Method and system for intelligently monitoring and analyzing carbon dioxide in composting process

Abstract

The invention discloses an intelligent detection system for carbon dioxide in a composting process, particularly relates to the technical field of carbon dioxide detection, and is used for solving the problem of inaccurate detection of carbon dioxide in an existing compost pile. Comprising a real-time data detection module and a data analysis module which are in signal connection. According to the method, the composting heap is partitioned, and the representative carbon dioxide concentration in the composting process is determined according to the carbon dioxide concentration weight of each partition, so that the problem that the carbon dioxide concentration confirmation is relatively fuzzy in the existing composting process is solved; the carbon dioxide concentration can be effectively and accurately analyzed, the carbon dioxide concentration in the future can be predicted, and the risk of excessive carbon dioxide in the future is reduced on the premise of ensuring real-time detection.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon dioxide detection, and in particular to a method and system for intelligent monitoring and analysis of carbon dioxide in a composting process. Background Art

[0002] Composting is an important way to treat organic waste. It converts waste into fertilizer by decomposing organic matter through microorganisms. However, during the composting process, the carbon dioxide concentration parameters in the compost pile need to be strictly monitored to ensure the smooth progress of the composting reaction and avoid safety hazards caused by overreaction. Existing composting detection methods are usually single and limited. They cannot effectively and accurately detect and analyze the carbon dioxide concentration. They are inefficient and prone to data errors. Therefore, it is of great significance to develop an automated detection and analysis system based on intelligent sensors. Summary of the invention

[0003] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method and system for intelligent monitoring and analysis of carbon dioxide in a composting process to solve the problems raised in the above-mentioned background technology.

[0004] An intelligent carbon dioxide detection system for composting process, including real-time data detection module, data analysis module, future carbon dioxide concentration

[0005] Prediction module and data storage module, signal connection between modules;

[0006] The real-time data detection module is used to obtain the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer of the compost pile, and send the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer to the data analysis module;

[0007] After receiving the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, the data analysis module determines the weight coefficients of the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, and performs weighted calculation of the real-time representative carbon dioxide concentration of the compost pile according to the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, and sends the real-time representative carbon dioxide concentration of the compost pile to the future carbon dioxide concentration prediction module;

[0008] After receiving the real-time representative carbon dioxide concentration of the compost pile, the future carbon dioxide concentration prediction module uses a time series model to predict the future carbon dioxide concentration;

[0009] The data storage module is used to store all data during the platform processing process.

[0010] In a preferred embodiment, the real-time data detection module divides the compost pile into several layers from top to bottom, and then performs separate real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration monitoring on each layer.

[0011] In a preferred embodiment, the data analysis module determines the real-time temperature and carbon-nitrogen ratio of each layer area and the weight coefficient of carbon dioxide concentration, including the following steps;

[0012] After receiving the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, the data analysis module calculates the weight of the real-time temperature and carbon-nitrogen ratio of each layer;

[0013] The weight coefficient of the real-time carbon dioxide concentration of each layer is calculated according to the normalized weight of the real-time temperature and carbon-nitrogen ratio of each layer, and the weight value of the real-time carbon dioxide concentration of each layer is determined by assigning weights to the implemented carbon dioxide weight coefficients of each layer according to the priority diagram method;

[0014] The real-time carbon dioxide concentration of each layer is weighted and calculated according to the weight value of the real-time carbon dioxide concentration of each layer to obtain the real-time carbon dioxide concentration representative of the compost pile.

[0015] In a preferred embodiment, the future carbon dioxide concentration prediction module uses the time series model to predict the future carbon dioxide concentration, including the following steps:

[0016] After receiving the representative real-time carbon dioxide concentration of the compost pile, the future carbon dioxide concentration prediction module defines the representative real-time carbon dioxide concentration of the compost pile as an input variable and substitutes it into the time series model; the representative real-time carbon dioxide concentration is simulated and trained using the time series model to predict the future carbon dioxide concentration.

[0017] A method for intelligent detection and analysis of carbon dioxide in a composting process comprises the following steps:

[0018] The real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer of the compost pile are obtained, the weight coefficients of the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer are determined, and the real-time representative carbon dioxide concentration of the compost pile is weightedly calculated according to the real-time representative carbon dioxide concentration of the compost pile. The future carbon dioxide concentration is predicted using a time series model based on the real-time representative carbon dioxide concentration of the compost pile.

[0019] In a preferred embodiment, after the compost pile is divided into several layers from top to bottom, each layer is separately monitored for its temperature, carbon-nitrogen ratio and carbon dioxide concentration in real time.

[0020] In a preferred embodiment, determining the real-time temperature and carbon-nitrogen ratio of each layer area and the weight coefficient of carbon dioxide concentration includes the following steps:

[0021] After obtaining the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, the weights of the real-time temperature and carbon-nitrogen ratio of each layer are calculated; the weight coefficient of the real-time carbon dioxide concentration of each layer is calculated according to the normalized weights of the real-time temperature and carbon-nitrogen ratio of each layer, and the implemented carbon dioxide weight coefficient of each layer is weighted according to the priority diagram method to determine the weight value of the real-time carbon dioxide concentration of each layer;

[0022] The real-time carbon dioxide concentration of each layer is weighted and calculated according to the weight value of the real-time carbon dioxide concentration of each layer to obtain the real-time carbon dioxide concentration representative of the compost pile.

[0023] In a preferred embodiment, using a time series model to predict future carbon dioxide concentrations includes the following steps:

[0024] After obtaining the representative real-time carbon dioxide concentration of the compost pile, the representative real-time carbon dioxide concentration of the compost pile is defined as an input variable and substituted into the time series model; the representative real-time carbon dioxide concentration is simulated and trained using the time series model to predict the future carbon dioxide concentration.

[0025] The technical effects and advantages of the method and system for intelligent monitoring and analysis of carbon dioxide in a composting process of the present invention are as follows:

[0026] The present invention divides the carbon dioxide concentration of the compost pile into concentration zones and determines the overall concentration of carbon dioxide in the composting process according to the state of each concentration zone, thereby solving the problem of inaccurate detection of carbon dioxide concentration in the existing composting process. At the same time, the present invention can effectively and accurately detect the carbon dioxide concentration by combining the overall concentration of carbon dioxide in the composting process with the real-time temperature and carbon-nitrogen ratio of the compost pile, thereby improving the organic matter conversion rate of the compost pile. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0028] Figure 1 This is a framework diagram of an intelligent carbon dioxide detection and analysis system for a composting process in the present invention;

[0029] Figure 2 The present invention is a flow chart of a method for intelligent detection and analysis of carbon dioxide in a composting process. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] The present invention first divides the carbon dioxide concentration of the compost pile into concentration zones, and determines the overall concentration of carbon dioxide in the composting process according to the state of each concentration zone, thereby solving the problem of inaccurate detection of carbon dioxide concentration in the existing composting process. At the same time, the present invention can effectively and accurately detect the carbon dioxide concentration by combining the overall concentration of carbon dioxide in the composting process with the real-time temperature and carbon-nitrogen ratio of the compost pile, thereby improving the organic matter conversion rate of the compost pile.

[0032] Embodiment, a carbon dioxide intelligent detection system for composting process, such as Figure 1 As shown, it includes: a real-time data detection module, a data storage module, a data analysis module, a future carbon dioxide concentration prediction module, and signal connections between the modules.

[0033] The functions of each module are as follows:

[0034] The real-time data detection module is used to detect the real-time concentration of carbon dioxide in several areas of the compost pile, and send the real-time concentration of each layer to the data analysis module. The data analysis module is used to determine the concentration coefficient of carbon dioxide in the composting process to ensure that the overall concentration assessment of the compost pile is accurate. At the same time, the real-time data detection module is also used to monitor the real-time temperature and carbon-nitrogen ratio in the compost, and send the real-time temperature and carbon-nitrogen ratio data to the data analysis module for the data analysis module to generate analysis and statistical reports as a decision-making reference to ensure that the conversion rate of organic matter is improved.

[0035] After receiving the data sent by the real-time data detection module, the data analysis module determines the weight coefficients of the real-time temperature and carbon-nitrogen ratio of each monitoring area, and weights the weight coefficients of the real-time data of each monitoring area to obtain the overall concentration coefficient of carbon dioxide in the composting process, which is used for the data analysis module to generate analysis and statistical reports as a decision-making reference to ensure that the conversion rate of organic matter is improved, realize the recycling of resources, and improve soil health.

[0036] After receiving the overall concentration coefficient from the real-time data detection module, the data analysis module generates a data statistical analysis report using real-time data stream processing.

[0037] The future carbon dioxide concentration prediction module is used to predict the future carbon dioxide concentration based on the real-time temperature and carbon-nitrogen ratio data and the representative carbon dioxide concentration data after the data analysis module obtains representative carbon dioxide through data processing.

[0038] The data storage module is used to store all data during the platform processing process.

[0039] When the real-time data detection module monitors the real-time concentration of several areas of the compost pile, the division method and results of the several areas are not the same. For example, the entire compost pile can be evenly divided in a certain direction, that is, from top to bottom, from left to right, etc.

[0040] It should be noted that this software system is divided into four main functional modules: real-time data detection module, data storage module, future carbon dioxide concentration prediction module, and data analysis module. The real-time data detection module is responsible for connecting with sensors, collecting and transmitting real-time carbon dioxide concentration, temperature, and carbon-nitrogen ratio data, while the data analysis module is responsible for receiving and processing these data, generating visual reports, and providing decision support.

[0041] It should be noted that, considering the environmental characteristics and detection requirements of the composting process, non-dispersive infrared sensors with high precision and stability and suitable for multi-layer monitoring are used uniformly.

[0042] The specific workflow of the real-time data detection module is as follows:

[0043] The real-time data detection module is first connected to the sensor devices of each layer of the compost pile through the sensor interface. The data analysis module receives data from the sensor at regular intervals. Each data collection includes the number of layers, carbon dioxide concentration, temperature, carbon-nitrogen ratio and timestamp. After each data collection, the data analysis module will parse the data and mark the carbon dioxide concentration and temperature information of each layer with a timestamp.

[0044] The real-time data detection module encapsulates the data into a standardized JSON data packet through a message queue or API. It should be noted that the JSON data packet needs to contain hierarchical information, carbon dioxide concentration and temperature, carbon-nitrogen ratio and timestamp. After the JSON data packet is formed, the real-time data detection module passes the data to the data analysis module through the HTTP API. During the data transmission process, the real-time data detection module sets a retry mechanism to prevent transmission failure and ensure the continuity and real-time nature of the data. It should be noted that the descriptions in this paragraph are all conventional technical means and will not be repeated here.

[0045] The specific workflow of the data analysis module is as follows:

[0046] After receiving the real-time data, the data analysis module first performs hierarchical data processing and stores the data of each layer in the database in chronological order. The data storage is organized by "layer" and "timestamp" to facilitate subsequent query and analysis.

[0047] Specifically, the compost pile is divided into the bottom layer, the middle layer and the top layer. The data collected by the real-time data detection module includes the following:

[0048] CO2 concentration, temperature, carbon-nitrogen ratio and timestamp for each layer

[0049] Data collected by the sensor:

[0051] After receiving this set of data, the data analysis module processes each layer of data separately to ensure that the data of each layer is recorded in chronological order.

[0052] Specifically, we first split the data and mark each layer of data as "bottom layer", "middle layer" and "top layer", and attach the carbon dioxide concentration, temperature, carbon-nitrogen ratio and timestamp to each layer to form the following three sets of layered data records:

[0053] Bottom layer: CO2 concentration 200ppm, temperature 25℃, C / N ratio 20, time 202X-XX-XX 10:00

[0054] Middle layer: CO2 concentration 250ppm, temperature 30℃, C / N ratio 24, time 202X-XX-XX 10:00

[0055] Top layer: CO2 concentration 150ppm, temperature 35℃, C / N ratio 32, time 202X-XX-XX 10:00

[0056] Next, the data after layering processing is stored in the data storage module. It should be noted that storing data in a database is a conventional technical means and will not be elaborated here.

[0057] The records in the database will store the data of each layer in chronological order, as shown in the following example:

[0059] Through this hierarchical data processing and database storage method, the data analysis module can efficiently manage and analyze data from different layers, ensuring that the CO2 and temperature data of each layer of the compost pile are fully recorded and tracked.

[0060] Next, the data analysis module summarizes the data of each layer, calculates the average carbon dioxide concentration and temperature and carbon-nitrogen ratio of each layer, and compares them with the set safety threshold to check whether the data is abnormal. If the carbon dioxide concentration or temperature, carbon-nitrogen ratio of a layer exceeds the set safety range, the data analysis module will generate an abnormal mark in the data analysis module.

[0061] Specifically: The data analysis module queries the database for records of each layer (such as the bottom layer, middle layer, and top layer) within the time window. The data of each layer contains records of multiple time points. The data analysis module will put these data into an array or table of the corresponding level for easy calculation.

[0062] It should be noted that the query and storage of the database are both conventional technologies and will not be elaborated here.

[0063] Furthermore, after completing the data aggregation, the data analysis module will calculate the data of each layer to obtain the average value of the carbon dioxide concentration, real-time temperature and carbon-nitrogen ratio of each layer within the time window.

[0064] It should be noted that:

[0065] Average carbon dioxide concentration: Sum all carbon dioxide concentration data for each layer within the time period, and then divide by the number of data to get the average carbon dioxide concentration for each layer.

[0066] Temperature average: Sum the temperature data of each layer within the time period, and then divide it by the number of data to get the temperature average of each layer.

[0067] Next, the data analysis module compares the average value of each layer with the preset safety threshold. The safety upper limit of carbon dioxide concentration is set to 400ppm, the safety upper limit of temperature is set to 60℃, and the safety upper limit of carbon-nitrogen ratio is set to 40. If the average value of carbon dioxide, the average value of temperature, or the average value of carbon-nitrogen ratio exceeds the threshold, the data analysis module marks the layer as "abnormal". The comparison process is implemented using simple conditional judgment logic, which will not be described here.

[0068] The data analysis module transmits the abnormal situation to the visualization interface, prompting the user that the data at this layer is abnormal and recommends timely management measures.

[0069] Specifically, the data analysis module first calculates the average value of the carbon dioxide concentration and temperature of each layer, and finds that the carbon dioxide concentration in the middle layer has reached 500ppm, exceeding the set safety threshold of 400ppm. Therefore, the data analysis module will mark the middle layer as "abnormal" and prepare to pass this information to the visualization interface. The data analysis module packages the abnormal information into a data object and sends it to the visualization interface through the API in the data analysis module. It should be noted that this data object contains detailed information about the abnormality, including layer, abnormality type, current value, threshold, occurrence time, and processing suggestions.

[0070] The workflow of the future carbon dioxide concentration prediction module is as follows:

[0071] The future CO2 concentration prediction module will perform time series analysis on the data of each layer to identify the long-term trend of the data. Based on historical data, the future CO2 concentration prediction module uses the ARIMA prediction model to predict the change of CO2 concentration in the next hour. This prediction result helps to detect potential abnormalities in advance and provide support for management decisions.

[0072] Specifically, the carbon dioxide concentration sensors deployed on each layer of the composting area detect the carbon dioxide concentration of each layer, and use a periodic sampling method with automatic collection at a set time interval to collect data. The collected carbon dioxide concentration data is transmitted to the data center via the WiFi wireless communication protocol. After the data is transmitted to the data storage module, the future carbon dioxide concentration prediction module will store and process the time series data in the Influx DB way. It should be noted that the storage and processing technology of the Influx DB database is a conventional technology and will not be described here.

[0073] The carbon dioxide concentration of each layer in the past few hours is shown in the following table:

[0075] Next, the future carbon dioxide concentration prediction module uses the ARIMA method to predict the future carbon dioxide concentration.

[0076] It should be noted that the higher the temperature, the more intense the decomposition activity, so the weight of the impact on the carbon dioxide concentration can be proportional to the temperature. During the composting process, microorganisms produce carbon dioxide by decomposing organic matter. Microorganisms need carbon and nitrogen sources for metabolic activities, but the ratio of the two directly affects their decomposition efficiency. We can use temperature and carbon-nitrogen ratio as weights to weight the carbon dioxide concentration of each layer.

[0077] Calculate the weights of the real-time temperature and carbon-nitrogen ratio of each layer, and use linear normalization to map the real-time temperature and carbon-nitrogen ratio of each layer to the interval [0,1]. The formula is: Where Normalized_Score is the normalized value.

[0078] It should be noted that the normalization formula given in this embodiment is a general formula and will not be described in detail here.

[0079] After normalizing the real-time temperature and carbon-nitrogen ratio of each layer, they are marked as a and b respectively, and the carbon dioxide consideration weight of each layer is Q(i)=a+b. In the formula, Q(i) is the carbon dioxide consideration weight of each layer, and i represents the sequence number of each layer.

[0080] After calculating the carbon dioxide consideration weights of each layer, the carbon dioxide consideration weights of each layer are compared.

[0081] Obviously, the greater the real-time temperature and carbon-nitrogen ratio, the lower the carbon dioxide concentration in the corresponding layer, and the more attention it needs to be paid, that is, the more important it is, the greater the weight of carbon dioxide consideration should be, and the unit time can be set according to actual needs, which will not be elaborated here.

[0082] It should be noted that the real-time temperature of each layer and the carbon-nitrogen ratio of each layer can also be calculated by weighting according to actual conditions, which will not be elaborated here.

[0083] The weight coefficient and weight value of the real-time temperature and carbon-nitrogen ratio of each layer are calculated according to the normalized real-time temperature and carbon-nitrogen ratio of each layer, and the carbon dioxide consideration weight of each layer is assigned according to the priority diagram method to determine the weight value of the carbon dioxide concentration of each layer.

[0084] Specifically, the weights of carbon dioxide considerations at each layer are assigned according to the priority diagram method as shown in the following table: A B C TTL Weight A 0.5 1 1 2.5 0.5556 B 0 0.5 1 1.5 0.6 C 0 0 0.5 0.5 0.1111

[0086] It should be noted that the A, B, and C areas in the two tables correspond to each layer in this embodiment one by one. After sorting each layer according to the size of the carbon dioxide consideration weight, they correspond to the A, B, and C areas in order from large to small. Next, the carbon dioxide consideration weights of each layer are weighted and calculated to obtain representative carbon dioxide concentration data. It should be noted that the weighted calculation of real-time temperature and carbon-nitrogen ratio and the calculation of the final representative carbon dioxide concentration are all performed in the data analysis module.

[0087] The present invention determines the carbon dioxide consideration weight of each layer by first evaluating the real-time temperature and carbon-nitrogen ratio of each layer, and weights them according to the relative weight. In this way, the overall carbon dioxide concentration calculated is more representative and can better grasp the carbon dioxide concentration index of the composting process.

[0088] The ARIMA model requires that the input data is stable. In the future, the CO2 concentration prediction module will first use the ADF test method to test the stability of the representative CO2 concentration time series. It should be noted that the representative CO2 concentration is collectively referred to as CO2 concentration here. In this test, when the p-value is less than 0.05, it indicates that the data is stable and can be directly modeled; if the test result finds that the p-value of the CO2 concentration is greater than 0.05, it means that the data has a trend and needs to be differentiated. Through differentiation, the trend of the data will be removed, making it stable and suitable for modeling the ARIMA model. Differentiation is a conventional technique here and will not be described in detail.

[0089] It should be noted that the parameter selection of the ARIMA model is a crucial step, which involves how to determine the autoregressive order (p), difference order (d) and moving average order (q) in the model. The selection of these three parameters directly affects the prediction effect of the model, ensuring that the model can accurately capture the law of carbon dioxide concentration changes over time. The future carbon dioxide concentration prediction module will first perform autocorrelation analysis and select the best model parameters. Here, the autocorrelation function (ACF) and partial autocorrelation function (PACF) graphs are used as analysis tools to help determine the order of autoregression and moving average. By analyzing the autocorrelation of the data, the future carbon dioxide concentration prediction module can determine the degree of influence of historical data on the current value, thereby determining the autoregressive order (p) and moving average order (q). The future carbon dioxide concentration prediction module automatically selects the most appropriate combination of p, d, and q by analyzing the ACF and PACF graphs of historical data. For example, the analysis results show that ARIMA (1,1,1) is the most suitable model parameter for the current data, which means that the future carbon dioxide concentration prediction module selects one lagged autoregressive term (p=1), performs one difference on the data (d=1) to ensure stationarity, and one lagged moving average term (q=1) to handle the error term. According to the selected ARIMA (1,1,1) model, the future carbon dioxide concentration prediction module uses the historical weighted carbon dioxide concentration data (such as data from 10:00 to 14:00) to train the ARIMA model. By minimizing the error function, the coefficients of the model (i.e., the weights of the AR and MA terms) are fitted. After the training is completed, the future carbon dioxide concentration prediction module can predict the future carbon dioxide concentration based on the model. Suppose we need to predict the carbon dioxide concentration in the next two hours (15:00 and 16:00). The future carbon dioxide concentration prediction module is extrapolated according to the ARIMA model and obtains the following prediction results:

[0090] Predicted CO2 concentration at 15:00: about 450 ppm

[0091] Predicted carbon dioxide concentration at 16:00: about 475ppm

[0092] Predicted carbon dioxide concentration at 17:00: about 500ppm

[0093] Predicted carbon dioxide concentration at 18:00: about 550 ppm

[0094] Predicted carbon dioxide concentration at 19:00: about 535ppm

[0095] Predicted carbon dioxide concentration at 20:00: about 650 ppm

[0096] After the future CO2 concentration prediction module completes the prediction, a chart will be drawn to show the actual CO2 concentration from 10:00 to 14:00 and the predicted value from 15:00 to 20:00. The safety threshold will also be marked in the chart, and when the predicted CO2 concentration exceeds the threshold, the future CO2 concentration prediction module will highlight these predicted data points and issue an alarm. For example, the predicted CO2 concentration at 15:00 is 450ppm, which exceeds the safety threshold of 400ppm. The future CO2 concentration prediction module will mark the point in red and prompt "Exceeding the safety threshold, measures must be taken." Users can view the historical data and predicted data of CO2 concentration through the visual interface. At the same time, based on the predicted carbon dioxide concentration, the future carbon dioxide concentration prediction module will provide specific operational suggestions: if the carbon dioxide concentration continues to exceed 400ppm in the next few hours, the future carbon dioxide concentration prediction module will suggest users to turn on or enhance ventilation equipment to reduce the carbon dioxide concentration; if the carbon dioxide concentration rises rapidly and the composting temperature is high, the future carbon dioxide concentration prediction module may suggest users to lower the composting temperature to reduce carbon dioxide generation; if the future carbon dioxide concentration prediction module is connected to the composting equipment, it will automatically adjust the equipment settings according to the predicted carbon dioxide concentration to help users respond to changes in carbon dioxide concentration in a timely manner.

[0097] The present invention also relates to an intelligent detection and analysis method for carbon dioxide in a composting process;

[0098] The specific process is as follows:

[0099] Step 1: Determine the geospatial dimensions of the compost pile, i.e., stratify the compost pile from top to bottom.

[0100] Step 2: Determine the real-time temperature and carbon-nitrogen ratio of each layer of the compost pile.

[0101] Step 3: Confirm the carbon dioxide concentration of the corresponding layer through the real-time temperature and carbon-nitrogen ratio data of each layer, and use the time series model to predict the future carbon dioxide concentration.

[0102] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0103] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent carbon dioxide detection system for composting process, characterized in that: It includes real-time data detection module, data analysis module, future carbon dioxide concentration prediction module and data storage module, and signal connections between the modules; The real-time data detection module is used to obtain the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer of the compost pile, and send the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer to the data analysis module; After receiving the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, the data analysis module determines the weight coefficients of the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, and performs weighted calculation of the real-time representative carbon dioxide concentration of the compost pile according to the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, and sends the real-time representative carbon dioxide concentration of the compost pile to the future carbon dioxide concentration prediction module; After receiving the real-time representative carbon dioxide concentration of the compost pile, the future carbon dioxide concentration prediction module uses a time series model to predict the future carbon dioxide concentration; The data storage module is used to store all data during the platform processing process.

2. The intelligent carbon dioxide detection system for composting process according to claim 1, characterized in that: The real-time data detection module divides the compost pile into several layers from top to bottom, and then monitors each layer's partition separately in real time for its temperature, carbon-nitrogen ratio and carbon dioxide concentration.

3. The intelligent carbon dioxide detection system for composting process according to claim 2, characterized in that: The data analysis module determines the real-time temperature and carbon-nitrogen ratio of each layer area and the weight coefficient of carbon dioxide concentration, including the following steps; After receiving the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer, the data analysis module calculates the weight of the real-time temperature and carbon-nitrogen ratio of each layer; The weight coefficient of the real-time carbon dioxide concentration of each layer is calculated according to the normalized weight of the real-time temperature and carbon-nitrogen ratio of each layer, and the weight value of the real-time carbon dioxide concentration of each layer is determined by assigning weights to the implemented carbon dioxide weight coefficients of each layer according to the priority diagram method; The real-time carbon dioxide concentration of each layer is weighted and calculated according to the weight value of the real-time carbon dioxide concentration of each layer to obtain the real-time carbon dioxide concentration representative of the compost pile.

4. The intelligent carbon dioxide detection system for composting process according to claim 1, characterized in that: The future carbon dioxide concentration prediction module uses a time series model to predict future carbon dioxide concentrations, including the following steps: After receiving the representative real-time carbon dioxide concentration of the compost pile, the future carbon dioxide concentration prediction module defines the representative real-time carbon dioxide concentration of the compost pile as an input variable and substitutes it into the time series model; the representative real-time carbon dioxide concentration is simulated and trained using the time series model to predict the future carbon dioxide concentration.

5. A method for intelligent detection and analysis of carbon dioxide in a composting process, based on an intelligent detection system for carbon dioxide in a composting process according to any one of claims 1 to 4, characterized in that: The steps include: Divide the compost pile into several layers from top to bottom, and obtain the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration of each layer of the compost pile; Determine the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration weight coefficient of each layer, and calculate the real-time representative carbon dioxide concentration of the compost pile based on the real-time temperature, carbon-nitrogen ratio and carbon dioxide concentration weight coefficient of each layer; use a time series model to predict the future carbon dioxide concentration based on the real-time representative carbon dioxide concentration of the compost pile.

Images