Chrysanthemum production quality prediction system and method

Abstract

The invention discloses a chrysanthemum production quality prediction system and method. The system comprises a data monitoring module, a quality prediction module, an optimization module, an intelligent control module and an irrigation, illumination, temperature control, nutrition supply and carbon dioxide supply system. The data monitoring module collects production parameters in real time and transmits the production parameters to the quality prediction module, and the quality prediction module carries out quality prediction on the current production parameters through a data model. And the prediction result is transmitted to the optimization module, and control data is generated by the optimization module. And control data is transmitted to each environment regulation and control system through the intelligent control module, so that the growth environment of the chrysanthemum is intelligently regulated, and the quality is optimized. The whole structure is simple, and automatic management and quality optimization in the chrysanthemum growth process are achieved by introducing the real-time data monitoring module, the quality prediction module and the intelligent control module into the prediction system.

Description

Technical Field

[0001] The present invention relates to the field of chrysanthemum production, and in particular to a chrysanthemum production quality prediction system and method. Background Art

[0002] High-quality chrysanthemum crops are the key to producing high-quality inulin. The growth environment and quality of chrysanthemum crops during the growth process directly affect the quality of inulin. The quality of chrysanthemum crops needs to be strictly controlled during the production process to ensure the quality of inulin. At present, most chrysanthemum production methods rely on simple sensor data acquisition to judge the growth status of chrysanthemums. Although these sensors can provide basic environmental information such as humidity, light, temperature, soil nutrient level and carbon dioxide concentration, the system only stays at monitoring the current state and cannot realize dynamic prediction of growth trends. This monitoring method often cannot respond in time when abnormal conditions or environmental fluctuations occur, resulting in the growth state of chrysanthemums being affected and affecting the overall quality. Therefore, in order to solve the above problems, a chrysanthemum production quality prediction system and method are needed. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention proposes a chrysanthemum production quality prediction system and method. Among them, the specific technical scheme of a chrysanthemum production quality prediction system is as follows:

[0004] A chrysanthemum production quality prediction system, characterized by:

[0005] It includes data monitoring module, quality prediction module, optimization module, intelligent control module, irrigation system, lighting system, temperature control system, nutrition supply system and carbon dioxide supply system;

[0006] The data monitoring module is used to collect production parameters in real time;

[0007] The data monitoring module is connected to the quality prediction module, and the data monitoring module is used to transmit the collected data to the quality prediction module, and the quality prediction module is used to predict the quality by using the current production parameters through the data model;

[0008] The quality prediction module is connected to the optimization module, and the quality prediction module is used to send prediction data to the optimization module;

[0009] The output end of the optimization module is connected to the input port of the intelligent control module, the optimization module generates control data according to the analysis data, and the control port of the intelligent control module communicates with the irrigation system, lighting system, temperature control system, nutrient supply system and carbon dioxide supply system through a channel.

[0010] In order to better realize the present invention, it is possible to further:

[0011] It includes an early warning module, which is connected to the optimization module. The optimization module is used to send an alarm signal to remind supervisors when quality abnormalities are predicted.

[0012] Furthermore: it includes a display module, the display module is connected to the optimization module, and the display module is used to display the current environmental parameters, quality prediction results and control status in real time.

[0013] Furthermore: the data acquisition module is used to collect parameters of humidity, light, temperature, soil nutrient level and carbon dioxide concentration in real time.

[0014] Furthermore: the quality prediction module includes a random forest model, the random forest model is used to predict quality, and the optimization module is preset with a fuzzy rule model and a fuzzy rule base.

[0015] A working method of a chrysanthemum production quality prediction system, the specific technical scheme is as follows:

[0016] A working method of a chrysanthemum production quality prediction system, characterized in that:

[0017] The process includes:

[0018] S1: The data monitoring module collects humidity, light, temperature, soil nutrient level and carbon dioxide concentration parameters in the chrysanthemum growth environment in real time, and transmits the collected environmental parameters to the quality prediction module;

[0019] S2: The quality prediction module predicts the quality of chrysanthemums using a random forest model to generate quality prediction data and key features, and the quality prediction module transmits the quality prediction data and influencing features to the optimization module;

[0020] S3: The optimization module maps key features into fuzzy variables through a fuzzy logic model;

[0021] S4: The optimization module performs fuzzy reasoning on fuzzy variables based on the fuzzy rule base to generate corresponding control strategies;

[0022] S5: The optimization module transmits the generated control strategy data to the intelligent control module;

[0023] S6: The intelligent control module receives the control strategy data and automatically adjusts the operating states of the irrigation system, the lighting system, the temperature control system, the nutrient supply system and the carbon dioxide supply system to optimize the growth environment of the chrysanthemums.

[0024] To better implement the present invention, the following steps may be further included:

[0025] S7: When the prediction quality is lower than the set standard, the optimization module generates an alarm signal through the early warning module to remind the management personnel;

[0026] S8: The display module displays the current data stream in real time.

[0027] Further: the data monitoring module collects the humidity, light, temperature, soil nutrient level and carbon dioxide concentration parameters in the chrysanthemum growth environment in real time, forms a feature vector x(t) after preprocessing, and the data monitoring module transmits the feature vector x(t) to the quality prediction module;

[0028] Where x(t) = [x1(t), x2(t), x3(t), x4(t), x5(t)];

[0029] x1(t) is the humidity feature, x2(t) is the light feature, x3(t) is the temperature feature, x4(t) is the soil feature, and x5(t) is the gas feature.

[0030] Further: in S2, the quality prediction module is preset with a random forest model M, and the random forest model M includes N decision trees {T1, T1, ..., T N}, when the quality prediction module inputs the feature vector x(t), the random forest model outputs the predicted average value of N decision trees

[0031]

[0032] The random forest model M calculates the feature x for the splitting node of each tree in the N decision trees. j The amount of impurity reduction during splitting I j , and obtain the feature contribution f of the random forest model M j :

[0033]

[0034] Among them, I j (T i ) is the decision tree T i In the feature x j Contribution to impurity reduction;

[0035] The random forest model M sorts the feature contributions from large to small to obtain key features;

[0036] The quality prediction module predicts the average And the key feature set {x j ∣f j ≥θ} is sent to the optimization module, where θ is the feature importance threshold.

[0037] The beneficial effects of the present invention are as follows: the overall structure is simple, and the automatic management and quality optimization of chrysanthemum growth process are realized by introducing real-time data monitoring, quality prediction and intelligent control modules in the prediction system. Environmental parameters are collected in real time by the data monitoring module, and after these data are transmitted to the quality prediction module, they are analyzed and predicted by the random forest model, so as to obtain the evaluation data of chrysanthemum quality and its influencing characteristics. Then, the system uses the fuzzy logic model and the rule base for fuzzy reasoning, maps important features into fuzzy variables, and generates an accurate control strategy adapted to the current environment. By transmitting the optimized control strategy to the intelligent control module, the system can automatically adjust the operating status of irrigation, lighting, temperature control, nutrient supply and carbon dioxide supply systems to meet the optimal growth requirements of chrysanthemum crops. At the same time, the early warning module promptly reminds the supervisor when the quality prediction is abnormal. The display module is provided to display the environmental parameters, quality prediction results and control status in real time, so as to facilitate the operator to carry out real-time monitoring and adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is the overall architecture diagram of the present invention;

[0039] Figure 2 It is the work flow chart of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with 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 of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] like Figure 1 As shown:

[0042] A specific technical solution of a chrysanthemum production quality prediction system is as follows:

[0043] A chrysanthemum production quality prediction system includes a data monitoring module, a quality prediction module, an optimization module, an intelligent control module, an irrigation system, a lighting system, a temperature control system, a nutrient supply system and a carbon dioxide supply system, an early warning module and a display module. The data monitoring module is used to collect production parameters in real time;

[0044] The data monitoring module is connected to the quality prediction module. The data monitoring module is used to transmit the collected data to the quality prediction module. The data collection module is used to collect parameters such as humidity, light, temperature, soil nutrient level and carbon dioxide concentration in real time.

[0045] The quality prediction module is used to predict the quality by using the current production parameters through the data model. The quality prediction module includes a random forest model, which is used to predict the quality. The optimization module is preset with a fuzzy rule model and a fuzzy rule base.

[0046] The quality prediction module is connected to the optimization module, and the quality prediction module is used to send the prediction data to the optimization module;

[0047] The output end of the optimization module is connected to the input port of the intelligent control module. The optimization module generates control data based on the analysis data. The control port of the intelligent control module communicates with the irrigation system, lighting system, temperature control system, nutrient supply system and carbon dioxide supply system through the channel.

[0048] The irrigation system is used to adjust the water supply according to the control signal and optimize the humidity level. The lighting system is used to adjust the lighting duration and intensity according to the control signal to maintain the best lighting conditions. The temperature control system is used to adjust the ambient temperature according to the control signal to keep the temperature within the ideal range for inulin production. The nutrient supply system is used to adjust the concentration and application frequency of the nutrient solution according to the control signal to ensure that the nutritional needs of the inulin plant are met. The carbon dioxide supply system is used to adjust the carbon dioxide concentration according to the control signal to improve the photosynthesis efficiency of the plant and promote the improvement of inulin quality.

[0049] The early warning module is connected to the optimization module, and the optimization module is used to send out an alarm signal to remind supervisors when quality abnormalities are predicted.

[0050] The display module is connected to the data and optimization module, and is used to display the current environmental parameters, quality prediction results and control status in real time.

[0051] A working method of a chrysanthemum production quality prediction system, the specific technical scheme is as follows:

[0052] A working method of a chrysanthemum production quality prediction system includes the following process:

[0053] S1: The data monitoring module collects humidity, light, temperature, soil nutrient level and carbon dioxide concentration parameters in the chrysanthemum growth environment in real time, and transmits the collected environmental parameters to the quality prediction module;

[0054] Specifically: the data monitoring module collects the humidity, light, temperature, soil nutrient level and carbon dioxide concentration parameters in the chrysanthemum growth environment in real time, forms a feature vector x(t) after preprocessing, and transmits the feature vector x(t) to the quality prediction module;

[0055] Where x(t) = [x1(t), x2(t), x3(t), x4(t), x5(t)];

[0056] x1(t) is the humidity feature, x2(t) is the light feature, x3(t) is the temperature feature, x4(t) is the soil feature, and x5(t) is the gas feature.

[0057] S2: The quality prediction module predicts the quality of chrysanthemums using a random forest model to generate quality prediction data and key features, and the quality prediction module transmits the quality prediction data and influencing features to the optimization module;

[0058] Specifically: the quality prediction module is preset with a random forest model M, which includes N decision trees {T1, T1, ..., T N}, when the quality prediction module inputs the feature vector x(t), the random forest model outputs the predicted average value of N decision trees

[0059]

[0060] The random forest model M calculates the feature x for the splitting node of each tree in the N decision trees. j The amount of impurity reduction during splitting I j , and obtain the feature contribution f of the random forest model M j :

[0061]

[0062] Among them, I j (T i ) is the decision tree T i In the feature x j Contribution to impurity reduction;

[0063] The random forest model M sorts the feature contributions from large to small to obtain key features;

[0064] The quality prediction module predicts the average And the key feature set {x j ∣f j ≥θ} is sent to the optimization module, where θ is the feature importance threshold.

[0065] S3: The optimization module maps key features into fuzzy variables through a fuzzy logic model;

[0066] S4: The optimization module performs fuzzy reasoning on fuzzy variables based on the fuzzy rule base to generate corresponding control strategies;

[0067] S5: The optimization module transmits the generated control strategy data to the intelligent control module;

[0068] S6: The intelligent control module receives the control strategy data and automatically adjusts the operating states of the irrigation system, the lighting system, the temperature control system, the nutrient supply system and the carbon dioxide supply system to optimize the growth environment of the chrysanthemums.

[0069] S7: When the prediction quality is lower than the set standard, the optimization module generates an alarm signal through the early warning module to remind the management personnel;

[0070] S8: The display module displays the current data stream in real time.

[0071] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0072] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A chrysanthemum production quality prediction system, characterized by: It includes data monitoring module, quality prediction module, optimization module, intelligent control module, irrigation system, lighting system, temperature control system, nutrition supply system and carbon dioxide supply system; The data monitoring module is used to collect production parameters in real time; The data monitoring module is connected to the quality prediction module, and the data monitoring module is used to transmit the collected data to the quality prediction module, and the quality prediction module is used to predict the quality by using the current production parameters through the data model; The quality prediction module is connected to the optimization module, and the quality prediction module is used to send prediction data to the optimization module; The output end of the optimization module is connected to the input port of the intelligent control module, the optimization module generates control data according to the analysis data, and the control port of the intelligent control module communicates with the irrigation system, lighting system, temperature control system, nutrient supply system and carbon dioxide supply system through a channel.

2. A chrysanthemum production quality prediction system according to claim 1, characterized in that: It includes an early warning module, which is connected to the optimization module. The optimization module is used to send an alarm signal to remind supervisors when quality abnormalities are predicted.

3. A chrysanthemum production quality prediction system according to claim 2, characterized in that: It includes a display module, which is connected to the optimization module and is used to display current environmental parameters, quality prediction results and control status in real time.

4. A chrysanthemum production quality prediction system according to claim 3, characterized in that: The data acquisition module is used to collect parameters of humidity, light, temperature, soil nutrient level and carbon dioxide concentration in real time.

5. A chrysanthemum production quality prediction system according to claim 4, characterized in that: The quality prediction module includes a random forest model, which is used to predict quality. The optimization module is preset with a fuzzy rule model and a fuzzy rule base.

6. A working method of a chrysanthemum production quality prediction system according to claim 5, characterized in that: The process includes: S1: The data monitoring module collects humidity, light, temperature, soil nutrient level and carbon dioxide concentration parameters in the chrysanthemum growth environment in real time, and transmits the collected environmental parameters to the quality prediction module; S2: The quality prediction module predicts the quality of chrysanthemums using a random forest model to generate quality prediction data and key features, and the quality prediction module transmits the quality prediction data and influencing features to the optimization module; S3: The optimization module maps key features into fuzzy variables through a fuzzy logic model; S4: The optimization module performs fuzzy reasoning on fuzzy variables based on the fuzzy rule base to generate corresponding control strategies; S5: The optimization module transmits the generated control strategy data to the intelligent control module; S6: The intelligent control module receives the control strategy data and automatically adjusts the operating states of the irrigation system, the lighting system, the temperature control system, the nutrient supply system and the carbon dioxide supply system to optimize the growth environment of the chrysanthemums.

7. The working method of the chrysanthemum production quality prediction system according to claim 6, characterized in that: The steps include: S7: When the prediction quality is lower than the set standard, the optimization module generates an alarm signal through the early warning module to remind the management personnel; S8: The display module displays the current data stream in real time.

8. The working method of the chrysanthemum production quality prediction system according to claim 7, characterized in that: The data monitoring module collects the humidity, light, temperature, soil nutrient level and carbon dioxide concentration parameters in the chrysanthemum growth environment in real time, forms a feature vector x(t) after preprocessing, and transmits the feature vector x(t) to the quality prediction module; Where x(t) = [x1(t), x2(t), x3(t), x4(t), x5(t)]; x1(t) is the humidity feature, x2(t) is the light feature, x3(t) is the temperature feature, x4(t) is the soil feature, and x5(t) is the gas feature.

9. The working method of the chrysanthemum production quality prediction system according to claim 8, characterized in that: In S2, the quality prediction module is preset with a random forest model M, which includes N decision trees {T1, T2, ..., T N }, when the quality prediction module inputs the feature vector x(t), the random forest model outputs the predicted average value of N decision trees The random forest model M calculates the feature x for the splitting node of each tree in the N decision trees. j The amount of impurity reduction during splitting I j , and obtain the feature contribution f of the random forest model M j : Among them, I j (T i ) is the decision tree T i In the feature x j Contribution to impurity reduction; The random forest model M sorts the feature contributions from large to small to obtain key features; The quality prediction module predicts the average And the key feature set {x j ∣f j ≥θ} is sent to the optimization module, where θ is the feature importance threshold.

Images