An intelligent method and system for monitoring abnormal growth environment of industrial peppers

Abstract

The present invention discloses an intelligent method and system for monitoring abnormalities in the growth environment of industrial peppers. The method includes data collection, preprocessing, establishing an abnormal monitoring model for the growth environment of industrial peppers, and abnormal monitoring of the growth environment of industrial peppers. The present invention belongs to the field of growth environment monitoring, and specifically refers to an intelligent method and system for monitoring abnormalities in the growth environment of industrial peppers. This scheme establishes a drive system and an actual environment response system, defines errors and calculates control inputs in detail, combines control gain parameters, responds to changes in the growth environment variables of industrial peppers, and improves the stability of abnormal monitoring; makes preliminary judgments based on detection time and realizes final abnormal judgments based on error change rate of the growth environment of industrial peppers, thereby ensuring the accuracy and reliability of monitoring; introduces position deviation measurement to dynamically adjust the optimization intensity, thereby improving the suitability for the changeable growth environment of industrial peppers and improving the efficiency of abnormal monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of growth environment monitoring, and in particular to an intelligent method and system for monitoring abnormal growth environment of industrial peppers. Background Art

[0002] The method for monitoring the abnormal growth environment of industrial peppers is a monitoring system based on data-driven and intelligent algorithms, which is used to monitor and identify environmental abnormalities that may affect the normal growth of peppers in real time in large-scale industrial pepper planting environments. This method monitors and analyzes the multi-dimensional variables of the pepper growth environment, and promptly detects and warns of abnormal conditions to ensure the healthy growth and yield of peppers. However, the general method for monitoring the abnormal growth environment of industrial peppers has the problem of false alarms due to noise and short-term fluctuations in the pepper growth environment, and cannot quickly detect abnormal conditions in the pepper growth environment; the general method for monitoring the abnormal growth environment of industrial peppers has the problem that the parameter settings cannot adapt to the changes in complex industrial pepper growth environment data, resulting in low efficiency in monitoring environmental abnormalities. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent industrial pepper growth environment abnormality monitoring method and system. The general industrial pepper growth environment abnormality monitoring method has false alarms due to the noise and short-term fluctuations of the pepper growth environment, and cannot quickly detect the abnormal situation of the pepper growth environment. This solution establishes a drive system and an actual environment response system, defines the error and calculates the control input in detail, and combines the control gain parameters to respond to the changes in the industrial pepper growth environment variables, thereby improving the stability of abnormal monitoring; the final abnormal judgment of the industrial pepper growth environment is achieved based on the preliminary judgment of the detection time and the error change rate, thereby ensuring the accuracy and reliability of monitoring; the general industrial pepper growth environment abnormality monitoring method has the problem that the parameter setting cannot adapt to the changes in the complex industrial pepper growth environment data, thereby resulting in low efficiency of environmental abnormality monitoring. This solution introduces a position deviation metric to dynamically adjust the optimization intensity, optimizes the sensitivity to the optimal solution position during the parameter setting process, designs the inertia weight based on the tangent function and defines the individual fitness based on the sample, thereby improving the adaptability to the changeable industrial pepper growth environment and improving the efficiency of abnormal monitoring.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides an intelligent method for monitoring abnormal growth environment of industrial peppers, the method comprising the following steps:

[0005] Step S1: data collection;

[0006] Step S2: preprocessing;

[0007] Step S3: Establishing an abnormal monitoring model for the growth environment of industrial peppers;

[0008] Step S4: Monitoring of abnormal growth environment of industrial peppers.

[0009] Furthermore, in step S1, the data collection is to collect historical industrial pepper growth environment data; the historical industrial pepper growth environment data includes growth environment data and environment monitoring status; the environment monitoring status includes normal and abnormal; and the environment monitoring status is used as a data label.

[0010] Furthermore, in step S2, the preprocessing is to perform data cleaning, data conversion and standardization on the data collected in step S1; the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into a vector form; and the standardization is to standardize the data based on the maximum and minimum normalization method.

[0011] Further, in step S3, the establishment of an abnormal monitoring model for the growth environment of industrial peppers specifically includes the following steps:

[0012] Step S31: construct a driving system; construct a driving system for the normal growth environment of industrial peppers based on a neural network, expressed as: ;in, and are the predicted values ​​of the lth and mth variables in the industrial pepper growth environment, respectively, and t is the time; yes The rate of change of is the decay rate of the lth variable; is the feedback coefficient of the mth variable to the lth variable; is external input; is the nonlinear activation function of the mth variable; n is the total number of variables;

[0013] Step S32: construct a response system for actual environment detection, expressed as: ;in, and are the true values ​​of the lth and mth variables in the industrial pepper growth environment, respectively; yes The rate of change of is the control input;

[0014] Step S33: define system error; System error It is expressed as: ; Define control input for: ; ; ; ;in, is a sign function; is the response gain; is the adaptive control gain, is the basic control gain; is the gain factor; is the time increment; is a nonlinear index; is the dynamic threshold; is the static control quantity; is the derivative of the error of the lth variable; is a smoothing term; is the basic feedback coefficient; is the enhancement coefficient; is the sum of errors; is the basic threshold; k2 is the amplification factor; is the L1 norm;

[0015] Step S34: define the control gain parameter; expressed as:

[0016] ;

[0017] ;

[0018] ;

[0019] Where A is the minimum control gain; is the amplification factor of the mth variable to the lth variable; B is the adjustment coefficient of the adaptive control gain; C is the sum of the static control gains; is the fuzzy feedback amplification factor; is a set of variables; is the minimum feedback coefficient; is the maximum feedback coefficient;

[0020] Step S35: Calculate the detection time, detection time It is expressed as: ; Pre-set the detection threshold. When the detection time is higher than the detection threshold, it is judged as a preliminary abnormality;

[0021] Step S36: Final monitoring and determination; calculating the error change rate, expressed as: ; D is the error change rate; the error change rate is determined for the data determined to be initially abnormal, and an error threshold is set in advance. When the error change rate is higher than the error threshold, the monitoring data is finally determined to be abnormal, and the relevant personnel are notified for early warning processing;

[0022] Step S37: model verification; pre-dividing the preprocessed data set into a test set and a training set; using the cross entropy loss function and updating the parameters based on the gradient descent method; when the industrial pepper growth environment abnormality monitoring model converges to the training set, the industrial pepper growth environment abnormality monitoring model is established; a prediction threshold is set in advance, and when the prediction accuracy of the established industrial pepper growth environment abnormality monitoring model for the test set is higher than the prediction threshold, the industrial pepper growth environment abnormality monitoring model is established; otherwise, the data set is re-divided and the initial parameters are adjusted;

[0023] Step S38: initial parameter adjustment; specifically including:

[0024] Step S381: construct parameter adjustment space based on feedback coefficient, attenuation rate, basic control gain, gain coefficient, basic feedback coefficient, enhancement coefficient, basic threshold, amplification coefficient, fuzzy feedback amplification coefficient, and amplification factor; initialize the optimization population to a uniform distribution; introduce position deviation measurement and inertia weight to update individual positions; the update strategy of the optimization individual is expressed as: ; ; ; ;in, and are the positions of the t1+1th iteration and the t1th iteration of the dth dimension of the i-th individual, respectively; and are the speeds of the t1+1th iteration and the t1th iteration of the dth dimension of the ith individual, respectively; is the inertia weight; is the position deviation measure; c1 is the learning factor; rand is a random number between 0 and 1; and are the optimal individual position and the random individual position respectively; n1 is the measurement variable; and are the initial inertia and final inertia respectively; tanh(·) is the tangent function; is the adjustment coefficient; T is the maximum number of iterations; is the control coefficient; is the initial deviation;

[0025] Step S382: define individual fitness; expressed as: ;

[0026] Among them, f(·) is the individual fitness value; is the training set sample size; and are the predicted labels and the actual labels respectively.

[0027] Furthermore, in step S4, the abnormal growth environment monitoring of industrial peppers is based on the established abnormal growth environment monitoring model of industrial peppers; the ambient temperature, ambient humidity, soil humidity, light intensity, carbon dioxide concentration, soil temperature, soil pH value, air flow velocity, conductivity and rainfall are collected in real time; and they are input into the abnormal growth environment monitoring model of industrial peppers after preprocessing; the environmental monitoring status predicted by the model is used as the monitoring result, and when the monitoring result is abnormal, the management personnel are given an early warning.

[0028] The present invention provides an intelligent industrial pepper growth environment abnormality monitoring system, comprising a data acquisition module, a preprocessing module, an industrial pepper growth environment abnormality monitoring model establishment module and an industrial pepper growth environment abnormality monitoring module;

[0029] The data acquisition module collects historical industrial pepper growth environment data and sends the data to the preprocessing module;

[0030] The preprocessing module performs data cleaning, data conversion and standardization on the collected data; and sends the data to the industrial pepper growth environment abnormality monitoring model establishment module;

[0031] The industrial pepper growth environment abnormality monitoring model establishment module establishes a drive system and an actual environment response system, defines errors, and combines control gain parameters; makes a preliminary judgment based on the detection time and realizes the final abnormality judgment of the industrial pepper growth environment based on the error change rate; dynamically adjusts the optimization intensity by introducing the position deviation metric, designs the inertia weight based on the tangent function and defines the individual fitness based on the sample to realize parameter adjustment; and then completes the establishment of the industrial pepper growth environment abnormality monitoring model; and sends the data to the industrial pepper growth environment abnormality monitoring module;

[0032] The industrial pepper growth environment abnormality monitoring module realizes the industrial pepper growth environment abnormality monitoring based on the established industrial pepper growth environment abnormality monitoring model.

[0033] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0034] (1) In view of the problem that the general abnormal monitoring method of the industrial pepper growth environment has false alarms due to the noise and short-term fluctuations of the pepper growth environment, and cannot quickly detect abnormal conditions in the pepper growth environment, this scheme establishes a drive system and an actual environment response system, defines the error and calculates the control input precisely, combines the control gain parameters, responds to the changes in the industrial pepper growth environment variables, and improves the stability of abnormal monitoring; the final abnormal judgment of the industrial pepper growth environment is achieved based on the preliminary judgment of the detection time and the error change rate, thereby ensuring the accuracy and reliability of monitoring.

[0035] (2) In view of the problem that the parameter settings of general industrial pepper growth environment anomaly monitoring methods cannot adapt to the changes in complex industrial pepper growth environment data, resulting in low efficiency of environmental anomaly monitoring, this scheme introduces position deviation measurement to dynamically adjust the optimization intensity, optimizes the sensitivity to the optimal solution position during parameter setting, designs inertia weights based on tangent functions and defines individual fitness based on samples, thereby improving the adaptability to the changeable industrial pepper growth environment and improving the efficiency of anomaly monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a process of an intelligent method for monitoring abnormal growth environment of industrial peppers provided by the present invention;

[0037] Figure 2 A schematic diagram of an intelligent industrial pepper growth environment abnormality monitoring system provided by the present invention;

[0038] Figure 3 It is a schematic diagram of the process of step S3.

[0039] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0041] In the description of the present invention, it is necessary to understand that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred system or element must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0042] Example 1, see Figure 1 The present invention provides an intelligent method for monitoring abnormal growth environment of industrial peppers, which comprises the following steps:

[0043] Step S1: data collection, collecting historical industrial pepper growth environment data;

[0044] Step S2: preprocessing, data cleaning, data conversion and standardization of the collected data;

[0045] Step S3: Establish an abnormal monitoring model for the growth environment of industrial peppers, establish a drive system and an actual environment response system, define errors, and combine control gain parameters; make a preliminary judgment based on the detection time and realize the final abnormal judgment of the growth environment of industrial peppers based on the error change rate; dynamically adjust the optimization intensity by introducing the position deviation metric, design the inertia weight based on the tangent function and define the individual fitness based on the sample to achieve parameter adjustment; and then complete the establishment of the abnormal monitoring model for the growth environment of industrial peppers;

[0046] Step S4: abnormality monitoring of the growth environment of industrial peppers, based on the established abnormality monitoring model for the growth environment of industrial peppers to realize abnormality monitoring of the growth environment of industrial peppers.

[0047] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the historical industrial pepper growth environment data includes growth environment data and environment monitoring status; the growth environment data includes ambient temperature, ambient humidity, soil humidity, light intensity, carbon dioxide concentration, soil temperature, soil pH value, air flow velocity, conductivity, time and rainfall; the environment monitoring status includes normal and abnormal; the environment monitoring status is used as a data label.

[0048] Example 3, see Figure 1 This embodiment is based on the above embodiment. In step S2, data cleaning is to process missing values ​​and duplicate values; data conversion is to convert data into vector form; and standardization processing is to standardize data based on the maximum and minimum normalization method.

[0049] Example 4, see Figure 1 and Figure 3 Based on the above embodiment, in step S3, establishing an abnormal monitoring model for the growth environment of industrial peppers specifically includes the following steps:

[0050] Step S31: construct a driving system; construct a driving system for the normal growth environment of industrial peppers based on a neural network, expressed as: ;in, and are the predicted values ​​of the lth and mth variables in the industrial pepper growth environment, respectively, and t is the time; yes The rate of change of is the decay rate of the lth variable; is the feedback coefficient of the mth variable to the lth variable; is external input; is the nonlinear activation function of the mth variable, and the sigmoid activation function is selected; n is the total number of variables; is the L1 norm;

[0051] Step S32: construct a response system for actual environment detection, expressed as: ;in, and are the true values ​​of the lth and mth variables in the industrial pepper growth environment, respectively; yes The rate of change of is the control input;

[0052] Step S33: define system error; System error It is expressed as: ; Define control input for: ; ; ; ;in, is a sign function; is the response gain; is the adaptive control gain, is the basic control gain; is the gain factor; is the time increment; is a nonlinear index; is the dynamic threshold; is the static control quantity; is the derivative of the error of the lth variable; is a smoothing term; is the basic feedback coefficient; is the enhancement coefficient; is the sum of errors; is the basic threshold; k2 is the amplification factor;

[0053] Step S34: define the control gain parameter; expressed as:

[0054] ;

[0055] ;

[0056] ;

[0057] Where A is the minimum control gain; is the amplification factor of the mth variable on the lth variable; is the L1 norm; B is the adjustment coefficient of the adaptive control gain; C is the sum of the static control gains; is the fuzzy feedback amplification factor; is a set of variables; is the minimum feedback coefficient; is the maximum feedback coefficient;

[0058] Step S35: Calculate the detection time, detection time It is expressed as: ; Pre-set the detection threshold. When the detection time is higher than the detection threshold, it is judged as a preliminary abnormality;

[0059] Step S36: Final monitoring and determination; calculating the error change rate, expressed as: ; D is the error change rate; the error change rate is determined for the data determined to be initially abnormal, and an error threshold is set in advance. When the error change rate is higher than the error threshold, the monitoring data is finally determined to be abnormal, and the relevant personnel are notified for early warning processing;

[0060] Step S37: model verification; pre-dividing the preprocessed data set into a test set and a training set; using the cross entropy loss function and updating the parameters based on the gradient descent method; when the industrial pepper growth environment abnormality monitoring model converges to the training set, the industrial pepper growth environment abnormality monitoring model is established; a prediction threshold is set in advance, and when the prediction accuracy of the established industrial pepper growth environment abnormality monitoring model for the test set is higher than the prediction threshold, the industrial pepper growth environment abnormality monitoring model is established; otherwise, the data set is re-divided and the initial parameters are adjusted;

[0061] Step S38: initial parameter adjustment.

[0062] By performing the above operations, the general abnormal monitoring method of the industrial pepper growth environment has false alarms due to the noise and short-term fluctuations in the pepper growth environment, and cannot quickly detect abnormal conditions in the pepper growth environment. This solution establishes a drive system and an actual environment response system, defines errors and calculates control inputs precisely, and combines control gain parameters to respond to changes in industrial pepper growth environment variables and improve the stability of abnormal monitoring; it makes preliminary judgments based on detection time and final abnormal judgments based on the error change rate to ensure the accuracy and reliability of monitoring.

[0063] Example 5, see Figure 3 This embodiment is based on the above embodiment. In step S3, the initial parameter adjustment specifically includes the following steps:

[0064] Step S381: construct parameter adjustment space based on feedback coefficient, attenuation rate, basic control gain, gain coefficient, basic feedback coefficient, enhancement coefficient, basic threshold, amplification coefficient, fuzzy feedback amplification coefficient, and amplification factor; initialize the optimization population to a uniform distribution; introduce position deviation measurement and inertia weight to update individual positions; the update strategy of the optimization individual is expressed as: ; ; ; ;in, and are the positions of the t1+1th iteration and the t1th iteration of the dth dimension of the i-th individual, respectively; and are the speeds of the t1+1th iteration and the t1th iteration of the dth dimension of the ith individual, respectively; is the inertia weight; is the position deviation measure; c1 is the learning factor; rand is a random number between 0 and 1; and are the optimal individual position and the random individual position respectively; n1 is the measurement variable; and are the initial inertia and final inertia respectively; tanh(·) is the tangent function; is the adjustment coefficient; T is the maximum number of iterations; is the control coefficient; is the initial deviation;

[0065] Step S382: define individual fitness; expressed as: ;

[0066] Among them, f(·) is the individual fitness value; is the training set sample size; and are the predicted labels and the actual labels respectively.

[0067] By performing the above operations, the problem of low efficiency of environmental anomaly monitoring due to the inability of parameter settings to adapt to changes in complex industrial pepper growth environment data in general industrial pepper growth environment monitoring methods is solved. This scheme introduces position deviation measurement to dynamically adjust the optimization intensity, optimizes the sensitivity to the optimal solution position during parameter setting, designs inertia weights based on tangent functions, and defines individual fitness based on samples, thereby improving the adaptability to the changeable industrial pepper growth environment and the efficiency of anomaly monitoring.

[0068] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S4, the abnormal monitoring of the industrial pepper growth environment is based on the established abnormal monitoring model of the industrial pepper growth environment; the ambient temperature, ambient humidity, soil humidity, light intensity, carbon dioxide concentration, soil temperature, soil pH value, air flow velocity, conductivity and rainfall are collected in real time; after preprocessing, they are input into the abnormal monitoring model of the industrial pepper growth environment; the environmental monitoring status predicted by the model is used as the monitoring result, and when the monitoring result is abnormal, the management personnel are warned.

[0069] Embodiment 7, see Figure 2 , this embodiment is based on the above embodiment, and the present invention provides an intelligent industrial pepper growth environment abnormality monitoring system, including a data acquisition module, a preprocessing module, an industrial pepper growth environment abnormality monitoring model establishment module and an industrial pepper growth environment abnormality monitoring module;

[0070] The data acquisition module collects historical industrial pepper growth environment data and sends the data to the preprocessing module;

[0071] The preprocessing module performs data cleaning, data conversion and standardization on the collected data; and sends the data to the industrial pepper growth environment abnormality monitoring model establishment module;

[0072] The industrial pepper growth environment abnormality monitoring model establishment module establishes a drive system and an actual environment response system, defines errors, and combines control gain parameters; makes a preliminary judgment based on the detection time and realizes the final abnormality judgment of the industrial pepper growth environment based on the error change rate; dynamically adjusts the optimization intensity by introducing the position deviation metric, designs the inertia weight based on the tangent function and defines the individual fitness based on the sample to realize parameter adjustment; and then completes the establishment of the industrial pepper growth environment abnormality monitoring model; and sends the data to the industrial pepper growth environment abnormality monitoring module;

[0073] The industrial pepper growth environment abnormality monitoring module realizes the industrial pepper growth environment abnormality monitoring based on the established industrial pepper growth environment abnormality monitoring model.

[0074] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0075] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0076] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An intelligent method for monitoring abnormal growth environment of industrial peppers, characterized by: The method comprises the following steps: Step S1: data collection, collecting historical industrial pepper growth environment data; the historical industrial pepper growth environment data includes growth environment data and environmental monitoring status; the growth environment data includes ambient temperature, ambient humidity, soil humidity, light intensity, carbon dioxide concentration, soil temperature, soil pH value, air flow velocity, conductivity, time and rainfall; Step S2: preprocessing; Step S3: Establish an abnormal monitoring model for the growth environment of industrial peppers; establish a drive system and an actual environment response system, define errors, and realize the final abnormal judgment of the growth environment of industrial peppers based on the error change rate; Step S4: abnormality monitoring of the growth environment of industrial peppers, realizing abnormality monitoring of the growth environment of industrial peppers based on the established abnormality monitoring model of the growth environment of industrial peppers; Step S3 includes step S33: defining a system error; a system error It is expressed as: ; Define control input for: ; ; ; ;in, is a sign function; is the response gain; is the adaptive control gain, is the basic control gain; is the gain factor; is the time increment; is a nonlinear index; is the dynamic threshold; is the static control quantity; is the derivative of the error of the lth variable; is a smoothing term; is the basic feedback coefficient; is the enhancement coefficient; is the sum of errors; is the basic threshold; k2 is the amplification factor; is the predicted value of the lth variable in the industrial pepper growth environment, and t is the time; is the true value of the lth variable in the industrial pepper growing environment; yes The rate of change of is the L1 norm.

2. The intelligent method for monitoring abnormal growth environment of industrial peppers according to claim 1 is characterized in that: In step S3, the establishment of an abnormal monitoring model for the growth environment of industrial peppers specifically includes the following steps: Step S31: construct a driving system; construct a driving system for the normal growth environment of industrial peppers based on a neural network, expressed as: ;in, and are the predicted values ​​of the lth and mth variables in the industrial pepper growth environment, respectively, and t is the time; yes The rate of change of is the decay rate of the lth variable; is the feedback coefficient of the mth variable to the lth variable; is external input; is the nonlinear activation function of the mth variable; n is the total number of variables; Step S32: construct a response system for actual environment detection, expressed as: ;in, and are the true values ​​of the lth and mth variables in the industrial pepper growth environment, respectively; yes The rate of change of is the control input; Step S33: define the system error; Step S34: define the control gain parameter; expressed as: ； ； ； Where A is the minimum control gain; is the amplification factor of the mth variable to the lth variable; B is the adjustment coefficient of the adaptive control gain; C is the sum of the static control gains; is the fuzzy feedback amplification factor; is a set of variables; is the minimum feedback coefficient; is the maximum feedback coefficient; Step S35: Calculate the detection time, detection time It is expressed as: ; Pre-set the detection threshold. When the detection time is higher than the detection threshold, it is judged as a preliminary abnormality; Step S36: Final monitoring and determination; calculating the error change rate, expressed as: ; D is the error change rate; the error change rate is determined for the data determined to be initially abnormal, and an error threshold is set in advance. When the error change rate is higher than the error threshold, the monitoring data is finally determined to be abnormal, and the relevant personnel are notified for early warning processing; Step S37: model verification; pre-dividing the preprocessed data set into a test set and a training set; using the cross entropy loss function and updating the parameters based on the gradient descent method; when the industrial pepper growth environment abnormality monitoring model converges to the training set, the industrial pepper growth environment abnormality monitoring model is established; a prediction threshold is set in advance, and when the prediction accuracy of the established industrial pepper growth environment abnormality monitoring model for the test set is higher than the prediction threshold, the industrial pepper growth environment abnormality monitoring model is established; otherwise, the data set is re-divided and the initial parameters are adjusted; Step S38: initial parameter adjustment.

3. The intelligent method for monitoring abnormal growth environment of industrial pepper according to claim 2 is characterized in that: In step S38, the initial parameter adjustment specifically includes: Step S381: construct parameter adjustment space based on feedback coefficient, attenuation rate, basic control gain, gain coefficient, basic feedback coefficient, enhancement coefficient, basic threshold, amplification coefficient, fuzzy feedback amplification coefficient, and amplification factor; initialize the optimization population to a uniform distribution; introduce position deviation measurement and inertia weight to update individual positions; the update strategy of the optimization individual is expressed as: ; ; ; ;in, and are the positions of the t1+1th iteration and the t1th iteration of the dth dimension of the i-th individual, respectively; and are the speeds of the t1+1th iteration and the t1th iteration of the dth dimension of the ith individual, respectively; is the inertia weight; is the position deviation measure; c1 is the learning factor; rand is a random number between 0 and 1; and are the optimal individual position and the random individual position respectively; n1 is the measurement variable; and are the initial inertia and final inertia respectively; tanh(·) is the tangent function; is the adjustment coefficient; T is the maximum number of iterations; is the control coefficient; is the initial deviation; Step S382: define individual fitness; expressed as: ; Among them, f(·) is the individual fitness value; is the training set sample size; and are the predicted labels and the actual labels respectively.

4. The intelligent method for monitoring abnormal growth environment of industrial peppers according to claim 1 is characterized in that: In step S1, the environmental monitoring status includes normal and abnormal; the environmental monitoring status is used as a data label.

5. The intelligent method for monitoring abnormal growth environment of industrial pepper according to claim 1 is characterized in that: In step S4, the abnormal growth environment monitoring of industrial peppers is based on the established abnormal growth environment monitoring model of industrial peppers; the ambient temperature, ambient humidity, soil humidity, light intensity, carbon dioxide concentration, soil temperature, soil pH value, air flow velocity, conductivity and rainfall are collected in real time; after pre-processing, they are input into the abnormal growth environment monitoring model of industrial peppers; the environmental monitoring status predicted by the model is used as the monitoring result, and when the monitoring result is abnormal, the management personnel are warned.

6. The intelligent method for monitoring abnormal growth environment of industrial peppers according to claim 1 is characterized by: In step S2, the preprocessing is to perform data cleaning, data conversion and standardization on the data collected in step S1; the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into a vector form; and the standardization is to standardize the data based on the maximum and minimum normalization method.

7. An intelligent industrial pepper growth environment abnormality monitoring system, used to implement an intelligent industrial pepper growth environment abnormality monitoring method as described in any one of claims 1 to 6, characterized in that: It includes a data acquisition module, a preprocessing module, an industrial pepper growth environment abnormality monitoring model establishment module and an industrial pepper growth environment abnormality monitoring module; The data acquisition module collects historical industrial pepper growth environment data and sends the data to the preprocessing module; The preprocessing module performs data cleaning, data conversion and standardization on the collected data; and sends the data to the industrial pepper growth environment abnormality monitoring model establishment module; The industrial pepper growth environment abnormality monitoring model establishment module establishes a drive system and an actual environment response system, defines an error, and combines a control gain parameter; a preliminary judgment based on the detection time and a final abnormal judgment based on the error change rate are realized; By introducing the position deviation metric to dynamically adjust the optimization intensity, the inertia weight is designed based on the tangent function and the individual fitness is defined based on the sample to achieve parameter adjustment; thus completing the establishment of the abnormal monitoring model for the growth environment of industrial peppers; and sending the data to the abnormal monitoring module for the growth environment of industrial peppers; The industrial pepper growth environment abnormality monitoring module realizes the industrial pepper growth environment abnormality monitoring based on the established industrial pepper growth environment abnormality monitoring model.

Images