Switch cabinet with built-in intelligent management and control system

Abstract

The invention relates to a switch cabinet with a built-in intelligent management and control system, through integration of a sensor network module, a data acquisition module, an intelligent processing module, a remote monitoring module and an active safety protection module, conversion from passive maintenance to active management and control is realized, and the switch cabinet is equipped with various sensors, so that the operation state of equipment can be monitored in real time; historical data are generated through timestamp records, and the intelligent processing module predicts the service life and the fault risk of the equipment in real time by applying a health management algorithm and a deep learning algorithm, identifies different fault modes and sends out an alarm signal; the active safety protection module comprises an electric power cut-off device, a temperature overrun protection unit and an emergency power supply unit, and can quickly cut off a power supply or start a cooling measure when abnormal parameters are detected, so that the equipment safety is ensured; and the intelligent level and the reliability of the switch cabinet are improved.

Description

Technical Field

[0001] The invention relates to a switch cabinet with a built-in intelligent management and control system. Background Art

[0002] With the popularization of power systems and automation equipment, switchgear has become one of the core equipment in the fields of power systems, industrial automation, communications and building power distribution, used to provide power control and distribution. Traditional switchgear mainly relies on manual monitoring and regular maintenance. However, this model has the following technical defects and limitations: Traditional switchgear usually ensures the normal operation of equipment through regular maintenance and manual inspections. This method cannot grasp the internal status of the equipment in real time. For example, equipment overload, abnormal temperature and humidity, current fluctuations and other conditions may have no obvious external characteristics in the early stages before a major failure occurs, resulting in equipment overheating, line failure or fire risks. The risk cannot be warned in time. In addition, there are often hidden dangers of local discharge and vibration in the switchgear. These factors will have a serious impact on the stability and safety of the equipment after long-term operation. The traditional method that lacks real-time monitoring and data collection can no longer meet the needs of modern power equipment.

[0003] Since traditional switchgear lacks intelligent analysis capabilities, the assessment of equipment status is mainly based on manual records and empirical judgments, and accurate fault prediction and management are impossible. With the complexity of power systems and the diversification of equipment operating environments, it is difficult to ensure the safe operation of equipment by relying on traditional regular maintenance and empirical predictions, which often results in waste of maintenance resources and accumulation of potential risks. Existing technologies lack effective methods for fault prediction and management through equipment operation data modeling and combined with intelligent algorithms, resulting in difficulty in timely detection and response measures when potential hidden dangers occur.

[0004] Therefore, technical personnel in this field need a switch cabinet with an integrated multi-modular system to achieve real-time monitoring, intelligent analysis and fault prediction of equipment status, and a built-in intelligent management and control system with active safety protection and remote monitoring functions. Summary of the invention

[0005] The purpose of the present invention is to solve the above shortcomings of the prior art and provide a switch cabinet with a built-in intelligent management and control system. By integrating a sensor network, an intelligent analysis algorithm and an active protection device, the switch cabinet has intelligent management and control capabilities, realizing the transition from passive maintenance to active management and control:

[0006] On the one hand, a switch cabinet with a built-in intelligent management and control system includes a sensor network module, a data acquisition module, an intelligent processing module, a remote monitoring module and an active safety protection module. The sensor network module includes a sensor unit, which is arranged in the switch cabinet. The sensor unit includes a temperature and humidity sensor, a current sensor, a smoke sensor, a partial discharge sensor and a vibration sensor. The sensor network module also includes a timestamp recording unit, which is connected to each sensor and is used to add a timestamp to each collected data and generate historical data; the data acquisition module is connected to the sensor network module, and the data acquisition module is used to receive the data collected by the sensor network module and save it to the intelligent processing module; the intelligent processing module includes a health management algorithm unit, a deep learning algorithm unit and a data analysis unit, wherein the health management algorithm unit is based on the sensor network module The real-time data of the block generates an equipment operation status model, predicts equipment life and failure risk, and transmits the results to the remote monitoring module; the deep learning algorithm unit constructs a multidimensional feature model based on historical data to identify different failure modes, generate corresponding alarm signals, and transmit the results to the remote monitoring module; the data analysis unit is used to generate a switch cabinet operation report and transmit the results to the remote monitoring module; the active safety protection module includes a power cut-off device, a temperature over-limit protection unit and an emergency power supply unit, wherein the power cut-off device is connected to the intelligent processing module, and is used to disconnect the power supply of the switch cabinet when the intelligent processing module receives abnormal sensor parameters; the temperature over-limit protection unit is used to trigger the cooling device when the intelligent processing module receives an internal temperature exceeding a preset threshold; the emergency power supply unit is used to provide continuous power to the sensor network module, the data acquisition module and the communication module in the event of a power outage.

[0007] Furthermore, the health management algorithm unit realizes multi-dimensional parameter estimation of the equipment operation state through dynamic state space modeling, and the dynamic state space model is expressed as:

[0008] Among them, X t is the state vector, representing the various parameters collected by the sensor unit, U t is the external input disturbance variable, A, B, C, D are the state transfer matrix and observation matrix, W t 、V tThey represent process noise and measurement noise respectively; the health management algorithm unit adopts dynamic state space modeling, which aims to perform multi-dimensional parameter estimation of the equipment operation status through real-time monitoring data. The setting of this model includes state vector and external input interference variables. Combined with the state transfer matrix and the observation matrix, it can effectively capture the changing law of the equipment state. Through this model, it is possible to accurately describe and predict the dynamic behavior of the system, improve the accuracy of fault prediction, and ensure that maintenance measures are taken in time before potential faults occur, which solves the problem of insufficient state recognition ability of traditional methods in dynamic environments.

[0009] Furthermore, the deep learning algorithm unit constructs a time series model based on a long short-term memory network and calculates based on the following formula: in, is the output of the long short-term memory network model, y t is the actual output, θ is the model parameter vector, λ is the regularization coefficient, and the model parameter vector is gradually updated through the back propagation algorithm and the gradient descent algorithm. The update formula is: Among them, η is the learning rate; the deep learning algorithm unit uses a long short-term memory network to construct a time series model for processing and analyzing historical data to identify potential fault modes. The long short-term memory network can effectively capture the long-term dependency of data and overcome the shortcomings of traditional RNN in sequence data processing. The model parameters are gradually updated through the back propagation algorithm and the gradient descent algorithm, which realizes the accurate identification of complex fault modes and generates alarm signals, improves the system's adaptability and response speed, and can improve the intelligence level of the switchgear without relying on a lot of manual experience.

[0010] Furthermore, the stability evaluation of the switch cabinet operation report generated by the data analysis unit is performed by the following distributed variational Bayesian algorithm, assuming Represents the data set, and the evaluation function is: in, represents the hypothesized model, z j represents latent variables; the data analysis unit evaluates the stability of the switch cabinet operation report through the distributed variational Bayesian algorithm. The set evaluation function can combine various data sets to process and analyze the complexity of the equipment operation status. This method provides an effective way to infer latent variables and evaluate the reliability of the hypothetical model, providing more accurate suggestions for equipment maintenance, avoiding maintenance errors caused by insufficient data analysis, and ensuring efficient and stable operation of the equipment.

[0011] Furthermore, the power cut-off device dynamically adjusts the cut-off condition according to the fuzzy logic control rule, and the fuzzy control function is: Among them, μ C(x) is the membership of the cut-off command, x is the sensor parameter, α and x0 are the adjustment coefficient and critical point respectively. The fuzzy membership is used to determine whether to trigger the cut-off operation to adapt to the volatility of environmental parameters. The power cut-off device is dynamically adjusted according to the fuzzy logic control rules so that the cut-off conditions can adapt to the volatility of environmental parameters. The fuzzy control function provides a flexible and efficient dynamic response mechanism by evaluating the membership of the cut-off command, combining the sensor parameters and their adjustment coefficients and critical points, which solves the problem of slow response of traditional cut-off systems when facing uncertainty.

[0012] Furthermore, the temperature over-limit protection unit adopts an adaptive predictive control algorithm to adjust the triggering condition of the cooling device, and the trigger prediction function is:

[0013] in, is the predicted temperature at the next moment, T t is the current temperature, m is the backtracking time, ∈ t The error term is used, and the prediction model parameters are dynamically updated through the recursive least squares algorithm to ensure that the cooling device is accurately triggered under temperature fluctuations. The temperature over-limit protection unit adopts an adaptive predictive control algorithm, which can adjust the triggering conditions of the cooling device in real time. The prediction model parameters are dynamically updated through the recursive least squares algorithm. The system can accurately trigger the cooling device under temperature fluctuations, thereby effectively preventing equipment overheating.

[0014] Furthermore, the emergency power supply unit adopts a residual power state transfer model based on a Markov chain, and the model state transfer equation is: P(E t+1 =k|E t =i)=p ij , where R t is the power state at time t, p ij The probability of transitioning from state i to state j is calculated by solving the state transfer matrix to estimate the remaining power time of the emergency power supply, so as to optimize the emergency power supply strategy and ensure the continuous operation of the module; the emergency power supply unit uses the remaining power state transfer model based on the Markov chain to estimate the remaining power time of the emergency power supply by solving the state transfer matrix, so that the switch cabinet can dispatch the power supply more effectively when the power is insufficient, optimize the emergency power supply strategy, and ensure continuous operation in emergency situations.

[0015] On the other hand, a method for using a switch cabinet with a built-in intelligent management and control system includes the following steps: a sensor network module continuously generates data, and the data is transmitted to an intelligent processing module in real time through a data acquisition module; the intelligent processing module generates an equipment operation status model to predict failure risks, and identifies abnormal patterns through algorithms, generates corresponding alarm signals and notifies operation and maintenance personnel; generates a switch cabinet operation report and transmits the results to a remote monitoring module; and the active safety protection module performs active safety protection based on the processing results of the intelligent processing module.

[0016] Furthermore, after the active safety protection module performs active safety protection according to the processing result of the intelligent processing module, the active safety protection module further includes the step of generating a switch cabinet operation report, wherein the switch cabinet operation report includes a status assessment and maintenance suggestions.

[0017] Beneficial effects: Accurate equipment health management and fault prediction are achieved through a variety of data collection and learning algorithms; integrated power cut-off devices, over-temperature protection units and emergency power supply units can achieve rapid response to sudden current fluctuations or temperature anomalies, ensuring the safety and continuity of equipment; by integrating various modules, the intelligent management and control capabilities of the switchgear are improved, and the transition from passive maintenance to active management and control is achieved, which improves the safety of equipment and the convenience of maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the system structure of a switch cabinet with a built-in intelligent control system;

[0019] Figure 2 This is a schematic diagram of how to use a switch cabinet with a built-in intelligent management and control system. DETAILED DESCRIPTION

[0020] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with embodiments and drawings. The embodiments are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0021] Please see Figure 1A switch cabinet with a built-in intelligent management and control system includes a sensor network module, a data acquisition module, an intelligent processing module, a remote monitoring module and an active safety protection module. The sensor network module includes a sensor unit, which is arranged in the switch cabinet. The sensor unit includes a temperature and humidity sensor, a current sensor, a smoke sensor, a partial discharge sensor and a vibration sensor. The sensor network module also includes a timestamp recording unit, which is connected to each sensor and is used to add a timestamp to each collected data and generate historical data; the data acquisition module is connected to the sensor network module, and the data acquisition module is used to receive the data collected by the sensor network module and save it to the intelligent processing module; the intelligent processing module includes a health management algorithm unit, a deep learning algorithm unit and a data analysis unit, wherein the health management algorithm unit is based on the actual The deep learning algorithm unit constructs a multidimensional feature model based on historical data to identify different failure modes, generate corresponding alarm signals and transmit the results to the remote monitoring module; the data analysis unit is used to generate a switch cabinet operation report and transmit the results to the remote monitoring module; the active safety protection module includes a power cut-off device, a temperature over-limit protection unit and an emergency power supply unit, wherein the power cut-off device is connected to the intelligent processing module, and is used to disconnect the power supply of the switch cabinet when the intelligent processing module receives abnormal sensor parameters; the temperature over-limit protection unit is used to trigger the cooling device when the intelligent processing module receives an internal temperature exceeding a preset threshold; the emergency power supply unit is used to provide continuous power to the sensor network module, the data acquisition module and the communication module in the event of a power outage.

[0022] The health management algorithm unit realizes multi-dimensional parameter estimation of the equipment operation status through dynamic state space modeling. The dynamic state space model is expressed as: Among them, X t is the state vector, representing the various parameters collected by the sensor unit, U t is the external input disturbance variable, A, B, C, D are the state transfer matrix and observation matrix, W t 、V t represent process noise and measurement noise respectively.

[0023] The deep learning algorithm unit builds a time series model based on the long short-term memory network and is calculated based on the following formula: in, is the output of the long short-term memory network model, y t is the actual output, θ is the model parameter vector, λ is the regularization coefficient, and the model parameter vector is gradually updated through the back propagation algorithm and the gradient descent algorithm. The update formula is:

[0024] Among them, η is the learning rate.

[0025] The stability evaluation of the switchgear operation report generated by the data analysis unit is performed using the following distributed variational Bayesian algorithm. Represents the data set, and the evaluation function is:

[0026] in, represents the hypothesized model, z j represents a hidden variable.

[0027] The power cut-off device dynamically adjusts the cut-off conditions according to the fuzzy logic control rules. The fuzzy control function is: Among them, μ C (x) is the membership of the cut-off command, x is the sensor parameter, α and x0 are the adjustment coefficient and critical point respectively. The fuzzy membership is used to determine whether to trigger the cut-off operation to adapt to the volatility of environmental parameters.

[0028] The temperature over-limit protection unit uses an adaptive predictive control algorithm to adjust the triggering conditions of the cooling device. The trigger prediction function is: in, is the predicted temperature at the next moment, T t is the current temperature, m is the backtracking time, ∈ t The error term is used, and the prediction model parameters are dynamically updated through the recursive least squares algorithm to ensure that the cooling device is accurately triggered in the case of temperature fluctuations.

[0029] The emergency power supply unit adopts a residual power state transfer model based on a Markov chain. The model state transfer equation is: P(E t+1 =k|E t =i)=p ij , where E t is the power state at time t, p ij The probability of transitioning from state i to state j is calculated by solving the state transition matrix to estimate the remaining power time of the emergency power supply, so as to optimize the emergency power supply strategy and ensure the continuous operation of the module.

[0030] Please see Figure 2 A method for using a switch cabinet with a built-in intelligent management and control system includes the following steps: a sensor network module continuously generates data, and the data is transmitted to an intelligent processing module in real time through a data acquisition module; the intelligent processing module generates an equipment operation status model to predict the risk of failure, and identifies abnormal patterns through an algorithm, generates corresponding alarm signals and notifies operation and maintenance personnel; generates a switch cabinet operation report and transmits the result to a remote monitoring module; an active safety protection module performs active safety protection according to the processing result of the intelligent processing module; generates a switch cabinet operation report, and the switch cabinet operation report includes a status evaluation and maintenance suggestions.

[0031] For the purpose of greater clarity, the invention is described in detail through the following examples.

[0032] In a specific embodiment, the external dimensions of the switch cabinet are: height 1800mm×width 800mm×depth 600mm; the shell is made of cold-rolled steel plate with a thickness of 2.0mm and an anti-rust coating is sprayed on the surface; the temperature and humidity sensor model is DHT22, with a measuring range of -40℃~80℃ and an accuracy of ±0.5℃; the current sensor: model ACS712, measuring range ±5A, sensitivity 185mV / A; the smoke sensor: model MQ-2, sensitivity 300ppm~10000ppm; the partial discharge sensor: type: ultrasonic partial discharge sensor, frequency range 20kHz~100kHz; the vibration sensor: model ADXL345, measuring range ±16g, accuracy 0.04g; the data acquisition module: adopts STM32 microcontroller, sampling frequency 1Hz.

[0033] In a specific embodiment, the operating frequency of the health management algorithm unit is 100Hz; the deep learning algorithm unit uses the Keras framework, based on the LSTM model, and the input feature dimension is 10; the data analysis unit generates reports once every 5 minutes; the active safety protection module includes a power cut-off device: rated voltage 380V, current 10A; temperature over-limit protection unit: trigger threshold 85℃; emergency power supply unit: lithium battery, capacity 12V7Ah.

[0034] The following is a specific implementation method:

[0035] The switch cabinet is installed on site at the power station to ensure that the sensor units are evenly distributed inside the cabinet in order to comprehensively monitor the equipment status; the switch cabinet power is turned on, the sensor network module is initialized, and data collection begins; the data collection module receives sensor data in real time and saves it to the intelligent processing module; the intelligent processing module generates an equipment operation status model based on real-time data and predicts the risk of failure; the health management algorithm unit performs multi-dimensional parameter estimation based on dynamic state space modeling to understand the equipment's operating status in real time; during the fault simulation process, when the system detects that the internal temperature exceeds 85°C, the temperature over-limit protection unit triggers the cooling device and sends an alarm signal to the remote monitoring module; if the current sensor detects that the current exceeds the set threshold, the power cut-off device immediately cuts off the switch cabinet power supply to ensure equipment safety; after data collection is completed, the data analysis unit generates a switch cabinet operation report every 5 minutes, including status assessment and maintenance recommendations, and transmits the results to the remote monitoring module.

[0036] Over-temperature fault handling: In the simulated over-temperature situation, the system can issue an early warning when the temperature reaches 82°C. After the cooling device is started, the temperature drops to 78°C within 2 minutes, successfully avoiding equipment damage.

[0037] Abnormal current processing: When the current simulation reaches 12A, the power cut-off device cuts off the power supply, and the response time is less than 200ms, ensuring the safety of the equipment.

[0038] Operation report: During the 72-hour operation test, the system successfully recorded and analyzed 12 abnormal situations and generated a detailed operation report, providing an important reference for subsequent maintenance.

[0039] Through this embodiment and example, it can be seen that the switch cabinet with a built-in intelligent management and control system of the present invention has significant advantages in equipment monitoring, fault handling and data analysis, and effectively improves the safety and intelligence level of the equipment.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A switch cabinet with a built-in intelligent management and control system, characterized in that: It includes a sensor network module, a data acquisition module, an intelligent processing module, a remote monitoring module and an active safety protection module. The sensor network module includes a sensor unit, which is arranged in the switch cabinet. The sensor unit includes a temperature and humidity sensor, a current sensor, a smoke sensor, a partial discharge sensor and a vibration sensor. The sensor network module also includes a timestamp recording unit, which is connected to each sensor and is used to add a timestamp to each collected data and generate historical data; the data acquisition module is connected to the sensor network module, and the data acquisition module is used to receive the data collected by the sensor network module and save it to the intelligent processing module; the intelligent processing module includes a health management algorithm unit, a deep learning algorithm unit and a data analysis unit, wherein the health management algorithm unit generates an equipment operation status model based on the real-time data of the sensor network module, predicts the equipment life and failure risk and transmits the results to the remote monitoring module; the deep learning algorithm unit constructs a multidimensional feature model based on historical data to identify different failure modes, generate corresponding alarm signals and transmit the results to the remote monitoring module; the data analysis unit is used to generate a switch cabinet operation report and transmit the results to the remote monitoring module; The active safety protection module includes a power cut-off device, an over-temperature protection unit and an emergency power supply unit, wherein the power cut-off device is connected to the intelligent processing module and is used to disconnect the power supply of the switch cabinet when the intelligent processing module receives abnormal sensor parameters; the over-temperature protection unit is used to trigger the cooling device when the intelligent processing module receives an internal temperature exceeding a preset threshold; the emergency power supply unit is used to provide continuous power to the sensor network module, the data acquisition module and the communication module in the event of a power outage.

2. A switch cabinet with a built-in intelligent management and control system according to claim 1, characterized in that: The health management algorithm unit realizes multi-dimensional parameter estimation of the equipment operation status through dynamic state space modeling, and the dynamic state space model is expressed as: Among them, X t is the state vector, representing the various parameters collected by the sensor unit, U t is the external input disturbance variable, A, B, C, D are the state transfer matrix and observation matrix, W t 、V t represent process noise and measurement noise respectively.

3. The switch cabinet with a built-in intelligent management and control system according to claim 1, characterized in that: The deep learning algorithm unit constructs a time series model based on the long short-term memory network and calculates based on the following formula: in, is the output of the long short-term memory network model, y t is the actual output, θ is the model parameter vector, λ is the regularization coefficient, and the model parameter vector is gradually updated through the back propagation algorithm and the gradient descent algorithm. The update formula is: Among them, η is the learning rate.

4. The switch cabinet with a built-in intelligent management and control system according to claim 1, characterized in that: The stability evaluation of the switch cabinet operation report generated by the data analysis unit is performed by the following distributed variational Bayesian algorithm: Represents the data set, and the evaluation function is: in, represents the hypothesized model, z j represents a hidden variable.

5. The switch cabinet with a built-in intelligent management and control system according to claim 1, characterized in that: The power cut-off device dynamically adjusts the cut-off condition according to the fuzzy logic control rule, and the fuzzy control function is: Among them, μ C (x) is the membership of the cut-off command, x is the sensor parameter, α and x0 are the adjustment coefficient and critical point respectively. The fuzzy membership is used to determine whether to trigger the cut-off operation to adapt to the volatility of environmental parameters.

6. The switch cabinet with a built-in intelligent management and control system according to claim 1, characterized in that: The temperature over-limit protection unit adopts an adaptive predictive control algorithm to adjust the triggering condition of the cooling device, and the trigger prediction function is: in, is the predicted temperature at the next moment, T t is the current temperature, m is the backtracking time, ∈ t The error term is used, and the prediction model parameters are dynamically updated through the recursive least squares algorithm to ensure that the cooling device is accurately triggered in the case of temperature fluctuations.

7. The switch cabinet with a built-in intelligent management and control system according to claim 1, characterized in that: The emergency power supply unit adopts a residual power state transfer model based on a Markov chain, and the model state transfer equation is: P(E t+1 =k|E t =i)=p ij , where E t is the power state at time t, p ij The probability of transitioning from state i to state j is calculated by solving the state transition matrix to estimate the remaining power time of the emergency power supply, so as to optimize the emergency power supply strategy and ensure the continuous operation of the module.

8. A method for using a switch cabinet with a built-in intelligent management and control system, used to implement a switch cabinet with a built-in intelligent management and control system according to any one of claims 1 to 7, characterized in that: The method comprises the following steps: the sensor network module continuously generates data, and the data is transmitted to the intelligent processing module in real time through the data acquisition module; The intelligent processing module generates an equipment operation status model to predict the risk of failure, and identifies abnormal patterns through algorithms, generates corresponding alarm signals and notifies the operation and maintenance personnel; generates switch cabinet operation reports and transmits the results to the remote monitoring module; The active safety protection module performs active safety protection according to the processing results of the intelligent processing module.

9. The switch cabinet with a built-in intelligent management and control system according to claim 8, characterized in that: After the active safety protection module performs active safety protection according to the processing result of the intelligent processing module, the active safety protection module further includes the step of generating a switch cabinet operation report, wherein the switch cabinet operation report includes a status assessment and maintenance suggestions.

Images