Auxiliary measuring, monitoring and early warning system for foundation construction of low-voltage-class power transmission line

Abstract

The invention relates to the technical field of construction auxiliary monitoring and early warning, in particular to a low-voltage-class power transmission line foundation construction auxiliary measuring, monitoring and early warning system which comprises a data acquisition module, a data transmission module, a data processing and analyzing module, a monitoring module and an early warning module. According to the scheme, a multi-level early warning mechanism is established, basic structure parameters, environmental parameters and electrical parameters are comprehensively considered, early warning threshold values of different levels are set, a time sequence prediction algorithm is used for pre-judging the parameter change trend in advance, early warning signals are sent out in advance, and meanwhile, differential strategies are implemented according to different early warning levels on the aspect of abnormal tracking and recording, so that the early warning accuracy is improved. Accurate control over the construction state is achieved, construction accidents are effectively avoided, and safe construction of the low-voltage-class power transmission line foundation is greatly guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of construction auxiliary monitoring and early warning, and particularly to an auxiliary measurement, monitoring and early warning system for the foundation construction of low-voltage transmission lines. Background Art

[0002] In modern power infrastructure construction, low-voltage transmission lines are widely distributed in various urban and rural areas and are an important part of the power transmission network. The quality of their foundation construction is directly related to the safe and stable operation of the transmission lines. However, the current foundation construction of low-voltage transmission lines faces many technical problems. In the construction measurement link, the accuracy of traditional measurement tools and methods is limited, and they are easily interfered by factors such as terrain and climate. It is difficult to accurately obtain key parameters such as the displacement, inclination, stress and strain of the foundation structure, which may lead to the deviation of the foundation construction exceeding the allowable range and posing a safety hazard to the subsequent line operation; in terms of monitoring, the existing monitoring means often cannot comprehensively monitor environmental parameters and electrical parameters; in addition, once an abnormal situation occurs during the construction process, the existing early warning mechanism is not perfect enough, the early warning method is single, and the setting of the early warning threshold lacks scientificity and flexibility, and it is impossible to send an alarm to the construction personnel in a timely and accurate manner, thus it is difficult to effectively avoid the occurrence of construction accidents, resulting in economic losses and construction period delays. Therefore, we propose an auxiliary measurement, monitoring and early warning system for the foundation construction of low-voltage transmission lines. Summary of the Invention

[0003] In view of the deficiencies of the prior art, the present invention provides an auxiliary measurement, monitoring and early warning system for the foundation construction of low-voltage transmission lines, thereby solving the technical problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention is realized through the following technical solutions:

[0005] An auxiliary measurement, monitoring and early warning system for the foundation construction of low-voltage transmission lines, comprising a data acquisition module, a data transmission module, a data processing and analysis module, a monitoring module and an early warning module;

[0006] The data acquisition module is used to collect the construction data of the transmission line foundation, including the acquisition of foundation structure parameters, environmental parameters and electrical parameters;

[0007] The data transmission module is responsible for transmitting the collected data to the processing module;

[0008] The data processing and analysis module performs cleaning, preprocessing, feature extraction and in-depth analysis on the transmitted data; for data cleaning and preprocessing, an outlier detection model based on deep learning, a filtering algorithm and an interpolation algorithm are used; for feature extraction, wavelet transform and principal component analysis algorithms are used for different types of data; for data analysis, machine learning algorithms and association rule mining algorithms are used, and a convolutional neural network is used to analyze image data;

[0009] The monitoring module, based on the processing and analysis results, monitors the construction status of the transmission line foundation in real time and tracks and records anomalies in a timely manner; the status monitoring establishes a real-time monitoring model based on multi-source data fusion, sets different levels of early warning and fault thresholds, and uses time series prediction algorithms to detect potential anomalies in advance; the anomaly tracking and recording adopt different tracking and recording methods according to different early warning levels;

[0010] The early warning module, when it monitors that an anomaly reaches the early warning condition, issues different forms of early warning signals according to different degrees; the early warning threshold setting adopts a dynamic threshold adjustment algorithm, which automatically adjusts the early warning threshold according to design requirements, historical data, standard specifications, data analysis results, combined with the real-time data change trend and environmental factors; the early warning methods include acoustic and optical early warning, SMS early warning, platform push early warning, and voice early warning.

[0011] In a possible implementation manner, the intelligent compensation algorithm for basic displacement measurement in the data acquisition module is based on the capacitance formula where τ is the dielectric constant, S is the plate area, d is the plate spacing, and the calibration formula is Δx = kΔC, where k is the calibration coefficient, to calculate the displacement amount, and uses machine learning algorithms to dynamically adjust the compensation parameters according to environmental factors.

[0012] In a possible implementation manner, in the improved time division multiple access mechanism adopted for short-distance transmission in the data transmission module, the TDMA time slot allocation formula is where T is the total time period, N1 is the number of high-priority nodes, N2 is the number of low-priority nodes, and α is the priority coefficient.

[0013] In a possible implementation manner, in the status monitoring of the monitoring module, three levels of early warning severity are set according to different parameter ranges:

[0014] Level 1 early warning: When the basic displacement change rate V is between 0.05 - 0.08 mm / d, the inclination angle θ is between 0.3 - 0.5°, the stress and strain σ reaches 80% - 90% of the design value σ 设计 , the wind speed v in the environmental parameters exceeds 10 m / s, the rainfall r reaches 10 - 20 mm / h, and the temperature and humidity exceed the normal range but not reach the severe level, it is determined as a level 1 early warning. At this time, the time series prediction algorithm is used to predict the parameter change trend. If the predicted parameters have a tendency to continuously approach the higher-level early warning threshold, an early warning signal is sent in advance;

[0015] Level 2 early warning: When the basic displacement change rate V is between 0.08 - 0.12 mm / d, the displacement reaches 5 - 8 mm, the inclination angle θ is between 0.5 - 1°, the stress and strain σ reaches the design value σ 设计90% - 105% of it, the wind speed v in the environmental parameters exceeds 15 m / s, the rainfall r reaches 20 - 30 mm / h, and the abnormal change in light intensity affects the construction safety, then it is determined as a secondary warning. When the system issues a secondary warning, it will increase the monitoring frequency and further analyze the change characteristics of displacement and tilt data using wavelet transform. The formula is: Among them, W(a, b) is the wavelet transform result, f(t) is the original signal, a is the scale parameter, b is the translation parameter, and ψ is the wavelet function, in order to more accurately evaluate the construction state;

[0016] Tertiary warning: When the rate of change of foundation displacement V exceeds 0.12 mm / d, the displacement exceeds 8 mm, the tilt angle θ exceeds 1°, and the stress strain σ exceeds 105% of the design value σ 设计 of it, the wind speed v in the environmental parameters exceeds 20 m / s, the rainfall r exceeds 30 mm / h, and there are serious abnormalities in the electrical parameters, it is determined as a tertiary warning. At this time, the system immediately takes emergency measures to avoid the occurrence of safety accidents.

[0017] Beneficial effects compared with the prior art:

[0018] 1. In this solution, by establishing a multi-level warning mechanism, comprehensively considering foundation structure parameters, environmental parameters, and electrical parameters, setting warning thresholds for different levels, and dividing primary, secondary, and tertiary warnings according to different ranges of parameters such as the rate of change of foundation displacement, tilt angle, stress strain, and environmental wind speed and rainfall, using time series prediction algorithms to predict the parameter change trend in advance and send warning signals in advance. At the same time, in abnormal tracking and recording, implementing differential strategies according to different warning levels, achieving precise control of the construction state, which effectively avoids the occurrence of construction accidents and greatly guarantees the safe progress of the foundation construction of low-voltage transmission lines;

[0019] 2. In this solution, the data processing and analysis module uses multiple algorithms such as deep learning, wavelet transform, and principal component analysis to clean, preprocess, extract features, and deeply analyze the transmitted data. It detects outliers through autoencoders, removes noise using multiple filtering algorithms, normalizes the data, and processes missing data using interpolation algorithms; in feature extraction, corresponding algorithms are used for different types of data to comprehensively and accurately obtain features; machine learning algorithms and association rule mining algorithms are used to find data associations and patterns, and convolutional neural networks are used to analyze image data to identify potential safety hazards, which optimizes construction decisions and improves construction quality and efficiency. Brief Description of the Drawings

[0020] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly and implement it according to the content of the specification, the following will be described in detail with reference to the preferred embodiments of the present invention and the accompanying drawings.

[0021] Figure 1 This is a schematic diagram of the system framework structure of the present invention. Specific Embodiments

[0022] The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the present invention can be implemented in various different forms. Therefore, the present invention is not limited to the embodiments described below. Additionally, in order to more clearly describe the present invention, components not connected to the invention will be omitted from the drawings;

[0023] The technical solutions in the embodiments of the present application are to solve the problems in the above-mentioned background technology, and the general idea is as follows:

[0024] Embodiment:

[0025] This embodiment introduces a low-voltage level transmission line foundation construction auxiliary measurement and monitoring warning system, including a data acquisition module, a data transmission module, a data processing and analysis module, a monitoring module, and a warning module;

[0026] I. Data Acquisition Module

[0027] There are problems of insufficient accuracy and large environmental interference in the data acquisition of the existing system. This module is responsible for comprehensively and accurately collecting data related to the transmission line foundation construction, providing a reliable basis for subsequent analysis.

[0028] 1. Acquisition of Foundation Structure Parameters

[0029] 1.1 Displacement measurement: Based on the traditional MEMS displacement sensor, an intelligent compensation algorithm is introduced. When the foundation displacement causes a change in the internal capacitance of the sensor, according to the capacitance formula (τ is the permittivity, S is the plate area, and d is the plate spacing), by measuring the change in capacitance ΔC, the displacement Δx is calculated using the calibration formula Δx = kΔC (k is the calibration coefficient). At the same time, machine learning algorithms are used to perform real-time analysis on the output data of the sensor, and the compensation parameters are dynamically adjusted according to environmental factors (such as the influence of temperature and humidity changes on the sensor performance) to improve the measurement accuracy and overcome the problem of accuracy decline caused by environmental interference.

[0030] 1.2 Inclination measurement: The combination of a biaxial MEMS accelerometer and a gyroscope is adopted. The MEMS accelerometer is based on Newton's second law. When the foundation is inclined, the gravitational acceleration g generates a component force on the sensitive axis. Let the angle between the sensitive axis and the direction of the gravitational acceleration be θ, then the acceleration a = gsinθ, and the inclination angle at this time is The gyroscope measures the rotational angular velocity ω using the conservation of angular momentum, and the inclination angle θ is obtained by integrating gyro= ∫wdt to obtain the angular change. On this basis, the Kalman filtering algorithm is used to fuse the data of both, and the tilt angle can be more accurately output in both static and dynamic states, effectively solving the problem of low tilt measurement accuracy in complex environments.

[0031] 1.3 Stress and Strain Measurement: Resistance strain gauges are pasted on the surface of the steel bars in the basic reinforced concrete structure. When the foundation is stressed, the resistance value R of the resistance strain gauge changes. According to Hooke's law (k1 is the sensitivity coefficient, and τ is the strain). The resistance change is converted into a voltage change through a Wheatstone bridge, and the output voltage (U in is the input voltage). To overcome the defect that the traditional measurement method is greatly affected by the environment, a distributed temperature compensation technology is adopted. Temperature sensors are deployed near the strain gauges, and the strain measurement value is adjusted in real time according to the temperature change to improve the measurement accuracy.

[0032] 2. Environmental Parameter Acquisition

[0033] 2.1 Temperature and Humidity Measurement: A high-precision digital temperature and humidity sensor is selected, specifically the SHT31. The temperature measurement is based on the characteristics of the thermistor, and the relationship between the resistance value R T and the temperature T is (R0 is the resistance value at T0, and B is a constant). The temperature is converted through a calibration curve. The humidity measurement uses the relationship between the humidity-sensitive capacitor and the relative humidity RH, and the calibration formula is (a i is the coefficient, and C H is the capacitance value). To improve the measurement accuracy, a protective housing is added outside the sensor to reduce the interference of environmental factors. The temperature accuracy can reach ±0.2 °C, and the humidity accuracy can reach ±1.5% RH.

[0034] 2.2 Wind Speed Measurement: Drawing on the ultrasonic wind speed measurement principle in the meteorological field, an ultrasonic wind speed sensor is used. The wind speed is calculated by measuring the time difference of ultrasonic waves propagating in the air. Let the propagation times of ultrasonic waves in the downwind and upwind directions be t1 and t2 respectively, and the propagation distance be L. Then the wind speed This sensor is not affected by the wind direction, has high measurement accuracy, can effectively meet the wind speed measurement requirements in complex construction environments, and solves the problem of inaccurate measurement of existing three-cup anemometers in harsh environments.

[0035] 2.3 Rainfall Measurement: Image recognition technology is used in combination with a rain gauge for rainfall measurement. A high-definition camera is installed above the rain gauge to capture images of the change in the rainwater level in the rain gauge. The change in the liquid level height is identified through an image recognition algorithm, and combined with the calibration parameters of the rain gauge, the rainfall is calculated. Compared with the traditional tipping bucket rain gauge, this method can monitor the change in rainfall in real time, and is not affected by the mechanical failure of the tipping bucket, and the measurement is more accurate and reliable.

[0036] 2.4 Light intensity measurement: Use a light intensity sensor based on an organic optoelectronic diode. The current response of the organic optoelectronic diode has a linear relationship with the light intensity E. By measuring the current change and according to the calibration formula I = k2E (k2 is a coefficient), the light intensity value can be obtained. This sensor has a fast response speed and low cost, and can accurately measure the light intensity in a complex light environment, overcoming the defect that traditional silicon photovoltaic cells are greatly affected by factors such as temperature.

[0037] 3. Electrical parameter acquisition

[0038] 3.1 Voltage measurement: Install a voltage transformer on the transmission line to convert high voltage to low voltage (specifically 100V), and use a resistive voltage division circuit. According to the voltage division formula (R1 and R2 are resistors, U in is the input voltage, U out is the output voltage) for sampling. To improve the measurement accuracy, an adaptive filtering algorithm is used to process the sampled signal, real-time filter out noise and interference, and then collect it by a high-speed A / D converter after signal conditioning.

[0039] 3.2 Current measurement: Use a Rogowski coil to collect the current in the transmission line. The Rogowski coil is based on the principle of electromagnetic induction. When there is current passing through the wire, an induced electromotive force will be generated in the Rogowski coil (M is the mutual inductance coefficient between the coil and the wire, is the current change rate). By measuring the induced electromotive force and through integral operation the current value can be obtained. To overcome the problem of inaccurate measurement in a complex electromagnetic environment, a magnetic shielding layer is added outside the Rogowski coil to reduce external magnetic field interference and improve the measurement accuracy.

[0040] 3.3 Power measurement: Through a digital signal processor (DSP), according to the collected voltage and current data, use the formula (U is the effective voltage value, I is the effective current value, is the power factor) to calculate the power. Synchronous sampling technology is used to ensure the synchronization of voltage and current sampling and improve the accuracy of power calculation. At the same time, the fast Fourier transform (FFT) algorithm is used to analyze the voltage and current signals to accurately calculate the effective values and phase differences of voltage and current, solving the problem of low accuracy of existing power measurement in a complex electrical environment.

[0041] II. Data transmission module

[0042] Existing data transmission has problems such as instability, susceptibility to interference, and low security. This module is responsible for stably, quickly, and securely transmitting the collected data to the processing module to ensure data integrity and real-time performance.

[0043] 1. Short-distance transmission

[0044] Inside the construction site, a hybrid networking technology of Bluetooth 5.3 and LoRaWAN is adopted. Bluetooth 5.3 features low power consumption and high speed, and is suitable for the rapid transmission of small amounts of data between sensor nodes and nearby relay nodes. LoRaWAN, on the other hand, constructs a long-distance, low-power self-organizing network for the wide coverage and reliable transmission of data within the construction site. The sensor first sends data to a nearby relay node via Bluetooth 5.3, and the relay node then transmits the data to the data aggregation node through the LoRaWAN network. Improved Time Division Multiple Access (TDMA) and Carrier Sense Multiple Access / Collision Avoidance (CSMA / CA) mechanisms are adopted. The TDMA time slot allocation takes into account node priorities, and the formula is (T is the total time period, N1 is the number of high-priority nodes, N2 is the number of low-priority nodes, and α is the priority coefficient). CSMA / CA is combined with an intelligent backoff algorithm to reduce collisions. The transmitted data is encrypted with AES to ensure data security, and the transmission reliability can reach over 99.5%, effectively solving the problems of large electromagnetic interference and low transmission efficiency in existing short-distance transmissions.

[0045] 2. Long-distance transmission

[0046] A solution combining 5G and satellite communication is adopted between the aggregation node and the server. 5G communication features high speed and low latency. After the aggregation node packs and processes the sensor data collected, it is sent to the server through the 5G communication module. In areas where the 5G signal is unstable or not covered, it automatically switches to satellite communication. Satellite communication adopts advanced error correction coding technology to improve the reliability of data transmission. At the same time, blockchain technology is used to record the transmitted data to ensure the immutability and traceability of the data, solving the problems of unstable long-distance transmission and low security in the existing situation.

[0047] III. Data processing and analysis module

[0048] This module cleans, preprocesses, extracts features from, and deeply analyzes the transmitted data, providing a scientific basis for monitoring and early warning.

[0049] 1. Data cleaning and preprocessing

[0050] An outlier detection model based on deep learning is adopted, specifically an autoencoder. The autoencoder constructs a feature representation of the data through learning a large amount of normal data. When abnormal data is input, the reconstruction error of the model will increase significantly, thus identifying outliers. Compared with the traditional 3σ criterion, it can more accurately detect outliers in complex data. An algorithm combining moving average filtering and median filtering is used to denoise the data. First, the high-frequency noise in the data is removed through moving average filtering, and then the remaining impulse noise is removed using median filtering. The data is normalized, and the formula is (where \(x\) is the original data, \(x\) min and \(x\) max are the minimum and maximum values of this type of data respectively). For missing data, an interpolation algorithm based on time series prediction is adopted to predict the missing values using the trends and correlations of historical data, solving the problem of poor effects of existing data cleaning and preprocessing methods.

[0051] 2. Feature Extraction

[0052] For basic displacement and tilt data, wavelet transform is used to extract features such as change trends, rates, and accelerations. Wavelet transform can analyze data at different time scales and more accurately capture the dynamic change features of data. When extracting features such as peak values, mean values, variance stress concentration coefficients from stress-strain data, in combination with the finite element analysis model, the stress-strain data is associated with the mechanical properties of the basic structure to more comprehensively understand and extract features. When extracting features such as extreme values, change periods, and correlation coefficients from environmental parameters, the principal component analysis (PCA) algorithm is used to reduce the dimensionality of multi-dimensional environmental parameter data and extract the main features to reduce data redundancy. When extracting features such as harmonic content, inter-harmonic content, voltage fluctuations, and flicker from electrical parameters, the fast Fourier transform (FFT) combined with the wavelet packet transform algorithm is adopted to improve the accuracy and efficiency of feature extraction and solve the problems of incomplete and inaccurate existing feature extraction.

[0053] 3. Data Analysis

[0054] Machine learning algorithms such as support vector machine (SVM), random forest (RF), and long short-term memory network (LSTM) are used to classify the feature data. Specifically for LSTM, the input layer receives the time series data \(X\) t , and through the forget gate \(f\) t =σ(\(W\) f [\(h\) t-1 , \(X\) t + \(b\) f ), input gate \(i\) t =σ(\(W\) i [\(h\) t-1 , \(X\) t + \(b\) i ), output gate \(o\) t =σ(\(W\) o [\(h\) t-1 , \(X\) t + \(b\) o ) and the memory unit are processed (\(W\) is the weight matrix, \(b\) is the bias vector, is element-wise multiplication, and σ is the sigmoid activation function). Combining with the association rule mining algorithm, potential association relationships and data patterns among different parameters are found. The convolutional neural network (CNN) is used to analyze the image data of the transmission line (such as the monitoring video images at the construction site), and potential safety hazards are identified, such as the soil collapse around the foundation and the illegal operation of construction equipment, to solve the problems of low efficiency and low accuracy of the existing data analysis algorithms.

[0055] IV. Monitoring Module

[0056] There are problems in the existing monitoring, such as inaccurate, poor real-time performance, and incomplete abnormal tracking. Based on the processing and analysis results, this module monitors the construction status of the transmission line foundation in real time and accurately, tracks and records the abnormalities in time, and provides accurate information for early warning.

[0057] 1. Status Monitoring

[0058] 1.1 Primary Early Warning

[0059] It is determined as a primary early warning when one of the following conditions is met: the rate of change of foundation displacement V is 0.05 ≤ V ≤ 0.08 (unit: mm / d); the inclination angle θ is 0.3° ≤ θ ≤ 0.5°; the stress and strain σ reach the design value σ 设计 of in the environmental parameters, the wind speed v exceeds 10 m / s, the rainfall r reaches 10 ≤ r ≤ 20 (unit: mm / h), the temperature and humidity exceed the normal range but do not reach the severe level, etc. At this time, the time series prediction algorithm (such as the ARIMA model) is used to predict the change trend of the parameters. If the predicted parameters have a trend of continuously approaching the warning threshold of a higher level, an early warning signal is sent in advance. Specifically, if the current rate of change of foundation displacement is 0.06 mm / d, and it is predicted by the ARIMA model that it may reach 0.07 mm / d within the next 24 hours, the system will send a primary early warning signal.

[0060] 1.2 Secondary Early Warning

[0061] It is determined as a secondary early warning when the following conditions are met: the rate of change of foundation displacement V is 0.08 ≤ V ≤ 0.12 (unit: mm / d), the displacement D reaches 5 ≤ D ≤ 8 (unit: mm), the inclination angle θ is 0.5° ≤ θ ≤ 1°, the stress and strain σ reach the design value σ 设计 of in the environmental parameters, the wind speed v exceeds 15 m / s, the rainfall r reaches 20 ≤ r ≤ 30 (unit: mm / h), and the abnormal change of the light intensity I affects the construction safety. When the system issues a secondary early warning, it will increase the monitoring frequency and use wavelet transform to further analyze the change characteristics of displacement and inclination data. The formula is: Among them, W(a, b) is the wavelet transform result, f(t) is the original signal, a is the scale parameter, b is the translation parameter, and ψ is the wavelet function. Through this formula, data can be analyzed at different time scales to more accurately capture the dynamic change characteristics of the data, so as to more accurately evaluate the construction status.

[0062] 1.3 Three-level early warning

[0063] It is determined as a three-level early warning when the following situations occur: the rate of change of foundation displacement V exceeds 0.12 mm / d, the displacement D exceeds 8 mm, the inclination angle θ exceeds 1°, and the stress and strain σ exceed 105% of the design value σ 设计 That is Or the environmental parameters show that the wind speed v exceeds 20 m / s, the rainfall r reaches 30 mm / h or more, and the electrical parameters show serious abnormalities. At this time, the system immediately takes emergency measures to automatically suspend the operation of relevant construction equipment to avoid safety accidents.

[0064] 2. Abnormality tracking and recording

[0065] 2.1 When a first-level early warning occurs

[0066] The system automatically starts a multi-source data fusion tracking mechanism based on the Internet of Things and big data, and collects various data (including videos, audios, etc.) related to the abnormal part every 15 minutes. Using big data analysis technology, a preliminary correlation analysis is carried out on the collected multi-source data, and the abnormal occurrence time t, location L, abnormal type T and parameter change situation are recorded and stored in the distributed database. The foundation deformation situation is marked with light red lines in the 3D model, and the parameter change trend is displayed in the form of a line chart on the monitoring and management platform. The abscissa of the line chart is the time t, and the ordinate is the corresponding parameter value, which is convenient for the staff to understand the preliminary situation of the abnormality.

[0067] 2.2 When a second-level early warning occurs

[0068] Data of the abnormal part are collected every 10 minutes, and a more in-depth analysis is carried out on the abnormal data. For example, machine learning algorithms are used to comprehensively analyze the foundation structure parameters, environmental parameters and electrical parameters to dig out potential safety hazards. While recording the abnormal information, the data for a period of time before and after the occurrence of the abnormality are backed up for subsequent detailed analysis. The foundation deformation situation is marked with red lines in the 3D model, and the severity of the deformation is shown through the change of transparency. The calculation formula of the transparency T is The parameter change trend is displayed in the form of a dynamic curve, which can more intuitively reflect the change process.

[0069] 2.3 When a third-level early warning occurs

[0070] Collect data of abnormal parts in real time, analyze abnormal situations comprehensively and deeply, combine historical data and real-time data, and use artificial intelligence algorithms to predict the development trend of abnormalities. While recording abnormal information, send detailed abnormal reports to relevant departments and personnel in a timely manner. The report content includes the cause analysis of the abnormality, the possible consequences, and the recommended measures to be taken. Highlight the foundation deformation in the 3D model with a flashing red warning sign, and display the parameter change trend in the form of a prominent bar chart, so that the staff can quickly understand the severity of the abnormality.

[0071] V. Early Warning Module

[0072] When this module detects that an abnormality reaches the early warning condition, it issues various forms of early warning signals in a timely and accurate manner to remind relevant personnel to take measures to avoid accidents.

[0073] 1. Early Warning Threshold Setting

[0074] According to design requirements, historical data, standards and specifications, and data analysis results, adopt a dynamic threshold adjustment algorithm. This algorithm combines the real-time data change trend and environmental factors to automatically adjust the early warning threshold. For example, under bad weather conditions, appropriately reduce the early warning thresholds of parameters such as foundation displacement, stress and strain to improve the accuracy and timeliness of early warning.

[0075] 1.1 Primary Early Warning Threshold

[0076] Under normal circumstances, the threshold V of the foundation displacement change rate 1阈值 is set to 0.05 mm / d, the threshold θ of the inclination angle 1阈值 is set to 0.3°, and the threshold σ of stress and strain 1阈值 is set to 80% of the design value σ 设计 , that is, σ 1阈值 = 0.8σ 设计 . When the environmental parameters are within the normal range, these thresholds remain stable; if the environmental parameters change to a certain extent, for example, the wind speed v is between 8 - 10 m / s and the rainfall r is between 5 - 10 mm / h, according to the dynamic threshold adjustment algorithm, appropriately reduce the early warning thresholds of parameters such as foundation displacement and stress and strain. Taking the threshold of the foundation displacement change rate as an example, the adjustment formula is: When the wind speed v = 9 m / s, to send out early warning signals in advance to remind the construction personnel to pay attention.

[0077] 1.2 Secondary Early Warning Threshold

[0078] The threshold V of the foundation displacement change rate 2阈值 is set to 0.08 mm / d, the displacement threshold D 2阈值 is set to 5 mm, and the threshold θ of the inclination angle 2阈值Set to 0.5°, stress-strain threshold σ 2阈值 Set to the design value σ 设计 Of 90%, i.e., σ 2阈值 = 0.9σ 设计 . When the environmental parameters change significantly, such as the wind speed v is between 12 - 15 m / s and the rainfall r is between 15 - 20 mm / h, according to the dynamic threshold adjustment algorithm, the warning threshold is further reduced. Taking the threshold of the basic displacement change rate as an example, the adjustment formula is: When the wind speed v = 14 m / s, Ensure that timely warnings can be issued when the abnormal situation develops to the moderate stage.

[0079] 1.3 Three-level warning threshold

[0080] Threshold of basic displacement change rate V 3阈值 Set to 0.12 mm / d, displacement threshold D 3阈值 Set to 8 mm, tilt angle threshold θ 3阈值 Set to 1°, stress-strain threshold σ 3阈值 Set to 105% of the design value σ 设计 , i.e., σ 3阈值 = 1.05σ 设计 . Under bad weather conditions, such as when the wind speed v exceeds 15 m / s, the rainfall r exceeds 20 mm / h, or there are abnormal fluctuations in electrical parameters, the warning threshold is significantly reduced. Taking the threshold of the basic displacement change rate as an example, the adjustment formula is: When the wind speed v = 18 m / s, So as to quickly issue warnings when serious abnormal situations occur and ensure construction safety.

[0081] 2. Warning methods

[0082] 2.1 Acoustic-optic warning: Set up intelligent acoustic-optic alarms at the construction site. Different frequency and color acoustic-optic signals are emitted according to the warning level. The first-level warning is yellow light and low-frequency sound, and the second-level warning is red light and high-frequency sound. The acoustic-optic alarm has an environmental adaptive function and can automatically adjust the acoustic-optic intensity according to the on-site noise and light intensity to ensure the warning effect.

[0083] 2.2 SMS warning: Send warning messages to relevant personnel through the SMS platform, including time, location, type, level, and handling suggestions. SMS encryption technology is used to ensure information security. At the same time, artificial intelligence algorithms are used to analyze the feedback of the receiving personnel to optimize the SMS content and sending strategy and improve the information transmission efficiency.

[0084] 2.3 Platform Push Warning: The warning is displayed in the dedicated monitoring and management platform through pop-up windows and message pushes. The platform supports multi-terminal access and provides personalized settings. Users can set reminder methods and display content. By using virtual reality (VR) and augmented reality (AR) technologies, the warning scenarios and related data are displayed in an immersive manner on the platform, facilitating users to understand the warning situation more intuitively.

[0085] 2.4 Voice Warning: In noisy construction scenarios, warnings are issued through voice broadcasts. Intelligent voice broadcast devices are set at key positions, and voice messages are automatically generated according to the warning content. Voice synthesis technology is used to improve the clarity and intelligibility of the voice.

[0086] Finally, it should be noted that: Obviously, the above embodiments are merely examples for clearly illustrating the present invention and are not limitations on the implementation manners. For those of ordinary skill in the art, other different forms of changes or variations can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. And the obvious changes or variations derived therefrom are still within the protection scope of the present invention.

Claims

1. An auxiliary measurement and monitoring warning system for the foundation construction of low-voltage transmission lines, characterized in that, It includes a data acquisition module, a data transmission module, a data processing and analysis module, a monitoring module, and an early warning module; The data acquisition module is used to collect the basic construction data of the transmission line, including the acquisition of basic structure parameters, environmental parameters, and electrical parameters; The data transmission module is responsible for transmitting the collected data to the processing module; The data processing and analysis module cleans, preprocesses, extracts features, and deeply analyzes the transmitted data; For data cleaning and preprocessing, an outlier detection model based on deep learning, a filtering algorithm, and an interpolation algorithm are used; For feature extraction, wavelet transform and principal component analysis algorithms are used for different types of data; For data analysis, machine learning algorithms and association rule mining algorithms are used, and a convolutional neural network is used to analyze image data; The monitoring module, based on the processing and analysis results, monitors the basic construction status of the transmission line in real time and timely tracks and records anomalies; For status monitoring, a real-time monitoring model based on multi-source data fusion is established, different levels of early warning and fault thresholds are set, and a time series prediction algorithm is used to detect potential anomalies in advance; For anomaly tracking and recording, different tracking and recording methods are adopted according to different early warning levels; The early warning module, when it detects that an anomaly reaches the early warning condition, issues different forms of early warning signals according to different degrees; The early warning threshold setting adopts a dynamic threshold adjustment algorithm, which automatically adjusts the early warning threshold according to design requirements, historical data, standard specifications, and data analysis results, combined with the real-time data change trend and environmental factors; The early warning methods include audible and visual warnings, text message warnings, platform push warnings, and voice warnings.

2. The auxiliary measurement, monitoring and early warning system for the construction of the low-voltage level transmission line foundation according to claim 1, wherein, The intelligent compensation algorithm for basic displacement measurement in the data acquisition module is based on the capacitance formula where τ is the dielectric constant, S is the plate area, d is the plate spacing, and the calibration formula is Δx = kΔC, where k is the calibration coefficient, to calculate the displacement, and a machine learning algorithm is used to dynamically adjust the compensation parameters according to environmental factors.

3. The auxiliary measurement, monitoring and early warning system for the foundation construction of low-voltage transmission lines according to claim 1, characterized in that, In the improved time division multiple access mechanism adopted by the short-distance transmission of the data transmission module, the TDMA time slot allocation formula is where T is the total time period, N1 is the number of high-priority nodes, N2 is the number of low-priority nodes, and α is the priority coefficient.

4. The auxiliary measurement, monitoring and early warning system for the foundation construction of low-voltage transmission lines according to claim 1, wherein, In the status monitoring of the monitoring module, three levels of early warning severity are set according to different parameter ranges: Level 1 Early Warning: When the rate of change of foundation displacement V is between 0.05 - 0.08 mm / d, the inclination angle θ is between 0.3 - 0.5°, the stress and strain σ reaches 80% - 90% of the design value σ 设计 , when the wind speed v in the environmental parameters exceeds 10 m / s, the rainfall r reaches 10 - 20 mm / h, and the temperature and humidity exceed the normal range but do not reach the severe level, it is determined as a Level 1 Early Warning. At this time, the time series prediction algorithm is used to predict the trend of parameter changes. If the predicted parameters show a trend of continuously approaching the warning threshold of a higher level, an early warning signal is sent in advance; Secondary warning: When the rate of change of the foundation displacement V is between 0.08 - 0.12 mm / d, the displacement reaches 5 - 8 mm, the inclination angle θ is between 0.5 - 1°, the stress and strain σ reaches 90% - 105% of the design value σ 设计 and the wind speed v in the environmental parameters exceeds 15 m / s, the rainfall r reaches 20 - 30 mm / h, and the abnormal change in light intensity affects the construction safety, it is determined as a secondary warning. When the system issues a secondary warning, it will increase the monitoring frequency and use wavelet transform to further analyze the change characteristics of displacement and inclination data. The formula is: where W(a, b) is the wavelet transform result, f(t) is the original signal, a is the scale parameter, b is the translation parameter, and ψ is the wavelet function to more accurately evaluate the construction status; Level 3 Early Warning: When the rate of change of the foundation displacement V exceeds 0.12 mm / d, the displacement exceeds 8 mm, the inclination angle θ exceeds 1°, the stress and strain σ exceeds 105% of the design value σ 设计 , the wind speed v in the environmental parameters exceeds 20 m / s, the rainfall r exceeds 30 mm / h, and there are serious abnormalities in the electrical parameters, it is determined as a Level 3 early warning. At this time, the system immediately takes emergency measures to avoid safety accidents.

Images