Odor emission reduction control system and method for livestock manure compost

Abstract

The invention relates to the technical field of odor emission reduction, in particular to an odor emission reduction control system and method for livestock and poultry manure compositing. According to the system and the method, concentration changes of ammonia gas, hydrogen sulfide and volatile organic compounds and temperature and humidity data in a composting environment are accurately obtained through real-time performance and multi-parameter association of gas monitoring in the composting process; the method comprises the following steps of: calculating a diffusion path, a speed and a coverage area of gas in a compost body through finite element analysis, quantifying the distribution characteristics of gas concentration in space, optimizing the wind speed, the wind quantity and the layout of a ventilation system, and improving the ventilation efficiency. Pattern recognition is performed on compost environment gas emission data through the convolutional neural network, the turning frequency and the compost microenvironment are dynamically adjusted in combination with the gas concentration, a gas emission high-value area and a main guide source are accurately positioned, accurate control over compost fermentation odor emission is achieved, and the systematicness and refinement level of compost odor treatment is improved.

Description

Technical Field

[0001] The invention relates to the technical field of odor emission reduction, and in particular to an odor emission reduction control system and method for livestock and poultry manure composting. Background Art

[0002] The field of odor reduction technology aims to effectively control and treat odors generated in production, life and waste treatment processes through scientific and systematic methods, reduce the harm of odors to the environment and human health, improve air quality and protect the ecological environment.

[0003] The odor reduction control system for livestock and poultry manure composting aims to reduce the emission concentration of harmful gases such as ammonia, hydrogen sulfide and volatile organic compounds released during the composting fermentation process, reduce pollution to the surrounding environment and the impact on residents' lives, and improve the environmental friendliness and resource utilization of composting treatment. It aims to achieve effective control of odor emissions through scientific odor control methods, protect the ecological environment, and promote the harmless and resource-based treatment of livestock and poultry manure.

[0004] The existing technologies in odor reduction have the problems of single monitoring data, insufficient diffusion path analysis and low emission source positioning accuracy. Odor monitoring is usually limited to single-point data or data collection at specific time nodes, lacks full-cycle dynamic tracking of gas concentration during the composting process, and cannot provide a complete concentration change trend and its correlation with environmental conditions. For the analysis of gas diffusion, the existing technologies mainly rely on empirical judgment or simple mathematical models, and fail to accurately calculate the diffusion path, diffusion rate and coverage of the gas in the compost body, resulting in a lack of scientific basis for the layout and operation adjustment of ventilation equipment. In the identification of odor sources, the existing technologies usually obtain emission hot spots through manual detection or limited monitoring methods, with low accuracy, and it is difficult to clarify the dominant emission area of ​​high-concentration gas and its impact range. These deficiencies make it difficult to quickly eliminate the high local gas concentration during the composting fermentation process, and also limit the optimization space of the ventilation system and compost turning operations, resulting in a lack of refined control measures for composting environmental management, increasing the negative impact on the surrounding environment and reducing the quality and efficiency of compost resource processing. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an odor reduction control system and method for livestock and poultry manure composting.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: A odor reduction control system for livestock and poultry manure composting comprises: Gas monitoring module: equipped with precise gas sensors to record the concentrations of ammonia, hydrogen sulfide and volatile organic compounds in the compost in real time, monitor temperature and humidity at the same time, and convert the measured data into digital format to obtain primary gas data; Gas dynamic analysis module: uses time series analysis to process the primary gas data, determines the periodicity and abnormal points of gas concentration changes, identifies key change nodes through trend analysis, and generates a dynamic gas model; Gas diffusion control module: Based on the dynamic gas model, the finite element analysis method is used to analyze the diffusion path and rate of gas in the compost body, adjust the layout and operation parameters of the ventilation system, optimize the gas distribution through aerodynamic simulation, and generate a gas control strategy; Operation parameter adjustment module: Based on the gas control strategy, the turning frequency and ventilation conditions of the composting environment are adjusted according to real-time monitoring data, and the microenvironment of the compost body is dynamically adjusted according to the gas concentration to generate optimized operation parameters; Odor source location module: Based on the optimized operating parameters, a convolutional neural network is used to locate the specific areas of gas emission peaks, including specific areas in the fermentation stage, and the dominant source of odor emission is confirmed through pattern recognition to generate odor source analysis results; Odor reduction strategy module: Based on the odor source analysis results, the stack structure adjustment plan and ventilation improvement measures are designed to reduce the emission of high-concentration gases through air flow optimization, implement specific gas management operations, and generate an odor reduction implementation plan.

[0007] As a further solution of the present invention, the gas monitoring module includes a sensor data acquisition submodule, a gas data conversion submodule and an environmental data integration submodule, wherein: Sensor data acquisition submodule: Based on the configured precise gas sensors, it conducts real-time concentration monitoring of ammonia, hydrogen sulfide and volatile organic compounds. By recording the gas concentration signal output by the sensor and synchronously collecting temperature and humidity data, it completes the acquisition and storage of multiple data at preset time intervals to generate a collection of gas and environmental sensor data. Gas data conversion submodule: based on the gas and environmental sensor data set, performs digital conversion of gas concentration and environmental data, performs signal decoding and quantization processing on the collected data, performs consistency correction on the data range, calibrates concentration unit conversion and temperature and humidity, and obtains standardized gas and environmental data; Environmental data integration submodule: Based on the standardized gas and environmental data, time series integration of ammonia, hydrogen sulfide and volatile organic compound concentration data is performed, and temperature and humidity data are associated with gas concentration data and matched with corresponding time nodes to generate primary gas data.

[0008] As a further solution of the present invention, the gas dynamic analysis module includes a data time series processing submodule, a key node identification submodule and a dynamic gas modeling submodule, wherein: Data time series processing submodule: based on the primary gas data, perform time series segmentation of gas concentration and environmental data, perform data smoothing and detect abnormal concentration values ​​through data sorting and segmentation identification, complete periodic change extraction and abnormal point location of gas concentration and environmental data, and generate a set of gas concentration cycles and abnormal points; Key node identification submodule: Based on the gas concentration cycle and abnormal point set, the concentration change trend calculation and slope analysis are performed, the key nodes are located by segmenting the nodes in the periodic change and calculating the change amplitude and direction, the periodic feature points are screened and classified, and the key change node feature set is obtained; Dynamic gas modeling submodule: Based on the key change node feature set, mathematical modeling of the dynamic change of gas concentration is performed. By integrating the key node features and periodic change data and fitting the concentration curve, the gas dynamic model is generated and verified to generate a dynamic gas model.

[0009] As a further solution of the present invention, the gas diffusion control module includes a diffusion path analysis submodule, a ventilation parameter optimization submodule and a gas distribution simulation submodule, wherein: Diffusion path analysis submodule: Based on the dynamic gas model, the gas diffusion path in the compost is analyzed, data is collected on the gas diffusion area and the concentration distribution is analyzed, the diffusion rate is determined in combination with the concentration change data, and a gas concentration distribution map within the diffusion range is drawn. The spatial delineation and path marking of the gas diffusion range are completed, and gas diffusion characteristic data is generated; Ventilation parameter optimization submodule: Based on the gas diffusion characteristic data, the ventilation system layout and parameters are optimized. The vent positions are readjusted by analyzing the influence of the vent positions and airflow directions on the diffusion paths. The ventilation volume is set in combination with the gas diffusion rate data and the rationality of the airflow direction is verified. The ventilation conditions are optimized and a ventilation system optimization plan is established. Gas distribution simulation submodule: Based on the ventilation system optimization scheme, the finite element analysis method is used to simulate the diffusion and distribution of gas in the compost body, and the airflow model is adjusted. The gas concentration distribution diagram is re-evaluated and the parameter configuration is optimized based on the simulation results to generate a gas control strategy.

[0010] As a further solution of the present invention, the finite element analysis method is according to the formula: in: Indicates that the compost odor is at a certain location in the compost body and time The three-dimensional concentration distribution of Indicates the odor release rate, represents the environmental correction factor, represents the permeability coefficient of compost material, represents the diffusion coefficient, represents the three-dimensional spatial coordinates within the compost body, represents the diffusion time, Represents the velocity components of airflow in each direction in three-dimensional space.

[0011] As a further solution of the present invention, the operating parameter adjustment module includes a real-time monitoring and analysis submodule, a compost turning frequency adjustment submodule and a microenvironment adjustment submodule, wherein: Real-time monitoring and analysis submodule: Based on the gas control strategy, it monitors and analyzes the real-time gas concentration and environmental data, collects monitoring data to analyze the dynamic change trend of temperature, humidity and gas concentration in the stack, and processes and corrects the correlation between gas concentration change and ventilation conditions in combination with sensor collection data to obtain real-time monitoring and control data sets; Compost turning frequency adjustment submodule: based on the real-time monitoring and control data set, adjust the compost turning frequency, analyze the gas concentration change rate in the real-time data and the gas distribution data in the time series, adjust the compost turning interval time in combination with the compost turning operation record and record the new setting, and generate the compost turning frequency adjustment result; Microenvironment adjustment submodule: Based on the compost turning frequency adjustment result, the ventilation parameters in the composting area are adjusted to achieve gas concentration balance, and the microenvironment conditions in the composting area are optimized in combination with the humidity adjustment data to generate optimized operating parameters.

[0012] As a further solution of the present invention, the odor source positioning module includes a regional emission monitoring submodule, a dominant source identification submodule and an odor characteristic analysis submodule, wherein: Regional emission monitoring submodule: Based on the optimized operating parameters, the concentration data of ammonia, hydrogen sulfide and volatile organic compounds in the composting fermentation area are collected through a convolutional neural network, the emission concentration changes are recorded in combination with time nodes and the emission peak periods are divided, the concentration change data in different areas of the pile are spatially analyzed, and the classification and range of the emission area are calibrated to generate emission peak area data; The dominant source identification submodule: based on the emission peak area data, analyze the dominant odor source in the composting area, calculate the concentration ratio of each component by classifying the gas component concentration collected in the emission area, compare the component ratios in different areas to confirm the dominant emission gas type, locate the high emission point in the area by the concentration difference, identify the odor dominant source area by combining the component concentration in the area with the distribution characteristics of the high emission point, and generate the dominant odor source data; Odor characteristic analysis submodule: Based on the dominant odor source data, odor emission patterns and characteristics are extracted, and the temporal distribution characteristics of the emission area are extracted by analyzing the composition change law of the dominant odor source area and combining the odor diffusion trajectory in the fermentation stage. The regional emission pattern is established in combination with the composition change characteristics and the spatial distribution characteristics corresponding to each pattern are marked. The pattern feature annotation of the dominant odor source is completed to generate the odor source analysis result.

[0013] As a further solution of the present invention, the convolutional neural network is according to the formula: in: Nodes in the composting area In time The pollutant concentration, For monitoring point The weight coefficient of For monitoring point In time The actual measured pollutant concentration, For Node and monitoring points The spatial distance is the distance attenuation coefficient and the original formula similar, is the environment correction function, is the fermentation intensity, is the temperature, For humidity, is the total number of monitoring points.

[0014] As a further solution of the present invention, the odor reduction strategy module includes a structure optimization adjustment submodule, a ventilation condition improvement submodule and a gas management execution submodule, wherein: Structural optimization and adjustment submodule: According to the odor source analysis results, the compost pile structure is optimized and adjusted, the discharge path of the high-emission area of ​​the compost body is analyzed and the pile level is rearranged in combination with the regional characteristics, the air flow channel in the high-emission area is optimized to a short-distance discharge path, and gas diffusion control holes are arranged in the discharge path to complete the optimization adjustment of the pile structure, and generate pile structure optimization data; Ventilation condition improvement submodule: Based on the stack structure optimization data, the ventilation conditions in the high emission area are adjusted, the area and spacing of the vents in the high emission area are reset by combining the optimization data, the operation frequency and airflow direction of the ventilation equipment are adjusted, and the optimization condition configuration is completed by increasing and decreasing the ventilation channel pressure to match the gas concentration change, and a ventilation condition improvement plan is generated; Gas management execution submodule: Based on the ventilation condition improvement plan, dynamic emission management operations of composting odor are carried out, and the gas concentration in high emission areas is adjusted in real time in combination with the ventilation condition improvement plan, and the gas in the emission peak area is collected and drained. The regional emission dynamics are adjusted by real-time control of the ventilation equipment operating parameters, and the gas collection and emission coordination are completed to generate an odor reduction implementation plan.

[0015] A method for reducing odor emissions from livestock and poultry manure composting is provided. The method for reducing odor emissions from livestock and poultry manure composting is implemented based on the above-mentioned odor emission reduction control system for livestock and poultry manure composting, and comprises the following steps: Step 1: Send the compost material into the fermentation area, insert a gas sensor into the compost body, monitor the concentration of ammonia, hydrogen sulfide and volatile organic compounds, and record the temperature and humidity values ​​of the composting area. Collect and digitize the concentration value and environmental data at each time node in turn to generate primary gas data; Step 2: Based on the primary gas data, arrange the gas concentration in chronological order, calculate the concentration change rate of each set of data, mark the concentration sudden increase point and periodic change interval, integrate the change results according to the time node, and generate a dynamic gas model; Step 3: combining the dynamic gas model with the ventilation airflow path of the composting area, calculating the gas diffusion path length and diffusion rate, and generating a composting gas diffusion path distribution characteristic table through correlation analysis between concentration value and path position; Step 4: Based on the composting gas diffusion path distribution characteristic table, the ventilation parameters of the composting area are adjusted, including wind speed value, ventilation duct layout and airflow distribution state, the operation mode of the existing ventilation system is optimized, and a gas control strategy is generated; Step 5: Based on the gas control strategy, combined with the compost turning frequency, temperature and humidity data in the composting area, the dynamic distribution of compost gas concentration is analyzed, high-value points of odor concentration are marked, and the emission peak area is located to generate a distribution map of high-value points of compost odor emission; Step 6: Based on the distribution map of high-value points of composting odor emission, by adjusting the pile height, pile structure and airflow direction of the exhaust channel in the composting area, the ventilation conditions in the composting area are optimized, the gas distribution and emission path are dynamically controlled, and an odor reduction implementation plan is generated.

[0016] As a further solution of the present invention, multi-layer distributed gas sensors are added in the compost body, and the distribution positions are specifically the upper part, middle part and lower part of the compost body, so as to ensure that the monitored concentration data fully covers the compost gas diffusion process; The optimization of ventilation parameters specifically includes setting the ventilation time to 15 to 20 minutes per hour and the wind speed range to 1 to 1.5 meters per second, ensuring uniform airflow distribution in high-value areas while reducing ventilation operating costs; The rate of change of the sudden increase point of gas concentration in the dynamic gas model is calculated by dividing the concentration change value by the time interval, which shall not exceed five minutes; The pile height is adjusted to 1.2 to 1.8 meters to control the gas concentration distribution and reduce the odor emission concentration; When the monitoring results show that the diffusion path length is long, the stack density is increased to inhibit gas diffusion.

[0017] As a further solution of the present invention, the composting area is divided into a fermentation area and a maturation area, ventilation control is strengthened in the fermentation area, and ventilation volume is reduced in the maturation area, and the ventilation volume ratio is set to three to one; Set up multiple parallel exhaust channels, with the distance between each channel not less than two meters and the channel diameter ranging from 15 cm to 25 cm, to quickly exhaust composting gas and reduce gas concentration; Add odor adsorbing materials, including biochar and zeolite, to the high-value areas, with the specific amount added being 5 to 8 percent of the total weight of the compost material; During peak odor concentration periods, the ventilation frequency, wind speed and pile turning interval are automatically adjusted in combination with real-time monitoring data, and a real-time feedback control mechanism is established.

[0018] Compared with the prior art, the advantages and positive effects of the present invention are: 1. In the present invention, by real-time gas monitoring and multi-parameter correlation during the composting process, the concentration changes of ammonia, hydrogen sulfide and volatile organic compounds and the temperature and humidity data in the composting environment are accurately obtained and digitally processed, providing high-precision basic data for subsequent analysis; 2. In the present invention, the diffusion path, rate and coverage area of ​​gas in the compost body are calculated by finite element analysis, the distribution characteristics of gas concentration in space are quantified, the wind speed, air volume and layout of the ventilation system are optimized, the air flow in the composting area is made more uniform, and the local accumulation and diffusion range of high-concentration gas are reduced; 3. In the present invention, convolutional neural networks are used to perform pattern recognition on the gas emission data of the composting environment, and the frequency of turning the compost and the microenvironment of the compost body are dynamically adjusted in combination with the gas concentration, so as to accurately locate the high-value areas and dominant sources of gas emissions, realize the precise control of the odor emission of composting fermentation, and improve the systematic and refined level of composting odor treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a system flow chart of the present invention; Figure 2 It is a schematic diagram of the system framework of the present invention; Figure 3 It is a schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0021] See also Figure 1 The present invention provides a technical solution: an odor reduction control system for livestock and poultry manure composting includes: Gas monitoring module: equipped with precise gas sensors to record the concentrations of ammonia, hydrogen sulfide and volatile organic compounds in the compost in real time, monitor temperature and humidity at the same time, and convert the measured data into digital format to obtain primary gas data; Gas dynamic analysis module: Use time series analysis to process primary gas data, determine the periodicity and abnormal points of gas concentration changes, identify key change nodes through trend analysis, and generate a dynamic gas model; Gas diffusion control module: Based on the dynamic gas model, the finite element analysis method is used to analyze the diffusion path and rate of gas in the compost body, adjust the layout and operating parameters of the ventilation system, optimize the gas distribution through aerodynamic simulation, and generate a gas control strategy; Operation parameter adjustment module: Based on the gas control strategy, the turning frequency and ventilation conditions of the composting environment are adjusted according to real-time monitoring data, and the microenvironment of the compost body is dynamically adjusted according to the gas concentration to generate optimized operation parameters; Odor source location module: Based on the optimization of operating parameters, a convolutional neural network is used to locate the specific areas of gas emission peaks, including specific areas in the fermentation stage. The dominant source of odor emissions is confirmed through pattern recognition to generate odor source analysis results; Odor reduction strategy module: Based on the results of odor source analysis, design stack structure adjustment plans and ventilation improvement measures, reduce the emission of high-concentration gases through air flow optimization, implement specific gas management operations, and generate odor reduction implementation plans.

[0022] See also Figure 2 The gas monitoring module includes a sensor data acquisition submodule, a gas data conversion submodule and an environmental data integration submodule, among which: Sensor data acquisition submodule: Based on the configured precise gas sensors, it conducts real-time concentration monitoring of ammonia, hydrogen sulfide and volatile organic compounds. By recording the gas concentration signal output by the sensor and synchronously collecting temperature and humidity data, it completes the acquisition and storage of multiple data at preset time intervals to generate a collection of gas and environmental sensor data. Gas data conversion submodule: Based on the gas and environmental sensor data set, it performs digital conversion of gas concentration and environmental data, performs signal decoding and quantification processing on the collected data, performs consistency correction on the data range, calibrates the concentration unit conversion and temperature and humidity, and obtains standardized gas and environmental data; Environmental data integration submodule: Based on standardized gas and environmental data, it integrates the time series of ammonia, hydrogen sulfide and volatile organic compound concentration data, associates temperature and humidity data with gas concentration data and matches corresponding time nodes to generate primary gas data; Sensor data acquisition submodule: Based on the configured precise gas sensor, the gas electrochemical detection method is adopted to measure the real-time concentration of ammonia, hydrogen sulfide and volatile organic compounds through the voltage signal of the gas detection unit. The electrode potential in the electrochemical detection unit is set to 0.7 volts to 1.0 volts, and the signal response time is set to 100 milliseconds. The current signal collected by the sensor is combined with the temperature compensation coefficient to complete the gas concentration signal output. At the same time, the digital temperature and humidity sensor is used to synchronously obtain the temperature and humidity data in the composting environment. The acquisition frequency is set to once per second, and all sensor data are acquired and stored at the preset time interval to generate a gas and environmental sensor data set; Gas data conversion submodule: Based on the gas and environmental sensor data set, the signal decoding and quantization processing methods are used to digitally convert the gas concentration and environmental data. The linear interpolation method is used to fill the missing data for the gas concentration signal. The least squares method is used to fit the signal value output by the sensor to the calibration curve. After fitting, the signal is corrected and the concentration unit is unified to ppm. At the same time, the dimensional consistency correction method is used for the temperature and humidity data to unify the temperature to degrees Celsius and the humidity unit to the relative humidity percentage, and finally generate standardized gas and environmental data; Environmental data integration submodule: Based on standardized gas and environmental data, the time series data integration method is used to sort the gas concentration data in sequence according to the time nodes, and the concentration data of ammonia, hydrogen sulfide and volatile organic compounds are interpolated according to the time interval. The concentration change rate is calculated by the first-order difference method and inserted into the corresponding time node. The temperature and humidity data are matched and associated with the corresponding gas concentration through the dynamic window allocation method. The window time interval is set to 10 minutes, and the temperature and humidity data are mapped to the gas concentration time series to form a complete time series data table and generate primary gas data.

[0023] See also Figure 2 The gas dynamic analysis module includes a data time series processing submodule, a key node identification submodule and a dynamic gas modeling submodule, among which: Data time series processing submodule: Based on primary gas data, perform time series segmentation of gas concentration and environmental data, perform data smoothing and detect abnormal concentration values ​​through data sorting and segment identification, complete periodic change extraction and abnormal point location of gas concentration and environmental data, and generate gas concentration period and abnormal point set; Key node identification submodule: Based on the gas concentration cycle and abnormal point set, the concentration change trend calculation and slope analysis are performed. The key nodes are located by segmenting the nodes in the cycle change and calculating the change amplitude and direction. The cycle feature points are screened and classified to obtain the key change node feature set. Dynamic gas modeling submodule: Based on the key change node feature set, mathematical modeling of the dynamic change of gas concentration is performed. By integrating the key node features and periodic change data and fitting the concentration curve, the gas dynamic model is generated and verified to generate a dynamic gas model; Data time series processing submodule: Based on primary gas data, the sliding average algorithm is used to segment the gas concentration data and environmental data into time series. The sliding window size is set to 10 minutes and the sliding window is slid every 5 minutes. The segmented data is sorted in chronological order. The sequence data is smoothed by calculating the mean of each segment of data. At the same time, the interquartile range method is used to detect abnormal concentration values. The difference between the first quartile and the third quartile in the data distribution is calculated. The anomaly detection threshold is set to 1.5 times the IQR. The abnormal data is marked and eliminated by comparing the deviation between each data item and the threshold. The periodic change extraction and abnormal point location of gas concentration and environmental data are completed, and the gas concentration period and abnormal point set are generated; Key node identification submodule: Based on the gas concentration cycle and the set of abnormal points, the local least squares regression method is used to calculate the trend of the time series data of the concentration change, the trend line is fitted to the data points in the time window and the slope is calculated, and the data points with alternating positive and negative slope changes are screened according to the set threshold. The nodes in the periodic change are segmented, and the numerical difference is calculated for each segment using the change amplitude calculation formula. The maximum change amplitude and direction in the segment are marked, and all nodes are summarized and screened. The periodic feature points are classified according to the change amplitude and direction to generate a key change node feature set; Dynamic gas modeling submodule: Based on the key change node feature set, the polynomial fitting method is used to mathematically model the dynamic changes of gas concentration. The least squares method is used to fit the time series data. The fitting order is set to third order. The key node features are used as the control points for fitting. At the same time, the periodic change data are interpolated in chronological order. The Lagrange interpolation method is used to generate a concentration curve by calculating the weights of the interpolation points and the control points. The fitted curve is compared with the actual concentration data to calculate the error range. The error standard is set to 2% of the concentration value fluctuation range. Finally, the adjustment and verification of the fitted curve is completed to generate a dynamic gas model.

[0024] See also Figure 2 The gas diffusion control module includes a diffusion path analysis submodule, a ventilation parameter optimization submodule and a gas distribution simulation submodule, among which: Diffusion path analysis submodule: Based on the dynamic gas model, the gas diffusion path in the compost is analyzed. By collecting data on the gas diffusion area and analyzing the concentration distribution, the diffusion rate is determined in combination with the concentration change data, and the gas concentration distribution map within the diffusion range is drawn. The spatial delineation and path marking of the gas diffusion range are completed, and the gas diffusion characteristic data is generated; Ventilation parameter optimization submodule: Based on the gas diffusion characteristic data, the ventilation system layout and parameters are optimized. The vent positions are readjusted by analyzing the influence of the vent positions and airflow direction on the diffusion path. The ventilation volume is set in combination with the gas diffusion rate data and the rationality of the airflow direction is verified. The ventilation conditions are optimized and a ventilation system optimization plan is established. Gas distribution simulation submodule: Based on the ventilation system optimization scheme, the finite element analysis method is used to simulate the diffusion and distribution of gas in the compost body, and the airflow model is adjusted. The gas concentration distribution diagram is re-evaluated and the parameter configuration is optimized based on the simulation results to generate a gas control strategy; Diffusion path analysis submodule: Based on the dynamic gas model, the diffusion equation analytical method is used to analyze the gas diffusion path in the compost body. The concentration data collected by the sensor in the compost body is gridded according to the spatial coordinates, and the compost body is divided into equally spaced grid units. The gas concentration change rate of each unit is calculated using Fick's diffusion law. The gas concentration gradient in the diffusion area is analyzed and the diffusion rate is calculated in combination with the time step. The time step is set to 1 minute to capture the dynamic changes of gas diffusion. The concentration gradient in different areas is interpolated and the gas concentration distribution map within the diffusion range is drawn. The spatial concentration distribution is divided by threshold, the gas concentration diffusion path and boundary range are marked, and the gas diffusion characteristic data is generated; Ventilation parameter optimization submodule: Based on the gas diffusion characteristic data, the ventilation system simulation analysis method is used to optimize the layout and parameters of the vents. By analyzing the influence of the vent position and airflow direction on the gas diffusion path, the spatial coordinates of the existing vents are adjusted, and the minimum distance between the vents and the diffusion boundary is set to 0.5 meters. At the same time, the airflow direction is adjusted according to the center line direction of the diffusion path. The deflection range does not exceed 10 degrees. The ventilation volume is calculated in combination with the diffusion rate. The ventilation volume parameter is set as the volume of the diffusion area multiplied by the number of ventilation changes. The relationship between the airflow direction and the concentration distribution is simulated to verify the rationality of the existing ventilation volume and direction settings, optimize the ventilation conditions, and establish a ventilation system optimization plan; Gas distribution simulation submodule: Based on the ventilation system optimization plan, the finite element analysis method is used to simulate the gas diffusion and distribution in the compost body. The compost body space is divided into finite grid units, and the gas concentration is input into the simulation model as a node variable. The continuity equation is used to calculate the diffusion speed and diffusion amount of the gas within the time step. The time step is set to 1 minute and the space step is set to 0.1 meters. The diffusion path and concentration distribution of the simulated gas are iteratively updated, the simulated airflow model is adjusted, the airflow direction is fitted and analyzed with the compost gas diffusion boundary, and the gas concentration distribution map is redrawn in combination with the simulation results. The parameter configuration of the ventilation system is further optimized to generate a gas control strategy.

[0025] See also Figure 2 , finite element analysis method, according to the formula: in: Indicates that the compost odor is at a certain location in the compost body and time The three-dimensional concentration distribution of Indicates the odor release rate, represents the environmental correction factor, represents the permeability coefficient of compost material, represents the diffusion coefficient, Represents the three-dimensional spatial coordinates within the compost body, represents the diffusion time, Represents the velocity components of airflow in each direction in three-dimensional space; Implementation process: First, according to the odor generation rate during composting , combined with the internal environmental conditions of the compost body to determine the diffusion coefficient and environmental correction factor , calculate the velocity components of the airflow in the three-dimensional direction of the compost body through the ventilation system optimization scheme and the permeability coefficient of the compost material , then the compost body is modeled as a three-dimensional space and its coordinates are discretized , and based on the diffusion time The distribution process of odor diffusion inside the compost is simulated, and finally the formula is discretized and solved iteratively to generate the odor concentration distribution map inside the compost. The ventilation system configuration and composting parameters are optimized based on the simulation results, and the odor reduction regulation strategy is generated to achieve precise control of compost odor and emission reduction.

[0026] See also Figure 2 The operating parameter adjustment module includes a real-time monitoring and analysis submodule, a compost turning frequency adjustment submodule and a microenvironment adjustment submodule, wherein: Real-time monitoring and analysis submodule: Based on the gas control strategy, it monitors and analyzes the real-time gas concentration and environmental data, collects monitoring data to analyze the dynamic change trend of temperature, humidity and gas concentration in the pile, and processes and corrects the correlation between gas concentration changes and ventilation conditions in combination with sensor data to obtain real-time monitoring and control data sets; Compost turning frequency adjustment submodule: Based on the real-time monitoring and control data set, adjust the compost turning frequency, analyze the gas concentration change rate in the real-time data and the gas distribution data in the time series, adjust the compost turning interval time and record the new settings in combination with the compost turning operation records, and generate the compost turning frequency adjustment results; Microenvironment adjustment submodule: Based on the adjustment results of compost turning frequency, the ventilation parameters in the composting area are adjusted to achieve gas concentration balance, and the microenvironment conditions in the composting area are optimized in combination with humidity adjustment data to generate optimized operating parameters; Real-time monitoring and analysis submodule: Based on the gas control strategy, a dynamic data collection method is used to monitor the gas concentration and environmental data in the composting area in real time. The concentration data of ammonia, hydrogen sulfide and volatile organic compounds are collected through the sensor array. The sampling frequency is set to once per minute. The temperature and humidity data are collected synchronously. The collected data are pre-processed by the dynamic weighted average algorithm. The weighting coefficient is set to 0.7 for concentration data and 0.3 for temperature and humidity data. The smoothing of multi-parameter data in the time series is completed. At the same time, the Pearson correlation analysis method is used to process the correlation between gas concentration changes and ventilation conditions. The correlation threshold is set to 0.5, and the deviation value in the correlation data is corrected to generate a real-time monitoring and control data set; Compost turning frequency adjustment submodule: Based on the real-time monitoring and control data set, the trend decomposition algorithm is used to calculate the gas concentration change rate. The time series window size is set to 1 hour, and the concentration change value in the sequence is decomposed into long-term trends, periodic components and random fluctuations. The amplitude of the periodic component change is fitted with the compost turning interval time, and the compost turning interval time is recalculated in combination with the historical compost turning operation records. The compost turning time is controlled within the range of 30 to 60 minutes. At the same time, the adjustment results are recorded, and the compost turning time point is associated with the concentration change trend to generate the compost turning frequency adjustment result; Microenvironment adjustment submodule: Based on the adjustment results of the compost turning frequency, a multi-objective optimization algorithm is used to dynamically adjust the ventilation parameters in the composting area. The wind speed, air volume and ventilation time of the ventilation system are used as optimization variables. The ventilation wind speed is set to 0.5 to 2.0 m / s, the ventilation volume is set to 5% to 10% of the regional volume, and the ventilation time is set to 10 minutes. The particle swarm optimization algorithm is used to search for the optimal combination of ventilation parameters, and the humidity data is interpolated according to the regional distribution. The humidity is adjusted to the range of 40% to 60%, and the microenvironment conditions are dynamically updated according to the humidity and gas concentration to generate optimized operating parameters.

[0027] See also Figure 2 The odor source location module includes a regional emission monitoring submodule, a dominant source identification submodule, and an odor characteristic analysis submodule, among which: Regional emission monitoring submodule: Based on the optimized operating parameters, the concentration data of ammonia, hydrogen sulfide and volatile organic compounds in the composting fermentation area are collected through convolutional neural networks, the emission concentration changes are recorded in combination with time nodes and the emission peak periods are divided. The concentration change data in different areas of the pile are spatially analyzed, and the classification and range of the emission area are calibrated to generate emission peak area data; Dominant source identification submodule: Based on the data of the emission peak area, the dominant odor source in the composting area is analyzed, the concentration ratio of each component is calculated by classifying the gas component concentrations collected in the emission area, and the dominant emission gas type is confirmed by comparing the component ratios in different areas. The high emission points in the area are located by concentration differences, and the dominant odor source area is identified by combining the component concentrations in the area with the distribution characteristics of the high emission points, and the dominant odor source data is generated; Odor characteristic analysis submodule: Based on the dominant odor source data, odor emission patterns and characteristics are extracted. By analyzing the composition change law of the dominant odor source area and combining the odor diffusion trajectory during the fermentation stage, the time series distribution characteristics of the emission area are extracted. Combined with the composition change characteristics, the regional emission pattern is established and the spatial distribution characteristics corresponding to each pattern are marked. The pattern feature annotation of the dominant odor source is completed to generate the odor source analysis results; Regional emission monitoring submodule: Based on the optimized operating parameters, a convolutional neural network is used to collect and analyze the gas concentration in the composting fermentation area. By building a three-layer convolutional neural network model, the real-time concentration data of ammonia, hydrogen sulfide and volatile organic compounds are used as input. The number of convolution kernels in the first layer is 32, and the convolution kernel size is set to 3×3. The activation function uses ReLU with a step size of 1. The pooling layer uses maximum pooling and a pooling window of 2×2. The collected gas concentration data is feature extracted. The number of convolution kernels in the second layer is 64 and the same settings are used to deeply extract the temporal change characteristics of the data. The last layer is a fully connected layer, which outputs the distribution of concentration values ​​and classification results of time nodes. The emission peak period is divided by comparing the changing trend of gas concentration in different time periods, and the concentration change data in different regions are spatially distributed and analyzed. The classification and scope of the emission area are completed by marking the spatial position, and the emission peak area data is generated; Dominant source identification submodule: Based on the data of the emission peak area, the component concentration classification algorithm is used to analyze the dominant odor sources in the composting area, and the ammonia, hydrogen sulfide and volatile organic compound concentration data collected in the emission area are classified and processed. By calculating the concentration ratio of each component, the threshold range is set using the component concentration classification method. Ammonia is set to 30% to 60%, hydrogen sulfide is set to 10% to 30%, and volatile organic compounds are set to 20% to 50%. The component ratio data in different areas are compared to confirm the type of dominant emission gas. The concentration difference calculation method is used to determine the specific location of the high emission point by comparing the gas concentration difference. The distribution data of the high emission point is combined with the regional component concentration for analysis to complete the identification of the odor dominant source area and generate the dominant odor source data; Odor characteristic analysis submodule: Based on the dominant odor source data, the time series distribution characteristic extraction algorithm is used to extract the odor emission pattern and characteristics. By performing time series analysis on the gas composition of the dominant odor source area, the odor concentration data of the fermentation stage is divided into multiple time windows, and the window size is set to 1 hour. The variance value of the component change within the window is calculated to extract the component change law, and the change direction of the odor diffusion trajectory is annotated in combination with the diffusion path data of the fermentation stage. The emission concentration in the area is clustered according to the time period, and the characteristic points of the clustering results are fitted to generate the time series distribution characteristics of the emission area. The regional patterns of different emission stages are classified and labeled in combination with the component change trend, and the pattern feature labeling of the dominant odor source is completed to generate the odor source analysis results.

[0028] See also Figure 2 , convolutional neural network, according to the formula: in: Nodes in the composting area In time The pollutant concentration, For monitoring point The weight coefficient of For monitoring point In time The actual measured pollutant concentration, For Node and monitoring points The spatial distance is the distance attenuation coefficient and the original formula similar, is the environment correction function, is the fermentation intensity, is the temperature, For humidity, is the total number of monitoring points; Implementation process: First, collect pollutant concentration data at monitoring points in the composting fermentation area , including the actual concentration values ​​of ammonia, hydrogen sulfide and volatile organic compounds, combined with the composting area geometric model to calculate the spatial distance between each monitoring point and the node to be analyzed , the three-dimensional spatial structure of the composting area is decomposed by geometric modeling to determine The specific value of the monitoring equipment is then analyzed for errors, and the weight coefficient is fitted based on the historical data distribution of the equipment. , reflecting the impact of different equipment measurement accuracy on the overall concentration distribution, and then determining the environmental parameters of the composting area, including the monitoring points Fermentation intensity in the region ,temperature and humidity , by fitting the correction function To adjust the impact of environmental factors on the diffusion process of pollutants, the correction function combines the experimental data fitting parameters to ensure that the comprehensive effect of humidity, temperature and fermentation intensity on diffusion is accurately reflected. Finally, all parameters are substituted into the formula to calculate the pollutant concentration of each node in the composting area. , generate pollutant concentration distribution maps of composting areas, calibrate emission peak areas and time periods, and provide a scientific basis for optimizing composting ventilation configuration and formulating odor reduction strategies.

[0029] See also Figure 2 The odor reduction strategy module includes a structure optimization and adjustment submodule, a ventilation condition improvement submodule, and a gas management execution submodule, among which: Structural optimization and adjustment submodule: According to the results of odor source analysis, the compost pile structure is optimized and adjusted. By analyzing the emission path of the high emission area of ​​the compost body and rearranging the pile level according to the regional characteristics, the air flow channel in the high emission area is optimized to a short-distance emission path, and gas diffusion control holes are arranged in the emission path to complete the optimization adjustment of the pile structure and generate pile structure optimization data; Ventilation condition improvement submodule: Based on the stack structure optimization data, the ventilation conditions in the high-emission area are adjusted. The area and spacing of the vents in the high-emission area are reset by combining the optimization data, the operating frequency and airflow direction of the ventilation equipment are adjusted, and the optimization condition configuration is completed by increasing and decreasing the ventilation channel pressure to match the gas concentration changes, and a ventilation condition improvement plan is generated; Gas management execution submodule: Based on the ventilation condition improvement plan, dynamic emission management operations of composting odor are carried out. By combining the ventilation condition improvement plan, the gas concentration in the high emission area is controlled in real time, and the gas in the emission peak area is collected and drained. The regional emission dynamics are adjusted by real-time control of the ventilation equipment operating parameters, gas collection and emission coordination are completed, and the odor reduction implementation plan is generated; Structural optimization and adjustment submodule: Based on the results of odor source analysis, the short path analysis algorithm is used to analyze the emission path of the high emission area of ​​the compost pile. The gas diffusion path in the high emission area is segmented, and the length of each path is calculated and sorted. The long paths in the high emission area whose path length exceeds 10% of the average value are marked as optimization objects. The pile is divided into a three-layer structure using regional characteristic analysis, and the airflow channel of the middle layer is adjusted to shorten the original airflow path to 70% of the average distance. The local diffusion range of the gas is optimized by arranging diffusion control holes. The diameter of the diffusion control holes is set to 10 cm to 15 cm, and the hole spacing is set to 50 cm. The pile layer adjustment and path shortening operations are completed to generate pile structure optimization data; Ventilation condition improvement submodule: Based on the stack structure optimization data, the pressure distribution analysis method is used to adjust the ventilation conditions in the high-emission area. The area of ​​the vents is set to 20 cm to 30 cm, and the spacing of the vents is dynamically adjusted according to the diffusion concentration gradient in the high-emission area. The vent spacing is set to 1 m to 2 m. The frequency range is set to 5 to 10 times / hour by controlling the operating frequency of the ventilation equipment. The deflection angle of the airflow direction is corrected in combination with the regional pressure change analysis. The deflection angle is set to 5 to 15 degrees. By matching and calculating the gas concentration and pressure distribution data in the high-emission area, the operating parameters of the ventilation channel are dynamically adjusted to complete the optimal configuration of the ventilation conditions and generate a ventilation condition improvement plan. Gas management execution submodule: Based on the ventilation condition improvement plan, a real-time control algorithm is used to manage the dynamic emission of composting odor. By collecting gas concentration data in the peak emission area in real time, the operation mode of the ventilation equipment is adjusted in combination with the parameter configuration of the ventilation condition improvement. The wind speed of the ventilation equipment is set to 0.5 to 2.5 m / s. The opening and closing time of the equipment operation is adjusted in real time according to the gas concentration. The opening and closing time range is set to 10 to 20 minutes each time. The gas concentration distribution is dynamically monitored through the diffusion path drainage holes set in the high emission area. The data with emission concentration exceeding the set threshold is marked as the focus of control, and the parameter adjustment range of the ventilation equipment is narrowed. At the same time, high-concentration gases are discharged in a centralized manner through the drainage path to complete the balance adjustment operation of the gas concentration in the area and generate an odor reduction implementation plan.

[0030] See also Figure 3 A method for reducing odor emissions from livestock and poultry manure composting comprises the following steps: Step 1: Send the compost material into the fermentation area, insert a gas sensor into the compost body, monitor the concentration of ammonia, hydrogen sulfide and volatile organic compounds, and record the temperature and humidity values ​​of the composting area. Collect and digitize the concentration value and environmental data at each time node in turn to generate primary gas data; Step 2: Based on the primary gas data, arrange the gas concentrations in chronological order, calculate the concentration change rate of each set of data, mark the concentration sudden increase points and periodic change intervals, integrate the change results by time nodes, and generate a dynamic gas model; Step 3: Combine the dynamic gas model with the ventilation airflow path of the composting area to calculate the gas diffusion path length and diffusion rate, and generate a composting gas diffusion path distribution characteristic table through correlation analysis between concentration value and path position; Step 4: Based on the composting gas diffusion path distribution characteristic table, adjust the ventilation parameters of the composting area, including wind speed value, ventilation duct layout and airflow distribution state, optimize the operation mode of the existing ventilation system, and generate a gas control strategy; Step 5: Based on the gas control strategy, combined with the compost turning frequency, temperature and humidity data in the composting area, analyze the dynamic distribution of compost gas concentration, mark the high-value points of odor concentration, locate the emission peak area, and generate a distribution map of high-value points of compost odor emission; Step 6: Based on the distribution map of high-value points of composting odor emissions, optimize the ventilation conditions in the composting area by adjusting the pile height, pile structure and airflow direction of the exhaust channel in the composting area, dynamically control the gas distribution and emission path, and generate an odor reduction implementation plan.

[0031] Add multiple layers of gas sensors to the compost body, specifically at the top, middle and bottom of the pile, to ensure that the monitored concentration data fully covers the compost gas diffusion process; The optimization of ventilation parameters specifically includes setting the ventilation time to 15 to 20 minutes per hour and the wind speed range to 1 to 1.5 meters per second, ensuring uniform airflow distribution in high-value areas while reducing ventilation operating costs; The rate of change of the sudden increase point of gas concentration in the dynamic gas model is calculated by dividing the concentration change value by the time interval, which shall not exceed five minutes; The pile height is adjusted to 1.2 to 1.8 meters to control the gas concentration distribution and reduce the odor emission concentration; When the monitoring results show that the diffusion path length is long, the stack density is increased to inhibit gas diffusion.

[0032] The composting area is divided into a fermentation area and a maturation area. The ventilation control is strengthened in the fermentation area and the ventilation volume is reduced in the maturation area. The ventilation volume ratio is set at three to one. Set up multiple parallel exhaust channels, with the distance between each channel not less than two meters and the channel diameter ranging from 15 cm to 25 cm, to quickly exhaust composting gas and reduce gas concentration; Add odor adsorbing materials, including biochar and zeolite, to the high-value areas, with the specific amount added being 5 to 8 percent of the total weight of the compost material; During peak odor concentration periods, the ventilation frequency, wind speed and pile turning interval are automatically adjusted in combination with real-time monitoring data, and a real-time feedback control mechanism is established.

[0033] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A odor reduction control system for livestock and poultry manure composting, characterized in that: The system comprises: Gas monitoring module: equipped with precise gas sensors to record the concentrations of ammonia, hydrogen sulfide and volatile organic compounds in the compost in real time, monitor temperature and humidity at the same time, and convert the measured data into digital format to obtain primary gas data; Gas dynamic analysis module: uses time series analysis to process the primary gas data, determines the periodicity and abnormal points of gas concentration changes, identifies key change nodes through trend analysis, and generates a dynamic gas model; Gas diffusion control module: Based on the dynamic gas model, the finite element analysis method is used to analyze the diffusion path and rate of gas in the compost body, adjust the layout and operation parameters of the ventilation system, optimize the gas distribution through aerodynamic simulation, and generate a gas control strategy; Operation parameter adjustment module: Based on the gas control strategy, the turning frequency and ventilation conditions of the composting environment are adjusted according to real-time monitoring data, and the microenvironment of the compost body is dynamically adjusted according to the gas concentration to generate optimized operation parameters; Odor source location module: Based on the optimized operating parameters, a convolutional neural network is used to locate the specific areas of gas emission peaks, including specific areas in the fermentation stage, and the dominant source of odor emission is confirmed through pattern recognition to generate odor source analysis results; Odor reduction strategy module: Based on the odor source analysis results, the stack structure adjustment plan and ventilation improvement measures are designed to reduce the emission of high-concentration gases through air flow optimization, implement specific gas management operations, and generate an odor reduction implementation plan.

2. The odor reduction control system for livestock and poultry manure composting according to claim 1 is characterized in that: The gas monitoring module includes a sensor data acquisition submodule, a gas data conversion submodule and an environmental data integration submodule, wherein: Sensor data acquisition submodule: Based on the configured precise gas sensors, it conducts real-time concentration monitoring of ammonia, hydrogen sulfide and volatile organic compounds. By recording the gas concentration signal output by the sensor and synchronously collecting temperature and humidity data, it completes the acquisition and storage of multiple data at preset time intervals to generate a collection of gas and environmental sensor data. Gas data conversion submodule: based on the gas and environmental sensor data set, performs digital conversion of gas concentration and environmental data, performs signal decoding and quantization processing on the collected data, performs consistency correction on the data range, calibrates concentration unit conversion and temperature and humidity, and obtains standardized gas and environmental data; Environmental data integration submodule: Based on the standardized gas and environmental data, time series integration of ammonia, hydrogen sulfide and volatile organic compound concentration data is performed, and temperature and humidity data are associated with gas concentration data and matched with corresponding time nodes to generate primary gas data.

3. The odor reduction control system for livestock and poultry manure composting according to claim 1 is characterized in that: The gas dynamic analysis module includes a data time series processing submodule, a key node identification submodule and a dynamic gas modeling submodule, wherein: Data time series processing submodule: based on the primary gas data, perform time series segmentation of gas concentration and environmental data, perform data smoothing and detect abnormal concentration values ​​through data sorting and segmentation identification, complete periodic change extraction and abnormal point location of gas concentration and environmental data, and generate a set of gas concentration cycles and abnormal points; Key node identification submodule: Based on the gas concentration cycle and abnormal point set, the concentration change trend calculation and slope analysis are performed, the key nodes are located by segmenting the nodes in the periodic change and calculating the change amplitude and direction, the periodic feature points are screened and classified, and the key change node feature set is obtained; Dynamic gas modeling submodule: Based on the key change node feature set, mathematical modeling of the dynamic change of gas concentration is performed. By integrating the key node features and periodic change data and fitting the concentration curve, the gas dynamic model is generated and verified to generate a dynamic gas model.

4. The odor reduction control system for livestock and poultry manure composting according to claim 1 is characterized in that: The gas diffusion control module includes a diffusion path analysis submodule, a ventilation parameter optimization submodule and a gas distribution simulation submodule, wherein: Diffusion path analysis submodule: Based on the dynamic gas model, the gas diffusion path in the compost is analyzed, data is collected on the gas diffusion area and the concentration distribution is analyzed, the diffusion rate is determined in combination with the concentration change data, and a gas concentration distribution map within the diffusion range is drawn. The spatial delineation and path marking of the gas diffusion range are completed, and gas diffusion characteristic data is generated; Ventilation parameter optimization submodule: Based on the gas diffusion characteristic data, the ventilation system layout and parameters are optimized. The vent positions are readjusted by analyzing the influence of the vent positions and airflow directions on the diffusion paths. The ventilation volume is set in combination with the gas diffusion rate data and the rationality of the airflow direction is verified. The ventilation conditions are optimized and a ventilation system optimization plan is established. Gas distribution simulation submodule: Based on the ventilation system optimization scheme, the finite element analysis method is used to simulate the diffusion and distribution of gas in the compost body, and the airflow model is adjusted. The gas concentration distribution diagram is re-evaluated and the parameter configuration is optimized based on the simulation results to generate a gas control strategy.

5. The odor reduction control system for livestock and poultry manure composting according to claim 1 is characterized in that: The operating parameter adjustment module includes a real-time monitoring and analysis submodule, a compost turning frequency adjustment submodule and a microenvironment adjustment submodule, wherein: Real-time monitoring and analysis submodule: Based on the gas control strategy, it monitors and analyzes the real-time gas concentration and environmental data, collects monitoring data to analyze the dynamic change trend of temperature, humidity and gas concentration in the stack, and processes and corrects the correlation between gas concentration change and ventilation conditions in combination with sensor collection data to obtain real-time monitoring and control data sets; Compost turning frequency adjustment submodule: based on the real-time monitoring and control data set, adjust the compost turning frequency, analyze the gas concentration change rate in the real-time data and the gas distribution data in the time series, adjust the compost turning interval time in combination with the compost turning operation record and record the new setting, and generate the compost turning frequency adjustment result; Microenvironment adjustment submodule: Based on the compost turning frequency adjustment result, the ventilation parameters in the composting area are adjusted to achieve gas concentration balance, and the microenvironment conditions in the composting area are optimized in combination with the humidity adjustment data to generate optimized operating parameters.

6. The odor reduction control system for livestock and poultry manure composting according to claim 1 is characterized in that: The odor source positioning module includes a regional emission monitoring submodule, a dominant source identification submodule and an odor characteristic analysis submodule, wherein: Regional emission monitoring submodule: Based on the optimized operating parameters, the concentration data of ammonia, hydrogen sulfide and volatile organic compounds in the composting fermentation area are collected through a convolutional neural network, the emission concentration changes are recorded in combination with time nodes and the emission peak periods are divided, the concentration change data in different areas of the pile are spatially analyzed, and the classification and range of the emission area are calibrated to generate emission peak area data; The dominant source identification submodule: based on the emission peak area data, analyze the dominant odor source in the composting area, calculate the concentration ratio of each component by classifying the gas component concentration collected in the emission area, compare the component ratios in different areas to confirm the dominant emission gas type, locate the high emission point in the area by the concentration difference, identify the odor dominant source area by combining the component concentration in the area with the distribution characteristics of the high emission point, and generate the dominant odor source data; Odor characteristic analysis submodule: Based on the dominant odor source data, odor emission patterns and characteristics are extracted, and the temporal distribution characteristics of the emission area are extracted by analyzing the composition change law of the dominant odor source area and combining the odor diffusion trajectory in the fermentation stage. The regional emission pattern is established in combination with the composition change characteristics and the spatial distribution characteristics corresponding to each pattern are marked. The pattern feature annotation of the dominant odor source is completed to generate the odor source analysis result.

7. The odor reduction control system for livestock and poultry manure composting according to claim 1 is characterized in that: The odor reduction strategy module includes a structure optimization and adjustment submodule, a ventilation condition improvement submodule and a gas management execution submodule, wherein: Structural optimization and adjustment submodule: According to the odor source analysis results, the compost pile structure is optimized and adjusted, the discharge path of the high-emission area of ​​the compost body is analyzed and the pile level is rearranged in combination with the regional characteristics, the air flow channel in the high-emission area is optimized to a short-distance discharge path, and gas diffusion control holes are arranged in the discharge path to complete the optimization adjustment of the pile structure, and generate pile structure optimization data; Ventilation condition improvement submodule: Based on the stack structure optimization data, the ventilation conditions in the high emission area are adjusted, the area and spacing of the vents in the high emission area are reset by combining the optimization data, the operation frequency and airflow direction of the ventilation equipment are adjusted, and the optimization condition configuration is completed by increasing and decreasing the ventilation channel pressure to match the gas concentration change, and a ventilation condition improvement plan is generated; Gas management execution submodule: Based on the ventilation condition improvement plan, dynamic emission management operations of composting odor are carried out, and the gas concentration in high emission areas is adjusted in real time in combination with the ventilation condition improvement plan, and the gas in the emission peak area is collected and drained. The regional emission dynamics are adjusted by real-time control of the ventilation equipment operating parameters, and the gas collection and emission coordination are completed to generate an odor reduction implementation plan.

8. A method for reducing odor emissions from livestock and poultry manure composting, characterized in that: The odor reduction control system for livestock and poultry manure composting according to any one of claims 1 to 7 comprises the following steps: Step 1: Send the compost material into the fermentation area, insert a gas sensor into the compost body, monitor the concentration of ammonia, hydrogen sulfide and volatile organic compounds, and record the temperature and humidity values ​​of the composting area. Collect and digitize the concentration value and environmental data at each time node in turn to generate primary gas data; Step 2: Based on the primary gas data, arrange the gas concentration in chronological order, calculate the concentration change rate of each set of data, mark the concentration sudden increase point and periodic change interval, integrate the change results according to the time node, and generate a dynamic gas model; Step 3: combining the dynamic gas model with the ventilation airflow path of the composting area, calculating the gas diffusion path length and diffusion rate, and generating a composting gas diffusion path distribution characteristic table through correlation analysis between concentration value and path position; Step 4: Based on the composting gas diffusion path distribution characteristic table, the ventilation parameters of the composting area are adjusted, including wind speed value, ventilation duct layout and airflow distribution state, the operation mode of the existing ventilation system is optimized, and a gas control strategy is generated; Step 5: Based on the gas control strategy, combined with the compost turning frequency, temperature and humidity data in the composting area, the dynamic distribution of compost gas concentration is analyzed, high-value points of odor concentration are marked, and the emission peak area is located to generate a distribution map of high-value points of compost odor emission; Step 6: Based on the distribution map of high-value points of composting odor emission, by adjusting the pile height, pile structure and airflow direction of the exhaust channel in the composting area, the ventilation conditions in the composting area are optimized, the gas distribution and emission path are dynamically controlled, and an odor reduction implementation plan is generated.

9. The method for reducing odor emission from livestock and poultry manure composting according to claim 1, characterized in that: Add multiple layers of gas sensors to the compost body, specifically at the top, middle and bottom of the pile, to ensure that the monitored concentration data fully covers the compost gas diffusion process; The optimization of ventilation parameters specifically includes setting the ventilation time to 15 to 20 minutes per hour and the wind speed range to 1 to 1.5 meters per second, ensuring uniform airflow distribution in high-value areas while reducing ventilation operating costs; The rate of change of the sudden increase point of gas concentration in the dynamic gas model is calculated by dividing the concentration change value by the time interval, which shall not exceed five minutes; The pile height is adjusted to 1.2 to 1.8 meters to control the gas concentration distribution and reduce the odor emission concentration; When the monitoring results show that the diffusion path length is long, the stack density is increased to inhibit gas diffusion.

10. The method for reducing odor emission from livestock and poultry manure composting according to claim 1, characterized in that: The composting area is divided into a fermentation area and a maturation area. The ventilation control is strengthened in the fermentation area and the ventilation volume is reduced in the maturation area. The ventilation volume ratio is set at three to one. Set up multiple parallel exhaust channels, with the distance between each channel not less than two meters and the channel diameter ranging from 15 cm to 25 cm, to quickly exhaust composting gas and reduce gas concentration; Add odor adsorbing materials, including biochar and zeolite, to the high-value areas, with the specific amount added being 5 to 8 percent of the total weight of the compost material; During peak odor concentration periods, the ventilation frequency, wind speed and pile turning interval are automatically adjusted in combination with real-time monitoring data, and a real-time feedback control mechanism is established.

Images