Chinese bee honeycomb honey Baume degree data processing system and method based on data analysis

Abstract

The present invention discloses a data processing system and method for the Baume degree of honeycomb honey of Chinese bees based on data analysis, and relates to the field of bee breeding technology. The system includes: a workshop monitoring module, a Baume degree detection module, a Baume degree analysis module, a honeycomb honey evaluation module, a data visualization module and a storage management module; the workshop monitoring module is used to monitor and control the temperature and humidity data in the honeycomb honey maturation workshop in real time, and record the entry and exit time and storage location of each honeycomb frame; the Baume degree detection module is used to divide the honeycomb frame into multiple detection areas, and based on microwave technology, detect the water content of the honeycomb honey in each detection area; the Baume degree analysis module is used to analyze the Baume degree distribution of all positions of the honeycomb honey according to the Baume degree of the honeycomb honey in each detection area. The present invention can monitor and control the workshop environment in real time and accurately to ensure the production quality of the honeycomb honey through the intelligent and refined management of the whole process of Chinese bee honeycomb from production to evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of bee breeding, and in particular to a system and method for processing the Baume degree data of Chinese bee honeycomb based on data analysis. Background Art

[0002] Chinese honey bees, whose full name is Chinese honey bees (Apis cerana), are a native bee species widely distributed in East Asia and Southeast Asia. Compared with Western honey bees (Apis mellifera), Chinese honey bees have stronger disease resistance and adaptability, especially in complex terrain and climatic conditions. Chinese honey bee honeycomb is a bee product naturally brewed by Chinese honey bees in the hive. Unlike ordinary honey, Chinese honey bee honeycomb includes honey brewed by bees and wax cover that seals the hive. Chinese honey bee honeycomb not only contains honey, but is also rich in pollen, propolis and various active substances secreted by bees, so it has higher nutritional value and medicinal value.

[0003] Baumé degree is one of the important indicators for measuring honey quality, indicating the concentration of liquid, especially the content of dissolved solids. In honey testing, Baumé degree is usually used to reflect the water content of honey. The lower the water content, the higher the Baumé degree and the better the quality of the honey. Testing the Baumé degree of Chinese bee honeycomb is a key step to ensure the quality and market value of honey. The higher the Baumé degree, the thicker the honey is, the more durable it is to store, and the less likely it is to ferment and deteriorate. Therefore, testing the Baumé degree is crucial to controlling the quality of honey, improving product quality, and protecting the health of consumers.

[0004] In the prior art, the Baume degree detection of Chinese bee honeycomb mainly relies on equipment such as refractometers, densitometers or microwave sensors. The refractometer indirectly calculates the Baume degree by measuring the refractive index of light in honey, while the densitometer infers the Baume degree by measuring the density of honey. The traditional refractometer and densitometer measurement methods require sampling, and the operation process is complicated and easily interfered by external factors such as temperature and impurities. These methods usually need to be carried out in a laboratory environment, and it is difficult to achieve real-time online detection, and it is impossible to timely feedback the quality changes of honey. In addition, the measurement accuracy of these methods is limited, especially in the complex multi-component environment of honeycomb, which may affect the accuracy of the test results.

[0005] There are also challenges in processing existing Baume test data. Traditional methods often rely on manual recording and analysis, which results in inefficient data management and is prone to omissions or errors. In addition, a single Baume data cannot fully reflect the quality of honey in the hive. Since Baume may vary in space and time within the hive, it is difficult to provide an accurate honey quality assessment through a single or single-point measurement. Summary of the invention

[0006] Based on this, it is necessary to provide a Chinese bee hive honey Baume data processing system and method based on data analysis to address the above technical problems.

[0007] In a first aspect, the present invention provides a data processing system for the Baume degree of Chinese honeycomb honey based on data analysis, the system comprising: a workshop monitoring module, a Baume degree detection module, a Baume degree analysis module, a honeycomb honey evaluation module, a data visualization module and a storage management module;

[0008] Among them, the workshop monitoring module is used to monitor and control the temperature and humidity data in the honeycomb honey maturation workshop in real time, and record the entry and exit time and storage location of each honeycomb frame;

[0009] Baume degree detection module, used to divide the honeycomb frame into multiple detection areas, detect the moisture content of the honeycomb honey in each detection area based on microwave technology, and match the Baume degree corresponding to the honeycomb honey;

[0010] Baume degree analysis module, used to analyze the Baume degree distribution of honeycomb honey at all locations according to the Baume degree of honeycomb honey in each detection area, and predict the Baume degree change trend;

[0011] The honeycomb honey evaluation module is used to evaluate the honey grade of the honeycomb honey based on the Baume analysis results of the honeycomb honey and predict the honey collection time of the honeycomb honey;

[0012] Data visualization module, used to generate visual charts to display the analysis results and evaluation results, and generate a quality report of the corresponding honeycomb in each beehive frame;

[0013] The storage management module is used to store the real-time data in the honeycomb honey Baume analysis process.

[0014] Furthermore, the Baume degree detection module includes: a region setting submodule, a microwave measurement submodule, a signal processing submodule and a Baume degree matching submodule;

[0015] The area setting submodule is used to divide a plurality of detection areas according to the size specifications of the honeycomb frame, and select detection points in each detection area as measurement points for microwave detection;

[0016] The microwave measurement submodule is used to detect each detection point in the honeycomb frame by emitting microwaves, and then obtain the microwave signals after detection and convert them into stable electrical signals;

[0017] The signal processing submodule is used to establish a honeycomb honey moisture content detection model based on the electrical signal value, and output the moisture content of each detection point after processing and converting the signal data;

[0018] The Baume degree matching submodule is used to match the moisture content of each detection point in the honeycomb honey to the corresponding Baume degree according to the industry standard moisture content-Baume degree relationship table.

[0019] Furthermore, the microwave measurement submodule includes: a microwave signal source, an isolator, a signal receiver, a signal corrector, an A / D conversion unit and a core controller;

[0020] Wherein, the microwave signal source is used to output electromagnetic waves of a preset frequency;

[0021] Isolator, used to prevent load reflected signal from interfering with the transmitted electromagnetic wave signal;

[0022] A signal receiver, used to receive electromagnetic waves after reflection, transmission and resonance;

[0023] A signal corrector, used to receive microwave signals generated by electromagnetic waves and perform compensation correction;

[0024] An A / D conversion unit, used for converting microwave signals into electrical signals;

[0025] The core controller is used to control data acquisition, data communication and data storage.

[0026] Furthermore, the expression of the water content detection model is:

[0027] H=aU+b

[0028] In the formula, H represents the water content; a represents the value coefficient of the electrical signal; U represents the electrical signal; and b represents the statistical coefficient.

[0029] Furthermore, the Baume degree analysis module includes: an input integration submodule, a spatiotemporal modeling submodule, a time series submodule, a spatial distribution submodule, and a trend prediction submodule;

[0030] Among them, the input integration submodule is used to obtain the Baume degree of all detection points in each honeycomb frame, and integrate them according to the individual number of the honeycomb frame to form a honeycomb honey data set;

[0031] The spatiotemporal modeling submodule is used to establish a three-dimensional model of the honeycomb frame according to the spatial relationship between the detection area and the detection points, and to calibrate the position information and Baume value of each detection point;

[0032] The time series submodule is used to obtain the Baume degree of honeycomb honey after multiple tests at the same test point, establish the original time series, and perform time series decomposition through adaptive noise complete set empirical mode decomposition to analyze the time distribution of the Baume degree of honeycomb honey;

[0033] The spatial distribution submodule is used to establish a spatial distribution model based on the Baume degree of honeycomb honey at different detection points, and analyze the spatial distribution of the Baume degree of each detection area in the honeycomb honey;

[0034] The trend prediction submodule is used to predict the Baume degree trend of honeycomb honey at future moments based on the spatiotemporal distribution of Baume degree in each detection area in the honeycomb frame.

[0035] Furthermore, the Baume degree of honeycomb honey after multiple tests at the same test point is obtained, the original time series is established, and the time series is decomposed by adaptive noise complete set empirical mode decomposition. The time distribution of the Baume degree of honeycomb honey is analyzed, including:

[0036] Add N times of white noise sequence with standard normal distribution to the original time series to form N new Baume degree sequences;

[0037] Perform empirical mode decomposition on each Baume degree sequence respectively, calculate the average value of all first intrinsic mode function components, and obtain the first adaptive mode component and the first residual component of the adaptive noise complete set empirical mode decomposition;

[0038] Add N times a white noise sequence with a standard normal distribution to the residual component to construct N new component sequences, perform empirical mode decomposition on each new component sequence, and then calculate the average value of all first intrinsic mode function components to obtain the second adaptive mode component;

[0039] The remaining residual components and adaptive modal components of the adaptive noise complete set empirical mode decomposition are calculated in sequence until the number of extreme points of the residual components reaches the set threshold, the empirical mode decomposition is stopped, and the time distribution of the original time series is obtained.

[0040] Furthermore, the spatial distribution submodule includes: a data processing unit, a model building unit, a parameter optimization unit and a distribution display unit;

[0041] The data processing unit is used to normalize the spatial coordinates of the detection points and the Baume data, establish a data set, and divide it into a training set, a test set, and a validation set;

[0042] A model building unit is used to establish a three-layer fully connected neural network, set input neurons and output neurons as a spatial distribution model, and use the spatial distribution model to fit the nonlinear distribution of Baume data in the space where the honeycomb frame is located;

[0043] The parameter optimization unit is used to optimize the model training using the optimizer and automatically mine the spatial correlation of Baume data through weight matching;

[0044] The distribution display unit is used to fit the Baume degree of the remaining spatial nodes other than the detection point in each detection area using a fully connected neural network, and calculate the average Baume degree value of each detection area.

[0045] Furthermore, based on the spatiotemporal distribution of the Baume degree of each detection area in the beehive frame, the Baume degree trend of the honeycomb honey at future moments is predicted, including:

[0046] Based on the spatiotemporal graph convolutional network, combined with the intrinsic mode function components and spatial distribution model of historical time series, a joint spatiotemporal prediction model is established;

[0047] The joint spatiotemporal prediction model was trained using the historical Baume data distribution, the model's hyperparameters were adjusted, and the generalization ability of the joint spatiotemporal prediction model was evaluated using cross-validation.

[0048] Set the Baume evaluation interval, input the Baume data of the current time and space, and predict the Baume value of each detection area at the future time through the spatiotemporal joint model.

[0049] Further, the honeycomb honey assessment module includes: a state assessment submodule, a grade assessment submodule, a time prediction submodule and a risk assessment submodule;

[0050] Among them, the state evaluation submodule is used to evaluate the maturity state of honeycomb honey in different detection areas according to the distribution of Baume degrees;

[0051] The grade assessment submodule is used to assess the eligibility of the honeycomb honey according to the difference in the average Baume values ​​of each test area in the honeycomb honey, and to classify the grade of the honeycomb honey according to the Baume value based on the industry Baume standard after the eligibility assessment is passed;

[0052] The time prediction submodule is used to predict the best honey collection time to reach the set Baume value based on the value of the Baume degree at the current moment and the trend analysis results of the Baume degree;

[0053] The risk assessment submodule is used to combine the historical data and current status of Baume to assess whether the honeycomb honey will have Baume risk in the future.

[0054] In a second aspect, the present invention further provides a method for processing the Baume degree data of Chinese bee honeycomb based on data analysis, the method comprising the following steps:

[0055] S1. Real-time monitoring and control of temperature and humidity data in the honeycomb honey maturation workshop, and recording the entry and exit time and storage location of each honeycomb frame;

[0056] S2, dividing the honeycomb frame into multiple detection areas, detecting the water content of the honeycomb honey in each detection area based on microwave technology, and matching the corresponding Baume degree of the honeycomb honey;

[0057] S3. Analyze the distribution of the degree of Baume of the honeycomb honey at all locations according to the degree of Baume of the honeycomb honey in each detection area, and predict the trend of the degree of Baume change;

[0058] S4. Based on the Baume analysis result of the honeycomb honey, the honey grade of the honeycomb honey is evaluated, and the honey collection time of the honeycomb honey is predicted;

[0059] S5. Generate a visual chart display of the analysis results and the evaluation results, and generate a quality report of the honeycomb corresponding to each beehive frame.

[0060] The beneficial effects of the present invention are:

[0061] 1. By building a data processing system that integrates Baume detection, analysis and evaluation, the whole process of Chinese bee honeycomb from production to evaluation is intelligent and refined. It can monitor and control the workshop environment in real time and accurately to ensure the production quality of honeycomb. The use of microwave technology for Baume detection improves the detection efficiency and accuracy. The analysis and prediction based on spatiotemporal data helps to optimize the harvesting time of honeycomb and improve the quality grade of the product. Combined with data visualization and management modules, the production process of honeycomb is more transparent and traceable, reducing human errors and management costs, thereby improving the quality control and production management level of honeycomb.

[0062] 2. By acquiring and integrating the Baume degree data of each detection point in the hive frame, a three-dimensional spatiotemporal model of honeycomb honey is established, and the spatial distribution of honeycomb honey is visualized and quantitatively analyzed. The adaptive noise complete set empirical mode decomposition is used to improve the accuracy and stability of time series analysis, and it can dynamically predict the changes in Baume degree, optimize the production and collection time of honeycomb honey, and significantly improve the accuracy, timeliness and prediction ability of Baume degree detection, providing strong support for the quality control and management of honeycomb honey. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0064] Figure 1 : is a system principle block diagram of a Chinese bee hive honey Baume degree data processing system based on data analysis according to an embodiment of the present invention;

[0065] Figure 2 It is a flow chart of a method for processing the Baume degree data of Chinese bee honeycomb based on data analysis according to an embodiment of the present invention.

[0066] Figure numbers: 1. Workshop monitoring module; 2. Baume degree detection module; 3. Baume degree analysis module; 4. Honeycomb honey evaluation module; 5. Data visualization module; 6. Storage management module. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0068] See also Figure 1 , a Chinese bee honeycomb honey Baume degree data processing system based on data analysis is provided, the system includes: a workshop monitoring module 1, a Baume degree detection module 2, a Baume degree analysis module 3, a honeycomb honey evaluation module 4, a data visualization module 5 and a storage management module 6.

[0069] The workshop monitoring module 1 is used to monitor and control the temperature and humidity data in the honeycomb honey maturation workshop in real time, and record the entry and exit time and storage location of each honeycomb frame.

[0070] Specifically, the temperature and humidity levels in the workshop are continuously monitored by installing temperature and humidity sensors in the workshop. The sensors need to be distributed in different locations in the workshop to ensure the comprehensiveness and accuracy of the data. The monitored temperature and humidity data are collected in real time by sensor nodes and transmitted to the central control system for recording and storage. They will be saved in the database in the form of time series for subsequent analysis. In addition, the system automatically controls the air conditioning system, humidifier, dehumidifier and other equipment in the workshop according to the set temperature and humidity thresholds, adjusts the environmental conditions in the workshop, and ensures that the temperature and humidity during the maturation of the honeycomb are maintained within the optimal range.

[0071] By installing RFID or barcode scanning systems at the entrances and exits, each honeycomb frame is automatically identified and the time is recorded. The system automatically records the specific time when each honeycomb frame enters and leaves the warehouse. In the storage area of ​​the workshop, each storage location corresponds to a unique identifier (such as a QR code or RFID tag). When the honeycomb frame is placed in a specified location, the system records the specific storage location of the honeycomb frame by scanning the corresponding identifier. Managers can quickly locate and find any honeycomb frame through the system interface.

[0072] The Baume degree detection module 2 is used to divide the honeycomb frame into multiple detection areas, detect the water content of the honeycomb honey in each detection area based on microwave technology, and match the Baume degree corresponding to the honeycomb honey.

[0073] In the description of the present invention, the Baume detection module 2 includes: an area setting submodule (not marked in the figure), a microwave measurement submodule (not marked in the figure), a signal processing submodule (not marked in the figure) and a Baume matching submodule (not marked in the figure).

[0074] The area setting submodule is used to divide a plurality of detection areas according to the size specifications of the honeycomb frame, and select detection points in each detection area as measurement points for microwave detection.

[0075] The microwave measurement submodule is used to detect each detection point in the honeycomb frame by emitting microwaves, and then obtain the microwave signals after detection and convert them into stable electrical signals.

[0076] In the description of the present invention, the microwave measurement submodule includes: a microwave signal source (not marked in the figure), an isolator (not marked in the figure), a signal receiver (not marked in the figure), a signal corrector (not marked in the figure), an A / D conversion unit (not marked in the figure) and a core controller (not marked in the figure).

[0077] Among them, the microwave signal source is used to output electromagnetic waves of a preset frequency.

[0078] Isolator, used to prevent load reflected signal from interfering with the transmitted electromagnetic wave signal.

[0079] A signal receiver is used to receive electromagnetic waves that have been reflected, transmitted and resonated.

[0080] The signal corrector is used to receive the microwave signal generated by the electromagnetic wave and perform compensation correction.

[0081] The A / D conversion unit is used to convert the microwave signal into an electrical signal.

[0082] The core controller is used to control data acquisition, data communication and data storage.

[0083] The signal processing submodule is used to establish a honeycomb honey moisture content detection model based on the electrical signal value, and output the moisture content of each detection point after processing and converting the signal data.

[0084] In the description of the present invention, the expression of the water content detection model is:

[0085] In the formula H=aU+b, H represents the water content; a represents the value coefficient of the electrical signal; U represents the electrical signal; and b represents the statistical coefficient.

[0086] The Baume degree matching submodule is used to match the moisture content of each detection point in the honeycomb honey to the corresponding Baume degree according to the industry standard moisture content-Baume degree relationship table.

[0087] Specifically, there are three ways to express the concentration of honey, one is water content, one is sugar content, and one is Baume degree, and the meanings of the three are different. The lower the water content of honey, the higher the sugar content, the higher the concentration, the greater the specific gravity, and the higher the Baume degree. Honey concentration and Baume degree are directly proportional to each other, and they can be freely converted. As long as you know one of the values, you can convert the values ​​of the other two. Because Baume degree is easy to measure and read, the internationally accepted unit for honey concentration is Baume degree.

[0088] The water content and maturity of honey will affect the quality of honey. High water content and low maturity will cause honey to ferment. Studies have shown that when the water content of honey is below 17.1% and the degree of Baume is above 43°Bé, no matter how many osmophilic yeasts there are, the honey will not ferment at room temperature. When the water content of honey is above 17.2% and below 18%, and there are less than 1,000 yeast spores or less per gram of honey, it will not ferment within one year at room temperature. When the water content is above 18.1% and below 19%, and there are no more than 10 yeast spores per gram of honey, it will not ferment within one year at room temperature. When the water content exceeds 19%, even if there is only one spore per gram of honey, the honey will ferment within one year at room temperature.

[0089] The Baume degree analysis module 3 is used to analyze the Baume degree distribution of all locations of the honeycomb honey according to the Baume degree of the honeycomb honey in each detection area, and predict the Baume degree change trend.

[0090] In the description of the present invention, the Baume analysis module 3 includes: an input integration submodule (not marked in the figure), a spatiotemporal modeling submodule (not marked in the figure), a time series submodule (not marked in the figure), a spatial distribution submodule (not marked in the figure) and a trend prediction submodule (not marked in the figure).

[0091] Among them, the input integration submodule is used to obtain the Baume degree of all detection points in each honeycomb frame, and integrate them according to the individual number of the honeycomb frame to form a honeycomb honey data set.

[0092] The spatiotemporal modeling submodule is used to establish a three-dimensional model of the honeycomb frame according to the spatial relationship between the detection area and the detection points, and to calibrate the position information and Baume value of each detection point.

[0093] The time series submodule is used to obtain the Baume degree of honeycomb honey after multiple tests at the same test point, establish the original time series, and perform time series decomposition through adaptive noise complete set empirical mode decomposition to analyze the time distribution of the Baume degree of honeycomb honey.

[0094] Specifically, Ensemble Empirical Mode Decomposition with Adaptive Noise (EEMD-AN) is an improved algorithm based on empirical mode decomposition (EMD) to solve the inherent mode aliasing problem in the original EMD method. EEMD obtains a more robust intrinsic mode function (IMF) by introducing white noise and performing multiple decompositions, and then averaging the results. Based on EEMD, the adaptive noise complete ensemble method further optimizes the noise addition and processing methods, making the decomposition results more accurate and stable. When analyzing the temporal distribution of the Baume degree of honeycomb honey, the data is usually affected by a variety of complex factors, including seasonal changes, temperature, humidity, and random fluctuations in the production process of honeycomb honey. Traditional linear analysis methods (such as Fourier transform) are difficult to capture these nonlinear and non-stationary characteristics. Adaptive noise complete ensemble empirical mode decomposition can capture the complex pattern of Baume degree changing over time in a more detailed way by decomposing the original time series into multiple intrinsic mode functions (IMFs), each of which corresponds to a specific time scale and frequency.

[0095] In the description of the present invention, the Baume degree of honeycomb honey after multiple tests at the same test point is obtained, the original time series is established, and the time series is decomposed by adaptive noise complete set empirical mode decomposition, and the time distribution of the Baume degree of honeycomb honey is analyzed, including:

[0096] Step S311: Add N white noise sequences with standard normal distribution to the original time series to form N new Baume sequences.

[0097] Specifically, by introducing adaptive noise, EEMD-AN can effectively reduce the impact of noise on time series analysis, making the decomposed IMF more physically meaningful, thereby more accurately reflecting the true variation law of honeycomb honey Baume degree.

[0098] Step S312: Perform empirical mode decomposition on each Baume degree sequence respectively, calculate the average value of all first intrinsic mode function components, and obtain the first adaptive mode component and the first residual component of the adaptive noise complete set empirical mode decomposition.

[0099] Step S313: Add N times a white noise sequence with a standard normal distribution to the residual component to construct N new component sequences, perform empirical mode decomposition on each new component sequence, and then calculate the average value of all first intrinsic mode function components to obtain the second adaptive modal component.

[0100] Step S314, sequentially calculate the remaining residual components and adaptive modal components of the adaptive noise complete set empirical mode decomposition until the number of extreme value points of the residual components reaches a set threshold, stop the empirical mode decomposition, and obtain the time distribution of the original time series.

[0101] In the analysis of honeycomb honey Baume degree, EEMD-AN helps to reveal the detailed changes hidden in the time series, which is of great guiding significance for understanding the dynamic changes in the honeycomb honey maturation process, optimizing production management, and formulating honey extraction strategies. By analyzing the temporal distribution of honeycomb honey Baume degree, producers can better understand the honeycomb honey maturation cycle, thereby improving the quality and yield of honey.

[0102] The spatial distribution submodule is used to establish a spatial distribution model based on the Baume degree of honeycomb honey at different detection points, and analyze the spatial distribution of the Baume degree of each detection area in the honeycomb honey.

[0103] In the description of the present invention, the spatial distribution submodule includes: a data processing unit, a model building unit, a parameter optimization unit and a distribution display unit.

[0104] Among them, the data processing unit is used to normalize the spatial coordinates of the detection points and the Baume data, establish a data set, and divide it into a training set, a test set, and a validation set.

[0105] The model building unit is used to establish a three-layer fully connected neural network, set input neurons and output neurons as a spatial distribution model, and use the spatial distribution model to fit the nonlinear distribution of Baume data in the space where the honeycomb frame is located.

[0106] Specifically, the unit establishes a three-layer fully connected neural network (usually including input layer, hidden layer and output layer), and sets the number of input neurons (corresponding to the normalized spatial coordinates) and the number of output neurons (corresponding to the Baume value). This network will be used to learn and fit the Baume data of the detection points in the honeycomb frame and capture its nonlinear distribution law in space.

[0107] The parameter optimization unit is used to optimize the model training using the optimizer and automatically mine the spatial correlation of Baume data through weight matching.

[0108] Specifically, the neural network is trained through optimizers (such as Adam, SGD, etc.) to adjust the weights and biases of the model. The focus of this unit is to automatically mine the implicit correlation between Baume data and spatial coordinates. During the optimization process, the weight adjustment of the neural network can gradually highlight the correlation between Baume and spatial position, thereby enhancing the model's ability to fit spatial distribution.

[0109] The distribution display unit is used to fit the Baume degree of the remaining spatial nodes other than the detection point in each detection area using a fully connected neural network, and calculate the average Baume degree value of each detection area.

[0110] Specifically, the trained fully connected neural network is used to predict the Baume values ​​of unmeasured points in the honeycomb frame, and a spatial distribution map of the Baume value in the entire honeycomb frame is constructed. The Baume values ​​in each detection area are summarized and calculated to obtain the average Baume value of each area, which further helps to understand the overall quality distribution of honeycomb honey in the honeycomb frame.

[0111] The trend prediction submodule is used to predict the Baume degree trend of honeycomb honey at future moments based on the spatiotemporal distribution of Baume degree in each detection area in the honeycomb frame.

[0112] In the description of the present invention, based on the spatiotemporal distribution of the Baume degree of each detection area in the honeycomb frame, the prediction of the Baume degree trend of the honeycomb honey at a future moment includes:

[0113] Step S321: Taking the spatiotemporal graph convolutional network as the basis, combining the intrinsic mode function components and spatial distribution model of the historical time series, a joint spatiotemporal prediction model is established.

[0114] Specifically, the spatiotemporal graph convolutional network (STGCN) can effectively capture the complex correlations in space and time. It processes the Baume data of each detection area in the honeycomb frame through convolution operations and analyzes the spatial relationship between Baume in different detection areas. At the same time, through the convolution of time series, it captures the dynamic characteristics of Baume changing over time.

[0115] The historical time series is subjected to adaptive noise complete set empirical mode decomposition to obtain the intrinsic mode function components. The IMF component can decompose the different frequency components in the honeycomb honey Baume time series, provide more time change information, and enhance the model's ability to capture time characteristics.

[0116] Based on the previously constructed spatial distribution model, the spatial relationship of Baume degree in different detection areas is obtained. By combining spatiotemporal convolution and IMF components, a comprehensive spatiotemporal prediction model is established, which can simultaneously process the time series characteristics and spatial distribution characteristics of honeycomb honey Baume degree.

[0117] Step S322: Use the historical Baume data distribution to train the joint spatiotemporal prediction model, adjust the model's hyperparameters, and use cross-validation to evaluate the generalization ability of the joint spatiotemporal prediction model.

[0118] Specifically, historical honeycomb honey Baume data is input into the joint spatiotemporal prediction model for training. During the training process, the model will learn the complex patterns of temporal and spatial features and gradually improve its prediction ability. The hyperparameters of the model (such as learning rate, number of convolutional layers, number of filters, etc.) are adjusted through experiments to find the best configuration to ensure that the model has a good training effect.

[0119] During the training process, cross-validation is used to evaluate the generalization ability of the model. Cross-validation can effectively prevent the model from overfitting and ensure that the model can still perform well on unseen data.

[0120] Step S323, set the Baume evaluation interval, input the Baume data of the current time and space, and predict the Baume value of each detection area at the future time through the spatiotemporal joint model.

[0121] Specifically, according to production needs, a reasonable Baume evaluation time interval (such as hours, days or weeks) is set to balance the frequency and accuracy of the prediction. The Baume data of the current time and space are used as input to the trained joint spatiotemporal prediction model. The model will predict the Baume value of each detection area at the future time based on the historical trend of the time series and the current spatial distribution.

[0122] The prediction results will show the future trend of Baume changes in each test area, helping beekeepers or producers to better grasp the maturity of honeycomb, optimize honey collection time, and improve honey quality.

[0123] The honeycomb honey evaluation module 4 is used to evaluate the honey grade of the honeycomb honey based on the Baume analysis result of the honeycomb honey and predict the honey collection time of the honeycomb honey.

[0124] In the description of the present invention, the honeycomb honey evaluation module 4 includes: a state evaluation submodule (not marked in the figure), a level evaluation submodule (not marked in the figure), a time prediction submodule (not marked in the figure) and a risk evaluation submodule (not marked in the figure).

[0125] Among them, the state evaluation submodule is used to evaluate the maturity state of the honeycomb honey in different detection areas according to the distribution of Baume degrees.

[0126] Specifically, by analyzing the maturity status of honeycomb in different test areas. The maturity status is usually directly related to the Baume degree, because the higher the Baume degree, the lower the water content of the honey and the higher the maturity. By evaluating the maturity status of honeycomb in each test area, it can be determined which areas of honeycomb have reached the maturity standard, so as to decide whether honey extraction can be carried out, which helps to improve the quality of honey during extraction and reduce the mixing of immature honey.

[0127] The grade assessment submodule is used to assess the eligibility of the honeycomb based on the difference in the average Baume values ​​of each test area in the honeycomb, and after the eligibility assessment is passed, the honeycomb is graded according to the Baume values ​​based on the industry Baume standards.

[0128] The time prediction submodule is used to predict the best honey collection time to reach the set Baume degree value based on the current Baume degree value and the trend analysis results of the Baume degree.

[0129] The risk assessment submodule is used to combine the historical data and current status of Baume to assess whether the honeycomb honey will have Baume risk in the future.

[0130] Specifically, the historical data and current status of Baume degree are used to analyze the possible Baume degree risks in the future, such as the situation where Baume degree is too low or too high. Low Baume degree may indicate that the honey is not mature, and high Baume degree may indicate over-maturity or fermentation risk.

[0131] The data visualization module 5 is used to generate a visual chart display of the analysis results and the evaluation results, and to generate a quality report of the honeycomb corresponding to each honeycomb frame.

[0132] The storage management module 6 is used to store the real-time data in the honeycomb honey Baume analysis process.

[0133] See also Figure 2 , also provides a method for processing the Baume degree data of Chinese bee honeycomb based on data analysis, the method comprising the following steps:

[0134] S1. Real-time monitoring and control of temperature and humidity data in the honeycomb honey maturation workshop, and recording the entry and exit time and storage location of each honeycomb frame.

[0135] S2. Divide the honeycomb frame into multiple detection areas, detect the water content of the honeycomb honey in each detection area based on microwave technology, and match the Baume degree corresponding to the honeycomb honey.

[0136] S3. According to the Baume degrees of the honeycomb honey in each detection area, the Baume degree distribution of all locations of the honeycomb honey is analyzed, and the Baume degree change trend is predicted.

[0137] S4. Based on the Baume analysis results of the honeycomb honey, the honey grade of the honeycomb honey is evaluated, and the honey collection time of the honeycomb honey is predicted.

[0138] S5. Generate a visual chart display of the analysis results and the evaluation results, and generate a quality report of the honeycomb corresponding to each beehive frame.

[0139] In summary, with the help of the above technical scheme of the present invention, by building a data processing system integrating Baume detection and analysis and evaluation, the whole process of intelligent and refined management of Chinese honeycomb honey from production to evaluation is realized; it can monitor and control the workshop environment in real time and accurately to ensure the production quality of honeycomb honey; microwave technology is used for Baume detection to improve the detection efficiency and accuracy; analysis and prediction based on spatiotemporal data helps to optimize the harvesting time of honeycomb honey and improve the quality grade of the product; combined with data visualization and management modules, the production process of honeycomb honey is more transparent and traceable, reducing human errors and management costs, thereby improving the quality control and production management level of honeycomb honey. By acquiring and integrating the Baume data of each detection point in the honeycomb frame, a three-dimensional spatiotemporal model of honeycomb honey is established, and the spatial distribution of honeycomb honey is visualized and quantitatively analyzed; using adaptive noise complete set empirical mode decomposition, the accuracy and stability of time series analysis are improved, and the changes in Baume can be dynamically predicted, the production and honey collection time of honeycomb honey can be optimized, and the accuracy, timeliness and prediction ability of Baume detection are significantly improved, providing strong support for the quality control and management of honeycomb honey.

[0140] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

Claims

1. A data processing system for the Baume degree of Chinese bee honeycomb based on data analysis, characterized in that: The system includes: workshop monitoring module, Baume degree detection module, Baume degree analysis module, honeycomb honey evaluation module, data visualization module and storage management module; The workshop monitoring module is used to monitor and control the temperature and humidity data in the honeycomb honey maturation workshop in real time, and record the entry and exit time and storage location of each honeycomb frame; The Baume degree detection module is used to divide the honeycomb frame into multiple detection areas, detect the water content of the honeycomb honey in each detection area based on microwave technology, and match the Baume degree corresponding to the honeycomb honey; The Baume degree analysis module is used to analyze the Baume degree distribution of all locations of the honeycomb honey according to the Baume degree of the honeycomb honey in each detection area, and predict the Baume degree change trend; The honeycomb honey evaluation module is used to evaluate the honey grade of the honeycomb honey based on the Baume analysis result of the honeycomb honey and predict the honey collection time of the honeycomb honey; The data visualization module is used to generate a visual chart display of the analysis results and the evaluation results, and generate a quality report of the honeycomb corresponding to each honeycomb frame; The storage management module is used to store real-time data during the honeycomb honey Baume analysis process; The Baume degree analysis module includes: an input integration submodule, a spatiotemporal modeling submodule, a time series submodule, a spatial distribution submodule and a trend prediction submodule; The spatial distribution submodule is used to establish a spatial distribution model based on the Baume degree of honeycomb honey at different detection points, and analyze the spatial distribution of the Baume degree of each detection area in the honeycomb honey; The trend prediction submodule is used to predict the Baume degree trend of the honeycomb honey at a future moment based on the spatiotemporal distribution of the Baume degree of each detection area in the honeycomb frame.

2. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 1 is characterized in that: The Baume degree detection module includes: an area setting submodule, a microwave measurement submodule, a signal processing submodule and a Baume degree matching submodule; The area setting submodule is used to divide a plurality of detection areas according to the size specifications of the honeycomb frame, and select a detection point in each detection area as a measurement point for microwave detection; The microwave measurement submodule is used to detect each detection point in the honeycomb frame by emitting microwaves, and then obtain the detected microwave signals and convert them into stable electrical signals; The signal processing submodule is used to establish a honeycomb honey moisture content detection model based on the electrical signal value, and output the moisture content of each detection point after processing and converting the signal data; The Baume degree matching submodule is used to match the moisture content of each detection point in the honeycomb honey to the corresponding Baume degree according to the moisture content-Baume degree relationship table of the industry standard.

3. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 2 is characterized in that: The microwave measurement submodule includes: a microwave signal source, an isolator, a signal receiver, a signal corrector, an A / D conversion unit and a core controller; Wherein, the microwave signal source is used to output electromagnetic waves of a preset frequency; The isolator is used to prevent the load reflection signal from interfering with the transmitted electromagnetic wave signal; The signal receiver is used to receive the electromagnetic waves after reflection, transmission and resonance; The signal corrector is used to receive the microwave signal generated by the electromagnetic wave and perform compensation correction; The A / D conversion unit is used to convert the microwave signal into an electrical signal; The core controller is used to control data acquisition, data communication and data storage.

4. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 2 is characterized in that: The expression of the water content detection model is: ； In the formula, H Indicates water content; a Indicates the value coefficient of the electrical signal; U Represents an electrical signal; b Represents statistical coefficients.

5. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 2 is characterized in that: The input integration submodule is used to obtain the Baume degree of all detection points in each honeycomb frame, and integrate them according to the individual numbers of the honeycomb frames to form a honeycomb honey data set; The spatiotemporal modeling submodule is used to establish a three-dimensional model of the honeycomb frame according to the spatial relationship between the detection area and the detection points, and to calibrate the position information and Baume value of each detection point; The time series submodule is used to obtain the Baume degree of honeycomb honey after multiple tests at the same test point, establish the original time series, perform time series decomposition through adaptive noise complete set empirical mode decomposition, and analyze the time distribution of the Baume degree of honeycomb honey.

6. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 5 is characterized in that: The method of obtaining the Baume degree of honeycomb honey after multiple tests at the same test point, establishing the original time series, and performing time series decomposition by adaptive noise complete set empirical mode decomposition, and analyzing the time distribution of the Baume degree of honeycomb honey includes: Add N times of white noise sequence with standard normal distribution to the original time series to form N new Baume degree sequences; Perform empirical mode decomposition on each Baume degree sequence respectively, calculate the average value of all first intrinsic mode function components, and obtain the first adaptive mode component and the first residual component of the adaptive noise complete set empirical mode decomposition; Add N times a white noise sequence with a standard normal distribution to the residual component to construct N new component sequences, perform empirical mode decomposition on each new component sequence, and then calculate the average value of all first intrinsic mode function components to obtain the second adaptive mode component; The remaining residual components and adaptive modal components of the adaptive noise complete set empirical mode decomposition are calculated in sequence until the number of extreme points of the residual components reaches the set threshold, the empirical mode decomposition is stopped, and the time distribution of the original time series is obtained.

7. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 5 is characterized in that: The spatial distribution submodule includes: a data processing unit, a model building unit, a parameter optimization unit and a distribution display unit; The data processing unit is used to normalize the spatial coordinates of the detection points and the Baume data, establish a data set, and divide it into a training set, a test set, and a validation set; The model building unit is used to establish a three-layer fully connected neural network, set input neurons and output neurons as a spatial distribution model, and use the spatial distribution model to fit the nonlinear distribution of Baume data in the space where the honeycomb frame is located; The parameter optimization unit is used to optimize the model by using the optimizer, and automatically mine the spatial correlation of Baume degree data by weight matching; The distribution display unit is used to fit the Baume degree of the remaining spatial nodes other than the detection point in each detection area using a fully connected neural network, and calculate the average Baume degree value of each detection area.

8. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 7 is characterized in that: The prediction of the Baume degree trend of the honeycomb honey at a future moment based on the spatiotemporal distribution of the Baume degree of each detection area in the honeycomb frame includes: Based on the spatiotemporal graph convolutional network, combined with the intrinsic mode function components and spatial distribution model of historical time series, a joint spatiotemporal prediction model is established; The joint spatiotemporal prediction model was trained using the historical Baume data distribution, the model's hyperparameters were adjusted, and the generalization ability of the joint spatiotemporal prediction model was evaluated using cross-validation. Set the Baume evaluation interval, input the Baume data of the current time and space, and predict the Baume value of each detection area at the future time through the spatiotemporal joint model.

9. The Chinese bee honeycomb honey Baume degree data processing system based on data analysis according to claim 8, characterized in that: The honeycomb honey evaluation module includes: a state evaluation submodule, a grade evaluation submodule, a time prediction submodule and a risk evaluation submodule; Wherein, the state evaluation submodule is used to evaluate the maturity state of honeycomb honey in different detection areas according to the distribution of Baume degrees; The grade assessment submodule is used to assess the eligibility of the honeycomb honey according to the difference in the average Baume values ​​of each detection area in the honeycomb honey, and after the eligibility assessment is passed, classify the grade of the honeycomb honey according to the Baume value based on the industry Baume standard; The time prediction submodule is used to predict the optimal honey collection time to reach the set Baume degree value according to the value of the Baume degree at the current moment and the trend analysis result of the Baume degree; The risk assessment submodule is used to combine the historical data and current status of the Baume degree to assess whether the honeycomb honey will have a Baume degree risk in the future.

10. A method for processing the Baume degree data of honeycomb of Chinese bee based on data analysis, used to implement the Baume degree data processing system of honeycomb of Chinese bee based on data analysis as claimed in any one of claims 1 to 9, characterized in that: The method comprises the following steps: S1. Real-time monitoring and control of temperature and humidity data in the honeycomb honey maturation workshop, and recording the entry and exit time and storage location of each honeycomb frame; S2, dividing the honeycomb frame into multiple detection areas, detecting the water content of the honeycomb honey in each detection area based on microwave technology, and matching the corresponding Baume degree of the honeycomb honey; S3. Analyze the distribution of the degree of Baume of the honeycomb honey at all locations according to the degree of Baume of the honeycomb honey in each detection area, and predict the trend of the degree of Baume change; S4. Based on the Baume analysis result of the honeycomb honey, the honey grade of the honeycomb honey is evaluated, and the honey collection time of the honeycomb honey is predicted; S5. Generate a visual chart display of the analysis results and the evaluation results, and generate a quality report of the honeycomb corresponding to each beehive frame.

Images