Frequency conversion fan control method and system based on environment sensor

Abstract

The invention relates to the technical field of fan control, in particular to a frequency conversion fan control method and system based on an environment sensor, and aims to solve the problems that in the prior art, the response speed, stability and energy efficiency of a fan system are remarkably improved through intelligent environment perception and self-adaptive frequency conversion control in combination with anti-magnetic interference and power optimization; the problems that optimal operation and high safety are guaranteed, but abnormal change rates of key parameters cannot be captured, fan fault risks cannot be accurately quantified, and the safety of fan operation is reduced are solved. According to the invention, the fault monitoring module captures the change rate abnormity of key parameters, provides early warning, constructs a fault feature matrix and a logic regression model, quantifies the fault risk, supports precise decision, optimizes model parameters, improves the prediction precision, calculates the fault probability in real time, notifies a management and control platform, and achieves timely intervention.

Description

Technical Field

[0001] The present invention relates to the technical field of fan control, and more specifically, to a variable frequency fan control method and system based on an environmental sensor. Background Art

[0002] Traditional variable frequency fan control systems mainly rely on preset parameters and fixed logic to work, and are difficult to adapt to complex and changing environmental conditions. With the development of sensing technology and intelligent control, real-time monitoring of environmental parameters through integrated environmental sensors can significantly improve fan operating efficiency and response speed, and optimize energy use.

[0003] The patent application with reference publication number CN118242304A discloses a frequency conversion control method and system for a wind turbine in a cabin of a wind power installation ship, the method comprising the following steps: acquiring external environment information collection data; simulating the frequency of the wind turbine on the external environment information collection data to obtain the frequency simulation data of the wind turbine; performing anti-magnetic interference calculation based on the frequency simulation data of the wind turbine to generate the anti-magnetic interference data of the wind turbine; constructing an intelligent interference suppression strategy for the anti-magnetic interference data of the wind turbine to obtain the electromagnetic interference suppression strategy of the wind turbine; optimizing the power factor of the wind turbine anti-magnetic interference data of the wind turbine based on the electromagnetic interference suppression strategy of the wind turbine to generate the operating power optimization data of the wind turbine; performing adaptive frequency conversion control of the wind turbine according to the operating power optimization data of the wind turbine to generate the adaptive frequency conversion control scheme of the wind turbine; the present invention improves the operating efficiency and reliability of the frequency conversion control by constructing the intelligent interference suppression strategy and the adaptive frequency conversion control of the wind turbine;

[0004] However, the above-mentioned reference patent significantly improves the response speed, stability and energy efficiency of the fan system through intelligent environmental perception and adaptive frequency conversion control, combined with anti-magnetic interference and power optimization, to ensure optimal operation and high safety, but it cannot capture abnormal changes in key parameters, cannot accurately quantify the risk of fan failure, reduces the safety of fan operation, and cannot accurately predict the trend of environmental parameter changes, cannot adjust the fan operation in advance to adapt to environmental changes, reduces the operating efficiency of the fan, and cannot ensure stable operation of the fan. At the same time, it cannot accurately evaluate energy consumption and detect abnormalities, and cannot automatically adjust the fan operating frequency, making it difficult to effectively reduce the energy consumption of the fan.

[0005] To this end, we propose a variable frequency fan control method and system based on environmental sensors to address the above problems. Summary of the invention

[0006] The purpose of the present invention is to provide a variable frequency fan control method and system based on environmental sensors, which solves the problems that the prior art cannot capture abnormal change rates of key parameters, cannot accurately quantify the risk of fan failure, reduces the safety of fan operation, and cannot accurately predict the changing trends of environmental parameters. It is impossible to adjust the fan operation in advance to adapt to environmental changes, reduces the operating efficiency of the fan, and cannot ensure stable operation of the fan. At the same time, it is impossible to accurately evaluate energy consumption and discover abnormalities, and it is impossible to automatically adjust the fan operating frequency, making it difficult to effectively reduce the energy consumption of the fan.

[0007] The purpose of the present invention is achieved through the following technical solutions:

[0008] A variable frequency fan control method based on an environmental sensor comprises the following steps:

[0009] Step 1: Collect environmental parameters in real time and perform preprocessing operations on the collected environmental parameters;

[0010] Step 2: Monitor the risk assessment parameters of the variable frequency fan in real time and monitor and assess the failure risk of the variable frequency fan;

[0011] Step 3: Collect historical environmental parameters, build an environmental change prediction model, use the model to predict the environmental change trend in the next day, and adjust the operation status of the fan in advance according to the prediction results;

[0012] Step 4: Monitor the energy consumption evaluation parameters of the variable frequency fan in real time, monitor and evaluate the energy consumption status of the variable frequency fan, and optimize the operating frequency of the fan according to the evaluation results;

[0013] Step 5: Conduct a comprehensive analysis of the operating stability of the variable frequency fan based on the fault risk assessment results, environmental change prediction results, and energy consumption status assessment results, and make corresponding control decisions based on the analysis results.

[0014] As a preferred implementation of the present invention, the specific process of monitoring and evaluating the failure risk of the variable frequency fan in step 2 is as follows:

[0015] Obtain historical risk assessment parameters of the variable frequency fan, including vibration amplitude, motor winding temperature, bearing temperature, and operating current, generate a monitoring cycle, and divide the monitoring cycle MC into multiple monitoring periods {mc1, mc2, …, mcn}, that is, MC = {mc1, mc2, …, mcn};

[0016] Obtain the vibration amplitude change rate of the variable frequency fan in multiple monitoring periods. The vibration amplitude change rate represents the ratio between the vibration amplitude change and the duration of the corresponding time period. This is used to construct a set A of vibration amplitude change rates, and the mean of the difference between the maximum subset and the minimum subset in set A is recorded as the vibration amplitude change rate difference ZDF.

[0017] Obtain the motor winding temperature change rate of the variable frequency fan in multiple monitoring periods. The motor winding temperature change rate represents the ratio between the motor winding temperature change and the length of the corresponding time period. This is used to construct a set B of the motor winding temperature change rate, and the average of the difference between the maximum subset and the minimum subset in set B is recorded as the motor winding temperature change rate difference DRW;

[0018] Obtain the bearing temperature change rate of the variable frequency fan in multiple monitoring periods. The bearing temperature change rate represents the ratio between the bearing temperature change and the length of the corresponding time period. This is used to construct a set C of bearing temperature change rates, and the average of the difference between the maximum subset and the minimum subset in set C is recorded as the bearing temperature change rate difference ZCW;

[0019] The operating current change rate of the variable frequency fan in multiple monitoring periods is obtained. The operating current change rate represents the ratio between the change in the operating current and the duration of the corresponding time period. The set D of the operating current change rate is constructed in this way, and the mean of the difference between the maximum subset and the minimum subset in the set D is recorded as the operating current change rate difference YXD.

[0020] As a preferred embodiment of the present invention, the vibration amplitude change rate difference ZDF, the motor winding temperature change rate difference DRW, the bearing temperature change rate difference ZCW and the running current change rate difference YXD are obtained, and the vibration amplitude change rate difference ZDF, the motor winding temperature change rate difference DRW, the bearing temperature change rate difference ZCW and the running current change rate difference YXD are combined to construct a fault risk feature matrix FR;

[0021] The constructed fault risk feature matrix FR is used as the input of the logistic regression model, and the label vector v is used as the output of the logistic regression model. The label vector v indicates whether the variable frequency fan has a fault risk. The output of the label vector v is 0 or 1, 0 indicates that the variable frequency fan has no fault risk, and 1 indicates that the variable frequency fan has a fault risk. The label vector v is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The logistic regression model is trained until the sum of the prediction errors reaches convergence, and the training is stopped to obtain a logistic regression model that predicts the label vector v.

[0022] The expression formula of the logistic regression model is:

[0023]

[0024] Where P(v=1) represents the probability value of the variable frequency fan failure, u0 represents the intercept term, which represents the baseline probability of the variable frequency fan failure, and u1, u2, u3 and u4 are all regression coefficients;

[0025] Obtain the real-time risk assessment parameters of the variable frequency fan, process them and construct the fault risk feature matrix FR 实时 , the probability value P of the variable frequency fan failure is calculated through the trained logistic regression model 实时 , the calculated probability value P of variable frequency fan failure 实时 Sent to the wind turbine operation control platform.

[0026] As a preferred implementation of the present invention, the specific process of step 3 of constructing an environmental change prediction model and predicting the environmental change trend within the next day is as follows:

[0027] Obtain historical environmental parameters, including ambient temperature, ambient humidity, carbon dioxide concentration, and fine particulate matter concentration, generate a collection cycle, the collection cycle is one year long, divide the collection cycle into m consecutive sub-cycles, and mark the midpoint of each sub-cycle to obtain m midpoints;

[0028] Taking m midpoint moments as the base point, expand forward and backward by equal time lengths, mark s-1 expansion moments, and then summarize the midpoint moments and s-1 expansion moments to obtain s detection moments;

[0029] The ambient temperature values ​​at s detection moments are measured by the sensor to obtain s detection ambient temperature values, and the s detection ambient temperature values ​​are accumulated and averaged to obtain m sub-ambient temperature values;

[0030] The expression of the sub-ambient temperature value is:

[0031] Where ZHW zm is the sub-environment temperature value of the mth sub-cycle, ZHW jcmn is the nth detected ambient temperature value in the mth sub-cycle;

[0032] Remove the maximum and minimum values ​​of the sub-environment temperature values, accumulate the remaining m-2 sub-environment temperature values ​​and calculate the average to obtain the mean value of the environment temperature;

[0033] The expression of the mean ambient temperature is:

[0034] Where HW jz is the mean ambient temperature, ZHW zp is the sub-environment temperature value of the pth sub-period.

[0035] As a preferred embodiment of the present invention, the method of calculating the mean value of the ambient temperature can be used to obtain the mean value of the ambient humidity HS jz 、Mean carbon dioxide concentration EYN jz And the average concentration of fine particles XKNjz , the mean ambient temperature HW jz , Ambient humidity average HS jz 、Mean carbon dioxide concentration EYN jz And the average concentration of fine particles XKN jz The prediction matrix HYJ of environmental change is constructed by combination, and the prediction matrix HYJ is used as the input of the machine learning model, and the environmental change matrix within the next day corresponding to each group of prediction matrices HYJ is used as the output of the machine learning model. The environmental change matrix within the next day is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the training is stopped to obtain the environmental change prediction model. The environmental change prediction model is expressed as follows:

[0036] HBX=α·HW jz +β·HS jz +γ·EYN jz +ε·XKN jz +λ

[0037]

[0038] Among them, HBX represents the environmental change matrix within the next day, α, β, γ, and ε are all regression coefficients, λ is the random error term, ΔT represents the change value of ambient temperature, ΔH represents the change value of ambient humidity, ΔCO2 represents the change value of carbon dioxide concentration, and ΔPM2.5 represents the change value of fine particulate matter concentration;

[0039] Obtain real-time environmental parameters, convert them into corresponding prediction matrix HYJ and input them into the environmental change prediction model. The real-time environmental change matrix HBX within the next day is obtained through the environmental change prediction model. 实时 , the obtained HBX 实时 Send to the wind turbine operation control platform;

[0040] The wind turbine operation control platform receives HBX 实时 After that, take corresponding measures immediately to adjust the operating status of the fan in advance.

[0041] As a preferred implementation mode of the present invention, the specific process of monitoring and evaluating the energy consumption status of the variable frequency fan in step 4 is as follows:

[0042] Obtain energy consumption evaluation parameters of the variable frequency fan, which include input power, speed, air volume, inlet and outlet pressure difference, and ambient temperature;

[0043] The input power change rate of the variable frequency fan in multiple monitoring periods is obtained, where the input power change rate represents the ratio between the input power change and the length of the corresponding time period, and the arithmetic mean of the multiple input power change rates is calculated, and the arithmetic mean of the multiple input power change rates is recorded as the average input power change rate PSG;

[0044] The speed change rate of the variable frequency fan in multiple monitoring periods is obtained, where the speed change rate represents the ratio between the speed change amount and the length of the corresponding time period, and the arithmetic mean of the multiple speed change rates obtained is calculated, and the arithmetic mean of the multiple speed change rates is recorded as the average speed change rate PZS;

[0045] The air volume change rate of the variable frequency fan in multiple monitoring periods is obtained. The air volume change rate represents the ratio between the air volume change and the length of the corresponding time period. The arithmetic mean of the multiple air volume change rates obtained is calculated and recorded as the average air volume change rate PFL.

[0046] As a preferred embodiment of the present invention, the inlet and outlet pressure difference change rate of the variable frequency fan in multiple monitoring time periods is obtained, and the inlet and outlet pressure difference change rate represents the ratio between the inlet and outlet pressure difference change amount and the length of the corresponding time period, and the arithmetic mean of the multiple inlet and outlet pressure difference change rates obtained is calculated, and the arithmetic mean of the multiple inlet and outlet pressure difference change rates is recorded as the average inlet and outlet pressure difference change rate PJY;

[0047] The ambient temperature change rate of the variable frequency fan in multiple monitoring periods is obtained. The ambient temperature change rate represents the ratio between the ambient temperature change and the length of the corresponding time period. The arithmetic mean of the multiple ambient temperature change rates obtained is calculated, and the arithmetic mean of the multiple ambient temperature change rates is recorded as the average ambient temperature change rate PHW.

[0048] As a preferred embodiment of the present invention, the average input power change rate PSG, the average speed change rate PZS, the average air volume change rate PFL, the average inlet and outlet pressure difference change rate PJY and the average ambient temperature change rate PHW are obtained, and the energy consumption monitoring evaluation coefficient NJP is calculated by the following formula:

[0049]

[0050] Among them, j1, j2, j3, j4 and j5 are all preset proportional factor coefficients, j5>j4>j3>j2>j1>0, and the energy consumption monitoring evaluation coefficient NJP is compared with the preset energy consumption monitoring evaluation coefficient threshold:

[0051] If the energy consumption monitoring and evaluation coefficient NJP is less than the preset energy consumption monitoring and evaluation coefficient threshold, it indicates that the variable frequency fan is operating in a low energy consumption state, and a low operating energy consumption signal is generated and sent to the fan operation control platform;

[0052] If the energy consumption monitoring and evaluation coefficient NJP is greater than or equal to the preset energy consumption monitoring and evaluation coefficient threshold, it indicates that the variable frequency fan is operating in a high energy consumption state, and a high operating energy consumption signal is generated and sent to the fan operation control platform;

[0053] The fan operation control platform immediately takes corresponding measures to optimize the fan's operating frequency after receiving the low energy consumption signal;

[0054] After receiving the high energy consumption signal, the fan operation control platform immediately takes corresponding measures to optimize the fan's operating frequency.

[0055] As a preferred implementation of the present invention, the specific process of the step 5 of comprehensively analyzing the operating stability of the variable frequency fan is as follows:

[0056] Get the probability value P of the variable frequency fan failure 实时 , the ambient temperature change value ΔT, the ambient humidity change value ΔH, the carbon dioxide concentration change value ΔCO2, the fine particulate matter concentration change value ΔPM2.5 and the energy consumption monitoring evaluation coefficient NJP in the next day;

[0057] The running stability evaluation factor WPD is calculated by the following formula:

[0058] WPD=k1*P 实时 +k2*ΔT+k3*ΔH+k4*ΔCO2+k5*ΔPM2.5+k6*NJP;

[0059] Among them, k1+k2+k3+k4+k5+k6=1, k1, k2, k3, k4, k5 and k6 are all weight coefficients, and the operation stability assessment coefficient WPD is compared with the preset operation stability assessment coefficient threshold:

[0060] If the operation stability assessment coefficient WPD is less than the preset operation stability assessment coefficient threshold, it indicates that the variable frequency fan operation stability is good, and an operation stability signal is generated and sent to the fan operation control platform;

[0061] If the operation stability assessment coefficient WPD is greater than or equal to the preset operation stability assessment coefficient threshold, it indicates that the operation stability of the variable frequency fan is poor, and an operation instability signal is generated and sent to the fan operation control platform;

[0062] When the wind turbine operation control platform receives the stable operation signal, it immediately makes corresponding control decisions and sends control instructions to the corresponding actuator for execution;

[0063] When the fan operation control platform receives an operation instability signal, it immediately makes corresponding control decisions and sends control instructions to the corresponding actuator for execution.

[0064] As a preferred embodiment of the present invention, the variable frequency fan control system based on environmental sensors includes a fan operation control platform, a data acquisition module, a fault monitoring module, an environmental prediction and adjustment module, an energy consumption optimization module and an adaptive control module;

[0065] The data acquisition module is used to collect environmental parameters in real time and perform preprocessing operations on the collected environmental parameters;

[0066] Fault monitoring module, used to monitor the risk assessment parameters of variable frequency fans in real time and monitor and assess the fault risks of variable frequency fans;

[0067] The environmental prediction and adjustment module is used to collect historical environmental parameters, build an environmental change prediction model, predict the environmental change trend within the next day through the model, and adjust the operation status of the fan in advance according to the prediction results;

[0068] Energy consumption optimization module, which is used to monitor the energy consumption evaluation parameters of the variable frequency fan in real time, monitor and evaluate the energy consumption status of the variable frequency fan, and optimize the operating frequency of the fan according to the evaluation results;

[0069] The adaptive control module is used to conduct a comprehensive analysis of the operating stability of the variable frequency fan according to the fault risk assessment results, environmental change prediction results and energy consumption status assessment results, and make corresponding control decisions based on the analysis results.

[0070] Compared with the prior art, the advantages of the present invention are:

[0071] (1) In the present invention, the fault monitoring module captures abnormal change rates of key parameters and provides early warnings. By constructing a fault feature matrix and a logistic regression model, the fault risk is quantified to support accurate decision-making, optimize model parameters to improve prediction accuracy, calculate the fault probability in real time and notify the management and control platform to achieve timely intervention;

[0072] (2) In the present invention, an environmental prediction model based on historical data and multiple parameters is constructed through an environmental prediction adjustment module, and combined with machine learning and a fan control platform, automatic adjustment is achieved, operation efficiency is optimized, equipment life is extended, maintenance costs are reduced, and stable operation of the fan is ensured;

[0073] (3) In the present invention, the energy consumption of the variable frequency fan is monitored in real time through the energy consumption optimization module. By calculating the change rate and the evaluation coefficient, the energy consumption is accurately evaluated and anomalies are discovered. Based on multi-parameter analysis, the optimization signal is automatically generated to adjust the operating frequency, reduce manual intervention, improve efficiency and intelligence level, effectively reduce energy consumption, and ensure long-term stable operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a flow chart of a variable frequency fan control method in Embodiment 1 of the present invention;

[0075] Figure 2 This is a logical flow diagram of the second embodiment of the present invention;

[0076] Figure 3 This is a system block diagram of Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0077] The following will combine the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0078] Embodiment 1: Figure 1 As shown, the present invention proposes a variable frequency fan control method based on an environmental sensor, comprising the following steps:

[0079] Step 1: Collect environmental parameters in real time, perform preprocessing operations on the collected environmental parameters, including data cleaning, denoising and format conversion, and send the preprocessed environmental parameters to the wind turbine operation control platform;

[0080] Step 2: Monitor the risk assessment parameters of the variable frequency fan in real time and monitor and assess the failure risk of the variable frequency fan;

[0081] Step 2 The specific process of monitoring and evaluating the failure risk of variable frequency fans is as follows:

[0082] Obtain historical risk assessment parameters of the variable frequency fan, including vibration amplitude, motor winding temperature, bearing temperature, and operating current, generate a monitoring cycle, and divide the monitoring cycle MC into multiple monitoring periods {mc1, mc2, …, mcn}, that is, MC = {mc1, mc2, …, mcn};

[0083] Obtain the vibration amplitude change rate of the variable frequency fan in multiple monitoring periods. The vibration amplitude change rate represents the ratio between the vibration amplitude change and the duration of the corresponding time period. This is used to construct a set A of vibration amplitude change rates, and the mean of the difference between the maximum subset and the minimum subset in set A is recorded as the vibration amplitude change rate difference ZDF.

[0084] Obtain the motor winding temperature change rate of the variable frequency fan in multiple monitoring periods. The motor winding temperature change rate represents the ratio between the motor winding temperature change and the length of the corresponding time period. This is used to construct a set B of the motor winding temperature change rate, and the average of the difference between the maximum subset and the minimum subset in set B is recorded as the motor winding temperature change rate difference DRW;

[0085] Obtain the bearing temperature change rate of the variable frequency fan in multiple monitoring periods. The bearing temperature change rate represents the ratio between the bearing temperature change and the length of the corresponding time period. This is used to construct a set C of bearing temperature change rates, and the average of the difference between the maximum subset and the minimum subset in set C is recorded as the bearing temperature change rate difference ZCW;

[0086] Obtain the operating current change rate of the variable frequency fan in multiple monitoring periods. The operating current change rate represents the ratio between the operating current change and the duration of the corresponding time period. This is used to construct a set D of operating current change rates, and the average of the difference between the maximum subset and the minimum subset in set D is recorded as the operating current change rate difference YXD;

[0087] Obtain the vibration amplitude change rate difference ZDF, the motor winding temperature change rate difference DRW, the bearing temperature change rate difference ZCW and the running current change rate difference YXD, and combine the vibration amplitude change rate difference ZDF, the motor winding temperature change rate difference DRW, the bearing temperature change rate difference ZCW and the running current change rate difference YXD to construct a fault risk feature matrix FR;

[0088] The constructed fault risk feature matrix FR is used as the input of the logistic regression model, and the label vector v is used as the output of the logistic regression model. The label vector v indicates whether the variable frequency fan has a fault risk. The output of the label vector v is 0 or 1, 0 indicates that the variable frequency fan has no fault risk, and 1 indicates that the variable frequency fan has a fault risk. The label vector v is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The logistic regression model is trained until the sum of the prediction errors reaches convergence, and the training is stopped to obtain a logistic regression model that predicts the label vector v.

[0089] The expression formula of the logistic regression model is:

[0090]

[0091] Where P(v=1) represents the probability value of the variable frequency fan failure, u0 represents the intercept term, which represents the baseline probability of the variable frequency fan failure, and u1, u2, u3 and u4 are all regression coefficients;

[0092] Obtain the real-time risk assessment parameters of the variable frequency fan, process them and construct the fault risk feature matrix FR 实时 , the probability value P of the variable frequency fan failure is calculated through the trained logistic regression model 实时 , the calculated probability value P of variable frequency fan failure 实时 Send to the wind turbine operation control platform;

[0093] Through the above operations, abnormal change rates of key parameters can be captured to provide early warnings. By building a fault feature matrix and a logistic regression model, the fault risk can be quantified to support accurate decision-making, optimize model parameters to improve prediction accuracy, calculate the fault probability in real time and notify the management and control platform to achieve timely intervention.

[0094] Step 3: Collect historical environmental parameters, build an environmental change prediction model, use the model to predict the environmental change trend in the next day, and adjust the operation status of the fan in advance according to the prediction results;

[0095] Step 3: The specific process of building an environmental change prediction model and predicting the environmental change trend within the next day is as follows:

[0096] Obtain historical environmental parameters, including ambient temperature, ambient humidity, carbon dioxide concentration, and fine particulate matter concentration, generate a collection cycle, the collection cycle is one year long, divide the collection cycle into m consecutive sub-cycles, and mark the midpoint of each sub-cycle to obtain m midpoints;

[0097] Taking m midpoint moments as the base point, expand forward and backward by equal time lengths, mark s-1 expansion moments, and then summarize the midpoint moments and s-1 expansion moments to obtain s detection moments;

[0098] The ambient temperature values ​​at s detection moments are measured by the sensor to obtain s detection ambient temperature values, and the s detection ambient temperature values ​​are accumulated and averaged to obtain m sub-ambient temperature values;

[0099] The expression of the sub-ambient temperature value is:

[0100] Where ZHW zm is the sub-environment temperature value of the mth sub-cycle, ZHW jcmn is the nth detected ambient temperature value in the mth sub-cycle;

[0101] Remove the maximum and minimum values ​​of the sub-environment temperature values, accumulate the remaining m-2 sub-environment temperature values ​​and calculate the average to obtain the mean value of the environment temperature;

[0102] The expression of the mean ambient temperature is:

[0103] Where HW jz is the mean ambient temperature, ZHW zp is the sub-environment temperature value of the pth sub-period;

[0104] The mean ambient humidity HS can be obtained by using the method of calculating the mean ambient temperature. jz 、Mean carbon dioxide concentration EYN jzAnd the average concentration of fine particles XKN jz , the mean ambient temperature HW jz , Ambient humidity average HS jz 、Mean carbon dioxide concentration EYN jz And the average concentration of fine particles XKN jz The prediction matrix HYJ of environmental change is constructed by combination, and the prediction matrix HYJ is used as the input of the machine learning model, and the environmental change matrix within the next day corresponding to each group of prediction matrices HYJ is used as the output of the machine learning model. The environmental change matrix within the next day is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the training is stopped to obtain the environmental change prediction model. The environmental change prediction model is expressed as follows:

[0105] HBX=α·HW jz +β·HS jz +γ·EYN jz +ε·XKN jz +λ

[0106]

[0107] Among them, HBX represents the environmental change matrix within the next day, α, β, γ, and ε are all regression coefficients, λ is the random error term, ΔT represents the change value of ambient temperature, ΔH represents the change value of ambient humidity, ΔCO2 represents the change value of carbon dioxide concentration, and ΔPM2.5 represents the change value of fine particulate matter concentration;

[0108] Obtain real-time environmental parameters, convert them into corresponding prediction matrix HYJ and input them into the environmental change prediction model. The real-time environmental change matrix HBX within the next day is obtained through the environmental change prediction model. 实时 , the obtained HBX 实时 Send to the wind turbine operation control platform;

[0109] The wind turbine operation control platform receives HBX 实时 After that, take corresponding measures to adjust the operation status of the fan in advance. The specific adjustment measures are as follows:

[0110] If ΔT>0, increase the cooling capacity in advance and appropriately increase the fan speed. If there is a backup cooling system, start the backup cooling system immediately. If ΔT=0, keep the current fan running state unchanged. If ΔT<0, reduce unnecessary energy consumption and appropriately reduce the fan speed. If there is a backup cooling system, shut down the backup cooling system immediately.

[0111] If ΔH>0, the dehumidification capacity is increased and the fan speed is appropriately increased. If there is an auxiliary dehumidification device, the auxiliary dehumidification device is immediately started. If ΔH=0, the current fan operation state is kept unchanged. If ΔH<0, unnecessary energy consumption is reduced and the fan speed is appropriately reduced. If there is an auxiliary dehumidification device, the auxiliary dehumidification device is immediately turned off.

[0112] If ΔCO2>0, increase the ventilation volume and appropriately increase the fan speed. If there is a spare fan, start it immediately. If ΔCO2=0, keep the current fan running state unchanged. If ΔCO2<0, reduce unnecessary energy consumption and appropriately reduce the fan speed. If there is a spare fan, shut it down immediately.

[0113] If ΔPM2.5>0, the air purification capacity is improved and the fan speed is appropriately increased. If there is a backup air purification system, the backup air purification system is immediately started. If ΔPM2.5=0, the current fan operation state is kept unchanged. If ΔPM2.5<0, unnecessary energy consumption is reduced and the fan speed is appropriately reduced. If there is a backup air purification system, the backup air purification system is immediately shut down.

[0114] Through the above operations, an environmental prediction model based on historical data and multiple parameters is constructed, and combined with machine learning and the fan control platform, automatic adjustment is achieved, operating efficiency is optimized, equipment life is extended, maintenance costs are reduced, and stable operation of the fan is ensured.

[0115] Step 4: Monitor the energy consumption evaluation parameters of the variable frequency fan in real time, monitor and evaluate the energy consumption status of the variable frequency fan, and optimize the operating frequency of the fan according to the evaluation results;

[0116] Step 4 The specific process of monitoring and evaluating the energy consumption of the variable frequency fan is as follows:

[0117] Obtain energy consumption evaluation parameters of the variable frequency fan, which include input power, speed, air volume, inlet and outlet pressure difference, and ambient temperature;

[0118] The input power change rate of the variable frequency fan in multiple monitoring periods is obtained, where the input power change rate represents the ratio between the input power change and the length of the corresponding time period, and the arithmetic mean of the multiple input power change rates is calculated, and the arithmetic mean of the multiple input power change rates is recorded as the average input power change rate PSG;

[0119] The speed change rate of the variable frequency fan in multiple monitoring periods is obtained, where the speed change rate represents the ratio between the speed change amount and the length of the corresponding time period, and the arithmetic mean of the multiple speed change rates obtained is calculated, and the arithmetic mean of the multiple speed change rates is recorded as the average speed change rate PZS;

[0120] The air volume change rate of the variable frequency fan in multiple monitoring periods is obtained, where the air volume change rate represents the ratio between the air volume change and the length of the corresponding time period, and the arithmetic mean of the multiple air volume change rates is calculated, and the arithmetic mean of the multiple air volume change rates is recorded as the average air volume change rate PFL;

[0121] The inlet and outlet pressure difference change rate of the variable frequency fan in multiple monitoring periods is obtained. The inlet and outlet pressure difference change rate represents the ratio between the inlet and outlet pressure difference change amount and the length of the corresponding time period. The arithmetic mean of the multiple inlet and outlet pressure difference change rates obtained is calculated, and the arithmetic mean of the multiple inlet and outlet pressure difference change rates is recorded as the average inlet and outlet pressure difference change rate PJY;

[0122] The ambient temperature change rate of the variable frequency fan in multiple monitoring periods is obtained. The ambient temperature change rate represents the ratio between the ambient temperature change amount and the length of the corresponding time period. The arithmetic average of the multiple ambient temperature change rates is calculated and recorded as the average ambient temperature change rate PHW.

[0123] The average input power change rate PSG, average speed change rate PZS, average air volume change rate PFL, average inlet and outlet pressure difference change rate PJY and average ambient temperature change rate PHW are obtained, and the energy consumption monitoring evaluation coefficient NJP is calculated by the following formula:

[0124]

[0125] Among them, j1, j2, j3, j4 and j5 are all preset proportional factor coefficients, j5>j4>j3>j2>j1>0, and the energy consumption monitoring evaluation coefficient NJP is compared with the preset energy consumption monitoring evaluation coefficient threshold:

[0126] If the energy consumption monitoring and evaluation coefficient NJP is less than the preset energy consumption monitoring and evaluation coefficient threshold, it indicates that the variable frequency fan is operating in a low energy consumption state, and a low operating energy consumption signal is generated and sent to the fan operation control platform;

[0127] If the energy consumption monitoring and evaluation coefficient NJP is greater than or equal to the preset energy consumption monitoring and evaluation coefficient threshold, it indicates that the variable frequency fan is operating in a high energy consumption state, and a high operating energy consumption signal is generated and sent to the fan operation control platform;

[0128] After receiving the low energy consumption signal, the fan operation control platform immediately takes corresponding measures to optimize the fan operation frequency. The specific optimization measures are as follows:

[0129] Reduce speed: Reduce the speed when demand is low to ensure minimum ventilation demand;

[0130] Enable energy-saving mode: dynamically adjust frequency and set timing control;

[0131] After receiving the high energy consumption signal, the fan operation control platform immediately takes corresponding measures to optimize the fan operation frequency. The specific optimization measures are as follows:

[0132] Increase the speed and ventilation volume: Increase the speed appropriately when demand is high and start the standby fan to ensure adequate ventilation capacity;

[0133] Dynamic frequency adjustment: Use intelligent control system to adjust motor frequency in real time, optimize PID controller parameters and keep system stable;

[0134] Through the above operations, the energy consumption of the variable frequency fan can be monitored in real time. By calculating the change rate and evaluation coefficient, the energy consumption can be accurately evaluated and anomalies can be found. Based on multi-parameter analysis, optimization signals are automatically generated to adjust the operating frequency, reduce manual intervention, improve efficiency and intelligence level, effectively reduce energy consumption, and ensure long-term stable operation.

[0135] Embodiment 2: The technical solution of the embodiment of the present invention is different from that of embodiment 1 in that:

[0136] like Figure 1 and Figure 2 As shown, step five: conduct a comprehensive analysis of the operating stability of the variable frequency fan according to the fault risk assessment results, environmental change prediction results and energy consumption status assessment results, and make corresponding control decisions according to the analysis results;

[0137] Step 5 The specific process of comprehensive analysis of the variable frequency fan operation stability is as follows:

[0138] Get the probability value P of the variable frequency fan failure 实时 , the ambient temperature change value ΔT, the ambient humidity change value ΔH, the carbon dioxide concentration change value ΔCO2, the fine particulate matter concentration change value ΔPM2.5 and the energy consumption monitoring evaluation coefficient NJP in the next day;

[0139] The running stability evaluation factor WPD is calculated by the following formula:

[0140] WPD=k1*P 实时 +k2*ΔT+k3*ΔH+k4*ΔCO2+k5*ΔPM2.5+k6*NJP;

[0141] Among them, k1+k2+k3+k4+k5+k6=1, k1, k2, k3, k4, k5 and k6 are all weight coefficients. By analyzing historical data, we can understand the influence of weight coefficients k1, k2, k3, k4, k5 and k6 on the operating stability of the variable frequency fan. According to historical data, we can determine the specific values ​​of k1, k2, k3, k4, k5 and k6 to ensure that the calculated operating stability evaluation coefficient WPD can accurately reflect the actual operating status of the variable frequency fan.

[0142] Compare the operational stability assessment factor WPD with the preset operational stability assessment factor threshold:

[0143] If the operation stability assessment coefficient WPD is less than the preset operation stability assessment coefficient threshold, it indicates that the variable frequency fan operation stability is good, and an operation stability signal is generated and sent to the fan operation control platform;

[0144] If the operation stability assessment coefficient WPD is greater than or equal to the preset operation stability assessment coefficient threshold, it indicates that the operation stability of the variable frequency fan is poor, and an operation instability signal is generated and sent to the fan operation control platform;

[0145] When the fan operation control platform receives the stable operation signal, it immediately makes corresponding control decisions and sends control instructions to the corresponding actuators for execution. The specific control decisions are as follows:

[0146] Maintain current settings, fine-tune parameters to improve efficiency, implement the latest algorithms to enhance response, and perform regular maintenance and real-time monitoring to ensure optimal status;

[0147] When the fan operation control platform receives the operation instability signal, it immediately makes corresponding control decisions and sends control instructions to the corresponding actuators for execution. The specific control decisions are as follows:

[0148] Use professional tools to locate the cause. If there is a safety hazard, immediately shut down the machine for repair, optimize working parameters to reduce the load, increase monitoring frequency, and track in real time;

[0149] Through the above operations, we can comprehensively analyze the fault risks, environmental changes and energy consumption conditions, accurately evaluate the operating stability of the fan, discover potential problems in real time, and automatically generate control signals based on weight coefficients and historical data to reduce manual intervention and improve response efficiency. By predicting environmental changes and fault risks, we can optimize operations in advance to ensure stable, reliable, energy-saving and efficient operation of the fan.

[0150] Embodiment 3: The technical solution of the embodiment of the present invention is different from that of Embodiment 1 and Embodiment 2 in that:

[0151] like Figure 3 As shown, the variable frequency fan control system based on environmental sensors includes a fan operation control platform, a data acquisition module, a fault monitoring module, an environmental prediction and adjustment module, an energy consumption optimization module and an adaptive control module;

[0152] The data acquisition module is used to collect environmental parameters in real time and perform preprocessing operations on the collected environmental parameters;

[0153] Fault monitoring module, used to monitor the risk assessment parameters of variable frequency fans in real time and monitor and assess the fault risks of variable frequency fans;

[0154] The environmental prediction and adjustment module is used to collect historical environmental parameters, build an environmental change prediction model, predict the environmental change trend within the next day through the model, and adjust the operation status of the fan in advance according to the prediction results;

[0155] Energy consumption optimization module, which is used to monitor the energy consumption evaluation parameters of the variable frequency fan in real time, monitor and evaluate the energy consumption status of the variable frequency fan, and optimize the operating frequency of the fan according to the evaluation results;

[0156] Adaptive control module, used to comprehensively analyze the operation stability of the variable frequency fan according to the fault risk assessment results, environmental change prediction results and energy consumption status assessment results, and make corresponding control decisions according to the analysis results;

[0157] This variable frequency fan control system based on environmental sensors integrates data acquisition, fault monitoring, environmental prediction, energy consumption optimization and adaptive control to achieve comprehensive and accurate fan operation analysis, real-time parameter monitoring, risk assessment, environmental trend prediction, automatic operation adjustment, energy consumption optimization, reduce manual intervention, improve stability and reliability, and ensure efficient, intelligent and long-term reliable operation.

[0158] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and improved concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A variable frequency fan control method based on an environmental sensor, characterized in that: The following steps are involved: Step 1: Collect environmental parameters in real time and perform preprocessing operations on the collected environmental parameters; Step 2: Monitor the risk assessment parameters of the variable frequency fan in real time and monitor and assess the failure risk of the variable frequency fan; Step 3: Collect historical environmental parameters, build an environmental change prediction model, use the model to predict the environmental change trend in the next day, and adjust the operation status of the fan in advance according to the prediction results; Step 4: Monitor the energy consumption evaluation parameters of the variable frequency fan in real time, monitor and evaluate the energy consumption status of the variable frequency fan, and optimize the operating frequency of the fan according to the evaluation results; Step 5: Conduct a comprehensive analysis of the operating stability of the variable frequency fan based on the fault risk assessment results, environmental change prediction results, and energy consumption status assessment results, and make corresponding control decisions based on the analysis results.

2. A variable frequency fan control method and system based on an environmental sensor according to claim 1, characterized in that: The specific process of monitoring and evaluating the failure risk of the variable frequency fan in step 2 is as follows: Obtain historical risk assessment parameters of the variable frequency fan, including vibration amplitude, motor winding temperature, bearing temperature, and operating current, generate a monitoring cycle, and divide the monitoring cycle MC into multiple monitoring periods {mc1, mc2, …, mcn}, that is, MC = {mc1, mc2, …, mcn}; Obtain the vibration amplitude change rate of the variable frequency fan in multiple monitoring periods. The vibration amplitude change rate represents the ratio between the vibration amplitude change and the duration of the corresponding time period. This is used to construct a set A of vibration amplitude change rates, and the mean of the difference between the maximum subset and the minimum subset in set A is recorded as the vibration amplitude change rate difference ZDF. Obtain the motor winding temperature change rate of the variable frequency fan in multiple monitoring periods. The motor winding temperature change rate represents the ratio between the motor winding temperature change and the length of the corresponding time period. This is used to construct a set B of the motor winding temperature change rate, and the average of the difference between the maximum subset and the minimum subset in set B is recorded as the motor winding temperature change rate difference DRW; Obtain the bearing temperature change rate of the variable frequency fan in multiple monitoring periods. The bearing temperature change rate represents the ratio between the bearing temperature change and the length of the corresponding time period. This is used to construct a set C of bearing temperature change rates, and the average of the difference between the maximum subset and the minimum subset in set C is recorded as the bearing temperature change rate difference ZCW; The operating current change rate of the variable frequency fan in multiple monitoring periods is obtained. The operating current change rate represents the ratio between the change in the operating current and the duration of the corresponding time period. The set D of the operating current change rate is constructed in this way, and the mean of the difference between the maximum subset and the minimum subset in the set D is recorded as the operating current change rate difference YXD.

3. A variable frequency fan control method and system based on environmental sensor according to claim 2, characterized in that: Obtain the vibration amplitude change rate difference ZDF, the motor winding temperature change rate difference DRW, the bearing temperature change rate difference ZCW and the running current change rate difference YXD, and combine the vibration amplitude change rate difference ZDF, the motor winding temperature change rate difference DRW, the bearing temperature change rate difference ZCW and the running current change rate difference YXD to construct a fault risk feature matrix FR; The constructed fault risk feature matrix FR is used as the input of the logistic regression model, and the label vector v is used as the output of the logistic regression model. The label vector v indicates whether the variable frequency fan has a fault risk. The output of the label vector v is 0 or 1, 0 indicates that the variable frequency fan has no fault risk, and 1 indicates that the variable frequency fan has a fault risk. The label vector v is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The logistic regression model is trained until the sum of the prediction errors reaches convergence, and the training is stopped to obtain a logistic regression model that predicts the label vector v. The expression formula of the logistic regression model is: Where P(v=1) represents the probability value of the variable frequency fan failure, u0 represents the intercept term, which represents the baseline probability of the variable frequency fan failure, and u1, u2, u3 and u4 are all regression coefficients; Obtain the real-time risk assessment parameters of the variable frequency fan, process them and construct the fault risk feature matrix FR 实时 , the probability value P of the variable frequency fan failure is calculated through the trained logistic regression model 实时 , the calculated probability value P of variable frequency fan failure 实时 Sent to the wind turbine operation control platform.

4. A variable frequency fan control method and system based on an environmental sensor according to claim 1, characterized in that: The specific process of step 3 of constructing an environmental change prediction model and predicting the environmental change trend within the next day is as follows: Obtain historical environmental parameters, including ambient temperature, ambient humidity, carbon dioxide concentration, and fine particulate matter concentration, generate a collection cycle, the collection cycle is one year long, divide the collection cycle into m consecutive sub-cycles, and mark the midpoint of each sub-cycle to obtain m midpoints; Taking m midpoint moments as the base point, expand forward and backward by equal time lengths, mark s-1 expansion moments, and then summarize the midpoint moments and s-1 expansion moments to obtain s detection moments; The ambient temperature values ​​at s detection moments are measured by the sensor to obtain s detection ambient temperature values, and the s detection ambient temperature values ​​are accumulated and averaged to obtain m sub-ambient temperature values; The expression of the sub-ambient temperature value is: Where ZHW zm is the sub-environment temperature value of the mth sub-cycle, ZHW jcmn is the nth detected ambient temperature value in the mth sub-cycle; Remove the maximum and minimum values ​​of the sub-environment temperature values, accumulate the remaining m-2 sub-environment temperature values ​​and calculate the average to obtain the mean value of the environment temperature; The expression of the mean ambient temperature is: Where HW jz is the mean ambient temperature, ZHW zp is the sub-environment temperature value of the pth sub-period.

5. A variable frequency fan control method and system based on environmental sensor according to claim 4, characterized in that: The mean ambient humidity HS can be obtained by using the method of calculating the mean ambient temperature. jz 、Mean carbon dioxide concentration EYN jz And the average concentration of fine particles XKN jz , the mean ambient temperature HW jz , average ambient humidity HS jz 、Mean carbon dioxide concentration EYN jz And the average concentration of fine particles XKN jz The prediction matrix HYJ of environmental change is constructed by combination, and the prediction matrix HYJ is used as the input of the machine learning model, and the environmental change matrix within the next day corresponding to each group of prediction matrices HYJ is used as the output of the machine learning model. The environmental change matrix within the next day is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the training is stopped to obtain the environmental change prediction model. The environmental change prediction model is expressed as follows: HBX=α·HW jz +β·HS jz +γ·EYN jz +ε·XKN jz +λ Among them, HBX represents the environmental change matrix within the next day, α, β, γ, and ε are all regression coefficients, λ is the random error term, ΔT represents the change value of ambient temperature, ΔH represents the change value of ambient humidity, ΔCO2 represents the change value of carbon dioxide concentration, and ΔPM2.5 represents the change value of fine particulate matter concentration; Obtain real-time environmental parameters, convert them into corresponding prediction matrix HYJ and input them into the environmental change prediction model. The real-time environmental change matrix HBX within the next day is obtained through the environmental change prediction model. 实时 , the obtained HBX 实时 Send to the wind turbine operation control platform; The wind turbine operation control platform receives HBX 实时 After that, take corresponding measures immediately to adjust the operating status of the fan in advance.

6. A variable frequency fan control method and system based on environmental sensor according to claim 1, characterized in that: The specific process of monitoring and evaluating the energy consumption of the variable frequency fan in step 4 is as follows: Obtain energy consumption evaluation parameters of the variable frequency fan, which include input power, speed, air volume, inlet and outlet pressure difference, and ambient temperature; The input power change rate of the variable frequency fan in multiple monitoring periods is obtained, where the input power change rate represents the ratio between the input power change and the length of the corresponding time period, and the arithmetic mean of the multiple input power change rates is calculated, and the arithmetic mean of the multiple input power change rates is recorded as the average input power change rate PSG; The speed change rate of the variable frequency fan in multiple monitoring periods is obtained, where the speed change rate represents the ratio between the speed change amount and the length of the corresponding time period, and the arithmetic mean of the multiple speed change rates obtained is calculated, and the arithmetic mean of the multiple speed change rates is recorded as the average speed change rate PZS; The air volume change rate of the variable frequency fan in multiple monitoring periods is obtained. The air volume change rate represents the ratio between the air volume change and the length of the corresponding time period. The arithmetic mean of the multiple air volume change rates obtained is calculated and recorded as the average air volume change rate PFL.

7. A variable frequency fan control method and system based on an environmental sensor according to claim 6, characterized in that: The inlet and outlet pressure difference change rate of the variable frequency fan in multiple monitoring periods is obtained. The inlet and outlet pressure difference change rate represents the ratio between the inlet and outlet pressure difference change amount and the length of the corresponding time period. The arithmetic mean of the multiple inlet and outlet pressure difference change rates obtained is calculated, and the arithmetic mean of the multiple inlet and outlet pressure difference change rates is recorded as the average inlet and outlet pressure difference change rate PJY; The ambient temperature change rate of the variable frequency fan in multiple monitoring periods is obtained. The ambient temperature change rate represents the ratio between the ambient temperature change and the length of the corresponding time period. The arithmetic mean of the multiple ambient temperature change rates obtained is calculated, and the arithmetic mean of the multiple ambient temperature change rates is recorded as the average ambient temperature change rate PHW.

8. A variable frequency fan control method and system based on an environmental sensor according to claim 7, characterized in that: The average input power change rate PSG, average speed change rate PZS, average air volume change rate PFL, average inlet and outlet pressure difference change rate PJY and average ambient temperature change rate PHW are obtained, and the energy consumption monitoring evaluation coefficient NJP is calculated by the following formula: Among them, j1, j2, j3, j4 and j5 are all preset proportional factor coefficients, j5>j4>j3>j2>j1>0, and the energy consumption monitoring evaluation coefficient NJP is compared with the preset energy consumption monitoring evaluation coefficient threshold: If the energy consumption monitoring and evaluation coefficient NJP is less than the preset energy consumption monitoring and evaluation coefficient threshold, it indicates that the variable frequency fan is operating in a low energy consumption state, and a low operating energy consumption signal is generated and sent to the fan operation control platform; If the energy consumption monitoring and evaluation coefficient NJP is greater than or equal to the preset energy consumption monitoring and evaluation coefficient threshold, it indicates that the variable frequency fan is operating in a high energy consumption state, and a high operating energy consumption signal is generated and sent to the fan operation control platform; The fan operation control platform immediately takes corresponding measures to optimize the fan's operating frequency after receiving the low energy consumption signal; After receiving the high energy consumption signal, the fan operation control platform immediately takes corresponding measures to optimize the fan's operating frequency.

9. A variable frequency fan control method and system based on an environmental sensor according to claim 1, characterized in that: The specific process of the step 5 for comprehensive analysis of the operating stability of the variable frequency fan is as follows: Get the probability value P of the variable frequency fan failure 实时 , the ambient temperature change value ΔT, the ambient humidity change value ΔH, the carbon dioxide concentration change value ΔCO2, the fine particulate matter concentration change value ΔPM2.5 and the energy consumption monitoring evaluation coefficient NJP in the next day; The running stability evaluation factor WPD is calculated by the following formula: WPD=k1*P 实时 +k2*ΔT+k3*ΔH+k4*ΔCO2+k5*ΔPM2.5+k6*NJP; Among them, k1+k2+k3+k4+k5+k6=1, k1, k2, k3, k4, k5 and k6 are all weight coefficients, and the operation stability assessment coefficient WPD is compared with the preset operation stability assessment coefficient threshold: If the operation stability assessment coefficient WPD is less than the preset operation stability assessment coefficient threshold, it indicates that the variable frequency fan operation stability is good, and an operation stability signal is generated and sent to the fan operation control platform; If the operation stability assessment coefficient WPD is greater than or equal to the preset operation stability assessment coefficient threshold, it indicates that the operation stability of the variable frequency fan is poor, and an operation instability signal is generated and sent to the fan operation control platform; When the wind turbine operation control platform receives the stable operation signal, it immediately makes corresponding control decisions and sends control instructions to the corresponding actuator for execution; When the fan operation control platform receives an operation instability signal, it immediately makes corresponding control decisions and sends control instructions to the corresponding actuator for execution.

10. A variable frequency fan control system based on an environmental sensor, characterized in that: Used to execute a variable frequency fan control method based on an environmental sensor as claimed in claim 1, the variable frequency fan control system based on an environmental sensor includes a fan operation management and control platform, a data acquisition module, a fault monitoring module, an environmental prediction and adjustment module, an energy consumption optimization module and an adaptive control module; The data acquisition module is used to collect environmental parameters in real time and perform preprocessing operations on the collected environmental parameters; Fault monitoring module, used to monitor the risk assessment parameters of variable frequency fans in real time and monitor and assess the fault risks of variable frequency fans; The environmental prediction and adjustment module is used to collect historical environmental parameters, build an environmental change prediction model, predict the environmental change trend within the next day through the model, and adjust the operation status of the fan in advance according to the prediction results; Energy consumption optimization module, which is used to monitor the energy consumption evaluation parameters of the variable frequency fan in real time, monitor and evaluate the energy consumption status of the variable frequency fan, and optimize the operating frequency of the fan according to the evaluation results; The adaptive control module is used to conduct a comprehensive analysis of the operating stability of the variable frequency fan according to the fault risk assessment results, environmental change prediction results and energy consumption status assessment results, and make corresponding control decisions based on the analysis results.

Images