An online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic sensing.

Abstract

This invention discloses an online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing. It includes a sensing fiber optic module, a demodulation module, an acoustic wave signal reconstruction module, a feature selection and extraction module, and a monitoring and classification module. The sensing fiber optic module collects optical signals carrying acoustic wave information during gas-liquid transport and sends them to the demodulation module. The demodulation module converts the optical signals into electrical signals and demodulates the phase signal, which is linearly related to the acoustic wave signal. The acoustic wave signal reconstruction module decomposes the phase signal into several intrinsic mode components, selects highly correlated components, and superimposes them to obtain a denoised and reconstructed acoustic wave signal. The feature selection and extraction module selects discriminative features from the denoised and reconstructed acoustic wave signal to construct a feature matrix. The monitoring and classification module monitors the internal state of the petrochemical reactor based on the feature matrix. This invention achieves real-time monitoring of the internal state of a petrochemical reactor, providing a precise basis for its maintenance.

Description

Technical Field

[0001] This invention relates to an online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing. Background Technology

[0002] In the petroleum refining process, the internal temperature and pressure of the reactor, a key piece of equipment, directly determine the catalytic efficiency of the catalyst, thus affecting the efficiency and quality of petroleum production. Petrochemical reactors are prone to problems such as excessively high temperatures and pressures during production cycles, posing significant safety hazards. Currently, domestic and international petrochemical companies mainly use various mechanical instruments and electrical sensing systems to monitor the internal conditions of petrochemical reactors. Mechanical instrument monitoring relies primarily on manual inspection, but manual inspection is time-consuming, labor-intensive, has a limited monitoring range, and is prone to oversights. Electrical sensing systems have inherent deficiencies in explosion-proof and electromagnetic interference resistance. When these systems are subjected to electromagnetic interference, the signal-to-noise ratio decreases, reducing the accuracy of monitoring and classification. Therefore, the use of such sensing systems in the petrochemical industry is significantly limited. Summary of the Invention

[0003] The purpose of this invention is to provide an online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic sensing, in order to solve the technical problems of monitoring the internal state of the petrochemical reactor, providing accurate data for the maintenance of the petrochemical reactor, and ensuring the personal safety of workers and the safety of equipment.

[0004] To achieve the above-mentioned objectives, the present invention adopts the following technical solution:

[0005] An online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing includes a sensing fiber, a demodulation module, an acoustic wave signal reconstruction module, a feature selection and extraction module, and a monitoring and classification module.

[0006] The sensing optical fiber is used to collect optical signals carrying acoustic wave information during gas-liquid transportation and send them to the demodulation module.

[0007] The demodulation module is used to convert the optical signal into an electrical signal and demodulate the phase signal that is linearly related to the sound wave signal.

[0008] The acoustic signal reconstruction module is used to decompose the phase signal into several intrinsic mode components. By calculating the correlation coefficient between the optical signal and several intrinsic mode components, the components with larger correlation coefficients have higher correlation. The components with high correlation are selected and superimposed to obtain the denoised and reconstructed acoustic signal.

[0009] The feature selection and extraction module is used to select discriminative features from the denoised and reconstructed acoustic signal to form a feature matrix. By calculating the KL distance between each feature of the original signal and the denoised and reconstructed acoustic signal, which measures the difference between two probability distributions in the same event space, the larger the KL distance, the greater the feature difference, and thus the more discriminative the feature is.

[0010] The monitoring and classification module monitors the internal state of the petrochemical reactor based on a feature matrix.

[0011] According to the above scheme, the online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing is a fiber optic sensing fiber encapsulated within an optical cable and etched with an identical weak grating array.

[0012] According to the above scheme, in the online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, the acoustic wave sensing fiber is spirally wound along the pipeline axis on the outer wall of all pipelines to achieve distributed online monitoring.

[0013] According to the above scheme, the fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor includes a demodulation module based on optical time-domain reflectometry. The distributed acoustic sensing demodulation unit (DAS) includes a light source, an acousto-optic modulator (AOM), an erbium-doped fiber amplifier (EDFA), a circulator, a Michelson interferometer, a Faraday rotator, a 3×3 coupler, a photodetector (PD), and a high-speed acquisition and processing module.

[0014] According to the above scheme, in the online monitoring system for fiber optic acoustic wave sensing of the internal state of a petrochemical reactor, the light signal emitted by the light source is modulated by an acousto-optic modulator (AOM) and amplified by an erbium-doped fiber amplifier (EDFA) to form pulsed light that enters the sensing fiber.

[0015] According to the above scheme, in the online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, the light reflected from two adjacent gratings in the sensing fiber optic weak grating array is reflected by a Faraday rotating mirror after passing through the two arms of a Michelson interferometer, and then interferes at a 3×3 coupler. The distance between the two arms of the Michelson interferometer is the same as the distance between two adjacent gratings in the weak grating array.

[0016] According to the above scheme, in the online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, the 3×3 coupler outputs three optical signals with a phase difference of 2π / 3, which are then converted into electrical signals by three photodetectors (PDs).

[0017] According to the above scheme, in the online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, the high-speed acquisition and processing module acquires three signals and uses an arctangent algorithm to calculate a phase signal that is linearly related to the acoustic wave signal.

[0018] According to the above scheme, the optical fiber acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor includes an acoustic wave signal reconstruction module comprising a signal decomposition module and a signal superposition module.

[0019] According to the above scheme, in the online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic sensing, the signal decomposition module preprocesses the phase signal, including pre-emphasis, framing, and windowing. The preprocessed signal is then decomposed into several intrinsic mode components using Complete EEMD with Adaptive Noise.

[0020] According to the above scheme, in the online monitoring system for fiber optic acoustic wave sensing of the internal state of a petrochemical reactor, the signal superposition module uses correlation coefficient analysis to analyze the correlation between the intrinsic mode components and the preprocessed signal, selects the intrinsic mode components with high correlation for superposition, thereby removing high-frequency noise and obtaining a denoised and reconstructed acoustic wave signal.

[0021] According to the above scheme, in the online monitoring system for fiber optic acoustic wave sensing of the internal state of a petrochemical reactor, the feature selection and extraction module uses the Kullback-Leibler (KL) distance method to exclude irrelevant or redundant features from the time-domain features, frequency-domain features and spectral density index of the denoised and reconstructed acoustic wave signal, selects discriminative features, and combines them with Mel-frequency cepstral coefficients (MFCC) to form a feature matrix.

[0022] According to the above scheme, the online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, wherein the monitoring and classification module, based on a normalized feature matrix, employs a random forest classifier from machine learning to monitor and classify pipeline leaks.

[0023] The present invention has the following advantages and positive effects:

[0024] 1. This invention uses an acoustic wave sensing fiber with an identical weak grating array engraved inside the optical cable as a sensor. It has the characteristics of anti-electromagnetic interference, anti-corrosion, high temperature resistance, and intrinsic explosion-proof, and realizes the acquisition of acoustic wave signals of the internal state of petrochemical reactors in harsh environments.

[0025] 2. This invention employs optical time-domain reflectometry (OTDR) technology. The distributed acoustic wave sensing demodulation unit demodulates the acoustic wave signal. The demodulation unit has high positioning accuracy and fast response speed.

[0026] 3. This invention uses Complete Empirical Mode Decomposition with Adaptive Noise (EEMD) and correlation coefficient analysis to reconstruct the acoustic signal, thereby removing high-frequency noise and improving the signal-to-noise ratio of the system.

[0027] 4. This invention uses the Kullback-Leibler (KL) distance method to exclude irrelevant or redundant acoustic signal features and selects discriminative acoustic signal features, making it easier for the random forest classifier to identify acoustic signal features and improving the system's classification accuracy.

[0028] 5. This invention successfully solves the problems of excessive pressure or temperature in existing petrochemical reactor internal condition monitoring methods, realizes real-time monitoring of the internal condition of petrochemical reactors, provides accurate basis for the maintenance of petrochemical reactors, and avoids major safety accidents caused by overload of petrochemical reactors. Attached Figure Description

[0029] Figure 1 This is a schematic diagram of an online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, as proposed in an embodiment of the present invention.

[0030] Figure 2 This invention presents a method based on optical temporal reflectance. Schematic diagram of a distributed acoustic wave sensing demodulation unit (DAS);

[0031] Figure 3 This is a schematic diagram of an acoustic signal reconstruction process based on Complete EEMD with Adaptive Noise proposed in an embodiment of the present invention.

[0032] Figure 4 This is a schematic diagram of a feature selection and extraction process based on the Kullback-Leibler (KL) distance method proposed in an embodiment of the present invention. Detailed Implementation

[0033] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0034] Figure 1 An online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, as proposed in this embodiment of the invention, is provided. Figure 1 As shown, it specifically includes the following modules: sensing fiber, demodulation module, acoustic signal reconstruction module, feature selection and extraction module, and monitoring and classification module.

[0035] In this embodiment of the invention, the sensing optical fiber is used to collect optical signals of acoustic wave information inside the petrochemical reactor, as detailed below:

[0036] The sensing fiber uses an acoustic wave sensing fiber etched with an identical weak grating array, which can greatly increase the number of sensors reused in the system and realize real-time monitoring of the internal state of the petrochemical reactor.

[0037] In this embodiment of the invention, the demodulation module is used to convert the optical signal into an electrical signal and demodulate a phase signal that is linearly related to the sound wave signal, as follows:

[0038] like Figure 2 As shown, the light source in the demodulation module emits an optical signal, which is modulated into an optical pulse signal by an acousto-optic modulator (AOM). After being amplified by an erbium-doped fiber amplifier (EDFA), the signal enters the sensing fiber through circulator 1. The light reflected from two adjacent gratings in the weak grating array of the sensing fiber is amplified by the EDFA, then filtered by a bandpass filter to remove noise from the EDFA. The light is then reflected by the two arms of a Michelson interferometer and a Faraday rotator mirror to a 3×3 coupler where interference occurs. The distance between the two arms of the Michelson interferometer is the same as the distance between two adjacent gratings in the weak grating array. The 3×3 coupler outputs three optical signals with a phase difference of 2π / 3, which are converted into electrical signals by three photodetectors (PDs). The high-speed acquisition and processing module acquires these three electrical signals and uses an arctangent algorithm to calculate the phase signal, which is linearly related to the acoustic signal.

[0039] In this embodiment of the invention, the acoustic signal reconstruction module is used to decompose the phase signal into several intrinsic mode components, select highly correlated components for superposition, and obtain a denoised and reconstructed acoustic signal, as follows:

[0040] The acoustic signal reconstruction module is divided into a signal decomposition module and a signal superposition module. For example... Figure 3 As shown, the signal decomposition module first pre-emphasizes, frames, and windowes the phase signal from the demodulation module. The preprocessed signal is then decomposed into several intrinsic mode components (EMS) using Complete EEMD with Adaptive Noise. The signal superposition module analyzes the correlation between the EMS and the preprocessed signal using correlation coefficients, selects EMS with high correlation for superposition, thereby removing high-frequency noise and obtaining a denoised and reconstructed acoustic signal.

[0041] In this embodiment of the invention, the feature selection and extraction module is used to select discriminative features from the denoised and reconstructed acoustic signal to form a feature matrix, as follows:

[0042] like Figure 4As shown, the Kullback-Leibler (KL) distance measures the difference between two probability distribution functions, reducing feature dimensionality. A Kullback-Leibler (KL) distance d of 0 indicates that the two features have the same distribution or are completely redundant. The larger the distance, the stronger the discriminative power of the feature. Using the Kullback-Leibler (KL) distance method, irrelevant or redundant features are eliminated from the time-domain, frequency-domain, and spectral density indices of the denoised and reconstructed acoustic signal. Discriminative features are selected and combined with Mel-frequency cepstral coefficients (MFCCs) to form a feature matrix, improving the classification accuracy.

[0043] In this embodiment of the invention, the monitoring and classification module uses a random forest classifier in machine learning based on a normalized feature matrix to monitor the internal state of the petrochemical reactor and displays the monitoring results in real time on the host computer.

[0044] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. An online monitoring system for the internal state of a petrochemical reactor using fiber optic acoustic wave sensing, comprising a sensing fiber, a demodulation module, an acoustic wave signal reconstruction module, a feature selection and extraction module, and a monitoring and classification module, characterized in that: The sensing optical fiber is used to collect optical signals carrying acoustic wave information during gas-liquid transportation and send them to the demodulation module. The demodulation module is used to convert the optical signal into an electrical signal and demodulate the phase signal that is linearly related to the sound wave signal. The acoustic signal reconstruction module is used to decompose the phase signal into several intrinsic mode components. By calculating the correlation coefficient between the optical signal and several intrinsic mode components, the components with larger correlation coefficients have higher correlation. The components with high correlation are selected and superimposed to obtain the denoised and reconstructed acoustic signal. The feature selection and extraction module is used to select discriminative features from the denoised and reconstructed acoustic signal to form a feature matrix. By calculating the KL distance between each feature of the original signal and the denoised and reconstructed acoustic signal, the difference between two probability distributions in the same event space is measured. The larger the KL distance, the greater the feature difference, which means that the feature is discriminative. The monitoring and classification module monitors the internal state of the petrochemical reactor based on a feature matrix. The sensing fiber is encapsulated within an optical cable and has an identical weak grating array etched on it. The demodulation module is based on optical time-domain reflectometry. - The OTDR's Distributed Acoustic Sensing Demodulation Unit (DAS) includes a light source, an acousto-optic modulator (AOM), an erbium-doped fiber amplifier (EDFA), a circulator, a Michelson interferometer, a Faraday rotator, a 3×3 coupler, a photodetector (PD), and a high-speed acquisition and processing module.

2. The fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor according to claim 1, characterized in that: The sensing optical fiber is spirally wound along the pipe axis on the outer wall of all pipes to achieve distributed online monitoring.

3. The fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor according to claim 1, characterized in that: The light signal emitted by the light source is modulated by an acousto-optic modulator (AOM) and amplified by an erbium-doped fiber amplifier (EDFA) to form pulsed light that enters the sensing fiber. The light reflected from two adjacent gratings in the identical weak grating array of the sensing fiber passes through the arms of a Michelson interferometer and is reflected by a Faraday rotating mirror to a 3×3 coupler where interference occurs. The distance between the arms of the Michelson interferometer is the same as the distance between two adjacent gratings in the weak grating array. The 3×3 coupler outputs three optical signals with a phase difference of 2π / 3, which are converted into electrical signals by three photodetectors (PDs). The high-speed acquisition and processing module acquires the three signals and uses an arctangent algorithm to calculate the phase signal that is linearly related to the acoustic signal.

4. The fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor according to claim 1, characterized in that: The acoustic signal reconstruction module includes a signal decomposition module and a signal superposition module.

5. The fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor according to claim 4, characterized in that: The signal decomposition module preprocesses the phase signal, including pre-emphasis, frame segmentation, and windowing; the preprocessed signal is decomposed into several intrinsic mode components by Complete EEMD with Adaptive Noise.

6. The fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor according to claim 4, characterized in that: The signal superposition module uses correlation coefficient analysis to determine the correlation between the intrinsic mode components and the preprocessed signal, and selects the intrinsic mode components with high correlation for superposition, thereby removing high-frequency noise and obtaining a denoised and reconstructed acoustic signal.

7. The fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor according to claim 1, characterized in that: The feature selection and extraction module uses the Kullback-Leibler distance method to exclude irrelevant or redundant features from the time-domain features, frequency-domain features, and spectral density index of the denoised and reconstructed acoustic signal, and selects discriminative features, which are then combined with Mel-frequency cepstral coefficients (MFCC) to form a feature matrix.

8. The fiber optic acoustic wave sensing online monitoring system for the internal state of a petrochemical reactor according to claim 1, characterized in that: The monitoring and classification module uses a random forest classifier from machine learning, based on a normalized feature matrix, to monitor and classify pipeline leaks.

Images