55results about How to "Strong nonlinear fitting ability" patented technology

The present invention discloses a lithium battery SOC estimation method based on a BP neural network. The method comprises the steps of (1) establishing a neuron model; (2) establishing a BP neural network model; (3) constructing a BP neural network algorithm; (4) obtaining the network sample data; (5) carrying out the sample SOC calculation. The neural network algorithm has the stronger non-linear fitting capability, and the relation between input and output can be obtained by training a lot of input and output samples on the condition of not needing to consider the internal structure of a lithium battery and for the external excitation, thereby being able to fitting the dynamic characteristics of the lithium battery very well to estimate the SOC of the battery. The method is high in estimation precision and can obtain higher precision on the condition of enough battery data samples, and the neural network SOC estimation has the very good applicability and is suitable for various power batteries.

The invention discloses a vehicle recognition and tracking method based on convolutional neural networks. Through the method, the problem that it is difficult to guarantee instantaneity under a high-precision condition in the prior art is solved, and the defects of inaccurate classification results, long tracking and recognition time and the like are overcome. The method comprises the implementation steps that a quick region convolutional neural network is constructed and trained; an initial frame of a monitoring video is processed and recognized; a tracking convolutional neural network is trained off line; an optimal candidate box is extracted and selected; a sample queue is generated; online iterative training is performed; and a target image is acquired, and instant vehicle recognitionand tracking are realized. According to the method, a Faster-rcnn and the tracking convolutional neural network are combined, and high-level features with good robustness and high representativeness of vehicles are extracted by use of the convolutional neural networks; through network fusion and an online-offline training alternating mode, time needed for tracking and recognition is shortened on the basis of guaranteeing high precision; the recognition result is accurate, and tracking time is shorter; and the method can be used for cooperating with an ordinary camera to complete instant recognition and tracking of the vehicles.

The invention relates to a method for achieving robot multi-axis-hole assembling through deep reinforcement learning, and belongs to the technical field of robot assembling. The method comprises the steps that in the training process, common experience data and expert experience data which are produced through a traditional fuzzy force control method and a deep reinforcement learning network on the basis of a simulation model are added into an experience data set, experience data are randomly drawn from the experience data set to train the deep reinforcement learning network, and therefore theassembling action of the network can rapidly achieve the assembling level of the traditional fuzzy control method and can exceed the assembling effect of the traditional fuzzy control method if training continues to be carried out. The deep reinforcement learning network trained by the simulation model is directly used for a practical robot multi-axis-hole assembling task. The experience data produced by the simulation model are used for training, the problem that practical assembling environment cannot provide enough training data is solved, and meanwhile the training cost is reduced.

The invention discloses a wind power combined predication method based on ensemble average empirical mode decomposition and an improved Elman neural network, and belongs to the technical field of wind power prediction. The method comprises the following steps: step 1, extracting wind speed sequence historical data and normalizing the data; step 2, making sequence analysis of the extracted wind speed sequence historical data through empirical mode decomposition; step 3, reconstructing a phase space for the sequences obtained through empirical mode decomposition; step 4, cyclically selecting the number of nodes in a hidden layer to train an Elman neural network, and superposing the prediction results of the sequences to obtain a wind speed prediction result; and step 5, making error analysis of the wind speed prediction result. The modeling process of the method is simple and practical. By adopting the method, the wind power can be predicted quickly and effectively. The method is of great significance to the security and stability and dispatching operation of a power system under the condition of wind power grid-connection.

The invention discloses a hen house environment ammonia gas concentration intelligent monitoring system which is composed of two parts of a hen house environment parameter acquisition platform and a hen house environment ammonia gas concentration intelligent prediction model. The hen house environment ammonia gas concentration intelligent monitoring system based on a CAN field bus is designed in view of difficulties that hen house environment ammonia gas concentration change has characteristics of non-linearity, high time lag, high inertia and time variation and hen house area is relatively large and ammonia gas concentration is difficult to accurately predict. The system is the intelligent monitoring system which realizes detection, intelligent prediction and management of the monitored hen house environment ammonia gas concentration by the hen house environment parameter acquisition platform and the hen house environment ammonia gas concentration intelligent prediction model, and the basis of performing high-quality and high-efficiency purification on hen house environment ammonia gas concentration is provided. The system has wide application prospect and great popularization value.

The invention discloses an anti-attack and defense method based on an LSTM (Long Short Term Memory) detector. The method comprises the following steps that: 1) generating a candidate detector of an LSTM-FNN (Fuzzy Neural Network) structure, and asking the detector to detect abnormal samples as more as possible on a premise that the detector does not misjudge a normal sample; 2) storing the candidate detector into a register queue, detecting a training dataset by an abnormality detector taken out of the register queue, and deleting the detected abnormal sample to enable different abnormality detectors to cover different abnormal areas; and 3) in a detection stage, detecting a detected sample by all abnormality detectors, and comprehensively judging whether the sample is abnormal or not. Byuse of the method, a neural network is combined with a negative selection algorithm, each LSTM detector guarantees that the normal sample can not be misjudged, the abnormality detector set guaranteesthat the abnormal situation may be covered, and an algorithm detection effect is improved.

The invention relates to a forecasting method of burning and explosion characteristics of organic compounds based on a support vector machine; the method utilizes various structural parameters which reflect the structural characteristics of molecules to describe the burning and explosion characteristics of organic matters according to the principle that various burning and explosion characteristics are decided by the molecular structure; the introduction of the support vector machine of a powerful machine learning algorithm can carry out training and forecasting to the burning and explosion characteristics of the organic matter and the nonlinearity, nondeterminacy and complexity which exist in the molecular structure, thus establishing a forecasting module with stability and effectiveness; the established forecasting module is applied in the forecasting of the burning and explosion characteristics of other unknown compounds with the advantages of high forecasting precision, fastness and convenience.

The invention discloses an excellent driver lane changing imitation model establishment method based on a GRU network, belonging to the field of smart car automatic driving. The method comprises the following steps: performing real vehicle experiment under a lane changing condition, acquiring an excellent driver steering characteristic parameter, a vehicle dynamics parameter and a track parameter,and forming a lane changing behavior data set; performing training learning for the lane changing data set through the GRU network, and obtaining the excellent driver lane changing imitation model based on the GRU network. In the method provided by the invention, based on strong nonlinear fitting ability of the GRU network on a long-time sequence, one simple and efficient excellent driver lane changing imitation model is realized, further improvement of accuracy of learning can be guaranteed based on fast learning, imitating a lane changing behavior of an excellent driver can be realized better, and in the future, the method has certain referential significance in such field and other prediction problems related to driver models.

The invention discloses a method and device for controlling an air conditioner, the air conditioner, a storage medium and a processor. The method comprises the steps that whether the absolute value ofthe difference value between the current indoor environment parameters and the target indoor environment parameters of the air conditioner is larger than a set threshold value or not is determined; if the absolute value is larger than the set threshold value, the air conditioner is controlled to work at a first work mode, so that the absolute value of the difference value between the current indoor environment parameters and the target indoor environment parameters of the air conditioner is reduced through first adjustment on the current indoor environment parameters; and if the absolute value of the difference value is smaller than or equal to the set threshold value, the air conditioner is controlled to work at a second control mode, so that the absolute value of the difference value between the current indoor environment parameters and the target indoor environment parameters is maintained through second adjustment on the current indoor environment parameters. According to the scheme, the problem that the development process of the air conditioner depends on manual experience too much, and the energy efficiency ratio of the air conditioner cannot be adjusted can be solved, andthe effect of increasing the energy efficiency ratio of the air conditioner is achieved.

The invention discloses an electric vehicle power battery SOC intelligent detection device which is characterized in that the intelligent detection device includes a battery parameter acquisition platform and a battery SOC estimation system, the battery parameter acquisition platform collects real-time parameters of voltage, current and temperature of an electric vehicle power battery group, the battery SOC estimation system estimates an SOC value through the collected parameters, and a battery SOC system is a nonlinear, time-delay and multivariable coupling complex real-time system with a high requirement. According to the device, a problem that a conventional detection device can not obtain an ideal effect of the intelligent detection of the electric vehicle power battery SOC.

The invention discloses an intelligent SOC (State of Charge) prediction device for an electric vehicle power battery, which is characterized by comprising a battery parameter acquisition platform and a battery SOC prediction system, wherein the battery parameter acquisition platform is used to acquire real-time parameters of voltage, current, temperature, and ambient temperature of the vehicle power battery pack; and the battery SOC prediction system is used to predict the battery SOC value through the acquired real-time parameters. The battery SOC is a nonlinear, delayed, multivariable-coupling, and complex real-time system with extremely high real-time performance requirements. The problem that the conventional prediction device can not achieve ideal battery SOC prediction precision effects can be effectively solved.

Provided is a ranging method for overhead line power distribution network single-phase earth faults. The method comprises: using an off line method to inject three-phase symmetric high-voltage pulse to an overhead line power distribution network on a bus end, and sampling zero-module voltage in a preset time window from zero time, to obtain a zero-module voltage waveform; performing energy normalizing processing on the zero-module voltage waveform to obtain an energy normalizing waveform; extracting fault point reflected wave arrival time, front time, front steepness, and wave front energy from the energy normalizing waveform; using the arrival time, front time, front steepness, and wave front energy as input variables of a neural network, and using fault distances as output of the neural network to establish a ranging model. The errors of fault distances obtained by the ranging method for overhead line power distribution network single-phase earth faults are low.

The invention belongs to the field of cutting processing, and particularly discloses a main shaft and workpiece vibration prediction method based on a stack sparse automatic coding network, which comprises the following steps: S1, obtaining main shaft current signals, cutting force signals and main shaft and workpiece actual vibration signals under different cutting processing parameters; S2, inputting the main shaft current signal, the cutting force signal and the cutting machining parameter into a sparse automatic coding network layer for training to obtain a deep time sequence characteristic, inputting the deep time sequence characteristic into a full connection layer, and training the whole network on the basis of a pre-training parameter to obtain a main shaft and workpiece predictionvibration signal; S3, adjusting the stack sparse automatic coding network according to the main shaft and workpiece prediction and actual vibration signals, and completing training to obtain a prediction model; main shaft and workpiece vibration signal prediction in cutting machining is achieved through the prediction model, a dynamic frequency response function can be replaced, a good predictioneffect is achieved in the time domain and the frequency domain, the prediction model can adapt to working conditions of various machining parameter combinations, and the generalization capacity is high.

The invention relates to a river flow forecasting method, comprising the following steps: 1: data preprocessing; 2: VMD model decomposition; 3: component reconstruction of VMD decomposition results; 4: integration of a VMD-BP model and river flow forecasting. Variational mode decomposition is an effective method to process non-stationary signals. A river flow forecasting method based on a VMD-BP model is proposed and established in combination with the advantages of a BP neural network in processing nonlinear function fitting. The method decomposes original data into a plurality of intrinsic mode functions reflecting data characteristics, and smooths the data, thereby solving the problems of nonlinearity and undulation of water level flow data, and improving the forecasting accuracy.

The invention relates to an air knife pressure real-time optimization control method in the galvanizing process. On the basis of a plating thickness neural network prediction model, the corresponding error correction based on variable lag time and the real-time optimization technology based on an increment PID algorithm are adopted, and a good anti-interference and follow-up control effect is adopted. When the plating thickness deviates from a set value because of the outside interference, the air knife pressure is optimized in real time based on the difference between a plating thickness predicted value after being subjected to the error correction, and the set value, and the plating thickness is made to be kept nearby the set value; and during product switching, iterative optimization is performed on the air knife pressure based on a plating thickness predicted value not subjected to the error correction, and the plating thickness is made to fast complete the switching process closely along with a changing curve of the set value. According to the pressure real-time optimization control method in the galvanizing process, bad influences caused to the plating thickness by the outside interference are effectively overcome due to the above technology, fast switching between products in different plating thicknesses is achieved, the plating quality fluctuation can be obviously reduced, the excessive zinc consumption is reduced, and the percent of pass of galvanized products is increased.

The invention discloses an RBF adaptive neural network repetitive controller suitable for a repetitive servo system. According to the controller, the self-adaptive weight adjustment of an RBF neural network is utilized to approximate a servo motor input and output differential equation with unknown parameters; according to a repetitive control method, a control quantity at the current moment is corrected by utilizing the operation information of a previous period, so that periodic interference is overcome, and the tracking of a given periodic reference signal by an output quantity is realized.According to the RBF adaptive neural network repetitive controller suitable for the repetitive servo system, on the basis of the periodic operation characteristics of the repetitive servo system, onone hand, the RBF neural network is utilized to approximate the system model of unknown parameters, and on the other hand, the repetitive control method is introduced to eliminate common periodic interference in an repetitive operation process.

The invention discloses a traffic environment pedestrian multi-dimensional motion feature visual extraction method comprising a step 1 of constructing a pedestrian motion database; a step 2 of extracting a pedestrian detection frame image of the same pedestrian in consecutive image frames; a step 3 of extracting the HOG feature of the same pedestrian motion energy map; a step 4 of constructing a pedestrian motion pose recognition model based on an Elman neural network; a step 5 of determining a pedestrian pose in a current video by using the pedestrian motion pose recognition model based on the Elman neural network; a step 6 of calculating the instantaneous speed sequences of the pedestrian in the X-axis and Y-axis directions to obtain the real-time speed of the pedestrian; and a step 7 ofaccording to a three-dimensional scene in an intersection environment, obtaining the position information of the pedestrian in the image in real time, and obtaining the real-time motion feature of the pedestrian in combination with the pedestrian pose and the real-time speed. The method has high recognition accuracy and good robustness, is convenient to use, and has a good application and promotion space.

The invention provides a respiratory movement prediction method which comprises the following steps of constructing a BP neural network, and optimizing the BP neural network by fusing a simulated annealing genetic algorithm, optimizing a weighting error of the BP neural network, acquiring respiratory movement data and processing the respiratory movement data, training the BP neural network with the optimized weighting error by using the processed respiratory movement data to obtain a strong regression device, and predicting the respiratory movement state of the human body by using a strong regression device. The respiratory movement state of the patient can be predicted with high precision, and the actual tumor is prevented from exceeding the target area, so that the patient can be better subjected to radioactive therapy.

The invention relates to a video image Chinese wolfberry branch detection method for a Chinese wolfberry harvesting and clamping device. Compared with the prior art, the defect that the position of aChinese wolfberry branch is difficult to identify is overcome. The method comprises the following steps: obtaining and preprocessing a training sample; constructing and training a Chinese wolfberry leaf and key point detection network; constructing and training a Chinese wolfberry branch positioning model; collecting and preprocessing video images of the Chinese wolfberry branches to be detected;and obtaining a Chinese wolfberry branch detection result. According to the invention, the selection method of the ROIAlign input feature map in the traditional Mask-RCNN is optimized; meanwhile, description of a target area is improved according to the shape of a Chinese wolfberry leaf, and an inclined frame with a direction is used for replacing a common rectangular frame, so that on the basis of ensuring the data reliability, the memory space is reduced, and the branch identification and positioning accuracy and efficiency are improved.

The invention provides a torque control method for a built-in permanent magnet synchronous motor, which comprises steps of measuring the three-phase currents iA, iB, iC of the motor in a working state; converting the three-phase currents iA, iB, iC to obtain the two-phase currents iD, iQ; converting the the two-phase currents iD, iQ to obtain d-axis and q-axis currents id, iq; inputting the d-axisand q-axis currents id, iq into a trained neural network to obtain the predicted torque; calculating the torque output by the neural network and a torque command by a PI torque controller to output the q-axis current; subjecting the q-axis current to MTPA calculation to obtain the d-axis current corresponding to an MTPA value; inputting the d-axis and q-axis currents into a PI current controllerto obtain the voltage values corresponding to the d-axis and q-axis current values; subjecting the voltage values corresponding to the d-axis and q-axis current values to Park inverse transformation to output a three-phase voltage; passing the three-phase voltage through a SVPWM inverter to output a three-phase AC voltage required for the motor operation. The method uses the torque predicted by the LSTM neural network to form a feedforward compensation system, and uses the advantages of good nonlinear fitting ability, high precision and memory ability of historical data of the LSTM neural network.

The invention discloses a GRNN motorized spindle thermal error modeling method based on genetic algorithm optimization, and the method comprises the steps: building a four-layer generalized regression neural network (GRNN) structure, carrying out the global search of a generalized regression neural network smooth factor sigma through a genetic algorithm, and simply and accurately finding a global minimum value; initializing a generalized regression neural network smooth factor sigma by adopting a random population initialization mode, constructing a fitness function of a genetic algorithm (GA), calculating individual fitness, executing natural operation on a population, and selecting, crossing and inheriting individuals; establishing a GRNN framework, training samples, so population evolution gradually reaches the training precision, and finally, verifying the generalization of a generalized regression neural network (GA-GRNN) optimized by a genetic algorithm by adopting experimental data of different rotating speeds. According to the method, global optimal search is carried out on the smooth factor sigma of the GRNN by using the genetic algorithm, and the prediction precision and generalization ability of the GRNN are improved.

The invention provides a short-term photovoltaic power prediction method based on similar day wavelet transform and a multi-layer perceptron, a power prediction model is established by adopting an artificial intelligence technology, and a short-term photovoltaic power prediction model based on similar day wavelet transform and the multi-layer perceptron is established. According to the model provided by the invention, the advantages of various algorithms are combined, and the prediction accuracy can be effectively improved. The main innovation point of the method is that similar daily wavelet transform and a multilayer perceptron are combined to be used for the research of predicting the output power of the photovoltaic power station.

The invention discloses a personalized HRTF rapid modeling acquisition method, and the method comprises the following steps: S1, performing correlation analysis on a physiological appearance parameter database, and screening out characteristic physiological appearance parameters in combination with physical analysis; S2, performing multiple data dimension reduction on the personalized HRTF database, and extracting a feature matrix corresponding to a sample; S3, establishing, training and fitting a neural network of a relationship between the collected sample feature physiological shape parameters in the personalized HRTF database and the corresponding HRTF feature matrix; S4, inputting feature physiological appearance parameters of the user, predicting an HRTF feature matrix of the user by using the trained neural network, and reconstructing the feature matrix into a complete HRTF database. The method has the advantages that the personalized HRTF corresponding to the user can be rapidly and accurately obtained through a small number of feature physiological shape parameters, and therefore the positioning precision and user experience of the virtual auditory display technology can be improved to a certain degree.

The invention relates to a neural network fault arc detection system based on generalized S transformation. The system comprises a training sample generation module, a neural network training module and a fault arc identification module, the training sample generation module comprises a fault arc experiment and simulation data acquisition module and an arc feature extraction module based on generalized S transformation, and the fault arc identification module comprises a user real-time total load data acquisition and processing module, a neural network model module and a fault identification result module. A neural network fault arc identification method is provided on the basis of the system, an S transformation feature extraction method and a neural network mode identification method are fused, features of fault arc current signals can be accurately captured through S transformation, time-frequency features are grasped, and the problems that in the prior art, feature discrimination is not high, and confusion is prone to occurring are solved. Through verification, the load identification effect of the method has high accuracy, and a technical basis can be provided for a series of advanced applications of a non-intrusive load identification technology.

The invention discloses an intelligent regulation and control method for a high-speed motorized spindle water-cooling system, and the method comprises the steps: building a structure of an RBF neural network, building a four-layer GA-GRNN neural network structure frame and a four-layer generalized regression neural network (GRNN) structure on the improvement of the RBF neural network, and carrying out the global search of a generalized regression neural network smooth factor sigma through a genetic algorithm so that the global minimum value is simply and accurately found; initializing a generalized regression neural network smooth factor sigma by adopting a random population initialization mode; constructing a fitness function of a genetic algorithm (GA), calculating individual fitness, establishing a high-speed motorized spindle thermal characteristic regulation and control cooling medium flow model, so that it is better that the predicted output is closer to an actual value, and adopting the predicted temperature characteristic of a GRNN model to construct the fitness function; performing natural selection operation on the population, and performing selection, crossover and mutation operation on individuals to evolve the population; and repeatedly selecting the fitness function to establish the model and operating the population and the individuals until the precision is met or the maximum number of iterations is met. According to the method, global optimal search is performed on the smooth factor sigma of the GRNN by using the genetic algorithm, so that the prediction precision and generalization ability of the GRNN are improved, and the training precision and robustness of the GRNN are improved.

The invention discloses a three-dimensional dynamic grinding force detection device and its decoupling algorithm, which mainly solves the problems of low natural frequency, narrow measurable dynamic force range and piezoelectric grinding force measurement of the existing resistance strain grinding force measuring instrument. The instrument is complicated to manufacture, expensive, unable to detect static force, the multiple linear regression decoupling algorithm is highly dependent on the linearity of the detection device, and the decoupling effect is unstable. The three-dimensional dynamic grinding force detection device is mainly composed of a base, a column, a support, an elastic thin plate group, an upper cover plate and a resistance strain gauge group. The workpiece to be processed is installed on the upper surface platform through threaded connection. During grinding, the grinding force acts on the workpiece and is transmitted to the column through the upper surface platform, causing the column to deform accordingly, and then transmitted to the three sets of elastics installed in parallel with it. Thin plates, three groups of elastic thin plates are installed in two pairs vertically, causing the three groups of resistance strain gauges pasted on the elastic thin plates to produce corresponding resistance value changes, and after signal conditioning and collection, they are transmitted to the PC, realizing Three-dimensional dynamic grinding force detection. The decoupling algorithm uses the BP neural network as the decoupling model, and optimizes its initial weight and threshold parameters through the genetic algorithm to obtain the optimal decoupling model and realize the high-precision decoupling of the three-dimensional grinding force signal. The invention has ingenious structural design, high natural frequency, wide range of measurable dynamic force, and can measure static force at the same time, with low inter-directional coupling and simple manufacture, which greatly reduces the manufacturing difficulty and production cost of the three-dimensional dynamic grinding force detection device, and at the same time The decoupling algorithm has fast convergence, high precision and high reliability, and has good practical and popularization value.

The invention discloses a hen house environment ammonia gas concentration intelligent monitoring system which is composed of two parts of a hen house environment parameter acquisition platform and a hen house environment ammonia gas concentration intelligent prediction model. The hen house environment ammonia gas concentration intelligent monitoring system based on a CAN field bus is designed in view of difficulties that hen house environment ammonia gas concentration change has characteristics of non-linearity, high time lag, high inertia and time variation and hen house area is relatively large and ammonia gas concentration is difficult to accurately predict. The system is the intelligent monitoring system which realizes detection, intelligent prediction and management of the monitored hen house environment ammonia gas concentration by the hen house environment parameter acquisition platform and the hen house environment ammonia gas concentration intelligent prediction model, and the basis of performing high-quality and high-efficiency purification on hen house environment ammonia gas concentration is provided. The system has wide application prospect and great popularization value.

The invention relates to a method for achieving robot multi-axis-hole assembling through deep reinforcement learning, and belongs to the technical field of robot assembling. The method comprises the steps that in the training process, common experience data and expert experience data which are produced through a traditional fuzzy force control method and a deep reinforcement learning network on the basis of a simulation model are added into an experience data set, experience data are randomly drawn from the experience data set to train the deep reinforcement learning network, and therefore theassembling action of the network can rapidly achieve the assembling level of the traditional fuzzy control method and can exceed the assembling effect of the traditional fuzzy control method if training continues to be carried out. The deep reinforcement learning network trained by the simulation model is directly used for a practical robot multi-axis-hole assembling task. The experience data produced by the simulation model are used for training, the problem that practical assembling environment cannot provide enough training data is solved, and meanwhile the training cost is reduced.

The invention belongs to a method for diagnosing mechanical equipment faults, and provides a method for diagnosing actuator faults combined with multi-channel residuals and deep learning. Use the input and output data of different sensors in the normal state of the system to train multiple neural network observers, then generate multi-channel residuals according to the actual input and output data of the system, and perform feature extraction and fusion on the multi-channel residuals, and finally use deep learning to train and diagnose The model implements fault diagnosis. The multi-channel residual simplifies the data structure while retaining the fault feature information, and reduces the dependence of traditional model methods on expert knowledge and experience. In addition, multi-source information, multi-channel residual feature extraction and deep learning fault diagnosis can make full use of multi-sensor data feature information and the complex data processing advantages of deep learning, and can realize multi-redundant structure actuator fault diagnosis and improve the operating efficiency. Accuracy of actuator fault diagnosis.

The invention discloses a composite insulator pollution risk grade evaluation method based on temperature detection. The method comprises the steps of obtaining temperature rise distribution of a to-be-evaluated composite insulator, relative humidity of an environment where the to-be-evaluated composite insulator is located and an air speed; and inputting the temperature rise distribution of the composite insulator to be evaluated, the relative humidity of the environment and the air speed into the trained neural network to obtain the pollution risk level of the composite insulator. The invention further discloses a corresponding system. According to the method, the neural network is sampled, the pollution risk grade can be obtained only by taking the temperature rise distribution which iseasy to obtain, the relative humidity of the environment and the air speed as input, operation is easy, no specific technical requirement exists for workers, the cost is low, and large-area popularization is facilitated.