Surface temperature sensor and cable joint temperature monitoring system

Abstract

The invention relates to the field of power system intelligent monitoring, and discloses a surface temperature sensor and a cable joint temperature monitoring system, and the system comprises the surface temperature sensor which is used for obtaining the temperature data of a cable joint, and transmitting the data to a data processing module; the data processing module is used for receiving the temperature data from the surface temperature sensor, storing the temperature data, formatting the received temperature data, removing invalid data and preliminarily screening abnormal values; and the temperature modeling module is used for calculating temperature distribution of the cable joint based on a heat conduction model, and establishing a temperature distribution model of the cable joint through a heat conduction equation in combination with the effective data output by the temperature data preprocessing module. According to the method, an optimization technical scheme combining Fourier transform and dimension reduction calculation is adopted, efficient processing and analysis of temperature data are achieved, the system response speed is increased, and the method is more efficient especially in a large-scale data processing environment.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of power systems, and particularly to a surface temperature sensor and a cable joint temperature monitoring system. Background Art

[0002] In modern power systems, as a key connection component, the operating state of cable joints directly affects the safety and stability of the entire power grid. However, due to factors such as long-term high-load current, cable aging, and environmental temperature changes, cable joints are extremely prone to overheating problems, and may even cause serious accidents such as short circuits and fires. Therefore, real-time monitoring of the temperature of cable joints and fault early warning have become particularly important. The traditional manual inspection method can no longer meet the needs of large-scale power systems, while intelligent temperature monitoring systems can obtain cable joint temperature data in real time, analyze its change trend, and issue alarms in a timely manner in case of abnormalities, so as to reduce the risk of equipment failures and improve the safety and reliability of power grid operation.

[0003] Existing cable joint temperature monitoring technologies usually use thermistors, infrared sensors or fiber optic temperature measurement technologies to measure the temperature of cable joints. These methods can collect temperature data relatively accurately and trigger alarms when the temperature reaches a preset threshold, playing a certain role in safety protection. At the same time, some monitoring systems also have a data storage function, which can record historical temperature data for subsequent analysis. In addition, some advanced technical solutions have adopted wireless transmission methods, enabling monitoring devices to remotely transmit temperature data and improving the intelligence level of the system.

[0004] However, existing temperature monitoring technologies still have many deficiencies and are difficult to meet the accurate monitoring requirements in complex power grid environments. First of all, most traditional monitoring systems are based on single-point temperature acquisition, and can only obtain instantaneous temperature values, but cannot analyze the change trend of temperature, resulting in the inability to predict potential faults in advance. Usually, alarms are triggered only after temperature anomalies have occurred, showing a certain lag. Secondly, many systems use fixed threshold alarms, and fixed thresholds are difficult to adapt to different environments, seasons, and load changes, which may lead to frequent false alarms and affect operation and maintenance judgment. Moreover, the calculation efficiency of existing methods is relatively low. Many systems still use the method of directly performing time-domain analysis on temperature data, and fail to make full use of the frequency characteristics of the data, resulting in waste of computing resources and difficulty in meeting the requirements of efficient real-time monitoring. In addition, the alarm mechanism is single, usually only providing simple alarm signals, and cannot distinguish different levels of fault situations, resulting in low utilization rate of alarm information and difficulty for maintenance personnel to make reasonable scheduling according to the urgency of the alarm. Therefore, those skilled in the art have proposed a surface temperature sensor and a cable joint temperature monitoring system to solve the above problems. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a surface temperature sensor and a cable joint temperature monitoring system, which solve the deficiencies in the calculation efficiency, the accuracy of fault judgment, the alarm mechanism, etc. of the cable joint temperature monitoring technology in the prior art.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A surface temperature sensor and a cable joint temperature monitoring system, comprising: A surface temperature sensor, configured to obtain the temperature data of the cable joint and transmit the data to the data processing module; A data processing module, configured to receive the temperature data from the surface temperature sensor, store and format the received temperature data, remove invalid data, and preliminarily screen out outliers; A temperature modeling module, configured to calculate the temperature distribution of the cable joint based on the heat conduction model, combine the valid data output by the temperature data preprocessing module, and establish a temperature distribution model of the cable joint through the heat conduction equation; An optimization estimation module, configured to perform noise filtering on the temperature data, provide a more accurate temperature estimate, and optimize the effectiveness of the sensor measurement data; A calculation optimization module, configured to accelerate the temperature prediction calculation, combining the temperature distribution model output by the temperature modeling module and the data processed by the optimization estimation module; A fault detection module, configured to determine whether there is an abnormal temperature change in the cable joint, combine the prediction result of the temperature modeling module and the accurate data of the optimization estimation module, and generate an alarm signal to indicate that the temperature exceeds the standard or is abnormal.

[0007] Preferably, the data processing module includes: A temperature data receiving unit, configured to receive the temperature data sent by the surface temperature sensor; A data storage unit, configured to store the received temperature data; A data preprocessing unit, configured to format the temperature data, remove invalid data, and preliminarily screen outliers.

[0008] Preferably, the temperature modeling module includes: A heat conduction modeling unit, configured to establish a temperature distribution model of the cable joint based on the heat conduction equation; A discretization calculation unit, configured to perform discretization solution on the temperature model by using the finite difference method; A boundary condition setting unit, configured to set the convective heat transfer boundary condition between the cable joint and the external environment.

[0009] Preferably, the optimization estimation module includes: A state space modeling unit, configured to construct a state space model for estimating the temperature of the cable joint; A Kalman filter calculation unit for filtering measurement data using an adaptive Kalman filter method; A noise adaptive adjustment unit for dynamically optimizing measurement noise parameters based on the Bayesian inference method.

[0010] Preferably, the calculation and optimization module includes: A Fourier transform calculation unit for performing frequency-domain decomposition on temperature data based on the Fourier transform method; A dimensionality reduction calculation unit for screening out the main Fourier components to reduce the calculation complexity; A fast inverse transform unit for converting the screened frequency-domain data back to the time-domain temperature prediction result.

[0011] Preferably, the fault detection module includes: A threshold calculation unit for calculating the dynamic temperature alarm threshold; An anomaly detection unit for comparing the current temperature with the calculated alarm threshold and determining whether an anomaly has occurred; An alarm signal generation unit for triggering an alarm signal when the temperature exceeds the preset threshold.

[0012] Preferably, the modeling process of the temperature modeling module includes the following steps: Establish a temperature distribution calculation model, and calculate the spatial distribution of the internal temperature field of the cable joint based on the thermal diffusion coefficient of the cable joint material; Calculate the heat source term, calculate the Joule heat generated by the current passing through the cable joint based on the current and contact resistance of the cable joint, and input this heat as the heat source into the temperature modeling model; Solve the steady-state and transient temperature distributions, and calculate the steady-state temperature field and transient temperature change process of the cable joint respectively based on the established heat conduction model to obtain the temperature change of the cable joint under different working conditions.

[0013] Preferably, the calculation process of the optimization estimation module includes the following steps: Perform prediction calculation, calculate the prior estimate value of the temperature state at the current moment based on the state transition matrix, and obtain the temperature prediction result of the current time step; Perform measurement update, receive the temperature data measured by the sensor, and correct the temperature prediction result based on the measurement error model to obtain the optimal temperature estimate value; Adjust the gain parameter, calculate the optimal filtering gain based on the covariance matrix of the current temperature estimate, and dynamically adjust the weight parameter of the Kalman filter process to optimize the temperature estimation accuracy.

[0014] Preferably, the anomaly detection process of the fault detection module includes the following steps: Calculate the average temperature. Based on the temperature data over a period of time, calculate the historical average temperature of the cable joint; Calculate the temperature standard deviation. Based on the range of variation of the temperature data, calculate the standard deviation to characterize the amplitude of temperature fluctuations; Dynamically adjust the alarm threshold. According to the average temperature and the standard deviation, set alarm thresholds at different levels to determine abnormal temperature conditions; Perform anomaly detection. Compare the current temperature with the calculated alarm threshold. When the temperature exceeds the set threshold, generate an alarm signal of the corresponding level.

[0015] A surface temperature sensor, comprising: A temperature sensing unit for detecting the surface temperature of the cable joint and converting the temperature signal into an electrical signal or an optical signal for output; A signal conversion unit for converting the temperature signal output by the temperature sensing unit into a digital signal recognizable by the data processing module; A communication interface unit for transmitting the converted temperature data to the data processing module.

[0016] The present invention provides a surface temperature sensor and a cable joint temperature monitoring system. It has the following beneficial effects: 1. The present invention adopts an optimized technical solution combining Fourier transform and dimensionality reduction calculation, realizing efficient processing and analysis of temperature data. Compared with the existing solution that directly calculates based on time-domain data, this solution greatly reduces the computational complexity, avoids redundant calculations, improves the system response speed, and is particularly efficient in a large-scale data processing environment.

[0017] 2. Through the technical solution of dynamic threshold calculation and anomaly detection, the present invention enables fault detection to be adaptively adjusted according to environmental and load changes. Different from the traditional fixed-threshold judgment method, this solution can effectively reduce false alarms and improve the detection accuracy, especially suitable for the complex scenarios of long-term operation of cable joints.

[0018] 3. The present invention introduces sliding window analysis and trend judgment, which not only considers instantaneous temperature changes but also combines historical data for comprehensive analysis. Compared with the existing method that only relies on single-point temperature overlimit judgment, this solution can more accurately identify anomalies, solves the problems of high false positive rate and inability to identify progressive faults, and provides a more scientific basis for preventive maintenance.

[0019] 4. The present invention adopts a hierarchical alarm mechanism, which can trigger alarms at different levels according to the severity of temperature anomalies and supports linkage with external systems. In the prior art, there is usually only a simple over-temperature alarm, lacking hierarchical early warning capabilities. The present invention effectively improves the flexibility of fault handling, ensuring that maintenance personnel can take corresponding measures more timely and accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the system architecture of the present invention; Figure 2 It is a schematic diagram of the surface temperature sensor architecture of the present invention; Figure 3 It is a schematic diagram of the data processing module architecture of the present invention; Figure 4 It is a schematic diagram of the temperature modeling module architecture of the present invention; Figure 5 It is a schematic diagram of the optimization estimation module architecture of the present invention; Figure 6 It is a schematic diagram of the calculation optimization module architecture of the present invention; Figure 7 It is a schematic diagram of the fault detection module architecture of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Next, in conjunction with the accompanying drawings of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] Please refer to the attached Figure 1 - attached Figure 7 , the embodiments of the present invention provide a surface temperature sensor and a cable joint temperature monitoring system, including: A surface temperature sensor for obtaining the temperature data of the cable joint and transmitting the data to the data processing module; Specifically, the surface temperature sensor is one of the key components in the cable joint temperature monitoring system, responsible for real-time detection of the temperature change on the surface of the cable joint, and converting the collected temperature signal into a digital signal for subsequent modules to analyze and process. The surface temperature sensor is the basis of the entire monitoring system, playing the role of sensing the temperature change of the cable joint and providing initial data. The quality of its performance directly affects the accuracy of subsequent data processing, modeling, and prediction.

[0023] In this embodiment, the surface temperature sensor can be implemented by a variety of technologies, such as thermocouple technology, infrared sensing technology, or other sensor technologies that can measure the surface temperature in real time. Generally, the temperature sensor is directly installed on the surface of the cable joint to ensure that its temperature is highly consistent with that of the cable joint, so as to accurately reflect the change in the joint temperature.

[0024] Temperature sensing unit: Specifically, the temperature sensing unit in the surface temperature sensor is responsible for sensing the temperature of the cable joint surface. In some embodiments, this sensing unit can adopt thermocouple sensors, thermistors (NTC or PTC), infrared sensors, etc. Each sensor has its characteristics and applicable scenarios. For higher precision and response speed requirements, an infrared temperature sensor is preferably used. The infrared sensor can measure the temperature without contact, which is especially suitable for applications in high-voltage environments and avoids possible contact failures during the measurement of the cable joint surface temperature.

[0025] In other embodiments, when a thermocouple sensor is adopted, the sensor generates an electromotive force according to the temperature difference, and converts this electromotive force into temperature data through a built-in signal conversion circuit. The measurement range of the thermocouple is wide and stable, which is suitable for large-range temperature detection.

[0026] Signal conversion unit: Specifically, the signal conversion unit of the surface temperature sensor converts the analog signal detected by the temperature sensing unit into a digital signal for further analysis and processing by the subsequent data processing module. Specifically, the analog signal is sent to an analog-to-digital converter (ADC), and then converted into a data format suitable for digital processing. The accuracy and conversion rate in this process are crucial for the response speed of the entire system. Usually, an ADC chip with high precision and fast response characteristics is selected.

[0027] As an option, the signal conversion unit can be designed as an integrated module, which integrates the temperature sensing and signal conversion circuits inside to achieve direct conversion and output of the signal, reducing the interference and design complexity of the external circuit.

[0028] Communication interface unit: In this embodiment, the communication interface unit of the surface temperature sensor is responsible for transmitting the converted temperature data to the data processing module. The communication interface can adopt various protocols, such as I2C, SPI, RS485, CAN, etc. The specific selection depends on the requirements of the cable joint temperature monitoring system and the network architecture.

[0029] In some embodiments, the communication interface unit may also include wireless communication functions (such as Bluetooth, Wi-Fi, Zigbee, etc.), which are especially suitable for scenarios where remote monitoring of the cable joint temperature is required. This design can avoid physical connection problems in the cable joint environment and improve the flexibility and adaptability of the system.

[0030] In practical applications, the temperature signals measured by the surface temperature sensor may be affected by various factors, such as external environmental temperature fluctuations, electromagnetic interference, etc. To ensure the accuracy of temperature measurement, some error processing techniques are adopted in this embodiment, including temperature drift compensation, noise filtering, etc. Specifically, the signal processing module will denoise and smooth the temperature signals output by the sensor to further improve the reliability of the data.

[0031] For example, the temperature signal may be affected by electromagnetic interference during the measurement process, resulting in signal fluctuations. At this time, the signal can be filtered by the Kalman filter algorithm to eliminate high-frequency noise and retain the effective temperature change information. In addition, temperature drift is also one of the factors affecting the accuracy of the sensor. Therefore, the temperature compensation function of the sensor can correct the drift caused by long-term use within a certain range.

[0032] In this embodiment, the data output by the sensor should have high precision. To achieve this, the surface temperature sensor needs to use high-precision thermocouples, infrared sensors, etc., with low measurement errors. Generally, the accuracy of the sensor should meet the error range of ±0.5°C. In some special applications, higher accuracy requirements may require the use of higher-precision sensors or further improve the measurement accuracy through methods such as multi-point measurement and data fusion.

[0033] During the temperature sensing process, the temperature sensor has good response characteristics to the temperature changes on the surface of the cable joint. To minimize the hysteresis effect of the temperature sensor as much as possible, the contact area between the sensor and the cable joint is designed to be large, thus ensuring a fast and accurate temperature response.

[0034] The data processing module is used to receive the temperature data from the surface temperature sensor, store and format the received temperature data, remove invalid data, and preliminarily screen out outliers. Specifically, the data processing module plays a core role in the cable joint temperature monitoring system. Its main function is to receive the temperature data from the surface temperature sensor, store, preprocess, format the data, and screen out abnormal data, ensuring that only valid temperature data is transmitted to the subsequent analysis and modeling modules. The data processing module is not only the entry point of the data stream but also a key link to ensure the accuracy and performance of the subsequent modules.

[0035] In the data processing module, first, the temperature data receiving unit receives the temperature signals from the temperature sensor. These temperature signals may be affected by interference such as noise and drift, so they need to be effectively processed. During the data storage and preprocessing stage, the module will perform formatting, remove invalid data, and preliminarily screen out outliers to ensure the quality of the data for subsequent processing.

[0036] Data receiving unit: Specifically, the temperature data receiving unit is responsible for receiving the original temperature data transmitted by the surface temperature sensor and passing it to the data storage unit. Usually, the received temperature signal will first be converted into a digital signal and a simple error detection will be performed. In general, the signal output by the sensor is an analog signal, which is converted into a digital signal by an analog-to-digital converter (ADC) and then enters the data receiving unit.

[0037] The data receiving unit may also include a signal decoding module that can process the data packet structure, communication protocol, etc. of the temperature sensor to facilitate subsequent data processing. In some embodiments, the design of the data receiving unit also takes into account the delay and interference problems in signal transmission, and adopts noise suppression technology to ensure the quality of the received signal.

[0038] Data storage unit: Specifically, the data storage unit is used to store all received temperature data. In order to ensure the continuity and reliability of the stored data, the data storage unit usually uses an efficient and reliable storage device, such as a flash memory, an external hard disk or a memory array. The data storage unit has a large storage capacity and can support a large amount of temperature data storage, while also having fast reading and writing functions.

[0039] Specifically, the data storage unit not only needs to store the original temperature data, but also needs to store information about the sensor, the sensor's calibration data, and the intermediate data generated during the processing process. The storage process uses a timestamp to associate each data point with time to facilitate subsequent analysis and tracing.

[0040] In some embodiments, in order to prevent data loss, the data storage unit can be designed as a redundant structure (such as RAID technology) to ensure data integrity through a data backup mechanism. Such a design can further improve the reliability of the system in harsh working environments.

[0041] Data preprocessing unit: Specifically, the data preprocessing unit is a very important link in this embodiment. It is mainly responsible for the preliminary cleaning and filtering of the received temperature data. During the temperature sensor data transmission process, the data may be inaccurate or incomplete due to environmental factors, sensor failure or external interference. The core task of the data preprocessing unit is to eliminate these invalid data and ensure that the valid data enters the subsequent modeling and analysis modules.

[0042] Specifically, the data preprocessing unit can achieve data cleaning through the following steps: Formatting: Convert temperature data from different sources into a unified format. This process includes unit unification, data structure adjustment, etc., so that subsequent analysis can be processed in a unified manner.

[0043] Invalid data elimination: By setting appropriate thresholds, some unreasonable data are removed. For example, if the temperature value at a certain time point is abnormally low or high, it may indicate a sensor failure, and the data preprocessing unit will eliminate it.

[0044] Outlier screening: By setting certain rules, significantly abnormal data are screened out. Common outlier screening techniques include statistical methods (such as mean and standard deviation judgment) or anomaly detection methods based on machine learning algorithms.

[0045] In some embodiments, the data preprocessing unit may also adopt more advanced data correction algorithms. For example, the Kalman filter can correct data with certain noise, thereby improving the accuracy of the data.

[0046] After data preprocessing, the processed data will be formatted to ensure that the subsequent data modeling module can read and use these data efficiently and accurately. During the data formatting process, mainly through standardization steps, data in different formats are converted into a data structure suitable for input into the model.

[0047] For example, all temperature data will be converted to floating data types, and auxiliary data such as timestamps and sensor IDs will be appended to facilitate the subsequent establishment of the temperature distribution model and the analysis of the fault detection module.

[0048] The data after data formatting will be transmitted to the temperature modeling module through network protocols or interfaces. The output of data formatting is not only the temperature value, but also additional information such as possible identifiers and location data to ensure accurate docking between modules.

[0049] The temperature modeling module is used to calculate the temperature distribution of the cable joint based on the heat conduction model, combine the valid data output by the temperature data preprocessing module, and establish a temperature distribution model of the cable joint through the heat conduction equation; Specifically, the temperature modeling module plays a crucial role in the cable joint temperature monitoring system. Its main task is to calculate the temperature distribution inside the cable joint based on the heat conduction model and the temperature data of the cable joint. Through precise temperature modeling, the temperature changes of the cable joint under different working conditions can be predicted, providing more reliable temperature estimation data. This module provides key data support for subsequent modules such as fault detection and temperature warning.

[0050] In this embodiment, the temperature modeling module first uses the heat conduction modeling unit to establish a temperature distribution model of the cable joint in combination with factors such as external environmental conditions, material properties, and internal current. The establishment of the model is discretized through the numerical solution of the heat conduction equation to obtain the temperature values of the cable joint at different time and spatial positions. This process is based on certain physical principles to ensure the accuracy of temperature modeling.

[0051] Heat conduction modeling unit: Specifically, the task of the heat conduction modeling unit is to calculate the temperature distribution of the cable joint based on the heat conduction equation. Generally, the temperature of the cable joint is affected by factors such as the external environmental temperature, the current in the joint, and the resistance of the cable. Therefore, when modeling the temperature, the heat source term needs to be considered first. This part is mainly the Joule heat generated when the current passes through the cable joint.

[0052] The heat conduction equation can generally be expressed as: Where: T(x, t) represents the temperature at position x and time t; α is the thermal diffusivity, which represents the heat conduction ability of the material; is the second spatial derivative of the temperature, representing the spatial distribution of the temperature; Q(x, t) is the heat source term, representing the Joule heat caused by the current.

[0053] In some embodiments, the heat source term Q(x, t) can be calculated by the following formula: Q(x, t) = I 2 R(x, t); Where: I is the current intensity;; R(x, t) is the resistance value at position x and time t.

[0054] In the specific implementation, the heat source term of the cable joint changes with the change of the current. Therefore, the heat source term also needs to be dynamically adjusted over time for accurate modeling.

[0055] Discretization calculation unit: In order to solve the heat conduction equation, the temperature modeling module uses a discretization calculation unit to transform the heat conduction equation into a numerical calculation problem. The discretization process uses the Finite Difference Method (FDM) to numerically solve the heat conduction equation. This method discretizes the continuous temperature field in space and time to obtain an approximate solution composed of discrete points.

[0056] Specifically, the discretization of the heat conduction equation in space and time can be expressed as: Where: represents the temperature at position i and time step n; represents the temperature at position i and time step n + 1; represents the temperature at position i + 1 and time step n; represents the temperature at position i - 1 and time step n; Δt is the time step; Δx is the spatial step; is the heat source term at position i and time step n; α is the thermal diffusivity.

[0057] Through the above discretization steps, the change of the temperature field within each time step can be approximately calculated. This calculation process requires selecting appropriate time steps and spatial steps according to the accuracy requirements in actual applications to ensure the accuracy of the calculation results.

[0058] Boundary condition setting unit: The setting of boundary conditions is a very important part of the heat conduction model, which directly affects the accuracy of temperature modeling. For cable joints, the main boundary conditions include the heat exchange between the joint and the external environment. In general, the convective heat transfer between the cable joint and the outside is the most common boundary condition.

[0059] The boundary condition of convective heat transfer can be expressed by the following formula: q conv =h(T env -T cable ); Where: q conv is the convective heat transfer amount; h is the heat conduction coefficient, representing the heat exchange ability between the joint and the environment; T env is the external environment temperature; T cable is the surface temperature of the cable joint.

[0060] The setting of boundary conditions is not limited to convective heat transfer, and may also include factors such as radiative heat transfer and contact thermal resistance. The specific boundary conditions need to be adjusted according to the actual installation environment of the cable joint.

[0061] During the temperature modeling process, it is necessary to consider both the steady-state temperature distribution and the transient temperature change of the cable joint. The steady-state temperature distribution refers to the temperature distribution when the system reaches thermal equilibrium after the cable joint has been operating for a long time, while the transient temperature distribution is the process in which the temperature gradually changes over time when the cable joint starts to work.

[0062] For the steady-state temperature distribution, it can be obtained by solving the steady-state solution of the above heat conduction equation. In the steady state, the temperature no longer changes with time, the time term in the equation disappears, and the heat source term also tends to be a constant.

[0063] For the transient temperature distribution, it is necessary to gradually solve the temperature change of the cable joint through discretized calculations until the system reaches the steady state. The transient modeling process usually requires a long calculation time. Therefore, when designing, it is necessary to consider the balance between calculation efficiency and accuracy.

[0064] Optimization estimation module, used to filter noise from temperature data and provide more accurate temperature estimation, optimizing the effectiveness of sensor measurement data; Specifically, the optimization estimation module is used to improve the accuracy and reliability of the cable joint temperature monitoring system. The main task of this module is to perform noise filtering on the received temperature data and further provide a more accurate temperature estimate. The optimization estimation module processes the data to remove unnecessary noise and reduce errors, thereby improving the accuracy of subsequent model calculations.

[0065] Specifically, the optimization estimation module combines Kalman filtering technology and state space modeling methods. By dynamically estimating and real-time updating the temperature data, the system can better adapt to environmental changes and sensor errors. In this way, this module can extract effective temperature data from noisy signals and provide stable and reliable temperature estimates for subsequent modeling modules.

[0066] State space modeling unit: In this embodiment, the main task of the state space modeling unit is to construct a state space model for cable joint temperature estimation. Generally, the state space model can provide the necessary input for the Kalman filtering algorithm by establishing a set of equations describing the dynamic changes of the cable joint temperature. The basic form of the state space model can be expressed as: x k = Ax k-1 + Bu k + w k ; y k = Cx k + v k ; Where: x k represents the system state vector, which is the temperature state of the cable joint in the present invention; A is the state transition matrix, describing the dynamic evolution of the system state; B is the input matrix, indicating the influence of the control input on the system state; u k is the control input (for example, factors such as current, external environmental temperature, etc.); w k is the process noise, describing the uncertainty in the system dynamics; y k is the actual measurement value, that is, the temperature data measured by the sensor; C is the observation matrix, mapping the system state to the measurement data; v k is the observation noise, indicating the error in the measurement process.

[0067] In this model, the change of the temperature state is affected by the control input, and the state at each moment can be predicted based on the state of the previous moment. In this embodiment, by accurately establishing this state space model, the system can update the temperature estimate of the cable joint at each time step, thereby improving the accuracy of temperature monitoring.

[0068] Kalman Filter Calculation Unit: In the Kalman filter calculation unit, the Kalman filter algorithm is used to update and optimize the temperature state in real time. The Kalman filter is a recursive algorithm that dynamically adjusts the estimation of the cable joint temperature by integrating sensor data and system models. At each time step, the Kalman filter gives the optimal temperature estimation result based on the prior estimation and actual measurement data.

[0069] The recursive steps of the Kalman filter can be divided into two stages: prediction and update. Prediction stage: Predict the next state and covariance of the system according to the state space model: Where: is the predicted state; is the predicted covariance matrix; u k is the control input (e.g., factors such as current, ambient temperature, etc.); Q is the process noise covariance, which reflects the uncertainty of the system dynamics in the model; A is the state transition matrix, which describes the dynamic evolution of the system state; is the state estimate at the previous moment, i.e., the system state estimate value at time k - 1; B is the input matrix, which represents the influence of the control input on the system state; P k-1 is the state covariance matrix at the previous moment, which describes the state uncertainty at time k - 1.

[0070] Update stage: Correct according to the actual measurement data: Where: K k is the Kalman gain; R is the observation noise covariance; y k is the actual measurement value; is the updated optimal estimate; is the predicted covariance matrix; C is the measurement matrix, which is used to map the state variables to the measurement space; predicted state estimate value; P k updated covariance matrix; I1 is the identity matrix.

[0071] Through the Kalman filter algorithm, the system can gradually correct the temperature estimation of the cable joint according to the temperature sensor data and model prediction results at each moment, and make the estimation value approach the true value, so as to achieve accurate temperature prediction.

[0072] Noise Adaptive Adjustment Unit: To further improve the accuracy of temperature estimation, a noise adaptive adjustment unit is adopted in this embodiment. The function of this unit is to dynamically adjust the noise parameters in the Kalman filter, especially the covariance matrices of the process noise and the observation noise. The noise adaptation can be achieved by methods such as Bayesian inference, and the noise estimation is dynamically optimized according to the real-time state of the system and the measurement error.

[0073] Specifically, the noise adaptive adjustment unit monitors the difference between the output of the system and the actual measurement value, judges the noise level in the system, and updates the process noise and the observation noise. This adaptive adjustment can effectively cope with the noise fluctuations caused by sensor failures, environmental changes, etc., and improve the robustness of the system in complex environments.

[0074] Calculation Optimization Module: It is used to accelerate the temperature prediction calculation, combining the temperature distribution model output by the temperature modeling module and the data processed by the optimization estimation module. Specifically, the calculation optimization module aims to improve the calculation efficiency of the cable joint temperature monitoring system, ensuring that the temperature prediction process can still be carried out quickly and accurately in a complex calculation environment. This module optimizes the calculation process, introduces efficient algorithms, and reduces the calculation complexity, making the output of the temperature prediction result more rapid and meeting the requirements of real-time monitoring. Through this optimized design, the system can process a large amount of data in a short time, provide a quick response, and thus effectively support the real-time temperature monitoring and fault warning functions.

[0075] The calculation optimization module mainly optimizes the calculation process through Fourier transform and dimensionality reduction calculation methods, combined with the inverse transform unit, making the prediction of the temperature distribution more accurate and achieving a better balance in calculation complexity.

[0076] Fourier Transform Calculation Unit: In this embodiment, the task of the Fourier transform calculation unit is to convert the temperature data in the time domain into frequency domain data. The changes of temperature data in the time domain often contain multiple frequency components. Using the Fourier transform can effectively separate these components, making the processing of temperature signals more efficient. The basic formula of the Fourier transform is: where: F(ω) is the temperature data represented in the frequency domain; f(t) is the temperature data in the time domain; ω is the frequency; e -iωt is the complex exponential function in the Fourier transform, which is used to project the time domain signal onto different frequency components.

[0077] After the Fourier transform converts the temperature signal from the time domain to the frequency domain, the analysis of the signal becomes more intuitive and efficient. In the temperature prediction process, the high-frequency components of many signals have no significant impact on the final result. Therefore, after the Fourier transform, the main frequency components can be screened out to reduce the calculation burden.

[0078] Dimensionality reduction calculation unit: Specifically, the dimensionality reduction calculation unit adopts the main Fourier component screening technology to screen out the frequency components that have a significant impact on temperature prediction, while ignoring those high-frequency components with less impact. Through this method, the amount of frequency-domain data required for calculation is greatly reduced, thereby improving the calculation efficiency of temperature prediction.

[0079] The specific process of dimensionality reduction can be achieved by setting thresholds for the frequency-domain data after Fourier transform to remove those components with low amplitude and low frequency. The dimensionality reduction calculation unit performs data dimensionality reduction through the following steps: Calculate Fourier coefficients: First, perform Fourier transform on the temperature data to obtain its frequency-domain expression; Set threshold: According to the characteristics of the temperature signal and calculation requirements, set a threshold to remove the frequency components below this threshold; Screen effective components: By screening the main Fourier components, only retain the frequency data that makes a significant contribution to the temperature prediction result; Reduce computational complexity: By reducing the amount of data to be processed, significantly reduce the computational complexity and improve the operation speed.

[0080] Through the dimensionality reduction method, this module can reduce unnecessary calculations, improve the system response speed, and ensure good real-time performance when processing multi-sensor data simultaneously.

[0081] Fast inverse transform unit: In this embodiment, the fast inverse transform unit is used to convert the frequency-domain data after dimensionality reduction processing back to the time domain to obtain the final temperature prediction result. The process of fast inverse transform is achieved through inverse Fourier transform, and the specific formula is: where: f(t) is the temperature data in the time domain; F(ω) is the temperature data represented in the frequency domain; ω is the frequency; e iωt is the complex exponential function in the Fourier transform, which is used to convert the frequency-domain signal back to the time domain.

[0082] Through this process, the screened frequency-domain data will be reconverted into time-domain temperature data for use by subsequent modules. Since the dimensionality of the frequency-domain data has been reduced through dimensionality reduction, the time-domain data after inverse transform will contain valid temperature information, and the calculation efficiency has been improved.

[0083] Generally, the calculation process of temperature prediction may be very complex, especially when the temperature distribution model requires a large amount of calculation. By introducing Fourier transform and the dimensionality reduction calculation unit, this module can significantly improve the calculation speed on the premise of ensuring calculation accuracy. Specifically, through Fourier transform, we convert the complex temperature data into a frequency-domain signal, which is convenient for effective screening and dimensionality reduction, thereby avoiding processing redundant data.

[0084] After the main Fourier components are screened out by the dimensionality reduction calculation unit, the complexity of the calculation is greatly reduced. With the cooperation of the fast inverse transform unit, the temperature prediction result can be output in a short time. Compared with the traditional time-domain processing method, this module not only improves the operation efficiency but also reduces data redundancy, enabling the system to maintain a higher response speed in real-time monitoring.

[0085] As an option, the calculation optimization module can also combine parallel computing or distributed computing technologies to further enhance the system's computing power. In some large-scale power systems, multi-threaded or distributed computing architectures can process computing tasks in parallel, greatly improving the system's processing ability and further meeting the requirements of real-time monitoring and prediction.

[0086] The fault detection module is used to judge whether there is an abnormal temperature change in the cable joint. Combining the prediction result of the temperature modeling module and the accurate data of the optimization estimation module, it generates an alarm signal to indicate that the temperature exceeds the standard or is abnormal.

[0087] Specifically, the fault detection module is mainly responsible for judging whether there is a temperature abnormality in the cable joint according to the data obtained from the temperature monitoring system. By combining the historical records and real-time data of the temperature data, the module can accurately identify potential fault problems such as over-temperature and rapid temperature changes, thereby generating an alarm signal to prompt relevant personnel for further inspection and maintenance. This module not only improves the system's response ability to faults but also provides a strong guarantee for the preventive maintenance of the cable joint.

[0088] The design of the fault detection module needs to efficiently combine historical data, real-time temperature data, and the set alarm threshold. Through comparison and analysis, it judges whether the temperature data is abnormal and triggers corresponding alarms according to the temperature change trend. This module is a crucial part of the entire system, ensuring that the cable joint can be monitored and warned in time during operation to avoid serious consequences caused by faults.

[0089] Threshold calculation unit: In this embodiment, the fault detection module first sets the temperature alarm threshold through the threshold calculation unit. Generally, the operating temperature of the cable joint has a certain range. When the temperature exceeds this range, problems such as cable overheating and damage may occur. Therefore, setting a reasonable alarm threshold is crucial for fault detection.

[0090] The setting of the temperature threshold is usually based on the operating specifications, environmental conditions, and historical data of the cable joint. In some embodiments, the alarm threshold may be a fixed value or can be dynamically adjusted according to real-time changes in environmental conditions, workload, etc. For example, when the current intensity increases, the temperature of the cable joint will rise, so the alarm threshold can be appropriately increased to cope with the temperature fluctuations caused by the increased load.

[0091] The threshold calculation can be carried out in the following way: T threshold = T nominal + k·σ; Where: T threshold represents the temperature threshold; T nominal is the normal operating temperature; σ is the standard deviation of the temperature, which is used to reflect the temperature fluctuation range; k is a coefficient to adjust the temperature fluctuation range..

[0092] The temperature threshold calculation unit can also set the alarm threshold according to the temperature fluctuation amplitude in the historical data, automatically adapting to the requirements of different cable joints and working environments.

[0093] Abnormality detection unit: After the temperature threshold calculation, the abnormality detection unit of the fault detection module is responsible for comparing the real-time acquired temperature data with the historical data to determine whether the current temperature exceeds the set threshold. Specifically, the abnormality detection unit will perform a difference analysis on the current temperature value and the temperature value at the previous moment. When the temperature change exceeds the preset threshold, it is judged as abnormal.

[0094] During the abnormality detection process, the natural range of temperature fluctuation also needs to be considered. For example, the temperature of the cable joint may fluctuate in a short period during operation, but these fluctuations do not necessarily mean a fault. Therefore, the abnormality detection unit needs to combine the short-term and long-term temperature trends to screen the temperature data to avoid false alarms.

[0095] In some embodiments, the abnormality detection unit adopts a sliding window algorithm. By grouping the temperature data by time period, it analyzes the temperature data within each time window to determine whether there is an abnormality. If the temperature data exceeds the set normal range or the change trend is abnormal, the system will immediately trigger the alarm mechanism.

[0096] The specific abnormality detection can be carried out through the following formula: ΔT k = |T k - T k-1 |; Where: ΔT k represents the temperature change value; T k represents the temperature at the current time point; T k-1 represents the temperature at the previous time point.

[0097] If ΔT k > T threshold , the system judges it as abnormal and triggers an alarm.

[0098] Alarm signal generation unit: When the anomaly detection unit determines that the temperature is abnormal, the alarm signal generation unit generates an alarm signal based on the set early warning strategy. Alarm signals can be divided into different levels, such as slightly exceeding the temperature standard, severely exceeding the temperature standard, etc. According to different alarm levels, the system can adopt different response strategies.

[0099] The alarm signal generation unit can also be connected to an external monitoring system or control system. After the fault detection module generates an alarm signal, the external system can receive it through wireless network or wired communication, timely reminding the operation and maintenance personnel to handle it. The alarm information generally includes information such as the fault type, occurrence location, and alarm level, facilitating the staff to quickly locate and take appropriate measures.

[0100] For example, when the temperature exceeds the set threshold, the alarm signal generation unit can trigger the device to shut down, start the automatic cooling system, or send an emergency notice to the maintenance personnel. Through this mechanism, the system can take timely measures to avoid accidents when overheating or other faults occur at the cable joint.

[0101] To improve the accuracy and real-time performance of fault detection, the fault detection module can also introduce an adaptive mechanism. Specifically, based on the operating historical data of the cable joint, the system can dynamically adjust the temperature threshold to ensure that the alarm threshold always conforms to the current working conditions.

[0102] In some embodiments, the system can also combine machine learning algorithms to automatically learn the change trend of temperature data and model the temperature fluctuations. Through this method, the fault detection module can maintain a high degree of accuracy in different working environments and reduce the occurrence of false alarms.

[0103] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A cable joint temperature monitoring system, characterized in that: include: A surface temperature sensor is used to obtain the temperature data of the cable joint and transmit the data to the data processing module; A data processing module, used to receive temperature data from a surface temperature sensor, store and format the received temperature data, remove invalid data, and preliminarily screen abnormal values; The temperature modeling module is used to calculate the temperature distribution of the cable joint based on the heat conduction model, combine the valid data output by the temperature data preprocessing module, and establish the temperature distribution model of the cable joint through the heat conduction equation; The optimization estimation module is used to filter the noise of temperature data and provide more accurate temperature estimation, optimizing the validity of sensor measurement data; The calculation optimization module is used to accelerate the temperature prediction calculation, combining the temperature distribution model output by the temperature modeling module and the data processed by the optimization estimation module; The fault detection module is used to determine whether there is abnormal temperature change in the cable joint. It combines the prediction results of the temperature modeling module and the accurate data of the optimization estimation module to generate an alarm signal to indicate that the temperature exceeds the standard or is abnormal.

2. A cable joint temperature monitoring system according to claim 1, characterized in that: The data processing module comprises: A temperature data receiving unit, used for receiving temperature data sent by the surface temperature sensor; A data storage unit, used for storing received temperature data; The data preprocessing unit is used to format the temperature data, remove invalid data and perform preliminary screening of abnormal values.

3. A cable joint temperature monitoring system according to claim 1, characterized in that: The temperature modeling module includes: Heat conduction modeling unit, used to establish the temperature distribution model of the cable joint based on the heat conduction equation; A discretization calculation unit, used for discretizing and solving the temperature model by using a finite difference method; The boundary condition setting unit is used to set the convection heat transfer boundary condition between the cable connector and the external environment.

4. A cable joint temperature monitoring system according to claim 1, characterized in that: The optimization estimation module comprises: A state space modeling unit for constructing a state space model for cable joint temperature estimation; A Kalman filter calculation unit, used for filtering the measurement data using an adaptive Kalman filter method; The noise adaptive adjustment unit is used to dynamically optimize the measurement noise parameters based on the Bayesian reasoning method.

5. A cable joint temperature monitoring system according to claim 1, characterized in that: The calculation optimization module includes: A Fourier transform calculation unit, used for performing frequency domain decomposition of temperature data based on a Fourier transform method; Dimensionality reduction calculation unit, used to filter the main Fourier components to reduce the calculation complexity; The fast inverse transform unit is used to convert the filtered frequency domain data back to the time domain temperature prediction results.

6. A cable joint temperature monitoring system according to claim 1, characterized in that: The fault detection module comprises: A threshold calculation unit, used for calculating a dynamic temperature alarm threshold; An anomaly detection unit, used to compare the current temperature with the calculated alarm threshold and determine whether an anomaly occurs; The alarm signal generating unit is used to trigger an alarm signal when the temperature exceeds a preset threshold.

7. A cable joint temperature monitoring system according to claim 1, characterized in that: The modeling process of the temperature modeling module includes the following steps: Establish a temperature distribution calculation model and calculate the spatial distribution of the temperature field inside the cable joint based on the thermal diffusion coefficient of the cable joint material; Calculate the heat source term, based on the current and contact resistance of the cable joint, calculate the Joule heat generated by the current passing through the cable joint, and input the heat into the temperature modeling model as a heat source; The steady-state and transient temperature distributions are solved. Based on the established heat conduction model, the steady-state temperature field and transient temperature change process of the cable joint are calculated respectively to obtain the temperature change of the cable joint under different working conditions.

8. A cable joint temperature monitoring system according to claim 1, characterized in that: The calculation process of the optimization estimation module includes the following steps: Perform prediction calculations, calculate the prior estimate of the temperature state at the current moment based on the state transfer matrix, and obtain the temperature prediction result of the current time step; Perform measurement updates, receive temperature data measured by the sensor, and correct the temperature prediction results based on the measurement error model to obtain the optimal temperature estimate; Adjust the gain parameters, calculate the optimal filter gain based on the covariance matrix of the current temperature estimate, and dynamically adjust the weight parameters of the Kalman filter process to optimize the temperature estimation accuracy.

9. A cable joint temperature monitoring system according to claim 1, characterized in that: The abnormality detection process of the fault detection module includes the following steps: Calculate the temperature average. Based on the temperature data over a period of time, calculate the historical temperature average of the cable joint; Calculating the temperature standard deviation, based on the variation range of the temperature data, calculating the standard deviation to characterize the temperature fluctuation amplitude; Dynamically adjust the alarm threshold, set different levels of alarm thresholds according to the temperature mean and standard deviation to determine temperature abnormalities; Perform anomaly detection, compare the current temperature with the calculated alarm threshold, and generate an alarm signal of the corresponding level when the temperature exceeds the set threshold.

10. A surface temperature sensor, applied to a cable joint temperature monitoring system according to any one of claims 1 to 9, characterized in that: include: The temperature sensing unit is used to detect the surface temperature of the cable connector and convert the temperature signal into an electrical signal or an optical signal for output; A signal conversion unit, used for converting the temperature signal output by the temperature sensing unit into a digital signal that can be recognized by a data processing module; The communication interface unit is used to transmit the converted temperature data to the data processing module.

Images