Information management service system
By building a sensor network for engineering wells, cables and distribution room, and combining edge computing and cloud servers for data fusion and prediction models, the real-time and data utilization efficiency of the information management system are solved, and efficient equipment status monitoring and early warning are achieved.
Patent Information
- Application Number
- CN202510408765.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-02
- Publication Date
- 2025-07-25
AI Technical Summary
The existing information management systems of work wells, cables and distribution rooms have problems such as poor real-time performance, incomplete data, lack of collaborative analysis and early warning mechanisms for independent storage, and low data utilization efficiency, resulting in high energy consumption and lagging response.
The sensing network is built using well sensor components, cable sensor components, distribution room sensor components, edge computing gateways and cloud servers to perform data fusion and real-time processing, and equipment status adjustment and early warning are combined with prediction models.
Real-time data collection and processing is realized, comprehensiveness and reliability of detection is improved, cloud transmission delay is reduced, closed-loop control is formed, and real-time performance and energy efficiency of equipment operation are improved.
Smart Images
Figure CN120378446A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of information management systems, and more particularly to an information management service system. Background Art
[0002] The management of manhole information mainly involves the operation and maintenance, safety monitoring and data management of underground facilities (such as power wells, communication wells, oil and gas wells, etc.). Regarding the combination of cable and substation monitoring functions, there are few publicly available related technologies. In this industry, there are drawbacks in the signal management of manholes and the collection and collation of substation monitoring data. The user side cannot obtain relevant information in a timely and intuitive manner, and a large amount of manpower is required to sort out and classify the above-mentioned complex data. The demand for such an information management system is very obvious.
[0003] During the process of substation monitoring, a certain electricity customer cannot timely detect the faults of electrical equipment during the power consumption process, and the measures for the power consumption situation are very lagging. Often, many days have passed after the problem is discovered, and under the existence of faults, the power consumption is huge and no adjustment or regulation has been made, resulting in high energy consumption and serious waste of resources.
[0004] It is found that the above technologies have at least the following problems:
[0005] 1. The collected information is relatively limited, and it cannot be well combined with the power consumption data of the substation. The cable environment data is collected singly, and it cannot provide more reliable judgment results and corresponding measures. Traditional manhole monitoring relies on manual inspections, resulting in poor real-time performance and incomplete data.
[0006] 2. The data analysis and processing method is not optimized enough, so that the data utilization and results cannot help the user. The user spends a lot of time and effort in processing data, with low efficiency. The environment control of the distribution room relies on fixed threshold control, with high energy consumption and lagging response.
[0007] 3. The existing cable monitoring methods mainly focus on off-line detection, and cannot monitor the cable aging and partial discharge in real time. The manhole, cable, and distribution monitoring data are stored independently, lacking a collaborative analysis and early warning mechanism. Summary of the Invention
[0008] In order to solve the above technical problems and deficiencies: how to improve the information collection and data processing and analysis capabilities and apply them to multiple scenarios, the present invention provides an information management service system.
[0009] To achieve the above object and other related objects, the present invention adopts the following technical solutions:
[0010] An information management service system includes a manhole sensor assembly, a cable sensor assembly, a distribution room sensor assembly, an edge computing gateway, a cloud server, and a user terminal. The manhole sensor assembly includes a water level sensor, a gas concentration sensor for detecting CO2 and H2S, and a manhole temperature and humidity sensor.
[0011] The cable sensor assembly includes a high-frequency current transformer and an acoustic wave sensor for monitoring partial discharge and vibration of the cable.
[0012] The distribution room sensor assembly includes an SF6 gas sensor, a smoke sensor, and a distribution room temperature and humidity sensor.
[0013] The edge computing gateway connects the manhole sensor assembly, the cable sensor assembly, and the distribution room sensor assembly to obtain multi-party data, constructs a perception network, and provides it to the cloud server for collaborative processing. The cloud server connects to the user terminal to provide data services for the user terminal.
[0014] Preferably, the edge computing gateway aligns the time of the data collected by the manhole sensor assembly, the cable sensor assembly, and the distribution room sensor assembly, and processes the sensor data in real time.
[0015] Preferably, the data analysis performed by the cloud server includes:
[0016] When it is determined that the CO2 concentration in the manhole > 1% or the humidity > 85%, the following measure push is provided for the user terminal: automatically turn on the ventilation equipment; dynamically adjust the ventilation power in combination with the external environmental temperature;
[0017] Dynamically adjust the operation frequency of the air conditioner based on the SF6 gas concentration and the equipment temperature;
[0018] Based on the water level data and rainfall data, make a prediction and send in advance: warning information on the risk of waterlogging;
[0019] Based on the analysis of the partial discharge acoustic wave characteristics and load current, predict whether the cable insulation is broken down for early warning;
[0020] Based on the smoke concentration, temperature change rate, and SF6 detection analysis, achieve multi-parameter coupling early warning.
[0021] Preferably, the cloud server adjusts the ventilation power according to the external environmental temperature, including:
[0022] In the distribution room, when the temperature < 10°C, the power is reduced to 50%; when the temperature > 30°C, the power is increased to 120%;
[0023] When the SF6 concentration > 1000 ppm, start the exhaust system;
[0024] When the temperature of the transformer equipment in the distribution room > 45°C, the air conditioner switches to the maximum power.
[0025] When personnel activities are detected, the temperature set value is increased by 2°C.
[0026] Preferably, the water level sensor provides water level data, obtains rainfall data by accessing the local meteorological station API, normalizes the water level and rainfall data, calculates the water level change rate and rainfall accumulation value, selects the LSTM network model, trains with historical data, and determines the optimal warning threshold through the ROC curve. When the predicted values of the water level and rainfall are greater than the warning threshold, a warning is triggered.
[0027] Preferably, partial discharge signals are obtained through high-frequency current transformers, acoustic signals are obtained through acoustic sensors, load currents are obtained through current transformers in the distribution room, the partial discharge signals are denoised, the acoustic signals are subjected to FFT transformation, the discharge pulse amplitude, acoustic energy spectrum, and current harmonic content are extracted, a random forest classifier model is selected for training, self-learning is performed using cable aging sample data, and a warning is triggered when the failure probability is greater than the failure threshold.
[0028] Preferably, the smoke concentration is obtained through a smoke sensor, the temperature change rate is obtained through a distribution temperature and humidity sensor, whether there are SF6 decomposition products is obtained through an SF6 gas sensor, the smoke concentration and temperature change rate are smoothed, the smoke concentration growth rate and temperature change rate variance are calculated, a Bayesian network model is selected for data training, the data used for training comes from historical test data, the warning threshold is determined to be 0.9, and a warning is triggered when it is greater than 0.9.
[0029] Preferably, the outer layer of the cable insulation in the manhole is made of a self-healing special layer. The preparation steps of the self-healing special layer include: mixing tetraethyl orthosilicate, ethanol, and ammonia water in a weight ratio of 5:20:1, hydrolyzing to generate SiO2 sol, adding an ionic liquid as the core material, forming microcapsules through ultrasonic emulsification, and mixing the microcapsules into the material at a ratio of 1wt% when the cable insulation layer is extruded to ensure uniform distribution.
[0030] Preferably, the user terminal is used to display power transformation and distribution monitoring data, power consumption management data, meter reading management data, line loss statistics data, power consumption classification statistics data, load management data, alarm and warning data, and user data.
[0031] In summary, the present invention includes at least one of the following beneficial technical effects:
[0032] 1. Sensors collect data in real time, and the edge computing gateway (node) performs local processing, reducing cloud transmission latency;
[0033] 2. Integrate data from manholes, cables, and distribution rooms, construct a data analysis model, and realize real-time state mapping;
[0034] 3. Adjust the device operating status based on the prediction model, and at the same time trigger an early warning by combining real-time data to form a closed-loop control. Brief Description of the Drawings
[0035] Figure 1 It is a system block diagram of an embodiment of the present invention.
[0036] Description of the reference numerals: 100, manhole sensor assembly; 200, cable sensor assembly; 300, substation sensor assembly; 400, edge computing gateway; 500, cloud server; 600, user terminal. Detailed Embodiments
[0037] The following uses specific specific examples to illustrate the implementation manners of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.
[0038] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. The diagrams only show the components related to the present invention rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be changed arbitrarily, and the component layout type may also be more complex.
[0039] The following further describes the specific implementation manners of the present invention in conjunction with the drawings.
[0040] Embodiment 1:
[0041] An information management service system includes a manhole sensor assembly 100, a cable sensor assembly 200, a substation sensor assembly 300, an edge computing gateway 400, a cloud server 500, and a user terminal 600. The manhole sensor assembly 100 includes a water level sensor, a gas concentration sensor for detecting CO2 and H2S, and a manhole temperature and humidity sensor. The cable sensor assembly 200 includes a high-frequency current transformer and an acoustic wave sensor for monitoring partial discharge and vibration of the cable; the substation sensor assembly 300 includes an SF6 gas sensor, a smoke sensor, and a substation temperature and humidity sensor; the edge computing gateway 400 is connected to the manhole sensor assembly 100, the cable sensor assembly 200, and the substation sensor assembly 300 to obtain multi-party data, construct a perception network, and provide it to the cloud server 500 for collaborative processing. The cloud server 500 is connected to the user terminal 600 to provide data services for the user terminal 600.
[0042] In a specific example, the water level sensor can be a high-precision radar water level gauge (such as VEGAPULS 69), with a measurement range of 0 - 5m, an accuracy of ±2mm, and is suitable for the humid environment of the manhole. The gas concentration sensors can be CO2 sensors (such as SenseAir S8) and H2S sensors (such as CityTech 7000 series) based on the electrochemical principle, with a response time < 30 seconds. The temperature and humidity sensor can be an SHT40 sensor, with a temperature accuracy of ±0.2°C and a humidity accuracy of ±2%RH. Sensor for partial discharge of cables: Use a high-frequency CT (such as Powertech HFCT-50), with a bandwidth of 10MHz - 500MHz and a sensitivity > 1mV / mA. The acoustic wave sensor can be a piezoelectric acoustic wave sensor (such as PCB Piezotronics 352C22), with a frequency range of 20Hz - 100kHz. The edge computing gateway 400 device (module) uses an NVIDIA Jetson Nano edge computing module, equipped with a 4-core ARM A57 CPU and a 128-core Maxwell GPU. It integrates a 4G / 5G communication module (such as Quectel EP06-E) to support real-time data transmission.
[0043] The manhole sensor assembly 100 is installed in the middle of the well wall. The cable sensor assembly 200 is deployed in groups every 50m along the cable path to ensure signal coverage.
[0044] The edge computing gateway 400 aligns the time of the data collected by the manhole sensor assembly 100, the cable sensor assembly 200, and the distribution room sensor assembly 300, and processes the sensor data in real time.
[0045] Specifically, in an instance, the data analysis by the cloud server 500 includes:
[0046] When it is determined that the CO2 concentration in the well > 1% or the humidity > 85%, the measures pushed to the user terminal 600 are: automatically turn on the ventilation equipment; dynamically adjust the ventilation power in combination with the external environmental temperature; dynamically adjust the air conditioner operation frequency based on the SF6 gas concentration and the equipment temperature; make predictions based on the water level data and rainfall data and send in advance: early warning of the risk of waterlogging; predict whether the cable insulation is broken down and give an early warning based on the partial discharge acoustic wave characteristics and load current analysis; achieve multi-parameter coupling early warning based on the smoke concentration, temperature change rate, and SF6 detection analysis.
[0047] The following specifically describes the above functions:
[0048] The cloud server 500 adjusts the ventilation power according to the external environmental temperature, including:
[0049] In the power distribution room, when the temperature < 10°C, the power drops to 50%; when the temperature > 30°C, the power increases to 120%; when the SF6 concentration > 1000 ppm, the exhaust system is started; when the temperature of the transformer equipment in the power distribution room > 45°C, the air conditioner switches to the maximum power; when personnel activities are detected, the temperature set value is increased by 2°C. Detecting personnel activities can be based on the detection of an infrared sensor. When human activities are sensed, an induction signal will be triggered to determine whether there are personnel activities. Because when there are people in the power distribution room, the ambient temperature will increase, reducing the probability of false alarm triggering, so the temperature set value can be appropriately adjusted and increased. In a specific example, this solution increases the temperature by 2°C.
[0050] In a specific example, a water level sensor provides water level data, rainfall data is obtained by accessing the local weather station API, the water level and rainfall data are normalized, the water level change rate and rainfall cumulative value are calculated, an LSTM network model is selected (input dimension 2: water level data, rainfall data, hidden layer nodes 64, output dimension 1: warning value), trained using historical data, the best warning threshold is determined through the ROC curve or can be set by the user himself. When the predicted values of the water level and rainfall are greater than the warning threshold, a warning is triggered. In this example, a warning is triggered when the warning value after predicting the water level and rainfall > 0.8. The process is as follows: Real-time collect water level and rainfall data. Input into the LSTM model for prediction, and output the water level value in the next 2 hours. Combine with the predicted rainfall value to calculate the comprehensive risk index. If the risk index > 0.8, send a warning message to the client.
[0051] In a specific example, partial discharge signals are obtained through high-frequency current transformers, acoustic signals are obtained through acoustic sensors, load currents are obtained through current transformers in the power distribution room, the partial discharge signals are denoised, the acoustic signals are subjected to FFT transformation, the discharge pulse amplitude, acoustic energy spectrum, and current harmonic content are extracted, a random forest classifier model is selected (number of features 3: partial discharge signals, acoustic signals, load current signals, number of trees 100) for training, self-learning is carried out using cable aging sample data, and a warning is triggered when the failure probability is greater than the failure threshold. A warning is triggered when the failure probability > 0.7.
[0052] Preferably, the smoke concentration is obtained through a smoke sensor, the temperature change rate is obtained through a power distribution temperature and humidity sensor, whether there are SF6 decomposition products is obtained through an SF6 gas sensor, the smoke concentration and temperature change rate are smoothed, the smoke concentration growth rate and temperature change rate variance are calculated, a Bayesian network model is selected for data training, the data used for training comes from historical test data, the warning threshold is determined to be 0.9, and a warning is triggered when it is greater than 0.9.
[0053] Example 2:
[0054] Based on the above solution, the outer cable insulation layer in the manhole adopts a self-healing specific layer. The preparation steps of the self-healing specific layer include: mixing tetraethyl orthosilicate, ethanol, and ammonia water in a weight ratio of 5:20:1, hydrolyzing to generate SiO2 sol, adding ionic liquid as the core material, forming microcapsules through ultrasonic emulsification, and when extruding and molding the cable insulation layer, mixing the microcapsules into the material at a ratio of 1 wt%, ensuring uniform distribution. Ionic liquid ([EMIM][TFSI] mixture) is a molten salt composed of cations and anions. It has a low vapor pressure and is a special solvent. 1-ethyl-3-methylimidazolium bis(trifluoromethylsulfonyl)imide ([Emim][TFSI]) is used as the core material. When the ultrasonic sensor detects a partial discharge signal (amplitude > 50 mV), it is determined as an insulation defect. When the electric field strength at the defect > 3 kV / mm, the capsule shell breaks down, and the ionic liquid seeps out to fill the microcracks. The ionic liquid is oriented under the electric field to form a conductive path, reducing the local field strength and increasing the discharge inception voltage from 15 kV to 19.5 kV. In this way, it can be detected and sensed. The [EMIM]+ cations in the ionic liquid undergo surface adsorption with the thermoelectric thin film, reducing the interfacial thermal resistance. In a specific example, the temperature of the cable in the manhole rises to 65 °C due to overload. The output power of the thermoelectric thin film on the cable increases, and the edge node (edge computing gateway 400) activates the high-frequency sampling mode. The temperature data triggers power distribution reconstruction, shunting 20% of the load to the redundant line. After the load is reduced, the cable vibration weakens, and the piezoelectric power generation (discharge) decreases.
[0055] The user terminal 600 is used to display power transformation and distribution monitoring data, power consumption management data, meter reading management data, line loss statistics data, power consumption classification statistics data, load management data, alarm and warning data, and user data.
[0056] The above embodiments merely illustrate the principles and effects of the present invention, rather than limiting the present invention. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.
Claims
1. An information management service system, comprising a manhole sensor assembly, a cable sensor assembly, a distribution room sensor assembly, an edge computing gateway, a cloud server, and a user terminal, characterized in that The manhole sensor assembly includes a water level sensor, gas concentration sensors for detecting CO2 and H2S, and a manhole temperature and humidity sensor. The cable sensor assembly includes a high-frequency current transformer and an acoustic wave sensor, which are used to monitor partial discharge and vibration of the cable. The switchgear sensor assembly includes an SF6 gas sensor, a smoke sensor, and a switchgear temperature and humidity sensor. The edge computing gateway connects to the manhole sensor assembly, the cable sensor assembly, and the switchgear sensor assembly to obtain multi-party data, construct a perception network, and provide it to the cloud server for collaborative processing. The cloud server connects to the user side to provide data services for the user side.
2. The information management service system according to claim 1, characterized in that The edge computing gateway performs time alignment on the data collected by the manhole sensor assembly, the cable sensor assembly, and the switchgear sensor assembly, and processes the sensor data in real time.
3. An information management service system according to claim 2, wherein, The data analysis performed by the cloud server includes: When it is determined that the CO2 concentration in the well is >1% or the humidity is >85%, the measures pushed to the user side are: automatically turn on the ventilation equipment; dynamically adjust the ventilation power in combination with the external environmental temperature. Dynamically adjust the operating frequency of the air conditioner based on the SF6 gas concentration and the equipment temperature. Based on the water level data and rainfall data, make a prediction and send in advance: early warning information on the risk of waterlogging. Based on the analysis of the partial discharge acoustic wave characteristics and the load current, predict whether the cable insulation is broken down and give an early warning. Based on the smoke concentration, the temperature change rate, and the SF6 detection analysis, realize multi-parameter coupling early warning.
4. An information management service system according to claim 3, characterized in that, The cloud server adjusts the ventilation power according to the external environmental temperature, including: In the switchgear, when the temperature <10°C, the power is reduced to 50%; when the temperature >30°C, the power is increased to 120%. When the SF6 concentration >1000 ppm, start the exhaust system. When the temperature of the transformer equipment in the switchgear >45°C, the air conditioner switches to the maximum power. When human activities are detected, the temperature set value is increased by 2°C.
5. An information management service system according to claim 3, characterized in that, The water level sensor provides water level data, obtains rainfall data by accessing the API of the local meteorological station, normalizes the water level and rainfall data, calculates the water level change rate and the rainfall cumulative value, selects the LSTM network model, trains with historical data, determines the best early warning threshold through the ROC curve, and triggers an early warning when the predicted values of the water level and rainfall are greater than the early warning threshold.
6. An information management service system according to claim 3, wherein, Obtain the partial discharge signal through the high-frequency current transformer, obtain the acoustic wave signal through the acoustic wave sensor, obtain the load current through the current transformer in the switchgear, denoise the partial discharge signal, perform FFT transformation on the acoustic wave signal, extract the discharge pulse amplitude, the acoustic wave energy spectrum, and the current harmonic content, select the random forest classifier model for training, perform self-learning using the cable aging sample data, and trigger an early warning when the failure probability is greater than the failure threshold.
7. An information management service system according to claim 4, characterized in that, Obtain the smoke concentration through the smoke sensor, obtain the temperature change rate through the switchgear temperature and humidity sensor, obtain whether there are SF6 decomposition products through the SF6 gas sensor, smooth the smoke concentration and the temperature change rate, calculate the smoke concentration growth rate and the temperature change rate variance, select the Bayesian network model for data training, the data used for training comes from historical test data, determine the early warning threshold as 0.9, and trigger an early warning when it is greater than 0.
9.
8. An information management service system according to claim 1, wherein The outer insulating layer of the cable in the manhole adopts a self-healing specific layer. The preparation steps of the self-healing specific layer include: mixing tetraethyl orthosilicate, ethanol, and ammonia water in a weight ratio of 5:20:1, hydrolyzing to generate SiO2 sol, adding an ionic liquid as the core material, forming microcapsules through ultrasonic emulsification, and when the cable insulating layer is extruded and formed, mixing the microcapsules into the material at a ratio of 1 wt%, ensuring uniform distribution.
9. An information management service system according to claim 1, wherein The user terminal is used to display power transformation and distribution monitoring data, power consumption management data, meter reading management data, line loss statistical data, power consumption classification statistical data, load management data, alarm and early warning data, and user data.