Intelligent management system for edible mushroom cloud bin based on multi-source monitoring data
Through the edible fungi Yunfangcang intelligent management system based on multi-source monitoring data, the environmental parameters are collected and analyzed in real time, and the adjustment control parameters are generated, which solves the problems that cannot be predicted and adapted in the existing technology, and the optimization of the edible fungi growth environment is achieved. and improve production efficiency.
Patent Information
- Application Number
- CN202410985412.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing automated planting systems cannot predict based on real-time data and lack adaptability, resulting in the edible fungus growth environment that cannot meet the needs of modern efficient agricultural production.
Using the edible fungus cloud warehousing intelligent management system based on multi-source monitoring data, connect environmental control intelligent devices, collect environmental parameters in real time, conduct horizontal data fusion and vertical trend analysis, generate adjustment control parameters, and feed them back to the environmental control intelligent devices for intelligent Management control.
Real-time optimization of the edible fungus growth environment has been achieved, production efficiency and quality have been improved, and the dynamic needs of the edible fungus growth environment have been met.
Smart Images

Figure CN118941018A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent management technology, and in particular to an edible fungus cloud warehouse intelligent management system based on multi-source monitoring data. Background Art
[0002] As a high-value-added agricultural product, the growth process of edible fungi is extremely sensitive to environmental conditions, including parameters such as temperature, humidity, light intensity and carbon dioxide concentration. These environmental parameters need to be precisely controlled to ensure the high yield and quality of edible fungi. Although the existing automated planting system has achieved automatic monitoring and adjustment of environmental parameters to a certain extent, it relies on preset thresholds and rules for control and cannot predict future environmental changes based on historical data and real-time data and make adjustments in advance; and it lacks adaptive capabilities and is difficult to respond to small changes in the environment in a timely manner, resulting in large fluctuations in environmental parameters, affecting the growth of edible fungi, and it is difficult to fully meet the needs of modern efficient agricultural production. Summary of the invention
[0003] The present application provides an edible fungus cloud warehouse intelligent management system based on multi-source monitoring data, which is used to solve the technical problems that the existing technology is unable to make predictions based on real-time data and lacks adaptive capabilities, resulting in the edible fungus growth environment being unable to meet real-time needs.
[0004] In view of the above problems, the present application provides an edible fungus cloud warehouse intelligent management system based on multi-source monitoring data.
[0005] The present application provides an edible fungus cloud warehouse intelligent management system based on multi-source monitoring data, the system comprising:
[0006] A connection module, wherein the connection module is connected to a cloud warehouse structure, wherein the cloud warehouse structure integrates an environmental control intelligent device, wherein the environmental control intelligent device includes air circulation equipment, ultrasonic atomization control equipment, light formula supply equipment, water purification equipment, in-warehouse environment disinfection equipment, and sensor monitoring equipment; a monitoring data acquisition module, wherein the monitoring data acquisition module acquires the monitoring data of the environmental control intelligent device and constructs a monitoring data list; a state analysis and prediction module, wherein the state analysis and prediction module performs data relationship alignment based on the monitoring data list, and performs square warehouse state analysis and prediction through the square warehouse cloud platform in accordance with the two dimensions of horizontal monitoring data fusion and vertical monitoring data trend to obtain a state analysis result; a parameter matching module, wherein the parameter matching module performs parameter matching with the adaptive adjustment module according to the state analysis result, generates adjustment control parameters, and feeds the adjustment control parameters back to the environmental control intelligent device for intelligent management and control.
[0007] The technical solution provided in this application has at least the following technical effects or advantages:
[0008] This application is connected to a cloud warehouse structure, which integrates an environmental control intelligent device, including air circulation equipment, ultrasonic atomization control equipment, light formula supply equipment, water purification equipment, warehouse environment disinfection equipment and sensor monitoring equipment; obtain monitoring data of environmental control intelligent equipment and build a monitoring data list; align data relationships based on the monitoring data list, and analyze and predict the state of the warehouse through the square warehouse cloud platform according to the two dimensions of horizontal monitoring data fusion and vertical monitoring data trend, and obtain the state analysis results; match parameters with the adaptive adjustment module according to the state analysis results, generate adjustment control parameters, and feed back the adjustment control parameters to the environmental control intelligent device for intelligent management and control. The present invention solves the technical problem that the prior art cannot be predicted based on real-time data, lacks adaptive capabilities, and causes the edible fungus growth environment to be unable to meet real-time needs. By real-time collection of environmental parameters, horizontal fusion and vertical trend analysis are performed, and state analysis and prediction are performed, and adjustment control parameters are generated according to the analysis results and the adaptive adjustment module matching, and fed back to the environmental control intelligent device, to achieve intelligent management and control, optimize environmental parameters, and achieve the technical effect of improving the production efficiency and quality of edible fungi. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0010] Figure 1 A schematic diagram of the structure of an edible fungus cloud warehouse intelligent management system based on multi-source monitoring data provided in an embodiment of the present application;
[0011] Figure 2 A flow chart of the intelligent management method of edible fungi cloud warehouse based on multi-source monitoring data provided in an embodiment of the present application.
[0012] Explanation of the reference numerals: connection unit 11 , monitoring data acquisition unit 12 , state analysis and prediction unit 13 , parameter matching unit 14 . DETAILED DESCRIPTION
[0013] The present application provides an edible fungus cloud warehouse intelligent management system based on multi-source monitoring data to solve the technical problem that the existing technology is unable to make predictions based on real-time data and lacks adaptive capabilities, resulting in the edible fungus growth environment being unable to meet real-time needs. By collecting environmental parameters in real time, horizontal fusion and vertical trend analysis are performed, and state analysis and prediction are performed, adjustment control parameters are generated according to the analysis results and matched with the adaptive adjustment module, and the parameters are fed back to the environmental control intelligent equipment to achieve intelligent management and control, optimize environmental parameters, and achieve the technical effect of improving the production efficiency and quality of edible fungi.
[0014] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0015] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.
[0016] Embodiment 1
[0017] like Figure 1 As shown, the present application provides an edible fungus cloud warehouse intelligent management system based on multi-source monitoring data, which is used to perform the following Figure 2 The edible fungus cloud warehouse intelligent management method based on multi-source monitoring data shown in the figure includes:
[0018] The connection unit 11 is connected to the cloud warehouse structure, and the cloud warehouse structure integrates an environmental control intelligent device, which includes air circulation equipment, ultrasonic atomization control equipment, light formula supply equipment, water purification equipment, warehouse environment disinfection equipment and sensor monitoring equipment.
[0019] In the embodiment of the present application, the connection unit is connected to the cloud warehouse structure, and the cloud warehouse structure integrates a set of environmental control intelligent devices. These environmental control intelligent devices include multiple subsystems, each of which has its specific function to ensure the best growth environment for edible fungi, including air circulation equipment, ultrasonic atomization control equipment, light formula supply equipment, water purification equipment, warehouse environment disinfection equipment and sensor monitoring equipment.
[0020] Among them, the air circulation equipment is responsible for maintaining air circulation in the warehouse, ensuring the appropriate concentration of oxygen and carbon dioxide, thereby promoting the respiration and metabolism of edible fungi; the ultrasonic atomization control equipment is used to accurately adjust the humidity in the warehouse to meet the strict humidity requirements of edible fungi; the light formula supply equipment provides light of a specific spectrum and intensity to simulate the natural light environment and promote the photosynthesis and growth of edible fungi; in addition, it is equipped with water purification equipment to ensure the purity of the water quality of the water supply system, remove harmful substances, and prevent pollution. The warehouse environment disinfection equipment is used to disinfect the warehouse environment, prevent the invasion of diseases and harmful microorganisms, and ensure the healthy growth of edible fungi; finally, the sensor monitoring equipment is used to monitor the temperature, humidity, light, water quality and other environmental parameters in the warehouse in real time.
[0021] The monitoring data acquisition unit 12 acquires the monitoring data of the environmental control intelligent device and constructs a monitoring data list.
[0022] In the embodiment of the present application, the monitoring data acquisition unit is connected to the environmental control intelligent device, including air circulation equipment, ultrasonic atomization control equipment, light formula supply equipment, water purification equipment, warehouse environment disinfection equipment and sensor monitoring equipment. Each device is equipped with a sensor for real-time monitoring of the environmental parameters for which it is responsible. For example, the air circulation equipment monitors the air circulation, the ultrasonic atomization control equipment monitors the humidity, the light formula supply equipment monitors the light intensity and spectrum, the water purification equipment monitors the water quality, the warehouse environment disinfection equipment monitors the disinfection situation, and the sensor monitoring equipment comprehensively monitors the temperature, humidity, light and water quality.
[0023] The monitoring data acquisition unit continuously collects real-time data of various environmental control devices through these sensors, including but not limited to temperature, humidity, light intensity, water quality parameters, and air circulation. The collected data are recorded one by one based on the timestamp to ensure the timeliness and accuracy of the data. After collecting multi-source monitoring data, the monitoring data acquisition unit summarizes the collected multi-source monitoring data into a monitoring data list.
[0024] The state analysis and prediction unit 13 performs data relationship alignment based on the monitoring data list, performs square warehouse state analysis and prediction through the square warehouse cloud platform according to the two dimensions of horizontal monitoring data fusion and vertical monitoring data trend, and obtains state analysis results.
[0025] In an embodiment of the present application, when aligning data relationships based on a monitoring data list, horizontal monitoring data fusion is performed to integrate data from different sensors and devices at the same time point. For example, a comprehensive view of the environmental state is provided by combining the temperature, humidity, light intensity, and water quality parameters at the same time point. At the same time, longitudinal monitoring data trends are performed to analyze the changing trends of the same monitoring item at different time points. For example, the changes in parameters such as temperature and humidity are tracked over different time periods.
[0026] After completing the data alignment, the Fangcang Cloud Platform is used to conduct in-depth analysis and prediction of these aligned data. Specifically, when performing state analysis, the current growth state of edible fungi is evaluated through a comprehensive analysis of the current environmental data. For example, by analyzing the current temperature, humidity, light and other data, it is determined whether the current environment is suitable for the growth of edible fungi. When performing state prediction, based on historical data and current status, algorithms such as time series analysis are used to predict future environmental change trends, predict future temperature and humidity changes, possible changes in light intensity, etc. Through the above process, the state analysis results are generated.
[0027] The parameter matching unit 14 performs parameter matching with the adaptive adjustment module according to the state analysis result, generates adjustment control parameters, and feeds back the adjustment control parameters to the environmental control intelligent device for intelligent management and control.
[0028] In an embodiment of the present application, the parameter matching unit receives the state analysis results provided by the state analysis prediction unit, which include current environmental parameters and predictions of future environmental changes. The parameter matching unit performs a detailed analysis of these data to determine the target values of each environmental parameter. In combination with the adjustment strategy provided by the adaptive adjustment module, the parameter matching unit generates a comprehensive adjustment plan. Specifically, the parameter matching unit generates adjustment control parameters by independently matching each parameter. For example, when it is detected that the temperature is lower than the target value, the temperature is increased by increasing the heating function of the air circulation equipment; when the humidity is lower than the target value, the humidity is increased by increasing the operating frequency of the ultrasonic atomizer; according to the target value of the light intensity, the light source output of the light formula supply device is adjusted. Based on these matching results, the parameter matching unit generates specific adjustment control parameters, including equipment operation settings such as wind speed, atomization frequency, and light intensity.
[0029] These adjustment control parameters are then transmitted to various environmental control intelligent devices, such as air circulation equipment, ultrasonic atomization control equipment, and light formula supply equipment. After receiving the control parameters, the environmental control intelligent devices will automatically adjust their working status. For example, the air circulation equipment adjusts the wind speed, the atomization equipment adjusts the humidity, and the lighting equipment adjusts the light intensity. After that, the monitoring data acquisition unit continuously monitors environmental changes and collects the adjusted data. If there is a deviation between the actual environmental state and the target value, the parameters are matched and adjusted again to form a closed-loop control.
[0030] Furthermore, the state analysis and prediction unit 13 in the system provided in the embodiment of the application is also used for:
[0031] According to the growth cycle of edible fungi, a periodic state chain is constructed; based on the periodic state chain, the timeliness of the control parameters of each time node is configured; the node distribution of the Fangcang cloud platform is obtained, and each node includes a calculation timeliness label; according to the control parameter timeliness and the calculation timeliness label, traversal matching is performed to establish a mapping relationship between the calculation node of the Fangcang cloud platform and the time node and its corresponding control parameter.
[0032] In the embodiment of the present application, a cycle state chain is first constructed according to the growth cycle of edible fungi. Specifically, the environmental demand data of edible fungi at different growth stages are collected through historical data, including temperature, humidity, light intensity, and carbon dioxide concentration. The growth process of edible fungi is then divided into multiple key stages, including spore germination stage, mycelium growth stage, fruiting body formation stage, and maturity stage. Finally, the environmental demand data of each growth stage are analyzed and summarized to determine the optimal temperature, humidity, light intensity, and carbon dioxide concentration of each stage. For example, the temperature needs to be maintained at 20-25 degrees Celsius and the humidity needs to be maintained at 60%-70% during the mycelium growth stage.
[0033] Next, based on the cycle state chain, configure the timeliness of the control parameters for each time node. Specifically, according to the cycle state chain, the growth cycle is divided into several time nodes, and each time node corresponds to a specific growth stage. Then use statistical analysis methods to determine the adjustment frequency and validity period of the control parameters at each time node. For example, by analyzing past data, it is determined that during the mycelium growth stage, the temperature and humidity need to be adjusted every hour, while the light intensity is adjusted every 6 hours. Finally, based on the results of the timeliness analysis, configure a specific control parameter adjustment plan for each time node. For example, during the mycelium growth stage, the temperature is monitored and adjusted every hour, and the humidity is monitored and adjusted every 2 hours.
[0034] After that, network scanning tools and system query commands are used to collect information about all computing nodes on the Fangcang cloud platform, including the node's geographic location, computing power, storage capacity, and network latency. Performance tests and historical data analysis are performed on each computing node, and computing timeliness labels are assigned. These labels reflect the computing power and response time of the node. For example, the computing timeliness label of node A is "high performance, low latency", and that of node B is "medium performance, medium latency". Next, traversal matching is performed based on the control parameter timeliness and computing timeliness labels. Specifically, the control parameters of each time node are grouped according to timeliness. For example, temperature parameters that are adjusted frequently are grouped together, and humidity parameters that are adjusted frequently are grouped together. According to the timeliness labels of each computing node, the node is assigned to the corresponding control parameter group. For example, nodes with high performance and low latency are assigned to the temperature control group that needs to be adjusted frequently, and nodes with medium performance are assigned to the humidity control group.
[0035] By traversing and matching, the mapping relationship between the computing nodes and time nodes and their corresponding control parameters of the Fangcang cloud platform is established. Specifically, according to the allocation results, a detailed mapping table is constructed, which records the time nodes and control parameters that each computing node is responsible for. For example, node A is responsible for temperature control in the 1-3 period, and node B is responsible for humidity control in the 4-6 period.
[0036] Furthermore, the state analysis and prediction unit 13 in the system provided in the embodiment of the application is also used for:
[0037] Construct an adaptive discrimination module, which is used to locate the growth cycle according to time and determine the timeliness information of the monitoring data; match the computing nodes of the Fangcang cloud platform according to the timeliness information, load the computing tasks to the corresponding computing nodes, perform Fangcang status analysis and prediction, and obtain the status analysis results.
[0038] In the embodiment of the present application, firstly, an adaptive discrimination module is constructed, the main function of which is to locate the growth cycle of edible fungi according to time, and to determine the timeliness information of monitoring data. Specifically, the cycle state chain and the current monitoring data are input into the adaptive discrimination module. The adaptive discrimination module identifies the current growth stage by analyzing the current monitoring data, such as temperature, humidity, light intensity, etc., and compares the current data with the cycle state chain to locate the specific position of the current time point in the growth cycle. Next, the timeliness information of the monitoring data is determined. Through timeliness analysis, the validity period and adjustment frequency of the monitoring data are determined. For example, some parameters such as temperature need to be monitored and adjusted every hour, while other parameters such as light may be adjusted every 6 hours. According to these analysis results, a timeliness label is generated for each monitoring data to identify the adjustment frequency and validity period required.
[0039] Then, the computing node information of the Fangcang cloud platform is obtained. Through network scanning tools and system query commands, the information of all computing nodes is collected, including computing power, storage capacity, and network latency. Each computing node is assigned a computing timeliness label based on performance testing and historical data analysis. These labels reflect the computing power and response time of the node. For example, the computing timeliness label of node A is "high performance, low latency", and that of node B is "medium performance, medium latency". According to the timeliness information provided by the adaptive discrimination module, the analysis and prediction tasks of the monitoring data are matched to the appropriate computing nodes. For example, the frequently adjusted temperature parameters are assigned to the high-performance, low-latency node A, while the less adjusted lighting parameters are assigned to the medium-performance node B. After the matching is completed, the computing task is loaded to the corresponding computing node, the status analysis and prediction tasks are started, and the task execution is monitored to ensure that the task is completed on time, and the analysis and prediction results are collected.
[0040] Finally, the adaptive discrimination module and the computing node work together to analyze and predict the state of the warehouse and generate state analysis results, including current environmental state assessment and future environmental state prediction.
[0041] Furthermore, the state analysis and prediction unit 13 in the system provided in the embodiment of the application is also used for:
[0042] Obtain the control parameter operation accuracy requirements for each time node of the periodic state chain; determine the weight ratio relationship between the control parameter operation accuracy requirements and the control parameter timeliness; obtain the operation accuracy of the operation nodes of the Fangcang cloud platform and the operation timeliness labels; use the weight ratio relationship as a constraint condition, according to the control parameter operation accuracy requirements and control parameter timeliness, with the goal of minimizing the matching loss value, optimize the matching with the operation accuracy of the operation nodes and the operation timeliness labels of the Fangcang cloud platform, and determine the mapping relationship between the control parameters corresponding to the operation nodes and time nodes.
[0043] In the embodiment of the present application, the control parameter calculation accuracy requirements of each time node of the periodic state chain are first obtained. The periodic state chain is an ideal environmental model for describing each stage of edible fungi growth. By analyzing these models, the calculation accuracy requirements of the environmental parameters required for each time node, such as temperature, humidity, light intensity, etc., are determined. For example, during the mycelium growth stage, the temperature change requires an accuracy of ±0.5 degrees Celsius, while the humidity change requires an accuracy of ±1%.
[0044] Next, determine the weight ratio between the control parameter calculation accuracy requirements and the control parameter timeliness. The control parameter timeliness refers to the frequency and timeliness of parameter adjustment. Through weight analysis, weights are assigned according to the importance and priority of each control parameter. For example, if the calculation accuracy and timeliness of the temperature parameter are equally important, the weight ratio is 50:50; if the timeliness of the humidity parameter is more important than accuracy, the weight ratio is 70:30. This process ensures that accuracy and timeliness are balanced when matching calculation nodes.
[0045] Subsequently, the computing node information of the Fangcang cloud platform is obtained, including the computing accuracy and computing timeliness label of each node. Then, performance testing and historical data analysis are performed on each computing node, and computing timeliness labels are assigned. These labels reflect the computing power and response time of the node. For example, the label of node A is "high performance, low latency", and the label of node B is "medium performance, medium latency".
[0046] After obtaining the information of control parameters and operation nodes, optimization matching is performed to minimize the matching loss value. Specifically, the objective function of optimization matching is first set to minimize the mismatch between operation nodes and control parameters, that is, the matching loss value. The loss value reflects the mismatch between operation accuracy and timeliness. The objective function is M Where L is the total loss value, n is the number of control parameters, and w i is the weight ratio of the i-th parameter, P i is the computational accuracy requirement of the ith control parameter, N i is the computational accuracy of the ith computational node, T i is the timeliness of the ith control parameter, N t is the computational timeliness label of the computational node. Then, an optimization algorithm, such as linear programming or genetic algorithm, is used to match the control parameters and computational nodes according to the objective function. The algorithm considers the computational accuracy requirements, timeliness, and weight ratio of each control parameter, and combines the computational accuracy and computational timeliness label of the computational node to find the optimal matching solution. After the optimization algorithm runs, the mapping relationship between the control parameters of each time node and the corresponding computational node is determined. For example, node A is responsible for high-precision, low-latency temperature control, and node B is responsible for medium-precision, medium-latency humidity control.
[0047] Furthermore, the state analysis and prediction unit 13 in the system provided in the embodiment of the application is also used for:
[0048] Time alignment is performed based on the timestamp of the monitoring data; different monitoring data at the same time point are used as horizontal monitoring data, and different time series of the same monitoring data are used as vertical monitoring data; multi-source monitoring data fusion analysis is performed based on the horizontal monitoring data to obtain the status analysis results of the edible fungi in the square warehouse; based on the vertical monitoring data, trend analysis and prediction are performed using a time series analysis algorithm to obtain the status analysis results.
[0049] In an embodiment of the present application, time alignment is first performed based on the timestamp of the monitoring data. Real-time monitoring data, including temperature, humidity, light intensity, etc., are collected from each sensor, and each piece of data is ensured to have an accurate timestamp. Through timestamp processing, all monitoring data are time-aligned, and missing data are supplemented using interpolation or data filling methods to ensure that there are complete data records at each time point. Next, different monitoring data at the same time point are used as horizontal monitoring data, and different time series of the same monitoring data are used as vertical monitoring data. Specifically, the data of all sensors, such as temperature, humidity, and light intensity, are summarized at each time point to form a horizontal monitoring data set. At the same time, the data of each sensor is processed in time series, such as recording the data of the temperature sensor at multiple time points to form a vertical monitoring data sequence.
[0050] Next, multi-source monitoring data fusion analysis is performed based on the horizontal monitoring data. First, the data of different sensors are standardized to eliminate dimensional differences and ensure the accuracy of data fusion. Then, fusion algorithms such as weighted average and principal component analysis are used to fuse the horizontal monitoring data and extract key features. Through fusion analysis, the current environmental status is judged based on comprehensive data. For example, by analyzing the comprehensive data of temperature, humidity and light intensity, it is evaluated whether the current environment is suitable for the growth of edible fungi and the status analysis results of edible fungi in the square warehouse are obtained.
[0051] Based on the longitudinal monitoring data, the time series analysis algorithm is used to perform trend analysis and forecasting. First, a suitable time series model, such as the ARIMA model, is selected to model the longitudinal monitoring data. By applying the time series model, historical data is analyzed to identify the periodicity, trend, and random components in the data. Based on the analysis results of the time series model, future trend forecasts are made, such as predicting the changing trends of temperature and humidity in the next few hours or days, to obtain state analysis results.
[0052] Furthermore, the state analysis and prediction unit 13 in the system provided in the embodiment of the application is also used for:
[0053] The horizontal monitoring data is synchronously processed by a sliding window method to eliminate the time difference in sampling frequency or data transmission delay of different monitoring devices; the state analysis of the horizontal monitoring data is performed by a multi-source regression analysis model trained with sample data to obtain the state analysis result.
[0054] In an embodiment of the present application, a sliding window method is first used to perform data synchronization processing on the lateral monitoring data to eliminate the time difference in sampling frequency or data transmission delay of different monitoring devices. Specifically, a sliding window of appropriate size is first defined by a technical expert and adjusted according to the sampling frequency and data transmission delay of the device. For example, if the temperature sensor samples once per minute and the humidity sensor samples once every two minutes, the size of the sliding window is set to two minutes to ensure that all sampled data are covered. Within each sliding window, the data from different devices are time-aligned. The sliding window moves step by step on the time series data, one time step at a time, aligning the monitoring data of different devices within the window to ensure that the data at the same time point can be synchronized. For missing data points in the window, they are filled by interpolation methods. For example, linear interpolation fills missing values with the average value of adjacent data points to ensure the continuity and consistency of the data.
[0055] After completing the data synchronization processing, the state analysis of the horizontal monitoring data is performed through the multi-source regression analysis model trained with sample data. Specifically, the horizontal monitoring data after synchronization processing is standardized to eliminate the differences between different dimensions and ensure the accuracy of data fusion. For example, the data such as temperature, humidity, and light intensity are normalized so that their values are between 0 and 1. The multi-source regression analysis model is trained using historical sample data. Through regression analysis, the relationship between the various monitoring parameters is established. For example, a multivariate linear regression model is used to predict the overall state of the environment through parameters such as temperature, humidity, and light intensity. The current horizontal monitoring data after synchronization processing is input into the trained multi-source regression analysis model for state analysis to obtain the state analysis results.
[0056] Furthermore, the state analysis and prediction unit 13 in the system provided in the embodiment of the application is also used for:
[0057] Construct a time series for each monitoring data and record the numerical changes at different time points; use the time series analysis algorithm to analyze the changing trend of the monitoring data in the time series; identify and locate abnormal data based on the changing trend, and perform state analysis and state prediction based on the difference amount of the abnormal data and the change coefficient of the changing trend.
[0058] In the embodiment of the present application, firstly, a time series is constructed for each monitoring data, and the value changes at different time points are recorded. Specifically, various environmental data, including temperature, humidity, and light intensity, are collected in real time by sensors. Each data point is accompanied by an accurate timestamp to ensure the temporal continuity and consistency of the data. These data are arranged in chronological order to form a time series of each parameter. For example, the readings of the temperature sensor at different time points form a temperature time series, and the readings of the humidity sensor form a humidity time series.
[0059] Next, we use time series analysis algorithms to analyze the trend of these time series data. We select a suitable time series model, such as the ARIMA model, and train it on historical data. The trained model can identify the periodicity, trend, and random components in the data. By applying these models, we analyze the current time series data and extract potential trends. For example, the seasonal fluctuations and long-term trends of temperature data can be revealed through the ARIMA model.
[0060] Based on trend analysis, abnormal data is identified according to the change trend. By calculating the difference between the actual data and the predicted value of the time series model, a threshold is set to identify abnormal data. The threshold is pre-set. When the difference exceeds the set threshold, the data point is marked as abnormal. For example, the difference threshold of temperature data is set to 2 degrees Celsius. When the difference between the actual temperature and the predicted temperature exceeds 2 degrees Celsius, the data point is identified as abnormal data.
[0061] Subsequently, the abnormal data is located, and state analysis and state prediction are performed based on the difference amount of these abnormal data and the coefficient of variation of the time series analysis. First, the difference amount of the abnormal data is calculated. For example, the specific difference amount of the temperature abnormal data is calculated. Then, according to the coefficient of variation of the time series analysis, the current environmental state is analyzed to identify the key factors affecting the growth of edible fungi. Based on the current state analysis results and time series trends, further state prediction is performed. By analyzing the current environmental parameters and the identified abnormal data, the future environmental change trend is predicted. For example, the change trend of temperature and humidity in the next few hours or days is predicted. Through the above process, state analysis and state prediction are completed.
[0062] Furthermore, the state analysis and prediction unit 13 in the system provided in the embodiment of the application is also used for:
[0063] The state prediction analysis is performed by analyzing the prediction model, and the expression of the analysis prediction model is: in, is the autoregression coefficient, θ j is the moving average coefficient, e t is the error term, Δt is the difference of abnormal data, β tis the coefficient of change of the trend, γ and δ are the weight coefficients of the difference of abnormal data and the coefficient of change of the trend, T t is the current normal value, is an outlier, T t-1 is the normal value of the previous time node, is the outlier value at the previous time node.
[0064] In the embodiment of the present application, the analysis and prediction model is obtained by training historical data through a time series analysis model, such as an ARIMA model. According to the difference between the actual monitoring data and the predicted value of the time series model, the difference amount of the abnormal data and the coefficient of change of the change trend are calculated. The coefficient of change of the change trend represents the degree of deviation of the abnormal data from the normal trend, which is calculated by the time series analysis model. Specifically, the time series model is used to decompose the time series data into trend components, seasonal components and residual components. The trend components are analyzed to calculate the rate of trend change. For example, for the time series T t The trend change rate is obtained by calculating the difference between adjacent time points. To reduce the impact of noise, the change rate is smoothed and the smoothed change rate is used as the change coefficient β of the change trend. t .
[0065] Finally, the monitoring data at the current time point is input into the prediction model, and the environmental status at the future time point is predicted by combining the calculated difference and change trend. The future environmental status is calculated by the prediction model to form a status analysis report, including the current environmental status analysis and future environmental status prediction.
[0066] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:
[0067] This application is connected to a cloud warehouse structure, which integrates an environmental control intelligent device, including air circulation equipment, ultrasonic atomization control equipment, light formula supply equipment, water purification equipment, warehouse environment disinfection equipment and sensor monitoring equipment; obtain monitoring data of environmental control intelligent equipment and build a monitoring data list; align data relationships based on the monitoring data list, and analyze and predict the state of the warehouse through the square warehouse cloud platform according to the two dimensions of horizontal monitoring data fusion and vertical monitoring data trend, and obtain the state analysis results; match parameters with the adaptive adjustment module according to the state analysis results, generate adjustment control parameters, and feed back the adjustment control parameters to the environmental control intelligent device for intelligent management and control. The present invention solves the technical problem that the prior art cannot be predicted based on real-time data, lacks adaptive capabilities, and causes the edible fungus growth environment to be unable to meet real-time needs. By real-time collection of environmental parameters, horizontal fusion and vertical trend analysis are performed, and state analysis and prediction are performed, and adjustment control parameters are generated according to the analysis results and the adaptive adjustment module matching, and fed back to the environmental control intelligent device, to achieve intelligent management and control, optimize environmental parameters, and achieve the technical effect of improving the production efficiency and quality of edible fungi.
[0068] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0069] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
[0070] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.
Claims
1. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data is characterized by: The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data includes: A connection unit, wherein the connection unit is connected to a cloud warehouse structure, wherein the cloud warehouse structure integrates an environment control intelligent device, wherein the environment control intelligent device includes an air circulation device, an ultrasonic atomization control device, a light formula supply device, a water purification treatment device, an in-warehouse environment disinfection device, and a sensor monitoring device; A monitoring data acquisition unit, which acquires the monitoring data of the environmental control intelligent device and constructs a monitoring data list; A state analysis and prediction unit, which performs data relationship alignment based on the monitoring data list, performs square warehouse state analysis and prediction through the square warehouse cloud platform according to the two dimensions of horizontal monitoring data fusion and vertical monitoring data trend, and obtains a state analysis result; A parameter matching unit performs parameter matching with the adaptive adjustment module according to the state analysis result, generates adjustment control parameters, and feeds back the adjustment control parameters to the environmental control intelligent device for intelligent management and control.
2. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data according to claim 1, characterized in that: The obtaining of the state analysis result also includes: According to the growth cycle of edible fungi, a cycle state chain is constructed; Configure the timeliness of control parameters of each time node based on the periodic state chain; Obtain the node distribution of the Fangcang cloud platform, each node including a computing timeliness label; According to the control parameter timeliness and the operation timeliness label, a traversal match is performed to establish a mapping relationship between the operation node of the Fangcang cloud platform and the time node and its corresponding control parameter.
3. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data as claimed in claim 2, characterized in that: The obtaining of the state analysis result comprises: Constructing an adaptive discrimination module, wherein the adaptive discrimination module is used to locate the growth cycle according to time and determine the timeliness information of the monitoring data; The computing nodes of the Fangcang cloud platform are matched according to the timeliness information, the computing tasks are loaded to the corresponding computing nodes, the Fangcang status is analyzed and predicted, and the status analysis results are obtained.
4. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data as claimed in claim 2, characterized in that: Establishing a mapping relationship between the computing nodes of the Fangcang cloud platform and the time nodes and their corresponding control parameters also includes: Obtaining the control parameter calculation accuracy requirements for each time node of the periodic state chain; Determine the weight ratio relationship between the control parameter calculation accuracy requirement and the control parameter timeliness; Obtaining the computing accuracy of the computing nodes of the Fangcang cloud platform and the computing timeliness label; Taking the weight ratio relationship as a constraint condition, according to the control parameter operation accuracy requirements and control parameter timeliness, with the goal of minimizing the matching loss value, the operation accuracy of the operation nodes of the Fangcang cloud platform and the operation timeliness labels are optimized to determine the mapping relationship between the control parameters corresponding to the operation nodes and time nodes.
5. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data according to claim 1, characterized in that: Based on the monitoring data list, data relationship alignment is performed, and the Fangcang status analysis and prediction are performed through the Fangcang cloud platform in two dimensions: horizontal monitoring data fusion and vertical monitoring data trend, including: Time alignment based on the timestamp of monitoring data; Different monitoring data at the same time point are used as horizontal monitoring data, and different time series of the same monitoring data are used as longitudinal monitoring data; Perform multi-source monitoring data fusion analysis based on the horizontal monitoring data to obtain the status analysis results of the edible fungi in the square warehouse; Based on the longitudinal monitoring data, a time series analysis algorithm is used to perform trend analysis and prediction to obtain a status analysis result.
6. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data as claimed in claim 5, characterized in that: The multi-source monitoring data fusion analysis is performed based on the horizontal monitoring data to obtain the status analysis results of the edible fungi in the square warehouse, including: Performing data synchronization processing on the horizontal monitoring data by a sliding window method to eliminate time differences in sampling frequencies or data transmission delays of different monitoring devices; The state analysis is performed on the horizontal monitoring data by using a multi-source regression analysis model trained with sample data to obtain the state analysis result.
7. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data as claimed in claim 5, characterized in that: Based on the longitudinal monitoring data, trend analysis and forecasting are performed using time series analysis algorithms, including: Construct a time series for each monitoring data and record the changes in values at different time points; Analyzing the changing trend of the monitoring data in the time series using a time series analysis algorithm; Abnormal data is identified and located according to the change trend, and state analysis and state prediction are performed according to the difference amount of the abnormal data and the change coefficient of the change trend.
8. The edible fungus cloud warehouse intelligent management system based on multi-source monitoring data as claimed in claim 7, characterized in that: Performing state analysis and state prediction according to the difference amount of the abnormal data and the change coefficient of the change trend includes: The state prediction analysis is performed by analyzing the prediction model, and the expression of the analysis prediction model is: in, is the autoregression coefficient, θ j is the moving average coefficient, e t is the error term, Δt is the difference of abnormal data, β t is the coefficient of change of the trend, γ and δ are the weight coefficients of the difference of abnormal data and the coefficient of change of the trend, T t is the current normal value, is an outlier, T t-1 is the normal value of the previous time node, is the outlier value at the previous time node.
Citation Information
Cited By
Poria cocos strain activity detection method and device
CN120107196A
Photovoltaic-edible mushroom collaborative intelligent agricultural industry fusion management and control method and system
CN121168882A
