A heat exchange pipe maintenance and intelligent operation and maintenance control method of an energy pile active bridge deck deicing and snow melting system

Abstract

The present application belongs to the field of geothermal energy development and utilization, bridge engineering, and deicing and snow melting technology, and proposes a heat exchange pipe maintenance and intelligent operation and maintenance control method for an energy pile active bridge deck deicing and snow melting system, which comprises an energy pile active bridge deck deicing and snow melting federated learning operation and maintenance control model and a heat exchange pipe maintenance device based on electromagnetic induction principle; the energy pile active bridge deck deicing and snow melting federated learning operation and maintenance control model preliminarily judges and makes alarm positioning, and the heat exchange pipe maintenance device based on electromagnetic induction principle carries out fine repair work; the damaged point is repaired by automatic repair agent or the inner layer pipe is unscrewed. The heat exchange pipe maintenance device based on electromagnetic induction principle comprises a double-layer intelligent heat exchange pipe structure, a micro magneto-electric sensor, a cable storage tray, a data automatic acquisition instrument and a control end. The present application realizes fine control management and early warning of the energy pile active bridge deck deicing and snow melting system, accurately positions and repairs the damaged point, globally and accurately controls the snow melting system, and improves the deicing and snow melting efficiency.

Description

Technical Field

[0001] This invention relates to the fields of geothermal energy development and utilization, bridge engineering, and de-icing and snow melting technology, and in particular to a method for overhauling and intelligent operation and maintenance control of heat exchange tubes in an energy pile active bridge deck de-icing and snow melting system. Background Technology

[0002] Snow and ice accumulation on bridges severely impacts the transportation capacity of highways and municipal roads in northern Chinese cities. Studies show that snow and ice can reduce the road surface adhesion coefficient by 60-70%, leading to vehicle braking failure, skidding, and serious traffic accidents. To overcome the problems of traditional snow melting technologies, such as bridge surface corrosion, environmental pollution, and high costs, researchers have proposed various active bridge de-icing and snow melting technologies, mainly including phase change material (PCM) de-icing, solar de-icing, electrically heated pavement, and geothermal de-icing. PCM de-icing technology has good de-icing effect, but the cost of PCM materials is too high, and it is mostly used in demonstration projects. Solar snow melting technology has low energy consumption, but its de-icing stability is highly dependent on sunlight conditions and has poor stability. Electrothermal snow melting and de-icing technology has good thermal stability, but it consumes a lot of electricity and has high operating costs. In comparison, shallow geothermal energy, as a widely distributed renewable and clean energy source, has broad prospects for de-icing and snow melting.

[0003] The active bridge de-icing and snow-melting technology using energy piles involves burying heat exchange pipes in the bridge pile foundation and bridge deck. These pipes extract shallow geothermal energy, which is then pumped to the heat exchange pipes on the bridge deck by a heat pump unit, ultimately achieving the purpose of de-icing and snow-melting. This technology boasts advantages such as controllable construction costs, simple construction, high stability, and low operating costs.

[0004] Chinese invention patent application number CN202010660161.9, entitled "An Electric Heating System for Road Icing and Snow Melting and Its Laying Method," discloses an electric heating system for road icing and snow melting that includes several heating systems, such as road section and road surface slippage sensors, temperature sensors, and several heating cables. By replacing the traditional spraying method with heating cables, it can automatically heat and remove ice while monitoring road conditions in real time.

[0005] Chinese invention patent application number CN 202110608504.1, entitled "An Intelligent Snow Melting and Ice Removing System for Urban Pedestrian Roads and Its Construction Method", discloses an intelligent snow melting and ice removing system for urban pedestrian roads that includes an intelligent control module, a data acquisition module, a pedestrian road module, and a terminal system. The intelligent control module includes a server and an intelligent controller, and the data acquisition module includes a high-definition camera, an icing detector, and a temperature and humidity sensor.

[0006] Chinese invention patent application number CN 202210226666.3, entitled "A buried pipe ground source heat pump road de-icing and snow-melting system and method", discloses a buried pipe ground source heat pump road de-icing and snow-melting system including a ground source heat pump unit, a shallow geothermal heat exchange section structure and a heating pipeline section structure.

[0007] Chinese invention patent application number CN 202210017291.X, entitled "An Active Snow Melting System for Road Surfaces and Its Control Method", discloses a control method for starting and stopping the system by acquiring road surface temperature, road ice and snow images and comparing them with a database.

[0008] Chinese invention patent application number CN201610200872.1, entitled "A Ground Source Heat Pump Control Method and System", discloses a method that uses the predicted value of greenhouse temperature instead of the real-time temperature value as part of the input of the heat pump unit controller, thereby realizing pre-control.

[0009] Chinese invention patent application number CN202010244228.0, entitled "A Method and Apparatus for Performance Testing and Optimization Control of a Ground Source Heat Pump System," discloses a method for calculating the real-time unit energy efficiency ratio of the system based on collected real-time operating data, thereby further determining the real-time operating status of the system. The system adjustment mode is determined by comparing historical operating data.

[0010] The aforementioned research on active bridge de-icing and snow melting technology using energy piles mainly focuses on system composition, equipment, and construction methods, lacking research on the operation and maintenance control of such systems. The limited control methods available primarily address the control of ground source heat pump units based on bridge snow accumulation or changes in air conditioning terminal demand. In practical engineering, the operation of an active bridge de-icing and snow melting system involves dynamic coordination between the bridge deck buried pipe end, the unit equipment end, and the energy pile buried pipe end. Controlling only the heat pump unit is detrimental to stable system operation, easily causing overload alarms and reducing service life. Therefore, a scientific and reasonable refined operation and maintenance control and collaborative management method is needed to improve the accuracy of the control scheme and the stability of system operation.

[0011] Machine learning is a scientific technology that enables computers to automatically analyze and extract patterns from a type of data by establishing appropriate algorithms, and then use these patterns to predict unknown data. By training a large number of data samples with machine learning, control schemes under different operating conditions can be obtained. This can be used for the intelligent control of active bridge de-icing and snow melting systems using energy piles, and to promptly locate and alarm for initial faults.

[0012] Chinese utility model patent application number CN201721077937.4, entitled "A Permanently Detectable Polyethylene Composite Pipe", discloses a permanently detectable polyethylene composite pipe, comprising a double-layer structure pipe composed of a polyethylene layer and a modified PP coating layer. The pipe body is damaged by detecting the current of the tracer metal strip between the inner and outer layers using a multimeter.

[0013] Chinese invention patent application number CN202111660338.6, entitled "Anti-blockage and dredging system for municipal road engineering and its working method", discloses an anti-blockage and dredging system for municipal road engineering composed of a dredging trolley, a trolley drive mechanism, a visual inspection mechanism, an industrial and mining inspection mechanism and a display mechanism.

[0014] In the aforementioned composite pipeline technologies, the metal strips require assembly and connection, which can easily lead to short circuits or open circuits during the construction phase. Furthermore, municipal pipeline dredging systems are limited to large-diameter municipal pipe networks. Existing technologies cannot be applied to the inspection and maintenance of deeply buried, small-diameter energy piles and heat exchanger pipes within bridge deck pavement layers. Summary of the Invention

[0015] To overcome the following shortcomings and problems in the existing technology: (1) lack of control methods for bridge deck buried pipe structures; (2) lack of multi-module collaborative dynamic control methods for active bridge deck de-icing and snow melting using energy piles; (3) various heat exchange pipes are permanent or semi-permanent designs, making them impossible to repair after failure. Therefore, this invention patent provides a method for the maintenance and intelligent operation and maintenance control of heat exchange pipes in an active bridge deck de-icing and snow melting system using energy piles.

[0016] The technical solution of this invention is as follows: a method for the maintenance and intelligent operation and maintenance control of heat exchange tubes in an active bridge de-icing and snow melting system using energy piles, comprising a federated learning operation and maintenance control model for active bridge de-icing and snow melting using energy piles, consisting of a central server and local clients, and a heat exchange tube maintenance device based on the principle of electromagnetic induction; based on the federated learning operation and maintenance control model for active bridge de-icing and snow melting using energy piles, a preliminary judgment is made and a preliminary alarm location is established, and on this basis, the heat exchange tube maintenance device based on the principle of electromagnetic induction is arranged to carry out refined repair work;

[0017] The energy pile active bridge deck de-icing and snow melting federated learning operation and maintenance control model, consisting of a central server and local clients, includes three local client modules: a bridge deck buried pipe end control module, a generator equipment control module, and an energy pile buried pipe end control module. The local models of the three local client modules are trained on the local clients, and then the calculation results are encrypted and uploaded to the central processor for processing by the global federated learning model. The results obtained from the global federated learning model are then distributed to the local models of each local client. Through repeated iterations between the client and the central server, until the global federated learning model reaches stability, a matching control scheme for different modules is finally made.

[0018] The specific steps are as follows:

[0019] D1: Obtain the operating parameters of the bridge deck buried pipe end, the control parameters of the bridge deck buried pipe end, the operating parameters of the unit equipment, the control parameters of the unit equipment, the operating parameters of the energy pile buried pipe end, and the control parameters of the energy pile buried pipe end; perform sample data quality analysis and cleaning; extract the data distribution pattern from the cleaned sample data; analyze the characteristics of the sample data; and allocate them to the corresponding calculation module client.

[0020] The sample data can be obtained through at least one of the following: numerical simulation calculation, on-site monitoring technology, questionnaire survey technology, image recognition technology, and thermal infrared technology.

[0021] The data cleaning targets invalid values, outliers, missing values, and duplicate values. The data cleaning process includes identifying invalid values, outliers, and missing values; and processing outliers, invalid values, and missing values.

[0022] Optionally, the identification of invalid values, outliers, and missing values ​​can be based on one of the following: 1. Visually identifying outliers (i.e., invalid values) by plotting a scatter plot that reflects the relationship between two sets of data; 2. When the data follows a normal distribution, outliers can be identified using the 3σ principle. In this case, values ​​in a set of measurements that deviate from the mean by more than three times the standard deviation are defined as outliers; 3. Statistically calculating the maximum, minimum, median, and upper and lower quartiles of the dataset and plotting a box plot. Outliers or invalid values ​​can be identified based on the upper and lower quartiles of the box plot.

[0023] Optionally, the handling of invalid, outlier, and missing values ​​can be based on one of the following: 1. Direct deletion; 2. Fitting invalid, outlier, and missing values ​​according to a regression model or maximum likelihood estimation; 3. Filling invalid, outlier, and missing values ​​with statistical data features according to the mean, median, and mode.

[0024] D2: Update the local models of 3 local clients: the local model of support vector machine for bridge deck buried pipe control, the local model of random forest for generator equipment control, and the local model of decision tree for energy pile buried pipe control;

[0025] D3: Encrypt the local model results from the three local clients into de-identified parameters using a public key and upload them to the central server; the relevant data for client i is represented as follows: Can be encrypted as

[0026] D4: The central server uses its private key to decrypt the encrypted and anonymized parameters uploaded by the three local clients. The central server then performs the decoding operation on the encrypted and anonymized parameters, performs secure aggregation, and subsequently updates the global federated learning model. The central server can... Decoding of encrypted and desensitized parameters is performed. The central server updates the global federated learning model using one or more synchronous methods, such as gradient averaging, federated averaging, and knowledge distillation. After each round of global federated learning model weight update, the central server calculates the error and accuracy of the global federated learning model.

[0027] Preferably, all client models are aggregated through federated learning based on knowledge distillation, according to the formula... Perform global model weight updates on three clients, where W... n+1 These are the global model parameters for the nth round. The client sub-model weights are uploaded to the server by client i in the nth round. After each round of model weight updates, the central server calculates the error and accuracy of the global model.

[0028] D5: The central server generates a public key for encrypting transmitted data using the global federated learning model and distributes it to each client. Based on the global federated learning model, each local client updates the iteration results of other clients as the attribute parameters of the new sample data. For example, the random forest local model of the unit equipment control module client updates the operating parameters and control parameters of the bridge deck buried pipe control client and the energy pile buried pipe control client based on the global shared model.

[0029] D6: Repeat steps D2 to D5 iteratively until the global federated learning model is stable. Finally, the client calculates the corresponding results based on the global federated learning model. Calculate the mutually matched control states in the active bridge deck de-icing and snow melting system of the energy piles, including the opening degree of various regulating valves in the chilled water circulation loop at the bridge deck buried pipe end, the snow melting time at the bridge deck buried pipe end, the unit control parameters, and the control parameters at the energy pile buried pipe end.

[0030] The operating parameters of the bridge deck buried pipe end include: ambient temperature, ambient humidity, wind speed, snowfall, surface snow-free rate, manifold water level, pressure difference and temperature difference, manifold flow rate, manifold pressure, manifold temperature, bridge deck buried pipe supply water temperature, bridge deck buried pipe return water temperature, bridge deck buried pipe supply flow rate, bridge deck buried pipe return water flow rate, bridge deck buried pipe supply pressure, and bridge deck buried pipe return water pressure. The operating parameters of the unit equipment include: condenser working liquid level, condenser inlet temperature, evaporator working liquid level, evaporator inlet temperature, and compressor pressure. The operating parameters of the energy pile buried pipe end include: soil temperature, energy pile buried pipe end manifold water level, pressure difference, manifold flow rate, pressure, temperature, energy pile supply water temperature, and return water temperature. Flow rate and water pressure; the control parameters of the bridge deck buried pipe end include: the opening degree of the bridge deck buried pipe return water control valve, the opening degree of the bridge deck buried pipe supply water control valve, the opening degree of the water collector manifold control valve, the opening degree of the water collector branch pipe control valve, the opening degree of the water distributor manifold control valve, the opening degree of the water distributor branch pipe control valve, and the opening degree of the water supply pump control valve; the control parameters of the unit include: the opening degree of the water supply pump control valve, the opening degree of the cooling circulation pump control valve, the opening degree of the chilled water circulation pump control valve, the opening degree of the expansion valve, and the main unit; the control parameters of the energy pile buried pipe end include: the opening degree of the energy pile water collector manifold control valve, the opening degree of the water collector branch pipe control valve, the opening degree of the energy pile water distributor manifold control valve, the opening degree of the water distributor branch pipe control valve, the opening degree of the energy pile return water control valve, and the opening degree of the water supply control valve.

[0031] The energy pile buried pipe control module establishes a local decision tree model of the energy pile buried pipe control parameters based on the operating parameters of the energy pile buried pipe end, the unit equipment operating parameters updated by the central server, and the bridge deck buried pipe end operating parameters as sample attribute data; it determines the heat extraction of the energy pile and the control parameters of the energy pile buried pipe end and uploads them to the central processor in encrypted form; the decision tree model is generated through one or more of the following algorithms: ID3, C4.5, and CART; the specific steps are as follows:

[0032] D2.1.1: Decrypt the public key used for encrypted data transmission using the private key; update the bridge deck buried pipe end control module, unit equipment control module, and energy pile buried pipe end control module of the three local clients according to the global federated learning model of the central server; and use the iteration result as the attribute parameters of the new sample data; calculate the relationship between any attribute A and all its corresponding attribute values ​​A. i The Gini coefficient;

[0033] Given the Gini coefficient of a sample set D:

[0034] Given attribute A, the Gini coefficient of set D is:

[0035] Among them, C kLet D be a subset of samples belonging to the k-th class, where k is the number of classes, and D1 and D2 are sample sets D based on whether attribute A equals A. i A subset of the samples that has been split.

[0036] D2.1.2: Among all attributes A and their corresponding attribute values, select the attribute with the smallest Gini coefficient and its corresponding attribute value as the optimal attribute and the optimal split point; generate two child nodes with the optimal attribute and the optimal split point, and assign the corresponding samples to the root node;

[0037] D2.1.3: Treat each root node as a complete dataset, iteratively call steps D2.1.1 to D2.1.2, divide the samples according to the suboptimal attribute, and form leaf nodes by taking samples with the same suboptimal attribute value as the same sample set. Iterate in sequence using the REP method, PEP method or MEP method until the decision tree pruning condition is met, the number of samples in the leaf node or the Gini coefficient is less than the threshold, and the decision tree is formed.

[0038] D2.1.4: Compare the determined control parameters of the buried pipe end of the energy pile with the equipment control threshold. When the calculation result meets the equipment control threshold, the decision calculation result is used as advanced predictive control information, which is converted into encrypted parameters using a public key and uploaded to the central server for global federated learning model iteration. When the calculation result exceeds the equipment control threshold, proceed to step D2.1.5.

[0039] D2.1.5: Output the determined control parameters of the buried pipe end of the energy pile and issue an alarm. Use the control threshold as the advanced prediction control information and convert it into encrypted parameters using the public key to upload it to the central server for global federated learning model iteration; arrange the heat exchange tube maintenance device based on the principle of electromagnetic induction for fine detection and positioning.

[0040] The bridge deck buried pipe end control module uses the operating parameters of the bridge deck buried pipe end, the unit equipment operating parameters updated by the central server, and the energy pile buried pipe end operating parameters as sample attribute data for the bridge deck buried pipe end control local model; it establishes a bridge deck buried pipe end control support vector machine local model, predicts and calculates the control scheme, and uploads it to the central server in encryption; the specific steps are as follows:

[0041] D2.2.1: Decrypt the public key of the encrypted data using the private key, update the client of the energy pile buried pipe end control module, the unit equipment control module, and the bridge deck buried pipe end control module according to the global federated learning model of the central server, and use the iteration results as the attribute parameters of the new sample data; use the ambient temperature, ambient humidity, wind speed, snowfall, surface snow-free rate, manifold water level, pressure difference, temperature difference, bridge deck buried pipe supply and return water temperature, flow rate, and pressure as the sample attribute space set, and use the bridge deck buried pipe end control parameters as the learning target;

[0042] D2.2.2: Introducing slack variable ξ i A nonlinear segmentation support vector classifier considering soft margins is constructed using the penalty coefficient C to represent the relationship between the operating parameters and control parameters of the bridge deck buried pipe end; the prediction accuracy and self-stability of the local model of the bridge deck buried pipe end control support vector machine are represented by the loss function L = max(0,|z|-∈); the loss function is converted into a conditional extremum function;

[0043]

[0044] Where w is the normal vector of the hyperplane, C is the penalty coefficient, and ξ, ξ * y is the relaxation factor, ∈ is the hyperparameter that determines the boundary width; i The actual test results for the training samples; f(X) i )=w·Φ(X)+b is the classification hyperplane of the local model of the support vector machine for the control of the buried pipe end on the bridge deck; i is the training sample number; N is the number of training set samples; Φ(X) is the nonlinear mapping function;

[0045] D2.2.3: The above conditional extremum function is transformed into a multivariate function by using the Lagrange function. The partial derivatives of the Lagrange function with respect to the optimization objectives w, b, ξ are set to 0 to obtain the Lagrange multipliers. The conditional extremum function is then transformed into a dual function, thereby finding the minimum value of the prediction boundary.

[0046] D2.2.4: The inner product φ(X) of the nonlinear mapping function Φ(X) contained in the classification hyperplane in the local model of the support vector machine for bridge deck buried pipe control. i ) T φ(X j Choose one or more kernel functions from Gaussian kernel, linear kernel, polynomial kernel, and Sigmoid kernel for processing;

[0047] D2.2.5: Optimize the model parameters in the local model of the support vector machine for bridge deck buried pipe control: insensitive loss function ∈, penalty coefficient C, hyperparameters γ, λ, α, c, d in the kernel function; select one or more optimization methods from simulated annealing, grid search, particle swarm optimization, PSO algorithm, and genetic algorithm;

[0048] D2.2.6: Input the target operating parameters of the bridge deck buried pipe, and use the trained bridge deck buried pipe end control support vector machine local model to predict and calculate the bridge deck buried pipe end;

[0049] D2.2.7: Compare the calculation results with the control threshold of the chilled water circulation loop control valve. When the calculation results meet the control threshold of the chilled water circulation loop control valve, the predicted calculation results are used as advance prediction control information, which are converted into encrypted parameters using the public key and uploaded to the central server for global federated learning model iteration. When the calculation results exceed the control threshold of the chilled water circulation loop control valve, step D2.2.8 is executed.

[0050] D2.2.8: Output the calculated control results of the buried pipe end on the bridge deck and issue an alarm. Use the equipment control threshold as the advanced predictive control information, convert it into encrypted parameters using the public key, and upload it to the central server for global federated learning model iteration. At the same time, arrange a heat exchange tube maintenance device based on the principle of electromagnetic induction for fine detection and positioning.

[0051] The unit equipment control module uses various operating parameters of the unit equipment, energy pile operating parameters updated by the central server, and bridge deck buried pipe end operating parameters as sample attribute data to establish a random forest local model of the unit equipment control parameters, determine the unit equipment control parameters, and encrypt and upload them to the central processor; the specific steps are as follows:

[0052] D2.3.1: Decrypt the public key of the encrypted data using the private key, and use the updated energy pile operation parameters and bridge deck buried pipe end operation parameters from the global federated learning model of the central server as new sample data attribute parameters; based on the local sample data, use the state parameters of each unit equipment as the sample attribute space set, and use the unit equipment control parameters as the learning target; use the Bootstrap sampling method to randomly generate a subset of samples from the unit equipment control training samples, and use it as the training sample of one of the decision tree models, repeating the sampling k times to form k decision tree training samples;

[0053] D2.3.2: Train decision trees based on a subset of attributes from k training samples to form k independent random decision trees;

[0054] D2.3.3: The random forest randomly selects a classifier to vote on the control schemes of the unit equipment predicted by k decision trees, and the voting result is taken as the optimal control scheme of the unit equipment.

[0055] D2.3.4: Compare the determined unit equipment control parameters with the unit equipment control thresholds. When the calculation result meets the unit equipment control thresholds, the decision calculation result is used as advanced predictive control information, which is converted into encrypted parameters using a public key and uploaded to the central server for global federated learning model iteration. When the calculation result exceeds the unit equipment control thresholds, proceed to step D2.3.5.

[0056] D2.3.5: Output the decision-making unit equipment control results and issue alarms. Use the unit equipment control threshold as the advanced predictive control information, convert it into encrypted parameters using the public key, and upload it to the central server for global federated learning model iteration.

[0057] When using simulated annealing for optimization in step D2.2.5, the steps include the following:

[0058] D2.2.5.1: Randomly generate an initial parameter set for interactive verification. Record the error value EEP as the current annealing system state E0, the initial temperature T0, and the annealing end temperature as T1.

[0059] D2.2.5.2: According to the perturbation algorithm m′ i =m i +s·(μ-0.5)(B i -A i The parameters are perturbed to form a new parameter set, and the current annealing system state E is obtained through interactive verification. n Calculate ΔE = E n -E n-1 ;

[0060] Where: m′ i Let m be the variable after perturbation. i Let be the current variable, s be the perturbation ratio, μ be a random number in the range [0,1], and B be a variable. i A i For the current variable m i Scope;

[0061] D2.2.5.3: When ΔE < 0, accept the new parameter set and jump to step D2.2.5.5; otherwise, accept the corresponding parameter set according to the Metropolis criterion exp(ΔE / KT)-μ > 0 and jump to step D2.2.5.4; if none of the above conditions are met, reject the critical state and return to step D2.2.5.2, re-perturb to generate a new parameter set, and perform interactive verification until the parameter set acceptance condition in step D2.2.5.3 is met;

[0062] D2.2.5.4: Set the end temperature to T1, and the global maximum calculation error value (EEP count) to N; stop annealing when T1 or N is reached, otherwise return to step D2.2.5.2; the critical state cross-validation error E accepted when stopping annealing. n The lowest value corresponds to the optimal prediction parameter.

[0063] The heat exchanger tube maintenance device based on the electromagnetic induction principle includes a double-layer intelligent heat exchanger tube structure 1, a miniature magnetoelectric sensor 3 with a dredging module, a cable tray 4, an automatic data acquisition device 5, and a control terminal 6. The double-layer intelligent heat exchanger tube structure 1 is U-shaped or serpentine. The U-shaped double-layer intelligent heat exchanger tube structure 1 is installed inside the energy pile, and the serpentine double-layer intelligent heat exchanger tube structure 1 is installed in the bridge deck. Both ends of the double-layer intelligent heat exchanger tube structure 1 are connected to the automatic data acquisition device 5 via the cable tray 4, and the automatic data acquisition device 5 is connected to the control terminal 6. The double-layer intelligent heat exchanger tube structure 1 consists of an inner polyethylene tube 1-A, an outer polyethylene tube 1-B, and a magnetic induction ring 2. The inner polyethylene tube 1-A is located inside the inner wall of the outer polyethylene tube 1-B, and the two are filled with lubricating oil and threaded together. The magnetic induction ring 2 is embedded in the wall of the outer polyethylene tube 1-B and is arranged at equal intervals along the axial direction of the double-layer intelligent heat exchanger tube structure 1. The miniature magnetoelectric sensor 3 with a dredging module is located in the inner polyethylene tube. The device moves within 1-A and includes a unclog jack, a series motor 3-5, a drive wheel 3-7, and a cable 3-8. One end of the series motor 3-5 is connected to the cable 3-8, and the other end is fixed to the unclog jack via a gear 3-3 and a connecting member 3-2. Multiple drive wheels 3-7 are connected to the side of the series motor 3-5 and slide on the inner wall of the inner polyethylene pipe 1-A. A magnetoelectric sensor 3-6, a surround camera 3-4, and a lighting lamp 3-9 are all mounted on the surface of the series motor 3-5. When an electrical signal is passed through the magnetoelectric sensor 3-6, the electromagnetic frequency changes when it passes through the magnetic induction ring 2. The electrical signal is transmitted to the automatic data acquisition device 5 through the connected cable 3-8. The automatic data acquisition device 5 automatically records the time when the magnetoelectric sensor 3-6 passes through each magnetic induction ring 2 in sequence and transmits this information to the control terminal 6. If no electrical signal is transmitted to the next magnetic induction ring 2 after passing through a certain magnetic induction ring 2 for a set time, it is determined that there is a blockage between the two magnetic induction rings 2.

[0064] The magnetic induction ring 2 has a ring width of 5-8 mm and is integrally formed with the outer polyethylene pipe 1-B; the spacing of the magnetic induction rings 2 is 0.3-0.5 m; the unblocking component is a spiral metal wire 3-1 and / or a hot melt rod.

[0065] The heat exchanger tube inspection device based on the principle of electromagnetic induction is used to detect blockages and damage in heat exchanger tubes, and includes the following steps:

[0066] S1: After the Federal Learning Operation Control for De-icing and Snow Melting on the Energy Pile Bridge Issues an Initial Fault Alarm, Turn on the Automatic Data Acquisition Instrument 5. Use a magnetic induction ring to surround and move the magnetic electric sensor 3-6. When the magnetic induction ring encounters the sensing point of the magnetic electric sensor 3-6, an audible and visual alarm will be issued, and the Automatic Data Acquisition Instrument 5 will show an indication. The Automatic Data Acquisition Instrument 5 is working normally and the subsequent steps can be carried out.

[0067] S2: During testing, pipes are arranged vertically inside the energy pile, and the magnetoelectric sensor 3-6 is inserted by its own weight and the rotation of the cable tray 4. Pipes are arranged horizontally inside the bridge deck pavement layer, and the magnetoelectric sensor 3-6 is moved inside the pipe by the drive wheel 3-7. The miniature magnetoelectric sensor 3 with the unblocking module is moved inside the pipe. When the center of the magnetoelectric sensor 3-6 intersects with the magnetic induction ring 2, the automatic data acquisition instrument 5 emits a beeping sound and is accompanied by a light indicator. The surround camera 3-4 is activated to monitor the image and sound waveform inside the pipe in real time. The automatic data acquisition instrument 5 automatically records the number of each measurement point of the magnetic induction ring 2, the time interval between two adjacent measurement points of the magnetic induction ring 2, and real-time image and sound waveform information.

[0068] S3: The automatic data acquisition instrument 5 transmits the automatically recorded data to the control terminal 6, and uses one or more of the following methods to analyze the acquired data and accurately locate the damage point: isolated forest algorithm, X-ray digital imaging technology, ultrasonic detection, ultrasonic guided wave, ultrasonic C-scan, ultrasonic phased array, and high temperature thickness measurement method; the control terminal 6 accurately locates the blockage point based on the abnormal time and location of the analyzed data.

[0069] The ultrasonic phased array method described in step S3 above involves controlling the time delay of the excitation and reception pulses of each array element in the array transducer to change the phase relationship when a certain array element in the object receives sound waves, thereby changing the focal point and the direction of the sound beam to synthesize a phased array beam and thus scan for information.

[0070] The ultrasonic guided wave testing described in step S3 above involves placing several sensor probes at multiple locations within the pipeline to form a sensor array that detects the condition of the pipeline wall. As the information sensed by the sensors passes through the impact and reflection of guided waves, the damage to the pipeline wall is detected. Subsequent analysis and calculation of the relevant data then pinpoint the problems in the pipeline wall. To generate an appropriate waveform for typical pipe wall thicknesses, a much lower frequency than conventional ultrasonic testing is required. Guided waves typically use frequencies of 60–100 kHz. Therefore, the detection sensitivity of guided waves for individual defects is relatively low compared to ultrasonic testing, which typically uses frequencies in the MHz range. However, guided wave testing has the advantage of propagating over long distances of 20–30 meters with minimal attenuation. Therefore, a large-scale inspection can be performed by fixing a pulse-echo array at a single location, making it particularly suitable for detecting internal and external corrosion of in-service pipelines and dangerous defects in welds. Low-frequency guided wave distance ultrasonic testing is used for rapid inspection of pipelines in service; internal and external corrosion can be detected in a single operation, and planar defects in the pipe cross-section can also be detected.

[0071] The ultrasonic C-scan detection described in step S3 above is a deep scan of the pipeline. Its basic working principle is that ultrasonic waves are generated inside the component being inspected through a reflective probe. The probe then transmits the received information about the defect location back as ultrasonic waves, and the software displays various indicators of the reflected waves, thereby determining the specific information about the location and size of the pipeline defect.

[0072] In step S3, when analyzing the collected data using the isolated forest algorithm, an isolated tree is built in the attribute space of the sample set to isolate attributes. Within the same attribute space, outliers are separated through model training, while normal values ​​are located in deeper child nodes of the isolated tree. The specific steps are as follows:

[0073] S3.1: The current signal, acoustic signal, and electromagnetic signal transmitted from the magnetoelectric sensor 3-6 to the control terminal 6 are used as sample attributes to form a sample set, represented as X=(x1,x2,x3,…,x…). n ), where x n =(x n1 ,x n2 ,x n3 ,…,x nm ), x nm The nth type attribute signal at time m;

[0074] S3.2: Use the attribute dimension q as the attribute cut point to segment attribute types, forming different isolated trees. For each isolated tree, use the attribute value cut point p as the outlier cut point to segment the attribute values ​​within the attribute space; Q is a random value belonging to the range (0, n), and p is a random value belonging to the range min(x... n ) < p < max(x) n Random values ​​within a given range;

[0075] S3.3: Based on the split of attribute cut point q and outlier cut point p, a hyperplane is formed in the sample space. Samples smaller than the outlier cut point p are classified into one class, forming the left node of the isolated tree, and vice versa.

[0076] S3.4: Repeat steps S3.2 to S3.3 until each isolated tree leaf node contains only one sample, thus completing the training of the isolated tree model;

[0077] S3.5: Take the sample data x at each time step i By traversing and calculating the data in an isolated tree model, the average height h(x) of each sample data can be obtained. i The outlier score of the sample data is calculated using the following formula:

[0078]

[0079] Where h(x) is the height of x in each isolated tree, c(n) is the average path length for a given number of samples n, and E(h(x)) is the expected path length of x in multiple isolated trees;

[0080] When the score S(x,ψ)>0.75, the signal corresponding to the sample at that moment is considered an abnormal signal;

[0081] When the score S(x,ψ) is between 0.4 and 0.75, the signal corresponding to the sample at that moment is considered a suspected abnormal signal;

[0082] When the score S(x,ψ) < 0.4, the sample at that moment is considered a normal signal.

[0083] The heat exchanger tube maintenance device based on the principle of electromagnetic induction is used to unclog and repair heat exchanger pipelines, and includes the following steps:

[0084] T1: Turn on the surround camera 3-4 and the lighting 3-9, and transmit the data to the control terminal 6 in real time, so that the surround camera 3-4 is aimed at the blockage;

[0085] T2: Begin unblocking work. When the blockage is found to be caused by pipe heat fusion, turn on the series motor 3-5 controlling the spiral metal wire 3-1. After the spiral metal wire 3-1 rotates to the working speed, use the gravity of the magnetoelectric sensor 3-6 to slowly lower the sensor cable 3-8 in the vertical pipe. Use the drive wheel 3-7 to control the movement of the magnetoelectric sensor 3-6 in the horizontal pipe and slowly lower the sensor cable 3-8. The spiral metal wire 3-1 stirs the blockage until the blockage is cleared. When the blockage is caused by pipe heat fusion, replace the spiral metal wire 3-1 and connecting component 3-2 of the unblocking module with a heat fusion rod and place the magnetoelectric sensor 3-6 at the blockage again. Turn on the heating rod to the heat fusion temperature of the polyethylene material and use the gravity of the magnetoelectric sensor 3-6 to slowly lower the sensor cable 3-8 until the blockage is cleared.

[0086] T3: After removing the miniature magnetoelectric sensor 3 containing the unblocking module from the pipe, perform pipe pressure testing and flushing to clean the foreign objects remaining in the pipe, and the unblocking work is completed.

[0087] T4: After accurately locating the damage point, repair the heat exchange pipeline. The section of pipe where the damage point is located is unscrewed along the thread to replace the damaged section, or an automatic repair agent is used to repair the damaged section.

[0088] The automatic repair agent is one or more of polyethylene powder, polyethylene granules, nylon fiber filaments, ethylene glycol, and adhesive. When the automatic repair agent is nylon fiber filaments, the fineness is 200-300D, and the length of the nylon fiber filaments is 3-5mm to ensure that the mixture does not clump inside the pipe, thus reducing the effectiveness of the repair agent. The nylon fiber filaments are intertwined with the polyethylene powder, rubber powder, and granules, making it difficult for the polyethylene powder to fall off and participating in filling the pores of the heat exchange pipeline. Because the pipe wall has a double-layer structure, the fiber filaments penetrate on both sides of the pores, firmly fixing the polyethylene microparticles.

[0089] The repair process and method of the automatic repair agent are as follows:

[0090] P1: After locating the damage point, seal either end of the pipe inlet / outlet according to the pressure test standard, and inject an automatic repair agent into the pipe through the other pipe opening;

[0091] P2: After injecting the repair agent, pressurize the pipe, but the pressure should not exceed the rated pressure that the polyethylene pipe used can withstand.

[0092] P3: When the pressure gauge reading is stable, the initial repair of the damaged point is completed; after the automatic repair agent has fully reached the strength requirements, the pipeline is pressure tested. Under the test pressure, the pressure should be stabilized for 15 to 20 minutes. After stabilization, the pressure drop should be 1% to 3%, and there should be no leakage to be considered as the repair work is completed.

[0093] The beneficial effects of this invention: Compared with existing control technologies, this invention has the following technical advantages:

[0094] (1) Bridge deck buried pipes and energy piles are permanent and concealed. Traditional sensors are difficult to deploy and cannot predict abnormal information. The intelligent operation and maintenance control method based on machine learning analyzes various historical data to make advance predictions of abnormal information.

[0095] (2) The present invention proposes a method for overhauling and intelligent operation and maintenance control of heat exchange tubes in an active bridge de-icing and snow melting system using energy piles. This method realizes integrated control among multiple modules, including bridge deck buried pipe end, unit equipment, and energy piles. The resulting control scheme is scientific and reasonable, improving the stability of the bridge de-icing and snow melting system and the service life of the equipment.

[0096] (3) The heat exchange tube maintenance device based on the principle of electromagnetic induction proposed in this invention combines a double-layer intelligent heat exchange tube structure with a micro magnetoelectric sensor. The operation steps are simple, highly operable, easy to control, and easy to implement. The double-layer intelligent heat exchange tube structure with embedded metal ring structure is simple and easy to prefabricate; the micro magnetoelectric sensor has the functions of monitoring and unblocking pipelines, and has multiple functions.

[0097] (4) The present invention proposes a complete set of heat exchanger tube inspection devices based on the principle of electromagnetic induction for detecting blockages and damages in heat exchanger tubes. During the inspection process, if a blockage is found, the monitoring module and the unblocking module are immediately activated to unblock the tube. If the tube is damaged, the inner heat exchanger tube can be unscrewed and replaced immediately, thereby improving the efficiency of finding and solving problems.

[0098] (5) The automatic repair agent is readily available and economical. The repair agent is easy to use and has a good repair effect, which strengthens the structure of the heat exchange tube. Attached Figure Description

[0099] Figure 1 This is a conceptual diagram of an optional energy pile active bridge deck de-icing and snow melting federated learning operation and maintenance control model according to an embodiment of the present invention;

[0100] Figure 2 This is a schematic diagram of a local model structure of a decision tree for optional energy pile buried pipe control parameters according to an embodiment of the present invention;

[0101] Figure 3 This is a schematic diagram of a local model of a decision tree for optional energy pile buried pipe control parameters according to an embodiment of the present invention.

[0102] Figure 4 This is a schematic diagram of a partial model of a support vector machine for bridge deck buried pipe end control, according to an embodiment of the present invention.

[0103] Figure 5 This is a schematic diagram of a partial model structure of a support vector machine for bridge deck buried pipe end control, according to an embodiment of the present invention.

[0104] Figure 6 This is a schematic diagram of an optional simulated annealing improved support vector machine algorithm according to an embodiment of the present invention;

[0105] Figure 7 This is a schematic diagram of a random forest local model structure for optional unit equipment control parameters according to an embodiment of the present invention;

[0106] Figure 8 This is a schematic diagram of a random forest local model structure for optional unit equipment control parameters according to an embodiment of the present invention;

[0107] Figure 9 This is a schematic diagram of an optional heat exchanger tube maintenance device based on the principle of electromagnetic induction according to an embodiment of the present invention.

[0108] Figure 10 This is a schematic diagram of an optional double-layer intelligent heat exchange tube structure according to an embodiment of the present invention;

[0109] Figure 11This is a schematic diagram of the cross-sectional structure of an optional double-layer intelligent heat exchange tube structure according to an embodiment of the present invention;

[0110] Figure 12 This is a schematic diagram of an optional micro magnetoelectric sensor structure containing a dredging module according to an embodiment of the present invention;

[0111] Figure 13 This is a schematic cross-sectional view of an optional micro magnetoelectric sensor structure containing a dredging module according to an embodiment of the present invention.

[0112] Figure 14 This is a schematic diagram of an optional isolated forest algorithm for anomaly signal detection in an embodiment of the present invention.

[0113] In the diagram: 1-A-Inner polyethylene pipe, 1-B-Outer polyethylene pipe, 2-Magnetic induction ring, 3-Miniature magnetoelectric sensor with unblocking module, 3-1-Helical stainless steel wire, 3-2-Connecting component, 3-3-Gear, 3-4-Surround camera, 3-5-Series motor, 3-6-Magnetic sensor, 3-7-Drive wheel, 3-8-Cable, 3-9-Lighting lamp, 4-Cable reel, 5-Automatic data acquisition device, 6-Control terminal. Detailed Implementation

[0114] The specific embodiments of this invention are described in detail below with reference to the accompanying drawings. However, the scope of protection of this invention is not limited to the description of these embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0115] This invention provides a control method for an energy pile-based active bridge deck de-icing and snow melting federated learning operation and maintenance control model consisting of an optional central server and local clients. Figure 1 This is a schematic diagram of a selectable federated learning operation and maintenance control model for active bridge de-icing and snow melting using energy piles. It mainly consists of four parts: field equipment, data acquisition, a server, and control signals. All sub-modules perform learning calculations on local clients, including three main client modules: the bridge deck buried pipe control module, the generator unit equipment control module, and the energy pile buried pipe control module. Finally, the anonymized parameters calculated by the clients are aggregated to the central server for calculation and then distributed to each data holder (client) to update their local model until the global model is robust. The specific steps are as follows:

[0116] Step D1: Collect and organize the operating parameters and control parameters of the bridge deck buried pipe end, the unit equipment operating parameters and control parameters, and the energy pile buried pipe end operating parameters and control parameters of a bridge deck de-icing system in Jiangyin City through on-site survey technology, questionnaire survey technology, image intelligent recognition technology, and thermal infrared imaging technology. Perform simple quality analysis and cleaning of sample data, extract the distribution pattern of the cleaned sample data, analyze the characteristics of the sample data, and allocate them to the corresponding computing module client.

[0117] The operating parameters of the bridge deck buried pipe end include: ambient temperature, ambient humidity, wind speed, snowfall, surface snow-free rate, water level of the manifold, pressure difference and temperature difference, manifold flow rate, manifold pressure, manifold temperature, bridge deck buried pipe supply water temperature, bridge deck buried pipe return water temperature, bridge deck buried pipe supply flow rate, bridge deck buried pipe return water flow rate, bridge deck buried pipe supply pressure, and bridge deck buried pipe return water pressure; the operating parameters of the unit equipment include: condenser working liquid level, condenser inlet temperature, evaporator working liquid level, evaporator inlet temperature, and compressor pressure; the operating parameters of the energy pile buried pipe end include: soil temperature, water level of the energy pile buried pipe end manifold, pressure difference, manifold flow rate, pressure, temperature, energy pile supply water temperature, return water temperature, flow rate, and water pressure.

[0118] The control parameters for the bridge deck buried pipe end include: the opening degree of the bridge deck buried pipe return water control valve, the opening degree of the bridge deck buried pipe supply water control valve, the opening degree of the water collector manifold control valve, the opening degree of the water collector branch pipe control valve, the opening degree of the water distributor manifold control valve, the opening degree of the water distributor branch pipe control valve, and the opening degree of the water supply pump control valve; the control parameters for the unit equipment include: the opening degree of the water supply pump control valve, the opening degree of the cooling circulation pump control valve, the opening degree of the chilled water circulation pump control valve, the opening degree of the expansion valve, and the main unit; the control parameters for the energy pile buried pipe end include: the opening degree of the energy pile water collector manifold control valve, the opening degree of the water collector branch pipe control valve, the opening degree of the energy pile water distributor manifold control valve, the opening degree of the water distributor branch pipe control valve, the opening degree of the energy pile return water control valve, and the opening degree of the water supply control valve.

[0119] Table 1. Training sample space and sample quality of the operation control model for a bridge de-icing system using energy piles in Jiangyin City.

[0120]

[0121] Step D2: The local models of the three client-side modules—bridge deck buried pipe end control module, generator set equipment control module, and energy pile buried pipe end control module—are as follows:

[0122] Local Client 1 (Energy Pile Pipe Control Module): Figure 2This is a partial CART decision tree model structure diagram for an optional energy pile operation and maintenance control parameter. Based on various operating parameters of the energy pile buried pipe end, the unit equipment operating parameters updated by the central server, and the bridge deck buried pipe end operating parameters as sample attribute data, a partial CART decision tree model for the energy pile buried pipe control parameters is established to determine the heat extraction of the energy pile and the control parameters of the energy pile buried pipe end, and then encrypted and uploaded to the central processor. Figure 3 The following is a C4.5 decision tree flowchart for the operation and maintenance control parameters of an energy pile, as an example. The specific steps of the client in the s-th round are as follows:

[0123] Step D2.1.1: Decrypt the public key used to encrypt the transmitted data using the private key. Update the bridge deck buried pipe control module, generator equipment control module, and energy pile buried pipe control module of the three local clients according to the global shared model of the central server, and use the iteration result as the attribute parameter of the new sample data. Calculate the possible values ​​s of attribute A. i The Gini coefficient.

[0124] Step D2.1.2: Among all possible attributes A and their corresponding attribute values, select the attribute with the smallest Gini coefficient and its corresponding attribute value as the optimal attribute and optimal split point. Generate two child nodes with the optimal attribute and optimal split point, and assign the corresponding samples to the nodes.

[0125] Step D2.1.3: Treat each root node as a complete dataset and iteratively call D2.1.1 to D2.1.2. Divide the samples according to the suboptimal attribute. The samples with the same suboptimal attribute value are treated as the same sample set to form leaf nodes. Iterate until the REP decision tree pruning condition or the stopping condition (the number of samples in the node and the Gini coefficient are less than the threshold) are met to form a decision tree.

[0126] Step D2.1.4: Compare the determined control parameters of the buried pipe end of the energy pile with the equipment control threshold. If the calculation result meets the equipment control threshold, the decision calculation result is used as advanced predictive control information, converted into encrypted parameters using a public key, and uploaded to the central server for iteration of the globally shared model in federated learning. If the calculation result exceeds the equipment control threshold, proceed to step D2.1.5.

[0127] Step D2.1.5: Output the determined control parameters of the buried pipe end of the energy pile and issue an alarm. Use the control threshold as the advanced prediction control information and use the public key to convert it into encrypted parameters and upload it to the central server for the global shared model iteration of federated learning.

[0128] Local Client 2 (Bridge Deck Buried Pipe Control Module): Figure 4The present invention provides an optional support vector machine prediction model structure diagram for the bridge deck buried pipe end control module. The operating parameters of the bridge deck buried pipe end, the unit equipment operating parameters updated by the central server, and the operating parameters of the energy pile buried pipe end are used as sample attribute data of the bridge deck buried pipe end control local model. The support vector machine local model of the bridge deck buried pipe end control module is established, the control scheme is predicted and calculated, and the data is encrypted and uploaded to the central processing unit. Figure 5 The flowchart of the support vector machine prediction model for the bridge deck buried pipe end control module is shown below. The specific steps of the model in the s-th round are as follows:

[0129] Step D2.2.1: Decrypt the public key of the encrypted data using the private key. Update the relevant clients of the energy pile buried pipe control module, unit equipment control module, and bridge deck buried pipe control module according to the global shared model of the central server, and use the iteration result as the attribute parameters of the new sample data. Based on the sample data, ambient temperature, ambient humidity, wind speed, snowfall, surface snow-free rate, manifold water level, pressure difference, temperature difference, bridge deck buried pipe supply and return water temperature, flow rate, and pressure are used as sample attribute X. i This forms sample data X = {X1, X2, ..., X...} containing multiple features. n The relevant control parameters are used as the learning target y = {y1, y2, ... y}. n}

[0130] Step D2.2.2: Introduce slack variable ξ i A nonlinear segmentation support vector classifier considering soft margins is constructed using the penalty coefficient C to represent the relationship between the operating state parameters of the bridge deck buried pipe end and the control valve parameters of the bridge deck buried pipe end. The prediction accuracy and stability of the model can be represented by the loss function (L=max(0,|z|-∈)).

[0131] Step D2.2.3: Use the Lagrange function to convert the above conditions into a multivariate function for solution. Set the partial derivatives of the Lagrange function with respect to the optimization objectives w, b, ξ to 0 to obtain the Lagrange multipliers, thereby transforming the original condition extremum function into a dual function and finding the minimum value within the constraint region.

[0132] Step D2.2.4: The inner product φ(X) of the mapping function in the dual function i ) T φ(X j The Sigmoid kernel can be used: φ(X) i ) T φ(X j )=κ(X i ,X j )=tanh(αX i T X j The +c)” instruction is used for processing.

[0133] Step D2.2.5: Optimize the support vector machine model parameters based on the training set data: slack variable ξ i The parameters include the penalty coefficient C, and the hyperparameters γ, λ, α, c, and d in the kernel function. Preferably, simulated annealing is used for model parameter optimization. Figure 6 The flowchart of a local model of a support vector machine algorithm improved by an alternative simulated annealing method is as follows:

[0134] Step D2.2.5.1: Randomly generate an initial parameter set for interactive verification. Record the error value EEP as the current annealing system state E0, the initial temperature T0, and the annealing end temperature as T1.

[0135] Step D2.2.5.2: According to the perturbation algorithm m′ i =m i +s*(μ-0.5)(B i -A i The parameters are perturbed to form a new parameter set, and the current annealing system state E is obtained through interactive verification. n Calculate ΔE = E n -E n-1 .

[0136] Step D2.2.5.3: If ΔE < 0, accept the new parameter set and jump to step D2.2.5.5; otherwise, accept the corresponding parameter set according to the Metropolis criterion exp(ΔE / KT)-μ > 0 and jump to step D2.2.5.4; if none of the above conditions are met, reject the critical state and return to step D2.2.5.2, re-perturb to generate a new parameter set, perform interactive verification, until the parameter set acceptance condition in step D2.2.5.3 is met.

[0137] Step D2.2.5.4: Set the end temperature to T1 as the algorithm exit point, and the global maximum computational error value (EEP) count to N. Annealing stops when T1 or N is reached, at which point the critical state cross-validation error E is accepted. n It should be the lowest E n The corresponding parameters should be the optimal prediction parameters.

[0138] Step D2.2.6 Input the target operating parameters of the bridge deck buried pipe, and use the trained support vector machine model to predict the adjustment parameters of the chilled water circulation loop at the bridge deck buried pipe end and the opening degree of the relevant control valves.

[0139] Step D2.2.7: Compare the calculation result with the control threshold of the chilled water circulation loop control valve. If the calculation result meets the control threshold, the predicted calculation result is used as advance predictive control information, converted into encrypted parameters using a public key, and uploaded to the central server for iteration of the globally shared model in federated learning. If the calculation result exceeds the control threshold of the chilled water circulation loop control valve, proceed to step D2.2.8.

[0140] Step D2.2.8: Output the calculated control results of the chilled water circulation loop and issue an alarm. Use the control threshold as the advanced predictive control information, convert it into encrypted parameters using the public key, and upload it to the central server for the global shared model iteration of federated learning.

[0141] Local Client 3 (Unit Equipment Control Module): Figure 7 This is a flowchart of a random forest local model for optional unit equipment control parameters provided in an embodiment of the present invention. Based on various operating parameters of the unit equipment, energy pile operating parameters updated by the central server, and bridge deck buried pipe end operating parameters as sample attribute data, a random forest local model for the unit equipment control parameters is established to determine the unit equipment control parameters and encrypt and upload them to the central processing unit. Figure 8 A flowchart of a local random forest model provided in an embodiment of the present invention is shown below, with specific steps as follows:

[0142] Step D2.3.1: Decrypt the public key of the encrypted data using the private key. Use the updated energy pile operating parameters and bridge deck buried pipe end operating parameters from the central server's globally shared model as the new sample data attribute parameters. Based on the local sample data, use the status parameters of each unit's equipment as the sample attribute space set, and the unit's equipment control parameters as the learning target. Use the Bootstrap sampling method to randomly generate a subset of samples from the sample data, which will be used as training samples for one of the decision tree models. Repeat this sampling k times to form k decision tree training samples.

[0143] Step D2.3.2: Train decision trees based on the attribute subsets from the k training samples to form k independent random decision trees.

[0144] Step D2.3.3: Vote on the control schemes of the unit equipment predicted by the k decision trees, and take the voting result as the optimal control scheme of the unit equipment.

[0145] Step D2.3.4: Compare the determined control parameters of the unit equipment (evaporator, condenser, cooling pump, chilled water pump, expansion valve) with the unit equipment control thresholds. If the calculation result meets the unit equipment control thresholds, the decision calculation result is used as advanced predictive control information, converted into encrypted parameters using a public key, and uploaded to the central server for iteration of the globally shared model in federated learning. If the calculation result exceeds the unit equipment control thresholds, proceed to step D2.3.5.

[0146] Step D2.3.5: Output the determined unit equipment control results and issue an alarm. Use the unit equipment control threshold as the advanced predictive control information, convert it into encrypted parameters using the public key, and upload it to the central server for the global shared model iteration of federated learning.

[0147] Step D3: Encrypt the local model results of the three local clients—the bridge deck buried pipe end control module, the unit equipment control module, and the energy pile control module—in the form of public keys into desensitized parameters, and upload them to the central server.

[0148] Step D4: The server uses its private key to decrypt the encrypted and anonymized parameters uploaded by the three clients, aggregates the decrypted parameters of all client models based on knowledge distillation using federated learning, and updates the global model weights of the M clients according to the following formula: Among them W s+1 For the global model parameters in round s, For client i in round s, upload the client sub-model weights to the server. After each round of model weight updates, the central server calculates the error and accuracy of the globally shared model.

[0149] Step D5: The central server generates a public key for encrypting transmitted data using the globally shared model and distributes it to each client. Based on the globally shared model, each local client updates the relevant client iteration results required for training its local model, using these results as the attribute parameters for the new sample data.

[0150] Step D6: Repeat steps D2 to D5 iteratively until the global shared model is robust. Finally, the client calculates the corresponding result based on the global shared model. The matching control states of a certain energy pile active bridge deck de-icing and snow melting system in Jiangyin City were calculated, including the opening degrees of various regulating valves in the chilled water circulation loop at the bridge deck buried pipe end, the snow melting time at the bridge deck buried pipe end, the opening degrees of various regulating valves at the unit equipment end, and the opening degrees of various regulating valves in the cooling water circulation loop at the energy pile buried pipe end, as shown in Table 2.

[0151] Table 2. Control parameter results of a bridge de-icing system using energy-powered piles in Jiangyin City.

[0152]

[0153] This invention proposes a heat exchanger tube maintenance device based on the principle of electromagnetic induction. Specific implementation details are as follows.

[0154] like Figure 10 The diagram shows the schematic of a heat exchanger tube maintenance device based on the principle of electromagnetic induction. The device mainly includes a double-layer intelligent heat exchanger tube structure 1, a miniature magnetoelectric sensor 3 with a clearing module, a cable tray 4, an automatic data acquisition unit 5, and a control terminal 6. The detection principle is as follows: When an electrical signal is applied to the magnetoelectric sensor 3-6, the electromagnetic frequency changes as the sensor passes through the magnetic ring. The electrical signal is transmitted to the automatic data acquisition unit 5 via the connected cable. The automatic data acquisition unit 5 automatically records the time when the sensor passes through each magnetic ring and transmits this information to the control terminal 6. If no electrical signal is transmitted to the next measuring point for an extended period after passing a certain measuring point, it is determined that there may be a blockage between the two measuring points.

[0155] like Figure 11 and Figure 12 As shown, the double-layer intelligent heat exchange tube structure 1 includes an inner polyethylene tube 1-A, an outer polyethylene tube 1-B, and a magnetic induction ring 2. The magnetic induction ring 2 is heat-fused and embedded in the wall of the outer polyethylene tube 1-B, with a ring width of 5-8 mm. It is integrally formed with the outer polyethylene tube 1-B and is arranged at equal intervals along the axial direction of the heat exchange tube. The spacing is determined according to the design requirements of the energy pile and the bridge deck pavement layer, and is between 0.3 and 0.5 m. In this embodiment, it is 0.5 m. The inner wall of the outer polyethylene tube 1-B and the outer wall of the inner polyethylene tube 1-A are threaded. Lubricating oil is applied between the two polyethylene tubes, and the two polyethylene tubes are tightened using the threads. Figure 12 for Figure 11 A schematic diagram of the cross-section of a double-layer intelligent heat exchanger tube structure.

[0156] The structural diagram of the miniature magnetoelectric sensor 3 containing the unblocking module is shown below. Figure 13 As shown, Figure 14 for Figure 13 The cross-sectional view of AA includes a dredging module, a monitoring module, a magnetoelectric sensor 3-6, and a moving module. The dredging module includes a spiral metal wire 3-1 and / or a thermoplastic rod, a connecting component 3-2, a gear 3-3, and a series-wound motor 3-5; the monitoring module includes a surround camera 3-4 and a lighting lamp 3-9; and the moving module includes a drive wheel 3-7 and a corresponding motor.

[0157] This invention proposes a method for detecting blockages and damage in heat exchanger pipelines using a heat exchanger tube inspection device based on the principle of electromagnetic induction. The detection method steps are as follows:

[0158] Step S1: After the Federal Learning Operation Control for De-icing and Snow Melting on the Energy Pile Bridge Issues a Preliminary Fault Alarm, first turn on the power switch 5 of the data acquisition instrument, and move a magnetic induction ring 2 around the magnetoelectric sensor 3-6. When the magnetic induction ring 2 encounters the sensing point of the magnetoelectric sensor 3-6, an audible and visual alarm will be issued, and the instrument will show an indication, indicating that the data acquisition instrument is working normally.

[0159] Step S2: During testing, the miniature magnetoelectric sensor 3 containing the unblocking module is inserted into the pipeline along the magnetoelectric sensor 3-6. For vertically arranged pipelines within the energy pile, the magnetoelectric sensor 3-6 is slowly inserted using its own gravity and the rotation of the cable reel 4. For horizontally laid pipelines within the bridge deck pavement, the moving module of the miniature magnetoelectric sensor activates the motor corresponding to the drive wheel 3-7, causing the miniature magnetoelectric sensor 3-6 to move within the pipeline. When the center of the magnetoelectric sensor 3-6 intersects with the magnetic induction ring 2, the instrument emits a buzzer sound accompanied by a light indicator. Simultaneously, the surround camera 3-4 and the lighting 3-9 are activated, transmitting data in real-time to the control terminal 6, ensuring the camera is aimed at the blockage. The automatic data acquisition instrument 5 automatically records the number of each magnetic induction ring measuring point, the time interval between adjacent measuring points, real-time image data, and sound waveform information.

[0160] Step S3: The automatic data acquisition device 5 transmits the automatically recorded data to the control terminal 6. The control terminal 6 can use the isolated forest algorithm to analyze the collected data and accurately locate the damage point. Based on the analyzed abnormal time and location of the data, the location of the blockage point can be accurately located.

[0161] The Isolation Forest algorithm is used to analyze real-time data. An isolation tree is built in the attribute space of the sample set to isolate attributes. Within the same attribute space, outliers are relatively distant from the attribute values ​​of most samples. Through model training, outliers are separated earlier, while normal values ​​are located in deeper child nodes of the isolation tree. The algorithm structure is as follows: Figure 14 As shown. The specific steps are as follows:

[0162] Step S3.1: Organize the current signal, sound wave signal, and electromagnetic signal transmitted from the unblocking module to the control center as sample attributes to form a sample set, which can be represented as X=(x1,x2,x3,…,x…) n ), where x n =(x n1 ,x n2 ,x n3 ,…,x nm ), x nmLet be the nth type of attribute signal at time m. Step S3.2: Use the attribute dimension q as the attribute cut point to segment the attribute types, forming different isolated trees. For each isolated tree, use the attribute value cut point p as the outlier cut point to segment the attribute values ​​and divide the sample space. Q is a random value belonging to the range (0, n), and p is a random value belonging to the range min(x). n ) < p < max(x) n () random values ​​within the range.

[0163] Step S3.3: Based on the splitting of attribute cut points and outlier cut points, a hyperplane is formed in the sample space. Samples smaller than the cut point are classified into one class, forming the left node of the isolated tree, and vice versa.

[0164] Step S3.4: Repeat steps S3.2 to S3.3 until each isolated tree leaf node contains only one sample, thus completing the training of the isolated tree model.

[0165] Step S3.5: Take the sample data x at each time step i By traversing and calculating the data in an isolated tree model, the average height h(x) of each sample data can be obtained. i ), and the anomaly score S(x,ψ) of the sample data. Determine the anomaly signal based on the table below.

[0166] Table 3 Outlier Judgment Indicators

[0167] S(x,ψ) value Signal evaluation ＞0.75 Abnormal signals 0.4～0.75 Suspected abnormal signal ＜0.4 Normal signal

[0168] This invention proposes a heat exchanger tube maintenance device based on the principle of electromagnetic induction for unblocking and repairing heat exchanger pipelines. The specific steps are as follows:

[0169] Step T1: Turn on the surround camera 3-4 and the lighting 3-9, and transmit the data to the control terminal 6 in real time, so that the camera is aimed at the blockage.

[0170] Step T2: Begin the unblocking operation. If the blockage is found to be caused by pipe heat fusion, turn on the series motor 3-5 controlling the spiral stainless steel wire 3-1. After the spiral wire 3-1 rotates to the working speed, if it is in a vertical pipe, continue to use the gravity of the magnetoelectric sensor 3-6 to slowly lower the sensor cable. If it is in a horizontal pipe, use the moving module to control the movement of the magnetoelectric sensor 3-6 to slowly lower the cable. The spiral wire 3-1 stirs the blockage until the blockage is cleared. If the blockage is caused by pipe heat fusion, the spiral wire 3-1 and connecting component 3-2 of the unblocking module can be replaced with a heat fusion rod, and the magnetoelectric sensor 3-6 can be placed at the blockage again. Turn on the heating rod to the heat fusion temperature of the polyethylene material, and use the gravity of the sensor to slowly lower the sensor cable until the blockage is cleared.

[0171] Step T3: After removing the miniature magnetoelectric sensor from the pipe, perform pipe pressure testing and flushing to clean any remaining foreign objects inside the pipe, thus completing the unblocking process.

[0172] Step T4: After accurately locating the damaged point of the intelligent heat exchange tube, since there are pre-made threads and lubricating oil to reduce friction between the double-layer intelligent heat exchange tube structure, the tube section where the damaged point is located can be unscrewed along the threads to replace the damaged tube section.

Claims

1. A method for overhauling and intelligently operating the heat exchanger tubes of an active bridge deck de-icing and snow melting system using energy piles, characterized in that... The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes in the active bridge de-icing and snow melting system using energy piles includes a federated learning operation and maintenance control model for active bridge de-icing and snow melting system using energy piles, consisting of a central server and local clients, and a heat exchanger tube overhaul device based on the principle of electromagnetic induction. The system makes a preliminary judgment and makes a preliminary alarm location based on the federated learning operation and maintenance control model for active bridge de-icing and snow melting system using energy piles, consisting of a central server and local clients. Based on this, the heat exchanger tube overhaul device based on the principle of electromagnetic induction is arranged to carry out refined repair work. The energy pile active bridge deck de-icing and snow melting federated learning operation and maintenance control model, consisting of a central server and local clients, includes three local client modules: a bridge deck buried pipe end control module, a generator equipment control module, and an energy pile buried pipe end control module. The local models of the three local client modules are trained on the local clients, and then the calculation results are encrypted and uploaded to the central processor for processing by the global federated learning model. The results obtained from the global federated learning model are then distributed to the local models of each local client. Through repeated iterations between the client and the central server, until the global federated learning model reaches stability, a matching control scheme for different modules is finally made. The specific steps are as follows: D1: Obtain the operating parameters of the bridge deck buried pipe end, the control parameters of the bridge deck buried pipe end, the operating parameters of the unit equipment, the control parameters of the unit equipment, the operating parameters of the energy pile buried pipe end, and the control parameters of the energy pile buried pipe end; perform sample data quality analysis and cleaning; extract the data distribution pattern from the cleaned sample data; analyze the characteristics of the sample data; and allocate them to the corresponding calculation module client. D2: Update the local models of 3 local clients: the local model of support vector machine for bridge deck buried pipe control, the local model of random forest for generator equipment control, and the local model of decision tree for energy pile buried pipe control; D3: Encrypt the local model results of the three local clients into desensitized parameters using a public key and upload them to the central server; D4: The central server uses its private key to decrypt the encrypted and anonymized parameters uploaded by the three local clients. The central server performs the decoding operation of the encrypted and anonymized parameters and performs secure aggregation, and then updates the global federated learning model. The federated learning on the central server updates the global federated learning model using one or more synchronous methods, such as gradient averaging, federated averaging, and knowledge distillation. After each round of global federated learning model weight update, the central server calculates the error and accuracy of the global federated learning model. D5: The central server generates a public key for encrypting transmitted data using the global federated learning model and distributes it to each client; based on the global federated learning model, each local client updates the iteration results of other clients as the new sample data attribute parameters. D6: Repeat steps D2 to D5 iteratively until the global federated learning model is stable. Finally, the client calculates the corresponding results based on the global federated learning model. Calculate the mutually matched control states in the active bridge deck de-icing and snow melting system of the energy piles, including the opening degree of various regulating valves in the chilled water circulation loop at the bridge deck buried pipe end, the snow melting time at the bridge deck buried pipe end, the unit control parameters, and the control parameters at the energy pile buried pipe end.

2. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 1, characterized in that, The energy pile buried pipe control module establishes a local decision tree model of the energy pile buried pipe control parameters based on the operating parameters of the energy pile buried pipe end, the unit equipment operating parameters updated by the central server, and the bridge deck buried pipe end operating parameters as sample attribute data; it determines the heat extraction of the energy pile and the control parameters of the energy pile buried pipe end and uploads them to the central processor in encrypted form; the decision tree model is generated through one or more of the following algorithms: ID3, C4.5, and CART; the specific steps are as follows: D2.1.1: Decrypt the public key used for encrypted data transmission using the private key; update the bridge deck buried pipe control module, generator equipment control module, and energy pile buried pipe control module of the three local clients according to the global federated learning model of the central server; and use the iteration result as the attribute parameters of the new sample data; calculate the relationship between any attribute A and all its corresponding attribute values ​​A. i The Gini coefficient; D2.1.2: Among all attributes A and their corresponding attribute values, select the attribute with the smallest Gini coefficient and its corresponding attribute value as the optimal attribute and the optimal split point; generate two child nodes with the optimal attribute and the optimal split point, and assign the corresponding samples to the root node; D2.1.3: Treat each root node as a complete dataset, iteratively call steps D2.1.1 to D2.1.2, divide the samples according to the suboptimal attribute, and form leaf nodes by taking samples with the same suboptimal attribute value as the same sample set. Iterate in sequence using the REP method, PEP method or MEP method until the decision tree pruning condition is met, the number of samples in the leaf node or the Gini coefficient is less than the threshold, and the decision tree is formed. D2.1.4: Compare the determined control parameters of the buried pipe end of the energy pile with the equipment control threshold. When the calculation result meets the equipment control threshold, the decision calculation result is used as advanced predictive control information, which is converted into encrypted parameters using a public key and uploaded to the central server for global federated learning model iteration. When the calculation result exceeds the equipment control threshold, proceed to step D2.1.

5. D2.1.5: Output the determined control parameters of the buried pipe end of the energy pile and issue an alarm. Use the control threshold as the advanced prediction control information and convert it into encrypted parameters using the public key to upload it to the central server for global federated learning model iteration; arrange the heat exchange tube maintenance device based on the principle of electromagnetic induction for fine detection and positioning. The bridge deck buried pipe end control module uses the operating parameters of the bridge deck buried pipe end, the unit equipment operating parameters updated by the central server, and the energy pile buried pipe end operating parameters as sample attribute data for the bridge deck buried pipe end control local model; it establishes a bridge deck buried pipe end control support vector machine local model, predicts and calculates the control scheme, and uploads it to the central server in encryption; the specific steps are as follows: D2.2.1: Decrypt the public key of the encrypted data using the private key, update the client of the energy pile buried pipe end control module, the unit equipment control module, and the bridge deck buried pipe end control module according to the global federated learning model of the central server, and use the iteration results as the attribute parameters of the new sample data; use the ambient temperature, ambient humidity, wind speed, snowfall, surface snow-free rate, manifold water level, pressure difference, temperature difference, bridge deck buried pipe supply and return water temperature, flow rate, and pressure as the sample attribute space set, and use the bridge deck buried pipe end control parameters as the learning target; D2.2.2: Introducing slack variable ξ i A nonlinear segmentation support vector classifier considering soft margins is constructed with the penalty coefficient C to represent the relationship between the operating parameters and control parameters of the bridge deck buried pipe end; the prediction accuracy and self-stability of the local model of the bridge deck buried pipe end control support vector machine are represented by the loss function L=max(0,|z|-∈); the loss function is converted into a conditional extremum function; Where w is the normal vector of the hyperplane, C is the penalty coefficient, and ξ, ξ * y is the relaxation factor, ∈ is the hyperparameter that determines the boundary width; i The actual test results for the training samples; f(X) i )=w·Φ(X)+b is the classification hyperplane of the local model of the support vector machine for the control of the buried pipe end on the bridge deck; i is the training sample number; N is the number of training set samples; Φ(X) is the nonlinear mapping function; D2.2.3: The above conditional extremum function is transformed into a multivariate function by using the Lagrange function. The partial derivatives of the Lagrange function with respect to the optimization objectives w, b, ξ are set to 0 to obtain the Lagrange multipliers. The conditional extremum function is then transformed into a dual function, thereby finding the minimum value of the prediction boundary. D2.2.4: The inner product φ(X) of the nonlinear mapping function Φ(X) contained in the classification hyperplane in the local model of the support vector machine for bridge deck buried pipe control. i ) T φ(X j Choose one or more kernel functions from Gaussian kernel, linear kernel, polynomial kernel, and Sigmoid kernel for processing; D2.2.5: Optimize the model parameters in the local model of the support vector machine for bridge deck buried pipe control: insensitive loss function ∈, penalty coefficient C, hyperparameters γ, λ, α, c, d in the kernel function; select one or more optimization methods from simulated annealing, grid search, particle swarm optimization, PSO algorithm, and genetic algorithm; D2.2.6: Input the target operating parameters of the bridge deck buried pipe, and use the trained bridge deck buried pipe end control support vector machine local model to predict and calculate the bridge deck buried pipe end; D2.2.7: Compare the calculation results with the control threshold of the chilled water circulation loop control valve. When the calculation results meet the control threshold of the chilled water circulation loop control valve, the predicted calculation results are used as advance prediction control information, which are converted into encrypted parameters using the public key and uploaded to the central server for global federated learning model iteration. When the calculation results exceed the control threshold of the chilled water circulation loop control valve, step D2.2.8 is executed. D2.2.8: Output the calculated control results of the buried pipe end on the bridge deck and issue an alarm. Use the equipment control threshold as the advanced predictive control information, convert it into encrypted parameters using the public key, and upload it to the central server for global federated learning model iteration. At the same time, arrange a heat exchange tube maintenance device based on the principle of electromagnetic induction for fine detection and positioning. The unit equipment control module uses various operating parameters of the unit equipment, energy pile operating parameters updated by the central server, and bridge deck buried pipe end operating parameters as sample attribute data to establish a random forest local model of the unit equipment control parameters, determine the unit equipment control parameters, and encrypt and upload them to the central processor; the specific steps are as follows: D2.3.1: Decrypt the public key of the encrypted data using the private key, and use the updated energy pile operation parameters and bridge deck buried pipe end operation parameters from the global federated learning model of the central server as new sample data attribute parameters; based on the local sample data, use the state parameters of each unit equipment as the sample attribute space set, and use the unit equipment control parameters as the learning target; use the Bootstrap sampling method to randomly generate a subset of samples from the unit equipment control training samples, and use it as the training sample of one of the decision tree models, repeating the sampling k times to form k decision tree training samples; D2.3.2: Train decision trees based on a subset of attributes from k training samples to form k independent random decision trees; D2.3.3: The random forest randomly selects a classifier to vote on the control schemes of the unit equipment predicted by k decision trees, and the voting result is taken as the optimal control scheme of the unit equipment. D2.3.4: Compare the determined unit equipment control parameters with the unit equipment control thresholds. When the calculation result meets the unit equipment control thresholds, the decision calculation result is used as advanced predictive control information, which is converted into encrypted parameters using a public key and uploaded to the central server for global federated learning model iteration. When the calculation result exceeds the unit equipment control thresholds, proceed to step D2.3.

5. D2.3.5: Output the decision-making unit equipment control results and issue alarms. Use the unit equipment control threshold as the advanced predictive control information, convert it into encrypted parameters using the public key, and upload it to the central server for global federated learning model iteration.

3. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 2, characterized in that, When using simulated annealing for optimization in step D2.2.5, the steps include the following: D2.2.5.1: Randomly generate an initial parameter set for interactive verification. Record the error value EEP as the current annealing system state E0, the initial temperature T0, and the annealing end temperature as T1. D2.2.5.2: According to the perturbation algorithm m′ i =m i +s·(μ-0.5)(B i -A i The parameters are perturbed to form a new parameter set, and the current annealing system state E is obtained through interactive verification. n Calculate ΔE = E n -E n-1 ; Where: m′ i Let m be the variable after perturbation. i Let be the current variable, s be the perturbation ratio, μ be a random number in the range [0,1], and B be a variable. i A i For the current variable m i Scope; D2.2.5.3: When ΔE < 0, accept the new parameter set and jump to step D2.2.5.5; otherwise, accept the corresponding parameter set according to the Metropolis criterion exp(ΔE / KT)-μ > 0 and jump to step D2.2.5.4; if none of the above conditions are met, reject the critical state and return to step D2.2.5.2, re-perturb to generate a new parameter set, and perform interactive verification until the parameter set acceptance condition in step D2.2.5.3 is met; D2.2.5.4: Set the end temperature to T1, and the global maximum calculation error value (EEP count) to N; stop annealing when T1 or N is reached, otherwise return to step D2.2.5.2; the critical state cross-validation error E accepted when stopping annealing. n The lowest value corresponds to the optimal prediction parameter.

4. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 1, characterized in that, The heat exchanger tube maintenance device based on the electromagnetic induction principle includes a double-layer intelligent heat exchanger tube structure (1), a miniature magnetoelectric sensor (3) with a dredging module, a cable tray (4), an automatic data acquisition device (5), and a control terminal (6). The double-layer intelligent heat exchanger tube structure (1) is U-shaped or serpentine. The U-shaped double-layer intelligent heat exchanger tube structure (1) is installed inside the energy pile, and the serpentine double-layer intelligent heat exchanger tube structure (1) is installed in the bridge deck. Both ends of the double-layer intelligent heat exchanger tube structure (1) are connected to the automatic data acquisition device (5) via the cable tray (4). The data acquisition instrument (5) is connected to the control terminal (6); the double-layer intelligent heat exchange tube structure (1) consists of an inner polyethylene tube (1-A), an outer polyethylene tube (1-B), and a magnetic induction ring (2); the inner polyethylene tube (1-A) is located inside the inner wall of the outer polyethylene tube (1-B), and the two are filled with lubricating oil and connected by threads; the magnetic induction ring (2) is embedded in the wall of the outer polyethylene tube (1-B) and is arranged at equal intervals along the axial direction of the double-layer intelligent heat exchange tube structure (1); the micro magnetoelectric sensor (3) containing the unblocking module is located in the inner polyethylene tube (1-A) of the outer polyethylene tube (1-B). A) The internal movement includes a dredging component, a series motor (3-5), a drive wheel (3-7), and a cable (3-8); one end of the series motor (3-5) is connected to the cable (3-8), and the other end is fixed to the dredging component via a mounting gear (3-3) and a connecting member (3-2); multiple drive wheels (3-7) are connected to the side of the series motor (3-5) and slide on the inner wall of the inner polyethylene pipe (1-A); a magnetoelectric sensor (3-6), a surround camera (3-4), and a lighting lamp (3-9) are all installed on the surface of the series motor (3-5). When an electrical signal is passed through the magnetoelectric sensor (3-6), the electromagnetic frequency changes as it passes through the magnetic induction ring (2). The electrical signal is transmitted to the automatic data acquisition instrument (5) through the connected cable (3-8). The automatic data acquisition instrument (5) automatically records the time when the magnetoelectric sensor (3-6) passes through each magnetic induction ring (2) in sequence and transmits this information to the control terminal (6). If no electrical signal is transmitted to the next magnetic induction ring (2) after a set time has elapsed after passing through a certain magnetic induction ring (2), it is determined that there is a blockage between the two magnetic induction rings (2).

5. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 4, characterized in that, The magnetic induction ring (2) has a ring width of 5-8 mm and is integrally formed with the outer polyethylene pipe (1-B); the spacing of the magnetic induction rings (2) is 0.3-0.5 m; the unblocking component is a spiral metal wire (3-1) and / or a hot melt rod.

6. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 4 or 5, characterized in that, The heat exchanger tube inspection device based on the principle of electromagnetic induction is used to detect blockages and damage in heat exchanger tubes, and includes the following steps: S1: After the Federal Learning Operation Control for De-icing and Snow Melting on the Energy Pile Bridge Issues a Preliminary Fault Alarm, turn on the Automatic Data Acquisition Instrument (5) switch, and use a magnetic induction ring to surround the magnetoelectric sensor (3-6) and move it. When the magnetic induction ring encounters the sensing point of the magnetoelectric sensor (3-6), it will issue an audible and visual alarm. At the same time, the Automatic Data Acquisition Instrument (5) will have an indication. The Automatic Data Acquisition Instrument (5) is working normally and will proceed with subsequent steps. S2: During testing, the pipeline is arranged vertically inside the energy pile, and the magnetoelectric sensor (3-6) is inserted by rotating with its own weight and the cable tray (4); the pipeline is arranged horizontally inside the bridge deck pavement layer, and the magnetoelectric sensor (3-6) is moved inside the pipeline by the drive wheel (3-7) and the miniature magnetoelectric sensor (3) with the unblocking module is moved; when the center of the magnetoelectric sensor (3-6) intersects with the magnetic induction ring (2), the automatic data acquisition instrument (5) emits a beeping sound and is accompanied by light indication; the surround camera (3-4) is turned on to monitor the image and sound waveform inside the pipeline in real time, and the automatic data acquisition instrument (5) automatically records the number of each magnetic induction ring (2) measurement point and the time interval between the two adjacent magnetic induction rings (2) measurement points, as well as the real-time image and sound waveform information; S3: The automatic data acquisition instrument (5) transmits the automatically recorded data to the control terminal (6) and uses one or more of the following methods to analyze the acquired data and accurately locate the damage point: isolated forest algorithm, X-ray digital imaging technology, ultrasonic detection, ultrasonic guided wave, ultrasonic C-scan, ultrasonic phased array, high temperature thickness measurement method; the control terminal (6) accurately locates the blockage point based on the abnormal time and location of the analyzed data.

7. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 6, is characterized in that, In step S3, when analyzing the collected data using the isolated forest algorithm, an isolated tree is built in the attribute space of the sample set to isolate attributes. Within the same attribute space, outliers are separated through model training, while normal values ​​are located in deeper child nodes of the isolated tree. The specific steps are as follows: S3.1: The current signal, sound wave signal, and electromagnetic signal transmitted from the magnetoelectric sensor (3-6) to the control terminal (6) are used as sample attributes to form a sample set, represented as X=(x1,x2,x3,…,x…). n ), where x n =(x n1 ,x n2 ,x n3 ,…,x nm ), x nm The nth type attribute signal at time m; S3.2: Use the attribute dimension q as the attribute cut point to segment attribute types, forming different isolated trees. For each isolated tree, use the attribute value cut point p as the outlier cut point to segment the attribute values ​​within the attribute space; Q is a random value belonging to the range (0, n), and p is a random value belonging to the range min(x... n ) < p < max(x) n Random values ​​within a given range; S3.3: Based on the split of attribute cut point q and outlier cut point p, a hyperplane is formed in the sample space. Samples smaller than the outlier cut point p are classified into one class and form the left node of the isolated tree, and vice versa. S3.4: Repeat steps S3.2 to S3.3 until each isolated tree leaf node contains only one sample, thus completing the training of the isolated tree model; S3.5: Take the sample data x at each time step i By traversing and calculating the data in an isolated tree model, the average height h(x) of each sample data can be obtained. i The outlier score of the sample data is calculated using the following formula: Where h(x) is the height of x in each isolated tree, c(n) is the average path length for a given number of samples n, and E(h(x)) is the expected path length of x in multiple isolated trees; When the score S(x,ψ)>0.75, the signal corresponding to the sample at that moment is considered an abnormal signal; When the score S(x,ψ) is between 0.4 and 0.75, the signal corresponding to the sample at that moment is considered a suspected abnormal signal; When the score S(x,ψ) < 0.4, the sample at that moment is considered a normal signal.

8. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 4 or 5, characterized in that, The heat exchanger tube maintenance device based on the principle of electromagnetic induction is used for unblocking and repairing heat exchanger pipelines, and includes the following steps: T1: Turn on the surround camera (3-4) and the lighting (3-9) and transmit the data to the control terminal (6) in real time, so that the surround camera (3-4) is aimed at the blockage. T2: Begin unblocking work. When the blockage is found to be caused by pipe heat fusion, turn on the series motor (3-5) controlling the spiral metal wire (3-1). After the spiral metal wire (3-1) rotates to the working speed, use the gravity of the magnetoelectric sensor (3-6) to slowly lower the sensor cable (3-8) in the vertical pipe. Use the drive wheel (3-7) to control the movement of the magnetoelectric sensor (3-6) in the horizontal pipe and slowly lower the sensor cable (3-8). The spiral metal wire (3-1) stirs the blockage until the blockage is cleared. When the blockage is caused by pipe heat fusion, replace the spiral metal wire (3-1) and connecting component (3-2) of the unblocking module with a heat fusion rod and place the magnetoelectric sensor (3-6) at the blockage again. Turn on the heating rod to the heat fusion temperature of the polyethylene material and use the gravity of the magnetoelectric sensor (3-6) to slowly lower the sensor cable (3-8) until the blockage is cleared. T3: After removing the miniature magnetoelectric sensor (3) containing the unblocking module from the pipe, perform pipe pressure testing and flushing to clean the foreign matter remaining in the pipe and complete the unblocking work. T4: After accurately locating the damage point, repair the heat exchange pipeline. The section of pipe where the damage point is located is unscrewed along the thread to replace the damaged section, or an automatic repair agent is used to repair the damaged section.

9. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 8, characterized in that, The automatic repair agent is one or more of polyethylene powder, polyethylene granules, nylon fiber filaments, ethylene glycol, and adhesive; when the automatic repair agent is nylon fiber filaments, the fineness is 200-300D and the length of the nylon fiber filaments is 3-5mm.

10. The method for overhauling and intelligent operation and maintenance control of the heat exchanger tubes of the active bridge deck de-icing and snow melting system according to claim 7 or 8, characterized in that, The repair process and method of the automatic repair agent are as follows: P1: After locating the damage point, seal either end of the pipe inlet / outlet according to the pressure test standard, and inject an automatic repair agent into the pipe through the other pipe opening; P2: After injecting the repair agent, pressurize the pipe, but the pressure should not exceed the rated pressure that the polyethylene pipe used can withstand. P3: When the pressure gauge reading is stable, the initial repair of the damaged point is completed; after the automatic repair agent has fully reached the strength requirements, the pipeline is pressure tested. Under the test pressure, the pressure should be stabilized for 15 to 20 minutes. After stabilization, the pressure drop should be 1% to 3%, and there should be no leakage to be considered as the repair work is completed.

Images