Converter station fire-fighting foam pipeline leakage point detection method and device

Abstract

The embodiment of the invention provides a converter station fire-fighting foam pipeline leakage point detection method and device, and the method comprises the steps: obtaining a first data set based on the fluid data collected by a collection point of a foam pipeline; based on the first data set and a preset fluid identification model, determining a fluid type which is Newtonian fluid or non-Newtonian fluid; and determining a leakage point identification result based on a leakage point identification model corresponding to the fluid type and the first data set. According to the invention, leakage in the foam pipeline can be rapidly and accurately detected.

Description

Technical Field

[0001] This invention relates to the field of fire protection technology for converter stations, specifically to a method and device for detecting leaks in fire-fighting foam pipelines in converter stations. Background Technology

[0002] Traditional pipeline inspection methods primarily rely on manual labor or hardware testing instruments to monitor pipe wall and surrounding environmental parameters to detect leaks. Common methods include manual leak detection, acoustic emission, thermal infrared imaging, and radioactive tracer leak detection. In recent years, with the development of computer technology, more leak detection methods utilize computer data acquisition systems to collect pipeline operating parameters in real time. These parameters are transmitted to a central controller, and specific algorithms are used to analyze and calculate the specific pipe where a leak has occurred. More complex algorithms can even diagnose the exact leak point. These methods can generally be categorized into three types: pipeline leak diagnosis methods based on mathematical models, signal processing, and artificial intelligence. Compared to the pressure and flow characteristics of water, it is evident that when the parameters of the fire water tank and pump are the same, the pressure and flow characteristics of the compressed-air foam (CAFS) fire suppression system in the converter station differ. Therefore, existing pipeline leak detection methods are difficult to directly apply to the pipelines of the CAFS in the converter station, and there is currently limited research on leak detection in CAFS pipelines. Summary of the Invention

[0003] This application provides a method and apparatus for detecting leaks in fire-fighting foam pipelines in converter stations, which can quickly detect leaks in foam pipelines.

[0004] In a first aspect, embodiments of this application propose a method for detecting leaks in fire-fighting foam pipelines in converter stations, including:

[0005] The first data set is obtained by collecting fluid data from the collection points of the foam pipe;

[0006] Based on the first data set and the preset fluid identification model, the fluid type is determined; the fluid type includes Newtonian fluid or non-Newtonian fluid.

[0007] Based on the leak identification model corresponding to the fluid type and the first data set, the leak identification result is determined.

[0008] Optionally, the fluid recognition model is a bidirectional long short-term memory network and a residual fully connected network model; the loss function of the residual fully connected network is:

[0009] L total =L data +L 正则化项 +L物理约束

[0010] Among them, L 正则化项 Used to reset weights unrelated to rheological properties to zero, L 物理约束 The viscosity gradient used to make the Newtonian fluid prediction result approach zero.

[0011] Optionally, based on the first data set and a preset fluid identification model, the fluid type in the fire-fighting foam pipe is determined, including:

[0012] When the output layer of the fluid recognition model outputs a fuzzy probability, perform any of the following judgments:

[0013] When the pipe frequency is greater than a preset frequency threshold, the fluid type is determined to be a Newtonian fluid;

[0014] When the flow rate in the pipeline is greater than the predicted value of a theoretical Newtonian fluid, the fluid type is determined to be a non-Newtonian fluid.

[0015] Among them, fuzzy probability representation cannot determine whether the fluid type is a Newtonian fluid or a non-Newtonian fluid.

[0016] Optionally, when the fluid type is a Newtonian fluid, determining the leak identification result based on the leak identification model corresponding to the fluid type and the first data set includes:

[0017] Based on the first data set, determine the second data set corresponding to the Newtonian fluid;

[0018] Based on the second data set and the first leak identification model corresponding to Newtonian fluid, the leak identification result is determined.

[0019] Optionally, the first data set includes: pressure gradient data, flow velocity profile data, shear rate-viscosity curves, temperature sensor data, and fluid density measurements; determining the second data set corresponding to the Newtonian fluid based on the first data set includes:

[0020] The pressure gradient variation coefficient is determined based on the pressure gradient data.

[0021] The mass flow rate deviation is determined based on the aforementioned velocity profile data;

[0022] The viscous dissipation power density is determined based on the shear rate-viscosity curve and temperature sensor data.

[0023] The dynamic characteristics of bulk modulus are determined based on fluid density measurements.

[0024] Optionally, after determining the leak identification result based on the second data set and the first leak identification model corresponding to Newtonian fluid, the method further includes:

[0025] The leak identification result is that when a leak occurs in the pipeline, the pipeline segment where the leak occurs is determined based on the collection point where the first deviation value is greater than the preset first threshold and the second deviation value is greater than the preset second threshold; wherein, the first deviation value is the difference between the pressure gradient variation coefficient corresponding to the collection point and the preset normal pressure gradient variation coefficient, and the second deviation value is the difference between the mass flow deviation corresponding to the collection point and the preset normal mass flow deviation.

[0026] Optionally, when the fluid type is a non-Newtonian fluid, determining the leak identification result based on the leak identification model corresponding to the fluid type and the first data set includes:

[0027] Based on the first data set, determine the third data set corresponding to the non-Newtonian fluid;

[0028] Based on the third data set and the second leak identification model corresponding to non-Newtonian fluids, the leak identification result is determined.

[0029] Optionally, the first data set includes: flow velocity profile data, shear rate-viscosity curves, temperature sensor data, and fluid density measurements; the step of determining the third data set corresponding to the Newtonian fluid based on the first data set includes:

[0030] Based on the shear rate-viscosity curve, determine the dynamic characteristics of shear rate-viscosity;

[0031] Determine the intensity of the secondary flow based on velocity profile data;

[0032] Based on shear rate-viscosity curves and temperature sensor data, the viscous dissipation power density and the corresponding associated temperature are determined.

[0033] Based on fluid density measurements, the dynamic characteristics of bulk modulus are determined.

[0034] Optionally, after determining the leak identification result based on the second leak identification model corresponding to the third data set and non-Newtonian fluids, the method further includes:

[0035] The leak identification result is determined when a leak occurs in the pipeline, based on the pressure gradient decrease value of the target pipe section being greater than the third threshold and the viscous dissipation power density increase value of the target pipe section being greater than the fourth threshold; wherein, the target pipe section is the pipe section between two adjacent collection points.

[0036] Secondly, embodiments of this application propose a leak detection device for fire-fighting foam pipelines in converter stations, comprising:

[0037] The data processing module is used to obtain the first data set based on the fluid data collected from the collection points of the fire foam pipeline;

[0038] A fluid type identification module is used to determine the fluid type based on the first data set and a preset fluid identification model; the fluid type includes Newtonian fluid or non-Newtonian fluid.

[0039] The leak detection module is used to determine the leak detection result based on the leak detection model corresponding to the fluid type and the first data set.

[0040] Thirdly, embodiments of this application propose a computer storage medium storing a computer program, which, when executed, implements the steps of the converter station fire-fighting foam pipeline leak detection method described in the first aspect above.

[0041] Fourthly, embodiments of this application propose a computer program product, which includes a computer program that, when executed, implements the steps of the converter station fire-fighting foam pipeline leak detection method described in the first aspect above.

[0042] The method and apparatus for detecting leaks in fire-fighting foam pipelines in converter stations, as described in this application, first obtain a first data set based on fluid data collected from sampling points in the foam pipeline. Then, based on the first data set and a preset fluid identification model, the fluid type is determined; the fluid type is identified as either a Newtonian fluid or a non-Newtonian fluid. Finally, based on the leak identification model corresponding to the fluid type and the first data set, the leak identification result is determined. By identifying the fluid type in the fire-fighting foam pipeline, the method effectively utilizes the characteristic that foam fluid can be equivalently considered as a Newtonian or non-Newtonian fluid in different application scenarios, thereby calling the corresponding identification module for targeted leak identification. This enables faster, more accurate, and more reliable leak identification of fire-fighting foam pipelines. Attached Figure Description

[0043] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0044] Figure 1 This is a processing logic diagram of a leak detection method for fire-fighting foam pipelines in converter stations proposed in the embodiments of this application;

[0045] Figure 2 This is a flowchart illustrating a method for detecting leaks in fire-fighting foam pipelines in converter stations, as proposed in this application embodiment.

[0046] Figure 3A This is the leak identification process proposed in the embodiments of this application when the leak identification result is a Newtonian fluid;

[0047] Figure 3BThis is the leak identification process proposed in the embodiments of this application when the leak identification result is a non-Newtonian fluid;

[0048] Figure 4 This is a schematic diagram of the fire-fighting foam pipe model in the embodiments of this application;

[0049] Figure 5 This is a schematic diagram of the functional modules of a leak detection device for fire-fighting foam pipelines in a converter station, as described in an embodiment of this application. Detailed Implementation

[0050] To make the technical solutions and advantages of the embodiments of this application clearer, the exemplary embodiments of this application are described in further detail below. Obviously, the described embodiments are only a part of the embodiments of this application, and not an exhaustive list of all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0051] Compressed-air foam systems (CAFS) are a new type of fire extinguishing system used in converter stations. They mainly consist of water pumps, air compressors, foam pump sets, and corresponding pipes and valves. Compared to traditional water systems, CAFS uses both water pump pressure and air compressor pressure as driving pressure, and the propelled substance is only water-containing air bubbles. Therefore, under the same conditions, the sprayed foam reaches higher and farther distances than water or foam mixtures. CAFS primarily utilizes principles such as heat radiation isolation, heat absorption, and air isolation for fire extinguishing. After the foam liquid foams, it covers the surface of the burning material, forming a foam layer of a certain thickness, effectively isolating the burning material from heat radiation from the flames. Because the foam contains a certain amount of air and water, when the foam covers the surface of the burning material, the precipitated foam water molecules absorb a large amount of heat from the burning material, achieving rapid cooling. The foam layer provides excellent surface coverage for the burning material, effectively isolating it from air, thus quickly stopping the combustion.

[0052] Research on the piping of compressed air foam fire extinguishing systems revealed that the compressed air foam fluid in the foam pipes is a shear-thinning non-Newtonian fluid. Furthermore, the relative rate of change of the apparent viscosity of the foam decreases rapidly with increasing shear rate (shear rate-viscosity dynamics), and then remains almost constant after reaching a certain level. Therefore, the apparent viscosity of the foam can be studied in two stages: the first stage, at low shear rates, is studied as a non-Newtonian fluid; the second stage, at higher shear rates, the foam can be approximated as a Newtonian fluid, meaning that the apparent viscosity of the foam tends to a constant value.

[0053] Compressed air foam fluid is a ternary two-phase fluid characterized by its low density and high viscosity. In practical applications, due to varying scenarios, the foam in the pipeline may transition between two stages. For example, in some cases, the foam velocity and shear rate are low, which can be considered the first stage; in other cases, the foam velocity is high, and most of the foam fluid is in a turbulent state (higher shear rate), which can be approximated as the second stage. Therefore, based on the characteristics of Newtonian and non-Newtonian fluids, this invention is proposed. The invention's structure is as follows: Figure 1 As shown in the diagram, this solution constructs a bidirectional long short-term memory network-residual fully connected network (BiLSTM-ResDNN) model to identify the collected data and determine whether the fluid in the pipeline is a Newtonian or non-Newtonian fluid. Then, different leak detection models are matched for Newtonian and non-Newtonian fluids respectively for accurate identification. For example, when the fluid is Newtonian, the first leak detection module is used to identify the leak; when the fluid is non-Newtonian, the second leak detection model is used. Furthermore, the same set of collected data can be reused, saving resources. This solution can be applied in various scenarios of compressed air foam fire extinguishing systems. For example, when a fire occurs in a converter station, due to the complexity of the operating environment, users cannot promptly monitor the pipeline status of the compressed air foam fire extinguishing system. In this case, this solution can be used to monitor the foam pipeline in real time during operation and issue an alert when a pipeline leak is detected. Alternatively, during the routine management and maintenance of the compressed air foam fire extinguishing system, the system can be briefly activated to fill the pipeline with foam fluid, and this solution can be used for rapid detection to meet the needs of scheduled routine maintenance or testing. For details on the specific implementation and execution of this invention, please refer to the embodiments below.

[0054] like Figure 2 As shown in the embodiment of this application, a method for detecting leaks in fire-fighting foam pipelines in converter stations is proposed. The method includes the following steps:

[0055] Step S10: Obtain the first data set based on the fluid data collected from the collection points of the fire-fighting foam pipeline;

[0056] Step S20: Based on the first data set and the preset fluid identification model, determine the fluid type; the fluid type includes Newtonian fluid or non-Newtonian fluid;

[0057] Step S30: Determine the leak identification result based on the leak identification model corresponding to the fluid type and the first data set.

[0058] In this embodiment, the fluid data collected from the sampling points of the foam pipe is processed to obtain a first data set. This first data set is then input into a preset fluid identification model for identification, determining whether the fluid type is Newtonian or non-Newtonian. Subsequently, the corresponding leak identification model is called to process the first data set for different fluid types, performing leak identification and obtaining the leak identification result. The specific implementation of each step is described in detail below.

[0059] Step S10: Obtain the first data set based on the fluid data collected from the collection points of the foam pipe.

[0060] In step S10, data collection points can be set at certain intervals on various pipes of the fire-fighting foam pipe network. In this embodiment, for example, it can be set for pipes with a diameter of DN200, but it can also be reasonably extended to pipes with other diameters. For example, in a non-ring network (where the beginning and end are not connected), for pipes with a diameter of DN200, pressure sensors, temperature sensors, ultrasonic Doppler flow meters, and Coriolis mass flow meters are installed approximately every 100 meters. Other alternative sensor tools can also be used. Due to practical factors, there may be acceptable errors at each installation location. Each installation location is used as a data collection point for the pipeline to collect fluid data.

[0061] After preliminary processing of the collected fluid data, the first data set can be obtained. This includes, for example, fluid pressure parameters, velocity profile data, temperature sensor data, fluid density measurements, and shear stress. For instance, based on the fluid pressure parameters and pipe length, pressure gradient data (ΔP / ΔL) can be calculated; the shear rate-viscosity curve can be obtained from the velocity profile data and shear stress. The preliminary processing involves processing the sensor-collected data, which is well-known to those skilled in the art and will not be elaborated upon here. The first data set specifically includes pressure gradient data, velocity profile data, shear rate-viscosity curve, temperature sensor data, and fluid density measurements; these data are time-series data.

[0062] Step S20: Based on the first data set and the preset fluid identification model, determine the fluid type; the fluid type includes Newtonian fluid or non-Newtonian fluid.

[0063] In step S20, the fluid identification model employs a Bidirectional Long Short-Term Memory (LSTM)-Residual Fully Connected Network (BiLSTM-ResDNN) model. This model uses a bidirectional LSTM layer to process time-series data, such as continuously sampled flow velocity profile data sequences. This effectively captures the temporal dependencies of fluid behavior, thereby extracting the dynamic dependencies of various fluid data points in the time dimension, such as viscosity hysteresis. The first data set can be processed into multivariate parameter vectors for each time step, such as pressure gradient data, flow velocity profile data, shear rate-viscosity curves, temperature sensor data, and fluid density measurements corresponding to each time step. After processing by the bidirectional LSTM layer, temporal feature encoding is obtained and then input to the next processing module, namely the residual fully connected layer.

[0064] The residual fully connected network of the fluid recognition model can consist of two layers. The first layer, L1, can use 64 neurons and employs the Swish activation function to handle the ratio of shear rate to viscosity. The second layer, L2, can use 32 neurons and combines the Batch Normalization method to handle the interaction effect of temperature and pressure. Through the stacking of residual fully connected layers, the complex mapping relationship between shear rate and viscosity is learned. Furthermore, for Newtonian fluids, the network learns that the weights of shear rate input and viscosity output approach zero, meaning that changes in shear rate have no effect on changes in viscosity. A dropout layer is introduced when calculating the output of each layer during forward propagation. For example, with a dropout rate of 0.3, 30% of the neuron outputs are randomly masked (set to zero) during forward propagation to prevent overfitting to single fluid data.

[0065] Optionally, L1 / L2 joint regularization can be introduced when calculating the loss function during forward propagation. Specifically, a penalty term is added to the loss function to constrain the weights of the fully connected layers and ensure physical rationality. The implementation is as follows: the loss function of the residual fully connected network is:

[0066]

[0067] Among them, L 正则化项 Used to reset weights unrelated to rheological properties to zero, L 物理约束 The viscosity gradient used to make the Newtonian fluid prediction result approach zero; λ1 is the L1 regularization coefficient (in this embodiment, it can be on the order of 1e-4), λ2 is the L2 regularization coefficient (in this embodiment, it can be on the order of 1e-3), ∑||W||1 is the L1 norm, and W is the weight. Weights unrelated to rheological properties can be cleared to zero. The L2 norm can suppress abnormal fluctuations, ensuring physical rationality while preventing overfitting; λ phy Eγ is the physical constraint strength coefficient. ˙To obtain the desired value for the shear rate distribution, μ pred γ is the fluid viscosity value predicted by the neural network. ˙ The shear rate is used. Physical constraints can be applied to make the viscosity gradient in the Newtonian fluid prediction results approach zero, ensuring the accuracy of the Newtonian fluid prediction.

[0068] The output layer of the fluid identification model can use the Sigmoid function to output the probability value P of belonging to a non-Newtonian fluid. A dynamic threshold is then used to determine whether the fluid in the pipe is a Newtonian or non-Newtonian fluid. For example, when P < 0.4, it is judged as a Newtonian fluid; when P is greater than 0.6, it is judged as a non-Newtonian fluid; other P values ​​are judged as "uncertain".

[0069] Furthermore, fuzzy probabilities can be set to improve the accuracy of fluid type identification. A fuzzy probability indicates that the fluid type cannot be determined as either a Newtonian or non-Newtonian fluid. When the fluid identification model outputs fuzzy probabilities, an auxiliary judgment can be initiated. For example, when the model probability is in the fuzzy range (0.4 ≤ P ≤ 0.6), an auxiliary judgment can be initiated. The auxiliary judgment can be any of the following:

[0070] When the pipe frequency is greater than a preset frequency threshold, the fluid type is determined to be a Newtonian fluid;

[0071] When the flow rate in the pipeline exceeds the predicted value for a theoretical Newtonian fluid, the fluid type is determined to be a non-Newtonian fluid.

[0072] Because non-Newtonian fluids exhibit elastic memory effects, stress relaxation occurs during pipeline flow, leading to pressure fluctuations. Therefore, in one possible implementation, pipeline frequency and flow rate can be used as auxiliary indicators. For example, based on abnormally high-frequency fluctuations in the pipeline frequency detected by multiple (e.g., three or more, without limitation) pressure sensors, if the pipeline frequency exceeds a preset frequency threshold, it is determined to be a Newtonian fluid. The frequency threshold can be determined by testing under various possible operating conditions simulating a Newtonian fluid in the pipeline. When the deviation between multiple (e.g., three or more, without limitation) flowmeter readings and the theoretical Newtonian fluid prediction value exceeds a preset deviation threshold, such as exceeding 15%, it can be determined to be a non-Newtonian fluid. The theoretical Newtonian fluid prediction value can be determined by passing a Newtonian fluid through the pipeline and testing multiple sets of data under different operating conditions of the compressed air foam fire extinguishing system; each operating condition can correspond to a theoretical Newtonian fluid prediction value. Simultaneously, by passing a non-Newtonian fluid through the pipeline and testing multiple sets of data under different operating conditions of the compressed air foam fire extinguishing system, the flowmeter readings can be determined, thereby calculating the difference between the two fluids under the corresponding operating conditions as a deviation threshold. When determining the fluid type, the corresponding theoretical Newtonian fluid prediction value is selected for the specific operating condition to calculate the specific deviation, and then compared with the deviation threshold to determine whether it is a non-Newtonian fluid. In other words, when the fluid type cannot be identified by the model, auxiliary judgment methods can be used to further identify the fluid type, thereby improving the accuracy and effectiveness of fluid type identification.

[0073] After identifying the fluid type using the BiLSTM-ResDNN model, step S30 is further executed to identify leaks in the foam pipe.

[0074] Step S30: Determine the leak identification result based on the leak identification model corresponding to the fluid type and the first data set.

[0075] Step S30 may specifically include two cases: one is the leak identification process when the leak identification result is a Newtonian fluid; the other is the leak identification process when the leak identification result is a non-Newtonian fluid.

[0076] When the fluid type is Newtonian fluid, please refer to Figure 3A Step S30 may include:

[0077] Step S31: Based on the first data group, determine the second data group corresponding to the Newtonian fluid;

[0078] Step S32: Determine the leak identification result based on the second data set and the first leak identification model corresponding to Newtonian fluid.

[0079] In step S31, the first data set includes: pressure gradient data, flow velocity profile data, shear rate-viscosity curve, temperature sensor data, and fluid density measurements. The second data set is used to characterize the pressure gradient data fluctuations in the pipeline. The second data set includes parameters used to characterize these fluctuations, such as pressure gradient data, pressure gradient variation coefficient, mass flow rate deviation, viscous dissipation power density, and dynamic characteristics of the bulk modulus. The method for determining some parameters of the second data set is as follows:

[0080] Pressure gradient data is processed into the pressure gradient coefficient of variation (CV). The CV measures the relative fluctuation of the pressure gradient data. Pipeline leakage will significantly increase the CV. The CV is obtained as follows:

[0081]

[0082] Where ΔP / ΔL is the pressure gradient (unit: Pa / m), representing the pressure change per unit pipe length; std() is the standard deviation, reflecting the degree of fluctuation of the pressure gradient; mean() is the mean, representing the long-term stable value of the pressure gradient.

[0083] The mass flow rate deviation R is obtained based on the flow velocity profile data. mass The acquisition method is as follows;

[0084]

[0085] Among them, Q in Q represents the mass flow rate (kg / s) at the previous measurement point in the pipeline flow direction; out The initial Q is the mass flow rate (kg / s) at the current measurement point. in Provides the initial mass flow rate of the pipeline; if there is a bifurcation or pipe diameter change between two collection points, the parameters at the same pipe section location of the collection points shall be used to avoid data distortion.

[0086] The viscous dissipation power density q was determined based on shear rate-viscosity curves and temperature sensor data. ˙ A leak in the pipeline will cause the viscous dissipation power density q to decrease. ˙ As the value increases, the viscous dissipation power density q ˙ The methods for obtaining it are as follows:

[0087]

[0088] Where, q ˙ Viscous dissipation power density (W / m 3 The temperature-dependent dynamic viscosity (Pa·s) μ(T) can be obtained by fitting a viscosity-temperature curve. Radial velocity gradient (s) -1 ), which can be measured and determined.

[0089] Based on fluid density measurements, the dynamic characteristic K of the bulk modulus is determined. eff A leak in the pipeline will cause the dynamic characteristic K of the bulk modulus to change. eff Value fluctuation, dynamic characteristics of bulk modulus K eff The methods for obtaining it are as follows:

[0090]

[0091] Where ρ is the fluid density (kg / m³) 3 ), This is the partial derivative of pressure with respect to density under isothermal conditions.

[0092] In step S31, since different operating conditions exist during pipeline use, the aforementioned parameters, such as pressure gradient data, pressure gradient coefficient of variation (CV), and mass flow rate deviation (R), can be used. mass Viscous dissipation power density q ˙ Dynamic characteristics of bulk modulus K eff The input neural network model learns the correlations between various parameters and further explores these deeper relationships to achieve more accurate leak detection of Newtonian fluids. This first leak detection model can employ a commonly used LSTM+CNN+Attention neural network structure, or other neural network models; there are no restrictions. Finally, the leak detection result is obtained, which can indicate whether the pipe is leaking or not.

[0093] Following step S32, the method further includes: when the leak identification result indicates a leak in the pipeline, determining the leaking pipe section based on sampling points where a first deviation value is greater than a preset first threshold and a second deviation value is greater than a preset second threshold; wherein, the first deviation value is the difference between the pressure gradient variation coefficient corresponding to the sampling point and a preset normal pressure gradient variation coefficient, and the second deviation value is the difference between the mass flow rate deviation corresponding to the sampling point and a preset normal mass flow rate deviation. The first and second thresholds can be determined through experimental verification in actual application scenarios. After determining that a pipeline leak has occurred, the above process can quickly locate the leak point, effectively improving detection accuracy and avoiding the manual investigation costs caused by detection errors.

[0094] When the fluid type is a non-Newtonian fluid, please refer to Figure 3B Step S30 may include:

[0095] Step S31': Based on the first data set, determine the third data set corresponding to the non-Newtonian fluid;

[0096] Step S32': Based on the third data set and the second leak identification model corresponding to the non-Newtonian fluid, determine the leak identification result.

[0097] In step S31', the first data set includes: flow velocity profile data, shear rate-viscosity curve, temperature sensor data, and fluid density measurement values. The third data set is used to ensure the degree of flow separation in the pipeline. This third data set includes parameters characterizing the degree of flow separation, such as shear rate-viscosity dynamics, the secondary flow intensity, viscous dissipation power density and the corresponding associated temperature, and the dynamic characteristics of the bulk modulus. The method for determining some parameters of the third data set is as follows:

[0098] Based on the shear rate-viscosity curve, the dynamic characteristic of shear rate-viscosity (apparent viscosity) μ is determined as follows:

[0099] μ(γ ˙ )=K·γ ˙n-1

[0100] Where μ is the shear rate-viscosity dynamic characteristic (Pa·s), reflecting the fluid flow resistance; γ ˙ Shear rate (s) -1 The velocity gradient characterizes the fluid deformation rate; K is the consistency coefficient (Pa·s). n The apparent viscosity is denoted by , where n is the power-law exponent. A sudden increase in shear rate near the leak point can cause a significant decrease in apparent viscosity, deviating from the normal rheological curve.

[0101] The secondary flow intensity Γ is determined based on velocity profile data, as follows:

[0102]

[0103] Where Γ is the secondary flow intensity (dimensionless), reflecting the ratio of the radial and tangential velocity components to the axial velocity, and can be used to characterize the degree of flow separation, v r v θ v z These represent the radial velocity component, tangential velocity component, and axial velocity component (m / s), respectively. Pipe leaks can cause flow separation, leading to an abnormally high secondary flow intensity Γ.

[0104] Based on shear rate-viscosity curves and temperature sensor data, the viscous dissipation power density and corresponding associated temperature are determined as follows:

[0105]

[0106]

[0107] Where, q˙ Viscous dissipation power density (W / m 3 Heat production rate per unit volume; The radial gradient of the axial flow velocity (s) -1 ); ΔT is the temperature rise (K), which can represent the abnormal temperature near the leak point; ρ is the fluid density (kg / m³). 3 );C p Specific heat capacity (J / (kg·K)). Shear rate gradient near the leak point. Increasing this will lead to q ˙ As the temperature rises, the local temperature ΔT will increase significantly.

[0108] Based on fluid density measurements, the dynamic characteristic K of the bulk modulus is determined. eff The leak will lead to K eff The value fluctuates, and the method for obtaining it has been explained above, so it will not be repeated here.

[0109] The above pressure gradient data, shear rate-viscosity dynamics (apparent viscosity) μ, secondary flow intensity Γ, and viscous dissipation power density q are used to... ˙ and the dynamic characteristics of temperature ΔT and bulk modulus K eff As input data, the data is fed into a neural network model for learning, studying the correlations between various parameters, and further exploring their deeper relationships to achieve more accurate non-Newtonian fluid leak detection. This second leak detection model can employ a commonly used LSTM+CNN+Attention neural network structure, or other neural network models; there are no restrictions. Finally, the leak detection result is obtained, which can indicate whether the pipe is leaking or not.

[0110] Following step S32', the method further includes: when the leak identification result indicates a leak in the pipeline, based on the pressure gradient decrease value of the target pipe segment being greater than a third threshold and the viscous dissipation power density increase value of the target pipe segment being greater than a fourth threshold, a leak is determined in the target pipe segment; wherein, the target pipe segment is the pipe segment between two adjacent sampling points. Specifically, when the obtained detection result indicates a leak, the leak can be determined using the pressure gradient data and viscous dissipation power density q corresponding to each detection point. ˙ To locate the pipe section where the leak is found, one can use... Combined with ΔT verification, false alarms due to pressure fluctuations (such as pump and valve operation interference) are eliminated, and the obtained The data obtained during pump and valve operation were compared and verified with ΔT and experimental data. When the deviation was within the set threshold range, it was considered a pump and valve operation disturbance. Furthermore, when determining the pipe section where the leak occurred, a data collection point P was used. i and collection point P i+1 For example, pipe segment P i →P i+1The pressure gradient data decreases by more than a preset third threshold (e.g., 15%), and the viscous dissipation power density q in this pipe section... ˙ If the rate of increase exceeds a preset fourth threshold (e.g., 20%), a leak is determined to have occurred in that pipe section, allowing for rapid identification of the leak point. This process effectively improves detection accuracy and avoids the manual investigation costs caused by detection errors.

[0111] In this embodiment, the fluid identification model, the first leak identification model, and the second leak identification model are all pre-trained models. To train the models, corresponding pipeline models can be constructed according to actual application scenarios. For example... Figure 4 As shown, in this embodiment, when constructing the pipeline model, an outdoor experimental pipeline of approximately 400 meters (non-ring network, not connected end to end) with a diameter of DN200 was selected. Leakage holes were machined on the pipeline to simulate leakage. Pressure sensors, temperature sensors, ultrasonic Doppler flow meters, and Coriolis mass flow meters were installed approximately every 100 meters. Other alternative sensor tools could also be used (due to practical factors, the actual interval between installation positions P1 and P2 is 107 meters, between P2 and P3 is 86 meters, between P3 and P4 is 105 meters, and between P4 and P5 is 70 meters). These installation positions correspond to the fluid data acquisition points. Theoretically, the pipeline is divided into four sections, with leakage points set. Holes are drilled in increments of 5 meters, 10 meters, and 15 meters within each section. The leakage opening is a module consisting of an electromagnetic flow meter, a needle valve, and a gravity sensor. Taking the pressure sensor as an example, the arrangement is shown in the table below:

[0112] Table 1 Actual Distance of Pressure Sensor

[0113]

[0114] The aforementioned pipeline model effectively simulates leakage, normal use, and non-use conditions, allowing for the collection of fluid data at various installation locations at different times. This data includes fluid pressure parameters, velocity profile data, temperature sensor data, fluid density measurements, and shear stress. Based on the fluid pressure parameters and pipeline length, pressure gradient data can be calculated. Shear rate-viscosity can be obtained from the velocity profile data and shear stress, resulting in a shear rate-viscosity curve. In other words, the collected data can be processed into time-series data including pressure gradient data, velocity profile data, shear rate-viscosity curve, temperature sensor data, and fluid density measurements. Each data set is labeled with two categories: first, Newtonian fluids and non-Newtonian fluids; second, leakage, normal use, and non-use. This data can then be used as the raw data for model training. Existing methods such as interpolation and Generative Adversarial Networks (GANs) are then used to expand the sample. The BiLSTM-ResDNN model is trained using the sample data collected and processed by the above experimental model to obtain the fluid recognition model.

[0115] Furthermore, fluid pressure parameters, velocity profile data, temperature sensor data, fluid density measurements, and shear stress can be processed into pressure gradient data, pressure gradient variation coefficient, mass flow rate deviation, viscous dissipation power density, and dynamic characteristics of bulk modulus. Data annotation and sample expansion are then performed to obtain samples for training the first leak detection model. By training the model using these samples and learning the correlations between parameters, further exploring their deeper relationships, a well-trained first leak detection model can be obtained.

[0116] Furthermore, fluid pressure parameters, velocity profile data, temperature sensor data, fluid density measurements, and shear stress can be processed into pressure gradient data, shear rate-viscosity dynamic characteristics, secondary flow intensity, viscous dissipation power density, and associated temperature and bulk modulus dynamic characteristics. Data annotation and sample expansion are then performed to obtain samples for training the second leak detection model. By training the model using these samples, the correlations between various parameters are learned, and further exploration of these deeper correlations yields a well-trained second leak detection model.

[0117] In summary, the method of this application embodiment has the following advantages:

[0118] 1. The overall architecture of the leak detection method for fire-fighting foam pipelines in converter stations in this application embodiment is to identify fluid type by using a bidirectional long short-term memory network-residual fully connected network model (BiLSTM-ResDNN), and then call the first / second leak identification model corresponding to the fluid type to identify leaks in Newtonian / non-Newtonian fluids. In the application scenario of foam pipelines, it can significantly improve the leak identification accuracy and has good timeliness.

[0119] 2. The loss function of the BiLSTM-ResDNN model incorporates a regularization term, which clears weights unrelated to rheological properties to zero and suppresses abnormal fluctuations, ensuring physical plausibility while preventing overfitting. Simultaneously, the loss function also includes a physical constraint term, which makes the viscosity gradient of the Newtonian fluid prediction result approach zero, ensuring the accuracy of the Newtonian fluid prediction.

[0120] 3. When using the first / second leak identification model, different secondary preprocessing is performed on the pressure gradient data, flow velocity profile data, shear rate-viscosity curve, temperature sensor data, and fluid density measurement values ​​to adapt to the characteristics of Newtonian / non-Newtonian fluids. This allows the first / second leak identification model to more accurately learn the correlation between various parameters, further explore their deep correlation, improve leak detection accuracy, and use the same set of collected data for two different preprocessing without increasing data acquisition costs.

[0121] 4. A first leak detection model learns the deep correlation between parameters such as pressure gradient data, pressure gradient variation coefficient, mass flow rate deviation, viscous dissipation power density, and dynamic characteristics of bulk modulus to achieve more accurate Newtonian fluid leak detection. A second leak detection model learns the deep correlation between pressure gradient data, shear rate-viscosity dynamics (apparent viscosity), secondary flow intensity, viscous dissipation power density, and associated temperature and bulk modulus dynamic characteristics to achieve more accurate non-Newtonian fluid leak detection.

[0122] 5. For leaks of Newtonian fluids, the leaking pipe section can be determined by the pressure gradient variation coefficient data and mass flow deviation corresponding to each detection point, enabling rapid location of the leak. For leaks of non-Newtonian fluids, the leak location can be rapidly located by the pressure gradient and viscous dissipation power density corresponding to each detection point, ensuring efficient pipeline fault diagnosis.

[0123] Based on the same inventive concept, another embodiment of the present invention provides a leak detection device for fire-fighting foam pipelines in converter stations. Figure 5 This illustration shows a functional block diagram of a leak detection device for fire-fighting foam pipelines in a converter station, according to an embodiment of this application. The device includes:

[0124] The data processing module 501 is used to obtain the first data set based on the fluid data collected from the collection point of the fire foam pipeline;

[0125] The fluid type identification module 502 is used to determine the fluid type based on the first data set and a preset fluid identification model; the fluid type is a Newtonian fluid or a non-Newtonian fluid.

[0126] The leak identification module 503 is used to determine the leak identification result based on the leak identification model corresponding to the fluid type and the first data group.

[0127] In one possible implementation, the fluid recognition model includes a bidirectional long short-term memory network and a residual fully connected network model; the loss function of the residual fully connected network is:

[0128]

[0129] Among them, L 正则化项 Used to reset weights unrelated to rheological properties to zero, L 物理约束 The viscosity gradient used to make the Newtonian fluid prediction result approach zero.

[0130] In one possible implementation, the fluid type identification module 502 is used for:

[0131] When the output layer of the fluid recognition model outputs a fuzzy probability, perform any of the following judgments:

[0132] When the pipe frequency is greater than a preset frequency threshold, the fluid type is determined to be a Newtonian fluid;

[0133] When the flow rate in the pipeline is greater than the predicted value of a theoretical Newtonian fluid, the fluid type is determined to be a non-Newtonian fluid.

[0134] Among them, fuzzy probability representation cannot determine whether the fluid type is a Newtonian fluid or a non-Newtonian fluid.

[0135] In one possible implementation, the leak detection module 503 is used to: determine a second data group corresponding to the Newtonian fluid based on the first data group; and determine the leak detection result based on the second data group and the first leak detection model corresponding to the Newtonian fluid.

[0136] In one possible implementation, the first data set includes: pressure gradient data, flow velocity profile data, shear rate-viscosity curves, temperature sensor data, and fluid density measurements. The leak detection module 503 is configured to perform at least one of the following:

[0137] The pressure gradient variation coefficient is determined based on the pressure gradient data.

[0138] The mass flow rate deviation is determined based on the aforementioned velocity profile data;

[0139] The viscous dissipation power density is determined based on the shear rate-viscosity curve and temperature sensor data.

[0140] The dynamic characteristics of the bulk modulus are determined based on the fluid density measurement.

[0141] In one possible implementation, the converter station fire-fighting foam pipeline leak detection device further includes a leak-point pipe section positioning module, used to: when the leak identification result indicates that there is a leak in the pipeline, determine the pipe section with a leak based on the collection point where the first deviation value is greater than a preset first threshold and the second deviation value is greater than a preset second threshold; wherein, the first deviation value is the difference between the pressure gradient variation coefficient corresponding to the collection point and the preset normal pressure gradient variation coefficient, and the second deviation value is the difference between the mass flow rate deviation corresponding to the collection point and the preset normal mass flow rate deviation.

[0142] In one possible implementation, the leak detection module 503 is used to: determine a third data group corresponding to a non-Newtonian fluid based on the first data group; and determine the leak detection result based on the third data group and a second leak detection model corresponding to a non-Newtonian fluid.

[0143] In one possible implementation, the first data set includes: flow velocity profile data, shear rate-viscosity curves, temperature sensor data, and fluid density measurements. The leak detection module 503 is configured to perform at least one of the following:

[0144] Based on the shear rate-viscosity curve, the dynamic characteristics of shear rate-viscosity are determined;

[0145] The secondary flow intensity is determined based on the aforementioned velocity profile data;

[0146] Based on the shear rate-viscosity curve and temperature sensor data, the viscous dissipation power density and the corresponding associated temperature are determined.

[0147] Based on the fluid density measurement, the dynamic characteristics of the bulk modulus are determined.

[0148] In one possible implementation, the converter station fire-fighting foam pipeline leak detection device further includes a leak pipe section positioning module, used to: when the leak identification result indicates that there is a leak in the pipeline, determine that there is a leak in the target pipe section based on the pressure gradient decrease value of the target pipe section being greater than a third threshold and the viscous dissipation power density increase value of the target pipe section being greater than a fourth threshold; wherein, the target pipe section is the pipe section between two adjacent collection points.

[0149] It should be noted that the specific implementation and technical effects of the converter station fire-fighting foam pipeline leak detection device 300 provided in this embodiment of the invention are the same as those in the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0150] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0151] Based on the same inventive concept, this application also provides a computer storage medium, which may be a computer-readable storage medium storing computer instructions or computer-readable programs. When the computer instructions or computer-readable programs are run on a computer, the computer performs the steps of the aforementioned converter station fire-fighting foam pipeline leak detection method.

[0152] Based on the same inventive concept, this application also provides a computer storage medium, which may be a computer-readable storage medium storing computer instructions or computer programs. When the computer instructions or computer programs are run on a computer, the computer performs the steps of the converter station fire foam pipeline leak detection method described above.

[0153] Based on the same inventive concept, embodiments of this application also provide a computer program product. That is, various aspects of the video-based converter station fire emergency response method provided in embodiments of this application can also be implemented in the form of a computer program product, which includes program code or computer program. When the computer program product is run on a computer, the program code or computer program is used to cause the computer to perform the steps of the converter station fire foam pipeline leak detection method described above according to various exemplary embodiments of this application.

[0154] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0155] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0156] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0157] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0158] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0159] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for detecting leaks in fire-fighting foam pipelines in converter stations, characterized in that, include: The first data set is obtained by collecting fluid data from the collection points of the fire-fighting foam pipeline; Based on the first data set and the preset fluid identification model, the fluid type in the fire-fighting foam pipe is determined; the fluid type includes Newtonian fluid or non-Newtonian fluid. Based on the leak identification model corresponding to the fluid type and the first data set, the leak identification result of the fire-fighting foam pipeline is determined.

2. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 1, characterized in that, The fluid recognition model includes a bidirectional long short-term memory network and a residual fully connected network model; the loss function of the residual fully connected network is: L total =L data +L 正则化项 +L 物理约束 Among them, L 正则化项 Used to reset weights unrelated to rheological properties to zero, L 物理约束 The viscosity gradient used to make the Newtonian fluid prediction result approach zero.

3. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 1, characterized in that, Based on the first data set and the preset fluid identification model, the fluid type in the fire-fighting foam pipeline is determined, including: When the output layer of the fluid recognition model outputs a fuzzy probability, perform any of the following judgments: When the pipe frequency is greater than a preset frequency threshold, the fluid type is determined to be a Newtonian fluid; When the flow rate in the pipeline is greater than the predicted value of a theoretical Newtonian fluid, the fluid type is determined to be a non-Newtonian fluid. Among them, fuzzy probability representation cannot determine whether the fluid type is a Newtonian fluid or a non-Newtonian fluid.

4. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 1, characterized in that, When the fluid type is a Newtonian fluid, determining the leak identification result based on the leak identification model corresponding to the fluid type and the first data set includes: Based on the first data set, determine the second data set corresponding to the Newtonian fluid; Based on the second data set and the first leak identification model corresponding to Newtonian fluid, the leak identification result is determined.

5. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 4, characterized in that, The first data set includes: pressure gradient data, flow velocity profile data, shear rate-viscosity curves, temperature sensor data, and fluid density measurements; the determination of the second data set corresponding to the Newtonian fluid based on the first data set includes at least one of the following: The pressure gradient variation coefficient is determined based on the pressure gradient data. The mass flow rate deviation is determined based on the aforementioned velocity profile data; The viscous dissipation power density is determined based on the shear rate-viscosity curve and temperature sensor data. The dynamic characteristics of the bulk modulus are determined based on the fluid density measurement.

6. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 5, characterized in that, After determining the leak identification result based on the second data set and the first leak identification model corresponding to Newtonian fluid, the method further includes: The leak identification result is that when there is a leak in the pipeline, the pipeline segment with a leak is determined based on the collection point where the first deviation value is greater than the preset first threshold and the second deviation value is greater than the preset second threshold; wherein, the first deviation value is the difference between the pressure gradient variation coefficient corresponding to the collection point and the preset normal pressure gradient variation coefficient, and the second deviation value is the difference between the mass flow deviation corresponding to the collection point and the preset normal mass flow deviation.

7. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 1, characterized in that, When the fluid type is a non-Newtonian fluid, determining the leak identification result based on the leak identification model corresponding to the fluid type and the first data set includes: Based on the first data set, determine the third data set corresponding to the non-Newtonian fluid; Based on the third data set and the second leak identification model corresponding to non-Newtonian fluids, the leak identification result is determined.

8. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 7, characterized in that, The first data set includes: flow velocity profile data, shear rate-viscosity curves, temperature sensor data, and fluid density measurements; the third data set, determined based on the first data set, for non-Newtonian fluids, includes at least one of the following: Based on the shear rate-viscosity curve, the dynamic characteristics of shear rate-viscosity are determined; The secondary flow intensity is determined based on the aforementioned velocity profile data; Based on the shear rate-viscosity curve and temperature sensor data, the viscous dissipation power density and the corresponding associated temperature are determined. Based on the fluid density measurement, the dynamic characteristics of the bulk modulus are determined.

9. The method for detecting leaks in fire-fighting foam pipelines in converter stations according to claim 8, characterized in that, After determining the leak identification result based on the second leak identification model corresponding to the third data set and non-Newtonian fluids, the method further includes: The leak identification result is that when there is a leak in the pipeline, the leak is determined to exist in the target pipe section based on the pressure gradient decrease value of the target pipe section being greater than the third threshold and the viscous dissipation power density increase value of the target pipe section being greater than the fourth threshold; wherein, the target pipe section is the pipe section between two adjacent collection points.

10. A leak detection device for fire-fighting foam pipelines in a converter station, characterized in that, include: The data processing module is used to obtain the first data set based on the fluid data collected from the collection points of the fire foam pipeline; A fluid type identification module is used to determine the fluid type based on the first data set and a preset fluid identification model; the fluid type includes Newtonian fluid or non-Newtonian fluid. The leak detection module is used to determine the leak detection result based on the leak detection model corresponding to the fluid type and the first data set.

11. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed, implements the steps of the method for detecting leaks in fire-fighting foam pipelines in converter stations as described in any one of claims 1-9.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed, implements the steps of the method for detecting leaks in fire-fighting foam pipelines in converter stations as described in any one of claims 1-9.

Images