Environmental control system for electrical systems

Abstract

The application discloses an environment control system of an electrical system and relates to the technical field of power electronics, comprising a state sensing module, a risk estimation module and an intelligent processing module; by collecting load parameters, actuator parameters and environment parameters of the electrical system, the breathing entropy of the environment control system is calculated to reflect the efficiency of system operation; when the operation efficiency is abnormal, the expensive equipment in the electrical system is provided with multi-stage protection, the sensitivity of the environment parameters of the expensive equipment is lower than that of the fan wall and the power distribution unit which are low in cost and large in quantity, the control area is divided according to the distribution of the actuators, active actuator parameter testing is performed on the control area, the change trend of the system parameters can be accurately identified through gradient testing and real-time analysis, and it is judged which parameters will affect the system operation, the method avoids the deficiency of simply relying on preset threshold values, reduces the probability of false positives and false negatives, and actively finds abnormal and risky factors.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power electronics, in particular to an environment control system of an electrical system. BACKGROUND

[0002] The environment control system of an electrical system refers to an auxiliary system that creates and maintains a suitable operating environment for electrical equipment or electrical rooms through temperature and humidity adjustment, air purification, and air distribution, etc. The core function of the system is to ensure that the equipment works reliably and safely under stable temperature and humidity and cleanliness conditions, effectively prevent environmental factors such as overheating, condensation, dust, and corrosive gases from causing insulation deterioration, failure, and even safety accidents of electrical equipment, thereby prolonging the service life of the equipment, improving the operation stability, and reducing the maintenance cost.

[0003] The existing electrical system environment, such as a data center, has a control strategy that aims to maintain a set interval. In actual operation, when the environmental parameters approach the set threshold, although the system can intervene when detecting abnormal parameters, the electrical equipment is usually sensitive to environmental changes, and the target parameters have reached a critical state when the system takes measures. The environmental control system often intervenes too late, and the electrical equipment may be damaged, even leading to more serious risk accidents. The environmental control system is often passive in adjusting the environmental parameters of the electrical system, and its response time cannot meet the demand for rapid adjustment.

[0004] In view of the above technical defects, the present application provides a solution. SUMMARY

[0005] The purpose of the present application is to solve the technical problems that the existing electrical system environment control cannot meet the demand for rapid response, resulting in missing the intervention opportunity when detecting abnormality, and the early warning mechanism can only remind after the fact, lacking the function of early warning.

[0006] In order to achieve the above purpose, the present application adopts the following technical scheme: an environment control system of an electrical system, comprising a state perception module, a risk estimation module, and an intelligent processing module.

[0007] The state perception module is used for collecting load parameters, actuator parameters, and environmental parameters in the electrical system, and pre-processing and grouping them to generate a state vector ZT and send it to the risk estimation module and the intelligent processing module.

[0008] Further, the state vector ZT is generated, comprising the following steps:

[0009] Obtain the actuator distribution data of the environment control system, divide the electrical system into several control regions according to the distribution of the actuators, and generate a state vector ZT.

[0010] Each control area is provided with a complete set of actuators group to perform control operation of all environmental parameters in the electrical system;

[0011] In each control area, several collection points are arranged, each of which is configured with environmental parameter sensors, including temperature sensors, humidity sensors, EMI test probe groups, laser scattering PM sensors and electrochemical sensors; the environmental parameters include temperature, humidity, electric field intensity, magnetic field intensity, particle count and corrosive gas concentration;

[0012] The arrangement density of the collection points is optimized according to the heat sensitivity level and fault history distribution of the equipment, wherein the arrangement density of the collection points in the priority monitoring area is increased compared with that in the non-priority monitoring area;

[0013] Wherein, the load distribution in each control area is obtained and relevant load sensors are arranged, including current transformers, smart meters and clamp-on current sensors; the load parameters include load current, load voltage and current waveform of specific high-heat equipment;

[0014] The actuators in each control area are arranged with relevant actuator sensors, including current sensors, voltage sensors, temperature sensors and vibration sensors; the actuator parameters include the current, voltage, temperature and vibration amplitude and frequency of the actuators;

[0015] The above parameters are subjected to data cleaning, normalization processing, time alignment and synchronization and feature extraction to generate an environmental vector HJ= (environmental temperature, environmental humidity, environmental electric field intensity, environmental magnetic field intensity, environmental particle count and environmental corrosive gas concentration), an execution vector ZX= (actuator current, actuator voltage, actuator temperature and actuator vibration amplitude and frequency) and a load vector FZ= (load current, load voltage and current waveform of specific high-heat equipment), which are integrated to generate a state vector ZT= (HJ, ZX, FZ).

[0016] A risk estimation module is used to receive the state vector ZT and perform dimension reduction and symbolization processing, and to count and analyze the symbol distribution to obtain a continuous breathing entropy curve with the same length as the time axis of the original data, which is used to represent the trend of the running efficiency of the electrical system over time,

[0017] The slope curve is obtained by first-order difference calculation of the breathing entropy curve, and the change acceleration curve is obtained by second-order difference calculation, and the slope curve and the change acceleration curve are sent to the intelligent processing module;

[0018] Further, the breathing entropy is calculated, and the specific process is as follows:

[0019] According to the original time axis of the data collected by the state perception module, equidistant time points are set, when the state vector ZT is analyzed in time sequence, a time period is defined as a window W, a sliding step S, the state of each time of the state vector ZT in the window, that is, the specific value of all parameters of each vector at this time, is discretized to obtain the frequency of different states, and the calculation formula is:

[0020] ;

[0021] Wherein, is an element in the state vector ZT at time t, is the probability distribution of each element; is the number of times of appearing in the window W, is the number of data collection in the window;

[0022] The respiratory entropy in the window is calculated, and the calculation formula is:

[0023] ;

[0024] Wherein, i is the number of each element of the comprehensive vector ZT, n is the total number of elements in the environment vector HJ, m is the total number of elements in the execution vector ZX, and p is the total number of elements in the load vector FZ;

[0025] The intelligent processing module is used for receiving the state vector ZT, the slope curve and the change acceleration curve, analyzing the slope curve and the change acceleration curve, generating the slope abnormal interval and the acceleration abnormal interval,

[0026] The actuator parameters related to the slope abnormal interval and the acceleration abnormal interval are gradient tested, the output of the actuator parameters is controlled step by step, the slope curve and the change acceleration curve are analyzed, and the risk warning of environment control is carried out;

[0027] Further, the slope abnormal interval and the acceleration abnormal interval are generated, and the specific process is as follows:

[0028] The normal range in the slope curve is set as

XLmin, XLmax

BHmin, BHmax

[0029] When the change acceleration is in

BHmin, BHmax

BHmin, BHmax

[0030] When the slope curve is in

XLmin, XLmax

XLmin, XLmax

[0031] Further, the parameters in the execution vector ZX are subjected to gradient test, so as to give a risk warning for environmental control, and the specific process is as follows:

[0032] S501. Obtain the execution vector ZX in the control area corresponding to the time period of the slope abnormal interval and the acceleration abnormal interval, specifically the starting point t0 and the end point t1 of the slope abnormal interval;

[0033] Define the execution vector ZX (t0) at the starting point as the starting parameter of the variable parameter, and define the execution vector ZX (t1) at the end point as the terminal parameter of the variable parameter;

[0034] Suppose that the interval between every two test gradients is fixed as di, which depends on the difference between the variable parameters of the execution vector ZX at the starting point t0 and the end point t1, and there are three groups of test gradients based on the starting parameter and the terminal parameter, as follows:

[0035] D1=(ZXi(t0)-a×di,ZXi(t0)-(a-1)×di,……,ZXi(t0));

[0036] D2=(ZXi(t0)+di,ZXi(t0)+2di,……,ZXi(t1));

[0037] D3=(ZXi(t1)+di,ZXi(t1)+2di,……,ZXi(t1)+b×di);

[0038] Where i is each element in the execution vector ZX, and a and b are critical coefficients when the slope of the respiratory entropy and the change acceleration reach a preset threshold;

[0039] S502. Control the parameters of the execution vector ZX in the control area marked with an abnormality, select only one parameter as a variable parameter each time, and the absolute value of the increment of the parameter value of the variable parameter is di, where i is the parameter number of the execution vector ZX;

[0040] After changing the output value of the variable parameter, the load parameters, actuator parameters and environmental parameters in the control area with the abnormal flag are collected and preprocessed, the respiratory entropy curve is drawn for the load parameters, actuator parameters and environmental parameters, and the slope curve is calculated by first-order difference calculation, and the change acceleration curve is calculated by second-order difference calculation, and the slope curve and the change acceleration curve are defined as the control group;

[0041] The current value of the slope curve at t0+t2 in the control group is obtained, the absolute value of the difference between the current value and the termination parameter is calculated and recorded, thereby obtaining the slope difference value sequence; the current value of the change acceleration curve at t0+t2 in the control group is obtained, the absolute value of the difference between the current value and the termination parameter is calculated and recorded, thereby obtaining the change acceleration difference value sequence;

[0042] Wherein, the t2 is the time point when the slope curve of the respiratory entropy is less than the preset threshold after changing the parameter of the execution vector ZX;

[0043] The gradient test is performed on each parameter of the execution vector ZX, and a slope difference value sequence set and a change acceleration difference value sequence set are obtained;

[0044] S503. Analyze the slope difference value sequence set, calculate the absolute value of the difference between two adjacent elements in the slope difference value sequence set, mark it as an incremental difference value, find the parameter value of the first element before the first incremental difference value greater than the preset difference value according to the test gradient sorting of S501, and define the parameter value as the executable margin of the parameter, which represents the maximum value that the execution parameter can output when the system is safely running, i.e. the executable margin;

[0045] Wherein, the preset difference value is obtained by the operator based on historical data analysis;

[0046] Analyze the change acceleration difference value sequence set, find the parameter value before the first change acceleration difference value greater than the preset change acceleration difference value, define the parameter value as the warning value, and calculate the ratio of the actual value of the parameter to the warning value , ∈(0,1];

[0047] Wherein, the The closer to 1, the greater the probability of an accident in the environmental control system;

[0048] The closer to 0, the more stable the environmental control system;

[0049] Wherein, the preset change acceleration difference value is obtained by the operator based on historical data analysis;

[0050] S504. The operation and maintenance personnel constrain the actual output value of the parameter according to the operable margin corresponding to the parameter of the execution vector ZX in S503, and the constraint condition is as follows: set the actual maximum output value of the parameter in the execution vector ZX to 60% of the operable margin of the parameter;

[0051] By setting the early warning proportion threshold of the parameters in the execution vector ZX When ≥ Immediately carry out risk investigation on the related equipment in the corresponding control area.

[0052] In summary, due to the adoption of the above technical solutions, the beneficial effects of the present application are:

[0053] The environmental control system of the electrical system reflects the efficiency of system operation by collecting load parameters, actuator parameters and environmental parameters of the electrical system, calculating the breathing entropy of the environmental control system, when the operation efficiency is abnormal, based on the multi-level protection of expensive equipment in the electrical system, the sensitivity of the environmental parameters is lower than that of fan walls and power distribution units which are low-cost and large in number, according to the control area division of the actuator distribution, the control area is actively tested, through gradient test and real-time analysis, the change trend of system parameters can be accurately identified, so as to judge which parameters will affect the system operation, this method avoids the shortcomings of simply relying on preset threshold, reduces the probability of false positives and false negatives, actively finds abnormal and risky factors, and the constraint conditions of execution parameters, so as to realize early warning of possible risks of the system, and provide higher response sensitivity and emergency capability for the electrical system. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The overall framework schematic diagram of the present application is shown. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0056] Embodiment:

[0057] The present application provides an environmental control system of an electrical system, characterized in that it comprises a state perception module, a risk estimation module and an intelligent processing module.

[0058] a state perception module for collecting load parameters, actuator parameters and environmental parameters in the electrical system, and preprocessing and grouping to generate a state vector ZT and send to the risk estimation module and the intelligent processing module;

[0059] generating the state vector ZT, including the following steps:

[0060] obtaining actuator distribution data of the environmental control system, spatially dividing the electrical system according to the distribution of the actuators, and generating a plurality of control regions;

[0061] Each control region is provided with a complete set of actuator groups to perform control operations on all environmental parameters in the electrical system.

[0062] A plurality of collection points are arranged in each control region, each of which is configured with environmental parameter sensors, including temperature sensors, humidity sensors, EMI test probe groups, laser scattering PM sensors and electrochemical sensors; the environmental parameters include temperature, humidity, electric field intensity, magnetic field intensity, particle count and corrosive gas concentration.

[0063] The arrangement density of the collection points is optimized according to the heat sensitivity grade and fault history distribution of the equipment, wherein the arrangement density of the collection points in the priority monitoring area is increased compared with that in the non-priority monitoring area.

[0064] Wherein, the load distribution in each control region is obtained and arranged with related load sensors, including current transformers, smart meters and clamp-on current sensors; the load parameters include load current, load voltage and current waveform of specific high-heat equipment.

[0065] The actuators in each control region are arranged with related actuator sensors, including current sensors, voltage sensors, temperature sensors and vibration sensors; the actuator parameters include the current, voltage, temperature and vibration amplitude and frequency of the actuator.

[0066] The above parameters are subjected to data cleaning, normalization processing, time alignment and synchronization and feature extraction to generate an environmental vector HJ= (environmental temperature, environmental humidity, environmental electric field intensity, environmental magnetic field intensity, environmental particle count and environmental corrosive gas concentration), an execution vector ZX= (actuator current, actuator voltage, actuator temperature and actuator vibration amplitude and frequency) and a load vector FZ= (load current, load voltage and current waveform of specific high-heat equipment), and the state vector ZT= (HJ, ZX, FZ) is generated by integration.

[0067] The risk estimation module is configured to receive the state vector ZT and perform dimension reduction and symbolization processing, count symbol distribution and analyze to obtain a continuous breathing entropy curve with the same length as the time axis of the original data, to represent the change trend of the running efficiency of the electrical system over time.

[0068] The slope curve is obtained by performing a first-order difference calculation on the respiratory entropy curve, and the change acceleration curve is obtained by performing a second-order difference calculation. The slope curve and the change acceleration curve are then sent to the intelligent processing module.

[0069] The specific process for calculating respiratory entropy is as follows:

[0070] Based on the raw time axis of the data collected by the state-aware module, equally spaced time points are set. When performing time-series analysis on the state vector ZT, a time period is defined as a window W with a sliding step size S. For the state vector ZT at each moment within the window, i.e., the specific values ​​of all parameters of each vector at that moment, dimensionality reduction and discretization are performed to obtain the frequency of different states. The calculation formula is as follows:

[0071] ;

[0072] in, Let ZT be an element in the state vector ZT at time t. The probability distribution for each element; Within window W Number of times it appears This refers to the number of times data is collected within the window.

[0073] The respiratory entropy within this window is calculated using the following formula:

[0074] ;

[0075] Where i is the number of each element in the comprehensive vector ZT, n is the total number of elements in the environment vector HJ, m is the total number of elements in the execution vector ZX, and p is the total number of elements in the load vector FZ.

[0076] The intelligent processing module receives the state vector ZT, slope curve, and variable acceleration curve, analyzes the slope curve and variable acceleration curve to generate slope anomaly intervals and acceleration anomaly intervals.

[0077] Gradient tests are performed on actuator parameters related to abnormal slope and acceleration intervals. By gradually controlling the output of actuator parameters, slope curves and changing acceleration curves are analyzed to provide risk warnings for environmental control.

[0078] The specific process for generating slope anomaly intervals and acceleration anomaly intervals is as follows:

[0079] Let the normal range of the slope curve be [XLmin, XLmax], and the normal range of the acceleration curve be [BHmin, BHmax]. Based on the slope curve and the acceleration curve, determine the abnormal interval in the respiratory entropy curve. The determination criteria are as follows:

[0080] When the change acceleration is within

BHmin, BHmax

BHmin, BHmax

[0081] When the slope curve is within

XLmin, XLmax

XLmin, XLmax

[0082] The parameters in the execution vector ZX are tested by gradient, so as to give a risk warning to the environmental control, and the specific process is as follows:

[0083] S501. Obtain the execution vector ZX in the control area corresponding to the time period of the slope abnormal interval and the acceleration abnormal interval, specifically the starting point t0 and the ending point t1 of the slope abnormal interval;

[0084] Define the execution vector ZX (t0) at the starting point as the starting parameter of the variable parameter, and define the execution vector ZX (t1) at the ending point as the terminal parameter of the variable parameter;

[0085] Let the interval between every two test gradients be fixed as di, di depends on the difference of the variable parameters of the execution vector ZX at the starting point t0 and the ending point t1, and there are three groups of test gradients based on the starting parameter and the terminal parameter, as follows:

[0086] D1=(ZXi(t0)-a×di,ZXi(t0)-(a-1)×di,……,ZXi(t0));

[0087] D2=(ZXi(t0)+di,ZXi(t0)+2di,……,ZXi(t1));

[0088] D3=(ZXi(t1)+di,ZXi(t1)+2di,……,ZXi(t1)+b×di);

[0089] Where i is each element in the execution vector ZX, and a and b are the critical coefficients when the slope of the respiratory entropy and the change acceleration reach the preset threshold;

[0090] S502. Control the parameters of the execution vector ZX in the control area marked as abnormal, select only one parameter as the variable parameter each time, and the absolute value of the parameter value increment of the variable parameter is di, where i is the parameter number of the execution vector ZX;

[0091] After changing the output value of the variable parameter, the load parameter, the actuator parameter and the environment parameter in the control area with the abnormal flag are collected and preprocessed, the respiratory entropy curve of the load parameter, the actuator parameter and the environment parameter is drawn, the slope curve is calculated by the first-order difference, and the change acceleration curve is calculated by the second-order difference, and the slope curve and the change acceleration curve are defined as the control group;

[0092] The current value of the slope curve at t0+t2 in the control group is obtained, the absolute value of the difference between the current value and the termination parameter is calculated and recorded, so as to obtain the slope difference value sequence; the current value of the change acceleration curve at t0+t2 in the control group is obtained, the absolute value of the difference between the current value and the termination parameter is calculated and recorded, so as to obtain the change acceleration difference value sequence;

[0093] Wherein, t2 is the time point at which the slope curve of the respiratory entropy is less than the preset threshold after changing the parameter of the execution vector ZX;

[0094] Gradient test is performed on each parameter of the execution vector ZX, and the slope difference value sequence set and the change acceleration difference value sequence set are obtained;

[0095] S503. Analyze the slope difference value sequence set, calculate the absolute value of the difference between two adjacent elements in the slope difference value sequence set, record it as the increment difference value, find the parameter value of the first element before the first increment difference value greater than the preset difference value according to the test gradient sorting of S501, and define the parameter value as the executable margin of the parameter, which represents the maximum value that the execution parameter can output when the system is safely running, that is, the executable margin;

[0096] Wherein, the preset difference value is obtained by the operator based on historical data analysis;

[0097] Analyze the change acceleration difference value sequence set, find the parameter value before the first change acceleration difference value greater than the preset change acceleration difference value, define the parameter value as the warning value, and calculate the ratio of the actual value of the parameter to the warning value , ∈(0,1];

[0098] Wherein, The closer to 1, the greater the probability of accident of the environment control system;

[0099] The closer to 0, the more stable the environment control system;

[0100] Wherein, the preset change acceleration difference value is obtained by the operator based on historical data analysis;

[0101] S504. The operation and maintenance personnel constrain the actual output value of the parameter according to the operable margin corresponding to the parameter of the execution vector ZX in S503, and the constraint condition is as follows: set the actual maximum output value of the parameter in the execution vector ZX to 60% of the operable margin of the parameter;

[0102] By setting the early warning proportion threshold of the parameters of the execution vector ZX When ≥ Immediately investigate the risk of related equipment in the corresponding control area;

[0103] By collecting the load parameters, actuator parameters and environmental parameters of the electrical system, the breathing entropy of the environmental control system is calculated to reflect the efficiency of the system operation. When the operation efficiency is abnormal, based on the multi-level protection of the expensive equipment in the electrical system, the sensitivity of the environmental parameters is lower than that of the fan wall and power distribution unit which are low-cost and large-number devices. According to the control area division of the actuator distribution, the execution parameter test of the control area is carried out. Through gradient test and real-time analysis, the change trend of the system parameters can be accurately identified, so as to judge which parameters will affect the system operation. This method avoids the shortcomings of simply relying on preset threshold, reduces the probability of false positives and false negatives, actively finds abnormal and risky factors, and execution parameter constraints, and provides higher response sensitivity and emergency capability for the electrical system.

[0104] The size of the interval and the threshold is set for easy comparison. The size of the threshold depends on the number of sample data and the base number set by the person skilled in the art for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantized values.

[0105] The above formulas are dimensionless values calculated, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the nearest real situation. The preset parameters in the formula are set by the person skilled in the art according to the actual situation;

[0106] The above is only the preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can make equivalent replacement or change according to the technical solution and the inventive concept of the present application within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. An environmental control system for an electrical system, characterized by The state perception module, the risk estimation module and the intelligent processing module are included. The state perception module is used for collecting load parameters, actuator parameters and environmental parameters in the electrical system, pre-processing and grouping, generating a state vector ZT and sending it to the risk estimation module and the intelligent processing module. The risk estimation module is used for receiving the state vector ZT, performing dimension reduction and symbolization processing, counting and analyzing the symbol distribution to obtain a continuous breathing entropy curve with the same length as the original data time axis, which is used to represent the trend of the running efficiency of the electrical system over time. The slope curve and the change acceleration curve are sent to the intelligent processing module. The breathing entropy is calculated, and the specific process is as follows: According to the original time axis of the data collected by the state perception module, an equal-interval time point is set, and when the state vector ZT is analyzed in time sequence, a time period is defined as a window W, and a sliding step S is set. ； wherein, is the element in the state vector ZT at time t, is the probability distribution for each element; is the number of occurrences of the element within the window W, is the number of occurrences of the element within the window W, is the number of data acquisitions within the window. The state of the state vector ZT at each time in the window, i.e. the specific value of each vector at that time, is discretized to obtain the frequency of different states, and the calculation formula is: ； The breathing entropy in the window is calculated, and the calculation formula is: Where i is the number of each element of the comprehensive vector ZT, n is the total number of elements in the environmental vector HJ, m is the total number of elements in the execution vector ZX, and p is the total number of elements in the load vector FZ. The intelligent processing module is used for receiving the state vector ZT, the slope curve and the change acceleration curve, analyzing the slope curve and the change acceleration curve to generate a slope abnormal interval and an acceleration abnormal interval, 2. The environmental control system of an electrical system of claim 1, wherein, The actuator parameters related to the slope abnormal interval and the acceleration abnormal interval are tested by gradient, the output of the actuator parameters is gradually controlled, the slope curve and the change acceleration curve are analyzed, and the risk warning of the environmental control is performed. The state vector ZT is generated, including the following steps: Obtain the actuator distribution data of the environmental control system, divide the electrical system into several control areas according to the distribution of the actuators, and generate several control areas; Each control area is provided with a complete set of actuators to perform control operation of all environmental parameters in the electrical system; Several collection points are arranged in each control area, and each collection point is provided with environmental parameter sensors, including temperature sensors, humidity sensors, EMI test probe groups, laser scattering PM sensors and electrochemical sensors; the environmental parameters include temperature, humidity, electric field intensity, magnetic field intensity, particle count and corrosive gas concentration; The arrangement density of the collection points is optimized according to the equipment heat sensitivity level and the fault history distribution, and the arrangement density of the collection points in the priority monitoring area is increased compared with that in the non-priority monitoring area; Wherein, the load distribution in each control area is obtained and arranged with related load sensors, including current transformers, smart meters and clamp-on current sensors; the load parameters include load current, load voltage and current waveform of specific high-heat equipment; Each actuator in each control area is arranged with relevant actuator sensors, including current sensors, voltage sensors, temperature sensors, and vibration sensors; the actuator parameters include the current, voltage, temperature, and vibration amplitude and frequency of the actuator; The above parameters are subjected to data cleaning, normalization processing, time alignment and synchronization, and feature extraction to generate an environment vector HJ=(environment temperature, environment humidity, environment electric field strength, environment magnetic field strength, environment particle count, and environment corrosive gas concentration), an execution vector ZX=(actuator current, actuator voltage, actuator temperature, and actuator vibration amplitude and frequency), and a load vector FZ=(load current, load voltage, and current waveform of a specific high-heat equipment), which are integrated to generate a state vector ZT=(HJ, ZX, FZ).

3. The environmental control system of an electrical system of claim 1, wherein, The slope abnormal interval and the acceleration abnormal interval are generated, and the specific process is as follows: Let the normal range in the slope curve be 【XLmin, XLmax】, and let the normal range in the change acceleration curve be 【BHmin, BHmax】. According to the slope curve and the change acceleration curve, the abnormal interval in the respiratory entropy curve is determined, and the determination criteria are as follows: When the change acceleration is within 【BHmin, BHmax】, it is determined that the system is running normally in the time period corresponding to the change acceleration. When the change acceleration is outside 【BHmin, BHmax】, it is determined that the respiratory entropy of the system is abnormal in the time period corresponding to the curve, and the time range is marked and the acceleration abnormal interval is generated. When the slope curve is within 【XLmin, XLmax】, it is determined that the system is running normally in the time period corresponding to the slope curve. When the slope curve is outside 【XLmin, XLmax】, it is determined that the respiratory entropy of the system is abnormal in the time period corresponding to the curve, and the time range is marked and the slope abnormal interval is generated.

4. The environmental control system of an electrical system of claim 1, wherein, The parameters in the execution vector ZX are subjected to gradient testing to perform risk early warning on the environmental control, and the specific process is as follows: S501. Obtain the execution vector ZX in the control area in the time period corresponding to the slope abnormal interval and the acceleration abnormal interval, specifically the start point t0 and the end point t1 of the slope abnormal interval; Define the execution vector ZX(t0) at the start point as the starting parameter of the variable parameter, and define the execution vector ZX(t1) at the end point as the terminal parameter of the variable parameter; Let the interval between every two test gradients be di, which depends on the difference between the variable parameters of the execution vector ZX at the start point t0 and the end point t1. Based on the starting parameter and the terminal parameter, there are three sets of test gradients, as follows: D1=(ZXi(t0)-a×di, ZXi(t0)-(a-1)×di,..., ZXi(t0)); D2=(ZXi(t0)+di, ZXi(t0)+2di,..., ZXi(t1)); D3=(ZXi(t1)+di, ZXi(t1)+2di,..., ZXi(t1)+b×di); Wherein i is each element in the execution vector ZX, a, b are the slope of the respiratory entropy and the critical coefficient when the acceleration of change reaches the preset threshold; S502. Control the execution vector ZX parameters in the abnormal marked control area as a variable, only one parameter is selected as a variable parameter each time, and the absolute value of the increment of the parameter value of the variable parameter is di, where i is the parameter number of the execution vector ZX; After changing the output value of the variable parameter, the load parameters, actuator parameters and environment parameters in the abnormal marked control area are collected and preprocessed, the respiratory entropy curve of the load parameters, actuator parameters and environment parameters is drawn, and the slope curve is calculated by first-order difference, and the change acceleration curve is calculated by second-order difference. The slope curve and the change acceleration curve are defined as the control group; The current value of the slope curve at t0+t2 in the control group is obtained, the absolute value of the difference between the current value and the termination parameter is calculated and recorded, so as to obtain the slope difference value sequence; The current value of the change acceleration curve at t0+t2 in the control group is obtained, the absolute value of the difference between the current value and the termination parameter is calculated and recorded, so as to obtain the change acceleration difference value sequence; Wherein, the t2 is the time point when the slope curve of the respiratory entropy is less than the preset threshold after changing the parameters of the execution vector ZX; The gradient test is performed on each parameter of the execution vector ZX, and the slope difference value sequence set and the change acceleration difference value sequence set are obtained; S503. Analyze the slope difference value sequence set, calculate the absolute value of the difference between two adjacent elements in the slope difference value sequence set, mark it as the increment difference value, find the parameter value of the first element before the first increment difference value greater than the preset difference value according to the test gradient sorting of S501, and define the parameter value as the executable margin of the parameter. It represents the maximum value that the execution parameter can output when the system is safely running, that is, the executable margin; Wherein, the preset difference value is obtained by the operator based on historical data analysis; The analysis of the change acceleration difference value sequence set finds the first change acceleration difference value greater than the preset change acceleration difference value of the previous parameter value, defines the parameter value as a warning value, and calculates the ratio of the actual value of the parameter to the warning value , ∈ (0, 1] wherein the The closer to 1, the greater the probability that the environmental control system will have an accident. The closer it is to 0, the more stable the environmental control system is; Wherein, the preset change acceleration difference value is obtained by the operator based on historical data analysis; S504. The operation and maintenance personnel constrain the actual output value of the parameter according to the executable margin of the parameter corresponding to the execution vector ZX in S503, and the constraint condition is as follows: setting the actual maximum output value of the parameter in the execution vector ZX as 60% of the executable margin of the parameter. By setting a pre-warning proportion threshold of the parameters of the execution vector ZX When ≥ Immediately investigate the related equipment in the corresponding control area.

Images