Method and system for predicting freezing resistance of pipeline of automatic sprinkler system

Abstract

The invention provides a pipeline freezing resistance prediction method and system of an automatic sprinkler system. The method comprises the following steps: in a cold environment monitoring area, capturing an ice crystal growth vibration signal through an acoustic emission sensor, and synchronously associating real-time icing rate data; inputting a multi-scale long-short-term memory network, and outputting composite freezing features through a short-time-span memory unit and a long-time-span memory unit; the transmitting power and the modulation rate of the LoRaWAN node are adjusted in a self-adaptive mode, and the high-priority composite freezing characteristics and the geographic position codes of the corresponding pipe sections are transmitted to a far-end control center; ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics are matched based on a pipeline material ice expansion coefficient database, the fracture risk probability of the specific pipe section is calculated, and a pipeline electric heat tracing gradient temperature rising strategy corresponding to the fracture risk probability is activated. According to the technical scheme provided by the invention, the cracking risk of the pipeline of the automatic water-spraying fire extinguishing system in the cold environment is accurately predicted and effectively reduced.

Description

Technical Field

[0001] This application relates to the technical field of data prediction, and particularly to a method and system for predicting the anti-freezing property of pipes in an automatic sprinkler system. Background Art

[0002] In a wet automatic sprinkler system in a cold environment, the freezing caused by the phase change of the fluid inside the pipe can lead to material deformation or even rupture, posing a safety hazard. Traditional anti-freezing measures are difficult to monitor the dynamic process of ice crystal growth in real time, especially the microsecond-level stress changes caused by the instantaneous rupture of ice crystals and the low-frequency cumulative effect of material fatigue deformation. Therefore, an intelligent monitoring and control technology that can accurately capture the dynamic characteristics of ice formation inside the pipe, evaluate the rupture risk, and dynamically adjust the protection strategy is needed to ensure the safe operation of the fire-fighting pipes.

[0003] At present, a technical solution for this requirement is the static threshold control based on temperature sensors combined with an electric tracing system. This solution monitors the ambient temperature through temperature sensors arranged on the pipe surface. When the temperature is lower than a preset threshold (such as 4°C), the electric tracing device is started to uniformly heat the pipe to prevent freezing. Some solutions also combine heat-insulating materials to wrap the pipe to slow down heat dissipation, and reduce the freezing risk by periodically pressurizing and draining water.

[0004] The existing solutions rely on temperature thresholds to trigger passive heating and cannot sense dynamic characteristics such as the ice crystal growth rate and material stress changes. For example, the temperature sensor cannot capture the instantaneous vibration signal of ice crystal rupture and the low-frequency oscillation of material fatigue accumulation, resulting in the inability to evaluate the actual ice thickness and the pipe deformation risk; the uniform heating lacks targeted regulation of high-risk pipe sections, which may cause energy waste; the static threshold control cannot predict the critical freezing state, which may lead to the pipe entering a high-risk stage when the protection measure is started, resulting in a high rupture risk of the pipes in the automatic sprinkler system in a cold environment. Summary of the Invention

[0005] This application provides a method and system for predicting the anti-freezing property of pipes in an automatic sprinkler system to solve the problem of high rupture risk of pipes in a wet automatic sprinkler system in a cold environment in the prior art.

[0006] In a first aspect, this application provides a method for predicting the anti-freezing property of pipes in an automatic sprinkler system, including:

[0007] Collecting the ice crystal growth vibration signals caused by the phase change of the fluid inside the pipe wall of the automatic sprinkler system through an acoustic emission sensor, and synchronously correlating the real-time ice formation rate data collected by the temperature sensor mounted on the pipe surface;

[0008] Input the ice crystal growth vibration signal and the real-time icing rate data into a multi-scale long short-term memory network. The short-time-span memory unit captures the microsecond-level pulse waveform triggered by the instantaneous rupture of ice crystals, while the long-time-span memory unit tracks the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material, and outputs a composite freezing feature;

[0009] According to the spatial distribution of the pipeline network and the priority of the composite freezing feature, adaptively adjust the transmission power and modulation rate of the LoRaWAN node, encode the high-priority composite freezing feature and the geographical location of the corresponding pipe section into an emergency data frame, and preferentially transmit it to the remote control center through multi-hop routing;

[0010] Based on the ice expansion coefficient database of the pipeline material pre-stored in the remote control center, match the ice crystal dynamic parameters and material stress parameters in the composite freezing feature, calculate the rupture risk probability of a specific pipe section at the critical icing thickness, predict the anti-freezing property of the pipeline based on the rupture risk probability, and activate the pipeline heating strategy corresponding to the rupture risk probability according to the anti-freezing property prediction result.

[0011] Optionally, the step of inputting the ice crystal growth vibration signal and the real-time icing rate data into a multi-scale long short-term memory network, where the short-time-span memory unit captures the microsecond-level pulse waveform triggered by the instantaneous rupture of ice crystals, while the long-time-span memory unit tracks the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material, and outputs a composite freezing feature, includes:

[0012] Before the ice crystal growth vibration signal is input into the multi-scale long short-term memory network, perform vibration component elimination processing for non-phase change interference on the ice crystal growth vibration signal, and retain the vibration component coaxial with the pipeline axial stress direction;

[0013] Input the vibration component into the time-frequency decomposition layer to separate the high-frequency sub-signal representing the instantaneous rupture of ice crystals and the low-frequency sub-signal reflecting the plastic deformation of the material. At the same time, convert the real-time icing rate data into an icing dynamic coefficient aligned with the time stamps of each sub-signal;

[0014] Input the high-frequency sub-signal into the short-time-span memory unit for microsecond-level waveform profile tracking, capture the phase mutation points between adjacent ice crystal rupture events, and input the low-frequency sub-signal and the icing dynamic coefficient into the long-time-span memory unit for oscillation mode correlation to establish an implicit correlation between the change in the pipe cross-section ellipticity and the stress relaxation rate;

[0015] Perform dynamic weight allocation on the phase mutation points and the implicit correlation, and combine the pre-stored Young's modulus parameter and thermal expansion coefficient parameter of the pipeline to generate a composite freezing feature including the ice crystal distribution gradient and the attenuation trend of the material yield strength.

[0016] Optionally, according to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, adaptively adjust the transmission power and modulation rate of LoRaWAN nodes, and encode high-priority composite freezing characteristics and the geographical location of corresponding pipe segments into emergency data frames, and preferentially transmit them to the remote control center through multi-hop routing, including:

[0017] Analyze the pipeline rupture risk probability and stress concentration factor in the composite freezing characteristics, and combine the distance parameters of adjacent nodes and historical signal interference parameters in the pipeline distribution topology to calculate the dynamic transmission path loss threshold of each LoRaWAN node;

[0018] According to the dynamic transmission path loss threshold and the change rate of the ice crystal distribution gradient in the composite freezing characteristics, dynamically allocate the transmission power level and orthogonal modulation index, and synchronously combine the remaining energy parameter of the node to constrain the maximum adjustable power range;

[0019] Classify and encode high-priority composite freezing characteristics and the geographical location of corresponding pipe segments according to the pipe diameter specification, construct a frame header containing the pipe segment identifier and a check field of the ice crystal growth azimuth angle, and generate an emergency data frame with a topology-aware mark;

[0020] Based on the pre-stored metal obstacle attenuation map in the pipeline distribution topology, select a relay node sequence with the minimum path fading, and realize the multi-hop relay transmission of the emergency data frame by alternately using the ground reflection wave and direct wave propagation modes.

[0021] Optionally, the dynamically allocating the transmission power level and orthogonal modulation index according to the dynamic transmission path loss threshold and the change rate of the ice crystal distribution gradient in the composite freezing characteristics, and synchronously combining the remaining energy parameter of the node to constrain the maximum adjustable power range includes:

[0022] Establish a transmission power allocation model, and convert the change rate of the ice crystal distribution gradient and the remaining energy parameter of the node in the composite freezing characteristics into a power allocation reference value through the thermodynamic expansion margin;

[0023] Calibrate the phase sensitivity of the orthogonal modulation index according to the dynamic transmission path loss threshold. When the dynamic transmission path loss threshold exceeds the theoretical attenuation value of the pipeline insulation layer, trigger a compensation mechanism for the orthogonal modulation index to shift in the direction of anti-multipath interference, and output a time-varying compensation coefficient;

[0024] Inject the time-varying compensation coefficient into the transmission power allocation model. When the frost layer thickness exceeds the critical value of the sealing gap at the metal flange connection, trigger a transient overload transmission power pulse based on the power allocation reference value, and constrain the transient overload transmission power pulse within the maximum adjustable power range allowed by the remaining energy parameter of the node;

[0025] Perform time-slot interleaving coding on the quadrature modulation cable after phase sensitivity calibration and the power levels of the transient overload emission power pulses to generate an adaptive communication parameter configuration table adapted to the Doppler frequency shift characteristics at the pipe elbow.

[0026] Optionally, when injecting the time-varying compensation coefficient into the emission power distribution model, when the frost layer thickness exceeds the critical value of the sealing gap at the metal flange connection, trigger a transient overload emission power pulse based on the power distribution reference value, and constrain the transient overload emission power pulse within the maximum adjustable power range allowed by the remaining energy parameters of the node, including:

[0027] Input the time-varying compensation coefficient into the emission power distribution model, and combine the real-time growth rate of the frost layer thickness and the latent heat of phase change parameters of the pipe metal material to generate dynamic overload power margin parameters. The nodes corresponding to the pipe sections where the frost layer thickness exceeds the critical value of the sealing gap automatically activate the margin parameter compensation channel;

[0028] Based on the change rate of the ice crystal distribution gradient, perform azimuth weighting processing on the dynamic overload power margin parameters through the margin parameter compensation channel, and use the pipe axial stress distribution pattern to perform phase modulation on the waveform envelope of the transient overload emission power pulse to generate a pulse parameter set that matches the verification field of the ice crystal growth azimuth angle;

[0029] Based on the creep parameters of the sealing material and the bolt pre-tightening force attenuation coefficient at the metal flange connection, establish a time-domain energy distribution constraint condition to make the pulse parameter set form a non-uniform energy density distribution within the maximum adjustable power range allowed by the remaining energy parameters of the node;

[0030] Perform time-slot interleaving on the non-uniform energy density distribution and the dynamic overload power margin parameters to generate a transient overload emission instruction set carrying the stress concentration factor correction parameters at the metal flange connection.

[0031] Optionally, based on the change rate of the ice crystal distribution gradient, perform azimuth weighting processing on the dynamic overload power margin parameters through the margin parameter compensation channel, and use the pipe axial stress distribution pattern to perform phase modulation on the waveform envelope of the transient overload emission power pulse to generate a pulse parameter set that matches the verification field of the ice crystal growth azimuth angle, including:

[0032] Decompose the change rate of the ice crystal distribution gradient into the pipe axial ice crystal growth rate and the radial penetration rate components, and combine the residual stress parameters at the pipe weld to perform stress relaxation weight distribution on the two components to generate an ice crystal azimuth anisotropy compensation coefficient;

[0033] Compensate the anisotropic thermal conductivity of the metal material of the input pipeline of the channel through the remaining parameter, and correct the heat flux density vector of the dynamic overload power margin parameter by combining the anisotropic compensation coefficient of the ice crystal azimuth angle to generate an azimuth angle weighted matrix aligned with the main direction of ice crystal growth;

[0034] Based on the pipeline ovality deformation parameter, perform phase modulation on the waveform envelope of the transient overload emission power pulse, and generate a pulse amplitude attenuation gradient template by using the circumferential distribution characteristics of the bolt array at the metal flange connection;

[0035] Perform tensor fusion on the azimuth angle weighted matrix and the pulse amplitude attenuation gradient template, and combine the pipeline circumferential temperature gradient data recorded in the check field of the ice crystal growth azimuth angle to generate a pulse parameter set matching the check field of the ice crystal growth azimuth angle.

[0036] Optionally, based on the pipeline material ice expansion coefficient database pre-stored in the remote control center, match the ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics, and calculate the rupture risk probability of a specific pipe section at the critical ice thickness, including:

[0037] Decompose the ice crystal dynamic parameters in the composite freezing characteristics into the ice crystal axial growth rate and the ice crystal radial penetration rate, and combine the low-temperature phase change characteristic parameters and yield strength attenuation gradient of the pipe material in the pipeline material ice expansion coefficient database pre-stored in the remote control center to generate an ice layer thickness-pipe material stress coupling increment distribution map;

[0038] According to the historical frost heave deformation records of the pipe section stored in the pipeline material ice expansion coefficient database, match the direction of the maximum principal stress in the ice layer thickness-pipe material stress coupling increment distribution map, and combine the material stress parameters corresponding to the actual service life of the pipeline to generate a dynamic ice expansion stress concentration factor;

[0039] Based on the proportional relationship between the critical ice thickness in the composite freezing characteristics and the dynamic ice expansion stress concentration factor, introduce the anisotropic expansion coefficient of the pipeline material and the flange assembly prestress parameter, and calculate the rupture risk probability of a specific pipe section under the proportional relationship.

[0040] Optionally, predict the frost resistance of the pipeline based on the rupture risk probability, and activate the pipeline heating strategy corresponding to the rupture risk probability according to the frost resistance prediction result, including:

[0041] Based on the rupture risk probability, combine the low-temperature brittle transition temperature of the pipeline material and the ice crystal growth stress field distribution, divide the frost resistance level of the pipe section, and generate a pipeline frost resistance prediction result containing a frost resistance level identifier;

[0042] According to the anti-freezing level identifier, match the pre-stored pipeline heating-up strategy library, and extract the heating-up rate and target temperature corresponding to the anti-freezing level of the pipe segment.

[0043] Based on the spatial correlation between the axial stress distribution pattern of the pipeline and the ice crystal penetration path, activate the electric tracing heating areas in descending order of the anti-freezing level of the pipe segment, and generate a progressive heating-up instruction set for sub-sections.

[0044] Execute the progressive heating-up instruction set for sub-sections, combine the heating-up rate, the target temperature and the real-time frost layer thickness data on the pipeline surface, dynamically adjust the output of the electric tracing heating power, and generate a pipeline heating-up control signal matching the probability of rupture risk.

[0045] In a second aspect, the present application provides a pipeline anti-freezing prediction system for an automatic sprinkler system, including:

[0046] A capture module, configured to collect ice crystal growth vibration signals caused by the phase change of the internal fluid of the pipeline wall of the automatic sprinkler system through an acoustic emission sensor, and synchronously correlate the real-time icing rate data collected by a temperature sensor mounted on the pipeline surface.

[0047] An output module, configured to input the ice crystal growth vibration signals and the real-time icing rate data into a multi-scale long short-term memory network, capture the microsecond-level pulse waveform caused by the instantaneous rupture of ice crystals through a short-time-span memory unit, and simultaneously track the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material through a long-time-span memory unit, and output composite freezing characteristics.

[0048] A transmission module, configured to adaptively adjust the transmission power and modulation rate of LoRaWAN nodes according to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, encode the high-priority composite freezing characteristics and the geographical location of the corresponding pipe segment into an emergency data frame, and preferentially transmit it to a remote control center through multi-hop routing.

[0049] An activation module, configured to match the ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics based on the ice expansion coefficient database of the pipeline material pre-stored in the remote control center, calculate the rupture risk probability of a specific pipe segment at the critical icing thickness, predict the anti-freezing property of the pipeline based on the rupture risk probability, and activate a pipeline heating-up strategy corresponding to the rupture risk probability according to the anti-freezing prediction result.

[0050] In a third aspect, the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a pipeline anti-freezing prediction method for an automatic sprinkler system as described in the first aspect above.

[0051] In the embodiment of the present application, an acoustic emission sensor is used to collect the ice crystal growth vibration signals caused by the phase change of the internal fluid in the pipeline wall of the automatic sprinkler system, and synchronously correlate the real-time icing rate data collected by the temperature sensor mounted on the pipeline surface; the ice crystal growth vibration signals and the real-time icing rate data are input into a multi-scale long short-term memory network. The short-term memory unit captures the microsecond-level pulse waveform caused by the instantaneous rupture of ice crystals, and at the same time, the long-term memory unit tracks the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material, and outputs composite freezing characteristics; according to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, the transmission power and modulation rate of the LoRaWAN node are adaptively adjusted, and the high-priority composite freezing characteristics and the geographical location of the corresponding pipe section are encoded into an emergency data frame, which is preferentially transmitted to the remote control center through multi-hop routing; based on the pipeline material ice expansion coefficient database pre-stored in the remote control center, the ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics are matched, the rupture risk probability of a specific pipe section at the critical icing thickness is calculated, the anti-freezing of the pipeline is predicted based on the rupture risk probability, and the pipeline heating strategy corresponding to the rupture risk probability is activated according to the anti-freezing prediction result.

[0052] The technical solution of the present application has the following beneficial effects:

[0053] By collecting the vibration signals of ice crystal growth on the pipeline wall through an acoustic emission sensor and combining the real-time icing rate data of the temperature sensor, multi-dimensional dynamic monitoring of the internal phase change process of the pipeline is realized, improving the comprehensiveness and real-time of freeze risk identification; using the short-term memory unit to capture the microsecond-level pulse waveform of the instantaneous rupture of ice crystals (such as crack propagation signals), and at the same time, using the long-term memory unit to track the low-frequency oscillation of the fatigue deformation of the pipeline material (such as stress relaxation trend), enhancing the analysis accuracy of composite freezing characteristics; according to the spatial distribution of the pipeline network and the priority of freezing characteristics, dynamically optimizing the transmission power and modulation rate of the LoRaWAN node, encoding high-priority data and geographical location into an emergency data frame, preferentially ensuring the efficient transmission of key information, and reducing the response delay caused by network congestion; based on the pre-stored pipeline material ice expansion coefficient database, matching the ice crystal dynamic parameters and material stress parameters, accurately calculating the rupture risk probability at the critical icing thickness, and activating the electric tracing gradient heating strategy to avoid chain ruptures caused by local overload of the pipeline.

[0054] Further, by performing vibration component elimination processing on the ice crystal growth vibration signal to remove non-phase change interference vibrations, the vibration components coaxial with the pipeline axial stress direction are retained, and further combined with the high-frequency and low-frequency sub-signals separated by the time-frequency decomposition layer. The phase mutation points between adjacent ice crystal rupture events are traced respectively, and an implicit correlation between the change in pipeline cross-section ellipticity and the stress relaxation rate is established. Finally, a composite freezing feature including the ice crystal distribution gradient and the attenuation trend of material yield strength is generated through dynamic weight allocation. This process significantly improves the accurate recognition ability of the dynamic growth of internal ice crystals in the pipeline and their impact on materials, enhances the prediction accuracy of the frost resistance of the automatic sprinkler system pipeline in extremely cold environments, and effectively reduces the risk of pipeline rupture caused by freezing.

[0055] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0057] Figure 1 The flowchart of a method for predicting the frost resistance of a pipeline of an automatic sprinkler system provided by the present application is shown;

[0058] Figure 2 The structural schematic diagram of a system for predicting the frost resistance of a pipeline of an automatic sprinkler system provided by the present application is shown;

[0059] Figure 3 The structural schematic diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] In order to enable those skilled in the art to better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0061] In some of the processes described in the specification, claims, and the above-mentioned drawings of this application, a number of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any order of execution. Additionally, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., do not represent a sequence, and do not limit that "first" and "second" are of different types.

[0062] The research and development idea of this solution is as follows: First, deploy an acoustic emission and temperature sensor network, capture the physical characteristics (vibration signals) and thermodynamic parameters (icing rate) of ice crystal growth through multi-modal sensing fusion to form a real-time dynamic monitoring layer; Second, design a multi-scale LSTM network architecture, use short-term memory units to analyze microsecond-level ice crack pulse waves and long-term memory units to track low-frequency oscillations of material fatigue, and realize cross-time dimension feature extraction of freeze damage; Then, establish a priority evaluation model based on the pipeline topology structure, dynamically adjust communication parameters through LoRaWAN nodes, and preferentially transmit the geocoding data of high-risk pipe sections to ensure low-latency reporting of key information; Finally, combine the material ice expansion coefficient database, trigger a gradient heating strategy to achieve precise anti-freezing intervention through the coupling analysis of ice crystal dynamic parameters and pipeline stress. This strategy can refer to the zoning control logic of electric tracing in the pre-action system. The entire process forms a closed-loop control chain of "perception - analysis - transmission - decision", strengthening the intelligent prediction and directional protection capabilities on the basis of existing anti-freezing measures.

[0063] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0064] Figure 1 For the embodiments of the present application, a flowchart of a method for predicting the anti-freezing property of the pipeline of an automatic sprinkler system is provided, as Figure 1 shown, the method includes:

[0065] 101. Collect the vibration signals of ice crystal growth caused by the phase change of the internal fluid of the pipeline wall of the automatic sprinkler system through an acoustic emission sensor, and synchronously correlate the real-time icing rate data collected by the temperature sensor mounted on the pipeline surface;

[0066] In this step, the acoustic emission sensor is a device used to capture elastic wave signals released during the propagation of minute cracks inside materials or during phase transitions, and is particularly suitable for monitoring the ice crystal growth vibrations caused by the phase transition of the internal fluid in the pipe wall of an automatic sprinkler system. The temperature sensor is mounted on the pipe surface to collect and record the temperature change data on the pipe surface in real time, so as to calculate the real-time icing rate. The ice crystal growth vibration signal is collected by the acoustic emission sensor, which is the vibration signal generated during the ice crystal growth process caused by the phase transition of the internal fluid. The real-time icing rate data is the data collected by the temperature sensor, which reflects the temperature change of the pipe surface and is used to calculate the icing rate. The synchronous correlation data set is the ice crystal growth vibration signal and the real-time icing rate data that have been synchronously correlated through high-precision signal processing techniques (such as wavelet transform and adaptive filtering).

[0067] In the embodiment of the present application, first, an acoustic emission sensor and a temperature sensor are deployed inside the cold environment monitoring area. Specifically, a highly sensitive acoustic emission sensor is directly installed on the pipe wall of the automatic sprinkler system to capture the ice crystal growth vibration signals caused by the phase transition of the internal fluid. These vibration signals contain the minute elastic wave information released during the ice crystal formation process. At the same time, a high-precision temperature sensor is mounted on the pipe surface to collect and record the temperature change data on the pipe surface in real time and calculate the real-time icing rate. To ensure the time synchronization of the data, a timestamp synchronization technology is used to correlate the vibration signals with the temperature data. Then, an adaptive filtering algorithm is used to remove noise interference, and independent component analysis (ICA) is used to extract the pure vibration signals. Further, wavelet transform is applied to perform multi-scale decomposition on the pure vibration signals to separate the features in different frequency bands. These processed data are converted into time series data through signal processing techniques (such as fast Fourier transform FFT and recurrence plot analysis), and combined with the temperature data to finally output the ice crystal growth vibration signals and the real-time icing rate data.

[0068] Suppose the wet automatic sprinkler system of a commercial building in a northern city encounters an extremely cold environment of -20°C in winter, and the water flow in the system pipeline forms ice crystals due to low-temperature phase change. Acoustic emission sensors (sensitivity 50 kHz - 1 MHz, sampling rate 1 MHz) are installed at key nodes on the outer wall of the pipeline (such as elbows and valves) to capture high-frequency elastic wave signals in the range of 20 kHz - 50 kHz caused by ice crystal growth. The amplitude of a single pulse reaches 15 mV, and the duration is about 200 μs. At the same time, a PT1000 platinum resistance temperature sensor (accuracy ±0.1°C) is mounted on the pipeline surface. When the measured temperature drops suddenly from -15°C to -18°C, the ice formation rate jumps from 0.2 mm / min to 0.8 mm / min. The sensor data is aligned through a GPS synchronization module (time error < 1 μs), wavelet threshold denoising (db4 wavelet basis, 5-layer decomposition) is used to eliminate environmental vibration interference, and independent component analysis (ICA) is used to separate the ice crystal growth vibration signal and the real-time ice formation rate data, with the signal-to-noise ratio increased to 25 dB.

[0069] 102. Input the ice crystal growth vibration signal and the real-time ice formation rate data into a multi-scale long short-term memory network. The short-term memory unit captures the microsecond-level pulse waveform caused by the instantaneous rupture of ice crystals, and at the same time, the long-term memory unit tracks the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material, and outputs a composite freezing feature.

[0070] In this step, the multi-scale long short-term memory network is a deep learning model that can process information at different time scales simultaneously. The short-term memory unit is used to capture the microsecond-level pulse waveform, while the long-term memory unit tracks the minute-level low-frequency oscillation. The composite freezing feature is output by the multi-scale long short-term memory network and contains comprehensive features of the dynamic characteristics of ice crystals and the stress state of the material, which are used for subsequent analysis and prediction.

[0071] In the embodiments of the present application, the obtained ice crystal growth vibration signal and real-time icing rate data are input into a multi-scale long short-term memory network (Multi-Scale LSTM). Specifically, the short-time-span memory unit extracts the microsecond-level pulse waveform features in the high-frequency sub-signal through a convolutional neural network (CNN). These pulse waveforms reflect the dynamic characteristics of instantaneous ice crystal rupture. To enhance the feature extraction effect, local response normalization (LRN) and batch normalization (BN) techniques are used to standardize the feature maps. At the same time, the long-time-span memory unit analyzes the minute-level low-frequency oscillation features in the low-frequency sub-signal through a recurrent neural network (RNN) structure. These oscillations reflect the accumulation of material fatigue deformation. To improve the robustness of the model, a gated recurrent unit (GRU) and an attention mechanism (Attention Mechanism) are introduced to better capture the memory information over a long time span. These two types of information are integrated through a feature fusion technique (such as feature weighted average or feature splicing) to output a composite freezing feature.

[0072] For example, continuing with the above example, the preprocessed vibration signal (peak frequency 38 kHz, energy spectral density 0.8 V 2 / Hz) and the icing rate time series data are input into the multi-scale LSTM network. The short-term memory unit (CNN layer, 3×1 convolution kernel) extracts the microsecond-level pulse features: the slope of the pulse rising edge is 15 V / s, and the decay time constant is 120 μs, corresponding to the transient process of ice crystal rupture. The long-term memory unit (bidirectional GRU, time window 60 s) analyzes the 0.5 Hz low-frequency oscillation component, whose amplitude slowly increases from 5 mV to 12 mV, reflecting the fatigue accumulation of the HDPE pipeline material. In the feature fusion stage, a weight of 0.7 is assigned to the high-frequency features and 0.3 to the low-frequency features, and a composite freezing index is output (CFI = 0.82, and a threshold of 0.75 triggers an early warning).

[0073] 103. According to the spatial distribution of the pipeline network and the priority of the composite freezing feature, adaptively adjust the transmission power and modulation rate of the LoRaWAN node, encode the high-priority composite freezing feature and the geographical location of the corresponding pipe section into an emergency data frame, and preferentially transmit it to the remote control center through multi-hop routing;

[0074] In this step, the LoRaWAN node is a wireless communication node based on LoRa technology, which is used for efficient and low-power data transmission in a cold environment. The emergency data frame contains a data packet with the high-priority composite freezing feature and the geographical location information of the corresponding pipe section, and is preferentially transmitted to the remote control center through multi-hop routing. Adaptive adjustment is a mechanism for dynamically adjusting the transmission power and modulation rate of the LoRaWAN node and optimizing the data transmission efficiency according to the spatial distribution of the pipeline network and the priority of the composite freezing feature.

[0075] In the embodiments of the present application, according to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, a path loss model and channel quality assessment technology are used to determine the optimal transmission power and modulation rate configuration. Specifically, the ant colony optimization algorithm (ACO) is used to optimize the routing selection to determine the most efficient transmission path. In order to encode the high-priority composite freezing characteristics and the geographical location of the corresponding pipeline section into an emergency data frame, first, the geographical information system (GIS) technology is used to convert the geographical location information into a standard format, such as GeoJSON. Then, the data is compressed using the Huffman coding or LZ77 compression algorithm to reduce the transmission bandwidth requirements. Next, through the forward error correction (FEC) technology and the adaptive modulation and coding (AMC) strategy, the reliability and efficiency of data transmission are ensured. Finally, the multi-hop routing protocol is used to preferentially transmit the emergency data frame to the remote control center.

[0076] For example, continuing with the above example, after identifying that the CFI of the pipeline in layer B2 exceeds the threshold, communication optimization is initiated. First, the spatial parameters are obtained. The pipeline section is located in the northwest corner of the building (GPS 39.9042°N, 116.4074°E), and the distance from the relay node is 28 m (the attenuation measured by the path loss model is 42 dB). Then, the communication configuration is optimized. The LoRaWAN node switches to SF12 modulation (air rate 0.3 kbps), the transmission power is increased to 20 dBm, and the data packet encapsulation adopts the GeoJSON format (compression rate 65%). Finally, the routing is optimized. The optimal 3-hop path (B2 → 5F relay → roof gateway) is selected through the ant colony algorithm. The transmission delay is reduced from the default 800 ms to 320 ms, and the packet loss rate is <0.1%. The emergency data frame contains fields such as the pipeline section ID, CFI value, and GPS coordinates, and preferentially occupies the QoS level 1 channel to be transmitted to the control center.

[0077] 104. Based on the database of the ice expansion coefficient of pipeline materials pre-stored in the remote control center, match the ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics, calculate the rupture risk probability of a specific pipeline section under the critical ice thickness, predict the frost resistance of the pipeline based on the rupture risk probability, and activate the pipeline heating-up strategy corresponding to the rupture risk probability according to the frost resistance prediction result.

[0078] In this step, the rupture risk probability is the rupture risk probability of a specific pipeline section calculated by matching the ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics based on the pre-stored pipeline material database under the critical ice thickness. The pipeline electric tracing gradient heating-up strategy is a strategy to activate the corresponding electric tracing system according to the calculated rupture risk probability to prevent the pipeline from rupturing due to freezing.

[0079] In the embodiments of the present application, based on the database of ice expansion coefficients of pipeline materials pre-stored in the remote control center, first, a feature selection algorithm (such as Recursive Feature Elimination, RFE) is used to screen and standardize the ice crystal dynamic parameters and material stress parameters in the composite freezing features. Then, during the process of matching the ice crystal dynamic parameters and material stress parameters in the composite freezing features, the current features are input into a pre-trained classifier, and Bayesian inference technology is used to estimate the probability of rupture risk. According to the calculated probability of rupture risk, the corresponding electric tracing gradient heating strategy is automatically activated, and the heating power is adjusted in real time through fuzzy logic control or PID control algorithm to gradually increase the pipeline temperature, effectively inhibiting the growth of ice crystals and avoiding pipeline rupture.

[0080] For example, continuing with the above example, the control center retrieves the ice expansion coefficient database of HDPE pipelines (expansion coefficient of 1.5×10 -4 / °C, tensile strength of 19 MPa), combines the ice crystal dynamic parameter of the growth rate of 0.8 mm / min (exceeding the safety threshold of 0.5 mm / min), and the material stress parameter of the circumferential stress reaching 14.7 MPa (safety threshold of 16 MPa). The Bayesian risk model calculates that the probability of rupture is 82.3% (confidence interval of 95%), and immediately activates the gradient heating strategy: in the first stage, the electric tracing tape heats up to -5°C at a rate of 2°C / min (PID control parameters Kp = 8, Ki = 0.5); in the second stage, it maintains a constant temperature of 5°C for 30 minutes (energy consumption monitoring shows that the power drops from 500 W to 300 W). After the intervention, the monitoring shows that the ice layer thickness retracts from 12 mm to 3 mm, and the CFI index drops to 0.41, completing the activation of the pipeline electric tracing gradient heating strategy.

[0081] This solution realizes the microsecond-level pulse capture and minute-level stress accumulation monitoring of the pipeline icing process through the real-time data fusion of acoustic emission sensors and temperature sensors, combined with the dynamic analysis of ice crystal growth vibration signals and material deformation by a multi-scale LSTM network. It preferentially transmits the data of high-risk pipeline sections through adaptive LoRaWAN communication, and matches the probability of rupture based on the database of material ice expansion coefficients, and finally triggers the electric tracing gradient heating strategy, forming a full-chain anti-freezing protection system from monitoring, analysis to intervention, effectively preventing the risk of pipeline freezing and cracking.

[0082] To solve the problems of large interference in vibration signals and difficult multi-physical field coupling analysis in ice crystal growth monitoring, the research and development idea of this solution focuses on multi-source interference suppression and cross-scale feature fusion: eliminating environmental noise interference through axial stress constraint filtering to extract the intrinsic vibration of ice crystal growth; separating high-frequency fracture pulses and low-frequency material deformation signals by time-frequency decomposition and synchronously aligning the icing dynamic coefficient; combining short-time waveform tracking and long-term oscillation correlation model to analyze the cross-scale correlation between ice crystal evolution and material damage; finally, fusing physical parameters and real-time data through dynamic weight allocation to generate composite features of ice crystal distribution gradient and material property attenuation, and realizing accurate prediction of freezing damage risk. In some embodiments, the ice crystal growth vibration signal and the real-time icing rate data are input into a multi-scale long short-term memory network. The microsecond-level pulse waveform caused by instantaneous ice crystal fracture is captured by the short-time span memory unit, and at the same time, the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material is tracked by the long-time span memory unit, and the composite freezing features are output, including:

[0083] 201. Before the ice crystal growth vibration signal is input into the multi-scale long short-term memory network, perform vibration component elimination processing for non-phase change interference on the ice crystal growth vibration signal, and retain the vibration component coaxial with the pipeline axial stress direction;

[0084] In step 201, the non-phase change interference vibration component refers to the vibration signals caused by external mechanical vibrations of the pipeline (such as pump valve start-stop, support resonance) and non-icing phase change noises (such as bubble rupture, fluid turbulence). The axial stress coaxial vibration component is the vibration component consistent with the pipeline axial stress direction, reflecting the orthogonal stress effect of ice crystal growth on the pipe wall.

[0085] In the embodiment of the present application, first, an improved adaptive noise cancellation technology (ANC) is used to eliminate non-phase change interference. The environmental vibration noise is collected by a reference sensor installed on the pipeline support, and the least mean square algorithm (LMS) is used to generate an anti-sound wave to cancel the interference component. Further, in combination with pipeline structure parameters (such as bending radius, wall thickness gradient), wavelet packet decomposition is used to extract the vibration component coaxial with the pipeline axial stress direction. (Main frequency band 20kHz - 500kHz).

[0086] 202. Input the vibration component into the time-frequency decomposition layer to separate the high-frequency sub-signal representing instantaneous ice crystal fracture and the low-frequency sub-signal reflecting material plastic deformation, and at the same time convert the real-time icing rate data into an icing dynamic coefficient aligned with the time stamps of each sub-signal;

[0087] In step 202, the time-frequency decomposition layer is a multi-resolution analysis layer based on the local time-varying characteristics of the signal, used to separate the transient characteristics of ice crystal fracture and the slow-changing characteristics of material deformation. The icing dynamic coefficient is a dimensionless parameter that quantifies the correlation between the ice layer growth rate and the time-frequency energy of the vibration signal.

[0088] In the embodiment of the present application, when the vibration component is input into the time-frequency decomposition layer, empirical mode decomposition (EMD) is used to adaptively separate high-frequency intrinsic mode functions (IMF1-IMF3) and low-frequency residue components (Residue). The high-frequency sub-signal (IMF1) corresponds to the microsecond-level pulse of instantaneous ice crystal rupture, and the low-frequency sub-signal (Residue) reflects the minute-level oscillation of material plastic deformation. Synchronously, the real-time icing rate data is converted into an icing dynamic coefficient aligned with the time stamps of each sub-signal through cubic spline interpolation.

[0089] 203. Input the high-frequency sub-signal into the short-time span memory unit for microsecond-level waveform profile tracking to capture the phase mutation points between adjacent ice crystal rupture events, and input the low-frequency sub-signal and the icing dynamic coefficient into the long-time span memory unit for oscillation mode correlation to establish an implicit correlation between the change in the pipe cross-section ellipticity and the stress relaxation rate;

[0090] In step 203, the microsecond-level waveform profile tracking is to capture the timing correlation of the rising edge slope, peak energy, and pulse interval of the ice crystal rupture pulse. The oscillation mode correlation is to establish a non-linear mapping relationship between the low-frequency oscillation of material deformation and the icing dynamic coefficient.

[0091] In the embodiment of the present application, the high-frequency sub-signal is input into the short-time span memory unit, and a gated causal convolutional network (GCCN) is used to extract microsecond-level waveform features, and the phase mutation points between adjacent pulses (such as phase jumps exceeding π / 2) are identified through a phase-sensitive detection algorithm (PSD). The low-frequency sub-signal and the icing dynamic coefficient are jointly input into the long-time span memory unit, and a bidirectional gated recurrent network (Bi-GRU) is used to correlate the oscillation modes, and an implicit equation between the change in the pipe cross-section ellipticity and the stress relaxation rate is established in combination with the Timoshenko beam theory.

[0092] 204. Perform dynamic weight allocation on the phase mutation points and the implicit correlation, and combine the pre-stored Young's modulus parameter and thermal expansion coefficient parameter of the pipe to generate a composite freezing feature including the ice crystal distribution gradient and the material yield strength attenuation trend.

[0093] In step 204, the dynamic weight allocation is to adaptively allocate feature weights according to the correlation between the phase mutation point density and the stress relaxation rate. The composite freezing feature is a multi-dimensional feature vector that fuses the ice crystal distribution gradient (vector) and the material yield strength attenuation rate (scalar).

[0094] In the embodiments of the present application, the entropy weight method is used to calculate the weight coefficients of the phase mutation points (high-frequency features) and the stress relaxation rate (low-frequency features). Combining the pre-stored Young's modulus (calibrated by nanoindentation test) and the coefficient of thermal expansion (obtained by thermomechanical analyzer TMA) of the pipeline, an ice crystal growth-material degradation coupling model is constructed. The ice crystal distribution gradient (polar coordinate form) and the material yield strength attenuation trend (time series) are fused into composite freezing features through tensor splicing, and the feature dimension is dynamically adjusted by the pipeline topological structure (such as the number of tees and elbows).

[0095] The following is a specific example:

[0096] The original vibration signal amplitude collected by a piezoelectric vibration sensor installed at the elbow of the pipeline in the wet automatic sprinkler system of a shopping mall is 0.8V (peak-to-peak value), and its spectrum shows a multi-peak characteristic in the range of 15 kHz - 600 kHz. The main frequency of the environmental mechanical vibration noise measured by the reference sensor at the bracket is 50 Hz (amplitude 0.2V). The improved LMS algorithm is used to generate an anti-phase beamforming signal to suppress the non-phase change interference component below -45 dB. Combining the pipeline structure parameters (bending radius 3.5 m, wall thickness gradient 0.2 mm / m), the Daubechies 6 wavelet basis is selected for 5-layer decomposition, and the main frequency band of the axial coaxial vibration component is extracted as 250 kHz ± 5%, and its power spectral density reaches 1.2×10^-3 V 2 / Hz. After the time-frequency decomposition layer processes this component using EMD, the high-frequency IMF1 sub-signal presents a transient pulse sequence with a pulse width of 0.5 μs and a peak voltage of 1.5 V in the time domain, and the adjacent pulse intervals are randomly distributed between 10 - 150 μs; the low-frequency residual component shows a low-frequency oscillation wave with an amplitude of 0.12 V and a period of 2.8 min. The currently measured icing rate by the synchronously connected icing rate sensor is 1.2 mm / h, and the icing dynamic coefficient α = 0.45 ± 0.03 aligned with the time stamp is generated through cubic spline interpolation. The short-time span memory unit performs gated convolution processing on the high-frequency pulses and detects that the phase mutation points between adjacent pulses reach a jump of π / 3 radians, and the mutation point density is 8.5 times per second; the long-time span memory unit correlates the low-frequency oscillation amplitude envelope with the α coefficient through the Bi-GRU network and derives the change rate of the pipe cross-section ellipticity Δe = 0.017 / min, and the deviation of this parameter from the predicted value of the implicit equation established based on the Timoshenko beam theory is less than 5%. Combining the pipe material parameters (Young's modulus of 210 GPa, thermal expansion coefficient of 12.5×10^-6 / °C), the high-frequency feature weight of 0.62 and the low-frequency feature weight of 0.38 are assigned using the entropy weight method, and finally a 128-dimensional composite freezing feature containing the radial distribution gradient vector of ice crystals (polar angle 45° ± 3°, modulus length 1.8 mm / m) and the scalar of the yield strength attenuation rate (-2.3 MPa / h) is generated, and this dimension is dynamically adjusted and generated according to 3 elbows and 2 tee nodes in the pipe topology structure.

[0097] For the requirement of pipeline ice crystal monitoring, steps 201 - 204 achieve directional noise reduction of the axial stress vibration signal through adaptive noise cancellation and wavelet packet decomposition, separate and correlate high-frequency rupture pulses and low-frequency deformation oscillations by combining empirical mode decomposition and bidirectional gated recurrent network, dynamically fuse the ice crystal distribution gradient and the material yield strength attenuation trend using the entropy weight method, construct an interpretable composite freezing feature, realize microsecond-level rupture event detection and sub-hourly deformation tracking, improve the axial signal fidelity, reduce the prediction error of frost heave risk, and compress the end-to-end processing delay to meet the real-time monitoring requirements of the extreme cold environment.

[0098] To improve the transmission reliability and energy efficiency ratio of pipeline monitoring data in cold environments, based on the LoRaWAN network characteristics of pipeline monitoring scenarios, by dynamically evaluating the relationship between pipeline rupture risk and signal attenuation, a coupling model of ice crystal gradient change and node energy consumption is established, and an adaptive power allocation strategy driven by link quality is adopted to jointly optimize the transmission power and modulation method under the constraint of remaining energy; at the same time, the physical characteristics of the pipe section are encoded into a topology-aware data frame structure, and the transmission reliability of ice crystal orientation information is enhanced through the check field; finally, combined with the attenuation characteristics of metal obstacles and the multipath propagation model, a dynamic relay selection algorithm based on minimizing path fading is constructed to realize a multi-hop optimization mechanism for the alternate transmission of ground reflected waves and direct waves. In some embodiments, adaptively adjusting the transmission power and modulation rate of LoRaWAN nodes according to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, and encoding the high-priority composite freezing characteristics and the corresponding pipe section geographical location into an emergency data frame, and preferentially transmitting it to the remote control center through multi-hop routing, includes:

[0099] 301. Analyze the pipeline rupture risk probability and stress concentration factor in the composite freezing characteristics, and combine the distance parameter between adjacent nodes and the historical signal interference parameter in the pipeline distribution topology to calculate the dynamic transmission path loss threshold of each LoRaWAN node;

[0100] In step 301, the pipeline rupture risk probability quantifies the possibility of brittle fracture of the pipe section under ice expansion stress, and the value range is 0-1. The dynamic transmission path loss threshold is the critical value of wireless signal attenuation dynamically adjusted according to environmental interference and node spacing, which determines the stability of the communication link.

[0101] In the embodiments of the present application, first analyze the pipeline rupture risk probability (based on the Weibull survival analysis model) and stress concentration factor (calibrated by finite element simulation) in the composite freezing characteristics. Combine the Delaunay triangulation model of the pipeline distribution topology to extract the Euclidean distance between adjacent nodes and the historical signal interference parameter (such as the variance of bit error rate fluctuation). Adopt an improved Hata-COST231 hybrid propagation model, introduce the ice crystal dielectric constant (measured by time domain reflectometer) and the diffraction loss of metal obstacles (calculated by UTD theory), and determine the dynamic transmission path loss threshold of each LoRaWAN node through Monte Carlo sampling to ensure that the signal reception strength is ≥ -110dBm within a 95% confidence interval.

[0102] 302. Dynamically allocate the transmission power level and orthogonal modulation index according to the dynamic transmission path loss threshold and the change rate of the ice crystal distribution gradient in the composite freezing characteristics, and synchronously combine the node remaining energy parameter to constrain the maximum adjustable power range;

[0103] In step 302, the orthogonal modulation index is a communication efficiency parameter that defines the combination of the LoRa signal spreading factor and bandwidth. The maximum adjustable power range is a safe transmission power interval determined according to the remaining energy of the node and the circuit heat dissipation capacity.

[0104] In the embodiments of the present application, a coupling relationship model between the rate of change of the ice crystal distribution gradient (calculated by the optical flow method) and the path loss threshold is established. A power allocation strategy is designed using non-cooperative game theory: the transmission power levels are discretized into a Nash equilibrium solution set, and the orthogonal modulation index is solved for the Pareto optimal solution through convex optimization. The remaining energy parameter of the node (obtained by Coulomb counting method) and the PCB thermal resistance parameter (JEDEC JESD51 standard) are synchronously introduced to construct a thermoelectric joint constraint condition to limit the maximum adjustable power range (such as 14 - 20 dBm).

[0105] 303. Classify and code the high-priority composite freezing characteristics and the geographical locations of the corresponding pipe segments according to the pipe diameter specifications, construct a frame header containing the pipe segment identifier and a check field for the ice crystal growth azimuth angle, and generate an emergency data frame with a topology-aware tag;

[0106] In step 303, the pipe segment identifier is a unique code that combines the pipe diameter, material, and installation date, and is encoded using the Base32 variant. The ice crystal growth azimuth angle check field records the polar angle information of the main growth direction of the ice crystal and is used for spatial correlation verification.

[0107] In the embodiments of the present application, the high-priority composite freezing characteristics are classified into the DN50 - DN300 category by a pipe specification classifier (based on SVM), and the geographical location of the pipe segment is encoded into a 12-character string using an improved Geohash algorithm. The ice crystal growth azimuth angle extracts the main direction angle (0 - 360°) through the Hough transform and generates an 8-bit check code in combination with the cyclic redundancy check (CRC-16-CCITT). The frame header structure is designed as: 4-byte identifier (pipe diameter + material code) + 2-byte azimuth angle check field + 1-byte emergency level identifier, and the frame payload is encrypted using the AES-256-CTR mode to generate an emergency data frame with a topology-aware tag.

[0108] 304. Based on the pre-stored metal obstacle attenuation map in the pipeline distribution topology, select a relay node sequence with the minimum path fading, and realize the multi-hop relay transmission of the emergency data frame by alternately using the ground reflection wave and direct wave propagation modes.

[0109] In step 304, the metal obstacle attenuation map pre-stores the electromagnetic wave attenuation characteristic database of metal components such as flanges and valves in the pipeline system. The multi-hop relay transmission realizes the alternating propagation mode of the ground reflection wave and direct wave through relay nodes.

[0110] In the embodiments of the present application, a metal obstacle attenuation map is constructed based on a ray tracing algorithm (such as the SBR / Image method) to quantify the Fresnel zone loss at different incident angles. The improved AODVjr routing protocol is adopted, combined with the attenuation map and real-time RSSI (Received Signal Strength Indication) data, to dynamically select a relay sequence with the minimum path fading. When the ground reflection wave mode is enabled, BPSK modulation and diversity reception technology are used to compensate for the multipath effect; the direct wave mode uses LoRa Chirp spread spectrum and MRC (Maximum Ratio Combining) technology to improve the signal-to-noise ratio. By adaptively switching the propagation mode, reliable multi-hop relay transmission of emergency data frames is achieved.

[0111] The following is a specific example:

[0112] Suppose this solution is applied to the pipeline monitoring of a wet automatic sprinkler fire extinguishing system in a cold region logistics cold storage. First, through step 301, the composite freezing characteristics are analyzed to obtain a rupture risk probability of 0.93 (DN150 carbon steel pipe), and the stress concentration factor Kt = 2.3. Combining the adjacent node spacing of 28 m and the historical bit error rate variance of 0.12, the dynamic path loss threshold is calculated to be -107 dBm through the Hata-COST231 model. Secondly, through step 302, the ice crystal distribution gradient change rate of 1.8 mm / s triggers a high priority, and the transmission power is allocated 18 dBm (SF10 / BW125 kHz) by game theory. The remaining energy of the node is 3.2 Ah, which restricts the maximum power to 19 dBm; again, through step 303, the pipe section identifier code is obtained as "DN15-C-2023", and the azimuth angle of 225° generates a check code of 0x7B to construct an emergency data frame (6-byte frame header + 128-byte payload); finally, based on step 304, a 3-hop path (node A → valve V7 → bracket S12 → control center) is selected according to the attenuation map, and the ground reflection wave (bit error rate < 10 -6 ) and the direct wave (RSSI = -102 dBm) are alternately used to complete multi-hop relay transmission.

[0113] Aiming at the problem of data transmission reliability, steps 301-304 dynamically calculate the path loss threshold based on the Weibull survival analysis and Hata-COST231 hybrid model, adopt non-cooperative game theory to optimize the power-modulation parameter combination, design a topology-aware emergency data frame structure and integrate multi-modal propagation control, and realize the alternating transmission of ground reflection wave / direct wave through ray tracing and adaptive routing, so that the path loss prediction accuracy reaches ±1.5 dB, the node energy consumption balance is optimized by 32%, the emergency data packet delivery success rate exceeds 99.99%, and the multi-path interference suppression ability is improved by 28 dB, effectively ensuring low-latency and high-reliability multi-hop relay transmission in a complex metal pipeline environment.

[0114] To optimize the energy efficiency and anti-interference ability of the pipeline monitoring system in cold regions, the ice crystal evolution rate is dynamically correlated with the node energy consumption through a thermodynamic coupling model. Based on the path loss threshold, phase-sensitive quadrature modulation calibration compensation is triggered, and a limited transient power pulse is activated in combination with the frost layer thickness threshold. Finally, an adaptive communication parameter set resistant to Doppler frequency shift is generated through time slot interleaved coding, realizing cross-domain collaborative optimization of ice crystal dynamics, environmental attenuation, and wireless transmission characteristics. In some embodiments, dynamically allocating the transmission power level and quadrature modulation index according to the dynamic transmission path loss threshold and the change rate of the ice crystal distribution gradient in the composite freezing characteristics, and synchronously combining the remaining energy parameter of the node to constrain the maximum adjustable power range, includes:

[0115] 401. Establish a transmission power allocation model, and convert the change rate of the ice crystal distribution gradient in the composite freezing characteristics and the remaining energy parameter of the node into a power allocation reference value through the thermodynamic expansion margin;

[0116] In step 401, the thermodynamic expansion margin converts and quantifies the energy loss generated by the work done by the volume expansion of ice crystal phase change on the pipe wall, and is used as a proportional conversion factor for power allocation. The power allocation reference value is a basic power configuration parameter that comprehensively considers the thermodynamic effect of ice crystal growth and the node energy state.

[0117] In the embodiment of the present application, a coupling model of the change rate of the ice crystal distribution gradient (the ice-pipe contact stress gradient calculated based on the Hertz contact theory) and the remaining energy parameter of the node (corrected by Coulomb counting and Peukert equation) is established. The non-equilibrium thermodynamics method is used to calculate the ratio of the latent heat of ice crystal phase change (334 kJ / kg) to the elastic strain energy of the pipe material (Hooke's law) as the thermodynamic expansion margin coefficient. The energy constraint optimization problem is solved by the Lagrangian multiplier method to generate the power allocation reference value, where the allocation weight of the high-gradient pipe section (>1.5 mm / s) is increased by 30%-50%.

[0118] 402. Perform phase sensitivity calibration on the quadrature modulation index according to the dynamic transmission path loss threshold. When the dynamic transmission path loss threshold exceeds the theoretical attenuation value of the pipeline insulation layer, trigger a compensation mechanism for the quadrature modulation index to shift in the direction of anti-multipath interference, and output a time-varying compensation coefficient;

[0119] In step 402, the phase sensitivity calibration is to dynamically adjust the phase response characteristics of the modulation index for the signal phase distortion caused by multipath interference. The time-varying compensation coefficient is a dynamic correction factor that quantifies the offset of the modulation parameter and has a non-linear relationship with the path loss.

[0120] In the embodiments of the present application, the phase - sensitivity calibration of the quadrature modulation index is performed using the phase - locked loop (PLL) technology. When the dynamic transmission path loss threshold exceeds the theoretical attenuation value of the pipeline insulation layer (calibrated by COMSOL electromagnetic simulation), a compensation mechanism based on the Lyapunov stability theory is triggered: a phase - error dynamics equation is constructed, and the modulation index is driven to shift in the direction of anti - multipath interference through adaptive sliding - mode control. Through real - time iterative update by the Kalman filter, a time - varying compensation coefficient is output to suppress the phase jitter caused by the time - varying channel, and the phase - tracking accuracy reaches ±0.1 radian.

[0121] 403. Inject the time - varying compensation coefficient into the transmit power allocation model. When the frost layer thickness exceeds the critical value of the sealing gap at the metal flange connection, trigger a transient overload transmit power pulse based on the power allocation reference value, and constrain the transient overload transmit power pulse within the maximum adjustable power range allowed by the remaining energy parameter of the node.

[0122] In step 403, the transient overload transmit power pulse is a short - time high - power transmit mode triggered at the critical frost layer thickness, which is used to break through the channel blockage.

[0123] The maximum adjustable power range is the safety power limit based on the node's thermal design power (TDP) and the battery discharge curve.

[0124] In the embodiments of the present application, the time - varying compensation coefficient is injected into the power allocation model, and the pulse - width modulation (PWM) technology is used to generate the transient overload transmit power pulse. When the frost layer thickness (measured by a microwave resonant sensor) exceeds the critical value of the flange sealing gap (ASTM F37 standard), the pulse - trigger logic based on Bang - Bang control is activated. The pulse amplitude is dynamically adjusted according to the power allocation reference value and the remaining energy parameter of the node (estimated by the RC circuit equivalent model), and is limited by the maximum adjustable power range allowed by the remaining energy parameter of the node calculated by the Arrhenius equation (the maximum PCB temperature rise threshold (ΔT < 15°C)), ensuring that the pulse energy density does not exceed 2.8 J / cm 3 。

[0125] 404. Perform time - slot interleaved coding on the quadrature modulation index after phase - sensitivity calibration and the power levels of the transient overload transmit power pulses to generate an adaptive communication parameter configuration table that adapts to the Doppler frequency - shift characteristics at the pipeline elbow.

[0126] In step 404, the time - slot interleaved coding interleaves different modulation parameters in time slices to resist the inter - symbol interference caused by Doppler frequency shift. The adaptive communication parameter configuration table is a dynamic look - up table integrating power, modulation, and time - slot parameters, which supports the adaptation to the complex channel at the elbow.

[0127] In the embodiments of the present application, the fractional Fourier transform (FRFT) is used to analyze the Doppler frequency shift characteristics (typical value ±2.4 kHz) at the pipe elbow. The calibrated quadrature modulation index and the transient overload power level are subjected to time-slot interleaved coding: a time-slot allocation template is generated through the Gold sequence, and combined with the Turbo code error correction mechanism, an adaptive communication parameter configuration table adapted to the Doppler frequency shift characteristics at the pipe elbow is constructed. The configuration table contains 128 groups of parameter combinations (16 power levels × 8 modulations × 4 time-slot modes), and supports dynamic switching based on the channel coherence time (switching period < 10 ms).

[0128] The following is a specific example:

[0129] Suppose this solution is applied to the monitoring of the wet automatic sprinkler system pipe network in a subway tunnel in a cold region. First, through step 401, the ice crystal distribution gradient of 1.8 mm / s (X70 steel grade pipe material), the remaining energy of the node of 3.2 Ah, the conversion coefficient of the thermodynamic expansion margin of 0.67, and the generated power reference value of 18.3 dBm are obtained; according to step 402, the path loss threshold of -105 dBm exceeds the insulation layer attenuation value of -98 dBm, triggering the sliding mode compensation mechanism, and the modulation index shifts from SF9 to SF11, and the time-varying compensation coefficient of 0.82 is output; according to step 403, the frost layer thickness at the flange reaches 2.3 mm (critical value 2.0 mm), activating the transient overload pulse (amplitude 21 dBm, pulse width 50 ms), restricted by the maximum power of the node of 22 dBm; finally, based on step 404, a Doppler frequency shift of 1.8 kHz is detected at the elbow, and the configuration table selects the time-slot mode 3 (interleaving depth 8), and the Turbo code rate is 3 / 4, achieving a bit error rate < 10 -7 .

[0130] Steps 401-404 achieve a 40% increase in the energy utilization rate of ice crystal phase change, a phase tracking accuracy of ±0.1 radian, a 46% increase in the peak power of the transient pulse compared to the steady state and the temperature rise is controllable, the Doppler frequency shift tolerance is extended to ±3 kHz, the bit error rate in a complex bend environment is reduced by two orders of magnitude, and the comprehensive energy efficiency ratio of the node is optimized by 37% through thermodynamics-communication cross-domain modeling, sliding mode compensation control, transient pulse dynamic constraint, and Doppler adaptive coding, meeting the requirements for all-weather reliable monitoring of extremely cold pipelines.

[0131] In order to improve the pulse emission efficiency and spatial energy adaptability of the cold region pipeline monitoring system, by real-time monitoring the frost layer thickness and the ice crystal distribution gradient, combining the latent heat of phase change parameters with the axial stress distribution of the metal pipeline, a time-varying compensation model is constructed; based on the creep characteristics of the sealing material and the attenuation law of the bolt pre-tightening force, an energy constraint condition is established, and the pulse parameter set is optimized through azimuth angle weighting and phase modulation technology, and finally the adaptive generation of the transient overload emission command is realized. The core lies in integrating the thermodynamic phase change, material mechanics and stress wave modulation technology to form a closed-loop feedback control system to ensure the system stability is maintained through dynamic power compensation when the frost layer thickness exceeds the limit. In some embodiments, injecting the time-varying compensation coefficient into the emission power distribution model, when the frost layer thickness exceeds the critical value of the sealing gap at the metal flange connection, triggering a transient overload emission power pulse based on the power distribution reference value, and constraining the transient overload emission power pulse within the maximum adjustable power range allowed by the remaining energy parameters of the node, including:

[0132] 501. Input the time-varying compensation coefficient into the emission power distribution model, combine the real-time growth rate of the frost layer thickness with the latent heat of phase change parameters of the pipeline metal material, generate dynamic overload power margin parameters, and automatically activate the margin parameter compensation channel for the nodes corresponding to the pipe segments where the frost layer thickness exceeds the critical value of the sealing gap;

[0133] In step 501, the dynamic overload power margin parameter is a dynamic balance parameter that quantifies the energy absorption of ice frost phase change and the node power supply capacity during transient pulse emission. The margin parameter compensation channel is an energy redistribution logic channel activated when the frost layer thickness exceeds the limit to ensure the power supply of key nodes.

[0134] In the embodiments of the present application, the proper orthogonal decomposition (POD) method is used to establish the spatio-temporal correlation matrix between the time-varying compensation coefficient and the frost layer growth rate (measured by the laser diffraction method). Combining the latent heat of phase change parameters of the pipeline metal material (calibrated by DSC differential scanning calorimetry), a thermal-electric coupling transfer function is constructed, and the characteristic frequency components (0.1 - 10 Hz) are extracted through the Prony algorithm. When the frost layer thickness (monitored by the microwave resonance sensor) exceeds the critical value of the sealing gap (ASTM F37 standard), activate the compensation channel based on the fractional order integrator to generate dynamic overload power margin parameters (per unit value 0 - 1), and the compensation amount increases exponentially with the axial penetration rate of the ice crystal.

[0135] 502. Based on the change rate of the ice crystal distribution gradient, perform azimuth angle weighting processing on the dynamic overload power margin parameters through the margin parameter compensation channel, and use the axial stress distribution mode of the pipeline to perform phase modulation on the waveform envelope of the transient overload emission power pulse to generate a pulse parameter set that matches the verification field of the ice crystal growth azimuth angle;

[0136] In step 502, the azimuth weighting process is a polarization modulation technique that performs spatial weight allocation on the power margin based on the main growth direction of ice crystals. The pulse parameter set is a set of pulse waveform characteristics including elements such as amplitude, pulse width, and phase, which matches the spatial distribution of ice crystals.

[0137] In the embodiments of the present application, the principal components (PC1 - PC3) of the gradient change rate of the ice crystal distribution are extracted through tensor decomposition, and combined with the axial stress distribution pattern of the pipeline (finite element simulation based on Timoshenko beam theory), an azimuth weighting function (Gaussian distribution from 0° to 360°) is constructed. The IQ modulation technique is used to perform phase modulation on the envelope of the transient overload pulse waveform: the carrier frequency dynamically shifts (±5% of the center frequency point) according to the ice crystal azimuth angle check field (CRC - 8 check code), generating a pulse parameter set that matches the check field of the ice crystal growth azimuth angle, including 16 groups of pulse parameters, supporting the composite modulation of Barker code spread spectrum and Chirp linear frequency modulation.

[0138] 503. Based on the creep parameters of the sealing material and the bolt pre - tightening force attenuation coefficient at the metal flange connection, establish a time - domain energy distribution constraint condition, so that the pulse parameter set forms a non - uniform energy density distribution within the maximum adjustable power range allowed by the remaining energy parameters of the node;

[0139] In step 503, the creep parameter of the sealing material is to quantify the stress relaxation characteristics of the flange sealing gasket at low temperature, and is characterized by the creep compliance (J(t)). The non - uniform energy density distribution is a pulse energy envelope that decays exponentially in the time domain and matches the material stress relaxation curve.

[0140] In the embodiments of the present application, based on the generalized Maxwell model to fit the creep parameters of the sealing material (time constant τ = 120 min), combined with the bolt pre - tightening force attenuation coefficient (obtained by an ultrasonic bolt stress detector), a time - domain energy distribution constraint equation is established. The dynamic programming algorithm is used to optimize the energy distribution of the pulse parameter set: within the maximum adjustable power range (limited by the node supercapacitor discharge curve), design the first peak energy to account for 60%, and the subsequent pulses decay according to the law of e^(-t / τ), forming a non - uniform energy density distribution to ensure that the energy density of the pulse group does not exceed 3.2 J / cm 3 (the maximum adjustable power range of the IEC 62368 - 1 safety standard).

[0141] 504. Interleave the non - uniform energy density distribution and the dynamic overload power margin parameters in time slots to generate a transient overload transmission instruction set carrying the stress concentration factor correction parameters at the metal flange connection.

[0142] In step 504, time slot interleaving arranges pulses with different energy densities in a staggered manner according to preset time slices, enhancing the anti-multipath interference ability. The stress concentration factor correction parameter is a dynamic correction coefficient that reflects the local stress amplification effect at the flange connection.

[0143] In the embodiment of the present application, a Gold sequence is used to generate a time slot allocation template (with a period of 31 bits), and two-dimensional interleaving coding is performed on the non-uniform energy density distribution and the dynamic overload power margin parameter. Combining the flange stress concentration factor (calibrated through photoelastic experiments), a 32-bit correction parameter field (IEEE754 floating-point format) is embedded in the instruction set, and Turbo code (code rate 1 / 3) is used for forward error correction. The finally generated transient overload transmission instruction set contains 256 groups of instructions, supporting a dynamic selection strategy based on the pipe elbow curvature radius (R / D≥1.5).

[0144] The following is a specific example:

[0145] Suppose the monitoring node of the wet automatic sprinkler system in a certain data center applies this solution. First, through step 501, the frost layer thickness of 1.8 mm (critical value 1.5 mm) triggers the compensation channel, the latent heat of phase change parameter is 334 kJ / kg, and the dynamic overload power margin parameter of 0.78 is generated. Secondly, according to step 502, the ice crystal azimuth angle of 135° (check code 0x5E) and the axial stress peak value of 85 MPa are obtained, and a pulse parameter set [amplitude 20 dBm, pulse width 40 ms, frequency modulation slope 12 kHz / ms] is generated. Thirdly, through step 503, the creep compliance J(60 min) of the flange gasket is obtained as 0.032 GPa-1, and the bolt pre-tightening force decays to 85% of the initial value, and a non-uniform energy distribution is designed (the first peak is 18 dBm, and the subsequent pulses decay according to e^(-t / 80)). Finally, based on step 504, according to the Gold sequence time slot template (chip offset 15) and Turbo code error correction, an instruction set with a stress concentration factor correction coefficient of 1.8 is generated, and the bit error rate <10 -8 。

[0146] Steps 501-505 achieve a 55% increase in the transient pulse emission efficiency, an azimuth angle matching accuracy of ±3°, a 92% coincidence degree between the energy density distribution and the material creep characteristics, an improvement in the transmission reliability of the instruction set, a reduction in the flange stress concentration correction error, a reduction in the comprehensive energy consumption of the node, and meet the high-reliability monitoring requirements of polar pipelines through phase change thermodynamics feature extraction, tensor decomposition azimuth angle weighting, Maxwell creep modeling, and Gold sequence time slot interleaving.

[0147] To improve the spatial energy adaptability and the collaborative control ability of material deformation of the pipeline monitoring system in cold regions, by decomposing the axial / radial components of the ice crystal distribution gradient, an anisotropic compensation coefficient is generated by fusing the residual stress parameters of the weld; the heat flux density vector is corrected by combining the material thermal conductivity characteristics to generate an azimuth weighting matrix aligned with the main direction of the ice crystal; the ellipticity deformation parameter is used to modulate the pulse envelope phase, and an amplitude attenuation template is formed based on the bolt array distribution; finally, through the tensor fusion technology, the azimuth weight, the attenuation template and the temperature gradient data are integrated to generate a pulse parameter set that strictly matches the ice crystal azimuth check field, realizing the precise adaptation of the dynamic growth characteristics of the ice crystal and the electromagnetic wave energy distribution. In some embodiments, based on the change rate of the ice crystal distribution gradient, the dynamic overload power margin parameter is azimuth weighted through the margin parameter compensation channel, and the waveform envelope of the transient overload emission power pulse is phase modulated by using the pipeline axial stress distribution mode to generate a pulse parameter set that matches the check field of the ice crystal growth azimuth, including:

[0148] 601. Decompose the change rate of the ice crystal distribution gradient into the axial ice crystal growth rate and the radial penetration rate components of the pipeline, and combine the residual stress parameters at the pipeline weld to perform stress relaxation weight distribution on the two components to generate the ice crystal azimuth anisotropic compensation coefficient;

[0149] In step 601, the axial ice crystal growth rate is the ice layer expansion speed along the pipeline length direction, reflecting the fluid phase change volume expansion effect. The radial penetration rate component is the ice crystal intrusion speed perpendicular to the pipe wall, characterizing the ice-pipe interface adhesion strength. The ice crystal azimuth anisotropic compensation coefficient is a dynamic correction factor that quantifies the coupling effect between the ice crystal growth direction and the pipeline residual stress field.

[0150] In the embodiments of the present application, the principal component analysis (PCA) is used to decompose the change rate of the ice crystal distribution gradient, and the first principal component (PC1) is extracted as the axial growth rate, and the second principal component (PC2) is used as the radial penetration rate. The residual stress distribution at the pipeline weld is measured by the digital image correlation method (DIC), and the stress relaxation weight ratio of the axial and radial components is calculated by combining the Zener-Wert-Avrami phase change kinetic equation. The ice crystal azimuth anisotropic compensation coefficient is generated by the singular value decomposition (SVD) of the Hankel matrix, where the weight in the high residual stress area (>200 MPa) is increased by 20%-40%.

[0151] 602. Input the anisotropic thermal conductivity of the pipeline metal material through the margin parameter compensation channel, and combine the ice crystal azimuth anisotropic compensation coefficient to correct the heat flux density vector of the dynamic overload power margin parameter to generate an azimuth weighting matrix aligned with the main direction of the ice crystal growth;

[0152] In step 602, the anisotropic thermal conductivity is the thermal conductivity difference parameter of the metal material along different crystal orientations, which is calibrated by electron backscatter diffraction (EBSD). The azimuth angle weighting matrix is a polarization distribution matrix that spatially modulates the power margin according to the main crystal growth direction of ice crystals.

[0153] In the embodiment of the present application, a thermoelectric coupled finite element model (COMSOL Multiphysics) is constructed, and the anisotropic thermal conductivity (such as 16.2 W / m·K in the axial direction and 14.5 W / m·K in the radial direction of 304 stainless steel) and the compensation coefficient matrix are input. The heat flux density vector field is solved by the discrete dipole approximation (DDA) algorithm, and the spatial distribution of the dynamic overload power margin parameter is corrected by the Gram-Schmidt orthogonalization method. Finally, a 32×32 azimuth angle weighting matrix aligned with the main crystal growth direction of ice crystals is generated, and the matrix elements are proportional to the square of the cosine of the main crystal growth direction of ice crystals (detected by the Hough transform), and the azimuth angle resolution reaches ±1.5°.

[0154] 603. Phase-modulate the waveform envelope of the transient overload emission power pulse based on the pipeline ellipticity deformation parameter, and generate a pulse amplitude attenuation gradient template by using the circumferential distribution characteristics of the bolt array at the metal flange connection;

[0155] In step 603, the pipeline ellipticity deformation parameter is a dimensionless parameter that quantifies the change in the roundness of the pipeline cross-section, which is measured by a laser profile scanner. The pulse amplitude attenuation gradient template is a reference pattern that designs the pulse energy attenuation law according to the circumferential distribution of flange bolts.

[0156] In the embodiment of the present application, a correlation model between ellipticity deformation and pulse phase modulation is established based on the Mindlin-Reissner plate theory. The digital holographic interferometry (DHI) is used to monitor the pipeline cross-section deformation in real time, and the deformation parameter (such as the ellipticity from 1.05 to 1.12) is fitted by the Zernike polynomial. The circumferential distribution characteristics of the flange bolt array (such as the uniform distribution of 8 bolts) are used to generate a pulse amplitude attenuation gradient template through Fourier series expansion: where the amplitude of the main lobe is distributed cosine according to the bolt position, and the attenuation rate of the side lobe is inversely proportional to the pre-tightening force attenuation coefficient (measured by the ultrasonic time difference method).

[0157] 604. Perform tensor fusion on the azimuth angle weighting matrix and the pulse amplitude attenuation gradient template, and combine the pipeline circumferential temperature gradient data recorded in the verification field of the ice crystal growth azimuth angle to generate a pulse parameter set that matches the verification field of the ice crystal growth azimuth angle.

[0158] In step 604, tensor fusion is a high-order coupling operation that performs multi-dimensional spatial distribution matrices according to a given summation rule. The circumferential temperature gradient data is a thermal stress driving factor formed by the temperature difference in the circumferential direction of the pipeline.

[0159] In the embodiments of the present application, the azimuth weighted matrix (3rd order tensor) and the attenuation gradient template (2nd order tensor) are fused into a 4th order composite tensor by using Tucker decomposition. Combining the circumferential temperature gradient data (measured by an infrared thermal imager, ΔT_max = 8°C) in the ice crystal azimuth verification field, the tensor kernel function is optimized by the Levenberg-Marquardt algorithm. Finally, a set of pulse parameters matching the verification field of the ice crystal growth azimuth is generated, including 128 parameter combinations (16 amplitude levels × 8 pulse width levels × 4 frequency modulation modes), supporting an adaptive selection strategy based on the pipe curvature radius (R / D ≥ 2).

[0160] The following is a specific example:

[0161] Suppose this solution is adopted in the monitoring task of the wet automatic sprinkler system pipeline network in a certain data center. First, the ice crystal axial rate of 1.5 mm / s, radial 0.08 μm / s, and the weld residual stress of 225 MPa are obtained through step 601, and the anisotropy compensation coefficient of 0.18 is generated; the axial thermal conductivity of 15.8 W / m·K and radial 14.1 W / m·K, and the main lobe azimuth angle of the corrected azimuth weighted matrix of 147°, and the half-power beam width of ±12° are obtained through step 602; the ellipticity deformation of 1.08 and the flange 8 bolt pre-tightening force are attenuated to 78% through step 603, and a hexagonal attenuation template (main lobe amplitude -1.2 dB / bolt, side lobe attenuation slope -3.5 dB / 10°) is generated; finally, based on step 604, the circumferential temperature gradient ΔT = 6°C, the Tucker decomposition kernel function rank (3, 2, 2, 1) are obtained, and a set of pulse parameters [amplitude 19 dBm, pulse width 35 ms, frequency modulation slope 15 kHz / ms] is generated, and the bit error rate < 10 -9 。

[0162] Steps 601 - 604 achieve a tracking accuracy of ±1.8° for the main growth direction of ice crystals, an improvement in the spatial matching degree of pulse energy, a reduction in the compensation error of ellipticity deformation, a circumferential temperature gradient adaptability of ΔT = 10°C, an increase in the channel capacity of the pulse parameter set, and a control error of the flange bolt stress distribution < 4% through principal component decomposition of ice crystal anisotropy, thermal-electrical coupling vector correction, ellipticity deformation phase modulation, and high-order tensor fusion, meeting the requirements for multi-dimensional physical field collaborative monitoring of extremely cold pipelines.

[0163] To address the problem of insufficient accuracy in the ice-pipe multi-physical field coupling modeling for the risk assessment of frozen and cracked pipelines in cold regions, by decomposing the axial / radial components of the ice crystal dynamic parameters, a coupling increment map of ice layer thickness-tube material stress is generated in combination with the ice expansion coefficient database; based on the historical frost heave deformation data, the maximum principal stress direction is matched, and the dynamic stress concentration factor is generated by integrating the material aging characteristics; the anisotropic expansion coefficient of the material and the flange prestress parameters are introduced, and a proportional model of the critical ice thickness and the stress concentration factor is established to calculate the rupture risk probability; when the risk value exceeds the critical yield threshold of the material, according to the geometric mapping relationship between the ice crystal penetration rate and the pipe segment azimuth angle, the axial progressive electric tracing heating strategy is dynamically triggered to achieve hierarchical and precise suppression of the frost damage risk. In some embodiments, based on the ice expansion coefficient database of the pipeline material pre-stored in the remote control center, the ice crystal dynamic parameters and the material stress parameters in the composite freezing characteristics are matched, and the rupture risk probability of a specific pipe segment at the critical ice thickness is calculated, including:

[0164] 701. Decompose the ice crystal dynamic parameters in the composite freezing characteristics into the ice crystal axial growth rate and the ice crystal radial penetration rate, and combine the low-temperature phase change characteristic parameters and the yield strength attenuation gradient of the pipe material in the ice expansion coefficient database pre-stored in the remote control center to generate a coupling increment distribution map of ice layer thickness-tube material stress;

[0165] In step 701, the ice crystal axial growth rate is the length of the ice layer extension per unit time along the pipeline axis, reflecting the driving force of the fluid phase change volume expansion. The coupling increment distribution map of ice layer thickness-tube material stress is a spatio-temporal correlation matrix quantifying the ice layer thickening and the evolution of the tube material stress, including the principal stress vector field and the equivalent strain nephogram.

[0166] In the embodiments of the present application, the crystal plasticity finite element model (CPFEM) is used to decompose the ice crystal dynamic parameters, and the axial growth rate (based on the Norton power law equation) and the radial penetration rate (based on the Darcy-Stokes coupling equation) are calculated through the slip system activation theory. Combining the low-temperature phase change characteristic parameters of the pipe material (calibrated by differential scanning calorimetry) and the yield strength attenuation gradient (obtained by in-situ nanoindentation testing) in the ice expansion coefficient database, a multi-scale damage evolution equation is constructed. The extended finite element method (XFEM) is used to simulate the crack propagation at the ice-pipe interface, and a coupling increment distribution map of ice layer thickness-tube material stress containing 10^4 grid nodes is generated, with a spatial resolution of 0.1 mm / pixel.

[0167] 702. According to the historical frost heave deformation records of the pipe segments stored in the ice expansion coefficient database of the pipeline material, match the maximum principal stress direction in the coupling increment distribution map of ice layer thickness-tube material stress, and combine the material stress parameters corresponding to the actual service life of the pipeline to generate a dynamic ice expansion stress concentration factor;

[0168] In step 702, the historical frost heave deformation records are a time series database of the deformation amounts, temperature gradients, and stress concentration factors recorded in the annual frost heave events of the pipeline. The dynamic ice heave stress concentration factor is a three-dimensional stress amplification factor that integrates the real-time ice layer stress and the historical damage accumulation effect.

[0169] In the embodiment of the present application, the proper orthogonal decomposition (POD) is used to extract the dominant modes (the contribution rate of the first 5 modes > 85%) from the historical frost heave deformation records, and the maximum principal stress direction in the incremental distribution map is matched by Kriging interpolation (determined by Mohr circle analysis). Combining the material fatigue parameters corresponding to the service life of the pipeline (fitted by the Coffin-Manson equation), the Chaboche nonlinear kinematic hardening model is introduced to generate the dynamic ice heave stress concentration factor, where the factor value in the weld area is increased by 30% - 50%.

[0170] 703. Based on the proportional relationship between the critical ice thickness in the composite freezing characteristics and the dynamic ice heave stress concentration factor, the anisotropic expansion coefficient of the pipeline material and the flange assembly prestress parameters are introduced to calculate the rupture risk probability of a specific pipe section under the proportional relationship. In step 703, the anisotropic expansion coefficient is the thermal expansion difference parameter of the pipe material along the axial, radial, and circumferential directions, measured by laser speckle interferometry. The flange assembly prestress parameter is the contact stress distribution parameter of the flange sealing surface caused by the initial pre-tightening force of the bolts.

[0171] In the embodiment of the present application, a nonlinear proportional relationship model between the critical ice thickness and the dynamic stress concentration factor is established (R = P·Kt^m, m = 2.3). The anisotropic expansion coefficient (such as 17.5×10^-6 / ℃ axially and 15.2×10^-6 / ℃ radially) and the flange prestress (measured by an ultrasonic bolt stress gauge) are introduced through the multiaxial fatigue criterion (Crossland equation), and the Monte Carlo simulation (10^5 samplings) is used to calculate the rupture risk probability of a specific pipe section under the proportional relationship. The probability value is mapped to the 0 - 1 interval through the Weibull distribution function, and the threshold sensitivity reaches ±0.5%.

[0172] The following is a specific example:

[0173] Suppose this solution is adopted in the pipes of a wet automatic sprinkler system in a high-rise residential building in a cold region. First, based on step 701, the axial rate of ice crystals is 2.1 mm / s and the radial rate is 0.12 μm / s. The parameters of X80 steel (phase change expansion rate 0.018% / °C, yield strength attenuation -0.4 MPa / °C) are retrieved from the ice expansion coefficient database, and an incremental distribution map is generated showing a maximum equivalent strain of 0.35%. By matching the historical frost heave deformation mode 3 (contribution rate 28%) through step 702, the dynamic stress concentration factor Kt = 2.8 (reaching 3.5 at the weld). Then, through step 703, the critical ice thickness is 7.2 mm, the anisotropic expansion coefficient in the axial direction is 18.1×10^-6 / °C, the flange prestress is 82 MPa, and the Monte Carlo simulation gives a rupture risk probability of 94%.

[0174] To solve the problem of insufficient matching accuracy between the warming strategy and the risk probability after the frost heave and rupture of pipes in cold regions, this application proposes a gradient temperature control method based on the brittle transformation characteristics of materials and the spatial correlation of stress fields. In some embodiments, predicting the frost resistance of pipes based on the rupture risk probability and activating a pipe warming strategy corresponding to the rupture risk probability according to the prediction result of frost resistance includes:

[0175] 801. Based on the rupture risk probability, combining the low-temperature brittle transition temperature of the pipe material and the distribution of the ice crystal growth stress field, divide the frost resistance levels of pipe segments, and generate a prediction result of the frost resistance of the pipe including a frost resistance level identifier;

[0176] In step 801, the low-temperature brittle transition temperature is the critical temperature at which the material changes from ductile fracture to brittle fracture, and is calibrated through the Charpy impact test. The distribution of the ice crystal growth stress field is a three-dimensional stress tensor field generated by the expansion of the ice layer on the pipe wall, including the principal stress direction and the equivalent stress amplitude.

[0177] In the embodiments of this application, the crack driving force of different pipe segments under the action of the ice crystal growth stress field is calculated by the J integral method in fracture mechanics. Combining the low-temperature brittle transition temperature of the pipe material (such as -45°C for X70 steel), a two-parameter criterion of toughness and brittleness is constructed. When the local stress exceeds the toughness reserve of the material, it is divided into high, medium, and low frost resistance levels according to the risk probability thresholds (0.3 / 0.6 / 0.9), and a prediction result of the frost resistance of the pipe including a level identifier (H / M / L) is generated. The identifier is embedded in the pipe segment ID and the stress concentration coordinates.

[0178] 802. According to the frost resistance level identifier, match the pre-stored pipe warming strategy library, and extract the warming rate and target temperature corresponding to the frost resistance level of the pipe segment;

[0179] In step 802, the pipe warming strategy library is a set of pre-stored temperature control parameters corresponding to different frost resistance levels, including the warming rate and the target temperature.

[0180] In the embodiment of the present application, a case-based reasoning system (CBR) is used to design a pipeline heating-up strategy library. Each case contains the environmental parameters (temperature gradient, ice layer thickness) of historical frost heaving events and successful temperature control records. Through the OLAP multi-dimensional indexing technology, cases are quickly retrieved and matched according to the anti-freezing grade identifier, and the heating-up rate (such as 5°C / min for grade H and 3°C / min for grade M) and the target temperature (20°C higher than the brittle transition temperature) are extracted. At the same time, the material thermal hysteresis coefficient is introduced to correct the target temperature, and a time limit constraint is imposed on the heating-up parameter package.

[0181] 803. Based on the spatial correlation between the axial stress distribution pattern of the pipeline and the ice crystal penetration path, activate the electric tracing regions in descending order of the anti-freezing grade of the pipe segments, and generate a progressive heating-up instruction set for sub-regions;

[0182] In step 803, the axial stress distribution pattern of the pipeline is the stress propagation characteristic along the pipeline length direction, reflecting the energy accumulation trend of the ice crystal penetration path. The progressive heating-up instruction set for sub-regions is a control instruction sequence for activating the electric tracing in stages according to the priority of the risk level.

[0183] In the embodiment of the present application, an association model between the axial stress distribution pattern of the pipeline and the ice crystal penetration path is established based on the stress wave propagation theory, and the DBSCAN spatial clustering algorithm is used to identify the high-stress aggregation areas. The pipe segments are sorted in descending order of the anti-freezing grade of the pipe segments and divided into a core heating-up area, a transition area, and a monitoring area. The generation of the progressive heating-up instruction set for sub-regions adopts the Petri net modeling technology, defines the state transition rules of the temperature climbing stage (preheating, rapid rise, steady state), and ensures that there is a time overlap buffer period of 10 - 15 minutes in the heating-up process of adjacent segments to avoid secondary stress concentration caused by thermal shock.

[0184] 804. Execute the progressive heating-up instruction set for sub-regions, and dynamically adjust the electric tracing power output in combination with the heating-up rate, the target temperature, and the real-time frost layer thickness data on the pipeline surface, and generate a pipeline heating-up control signal matching the probability of rupture risk.

[0185] In step 804, the real-time frost layer thickness data on the pipeline surface is the thickness value of the ice and frost covering layer continuously measured by a microwave resonance sensor. The pipeline heating-up control signal is a closed-loop control signal integrating the power output instruction and the risk feedback.

[0186] In the embodiment of the present application, a fuzzy PID controller is constructed to perform multi-objective optimization on the heating rate, target temperature parameter, and real-time data of the frost layer thickness (sampling period: 500 ms). When the frost layer thickness exceeds the set threshold (such as 3 mm), the anti-integral saturation mechanism is triggered to dynamically increase the output slope of the electric tracing power. The pipeline heating control signal is transmitted in Manchester coding format, embedded with CRC-16 check code and timestamp information, and supports dual-mode communication of RS485 bus and power carrier to ensure the transmission integrity of the sectional progressive heating instruction set at a low temperature of -50°C.

[0187] The following is a specific example:

[0188] Suppose an ice crystal penetration event occurs in the DN150 pipeline section of the wet automatic sprinkler system in a large storage center. Through step 801, the brittle transition temperature of X80 steel is measured as -40°C, the maximum principal stress of the ice crystal stress field is 185 MPa, and the J integral value is 280 kJ / m 2 , the anti-freezing grade H is determined, and the prediction result [pipe section ID: GP-203, grade: H, coordinates: (x = 235 m, y = 0)] is generated; in step 802, the case of grade H is matched from the strategy library, the heating rate of 5°C / min and the target temperature of 20°C are extracted, and the superposed heat lag coefficient of 1.2 is corrected to 24°C; in step 803, the axial stress core area (235 - 240 m) is identified, and a sectional progressive heating instruction set [preheating area 230 - 235 m (2°C / min), rapid heating area 235 - 245 m (5°C / min), monitoring area 245 - 250 m (1°C / min)] is generated, and a 12-minute buffer overlap period is set; through step 804, the real-time frost layer thickness of 2.8 mm is obtained, the output power slope of the fuzzy PID is 0.8 kW / min, and the Manchester coding signal is transmitted to the tracing tape through RS485, and the temperature of the pipe section rises from -38°C to 20°C within 30 minutes.

[0189] Figure 2 The following is a schematic structural diagram of a pipeline anti-freezing prediction system for an automatic sprinkler system provided by an embodiment of the present application, as Figure 2 shown. The device includes:

[0190] A capture module 21, configured to collect ice crystal growth vibration signals caused by the phase change of the internal fluid of the pipeline wall of the automatic sprinkler system through an acoustic emission sensor, and synchronously correlate the real-time icing rate data collected by the temperature sensor mounted on the pipeline surface;

[0191] An output module 22 for inputting the ice crystal growth vibration signal and the real-time icing rate data into a multi-scale long short-term memory network, capturing the microsecond-level pulse waveform caused by the instantaneous rupture of ice crystals through a short-time-span memory unit, and simultaneously tracking the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material through a long-time-span memory unit, and outputting composite freezing features;

[0192] A transmission module 23 for adaptively adjusting the transmission power and modulation rate of LoRaWAN nodes according to the spatial distribution of the pipeline network and the priority of the composite freezing features, encoding the high-priority composite freezing features and the geographical location of the corresponding pipeline section into emergency data frames, and preferentially transmitting them to the remote control center through multi-hop routing;

[0193] An activation module 24 for matching the ice crystal dynamic parameters and material stress parameters in the composite freezing features based on the ice expansion coefficient database of the pipeline material pre-stored in the remote control center, calculating the rupture risk probability of a specific pipeline section at the critical icing thickness, predicting the anti-freezing ability of the pipeline based on the rupture risk probability, and activating the pipeline heating strategy corresponding to the rupture risk probability according to the anti-freezing ability prediction result.

[0194] Figure 2 The pipeline anti-freezing ability prediction device of an automatic sprinkler system can execute Figure 1 The pipeline anti-freezing ability prediction method of an automatic sprinkler system shown in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated. For the pipeline anti-freezing ability prediction device of an automatic sprinkler system in the above embodiment, the specific ways for each module and unit to execute operations have been described in detail in the embodiment related to the method, and will not be elaborated here.

[0195] In a possible design, Figure 2 The pipeline anti-freezing ability prediction device of an automatic sprinkler system shown in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and this computing device can include a storage component 31 and a processing component 32;

[0196] The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0197] The processing component 32 is used for the pipeline anti-freezing ability prediction method of an automatic sprinkler system in the above Figure 1 illustrated embodiment.

[0198] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above methods. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above methods.

[0199] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0200] Of course, the computing device may also necessarily include other components, such as input / output interfaces, display components, communication components, etc.

[0201] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above peripheral interface module may be an output device, an input device, etc.

[0202] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0203] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0204] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 shown embodiment of a method for predicting the anti-freezing property of the pipeline of an automatic sprinkler system.

[0205] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0206] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0207] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0208] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A method for predicting the frost resistance of pipes in an automatic sprinkler system, characterized in that Comprising: Collecting the ice crystal growth vibration signals caused by the phase change of the internal fluid in the pipeline wall of the automatic sprinkler system through acoustic emission sensors, and synchronously correlating the real-time icing rate data collected by the temperature sensors mounted on the pipeline surface; Inputting the ice crystal growth vibration signals and the real-time icing rate data into a multi-scale long short-term memory network, capturing the microsecond-level pulse waveforms caused by the instantaneous rupture of ice crystals through short-time-span memory units, and simultaneously tracking the minute-level low-frequency oscillations accumulated by the fatigue deformation of the pipeline material through long-time-span memory units, and outputting composite freezing characteristics; According to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, adaptively adjusting the transmission power and modulation rate of LoRaWAN nodes, encoding the high-priority composite freezing characteristics and the geographical location of the corresponding pipeline segments into emergency data frames, and preferentially transmitting them to the remote control center through multi-hop routing; Based on the pipeline material ice expansion coefficient database pre-stored in the remote control center, matching the ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics, calculating the rupture risk probability of a specific pipeline segment at the critical icing thickness, predicting the frost resistance of the pipeline based on the rupture risk probability, and activating the pipeline heating strategy corresponding to the rupture risk probability according to the frost resistance prediction result.

2. The method according to claim 1, wherein The step of inputting the ice crystal growth vibration signals and the real-time icing rate data into a multi-scale long short-term memory network, capturing the microsecond-level pulse waveforms caused by the instantaneous rupture of ice crystals through short-time-span memory units, and simultaneously tracking the minute-level low-frequency oscillations accumulated by the fatigue deformation of the pipeline material through long-time-span memory units, and outputting composite freezing characteristics, includes: Before inputting the ice crystal growth vibration signals into the multi-scale long short-term memory network, performing vibration component elimination processing on the ice crystal growth vibration signals to eliminate non-phase change interference, and retaining the vibration components coaxial with the pipeline axial stress direction; Inputting the vibration components into the time-frequency decomposition layer, separating the high-frequency sub-signals representing the instantaneous rupture of ice crystals and the low-frequency sub-signals reflecting the plastic deformation of the material, and simultaneously converting the real-time icing rate data into icing dynamic coefficients aligned with the time stamps of each sub-signal; Inputting the high-frequency sub-signals into the short-time-span memory unit for microsecond-level waveform profile tracking, capturing the phase mutation points between adjacent ice crystal rupture events, and jointly inputting the low-frequency sub-signals and the icing dynamic coefficients into the long-time-span memory unit for oscillation mode correlation to establish an implicit correlation between the change in the pipeline cross-section ellipticity and the stress relaxation rate; Performing dynamic weight allocation on the phase mutation points and the implicit correlation, and combining the pre-stored Young's modulus parameters and thermal expansion coefficient parameters of the pipeline to generate composite freezing characteristics including the ice crystal distribution gradient and the attenuation trend of the material yield strength.

3. The method according to claim 1, wherein According to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, adaptively adjusting the transmission power and modulation rate of LoRaWAN nodes, encoding the high-priority composite freezing characteristics and the geographical location of the corresponding pipeline segments into emergency data frames, and preferentially transmitting them to the remote control center through multi-hop routing, includes: Analyze the risk probability of pipeline rupture and the stress concentration factor in the composite freezing characteristics, and combine the distance parameter between adjacent nodes and the historical signal interference parameter in the pipeline distribution topology to calculate the dynamic transmission path loss threshold of each LoRaWAN node; According to the dynamic transmission path loss threshold and the change rate of the ice crystal distribution gradient in the composite freezing characteristics, dynamically allocate the transmission power level and the quadrature modulation index, and synchronously combine the remaining energy parameter of the node to constrain the maximum adjustable power range; Classify and code the high-priority composite freezing characteristics and the corresponding pipe segment geographical locations according to the pipe diameter specifications, construct a frame header containing the pipe segment identifier and a check field for the ice crystal growth azimuth angle, and generate an emergency data frame with a topology awareness mark; Based on the pre-stored metal obstacle attenuation map in the pipeline distribution topology, select a relay node sequence with the minimum path fading, and realize the multi-hop relay transmission of the emergency data frame by alternately using the ground reflection wave and the direct wave propagation modes.

4. The method according to claim 3, characterized in that, The step of dynamically allocating the transmission power level and the quadrature modulation index according to the dynamic transmission path loss threshold and the change rate of the ice crystal distribution gradient in the composite freezing characteristics, and synchronously combining the remaining energy parameter of the node to constrain the maximum adjustable power range includes: Establish a transmission power allocation model, and convert the change rate of the ice crystal distribution gradient and the remaining energy parameter in the composite freezing characteristics into a power allocation reference value through the thermodynamic expansion margin; Perform phase sensitivity calibration on the quadrature modulation index according to the dynamic transmission path loss threshold. When the dynamic transmission path loss threshold exceeds the theoretical attenuation value of the pipeline insulation layer, trigger a compensation mechanism for the quadrature modulation index to shift in the anti-multipath interference direction, and output a time-varying compensation coefficient; Inject the time-varying compensation coefficient into the transmission power allocation model. When the frost layer thickness exceeds the critical value of the sealing gap at the metal flange connection, trigger a transient overload transmission power pulse based on the power allocation reference value, and constrain the transient overload transmission power pulse within the maximum adjustable power range allowed by the remaining energy parameter of the node; Perform time slot interleaving coding on the quadrature modulation index after phase sensitivity calibration and the power level of the transient overload transmission power pulse to generate an adaptive communication parameter configuration table adapted to the Doppler frequency shift characteristics at the pipeline elbow.

5. The method according to claim 4, wherein The step of injecting the time-varying compensation coefficient into the transmission power allocation model. When the frost layer thickness exceeds the critical value of the sealing gap at the metal flange connection, trigger a transient overload transmission power pulse based on the power allocation reference value, and constrain the transient overload transmission power pulse within the maximum adjustable power range allowed by the remaining energy parameter of the node includes: Input the time-varying compensation coefficient into the transmission power allocation model, and combine the real-time growth rate of the frost layer thickness and the latent heat of phase change parameter of the pipeline metal material to generate a dynamic overload power margin parameter. The nodes corresponding to the pipe segments where the frost layer thickness exceeds the critical value of the sealing gap automatically activate the margin parameter compensation channel; Based on the change rate of the ice crystal distribution gradient, perform azimuthal weighting on the dynamic overload power margin parameter through the margin parameter compensation channel, and perform phase modulation on the waveform envelope of the transient overload emission power pulse using the pipeline axial stress distribution pattern to generate a set of pulse parameters that match the verification field of the ice crystal growth azimuth angle; Based on the creep parameter of the sealing material at the metal flange connection and the bolt pre-tightening force attenuation coefficient, establish a time-domain energy distribution constraint condition, so that the set of pulse parameters forms a non-uniform energy density distribution within the maximum adjustable power range allowed by the remaining energy parameter of the node; Interleave the non-uniform energy density distribution with the dynamic overload power margin parameter to generate a transient overload emission instruction set carrying the correction parameter of the stress concentration factor at the metal flange connection.

6. The method according to claim 5, wherein The method of performing azimuthal weighting on the dynamic overload power margin parameter through the margin parameter compensation channel based on the change rate of the ice crystal distribution gradient, and performing phase modulation on the waveform envelope of the transient overload emission power pulse using the pipeline axial stress distribution pattern to generate a set of pulse parameters that match the verification field of the ice crystal growth azimuth angle includes: Decompose the change rate of the ice crystal distribution gradient into the pipeline axial ice crystal growth rate and the radial penetration rate component, and combine the residual stress parameter at the pipeline weld to perform stress relaxation weight distribution on the two components to generate an ice crystal azimuth anisotropy compensation coefficient; Input the anisotropic thermal conductivity of the pipeline metal material through the margin parameter compensation channel, and combine the ice crystal azimuth anisotropy compensation coefficient to correct the dynamic overload power margin parameter for the heat flux density vector to generate an azimuthal weighting matrix aligned with the main direction of ice crystal growth; Perform phase modulation on the waveform envelope of the transient overload emission power pulse based on the pipeline ovality deformation parameter, and generate a pulse amplitude attenuation gradient template using the circumferential distribution characteristics of the bolt array at the metal flange connection; Perform tensor fusion on the azimuthal weighting matrix and the pulse amplitude attenuation gradient template, and combine the pipeline circumferential temperature gradient data recorded in the verification field of the ice crystal growth azimuth angle to generate a set of pulse parameters that match the verification field of the ice crystal growth azimuth angle.

7. The method according to claim 1, characterized in that The method of matching the ice crystal dynamic parameter and the material stress parameter in the composite freezing characteristic based on the pipeline material ice expansion coefficient database pre-stored in the remote control center, and calculating the rupture risk probability of a specific pipe section under the critical ice thickness includes: Decompose the ice crystal dynamic parameter in the composite freezing characteristic into the ice crystal axial growth rate and the ice crystal radial penetration rate, and combine the low-temperature phase change characteristic parameter and the yield strength attenuation gradient of the pipe material in the pipeline material ice expansion coefficient database pre-stored in the remote control center to generate an ice layer thickness - pipe material stress coupling increment distribution map; According to the historical frost heave deformation record of the pipe section stored in the pipeline material ice expansion coefficient database, match the direction of the maximum principal stress in the ice layer thickness - pipe material stress coupling increment distribution map, and combine the material stress parameter corresponding to the actual service life of the pipeline to generate a dynamic ice expansion stress concentration factor; Based on the proportional relationship between the critical ice thickness in the composite freezing characteristics and the dynamic ice expansion stress concentration factor, the anisotropic expansion coefficient of the pipeline material and the flange assembly prestress parameters are introduced to calculate the rupture risk probability of a specific pipe section under this proportional relationship.

8. The method according to claim 7, wherein Predict the frost resistance of the pipeline based on the rupture risk probability, and activate the pipeline heating-up strategy corresponding to the rupture risk probability according to the frost resistance prediction result, including: Based on the rupture risk probability, combined with the low-temperature brittle transition temperature of the pipeline material and the distribution of the ice crystal growth stress field, divide the frost resistance level of the pipe section, and generate a pipeline frost resistance prediction result including a frost resistance level identifier; According to the frost resistance level identifier, match the pre-stored pipeline heating-up strategy library, and extract the heating-up rate and target temperature corresponding to the frost resistance level of the pipe section; Based on the spatial correlation between the pipeline axial stress distribution pattern and the ice crystal penetration path, activate the electric tracing heating areas in order from high to low according to the frost resistance level of the pipe section, and generate a sectional progressive heating instruction set; Execute the sectional progressive heating instruction set, and combine the heating-up rate, the target temperature and the real-time frost layer thickness data on the pipeline surface to dynamically adjust the electric tracing heating power output, and generate a pipeline heating-up control signal matching the rupture risk probability.

9. A pipeline antifreeze prediction system for an automatic sprinkler system, characterized in that, Including: A capture module, configured to collect the ice crystal growth vibration signal caused by the phase change of the internal fluid of the automatic sprinkler system pipeline wall through an acoustic emission sensor, and synchronously correlate the real-time ice formation rate data collected by the temperature sensor mounted on the pipeline surface; An output module, configured to input the ice crystal growth vibration signal and the real-time ice formation rate data into a multi-scale long short-term memory network, capture the microsecond-level pulse waveform caused by the instantaneous rupture of ice crystals through the short-time span memory unit, and at the same time track the minute-level low-frequency oscillation accumulated by the fatigue deformation of the pipeline material through the long-time span memory unit, and output composite freezing characteristics; A transmission module, configured to adaptively adjust the transmission power and modulation rate of the LoRaWAN node according to the spatial distribution of the pipeline network and the priority of the composite freezing characteristics, encode the high-priority composite freezing characteristics and the corresponding pipe section geographical location into an emergency data frame, and preferentially transmit it to the remote control center through multi-hop routing; An activation module, configured to match the ice crystal dynamic parameters and material stress parameters in the composite freezing characteristics based on the pipeline material ice expansion coefficient database pre-stored in the remote control center, calculate the rupture risk probability of a specific pipe section at the critical ice thickness, predict the frost resistance of the pipeline based on the rupture risk probability, and activate the pipeline heating-up strategy corresponding to the rupture risk probability according to the frost resistance prediction result.

10. A computing device, characterized in that, Including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for predicting the frost resistance of the pipeline of an automatic sprinkler system according to any one of claims 1 to 7.

Images