Cleanness detection method and device suitable for long-distance refrigeration pipeline

Abstract

The invention discloses a cleanliness detection method and device suitable for a long-distance refrigeration pipeline, and relates to the related technical field of cleanliness detection.The method comprises the steps that the injection gas type and injection pulse signals of a to-be-detected long-distance pipeline are determined; a liquid nitrogen vaporization device is connected, a pulse injection valve is controlled by injecting pulse signals to inject gas into an inlet, an infrared thermal imaging array is adopted to collect the temperature of the outer surface, and real-time response data of the temperature of the outer surface are output; constructing a heat transfer abnormal area identification model through a pipeline three-dimensional transient heat transfer equation, and marking an abnormal area to obtain a heat transfer abnormal area; and analyzing the heat transfer abnormity response data of the heat transfer abnormity area, and generating a cleanliness detection result. The technical problems that in the prior art, the cleanliness detection efficiency of a long-distance refrigeration pipeline is low, real-time dynamic monitoring cannot be achieved, and a local pollution area is difficult to accurately recognize are solved, and the technical effects that the heat transfer abnormal area is accurately positioned, and high-efficiency and high-precision cleanliness detection is conducted on the pipeline are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cleanliness detection, and particularly relates to a cleanliness detection method and device suitable for long-distance refrigeration pipelines. BACKGROUND

[0002] Long-distance refrigeration pipelines are widely used in liquefied natural gas (LNG) transportation, cold chain logistics, large central air conditioning systems, and chemical refrigeration fields. However, during long-term operation, the pipelines are prone to accumulate pollutants such as oil stains, water stains, and particulate matter inside, which leads to a decrease in heat transfer efficiency, an increase in energy consumption, and even may cause pipeline blockage or corrosion, thereby seriously affecting the safety and economy of the system. Traditional pipeline cleanliness detection mainly includes visual inspection, endoscope detection, pressure drop analysis, and sampling analysis, and has low detection efficiency, limited applicability, and cannot realize real-time monitoring. In particular, for long-distance and large-diameter refrigeration pipelines, it is difficult to achieve comprehensive and rapid cleanliness evaluation. Existing non-contact detection based on infrared thermal imaging mainly relies on steady-state temperature field analysis, and cannot effectively identify local pollution or sediment distribution under dynamic gas flow conditions, thereby failing to achieve rapid and accurate evaluation of the cleanliness of long-distance refrigeration pipelines.

[0003] Therefore, in the related art, there are technical problems of low cleanliness detection efficiency, inability to realize real-time dynamic monitoring, and difficulty in accurately identifying local pollution areas for long-distance refrigeration pipelines. SUMMARY

[0004] The present application provides a cleanliness detection method and device suitable for long-distance refrigeration pipelines, which solves the technical problems of low cleanliness detection efficiency, inability to realize real-time dynamic monitoring, and difficulty in accurately identifying local pollution areas for long-distance refrigeration pipelines in the prior art, and achieves the technical effects of accurately positioning heat transfer abnormal areas and efficiently and accurately detecting the cleanliness of pipelines.

[0005] The present application provides a cleanliness detection method suitable for long-distance refrigeration pipelines, which comprises: determining the injection gas type and injection pulse signal of a long-distance pipeline to be tested; connecting a liquid nitrogen vaporization device to the inlet of the long-distance pipeline to be tested, wherein the liquid nitrogen vaporization device controls a pulse injection valve to inject gas into the inlet of the long-distance pipeline to be tested through the injection gas type and the injection pulse signal, and simultaneously collects temperature of the outer surface of the long-distance pipeline to be tested by using a deployed infrared thermal imaging array, and outputs outer surface temperature real-time response data; constructing a heat transfer abnormal area identification model through a pipeline three-dimensional transient heat transfer equation, marking abnormal areas according to the heat transfer abnormal area identification model based on the outer surface temperature real-time response data, and obtaining a heat transfer abnormal area; analyzing heat transfer abnormal response data of the heat transfer abnormal area, and generating a cleanliness detection result of the long-distance pipeline to be tested.

[0006] In a possible implementation, the method for detecting cleanliness of a long-distance refrigeration pipeline further performs the following processing: performing finite element modeling on the long-distance pipeline to be detected according to basic parameters and operating environment information of the long-distance pipeline to be detected, to obtain a three-dimensional pipeline structure model; performing pipeline three-dimensional transient heat transfer equation simulation on the three-dimensional pipeline structure model according to the injected gas type and the injected pulse signal, to output external surface temperature simulation response data; constructing a plurality of abnormal long-distance pipeline modeling samples containing known abnormal state labels; performing pipeline three-dimensional transient heat transfer equation simulation on the three-dimensional pipeline structure model according to the plurality of abnormal long-distance pipeline modeling samples, to output a plurality of external surface temperature abnormal simulation response data; and performing temperature response feature training on the known abnormal state labels based on the external surface temperature simulation response data and the plurality of external surface temperature abnormal simulation response data, to construct a heat transfer abnormal region identification model.

[0007] In a possible implementation, the method for detecting cleanliness of a long-distance refrigeration pipeline further performs the following processing: establishing a control group of the external surface temperature simulation response data and the plurality of external surface temperature abnormal simulation response data respectively, to obtain a plurality of groups of temperature simulation response training data; extracting temperature response feature vectors of the plurality of groups of temperature simulation response training data, the temperature response feature vectors including temperature drop values, temperature drop rates, and temperature residual distribution; performing multi-classification training on a defined random forest based on the temperature drop values, the temperature drop rates, the temperature residual distribution, and the known abnormal state labels, to obtain a heat transfer abnormal region identification model; wherein, defined parameters of the random forest include the number of random forest trees, tree depth, sample tree for splitting, and leaf node sample tree.

[0008] In a possible implementation, the method for detecting cleanliness of a long-distance refrigeration pipeline further performs the following processing: collecting temperatures of an external surface of the long-distance pipeline to be detected by using a deployed infrared thermal imaging array, wherein the infrared thermal imaging array includes a plurality of infrared thermal imaging units; collecting temperatures of the external surface of the long-distance pipeline to be detected by using the deployed infrared thermal imaging array, to output image time sequences corresponding to the plurality of infrared thermal imaging units; performing temperature mapping according to a temperature measurement calibration curve built in each infrared thermal imaging unit, to output a plurality of time-series temperature response matrices representing temperature changes of each pixel position; and fusing the plurality of time-series temperature response matrices to obtain external surface temperature real-time response data corresponding to the long-distance pipeline to be detected.

[0009] In a possible implementation, the method for detecting cleanliness of a long-distance refrigeration pipeline further performs the following processing: performing temperature response feature vector extraction on the real-time surface temperature response data according to the heat transfer abnormal area identification model, and outputting real-time temperature drop, real-time temperature drop rate, and real-time temperature residual error distribution; performing random forest classification and identification according to the real-time temperature drop, the real-time temperature drop rate, and the real-time temperature residual error distribution, to obtain the heat transfer abnormal area and heat transfer abnormal response data of the heat transfer abnormal area.

[0010] In a possible implementation, the method for detecting cleanliness of a long-distance refrigeration pipeline further performs the following processing: performing abnormal quantification on the heat transfer abnormal response data of the heat transfer abnormal area, and outputting a comprehensive abnormality index, wherein the heat transfer abnormal response data includes area position, area size, and abnormality level of the heat transfer abnormal area; and performing cleanliness conversion according to the comprehensive abnormality index to obtain a cleanliness detection result of the long-distance pipeline to be detected.

[0011] In a possible implementation, the method for detecting cleanliness of a long-distance refrigeration pipeline further performs the following processing: determining an injection gas type of the long-distance pipeline to be detected, wherein the injection gas type is fluorocarbon or CO2 gas with a boiling point lower than -40℃.

[0012] In a possible implementation, the method for detecting cleanliness of a long-distance refrigeration pipeline further performs the following processing: obtaining a pipeline length and a thermal response time constant of the long-distance pipeline to be detected; performing pipeline response effectiveness scoring according to the pipeline length and the thermal response time constant of the long-distance pipeline to be detected; performing pulse signal frequency, amplitude, and duration cycle optimization under the constraint condition of a preset response effectiveness scoring threshold; and generating an injection pulse signal.

[0013] The application also provides a cleanliness detection device suitable for long-distance refrigeration pipelines, which comprises: an injection data determination module, which is used to determine the injection gas type and injection pulse signal of a long-distance pipeline to be detected; a response data output module, which is used to access a liquid nitrogen vaporization device at the inlet of the long-distance pipeline to be detected, the liquid nitrogen vaporization device controls a pulse injection valve to inject gas into the inlet of the long-distance pipeline to be detected through the injection gas type and the injection pulse signal, and an infrared thermal imaging array is used to collect the temperature of the outer surface of the long-distance pipeline to be detected, and output real-time response data of the outer surface temperature; an abnormal area marking module, which is used to construct a heat transfer abnormal area identification model through a pipeline three-dimensional transient heat transfer equation, mark the abnormal area of the real-time response data of the outer surface temperature according to the heat transfer abnormal area identification model, and obtain a heat transfer abnormal area; and a cleanliness detection result generation module, which is used to analyze the heat transfer abnormal response data of the heat transfer abnormal area, and generate a cleanliness detection result of the long-distance pipeline to be detected.

[0014] The cleanliness detection device suitable for long-distance refrigeration pipelines provided by the application determines the injection gas type and injection pulse signal of a long-distance pipeline to be detected, accesses a liquid nitrogen vaporization device, controls a pulse injection valve to inject gas into the inlet through the injection pulse signal, uses an infrared thermal imaging array to collect the temperature of the outer surface, and outputs real-time response data of the outer surface temperature. The heat transfer abnormal area identification model is constructed through a pipeline three-dimensional transient heat transfer equation, and the abnormal area is marked to obtain a heat transfer abnormal area. The heat transfer abnormal response data of the heat transfer abnormal area is analyzed to generate a cleanliness detection result. The technical problems of low efficiency, inability to real-time dynamic monitoring and difficulty in accurately identifying the local pollution area of the long-distance refrigeration pipeline cleanliness detection in the prior art are solved, and the technical effects of accurately positioning the heat transfer abnormal area and high-efficiency and high-precision cleanliness detection of the pipeline are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. The flowcharts are used to illustrate the operations performed by the device according to the embodiments of the present application in the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, according to the needs, various steps can be processed in reverse order or at the same time. At the same time, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0016] Figure 1 The cleanliness detection method suitable for long-distance refrigeration pipelines provided by the embodiments of the present application is shown in the flowchart.

[0017] Figure 2An experimental cooling rate diagram of a plurality of abnormal long-distance pipeline modeling samples in a cleanliness detection method suitable for a long-distance refrigeration pipeline provided by the embodiment of the present application.

[0018] Figure 3 A structural diagram of a cleanliness detection device suitable for a long-distance refrigeration pipeline provided by the embodiment of the present application.

[0019] The reference signs are explained as follows: an injection data determination module 10, a response data output module 20, an abnormal area marking module 30, and a cleanliness detection result generation module 40. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical scheme of the present application, in order to more clearly understand the technical means of the present application, and to be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0021] In order to make the purpose, technical scheme and advantages of the present application more clear, the following will combine the drawings to further describe the present application in detail, the described embodiments should not be regarded as limiting the present application, all other embodiments obtained by the person skilled in the art without creative labor belong to the scope of protection of the present application.

[0022] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subset of all possible embodiments, and can be combined with each other without conflict, the term "first\second" involved only distinguishes similar objects, and does not represent the specific order of the object. The terms "include" and "have" and any variations, are intended to cover non-exclusive inclusion, for example, a process, method, device, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art in the technical field of the present application. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiment of the present application provides a cleanliness detection method suitable for a long-distance refrigeration pipeline, as shown in the figure, the method comprises the following steps: Figure 1

[0024] Step S100, determining the injection gas type and injection pulse signal of the long-distance pipeline to be tested.

[0025] ​Further, step S100 further comprises determining the injection gas type of the long-distance pipeline to be measured, wherein the injection gas type is fluorocarbon or CO2 gas with a boiling point lower than -40℃.

[0026] Preferably, the long-distance pipeline to be measured refers to a closed conveying pipeline in the refrigeration, energy or industrial fields, which has a length significantly greater than a conventional pipeline and needs to be detected for cleanliness, and is used to convey low-temperature medium such as liquefied natural gas, liquid ammonia, chilled water, etc., and the inner wall of which is prone to accumulate contaminants such as oil stains, frost, scale, etc. The injection gas type and the injection pulse signal are determined, wherein the injection gas type refers to the type of low-temperature gas generated by a liquid nitrogen vaporization device and injected into the pipeline in a pulse manner during the detection process, i.e., the injection gas type is fluorocarbon or CO2 gas with a boiling point lower than -40℃, which can be quickly vaporized and form a clear temperature gradient after being injected into the long-distance pipeline to be measured, thereby generating a detectable thermal response signal in the pipeline. The pulse signal is a combination of parameters such as time, frequency, amplitude and duration of gas injection, and periodic gas injection is realized by adjusting the pulse valve to excite the dynamic thermal response of the pipeline.

[0027] Step S100 further comprises the following steps: S110, obtaining the pipeline length and thermal response time constant of the long-distance pipeline to be measured; S120, performing pipeline response effectiveness scoring according to the pipeline length and thermal response time constant of the long-distance pipeline to be measured, and performing pulse signal frequency, amplitude and duration cycle optimization to meet a preset response effectiveness scoring threshold as a constraint condition to generate an injection pulse signal.

[0028] Preferably, the pipeline length of the long-distance pipeline to be measured is measured by a laser range finder, ultrasonic ranging or directly read from design drawings, which directly affects the propagation time and thermal response range of the pulse signal; the thermal response time constant is calculated by experimental measurement, which reflects the response speed of the pipeline material to temperature change, i.e., a characteristic parameter of the time required for temperature transfer to the outer surface, and the thermal response time constant wherein ρ is the density of the pipeline material kg / m 3 , c pis the specific heat capacity J / (kg·K), k is the thermal conductivity W / (m·K), and L is the wall thickness of the long-distance pipeline to be measured m; the pipeline response effectiveness score is scored according to the pipeline length and the thermal response time constant of the long-distance pipeline to be measured, that is, the detectability of the pulse signal under the current pipeline parameters is evaluated, to ensure that the temperature response signal meets the signal-to-noise ratio requirement and covers the entire pipeline, a scoring function is constructed based on the pipeline length and the thermal response time constant, that is, the ratio of the pipeline length and the thermal response time constant to the corresponding reference pipeline parameters is weighted calculated, a preset response effectiveness score threshold is set to be greater than or equal to 1.0, and the pulse signal frequency, amplitude and duration cycle are optimized under the constraint condition of meeting the preset response effectiveness score threshold, wherein the frequency refers to the number of gas pulse triggers per unit time, the amplitude refers to the volume of gas injected by a single pulse, and the duration cycle refers to the duration of each pulse, that is, the optimal pulse signal frequency, amplitude and duration cycle are calculated according to the pipeline length and the thermal response time constant, and finally the injection pulse signal is generated, for example, the frequency of the long pipeline needs to be reduced and the pulse width needs to be extended, to ensure that the temperature wave propagates to the far end.

[0029] Step S200, access the liquid nitrogen vaporization device at the inlet of the long-distance pipeline to be measured, the liquid nitrogen vaporization device controls the pulse injection valve to inject gas into the inlet of the long-distance pipeline to be measured through the injection gas type and the injection pulse signal, and simultaneously collects the temperature of the outer surface of the long-distance pipeline to be measured by using the deployed infrared thermal imaging array, and outputs the real-time response data of the outer surface temperature.

[0030] Preferably, liquid nitrogen vaporization device is accessed at the inlet of the long-distance pipeline to be tested, and the core components thereof include a liquid nitrogen storage tank, a vaporizer, a pulse injection valve, and a control system, which are used to convert liquid nitrogen into low-temperature gaseous nitrogen and inject the low-temperature gaseous nitrogen into the long-distance pipeline to be tested through the pulse valve according to a set parameter. Specifically, a quick connector is installed at the inlet of the pipeline to connect the output end of the liquid nitrogen vaporization device and ensure the sealing property. A gas with a boiling point lower than -40℃ is selected according to the characteristics of the pipeline to trigger a significant thermal response. The control system receives an optimized injection pulse signal and performs injection through the pulse injection valve, that is, the pulse injection valve is opened and closed at a set rhythm to realize intermittent low-temperature gas injection, thereby creating controllable temperature fluctuations in the pipeline, causing the characteristic delayed temperature drop of the fouling area due to the difference in thermal resistance. For example, the low-temperature gas is injected every 2 seconds, and each injection lasts for 100 ms. The injected low-temperature gas quickly absorbs heat in the pipeline, resulting in local cooling of the inner wall of the pipeline and a change in the temperature of the outer surface. At the same time, an infrared thermal imaging array is deployed to collect the temperature of the outer surface of the long-distance pipeline to be tested. The infrared thermal imaging array is a plurality of infrared thermal imaging units deployed at equal intervals along the outer surface of the pipeline, covering the entire pipeline. The units are connected through a synchronization signal to ensure the time consistency of the data. Each infrared thermal imaging unit captures thermal images of the outer surface of the pipeline at a fixed frequency to generate an image time sequence, which is converted into actual temperature values according to the built-in temperature measurement calibration curve, and finally the data of the plurality of infrared thermal imaging units are integrated into real-time response data of the outer surface temperature.

[0031] Further, step S200 further includes step S210 of collecting the temperature of the outer surface of the long-distance pipeline to be tested by using a deployed infrared thermal imaging array, wherein the infrared thermal imaging array includes a plurality of infrared thermal imaging units; step S220 of collecting the temperature of the outer surface of the long-distance pipeline to be tested by using the deployed infrared thermal imaging array and outputting an image time sequence corresponding to the plurality of infrared thermal imaging units; step S230 of performing temperature mapping according to a built-in temperature measurement calibration curve of each infrared thermal imaging unit and outputting a plurality of time-series temperature response matrices representing the temperature changes of each pixel position; and step S240 of fusing the plurality of time-series temperature response matrices to obtain real-time response data of the outer surface temperature of the long-distance pipeline to be tested.

[0032] Preferably, the infrared thermal imaging array includes a plurality of infrared thermal imaging units, each unit being an independent infrared camera including an infrared detector, an optical lens, and a signal processor, and being installed at equal intervals along the outer surface of the pipeline to ensure full coverage without dead angles. The infrared thermal imaging array is used to collect the temperature of the outer surface of the long-distance pipeline to be measured, i.e., each infrared thermal imaging unit captures thermal images at a fixed frequency to generate a time series of thermal images, and then outputs a time series of images corresponding to the plurality of infrared thermal imaging units. The temperature calibration curve refers to the mapping relationship between pixel grayscale value and temperature established by calibrating each infrared thermal imaging unit with a blackbody radiation source before leaving the factory. The temperature of each infrared thermal imaging unit is mapped according to the built-in temperature calibration curve to convert the pixel value of each thermal image into a temperature value to generate a time series temperature response matrix for representing the temperature change of each pixel position. Finally, the plurality of time series temperature response matrices are fused, i.e., the plurality of time series temperature response matrices are mapped to a unified pipeline three-dimensional coordinate system according to the installation position of the infrared thermal imaging unit, and the temperature values in the overlapping area are taken as a weighted average, wherein the weight is set based on the measurement distance. The final output is the real-time response data of the outer surface temperature of the long-distance pipeline to be measured, thereby providing high-resolution and high-reliability temperature field data for pipeline cleanliness detection.

[0033] Step S300, a heat transfer abnormal area recognition model is constructed by a pipeline three-dimensional transient heat transfer equation, and the outer surface temperature real-time response data is marked for abnormal areas according to the heat transfer abnormal area recognition model to obtain a heat transfer abnormal area.

[0034] Step S300 further includes the following steps: Step S310, finite element modeling is performed on the long-distance pipeline to be measured according to the basic parameters and operating environment information of the long-distance pipeline to be measured to obtain a three-dimensional pipeline structure model; Step S320, the three-dimensional pipeline structure model is simulated according to the injected gas type and the injected pulse signal to output outer surface temperature simulation response data; Step S330, a plurality of abnormal long-distance pipeline modeling samples containing known abnormal state labels are constructed; Step S340, the three-dimensional pipeline structure model is simulated according to the plurality of abnormal long-distance pipeline modeling samples to output a plurality of outer surface temperature abnormal simulation response data; and Step S350, the known abnormal state labels are trained for temperature response characteristics based on the outer surface temperature simulation response data and the plurality of outer surface temperature abnormal simulation response data to construct a heat transfer abnormal area recognition model.

[0035] Preferably, the basic parameters of the long-distance pipeline to be tested and the operating environment information are obtained, wherein the basic parameters include pipeline length, diameter, wall thickness, material density and thermal conductivity coefficient, etc., and the operating environment includes medium temperature, environment temperature, insulation layer thickness, etc., and then ANSYS, COMSOL or the like is used to perform finite element modeling on the long-distance pipeline to be tested based on the basic parameters and the operating environment information, and a three-dimensional pipeline structure model containing material properties and boundary conditions is output; then the three-dimensional pipeline structure model is simulated according to the type of injected gas and the injected pulse signal, wherein the expression of the pipeline three-dimensional transient heat conduction equation is as follows: wherein ρ is the material density of the long-distance pipeline to be tested, c p is the specific heat capacity, k is the thermal conductivity coefficient, is the rate of change of temperature T with time t, which describes the transient change of temperature with time, T is the temperature distribution, is the heat conduction term, is the temperature gradient, is the divergence operation, q(x, y, z, t) is the heat flux term, which represents the heat generated or consumed per unit volume per unit time by the pulse gas injection, and can vary with the spatial coordinates (x, y, z) and time t, and finally outputs the external surface temperature simulation response data, which can be simulation data of the external surface temperature change with time.

[0036] Preferably, for the pipeline historical failure data, a plurality of abnormal long-distance pipeline modeling samples containing known abnormal state labels are constructed, wherein the known abnormal state labels include but are not limited to dirt or residue, scaling / deposition, lubricating oil film, oxidation layer, ice crystal layer, for example, dirt or residue reduces the thermal conductivity coefficient of the pipeline, scaling / deposition increases the wall thickness of the pipeline, lubricating oil film forms a nanoscale film to hinder the heat transfer of the pipeline, oxidation layer causes the thermal conductivity of the pipeline to decrease, and ice crystal layer causes the pipeline to have a phase change latent heat effect (endothermic / exothermic); then the plurality of abnormal long-distance pipeline modeling samples are mapped on the three-dimensional pipeline structure model, and the pipeline three-dimensional transient heat conduction equation is simulated, that is, by solving the pipeline three-dimensional transient heat conduction equation, the dynamic temperature distribution of the external surface of the pipeline after the pulse gas injection is simulated, and a plurality of external surface temperature abnormal simulation response data are output, containing temperature response data corresponding to various abnormalities (such as oil stains, water stains, ice layers, etc.).

[0037] Preferably, the known abnormal state label is trained based on the outer surface temperature simulation response data and the plurality of outer surface temperature abnormal simulation response data, that is, the simulation temperature response data of the normal and abnormal pipelines are used to extract features and train a classification model through a machine learning algorithm, so that the classification model can automatically identify abnormal areas and their pollution types in the pipeline outer surface temperature data. Specifically, key features are extracted from the pipeline outer surface temperature response data, including temperature drop value, temperature drop rate, and temperature residual distribution. The abnormal area has a heat transfer blocked, and the temperature drop value is usually smaller than that of the normal area. The pollutant significantly reduces the cooling rate, and the temperature residual distribution refers to the difference between the actual data and the simulation data of the clean pipeline, reflecting the local anomaly. Then, the plurality of outer surface temperature abnormal simulation response data are mapped and associated with the known abnormal state label to form a supervised learning sample set. The supervised learning sample is used to classify and train a random forest model to construct a heat transfer abnormal area recognition model, which can output the abnormal area position and abnormal type probability of the pipeline according to the real-time infrared temperature data of the pipeline. An experimental cooling rate example is shown in FIG. 8, where the horizontal axis is the time 0-10 seconds, that is, the transient response stage after pulse injection, and the vertical axis is the temperature drop rate. The clean pipeline (Experimental clean) represents the ideal temperature drop state without dirt, the 50 μm dirt layer (Experimental 50 μm) is the simulated slightly contaminated pipeline temperature drop state, and the 200 μm dirt layer (Experimental 200 μm) is the simulated severely contaminated pipeline temperature drop state. The heat transfer efficiency of the clean pipeline is the highest, the thermal resistance of the 50 μm dirt layer increases by about 28%, and the thermal resistance of the 200 μm dirt layer increases by about 72%, which reduces the cooling rate to 20%-30% of the clean state. Figure 2

[0038] Further, the step S350 further includes a step S351 of establishing a control group of the outer surface temperature simulation response data and the plurality of outer surface temperature abnormal simulation response data, respectively, to obtain a plurality of groups of temperature simulation response training data; a step S352 of extracting a temperature response feature vector of the plurality of groups of temperature simulation response training data, the temperature response feature vector including a temperature drop value, a temperature drop rate, and a temperature residual distribution; and a step S353 of performing multi-classification training on a defined random forest based on the temperature drop value, the temperature drop rate, and the temperature residual distribution and the known abnormal state label to obtain a heat transfer abnormal area recognition model. The defined parameters of the random forest include the number of random forest trees, tree depth, sample tree segmentation, and leaf node sample tree.

[0039] ​Preferably, the established outer surface temperature simulation response data is compared with a plurality of outer surface temperature anomaly simulation response data, i.e. the normal pipeline simulation data is aligned with the corresponding abnormal pipeline simulation data at the same position and time point to form a structured data pair, and a plurality of sets of temperature simulation response training data are obtained; then the temperature response feature vectors of the plurality of sets of temperature simulation response training data are extracted, including temperature drop value, temperature drop rate and temperature residual distribution, wherein the temperature drop value is extracted by calculating the difference between the highest and lowest temperatures in the pulse period, the temperature drop rate is determined by first-order differentiation of the temperature curve, and the temperature residual distribution is determined by subtracting the measured value from the clean pipeline model prediction value, and then calculating the standard deviation and extreme value.

[0040] Preferably, the random forest defined based on the temperature drop value, the temperature drop rate, the temperature residual distribution and the known abnormal state label is subjected to multi-classification training, the random forest distinguishes between multiple abnormal types through a voting mechanism, and finally a heat transfer abnormal region recognition model is obtained, which can identify the abnormal type and corresponding probability of each region of the pipeline, wherein the defined parameters of the random forest include the number of random forest trees, tree depth, split sample tree and leaf node sample tree, the number of random forest trees is used to increase the robustness of the model and reduce overfitting, such as 200; the tree depth is used to control the complexity of the model to prevent overfitting, such as 15; the split sample number refers to the minimum number of samples required for node splitting to avoid over-fine division, such as 8; and the leaf node sample number refers to the minimum number of samples in the leaf node, which is used to smooth the prediction result, such as 3.

[0041] Further, step S300 further comprises step S360 of extracting temperature response feature vectors from the heat transfer abnormal region recognition model according to the real-time response data of the outer surface temperature, outputting real-time temperature drop value, real-time temperature drop rate and real-time temperature residual distribution; and step S370 of performing random forest classification and recognition according to the real-time temperature drop value, the real-time temperature drop rate and the real-time temperature residual distribution to obtain the heat transfer abnormal region and the heat transfer abnormal response data of the heat transfer abnormal region.

[0042] Preferably, the heat transfer abnormal area identification model extracts the temperature response feature vector from the real-time response data of the outer surface temperature. Specifically, the difference between the highest and lowest temperatures in the current pulse period is calculated to determine the real-time temperature drop value. For example, the real-time temperature drop value of the normal area is 4.2°C, and the real-time temperature drop value of the contaminated area is 2.5°C. The cooling speed is calculated by differential calculation of the temperature curve to determine the real-time temperature drop rate. For example, the rate of the oil pollution area drops to 40% of the normal value. The measured data is compared with the predicted value of the pre-stored clean pipeline heat transfer model to generate a residual matrix and determine the real-time temperature residual distribution. For example, the abnormal area usually presents a local residual of >1.5°C. Then, the real-time temperature drop value, the real-time temperature drop rate, and the real-time temperature residual distribution are input into the heat transfer abnormal area identification model to output the abnormal area positioning, i.e., the pipeline coordinate section with abnormal temperature response, through the multi-decision tree voting mechanism. The abnormal type determination, i.e., the probability distribution of the contaminant type, and the abnormal response data, which may include the position, area, temperature characteristic deviation degree, etc., are output. Finally, the heat transfer abnormal area and the heat transfer abnormal response data corresponding to the heat transfer abnormal area are obtained.

[0043] Step S400, analyze the heat transfer abnormal response data of the heat transfer abnormal area to generate the cleanliness detection result of the long-distance pipeline to be tested.

[0044] Step S400 further includes step S410, quantifying the heat transfer abnormal response data of the heat transfer abnormal area to output a comprehensive abnormality index, wherein the heat transfer abnormal response data includes the area position, area size, and abnormality level of the heat transfer abnormal area. Step S420, convert the cleanliness according to the comprehensive abnormality index to obtain the cleanliness detection result of the long-distance pipeline to be tested.

[0045] Preferably, the heat transfer anomaly response data of the heat transfer anomaly area is analyzed and quantified, and converted into an intuitive pipeline cleanliness evaluation result. Specifically, the heat transfer anomaly response data of the heat transfer anomaly area is quantified as an anomaly, that is, the area position, area size and anomaly level of the heat transfer anomaly area are weighted and scored. The distance from the pipeline inlet is standardized to 0-1 (inlet = 0, end = 1), the near-end anomaly weight is higher, the percentage of the anomaly area in the total surface area of the pipeline is calculated and multiplied by an amplification coefficient (for example, oil stain x 1.0, scale x 1.5, ice crystal x 0.8), the product of the probability value and the temperature deviation degree calculated by the model determines the anomaly level, and the weights of the area position, area size and anomaly level of the heat transfer anomaly area are set to 30%, 40% and 30% respectively according to experimental data, and then a comprehensive anomaly index is output. Then, the cleanliness conversion is performed according to the comprehensive anomaly index, that is, the comprehensive anomaly index is mapped to the cleanliness level according to the comprehensive anomaly index-cleanliness mapping relationship, and finally the cleanliness detection result of the long-distance pipeline to be tested is determined. For example, the comprehensive anomaly index 0-30 represents that the pollution coverage is <0.5%, the heat transfer efficiency loss is <3%, and the cleanliness level is excellent and no treatment is required; the comprehensive anomaly index 30-60 represents that there is local micro-deposition (such as oil film), the efficiency loss is 3-10%, and the cleanliness level is good and planned inspection is required; the comprehensive anomaly index 60-80 represents that there is obvious scaling (such as scale), the efficiency loss is 10-25%, and the cleanliness level is warning and cleaning treatment is required within 3 months; and the comprehensive anomaly index 80-100 represents that there is large-area pollution or ice blockage, and the efficiency loss is >25%, and the cleanliness level is dangerous and cleaning treatment is required to stop the pipeline operation.

[0046] In the foregoing, with reference to Figure 1 The cleaning degree detection method suitable for long-distance refrigeration pipeline according to the embodiments of the present application is described in detail. Next, the cleaning degree detection device suitable for long-distance refrigeration pipeline according to the embodiments of the present application will be described with reference to Figure 3 The cleaning degree detection device suitable for long-distance refrigeration pipeline according to the embodiments of the present application is described in detail. Next, the cleaning degree detection device suitable for long-distance refrigeration pipeline according to the embodiments of the present application will be described with reference to

[0047] The cleaning degree detection device suitable for long-distance refrigeration pipeline according to the embodiments of the present application is described in detail. Next, the cleaning degree detection device suitable for long-distance refrigeration pipeline according to the embodiments of the present application will be described with reference to Figure 3 As shown in FIG. 1, the cleaning degree detection device suitable for long-distance refrigeration pipeline includes an injection data determination module 10, a response data output module 20, an anomaly area marking module 30 and a cleanliness detection result generation module 40.

[0048] The injection data determination module 10 is configured to determine an injection gas type and an injection pulse signal of a long-distance pipeline to be tested; the response data output module 20 is configured to access a liquid nitrogen vaporization device at an inlet of the long-distance pipeline to be tested, the liquid nitrogen vaporization device controls a pulse injection valve to inject gas into the inlet of the long-distance pipeline to be tested through the injection gas type and the injection pulse signal, and collects temperature of an outer surface of the long-distance pipeline to be tested by using a deployed infrared thermal imaging array, and outputs real-time response data of the outer surface temperature; the abnormal area marking module 30 is configured to construct a heat transfer abnormal area identification model by using a pipeline three-dimensional transient heat transfer equation, mark an abnormal area according to the heat transfer abnormal area identification model based on the real-time response data of the outer surface temperature, and obtain a heat transfer abnormal area; and the cleanliness detection result generation module 40 is configured to analyze heat transfer abnormal response data of the heat transfer abnormal area, and generate a cleanliness detection result of the long-distance pipeline to be tested.

[0049] Next, the specific configuration of the abnormal area marking module 30 will be described in detail. The abnormal area marking module 30 further comprises: performing finite element modeling on the long-distance pipeline to be tested according to basic parameters and operating environment information of the long-distance pipeline to be tested, and obtaining a three-dimensional pipeline structure model; performing pipeline three-dimensional transient heat transfer equation simulation on the three-dimensional pipeline structure model according to the injection gas type and the injection pulse signal, and outputting simulated response data of the outer surface temperature; constructing a plurality of abnormal long-distance pipeline modeling samples containing known abnormal state labels; performing pipeline three-dimensional transient heat transfer equation simulation on the three-dimensional pipeline structure model according to the plurality of abnormal long-distance pipeline modeling samples, and outputting a plurality of simulated response data of the outer surface temperature; and performing temperature response feature training on the known abnormal state labels based on the simulated response data of the outer surface temperature and the plurality of simulated response data of the outer surface temperature, and constructing a heat transfer abnormal area identification model.

[0050] Next, the specific configuration of the abnormal area marking module 30 will be described in detail. The abnormal area marking module 30 further comprises: establishing a control group of the simulated response data of the outer surface temperature and the plurality of simulated response data of the outer surface temperature, and obtaining a plurality of groups of temperature simulation response training data; extracting a temperature response feature vector of the plurality of groups of temperature simulation response training data, the temperature response feature vector comprising a temperature drop value, a temperature drop rate, and a temperature residual distribution; performing multi-classification training on a defined random forest based on the temperature drop value, the temperature drop rate, the temperature residual distribution, and the known abnormal state labels, and obtaining a heat transfer abnormal area identification model; wherein the defined parameters of the random forest comprise the number of random forest trees, the tree depth, the sample tree for splitting, and the leaf node sample tree.

[0051] The specific configuration of the response data output module 20 will be described in detail below. The response data output module 20 further comprises: collecting the temperature of the outer surface of the long-distance pipeline to be tested by deploying an infrared thermal imaging array, wherein the infrared thermal imaging array comprises a plurality of infrared thermal imaging units; collecting the temperature of the outer surface of the long-distance pipeline to be tested by deploying the infrared thermal imaging array, and outputting the image time sequence corresponding to the plurality of infrared thermal imaging units; performing temperature mapping according to the temperature calibration curve built-in each infrared thermal imaging unit, and outputting a plurality of time-series temperature response matrices representing the temperature change of each pixel position; and fusing the plurality of time-series temperature response matrices to obtain the outer surface temperature real-time response data corresponding to the long-distance pipeline to be tested.

[0052] The specific configuration of the abnormal area marking module 30 will be described in detail below. The abnormal area marking module 30 further comprises: extracting a temperature response feature vector from the outer surface temperature real-time response data according to the heat transfer abnormal area identification model, and outputting a real-time temperature drop value, a real-time temperature drop rate, and a real-time temperature residual error distribution; performing random forest classification and identification according to the real-time temperature drop value, the real-time temperature drop rate, and the real-time temperature residual error distribution to obtain a heat transfer abnormal area and heat transfer abnormal response data of the heat transfer abnormal area.

[0053] The specific configuration of the cleanliness detection result generation module 40 will be described in detail below. The cleanliness detection result generation module 40 further comprises: quantifying the heat transfer abnormal response data of the heat transfer abnormal area, and outputting a comprehensive abnormality index, wherein the heat transfer abnormal response data includes the area position, area size, and abnormality level of the heat transfer abnormal area; and converting the cleanliness according to the comprehensive abnormality index to obtain the cleanliness detection result of the long-distance pipeline to be tested.

[0054] The specific configuration of the injection data determination module 10 will be described in detail below. The injection data determination module 10 further comprises: determining the injection gas type of the long-distance pipeline to be tested, wherein the injection gas type is a fluorocarbon or CO2 gas with a boiling point lower than -40°C.

[0055] The specific configuration of the injection data determination module 10 will be described in detail below. The injection data determination module 10 further comprises: obtaining the pipeline length and thermal response time constant of the long-distance pipeline to be tested; performing pipeline response effectiveness scoring according to the pipeline length and thermal response time constant of the long-distance pipeline to be tested; performing pulse signal frequency, amplitude, and duration cycle optimization under the constraint condition that the preset response effectiveness scoring threshold is satisfied; and generating an injection pulse signal.

[0056] The cleaning degree detection device suitable for the long-distance refrigeration pipeline provided by the embodiment of the present application can execute the cleaning degree detection method suitable for the long-distance refrigeration pipeline provided by any embodiment of the present application, has the function modules and beneficial effects corresponding to the execution method.

[0057] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server, the various units and modules included are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for the convenience of mutual differentiation, and do not limit the protection scope of the present application.

[0058] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting the cleanliness of long-distance refrigeration pipelines, characterized in that, The method includes: Determine the type of gas to be injected and the injection pulse signal for the long-distance pipeline under test; A liquid nitrogen vaporization device is connected to the inlet of the long-distance pipeline under test. The liquid nitrogen vaporization device controls the pulse injection valve to inject gas into the inlet of the long-distance pipeline under test through the type of injected gas and the injection pulse signal. At the same time, an infrared thermal imaging array is deployed to collect the temperature of the outer surface of the long-distance pipeline under test and output the real-time response data of the outer surface temperature. A heat transfer anomaly region identification model is constructed by the three-dimensional transient heat transfer equation of the pipeline. Based on the heat transfer anomaly region identification model, the real-time response data of the outer surface temperature is marked as anomaly region to obtain the heat transfer anomaly region. Analyze the heat transfer anomaly response data of the heat transfer anomaly area to generate the cleanliness test results of the long-distance pipeline under test.

2. The cleanliness detection method for long-distance refrigeration pipelines as described in claim 1, characterized in that, A heat transfer anomaly region identification model is constructed using the three-dimensional transient heat transfer equation of a pipeline. The method includes: Based on the basic parameters and operating environment information of the long-distance pipeline to be tested, a finite element model is performed on the long-distance pipeline to be tested to obtain a three-dimensional pipeline structure model; The three-dimensional transient heat transfer equation of the pipeline structure model is simulated according to the injected gas type and injection pulse signal, and the simulated response data of the outer surface temperature is output. Construct multiple abnormal long-distance pipeline modeling samples containing known abnormal state labels; Based on the modeling samples of multiple abnormal long-distance pipelines to be tested, the three-dimensional pipeline structure model is simulated by the three-dimensional transient heat transfer equation of the pipeline, and multiple simulated response data of abnormal external surface temperature are output. Based on the simulated response data of the outer surface temperature and the simulated response data of multiple outer surface temperature anomalies, the temperature response features of the known abnormal state labels are trained to construct a heat transfer anomaly region identification model.

3. The cleanliness detection method for long-distance refrigeration pipelines as described in claim 2, characterized in that, The method for training temperature response features on the known abnormal state labels based on the simulated response data of the outer surface temperature and multiple simulated response data of outer surface temperature anomalies includes: Establish control groups for the simulated response data of the outer surface temperature and multiple simulated response data of the outer surface temperature anomaly, and obtain multiple sets of temperature simulation response training data. Extract the temperature response feature vector from the multiple sets of temperature simulation response training data. The temperature response feature vector includes the temperature drop value, the temperature drop rate, and the temperature residual distribution. Based on the temperature drop value, temperature drop rate, temperature residual distribution, and known abnormal state labels, a multi-class classification training is performed on the defined random forest to obtain a heat transfer anomaly region identification model. The defining parameters of a random forest include the number of random forest trees, tree depth, split sample trees, and leaf node sample trees.

4. The cleanliness detection method for long-distance refrigeration pipelines as described in claim 1, characterized in that, The temperature of the outer surface of the long-distance pipe under test is collected by a deployed infrared thermal imaging array, wherein the infrared thermal imaging array includes multiple infrared thermal imaging units. The temperature of the outer surface of the long-distance pipe under test is collected by the deployed infrared thermal imaging array, and the image time series corresponding to the multiple infrared thermal imaging units is output. Temperature mapping is performed based on the built-in temperature calibration curve of each infrared thermal imaging unit, and multiple time-series temperature response matrices characterizing the temperature change at each pixel location are output. The real-time response data of the outer surface temperature of the long-distance pipeline under test is obtained by fusing the multiple time-series temperature response matrices.

5. The cleanliness detection method for long-distance refrigeration pipelines as described in claim 1, characterized in that, The abnormal regions are identified by marking the real-time response data of the outer surface temperature according to the heat transfer anomaly identification model. The method includes: Based on the heat transfer anomaly region identification model, the temperature response feature vector of the real-time external surface temperature response data is extracted, and the real-time temperature drop value, real-time temperature drop rate and real-time temperature residual distribution are output. Random forest classification is performed based on the real-time temperature drop value, real-time temperature drop rate, and real-time temperature residual distribution to obtain heat transfer anomaly regions and heat transfer anomaly response data of the heat transfer anomaly regions.

6. The cleanliness detection method for long-distance refrigeration pipelines as described in claim 5, characterized in that, Analyzing the heat transfer anomaly response data in the heat transfer anomaly region to generate the cleanliness detection result of the long-distance pipeline under test, the method includes: The heat transfer anomaly response data of the heat transfer anomaly region is quantified to output a comprehensive anomaly index. The heat transfer anomaly response data includes the regional location, area, and anomaly level of the heat transfer anomaly region. The cleanliness test result of the long-distance pipeline under test is obtained by converting the cleanliness index according to the comprehensive anomaly index.

7. The cleanliness detection method for long-distance refrigeration pipelines as described in claim 1, characterized in that, The type of gas to be injected into the long-distance pipeline to be tested is determined. The type of gas to be injected is a fluorocarbon or CO2 gas with a boiling point below -40°C.

8. The cleanliness detection method for long-distance refrigeration pipelines as described in claim 1, characterized in that, Methods for determining the injection pulse signal of a long-distance pipeline under test include: Obtain the pipe length and thermal response time constant of the long-distance pipe to be tested; The pipeline response effectiveness score is calculated based on the pipeline length and thermal response time constant of the long-distance pipeline under test. The frequency, amplitude and duration of the pulse signal are optimized to generate the injected pulse signal, with the preset response effectiveness score threshold as a constraint.

9. A cleanliness testing device suitable for long-distance refrigeration pipelines, characterized in that, The apparatus is used to implement the cleanliness detection method for long-distance refrigeration pipelines as described in any one of claims 1 to 8, and the apparatus comprises: The injection data determination module is used to determine the type of injected gas and the injection pulse signal for the long-distance pipeline under test; The response data output module is used to connect a liquid nitrogen vaporization device to the inlet of the long-distance pipeline under test. The liquid nitrogen vaporization device controls the pulse injection valve to inject gas into the inlet of the long-distance pipeline under test through the type of injected gas and the injection pulse signal. At the same time, the deployed infrared thermal imaging array collects the temperature of the outer surface of the long-distance pipeline under test and outputs real-time response data of the outer surface temperature. The abnormal region marking module is used to construct a heat transfer abnormal region identification model through the three-dimensional transient heat transfer equation of the pipeline, and mark the abnormal region of the real-time response data of the outer surface temperature according to the heat transfer abnormal region identification model to obtain the heat transfer abnormal region. The cleanliness test result generation module is used to analyze the heat transfer anomaly response data of the heat transfer anomaly area and generate the cleanliness test result of the long-distance pipeline under test.

Images