Intelligent safety monitoring system and method for operating environment of power distribution cabinet
Through high-density sensor network and microclimate modeling technology, combined with intelligent control and multi-parameter fusion algorithm, accurate monitoring of the internal environment of the distribution cabinet and early fire warning are achieved, and incomplete monitoring and late fire warning in the existing technology are solved. The problem of the distribution cabinet improves the safety and reliability.
Patent Information
- Application Number
- CN202411097850.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing distribution cabinet operating environment monitoring system cannot comprehensively and accurately monitor the tiny environmental changes inside the distribution cabinet, especially local hot spots and humidity agglomerations, and the fire warning time is lagging, resulting in high system complexity and false alarm rate. , accurate adjustment cannot be achieved.
A high-density sensor network is used to monitor environmental parameters, simulate air flow and temperature and humidity distribution through microclimate modeling, identify potential hot spots and humidity agglomerations, dynamically adjust the local environment with an intelligent control system, and use multi-parameter fusion algorithm and machine learning model Analyze fire risks in real time, issue early warnings and initiate fire prevention measures.
It realizes accurate monitoring and adjustment of the local environment inside the distribution cabinet, early warning and effective fire prevention, and solves the problems of incomplete monitoring and lagging fire warning in the existing technology.
Smart Images

Figure CN119010341A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power distribution cabinet monitoring, and in particular to an intelligent safety monitoring system and method for the operating environment of a power distribution cabinet. Background Art
[0002] The distribution cabinet is divided into power distribution cabinet, lighting distribution cabinet and metering cabinet, which is the final equipment of the distribution system.
[0003] Chinese Patent Publication No.: CN114665611B discloses an intelligent monitoring and management system for the operation of a distribution cabinet based on data analysis, including a state monitoring module, an environmental analysis module, a cycle management module and a regularity analysis module, wherein the state monitoring module is communicatively connected with the environmental analysis module and the cycle management module; the state monitoring module is used to monitor, manage and analyze the operation state of the distribution cabinet and mark the monitored object as a normal object or an abnormal object, the state monitoring module sends the normal object and the overall analysis signal to the cycle management module, and the state monitoring module sends the abnormal object and the environmental analysis signal to the environmental analysis module; the present invention solves the problem that the existing distribution cabinet operation monitoring and management system cannot perform regularity analysis on a distribution cabinet with large fluctuations in the operation state, and can perform real-time monitoring of the operation state of the distribution cabinet, and timely issue an early warning when the operation of the distribution cabinet is abnormal.
[0004] The current distribution cabinet operating environment monitoring mainly relies on temperature and humidity sensors distributed in several key locations. This method cannot comprehensively and accurately monitor the tiny environmental changes inside the entire distribution cabinet, especially local hot spots and humidity concentration areas. In addition, the early warning system for distribution cabinet fires mainly relies on smoke and temperature sensors, which can often detect abnormalities only after the fire has developed to a certain extent, resulting in a delay in the warning time. At present, for such problems, the number of sensors and cooling equipment are usually increased to increase the monitoring coverage, and the early warning capability is improved by increasing the types and number of sensors, but this brings about system complexity and false alarm rate problems, and cannot achieve accurate adjustment of the local environment. Therefore, there is an urgent need for an intelligent safety monitoring system and method for the distribution cabinet operating environment to solve such problems. Summary of the invention
[0005] To this end, the present invention provides an intelligent safety monitoring system and method for the operating environment of a distribution cabinet, so as to overcome the problems in the prior art of being unable to comprehensively and accurately monitor the slight environmental changes inside the entire distribution cabinet, as well as the time lag of fire warning.
[0006] To achieve the above objectives, on the one hand, the present invention provides an intelligent safety monitoring system for the operating environment of a power distribution cabinet, comprising:
[0007] High-density sensor networks to monitor environmental parameters;
[0008] Microclimate monitoring module, which simulates the air flow and temperature and humidity distribution inside the distribution cabinet through the microclimate model, and identifies potential hot spots and humidity concentration areas;
[0009] Intelligent control system, used to dynamically adjust the local environment inside the power distribution cabinet;
[0010] Fire monitoring module, real-time analysis of environmental data change trends and identification of fire risks;
[0011] Intelligent early warning system, used to issue early fire warnings and initiate fire prevention measures.
[0012] On the other hand, the present invention also provides an intelligent safety monitoring method for the operating environment of a power distribution cabinet, comprising:
[0013] Step S1, high-density sensor network data monitoring, using high-density micro sensor nodes to collect real-time data, including environmental parameters such as temperature, humidity and gas concentration; the high-density micro sensor nodes are arranged inside the power distribution cabinet;
[0014] Step S2, multi-sensor data fusion, based on the environmental parameters collected in step S1, multi-sensor data fusion is performed, and the fused data is used for subsequent microclimate simulation and fire risk prediction;
[0015] Step S3, microclimate simulation, using CFD tools to establish a microclimate model inside the distribution cabinet, simulating the air flow and temperature and humidity distribution inside the distribution cabinet; based on the sensor data fused in step S2, the model is updated in real time, and potential hot spots and humidity concentration areas are identified through CFD simulation to guide the adjustment of the local environment;
[0016] Step S4, fire risk prediction, uses a multi-parameter fusion algorithm to analyze the change trend of environmental data in real time and predict fire risks in advance; uses a machine learning model to perform time series analysis on sensor data to identify potential fire risks; and establishes an environmental parameter change model, and verifies the analysis results through the principal component analysis PCA algorithm;
[0017] Step S5, local environment adjustment and fire warning, the intelligent control system dynamically adjusts the local environment based on the real-time data analysis results of step S4;
[0018] Furthermore, the data fusion step in step S2 includes:
[0019] Normalize and align the data. where x i,j represents the raw data of the i-th sensor at the j-th moment,
[0020] min(x i ) and max(x i) are the minimum and maximum values of the i-th sensor data, x' i,j is the normalized data;
[0021] x i (t) = ip(x i (t1),x i (t2),...,x i (t j )), where x i (t) is the alignment data of the i-th sensor at time t, x i (t j ) is the value of the ith sensor at time t j The original data, ip refers to the interpolation process;
[0022] The state space model fuses multi-sensor data. Assume that the system state x(t) is affected by the control input u(t) and process noise w(t), and the measured value z(t) is affected by the measurement noise v(t). The state equation is: x(t+1)=Ax(t)+Bu(t)+w(t), where x(t+1) is the system state vector at time t+1, including temperature, humidity, and gas concentration. A is the state transfer matrix, which represents the change of the system state. B is the control matrix, which represents the influence of the control input on the system state. u(t) is the control input vector, and w(t) is the process noise vector, which is set to zero-mean Gaussian white noise.
[0023] Observation equation: z(t)=Hx(t)+v(t), where z(t) is the measurement vector at time t, H is the observation matrix, which represents the influence of the system state on the measurement value, and v(t) is the measurement noise vector, which is set to zero-mean Gaussian white noise;
[0024] Furthermore, the data fusion step in step S2 also includes:
[0025] Use Kalman filtering to estimate the state space model, fuse multi-sensor data, and predict the steps: P(t|t-1)=AP(t-1|t-1)A T +Q, here is the prior state estimate at time t,
[0026] P(t|t-1) is the prior error covariance matrix at time t, Q is the process noise covariance matrix, A T represents the transpose of the state transfer matrix, represents the posterior state estimate at time t-1, u(t-1) represents the control input vector at time t-1, and P(t-1|t-1) is the posterior error covariance matrix at time t-1;
[0027] Update steps:
[0028] K(t)=P(t|t-1)H T (HP(t|t-1)H T +R) -1 ;
[0029]
[0030] P(t|t)=(IK(t)H)P(t|t-1), where K(t) is the Kalman gain matrix at time t, P(t|t-1) is the prior error covariance matrix at time t, H is the observation matrix, and R is the measurement noise covariance matrix; is the posterior state estimate at time t, z(t) is the measured value at time t, is the prior measurement estimate at time t, P(t|t) is the a posteriori error covariance matrix at time t, R is the measurement noise covariance matrix, and I is the identity matrix;
[0031] The data processed by Kalman filtering is used as the final fusion data;
[0032] Furthermore, the identification methods of hot spots and humidity concentration areas include:
[0033] Use CAD software to build a 3D geometric model of the power distribution cabinet, and use mesh generation tools to mesh the geometric model;
[0034] Define fluid properties and boundary conditions of the power distribution cabinet, including the temperature and convection heat transfer coefficient of the air inlet, air outlet, wall and equipment surface;
[0035] Use CFD tools to solve the continuity equation, momentum equation, and energy equation to obtain air flow and temperature distribution;
[0036] Calculate humidity distribution based on temperature distribution and air flow, and solve it using the humidity transfer equation;
[0037] Dynamically update the CFD model based on sensor data, identify potential hot spots and humidity concentration areas through CFD simulation results, and provide a basis for local environmental adjustment; Step 3 simulates the air flow and temperature and humidity distribution inside the distribution cabinet to provide important data support for subsequent environmental adjustment and fire risk prediction;
[0038] Furthermore, the microclimate simulation step performed in step S3 includes:
[0039] Construct the geometric model of the power distribution cabinet, including various devices and components inside the cabinet, and mesh the geometric model;
[0040] Set the physical properties of air, including density, viscosity, and thermal conductivity;
[0041] Define the boundary conditions of the power distribution cabinet, including air inlet, air outlet, wall and equipment surface;
[0042] Solve the Navier-Stokes equations, including:
[0043] Continuity equation: in represents the partial derivative of the fluid density ρ with respect to time t, ▽·(ρu) is the divergence of the fluid density and velocity u;
[0044] Momentum equation: in represents the partial derivative of velocity u with respect to time t multiplied by density ρ, u·▽u represents the dot product of velocity vector u and its gradient, -▽p is the pressure gradient, ▽·(μ▽u) is the viscous force term, representing momentum diffusion under viscosity, and f represents the volume force;
[0045] Energy equation: in represents the partial derivative of temperature T with respect to time t multiplied by density ρ and specific heat C p , u·▽T is the dot product of the temperature gradient and the velocity vector, ▽·(k▽T) represents the diffusion term of thermal conductivity k, and Φ is the viscous dissipation term;
[0046] Calculate humidity distribution, humidity transfer equation: in Indicates water vapor concentration C w The partial derivative with respect to time t, u·▽C w is the dot product of the water vapor concentration gradient and the velocity vector, D w ▽ 2 C w represents the diffusion term of water vapor in the air, ▽ 2 is the Laplace operator, ▽ is the Nabla operator;
[0047] Dynamically update the CFD model based on sensor data and identify potential hot spots and humidity concentration areas through CFD simulation results;
[0048] Furthermore, the fire risk prediction steps include:
[0049] Calculate the weighted sum of the comprehensive feature vectors to highlight important features;
[0050] Use historical data to train machine learning models for time series analysis;
[0051] Use trained machine learning models to detect anomalies in real-time data;
[0052] Assess fire risk based on anomaly scores and determine warning thresholds;
[0053] Trigger the early warning mechanism based on the risk assessment value, notify relevant personnel and initiate fire prevention measures;
[0054] Furthermore, the fire risk prediction method is to use a multi-parameter fusion algorithm to calculate the weighted sum of the comprehensive feature vector: where F j represents the comprehensive eigenvalue at time j, w i Represents the data weight of the i-th sensor, satisfying x' i,j represents the normalized data of the i-th sensor at time j;
[0055] Use historical data to train LSTM machine learning models for time series analysis;
[0056] Using the trained machine learning model, isolation forest is used to perform anomaly detection on real-time data: Here S(x) is the anomaly score, E(h(x)) represents the average path length of data point x, c(n) is the normalization factor, and n is the number of samples;
[0057] Assess fire risk based on anomaly scores and determine warning thresholds: Here R(t) represents the risk assessment value at time t, S(x j ) represents the anomaly score at time j, and N is the time window size;
[0058] Furthermore, the early warning mechanism in step S4 is: triggering the early warning mechanism according to the risk assessment value, notifying relevant personnel and initiating fire prevention measures, Here A l is the warning status (1 means triggering warning, 0 means normal), T d is the warning threshold;
[0059] Furthermore, in step S5, micro fans or local cooling devices are added in hot spots, and small dehumidifiers are added in areas with high humidity. Combined with the fuzzy logic control algorithm, the control strategy is automatically adjusted according to the sensor data to improve the regulation effect. The intelligent early warning system detects fire risks in advance based on real-time data and prediction results, issues early warnings and initiates fire prevention measures.
[0060] Compared with the prior art, the present invention has the following beneficial effects:
[0061] The present invention adopts a local environment control method based on microclimate modeling, utilizes microclimate modeling technology and a high-density micro-sensor network to achieve accurate monitoring and regulation of the local environment inside the power distribution cabinet;
[0062] High-density micro-sensor nodes are arranged inside the distribution cabinet to comprehensively monitor environmental parameters such as temperature, humidity and gas concentration. CFD tools are used to establish a microclimate model inside the distribution cabinet to simulate air flow and temperature and humidity distribution. The local environment is dynamically adjusted through real-time data analysis by the intelligent control system. Micro-fans or local cooling devices are added in hot spots, and small dehumidifiers are added in areas with high humidity to achieve precise adjustment.
[0063] The present invention adopts an intelligent fire warning method based on environmental parameters, adopts multi-dimensional environmental parameter monitoring technology and multi-parameter fusion algorithm to build an intelligent fire warning system to achieve early and accurate warning;
[0064] Use multi-parameter fusion algorithms to analyze the changing trends of environmental data in real time, predict fire risks in advance, conduct time series analysis of environmental data based on machine learning models, identify potential fire risks, and then detect fire risks in advance based on real-time data and prediction results, issue warnings and initiate fire prevention measures;
[0065] The problem that the existing technology cannot comprehensively and accurately monitor the tiny environmental changes inside the entire distribution cabinet and the time lag of fire warning is solved. BRIEF DESCRIPTION OF THE DRAWINGS
[0066] Figure 1 It is a flow chart of the intelligent safety monitoring method for the operating environment of the power distribution cabinet of the present invention;
[0067] Figure 2 It is a structural schematic diagram of the intelligent safety monitoring system for the operating environment of the power distribution cabinet of the present invention. DETAILED DESCRIPTION
[0068] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0069] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0070] The present invention is further described in detail below in conjunction with the accompanying drawings:
[0071] Example 1
[0072] See also Figure 1-Figure 2 The present invention provides an intelligent safety monitoring system for the operating environment of a power distribution cabinet:
[0073] High-density sensor networks to monitor environmental parameters;
[0074] Microclimate monitoring module, which simulates the air flow and temperature and humidity distribution inside the distribution cabinet through the microclimate model, and identifies potential hot spots and humidity concentration areas;
[0075] Intelligent control system, used to dynamically adjust the local environment inside the power distribution cabinet;
[0076] Fire monitoring module, real-time analysis of environmental data change trends and identification of fire risks;
[0077] Intelligent early warning system, used to issue early warning of fire and initiate fire prevention measures;
[0078] The present invention also provides an intelligent safety monitoring method for the operating environment of a power distribution cabinet:
[0079] Step S1, high-density sensor network data monitoring,
[0080] High-density micro-sensor nodes are used to collect real-time data, including environmental parameters such as temperature, humidity and gas concentration; high-density micro-sensor nodes are arranged inside the power distribution cabinet;
[0081] Specifically, by arranging high-density micro-sensor nodes inside the power distribution cabinet, key environmental parameters such as temperature, humidity and gas concentration are collected in real time, and multi-sensor data is comprehensively processed through state space model and Kalman filter to achieve highly accurate environmental parameter monitoring;
[0082] Step S2, multi-sensor data fusion,
[0083] Based on the environmental parameters collected in step S1, multi-sensor data fusion is performed, and the fused data is used for subsequent microclimate simulation and fire risk prediction;
[0084] The data fusion steps in step S2 include:
[0085] Normalize and align the data. where x i,j represents the raw data of the i-th sensor at the j-th moment,
[0086] min(x i ) and max(x i ) are the minimum and maximum values of the i-th sensor data, respectively, and x i,j is the normalized data;
[0087] x i (t) = ip(x i (t1),x i (t2),...,x i (t j )), where x i (t) is the alignment data of the i-th sensor at time t, x i (t j ) is the value of the ith sensor at time t j The original data, ip refers to the interpolation process;
[0088] The state space model fuses multi-sensor data. Assume that the system state x(t) is affected by the control input u(t) and process noise w(t), and the measured value z(t) is affected by the measurement noise v(t). The state equation is: x(t+1)=Ax(t)+Bu(t)+w(t), where x(t+1) is the system state vector at time t+1, including temperature, humidity, and gas concentration. A is the state transfer matrix, which represents the change of the system state. B is the control matrix, which represents the influence of the control input on the system state. u(t) is the control input vector, and w(t) is the process noise vector, which is set to zero-mean Gaussian white noise.
[0089] Observation equation: z(t)=Hx(t)+v(t), where z(t) is the measurement vector at time t, H is the observation matrix, which represents the influence of the system state on the measurement value, and v(t) is the measurement noise vector, which is set to zero-mean Gaussian white noise;
[0090] Use Kalman filtering to estimate the state space model, fuse multi-sensor data, and predict the steps: P(t|t-1)=AP(t-1|t-1)A T +Q, here is the prior state estimate at time t,
[0091] P(t|t-1) is the prior error covariance matrix at time t, Q is the process noise covariance matrix, A T represents the transpose of the state transfer matrix, represents the posterior state estimate at time t-1, u(t-1) represents the control input vector at time t-1, and P(t-1|t-1) is the posterior error covariance matrix at time t-1;
[0092] Update steps:
[0093] K(t)=P(t|t-1)H T (HP(t|t-1)H T +R) -1 ;
[0094]
[0095] P(t|t)=(IK(t)H)P(t|t-1), where K(t) is the Kalman gain matrix at time t, P(t|t-1) is the prior error covariance matrix at time t, H is the observation matrix, and R is the measurement noise covariance matrix; is the posterior state estimate at time t, z(t) is the measured value at time t, is the prior measurement estimate at time t, P(t|t) is the a posteriori error covariance matrix at time t, R is the measurement noise covariance matrix, and I is the identity matrix;
[0096] The data processed by Kalman filtering is used as the final fusion data;
[0097] Step S3, microclimate simulation,
[0098] Use CFD tools to establish a microclimate model inside the distribution cabinet to simulate the air flow and temperature and humidity distribution inside the distribution cabinet; update the model in real time based on the sensor data fused in step S2, identify potential hot spots and humidity concentration areas through CFD simulation, and guide the adjustment of the local environment;
[0099] Specifically, computational fluid dynamics (CFD) tools are used to build a detailed microclimate model inside the distribution cabinet to simulate air flow and temperature and humidity distribution. The hot spots and humidity concentration areas inside the distribution cabinet are identified and adjusted in real time by dynamically updating the CFD model. Combined with actual sensor data, the CFD simulation results provide a scientific basis for local environmental regulation, making the regulation measures more targeted and effective.
[0100] Hot spots and humidity concentration areas can be identified by:
[0101] Use CAD software to build a 3D geometric model of the power distribution cabinet, and use mesh generation tools to mesh the geometric model;
[0102] Define fluid properties and boundary conditions of the power distribution cabinet, including the temperature and convection heat transfer coefficient of the air inlet, air outlet, wall and equipment surface;
[0103] Use CFD tools to solve the continuity equation, momentum equation, and energy equation to obtain air flow and temperature distribution;
[0104] Calculate humidity distribution based on temperature distribution and air flow, and solve it using the humidity transfer equation;
[0105] Dynamically update the CFD model based on sensor data, identify potential hot spots and humidity concentration areas through CFD simulation results, and provide a basis for local environmental adjustment; Step 3 simulates the air flow and temperature and humidity distribution inside the distribution cabinet to provide important data support for subsequent environmental adjustment and fire risk prediction;
[0106] The microclimate simulation steps performed in step S3 include:
[0107] Construct the geometric model of the power distribution cabinet, including various devices and components inside the cabinet, and mesh the geometric model;
[0108] Set the physical properties of air, including density, viscosity, and thermal conductivity;
[0109] Define the boundary conditions of the power distribution cabinet, including air inlet, air outlet, wall and equipment surface;
[0110] Solve the Navier-Stokes equations, including:
[0111] Continuity equation: in represents the partial derivative of the fluid density ρ with respect to time t, ▽·(ρu) is the divergence of the fluid density and velocity u;
[0112] Momentum equation: in represents the partial derivative of velocity u with respect to time t multiplied by density ρ, u·▽u represents the dot product of velocity vector u and its gradient, -▽p is the pressure gradient, ▽·(μ▽u) is the viscous force term, representing momentum diffusion under viscosity, and f represents the volume force;
[0113] Energy equation: in represents the partial derivative of temperature T with respect to time t multiplied by density ρ and specific heat C p , u·▽T is the dot product of the temperature gradient and the velocity vector, ▽·(k▽T) represents the diffusion term of thermal conductivity k, and Φ is the viscous dissipation term;
[0114] Calculate humidity distribution, humidity transfer equation: in Indicates water vapor concentration C w The partial derivative with respect to time t, u·▽C w is the dot product of the water vapor concentration gradient and the velocity vector, D w ▽ 2 C w represents the diffusion term of water vapor in the air, ▽ 2 is the Laplace operator, ▽ is the Nabla operator;
[0115] Dynamically update the CFD model based on sensor data and identify potential hot spots and humidity concentration areas through CFD simulation results;
[0116] Step S4, fire risk prediction,
[0117] Use multi-parameter fusion algorithms to analyze environmental data change trends in real time and predict fire risks in advance; use machine learning models to perform time series analysis on sensor data to identify potential fire risks; and establish an environmental parameter change model, and verify the analysis results using the principal component analysis (PCA) algorithm;
[0118] Specifically, multi-parameter fusion algorithms and machine learning models are used to perform real-time analysis and anomaly detection on environmental data. Through time series analysis of the long short-term memory network (LSTM) machine learning model, the system can identify potential fire risks and issue early warnings. Principal component analysis (PCA) and the isolation forest algorithm further verify and evaluate abnormal data to improve the accuracy of fire risk prediction. The early warning mechanism is based on real-time risk assessment values, which can promptly notify relevant personnel and initiate fire prevention measures before a fire occurs, effectively preventing accidents.
[0119] The fire risk prediction steps include:
[0120] Calculate the weighted sum of the comprehensive feature vectors to highlight important features;
[0121] Use historical data to train machine learning models for time series analysis;
[0122] Use trained machine learning models to detect anomalies in real-time data;
[0123] Assess fire risk based on anomaly scores and determine warning thresholds;
[0124] Trigger the early warning mechanism based on the risk assessment value, notify relevant personnel and initiate fire prevention measures;
[0125] The fire risk prediction method is: use a multi-parameter fusion algorithm to calculate the weighted sum of the comprehensive feature vector: where Fj represents the comprehensive eigenvalue at time j, w i Represents the data weight of the i-th sensor, satisfying x' i,j represents the normalized data of the i-th sensor at time j;
[0126] Use historical data to train LSTM machine learning models for time series analysis;
[0127] Using the trained machine learning model, isolation forest is used to perform anomaly detection on real-time data: Here S(x) is the anomaly score, E(h(x)) represents the average path length of data point x, c(n) is the normalization factor, and n is the number of samples;
[0128] Assess fire risk based on anomaly scores and determine warning thresholds: Here R(t) represents the risk assessment value at time t, S(x j ) represents the anomaly score at time j, and N is the time window size;
[0129] The early warning mechanism in step S4 is: triggering the early warning mechanism according to the risk assessment value, notifying relevant personnel and initiating fire prevention measures, Here A l is the warning status (1 means triggering warning, 0 means normal), T d is the warning threshold;
[0130] Step S5: local environment adjustment and fire warning.
[0131] The intelligent control system dynamically adjusts the local environment based on the real-time data analysis results of step S4:
[0132] Specifically, after identifying hot spots and humidity concentration areas, the system will dynamically start micro fans, local cooling devices, small dehumidifiers and other conditioning equipment; through fuzzy logic control algorithms, the system automatically adjusts the control strategy according to sensor data; adaptive regulation not only improves the response speed of the system, but also effectively reduces human intervention and improves overall safety;
[0133] In step S5, micro fans or local cooling devices are added in hot spots, and small dehumidifiers are added in areas with high humidity. The control strategy is automatically adjusted according to sensor data in combination with the fuzzy logic control algorithm to improve the regulation effect.
[0134] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.
Claims
1. An intelligent safety monitoring system for the operating environment of a power distribution cabinet, comprising a high-density sensor network, a microclimate monitoring module, an intelligent control system, a fire monitoring module and an intelligent early warning system, characterized in that: High-density sensor networks to monitor environmental parameters; Microclimate monitoring module, which simulates the air flow and temperature and humidity distribution inside the distribution cabinet through the microclimate model, and identifies potential hot spots and humidity concentration areas; Intelligent control system, used to dynamically adjust the local environment inside the power distribution cabinet; Fire monitoring module, real-time analysis of environmental data change trends and identification of fire risks; Intelligent early warning system, used to issue early fire warnings and initiate fire prevention measures.
2. An intelligent safety monitoring method for the operating environment of a power distribution cabinet, characterized in that: An intelligent safety monitoring system for the operating environment of a power distribution cabinet according to claim 1 is used, comprising the following steps: Step S1, high-density sensor network data monitoring, using high-density micro sensor nodes to collect real-time data, including environmental parameters such as temperature, humidity and gas concentration; the high-density micro sensor nodes are arranged inside the power distribution cabinet; Step S2, multi-sensor data fusion, based on the environmental parameters collected in step S1, multi-sensor data fusion is performed, and the fused data is used for subsequent microclimate simulation and fire risk prediction; Step S3, microclimate simulation, using CFD tools to establish a microclimate model inside the distribution cabinet, simulating the air flow and temperature and humidity distribution inside the distribution cabinet; based on the sensor data fused in step S2, the model is updated in real time; Step S4, fire risk prediction, using a multi-parameter fusion algorithm to analyze the changing trend of environmental data in real time and predict fire risks in advance; Step S5, local environment adjustment and fire warning, the intelligent control system dynamically adjusts the local environment based on the real-time data analysis results of step S4.
3. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 2 is characterized in that: The data fusion steps in step S2 include: Normalize and align the data. where x i,j represents the raw data of the i-th sensor at the j-th moment, min(x i ) and max(x i ) are the minimum and maximum values of the i-th sensor data, respectively, x′ i,j is the normalized data; x i (t) = ip(x i (t1),x i (t2),...,x i (t j )), where x i (t) is the alignment data of the i-th sensor at time t, x i (t j ) is the value of the ith sensor at time t j The original data, ip refers to the interpolation process; The state space model fuses multi-sensor data. Assume that the system state x(t) is affected by the control input u(t) and process noise w(t), and the measured value z(t) is affected by the measurement noise v(t). The state equation is: x(t+1)=Ax(t)+Bu(t)+w(t), where x(t+1) is the system state vector at time t+1, including temperature, humidity, and gas concentration. A is the state transfer matrix, which represents the change of the system state. B is the control matrix, which represents the influence of the control input on the system state. u(t) is the control input vector, and w(t) is the process noise vector, which is set to zero-mean Gaussian white noise. Observation equation: z(t)=Hx(t)+v(t), where z(t) is the measurement vector at time t, H is the observation matrix, which represents the influence of the system state on the measurement value, and v(t) is the measurement noise vector, which is set to zero-mean Gaussian white noise.
4. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 3 is characterized in that: The data fusion step in step S2 also includes: Use Kalman filtering to estimate the state space model, fuse multi-sensor data, and predict the steps: P(t|t-1)=AP(t-1|t-1)A T +Q, here is the prior state estimate at time t, P(tt-1) is the prior error covariance matrix at time t, Q is the process noise covariance matrix, AT represents the transpose of the state transfer matrix, represents the posterior state estimate at time t-1, u(t-1) represents the control input vector at time t-1, and P(t-1|t-1) is the posterior error covariance matrix at time t-1; Update steps: K(t)=P(t|t-1)H T (HP(t|t-1)H T +R) -1 ; P(t|t)=(IK(t)H)P(t|t-1), where K(t) is the Kalman gain matrix at time t, P(t|t-1) is the prior error covariance matrix at time t, H is the observation matrix, and R is the measurement noise covariance matrix; is the posterior state estimate at time t, z(t) is the measured value at time t, is the prior measurement estimate at time t, P(t|t) is the a posteriori error covariance matrix at time t, R is the measurement noise covariance matrix, and I is the identity matrix; The data processed by Kalman filtering is used as the final fusion data.
5. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 4 is characterized in that: Hot spots and humidity concentration areas can be identified by: Use CAD software to build a 3D geometric model of the power distribution cabinet, and use mesh generation tools to mesh the geometric model; Define fluid properties and boundary conditions of the power distribution cabinet, including the temperature and convection heat transfer coefficient of the air inlet, air outlet, wall and equipment surface; Use CFD tools to solve the continuity equation, momentum equation, and energy equation to obtain air flow and temperature distribution; Calculate humidity distribution based on temperature distribution and air flow, and solve it using the humidity transfer equation; Dynamically update the CFD model based on sensor data.
6. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 5 is characterized in that: The microclimate simulation steps performed in step S3 include: Construct the geometric model of the power distribution cabinet, including various devices and components inside the cabinet, and mesh the geometric model; Set the physical properties of air, including density, viscosity, and thermal conductivity; Define the boundary conditions of the power distribution cabinet, including air inlet, air outlet, wall and equipment surface; Solve the Navier-Stokes equations, including: Continuity equation: in represents the partial derivative of fluid density ρ with respect to time t, is the divergence of fluid density and velocity u; Momentum equation: in represents the partial derivative of velocity u with respect to time t multiplied by density ρ, represents the dot product of the velocity vector u and its gradient, is the pressure gradient, ▽·(μ▽u) is the viscous force term, which represents the momentum diffusion under the action of viscosity, and f represents the volume force; Energy equation: in represents the partial derivative of temperature T with respect to time t multiplied by density ρ and specific heat C p , is the dot product of the temperature gradient and the velocity vector, represents the diffusion term of thermal conductivity k, and Φ is the viscous dissipation term; Calculate humidity distribution, humidity transfer equation: in Indicates water vapor concentration C w The partial derivative with respect to time t, u·▽C w is the dot product of the water vapor concentration gradient and the velocity vector, represents the diffusion term of water vapor in the air, is the Laplace operator, is the nabla operator; The CFD model is dynamically updated based on sensor data, and potential hot spots and humidity concentration areas are identified through CFD simulation results.
7. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 6 is characterized in that: The fire risk prediction steps include: Calculate the weighted sum of the comprehensive feature vectors to highlight important features; Use historical data to train machine learning models for time series analysis; Use trained machine learning models to detect anomalies in real-time data; Assess fire risk based on anomaly scores and determine warning thresholds; The early warning mechanism is triggered based on the risk assessment value, relevant personnel are notified and fire prevention measures are initiated.
8. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 7 is characterized in that: The fire risk prediction method is: use a multi-parameter fusion algorithm to calculate the weighted sum of the comprehensive feature vector: where F j represents the comprehensive eigenvalue at time j, w i Represents the data weight of the i-th sensor, satisfying x′ i,j represents the normalized data of the i-th sensor at time j; Use historical data to train LSTM machine learning models for time series analysis; Using the trained machine learning model, isolation forest is used to perform anomaly detection on real-time data: Here S(x) is the anomaly score, E(h(x)) represents the average path length of data point x, c(n) is the normalization factor, and n is the number of samples; Assess fire risk based on anomaly scores and determine warning thresholds: Here R(t) represents the risk assessment value at time t, S(x j ) represents the anomaly score at time j, and N is the time window size.
9. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 8, characterized in that: The early warning mechanism in step S4 is: triggering the early warning mechanism according to the risk assessment value, notifying relevant personnel and initiating fire prevention measures, Here Al is the warning state, 1 is the trigger warning, 0 is normal, T d is the warning threshold.
10. The intelligent safety monitoring method for the operating environment of a power distribution cabinet according to claim 9, characterized in that: In step S5, micro fans or local cooling devices are added in hot spots, and small dehumidifiers are added in areas with high humidity. The control strategy is automatically adjusted according to sensor data in combination with the fuzzy logic control algorithm.
Citation Information
Patent Citations
Intelligent property management and control system
CN109270911A
Building networking virtualization management platform, management method and system
CN117892655A
Building environment remote monitering system
CN207115150U
Cited By
Method for detecting chlorophyll content of plant leaves
CN119310018A
Intelligent interaction device control method and system
CN119356199A
Control method for intelligent fire prevention of flame-retardant material for power transmission and distribution complete switch
CN119541738A
Power distribution room remote monitoring and fire-fighting inspection system based on cloud platform
CN119656519A
Intelligent monitoring method and system for small space environment
CN120222626A
