Acoustic emission-based graph learning for internal valve leakage localisation in offshore pipelines

Internal valve leakage in a natural gas pipeline not only brings huge economic losses to the petroleum enterprises, but also causes immeasurable environmental pollution. Therefore, the diagnosis of internal valve leakage and the prediction of leakage rates are the basis to ensure the safe operation of natural gas pipeline. In this paper, based on acoustic emission detection system, the internal valve leakage signals were collected, which were analyzed and processed to diagnose the internal valve leakage and predict the leakage rates. Due to the complex work environment and serious noise interference, the collected acoustic emission signals contain a large amount of environmental noise. Therefore, singular spectrum analysis was proposed to reduce the environmental noise in acoustic emission signals. Radial basis function neural network was used to predict the leakage rates. Experimental results demonstrate that pure internal leakage source signals can be obtained via singular spectrum analysis. The prediction accuracy of leakage rates based on the characteristic parameters of pure AE signals is better than the accuracy without signals denoising. Therefore, singular spectrum analysis is an effective denoising method for acoustic emission signals, which can improve the prediction accuracy of internal valve leakage rate.

Prediction method of ball valve internal leakage rate based on acoustic emission technology

Valve internal leakage is easily found because of various defects resulting from environmental factors and load fluctuation. The timely detection of valve internal leakage is of great significance to the safe operation of pipelines. As an effective means for detecting valve internal leakage, the acoustic emission technique is characterized by nonintrusive and strong anti-interference ability, which can realize the in situ monitoring of the valve running status in real time. In this paper, acoustic emission signals from an internal leaking valve were obtained experimentally. Then, the dimensionality reduction technology based on factor analysis was introduced to the processing of valve internal leakage detection data. Next, the wavelet decomposition was carried out to decompose the sample feature set into four subsets. Finally, the decomposed sample feature sets were inputted into the error backpropagation (BP) neural network quantitative model, respectively. The optimized results show that the predicted internal leakage rate by the wavelet-BP neural network model has good precision with an error of less than 10%. The wavelet-BP neural network model can realize the analysis of the valve internal leakage rate quantitatively and has good robustness, which provides technical support and guarantees the safe operation of natural gas pipeline valves.

Theoretical analysis and experimental data show that the acoustic emission (AE) technology can detect the internal leakage state of the valve online. One of its key technologies is to determine the relationship between the characteristic of valve internal leakage AE signal (VILAES) and leakage rate and various parameters. However, most of the currently established models are a single‐variable model. In addition, the repeated and verification experiments are rarely introduced, and most experiments are conducted under a large leakage rate. To this end, the mixed multiple‐variable model is built to describe the relationship between the characteristics of VILAES and leakage rates, pressures, valve calibres and flow coefficients for the same type of valve. In the experiments, two rounds of experiments were performed for the same valve; then, a round of experiments was carried out after moving the sensor, and two rounds of experiments were conducted for two valves with the same parameters. In modelling, the VILAES is filtered first, and then the characteristics of the filtered signal are calculated. The mixed multiple‐variable model is established by the least‐squares support vector machine. The results show that the mixed multiple‐ variable model could realise online internal leakage for valves with different calibres and flow coefficients under different pressures.

In modern industry, the spring full-lift safety valve is a key device for safe pressure relief of pressure-bearing systems. Its valve seat sealing surface is easily damaged after long-term use, causing internal leakage, resulting in safety hazards and economic losses. Therefore, it is of great significance to quickly and accurately diagnose its internal leakage state. Among the current methods for identifying fluid machinery faults, model-based methods have difficulties in parameter determination. Although the data-driven convolutional neural network (CNN) has great potential in the field of fault diagnosis, it has problems such as hyperparameter selection relying on experience, insufficient capture of time series and multi-scale features, and lack of research on valve internal leakage type identification. To this end, this study proposes a safety valve internal leakage identification method based on high-frequency FPGA data acquisition and improved CNN. The acoustic emission signals of different internal leakage states are obtained through the high-frequency FPGA acquisition system, and the two-dimensional time–frequency diagram is obtained by short-time Fourier transform and input into the improved model. The model uses the leaky rectified linear unit (LReLU) activation function to enhance nonlinear expression, introduces random pooling to prevent overfitting, optimizes hyperparameters with the help of horned lizard optimization algorithm (HLOA), and integrates the bidirectional gated recurrent unit (BiGRU) and selective kernel attention module (SKAM) to enhance temporal feature extraction and multi-scale feature capture. Experiments show that the average recognition accuracy of the model for the internal leakage state of the safety valve is 99.7%, which is better than the comparison model such as ResNet-18. This method provides an effective solution for the diagnosis of internal leakage of safety valves, and the signal conversion method can be extended to the fault diagnosis of other mechanical equipment. In the future, we will explore the fusion of lightweight networks and multi-source data to improve real-time and robustness.

This paper summarizes leak detection technologies available for use on subseapipelines and the potential role of fiber optic cable (FOC) integritymonitoring systems to improve leak detection capabilities. Available systemswhich monitor offshore pipelines for potential leaks based on internalflowrates and pressures are described along with their limitations for rapidlydetecting small leaks. Alternative pipeline leak detection technologies whichhave been used on some specialized subsea pipeline projects to supplement thecapabilities of these flow-based systems are also described along with theirlimitations. The potential for modern FOC distributed sensing technologies tofill the remaining leak detection capability gaps is then addressed. There is increased interest in improving leak detection system capabilitiesthroughout the pipeline industry. However, the primary application of thispaper is for offshore pipeline projects which may not be adequately covered byconventional flow-based leak detection systems and supplemental monitoring forpotential oil sheens visible on the sea surface. These applications includedeep water pipelines, where potential oil leaks may not reach the surface untilmiles away from the source, and subsea arctic pipelines, which could slowlylose significant oil volumes under the cover of winter sea ice. Other potentialapplications include subsea field developments and pipelines installed inunusually sensitive marine environments. Distributed FOC sensor systems can monitor real-time temperature, acousticnoise/vibration and strain along many miles of pipeline. Changes in any one ofthese monitored parameters can indicate a leak event or other potentialintegrity threats to a pipeline. An overview of FOC systems already installedon offshore pipeline projects and the current testing status of FOC systems forpipeline leak detection are provided. Recommendations for installation andimplementation of the available FOC technologies for subsea pipeline leakdetection are summarized. The limited applications of distributed fiber optic cable (FOC) monitoringsystems on subsea pipelines have not yet been used specifically for leakdetection purposes. The leak detection thresholds defined for FOC systems andthe procedures for design, installation and system repair will facilitate theuse of FOC systems to help ensure leak free pipeline operations. Introduction Internal leak detection systems have historically been used for permanentlyinstalled, long-term leak detection monitoring of subsea pipelines. Thesesystems monitor internal parameters, such as internal pressures and/orflowrates based on internal pressure, temperature, density, and/or flowrateinstrument measurements. Discrepancies between the measured parameters and theoperating trends or calculated operating predictions are used to alert thepipeline operator of a potential leak event. However, the instruments aretypically located only at the ends of a pipeline segment, remote from an actualleak location. This has some effect on sensitivity. Instrument inaccuraciesalso introduce error in the measured parameters. Selecting the alarm settingsof these internal type leak detection systems for very small leaks may resultin an unacceptable number of false alarms (nuisance alarms) due to theirachievable sensitivity and this inherent error. Therefore, alarm settings forthese systems are set-high enough (for large enough leaks) to minimize falsealarms. Leaks that are smaller than the alarm settings (minimum leak detectionthresholds) may continue undetected by these systems. Periodic over-flights orvessel observations from areas with subsea pipelines are then relied upon toobserve oil sheens from potential leaks that fall below a system's minimumdetection threshold. A chronic leak from a deep-water pipeline may manifest as an oil sheen on thewater surface miles away from the leak source due to currents. There may be atime delay in determining the source of the oil sheen, especially if multiplepipelines are located near the observed oil sheen or if there are local subseafield developments.

This paper researched gate valve gas internal leakage acoustic emission characteristics under the operating conditions of different pressure, internal leakage rate and internal leakage size. Firstly, introduced structure of gate valve, the main reasons of internal leakage and acoustic emission detect technology. Then, established gate valve internal leakage experiment system, to realize the internal leakage under the operating conditions of different pressure, internal leakage rate and internal leakage size. Finally, on this basis, with acoustic emission non-destructive detection theory, put forward gate valve internal leakage AE detect experiment under variety operating conditions, analyzed and compared internal leakage AE characteristics under different operating conditions, such as pressure differences between 0.1MPa and 0.2MPa, internal leakage rate between 0L\min and 80L\min, internal leakage size between 0.5mm and 1.5mmm. The research results show that gate valve internal leakage can be represented by AE signal amplitude, ASL and energy. The three parameters may have linear variation or index movement under different operating conditions. The internal leakage AE parameters change slowly while internal leakage size is greater than a threshold value. These results can supply reference for gate valve internal leakage online detection and fault diagnosis in the petrochemical plant.

The performance of steam traps plays an important role in the normal operation of steam systems. It also contributes to the improvement of thermal efficiency of steam-using equipment and the rational use of energy. As an important component of the steam system, it is crucial to monitor the state of the steam trap and establish a correlation between the acoustic emission signal and the internal leakage state. However, in actual test environments, the acoustic emission sensor often collects various background noises alongside the valve internal leakage acoustic emission signal. Therefore, to minimize the impact of environmental noise on valve internal leakage identification, it is necessary to preprocess the original acoustic emission signals through noise reduction before identification. To address the above problems, a denoising method based on a sparrow search algorithm, variational modal decomposition, and improved wavelet thresholding is proposed. The sparrow search algorithm, using minimum envelope entropy as the fitness function, optimizes the decomposition level K and the penalty factor α of the variational modal decomposition algorithm. This removes modes with higher entropy in the modal envelopes. Subsequently, wavelet threshold denoising is applied to the remaining modes, and the denoised signal is reconstructed. Validation analysis demonstrates that the combination of SSA-VMD and the improved wavelet threshold function effectively filters out noise from the signal. Compared to traditional thresholding methods, this approach increases the signal-to-noise ratio and reduces the root-mean-square error, significantly enhancing the noise reduction effect on the steam trap's background noise signal.

Convolutional neural networks-based valve internal leakage recognition model

The monograph is devoted to the actual and practically important scientific and technical problem of non-contact diagnostic examinations of underground (and underwater) pipelines (UP) and other current-carrying communications. The results of theoretical and experimental studies and scientific and technical approaches to the development of new methods and devices for non-contact current measurements (NCM) and their applications for UP diagnosis are presented. The main stages of the development of contact and non-contact methods of measuring currents without breaking an electric circuit are described. Non-contact electromagnetic (EM) examination methods have significant advantages over known contact electrometric methods in terms of efficiency and informativeness. But they needed more advanced methods and appropriate special equipment. For their creation at the Physical and Mechanical Institute named after G. V. Karpenko of the National Academy of Sciences of Ukraine carried out a complex of research works and technical developments: the informative signs of the EM field of UP and their connections with the parameters of the structure were investigated; the measured characteristics of the field were selected and the algorithms for determining the parameters of the control object were established; appropriate NCM tools were developed and a new method of UP examinations was tested in real-world conditions; algorithms and recommendations for the interpretation of measured information and a new technology of diagnostic examinations and testing of the technical condition of anti-corrosion protection of UP according to NCM have been developed. The monograph consistently sets out the theoretical justification of the NCM method with a description of the proposed new methods and devices and the characteristics of the developed hardware and the results of field tests and practical use. The main stages of the development of the theory of electric currents and methods of their measurement are briefly described. The theory of the EM field of UP, informative features of the magnetic field of currents is described. NCM methods and devices, EM method and means, and the information and measurement system of UP diagnostic examinations are described. Examples of the use of NCM are given. The theoretical basis of NCM methods is the proposed triune mathematical model (TUMM) of the EM field of UP, which is based on the solutions of boundary value problems of electrodynamics, the theory of electric circuits with distributed parameters and the theory of spatial distribution of current fields. Informative features of the EM field of UP and anomalies of its distribution were studied. New methods of gradient, parallax and invariant NCM UP, new NCM methods and devices are proposed, and their classification and areas of rational application are given. The technical characteristics of new effective devices created at the PMI of the National Academy of Sciences of Ukraine for UP examinations are given. As a result of their hardware implementation, a method and means of monitoring and a new technology of surveys of the state of anti-corrosion protection of anti-corrosion protection of UP according to NCM have been developed. The results of their field tests and practical use on main pipeline routes and pipeline networks that transport gas, oil, water, and chemical industry products are given. The experience of practical use of NCM for integral, differential and local diagnostic examinations and control of the condition of insulating coatings and electrochemical protection against corrosion of UP and related metal structures is described and analyzed. It is shown that NCM provides the possibility of quantitative estimations of the “pipe-ground” transition resistance and its components – ground, insulation and polarization resistances. According to NCM, it is also possible to determine the specific resistance of the insulating coating in different sections of the UP with a resolution up to the length of the UP section commensurate with the depth of its occurrence. NCM detect the places of UP insulation damage and the most probable places of corrosion. The use of NCM makes it possible not only to increase the efficiency and informativeness of diagnostic examinations, but also to reduce labor costs. The monograph is intended and will be useful for scientists, specialists and students in the fields of information and measurement systems, electrodynamics, non-destructive testing and technical diagnostics, anti-corrosion protection, inspections and operation of pipelines and related underground metal structures.

A novel acoustic emission detection module for leakage recognition in a gas pipeline valve

Deep belief network-based internal valve leakage rate prediction approach

Accurately localizing the source of early structural damage on wind turbine blades poses a challenge for constructing acoustic emission (AE) based structural health monitoring (SHM) systems. Existing damage localization methods struggle to extract and utilize the intricate connections inherent in the AE signals. A novel method for localizing structural damage zone on wind turbine blades based on AE and graph neural networks (GNN) is proposed in this paper. First, the AE signals are converted into graph structure data in non-Euclidean space combined with time-frequency analysis. Then, the Euclidean distance between the features of each pair of nodes is calculated to determine the connectivity of the graph. The information of the neighboring nodes in the graph is aggregated using the message passing paradigm, which can not only make effective use of the node features, but also excavate the deeper intrinsic connection of the AE signals. The proposed method can easily localize structural damage on wind turbine blades with the assistance of the established graph. Another novelty of the proposed method is its ability to locate damage for wind turbine blade with high accuracy using only one AE sensor. This not only simplifies the sensor setup but also leads to significant cost reduction. The effectiveness of the proposed method is validated using an experimental dataset collected from a segment of a wind turbine blade. The results demonstrate the superior performance and high accuracy of the proposed method.

This study presents an experimental analysis of high-pressure liquid and gas gate valve leakage under multiple operating conditions, based on the variation patterns of ultrasonic signals. Focusing on a multi-physics field analysis of gate valve internal leakage and corresponding experiments, this research illustrates the acoustic wave characteristics of gate valves across diverse working media, pressures, internal leakage defect sizes, and valve diameters. By drawing upon both fluid mechanics and acoustics theory, an analytical approach suited to high-pressure gate valve leakage issues is devised. Separate high-pressure gate valve leakage test platforms for liquid and gas environments were designed and constructed, enabling 126 groups of tests under varying conditions, which include one measurement per condition of the valve size, defect size, and pressure value. These experiments examine the quantitative correlation of internal leakage flow rates and ultrasonic signal measurements under different situations. In addition, the distinct behaviors and principles exhibited by high-pressure liquid gate valves and gas gate valves are compared. The findings provide theoretical and technical support for quantifying high-pressure gate valve leakage. The study analyzes the theoretical basis for the generation of ultrasonic signals from valve internal leakage, providing specific experimental data under various operating conditions. It explains the various observations during the experiments and their principles. The conclusions of this research have practical engineering value and provide important references for future studies.

Internal leakage within the valve body constitutes a severe potential safety hazard in industrial fluid control systems, attributable to its high concealment and the resultant difficulty in detection via conventional methodologies. Acoustic emission (AE) technology, functioning as an efficient non-destructive testing approach, is capable of capturing the transient stress waves induced by leakage, thereby furnishing an effective means for the real-time monitoring and quantitative assessment of internal leakage within the valve body. This paper conducts a systematic review of the theoretical foundations, signal-processing methodologies, and the latest research advancements related to the technology for detecting internal leakage in the valve body based on acoustic emission. Firstly, grounded in Lechlier’s acoustic analogy theory, the generation mechanism of acoustic emission signals arising from valve body leakage is elucidated. Secondly, a detailed analysis is conducted on diverse signal processing techniques and their corresponding optimization strategies, encompassing parameter analysis, time–frequency analysis, nonlinear dynamics methods, and intelligent algorithms. Moreover, this paper recapitulates the current challenges encountered by this technology and delineates future research orientations, such as the fusion of multi-modal sensors, the deployment of lightweight deep learning models, and integration with the Internet of Things. This study provides a systematic reference for the engineering application and theoretical development of the acoustic emission-based technology for detecting internal leakage in valves.