boiler, and the location information of each detection point can be recorded. At the same time, the actual operating data of the boiler reheater can be recorded, which may include, but is not limited to, operating temperature, working pressure, steam flow rate, equipment operating years, etc., and this application does not impose specific limitations.

[0039] It should be noted that, for detection points with non-uniform oxide layer distribution, this application embodiment can use a 4-channel ultrasonic probe to perform multi-angle scanning and take the weighted average of the measurement results of each channel. The weight of the measurement results of each channel is determined according to the signal-to-noise ratio of the channel signal. The higher the signal-to-noise ratio, the greater the weight, to ensure the accuracy of the calculation results. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose any specific limitations.

[0040] Optionally, in one embodiment of this application, collecting actual ultrasonic data of the oxide layer to be tested in the boiler and actual operating data of the boiler includes: acquiring boiler temperature data based on the actual operating data; determining a correction value for the actual ultrasonic data based on the temperature data, and correcting the actual ultrasonic data according to the correction value to obtain corrected actual ultrasonic data.

[0041] It is understood that, in the embodiments of this application, the temperature data in the actual operating data is used to correct the propagation speed of ultrasound in the oxide layer.

[0042] As one possible approach, embodiments of this application can first obtain boiler temperature data based on actual operating data, then determine correction values ​​for actual ultrasonic data based on the temperature data, and then correct the actual ultrasonic data based on the correction values ​​to obtain corrected actual ultrasonic data.

[0043] For example, in this embodiment of the application, when the reheater operating temperature exceeds 300°C, the propagation speed of ultrasonic waves can be corrected. The correction formula can be, but is not limited to, expressed as: , in, This represents the propagation speed of ultrasound in the oxide layer at room temperature, and its value can be 5.9 mm / μs. The temperature coefficient can take the following values: / ℃; This is the actual temperature.

[0044] In addition, in the embodiments of this application, the propagation speed of ultrasound in the oxide layer can also be calibrated according to the oxide layer material. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose any specific limitations.

[0045] Optionally, in one embodiment of this application, collecting actual ultrasonic data of the oxide layer to be tested in the boiler and actual operating data of the boiler includes: detecting whether the actual ultrasonic data meets preset data conditions; if the actual ultrasonic data does not meet the preset data conditions, generating a repair instruction for the actual ultrasonic data according to the preset data conditions, and repairing the actual ultrasonic data according to the repair instruction until actual ultrasonic data that meets the preset data conditions is obtained.

[0046] It is understood that the embodiments of this application can detect whether the frequency, signal strength, etc., of the actual ultrasonic data meet certain data conditions. These certain data conditions can be set by those skilled in the art according to actual circumstances, and this application does not impose specific limitations. For example, the embodiments of this application can use wavelet threshold filtering to filter the actual ultrasonic data, removing noise from the ultrasonic signal; utilize signal enhancement algorithms to enhance the filtered signal, highlighting its characteristics; and systematically organize and verify the actual ultrasonic data, eliminating abnormal data to ensure the accuracy of the actual ultrasonic data.

[0047] In this embodiment of the application, signal anomalies in ultrasonic data can be determined by calculating the signal-to-noise ratio (SNR) of the echo signal. When the SNR is <30dB, it is determined to be a signal anomaly. In this case, this embodiment of the application can use a wavelet packet-based signal reconstruction algorithm to repair the signal. If the SNR is still <25dB after repair, the corresponding data is discarded and re-detected.

[0048] In some embodiments, when the actual ultrasonic data does not meet certain data conditions, a repair instruction for the actual ultrasonic data can be generated based on certain data conditions to repair the corresponding actual ultrasonic data until the actual ultrasonic data that meets certain data conditions is obtained.

[0049] For example, embodiments of this application may employ a low-pass filter with a cutoff frequency of 50MHz to remove high-frequency noise and use a minimum-maximum normalization algorithm to adjust the signal strength to the range of 0-1, thereby obtaining actual ultrasonic data that meets certain data conditions.

[0050] In step S102, time-domain features and / or frequency-domain features are extracted from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal features.

[0051] In actual implementation, the embodiments of this application can obtain the corresponding actual ultrasonic echo signal characteristics by extracting the time-domain and / or frequency-domain features from the actual ultrasonic data.

[0052] For example, in the embodiments of this application, wavelet transform (such as db4 wavelet basis function, with a decomposition layer of 3 layers, which is not specifically limited in this application) and Fourier transform (wherein, the frequency analysis range of Fourier transform can be 0-100MHz, which is not specifically limited in this application) can be used to extract features from actual ultrasonic data, thereby obtaining the mean, variance, frequency distribution characteristics, rate of change of propagation time of ultrasonic signals, and signal characteristics such as peak value, peak occurrence time, and signal energy of ultrasonic echo signals. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not make specific limitations.

[0053] Optionally, in one embodiment of this application, before inputting the actual ultrasonic echo signal features into the pre-trained oxidation thickness calculation model, the method further includes: collecting ultrasonic data of the target oxide layer to be measured in the target boiler and the operating data of the target boiler, and obtaining the actual thickness value of the target oxide layer to be measured; extracting time-domain features and / or frequency-domain features from the ultrasonic data to obtain the corresponding ultrasonic echo signal features; and determining the network structure, network parameters, training parameters, and validation function of the oxidation thickness calculation model based on the ultrasonic echo signal features and the actual thickness value, so as to construct the oxidation thickness calculation model.

[0054] In some embodiments, this application embodiment can acquire ultrasonic data of the target oxide layer in the target boiler using a high-frequency ultrasonic probe, and collect the operating data of the target boiler. At the same time, this application embodiment can also select some samples at the same detection point for offline sampling, and measure the actual thickness value of the target oxide layer using a microscope as tag data.

[0055] It should be noted that the embodiments of this application can organize and verify the tag data and remove abnormal data. Abnormal data can be understood as data whose deviation from the measurement value of adjacent detection points under the same working conditions exceeds 20%. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0056] For example, this application embodiment collected a total of 3,000 sets of data, covering 3 different models of reheaters, 5 devices with different operating years, and 6 oxidation thickness ranges (which may be, but are not limited to, 0.05-0.1mm, 0.1-0.2mm, 0.2-0.3mm, 0.3-0.5mm, 0.5-0.8mm, and above 0.8mm, etc., this application does not make specific limitations). Among them, 2,400 sets of data were used for training the oxidation thickness calculation model, and 600 sets were used for verifying the oxidation thickness calculation model. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not make specific limitations.

[0057] Furthermore, in this embodiment, the time-frequency local features can be obtained by using the db4 wavelet basis function to perform a three-level decomposition, and the signal spectrum distribution can be analyzed in the frequency range of 0-100MHz using Fourier transform to obtain frequency domain features, thereby obtaining the corresponding echo signal features, and these features are organized into feature vectors, which are used as input to the model for model training and verification.

[0058] Furthermore, embodiments of this application can determine the network structure, network parameters, training parameters, and verification function of the oxidation thickness calculation model based on the characteristics of the ultrasonic echo signal and the actual thickness value.

[0059] For example, in this application embodiment, a backpropagation neural network can be selected as the network structure for the oxidation thickness calculation model. This neural network model includes one input layer, two hidden layers, and one output layer. The number of neurons in the input layer is the same as the number of extracted echo signal features. The first hidden layer has 12 neurons, the second hidden layer has 6 neurons, and the output layer has one neuron, corresponding to the oxidation thickness. The activation function is the ReLU function, the initial learning rate is set to 0.01, and the learning rate is adjusted using an adaptive moment estimation algorithm. The number of iterations is set to 500, and training stops when the validation set error does not decrease for 10 consecutive iterations.

[0060] Furthermore, this application embodiment uses the gradient descent algorithm to train the model, and by adjusting the weights and biases of the network, the error between the model's output and the actual thickness value is minimized; during the training process, the 5-fold cross-validation method is used to evaluate and optimize the model, thereby constructing an oxide thickness calculation model.

[0061] Optionally, in one embodiment of this application, based on the characteristics of the ultrasonic echo signal and the actual thickness value, the network structure, network parameters, training parameters, and validation function of the oxide thickness calculation model are determined to construct the oxide thickness calculation model. This includes: inputting the ultrasonic echo signal characteristics into an initial oxide thickness calculation model using the network structure and network parameters to calculate the predicted thickness value of the target oxide layer to be measured using the initial oxide thickness calculation model; calculating the difference between the predicted thickness value and the actual thickness value; and training and validating the initial oxide thickness calculation model based on the training parameters and validation function until the difference is less than a preset threshold to obtain a trained oxide thickness calculation model.

[0062] As one possible implementation, embodiments of this application can input the characteristics of the ultrasonic echo signal into an initial oxide thickness calculation model employing a network structure and network parameters to obtain the predicted thickness value of the target oxide layer to be measured. The difference between the predicted thickness value and the actual thickness value is then calculated. Based on training parameters and a validation function, the initial oxide thickness calculation model is trained and validated until the difference is less than a certain threshold, thereby obtaining a trained oxide thickness calculation model. This certain threshold can be set by those skilled in the art according to actual conditions, and this application does not impose specific limitations.

[0063] For example, in this embodiment, ultrasonic echo signal features can be used as input, and the corresponding actual thickness value as output. The model is trained using gradient descent and 5-fold cross-validation to obtain a trained oxide thickness calculation model. For instance, in this embodiment, 2400 sets of training data are input into the initial oxide thickness calculation model, and the model is trained using gradient descent. By adjusting the network weights and biases, the difference between the predicted thickness value and the actual thickness value output by the model is minimized. During training, cross-validation is used to evaluate and optimize the model, thereby obtaining a trained oxide thickness calculation model.

[0064] Furthermore, in this embodiment, a trained oxidation thickness calculation model can be used to process 600 sets of verification data. The ultrasonic echo signal features in the verification data are input into the model to obtain the predicted thickness value. The predicted thickness value is then compared with the actual thickness value, so that the average absolute error of the model verification set is 0.02 mm and the root mean square error is 0.03 mm. The specific settings can be made by those skilled in the art according to the actual situation, and this application does not impose any specific limitations.

[0065] In step S103, the actual ultrasonic echo signal characteristics and actual operating data are input into the pre-trained oxide thickness calculation model. The initial thickness value of the oxide layer to be tested and the thickness correction coefficient of the oxide layer to be tested are calculated using the oxide thickness calculation model. The initial thickness value is then corrected according to the thickness correction coefficient to obtain the final thickness value of the oxide layer to be tested.

[0066] In actual implementation, the embodiments of this application can input the actual ultrasonic echo signal characteristics into a pre-trained oxide thickness calculation model, and then use the oxide thickness calculation model to calculate the initial thickness value and thickness correction coefficient of the oxide layer to be tested, thereby obtaining the final thickness value of the oxide layer to be tested.

[0067] For example, in this embodiment of the application, a pre-trained oxide thickness calculation model is used to process the characteristics of the actual ultrasonic echo signal. First, the initial thickness value of the oxide layer to be measured is calculated. The calculation process can be, but is not limited to, expressed as follows: , in, The initial thickness of the oxide layer to be measured is in mm. The speed of sound propagation in the oxide layer, in mm / μs; The time difference between the reflected echoes from the upper and lower interfaces of the oxide layer is expressed in μs.

[0068] Furthermore, in this embodiment of the application, the thickness correction coefficient of the oxide layer to be tested is calculated based on actual operating data. The formula for calculating the thickness correction coefficient can be, but is not limited to, expressed as: , in, , , , , , This is the thickness correction factor.

[0069] Furthermore, in this embodiment, the initial thickness value is corrected and optimized based on a thickness correction coefficient to output an accurate final thickness value of the oxide layer to be measured. The expression for this final thickness value can be, but is not limited to, the following: , in, This is the final thickness value.

[0070] The working principle of the boiler oxide layer thickness calculation method proposed in this application will be introduced below with reference to a specific embodiment.

[0071] in, Figure 2 This is a flowchart illustrating the working principle of a boiler oxide layer thickness calculation method according to an embodiment of this application.

[0072] like Figure 2 As shown, this calculation method includes a training phase and an application phase of the model.

[0073] Training phase.

[0074] Step S201: Collect ultrasonic data of the target oxide layer to be tested in the target boiler and the operating data of the target boiler, and obtain the actual thickness value of the target oxide layer to be tested.

[0075] Step S202: Extract features to obtain the corresponding ultrasonic echo signal features.

[0076] Step S203: Determine the network structure, network parameters, training parameters, and validation function of the oxidation thickness calculation model.

[0077] Step S204: Train and validate the initial oxidation thickness calculation model until a well-trained oxidation thickness calculation model is obtained.

[0078] Application phase.

[0079] Step S205: Collect actual ultrasonic data of the oxide layer to be tested in the boiler and actual operating data of the boiler.

[0080] Step S206: Extract features to obtain the corresponding actual ultrasonic echo signal features.

[0081] Step S207: Calculate the final thickness value of the oxide layer to be tested using a pre-trained oxide thickness calculation model.

[0082] The boiler oxide layer thickness calculation method proposed in this application can collect actual ultrasonic data of the oxide layer to be measured in the boiler and actual boiler operating data, extract signals from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal characteristics, and then input the actual ultrasonic echo signal characteristics and actual operating data into a pre-trained oxide thickness calculation model to obtain the initial thickness value and thickness correction coefficient of the oxide layer to be measured, and finally obtain the final thickness value of the oxide layer to be measured. This method can fully explore the nonlinear relationship between ultrasonic echo signals and oxide thickness, and significantly improve the accuracy and efficiency of oxide thickness calculation through operating parameter correction and abnormal signal processing. It is easy to operate, has a wide range of applications, and provides a reliable basis for the safe operation and maintenance of equipment. Therefore, it solves the problems in related technologies, such as offline sampling measurement methods causing damage to reheaters, long measurement cycles, inability to reflect oxide layer thickness changes in real time, and difficulty in meeting the requirements of high-precision measurement; and online non-destructive testing methods having high equipment requirements, high costs, poor environmental adaptability, and large measurement error.

[0083] Next, the apparatus for calculating the thickness of the boiler oxide layer according to an embodiment of this application is described with reference to the accompanying drawings.

[0084] Figure 3 This is a block diagram of a device for calculating the thickness of boiler oxide layer according to an embodiment of this application.

[0085] like Figure 3 As shown, the calculation device 10 for the thickness of the boiler oxide layer includes: a data acquisition module 100, an extraction module 200, and a calculation module 300.

[0086] The acquisition module 100 is used to acquire the actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler.

[0087] The extraction module 200 is used to extract time-domain and / or frequency-domain features from actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal features.

[0088] The calculation module 300 is used to input the actual ultrasonic echo signal characteristics and actual operating data into the pre-trained oxide thickness calculation model. The initial thickness value and the thickness correction coefficient of the oxide layer to be tested are calculated using the oxide thickness calculation model, and the initial thickness value is corrected according to the thickness correction coefficient to obtain the final thickness value of the oxide layer to be tested.

[0089] Optionally, in one embodiment of this application, it further includes: an acquisition module, a generation module, and a construction module.

[0090] The acquisition module is used to collect ultrasonic data of the target oxide layer in the target boiler and the operating data of the target boiler before inputting the actual ultrasonic echo signal characteristics into the pre-trained oxide thickness calculation model, and to obtain the actual thickness value of the target oxide layer.

[0091] The generation module is used to extract time-domain and / or frequency-domain features from ultrasonic data to obtain the corresponding ultrasonic echo signal features.

[0092] The module is used to determine the network structure, network parameters, training parameters, and validation function of the oxidation thickness calculation model based on the characteristics of ultrasonic echo signals and the actual thickness value, so as to construct the oxidation thickness calculation model.

[0093] Optionally, in one embodiment of this application, the construction module includes: a first computing unit, a second computing unit, and a first generation unit.

[0094] The first calculation unit is used to input the characteristics of the ultrasonic echo signal into the initial oxide thickness calculation model using a network structure and network parameters, so as to calculate the predicted thickness value of the target oxide layer using the initial oxide thickness calculation model.

[0095] The second calculation unit is used to calculate the difference between the predicted thickness value and the actual thickness value.

[0096] The first generation unit is used to train and validate the initial oxidation thickness calculation model based on the training parameters and the validation function until the difference is less than a preset threshold, so as to obtain the trained oxidation thickness calculation model.

[0097] Optionally, in one embodiment of this application, the acquisition module 100 includes: an acquisition unit and a second generation unit.

[0098] The acquisition unit is used to obtain boiler temperature data based on actual operating data.

[0099] The second generation unit is used to determine the correction value of the actual ultrasonic data based on the temperature data, so as to correct the actual ultrasonic data according to the correction value and obtain the corrected actual ultrasonic data.

[0100] Optionally, in one embodiment of this application, the acquisition module 100 includes a detection unit and a repair unit.

[0101] The detection unit is used to detect whether the actual ultrasonic data meets the preset data conditions.

[0102] The repair unit is used to generate repair instructions for the actual ultrasonic data according to the preset data conditions when the actual ultrasonic data does not meet the preset data conditions, and repair the actual ultrasonic data according to the repair instructions until the actual ultrasonic data that meets the preset data conditions is obtained.

[0103] It should be noted that the explanation of the above-mentioned method for calculating the thickness of the boiler oxide layer also applies to the calculation device for the thickness of the boiler oxide layer in this embodiment, and will not be repeated here.

[0104] The boiler oxide layer thickness calculation device proposed in this application can collect actual ultrasonic data of the oxide layer to be measured in the boiler and the actual operating data of the boiler. It extracts signals from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal characteristics. These characteristics and the actual operating data are then input into a pre-trained oxide thickness calculation model to obtain the initial thickness value and thickness correction coefficient of the oxide layer to be measured, ultimately yielding the final thickness value. This device fully exploits the nonlinear relationship between the ultrasonic echo signal and the oxide thickness. Furthermore, through operating parameter correction and abnormal signal processing, it significantly improves the accuracy and efficiency of oxide thickness calculation. It is easy to operate, has a wide range of applications, and provides a reliable basis for the safe operation and maintenance of equipment. Therefore, it solves the problems in related technologies, such as offline sampling measurement methods causing damage to the reheater, long measurement cycles, and inability to reflect oxide layer thickness changes in real time, making it difficult to meet the requirements of high-precision measurement; and online non-destructive testing methods having high equipment requirements, high costs, and poor environmental adaptability, leading to large measurement errors.

[0105] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0106] When the processor 402 executes the program, it implements the method for calculating the boiler oxide layer thickness provided in the above embodiments.

[0107] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0108] The memory 401 is used to store computer programs that can run on the processor 402.

[0109] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0110] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0111] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0112] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0113] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for calculating the thickness of the boiler oxide layer.

[0114] This application also provides a computer program product, including a computer program that, when executed, implements the above-described method for calculating the thickness of the boiler oxide layer.

[0115] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0116] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0117] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0118] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting or otherwise processing as necessary, and then stored in computer memory.

[0119] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0120] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0122] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for calculating the thickness of the oxide layer in a boiler, characterized in that, Includes the following steps: Collect actual ultrasonic data of the oxide layer to be tested in the boiler and actual operating data of the boiler; Extract the time-domain and / or frequency-domain features from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal features; The actual ultrasonic echo signal characteristics and the actual operating data are input into a pre-trained oxide thickness calculation model. The initial thickness value of the oxide layer to be tested and the thickness correction coefficient of the oxide layer to be tested are calculated using the oxide thickness calculation model. The initial thickness value is then corrected according to the thickness correction coefficient to obtain the final thickness value of the oxide layer to be tested.

2. The method according to claim 1, characterized in that, Before inputting the actual ultrasonic echo signal characteristics into the pre-trained oxide thickness calculation model, the following steps are also included: Ultrasonic data of the target oxide layer to be tested in the target boiler and the operating data of the target boiler are collected, and the actual thickness value of the target oxide layer to be tested is obtained. Extract the time-domain and / or frequency-domain features from the ultrasonic data to obtain the corresponding ultrasonic echo signal features; Based on the characteristics of the ultrasonic echo signal and the actual thickness value, the network structure, network parameters, training parameters, and validation function of the oxidation thickness calculation model are determined to construct the oxidation thickness calculation model.

3. The method according to claim 2, characterized in that, The process of determining the network structure, network parameters, training parameters, and validation function of the oxidation thickness calculation model based on the characteristics of the ultrasonic echo signal and the actual thickness value, in order to construct the oxidation thickness calculation model, includes: The ultrasonic echo signal features are input into an initial oxide thickness calculation model using the network structure and the network parameters, so as to calculate the predicted thickness value of the target oxide layer using the initial oxide thickness calculation model. Calculate the difference between the predicted thickness value and the actual thickness value; Based on the training parameters and the verification function, the initial oxidation thickness calculation model is trained and verified until the difference is less than a preset threshold, so as to obtain a trained oxidation thickness calculation model.

4. The method according to claim 1, characterized in that, The acquisition of actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler includes: Based on the actual operating data, the temperature data of the boiler is obtained; Based on the temperature data, a correction value for the actual ultrasonic data is determined, and the actual ultrasonic data is corrected according to the correction value to obtain the corrected actual ultrasonic data.

5. The method according to claim 1, characterized in that, The acquisition of actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler includes: Detect whether the actual ultrasonic data meets the preset data conditions; If the actual ultrasonic data does not meet the preset data conditions, a repair instruction for the actual ultrasonic data is generated according to the preset data conditions, and the actual ultrasonic data is repaired according to the repair instruction until actual ultrasonic data that meets the preset data conditions is obtained.

6. A device for calculating the thickness of a boiler oxide layer, characterized in that, include: The acquisition module is used to acquire the actual ultrasonic data of the oxide layer to be tested in the boiler and the actual operating data of the boiler. The extraction module is used to extract the time-domain features and / or frequency-domain features from the actual ultrasonic data to obtain the corresponding actual ultrasonic echo signal features. The calculation module is used to input the actual ultrasonic echo signal characteristics and the actual operating data into a pre-trained oxide thickness calculation model, and to calculate the initial thickness value of the oxide layer to be tested and the thickness correction coefficient of the oxide layer to be tested using the oxide thickness calculation model, and to correct the initial thickness value according to the thickness correction coefficient to obtain the final thickness value of the oxide layer to be tested.

7. The apparatus according to claim 6, characterized in that, Also includes: The acquisition module is used to collect ultrasonic data of the target oxide layer to be tested in the target boiler and the operating data of the target boiler before inputting the actual ultrasonic echo signal characteristics into the pre-trained oxide thickness calculation model, and to obtain the actual thickness value of the target oxide layer to be tested. A generation module is used to extract time-domain and / or frequency-domain features from the ultrasonic data to obtain the corresponding ultrasonic echo signal features. A construction module is used to determine the network structure, network parameters, training parameters, and validation function of the oxidation thickness calculation model based on the characteristics of the ultrasonic echo signal and the actual thickness value, so as to construct the oxidation thickness calculation model.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the method for calculating boiler oxide layer thickness as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the method for calculating the thickness of the boiler oxide layer as described in any one of claims 1-5.

10. A computer program product, characterized in that, Includes a computer program, which, when executed, is used to implement the method for calculating the boiler oxide layer thickness as described in any one of claims 1-5.

Images