A method and system for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste

Abstract

The present application provides a method and system for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste. Among them, the present invention provides a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste, taking a mixture of livestock and poultry manure and straw as the treatment object, obtaining a set of environmental parameters of microbial metabolic intensity, and then dynamically matching the microbial agent addition rate and the bacterial community activity decay curve. In the aerobic fermentation stage, the activity balance of the surface and deep bacterial communities is maintained by linking the compost turning operation with the microbial agent addition strategy, and the microbial agent addition time window is corrected in combination with historical data. A quantitative model with a carbon-nitrogen ratio imbalance threshold as a constraint is established, and the nonlinear correlation between the microbial agent addition rate and the compost turning operation frequency is iteratively optimized to output the full-cycle synergistic effect evaluation result. The technical solution provided by the present application enhances the synergistic effect of pollution reduction and carbon reduction in the treatment of agricultural solid waste, and achieves the dual goals of resource utilization and environmental protection.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and system for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste. Background Art

[0002] The treatment of agricultural solid waste (such as livestock and poultry manure and straw) is a key component of agricultural non-point source pollution prevention and resource utilization. Currently, achieving synergistic improvements in pollution and carbon reduction during the treatment process has become a core technical requirement. Existing technologies must address dynamic monitoring of key parameters within the waste pile, precise control of operational strategies, and quantitative assessment of pollution and carbon reduction benefits to improve treatment efficiency and minimize environmental impact.

[0003] Currently, a composting optimization scheme based on simple parameter collection is being applied to agricultural solid waste treatment. This scheme collects basic data such as compost temperature, humidity, and oxygen concentration. For example, it adjusts operating parameters based on temperature fluctuations (such as turning the compost when the temperature exceeds 60°C) and oxygen concentration (increasing the frequency of turning when the temperature is less than 5%) to achieve pollution and carbon reduction goals.

[0004] However, this plan has the following shortcomings: First, relying solely on simple parameters (such as temperature and humidity) cannot fully reflect the complex biochemical processes inside the pile, resulting in insufficient accuracy of the operating strategy; second, it does not consider the coordinated optimization of pollution reduction and carbon reduction goals, which may lead to an imbalance in treatment effects (such as excessive turning of the pile increases energy consumption but does not significantly improve pollution reduction benefits). Summary of the Invention

[0005] The embodiments of the present application provide a method and system for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste, which is used to solve the problem of poor calculation effect of the synergistic effect of pollution reduction and carbon reduction in the prior art.

[0006] In a first aspect, the present invention provides a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste, including:

[0007] In the process of agricultural solid waste treatment, a mixture of livestock and poultry manure and straw is used as the treatment object, and the temperature gradient, pH fluctuation range and volatile organic compound concentration change inside the pile composed of the treatment object are monitored in real time to obtain a set of environmental parameters reflecting the intensity of microbial metabolism;

[0008] Dynamically matching the microbial agent dosage rate with the bacterial community activity attenuation curve according to the changing trend of the environmental parameter set, wherein the microbial agent comprises a composite bacterial community of thermophilic cellulose decomposing bacteria and nitrogen-fixing bacteria, and the dosage is reversely compensated and adjusted based on the oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold within the pile;

[0009] During the aerobic fermentation stage of the pile, the activity distribution of the composite bacterial community in the surface and deep areas of the pile is maintained balanced through the linkage control of the pile turning operation and the microbial agent addition strategy. At the same time, the discrete interval of the microbial agent addition time window is corrected based on the historical data of the external environmental humidity and light intensity.

[0010] A quantitative model of the synergistic effect of pollution reduction and carbon reduction is established with the carbon-nitrogen ratio imbalance threshold as a constraint condition, so as to iteratively optimize the nonlinear correlation between the acceleration rate of the microbial agent addition and the frequency of the compost turning operation through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and output the effect evaluation results of the whole cycle of agricultural solid waste treatment.

[0011] Optionally, the method further includes: synchronously calculating a dynamic coupling coefficient between the organic matter degradation rate and the greenhouse gas emission reduction amount based on the distribution balance of the bacterial community activity and the phased product characteristics of the pile;

[0012] Based on the dynamic coupling coefficient, the nonlinear correlation between the microbial agent injection acceleration rate and the compost turning operation frequency is adjusted to optimize the effect evaluation results of the entire cycle of agricultural solid waste treatment.

[0013] Optionally, dynamically matching the microbial agent injection acceleration rate and the bacterial colony activity decay curve according to the change trend of the environmental parameter set includes:

[0014] Decomposing the temperature gradient, pH value fluctuation range, and volatile organic compound concentration change in the environmental parameter set into a trend component and a fluctuation component, respectively, wherein the trend component is characterized by the cumulative rate of parameter change within a sliding window, and the fluctuation component is extracted by the difference between the extreme points of the parameters in adjacent windows;

[0015] Based on the cumulative rate variation characteristics of the trend component, fitting the bacterial community activity decay curve of the composite bacterial community in the pile, wherein the activity decay curve is calibrated by a preset microbial agent addition experiment to determine the decay slope of the bacterial community metabolic rate under different oxygen diffusion efficiencies;

[0016] Based on the attenuation slope of the bacterial colony activity attenuation curve and the extreme point distribution characteristics of the fluctuation component, a dynamic response model of the microbial agent dosage acceleration rate is established, wherein the dynamic response model sets an inverse proportional constraint relationship between the activity maintenance threshold and the attenuation slope, and introduces a correction coefficient for the oxygen diffusion efficiency due to the change in the pile volume;

[0017] When the oxygen diffusion efficiency inside the stack is lower than a preset critical threshold and the carbon-nitrogen ratio imbalance threshold reaches a segmented compensation interval, a reverse compensation regulation rule based on the dynamic response model is triggered to dynamically adjust the incremental gradient of the microbial agent injection acceleration rate;

[0018] The dynamic control instructions for the microbial inoculant injection rate are updated in real time through the coupling effect of the reverse compensation regulation rule and the temperature gradient difference between the surface area and the deep area of ​​the pile.

[0019] Optionally, the dynamic control instruction of the microbial inoculant injection rate is updated in real time by coupling the reverse compensation regulation rule with the temperature gradient difference between the surface area and the deep area of ​​the pile body, including:

[0020] Layered temperature monitoring nodes are respectively set up in the surface area and deep area of ​​the pile body to obtain the surface temperature change sequence and the deep temperature change sequence, and the dynamic offset of the temperature gradient difference is calculated by the accumulated temperature difference in the sliding window;

[0021] Determining a dynamic compensation coefficient in the reverse compensation adjustment rule based on the dynamic offset and a preset bacterial colony activity distribution equilibrium threshold, wherein the dynamic compensation coefficient is quadratically weighted by the correction value of the oxygen diffusion efficiency according to the change in the stack volume;

[0022] Based on the correlation between the dynamic compensation coefficient and the carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the pile, a nonlinear mapping relationship between the temperature gradient difference and the microbial agent injection rate increment is constructed, and the historical fluctuation data of the external environmental humidity is introduced to discretize and calibrate the triggering time window of the mapping relationship;

[0023] When the temperature gradient difference exceeds the critical interval of the activity distribution equilibrium threshold, the segmented compensation mechanism of the reverse compensation adjustment rule is activated, a dynamic control instruction for the microbial agent injection acceleration rate is generated based on the nonlinear mapping relationship, and the real-time monitoring data of the volatile organic compound concentration change of the pile is coupled to update the weight distribution of the dynamic compensation coefficient;

[0024] Through the segmented compensation mechanism and the real-time feedback of the stack oxygen diffusion efficiency, the execution timing of the dynamic control instruction is iteratively adjusted, and the sliding window cumulative difference calculation period of the temperature gradient difference is synchronously corrected.

[0025] Optionally, during the aerobic fermentation stage of the pile, the activity distribution of the composite bacterial community in the surface and deep regions of the pile is maintained balanced by the linkage control of the pile turning operation and the microbial agent addition strategy, including:

[0026] During the aerobic fermentation stage of the pile, a surface bacterial community activity compensation coefficient and a deep oxygen diffusion correction coefficient are calculated based on the real-time monitoring data of the temperature gradient difference between the surface area and the deep area and the change in volatile organic compound concentration, wherein the surface bacterial community activity compensation coefficient is dynamically calibrated by the cumulative temperature change rate within the sliding window and the attenuation slope of a preset bacterial community activity attenuation curve;

[0027] Based on the nonlinear correlation between the surface bacterial community activity compensation coefficient and the deep oxygen diffusion correction coefficient, a collaborative control instruction for the triggering frequency of the turning operation and the microbial agent injection acceleration rate is generated to maintain the balanced distribution of the bacterial community activity of the composite bacterial community in the surface area and the deep area of ​​the pile body, wherein the weight distribution ratio of the surface and deep bacterial community activities is set in the collaborative control instruction.

[0028] Optionally, the method of simultaneously combining historical data of external environmental humidity and light intensity to correct the discrete interval of the microbial agent addition time window includes:

[0029] Extract historical data on the rate of change of external environmental humidity and the amplitude of light intensity fluctuations, and calculate the discrete interval offset of the inoculum addition time window by accumulating the difference between the humidity and light coupling parameters in adjacent time windows. The discrete interval offset is dynamically matched with the carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the pile.

[0030] Based on the discrete interval offset and the extreme point distribution characteristics of the surface temperature change sequence, a dynamic mapping relationship is constructed between the triggering time of the compost turning operation and the time window for adding the inoculant. In this dynamic mapping relationship, a critical threshold of oxygen diffusion efficiency is set as a segmented trigger condition, and the constraint boundary of the mapping relationship is updated by coupling with real-time feedback data on the change in volatile organic compound concentration.

[0031] When the oxygen diffusion efficiency in the deep layer of the pile is lower than the preset critical value or the surface bacterial community activity compensation coefficient deviates from the equilibrium range, the compensation weights of the incremental gradient of the pile turning operation frequency and the microbial agent injection acceleration rate are synchronously adjusted based on the dynamic mapping relationship, and the execution timing of the collaborative control instruction is iteratively updated through the real-time correction value of the oxygen diffusion efficiency due to the change in the pile volume.

[0032] Optionally, the nonlinear correlation between the microbial agent dosage rate and the compost turning frequency is iteratively optimized through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and the output of the effect evaluation result of the entire cycle of agricultural solid waste treatment is output, including:

[0033] The threshold value of microbial inoculant activity, the mechanical energy efficiency coefficient of compost turning, and the sudden drop threshold of pH in the deep region of the compost are obtained by sensors installed in the compost body and used as input parameters of the quantitative model, and a candidate solution set of microbial inoculant injection rate and compost turning operation frequency is generated by the quantitative model;

[0034] Calculating the partial derivatives of the objective function of the microbial agent dosage acceleration rate and the pile turning frequency in the candidate solution set, dynamically adjusting the microbial agent dosage acceleration rate and the pile turning frequency by combining real-time data from near-infrared spectroscopy and gas chromatography-mass spectrometry, and generating a three-dimensional response surface representing the nonlinear correlation between the two;

[0035] The three-dimensional response surface is integrated with the acquired UAV remote sensing and thermal infrared imaging data, and the abnormal operating conditions that deviate from the optimized path are screened using the pH sudden drop threshold in the deep layer of the pile as a constraint condition, and the discrete interval of the microbial agent addition time window is updated;

[0036] Based on the updated discrete intervals, a dynamic programming algorithm is used to segmentally calculate the synergistic effect index of the pollution reduction contribution and the carbon reduction contribution, and output the effect evaluation results after multiple rounds of iterative optimization. The results include the optimal microbial agent addition acceleration rate, the frequency of compost turning operations and the synergistic effect evaluation matrix.

[0037] In a second aspect, an embodiment of the present application provides a system for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste, including:

[0038] A monitoring module is used to obtain a set of environmental parameters reflecting the intensity of microbial metabolism by real-time monitoring of the temperature gradient, pH fluctuation range, and volatile organic compound concentration change within a pile of agricultural solid waste, using a mixture of livestock and poultry manure and straw as the treatment object during the treatment process;

[0039] a matching module for dynamically matching a microbial agent dosage rate with a bacterial community activity attenuation curve according to a changing trend of the set of environmental parameters, wherein the microbial agent comprises a composite bacterial community of thermophilic cellulolytic bacteria and nitrogen-fixing bacteria, and the dosage is reversely compensated and adjusted based on the oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold within the pile;

[0040] a control module for maintaining a balanced distribution of bacterial activity of the composite bacterial community in the surface and deep regions of the pile during the aerobic fermentation phase of the pile through the linkage control of the pile turning operation and the microbial agent dosing strategy, and for modifying the discrete interval of the microbial agent dosing time window based on historical data of the external environmental humidity and light intensity;

[0041] The optimization module is used to establish a quantitative model of the synergistic effect of pollution reduction and carbon reduction with the carbon-nitrogen ratio imbalance threshold as a constraint condition, so as to iteratively optimize the nonlinear correlation between the acceleration rate of the microbial agent addition and the frequency of the compost turning operation through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and output the effect evaluation results of the whole cycle of agricultural solid waste treatment.

[0042] In a third aspect, an embodiment of the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste as described in the first aspect above.

[0043] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste as described in the first aspect.

[0044] In the embodiment of the present application, during the treatment of agricultural solid waste, a mixture of livestock and poultry manure and straw is used as the treatment object, and the temperature gradient, pH fluctuation range, and volatile organic compound concentration change of the pile body formed by the treatment object are monitored in real time to obtain a set of environmental parameters reflecting the metabolic intensity of microorganisms; according to the change trend of the set of environmental parameters, the microbial agent addition rate and the microbial community activity decay curve are dynamically matched, wherein the microbial agent contains a composite microbial community of high-temperature cellulose decomposing bacteria and nitrogen-fixing bacteria, and the addition amount is reversely compensated and adjusted based on the oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold inside the pile body; During the aerobic fermentation stage of the pile, the activity distribution balance of the composite bacterial community in the surface and deep areas of the pile is maintained through the linkage control of the turning operation and the microbial agent addition strategy. At the same time, the discrete interval of the microbial agent addition time window is corrected in combination with the historical data of the external environmental humidity and light intensity. A quantitative model of the synergistic effect of pollution reduction and carbon reduction is established with the carbon-nitrogen ratio imbalance threshold as a constraint condition, so as to iteratively optimize the nonlinear correlation between the microbial agent addition acceleration rate and the pile turning operation frequency through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and output the effect evaluation results of the whole cycle of agricultural solid waste treatment.

[0045] The technical solution of this application has the following beneficial effects:

[0046] By real-time monitoring of the temperature gradient inside the pile, the pH fluctuation range, and the change in volatile organic compound concentration, a set of environmental parameters reflecting the metabolic intensity of microorganisms is obtained to provide accurate data support for subsequent operation strategies and ensure the dynamic controllability of the treatment process. According to the changing trend of environmental parameters, the microbial agent addition rate is dynamically matched with the bacterial community activity decay curve, and reverse compensation adjustment is performed in combination with the oxygen diffusion efficiency and the carbon-nitrogen ratio imbalance threshold to optimize the microbial agent addition amount, maintain the metabolic efficiency of microorganisms inside the pile, and improve the degradation effect of organic matter. In the aerobic fermentation stage, through the linkage control of the turning operation and the microbial agent addition strategy, the activity distribution balance of the composite bacterial community in the surface and deep areas of the pile is maintained to avoid the decline in treatment efficiency caused by local hypoxia or uneven temperature. At the same time, combined with the historical data of external environmental humidity and light intensity, the microbial agent addition time window is corrected to enhance the system's adaptability to sudden working conditions. A quantitative model with the carbon-nitrogen ratio imbalance threshold as the constraint condition is established. By iteratively optimizing the nonlinear correlation between the microbial agent dosage acceleration rate and the compost turning operation frequency, the synergistic efficiency of pollution reduction and carbon reduction goals is achieved, and the full-cycle synergistic effect evaluation results are output to provide a scientific basis for the resource utilization of agricultural solid waste and environmental protection.

[0047] The present invention significantly enhances the synergistic effect of pollution reduction and carbon reduction in agricultural solid waste treatment through real-time monitoring, dynamic matching, linkage control and quantitative model optimization, achieving the dual goals of resource utilization and environmental protection.

[0048] Furthermore, by using sensors installed in the pile to obtain the threshold of microbial activity, the mechanical energy efficiency coefficient of compost turning, and the threshold of the sudden drop in pH in the deep area of ​​the pile, these sensors are used as input parameters of the quantitative model to generate a candidate solution set for the microbial injection acceleration rate and the compost turning frequency, providing an initial data basis for subsequent optimization and ensuring the scientific nature and feasibility of the treatment strategy. By calculating the partial derivatives of the objective functions of the microbial injection acceleration rate and the compost turning frequency in the candidate solution set, the operating parameters are dynamically adjusted by combining near-infrared spectroscopy and gas chromatography-mass spectrometry real-time data, and a three-dimensional response surface is generated to characterize the nonlinear correlation between the two, providing a visual basis for the optimization path and improving the accuracy of the strategy adjustment. The three-dimensional response surface is fused with drone remote sensing and thermal infrared imaging data, and the pH sudden drop threshold in the deep area of ​​the pile is used as a constraint to screen abnormal conditions that deviate from the optimized path, update the discrete interval of the microbial injection time window, enhance the system's adaptability to sudden conditions, and ensure the stability of the treatment process. Based on the updated discrete intervals, the dynamic programming algorithm is used to segmentally calculate the synergistic effect index of pollution reduction contribution and carbon reduction contribution, and output the effect evaluation results after multiple rounds of iterative optimization, including the optimal microbial agent addition acceleration rate, compost turning operation frequency and synergistic effect evaluation matrix, providing a scientific basis for the resource utilization and environmental protection of agricultural solid waste treatment.

[0049] Finally, through input parameter acquisition, objective function optimization, multimodal data fusion and dynamic programming algorithm, the iterative optimization of the microbial agent injection acceleration rate and the compost turning operation frequency was achieved, which significantly improved the synergistic effect of pollution reduction and carbon reduction in agricultural solid waste treatment and ensured the scientificity and stability of the treatment effect.

[0050] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0052] Figure 1 A flowchart of a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste provided by this application is shown;

[0053] Figure 2A schematic diagram showing a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste provided in this application is shown;

[0054] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0056] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0057] The present invention takes a mixture of livestock and poultry manure and straw as the treatment object, and obtains a set of environmental parameters reflecting the metabolic intensity of microorganisms by real-time monitoring of the temperature gradient, pH fluctuation range and volatile organic compound concentration change inside the pile, providing accurate data support for subsequent operation strategies; according to the changing trend of environmental parameters, the microbial agent addition rate is dynamically matched with the bacterial community activity attenuation curve, and reverse compensation adjustment is performed in combination with the oxygen diffusion efficiency and the carbon-nitrogen ratio imbalance threshold to optimize the microbial agent addition amount and improve the organic matter degradation efficiency; in the aerobic fermentation stage, through the linkage control of the turning operation and the microbial agent addition strategy, the activity distribution balance of the composite bacterial community in the surface and deep areas of the pile is maintained, and at the same time, combined with the historical data of external environmental humidity and light intensity, the microbial agent addition time window is corrected to enhance the system's adaptability to sudden working conditions; finally, a quantitative model of the pollution reduction and carbon reduction synergistic effect is established with the carbon-nitrogen ratio imbalance threshold as the constraint condition, and the nonlinear correlation between the microbial agent addition rate and the turning operation frequency is iteratively optimized to output the full-cycle synergistic effect evaluation result, thereby realizing the synergistic effect of pollution reduction and carbon reduction in agricultural solid waste treatment.

[0058] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0059] Figure 1 A flowchart of a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste is provided for the embodiment of the present application. Figure 1 As shown, the method includes:

[0060] 101. In the process of treating agricultural solid waste, a mixture of livestock and poultry manure and straw is used as the treatment object, and the temperature gradient, pH fluctuation range and volatile organic compound concentration change of the pile formed by the treatment object are monitored in real time to obtain a set of environmental parameters reflecting the intensity of microbial metabolism;

[0061] In this step, the internal temperature gradient of the compost pile refers to the temperature difference between different areas of the compost pile due to heat generated by microbial metabolic activity during the composting process. It is an important indicator of microbial activity and composting efficiency. A larger temperature gradient indicates more active microbial metabolism and a more efficient composting process; a smaller temperature gradient may indicate insufficient microbial activity or poor composting conditions. By monitoring the temperature gradient, compost management can be optimized to ensure sufficient degradation of organic matter.

[0062] The pH fluctuation range refers to the temporal and spatial variations in pH during the composting process. pH directly impacts the microbial environment and metabolic efficiency. An optimal pH range (typically 6.5-8.5) is conducive to microbial activity, while excessive acidity or alkalinity inhibits degradation. Monitoring pH fluctuations helps adjust composting conditions, maintain microbial activity, and improve composting efficiency.

[0063] Volatile organic compound (VOC) concentration fluctuations refer to the temporal or spatial variation in the concentration of volatile organic compounds (VOCs) produced by microbial degradation of organic matter during the composting process. Changes in VOC concentrations directly reflect the rate and extent of organic matter degradation. A rapid decrease in concentration indicates efficient degradation, while excessively high concentrations may indicate poor composting conditions or odor issues. Monitoring VOC concentration fluctuations helps assess composting progress and optimize management measures.

[0064] The environmental parameter set refers to the data set obtained by real-time monitoring of the temperature gradient inside the pile, the pH fluctuation range and the change in the concentration of volatile organic compounds, which is used to characterize the dynamic changes in the metabolic intensity of microorganisms.

[0065] By deploying temperature sensors, pH probes, and volatile organic compound (VOC) detectors, we collect real-time data on the internal temperature gradient (e.g., surface-to-deep temperature difference ≥15°C), pH fluctuation range (e.g., 6.5-8.2), and changes in VOC concentrations (e.g., changes in BTEX concentrations) within the pile. The temperature gradient is calculated using the sliding window difference of multiple temperature sensors, the pH fluctuation range is dynamically calibrated using an embedded electrode array, and VOC concentrations are analyzed in real time using gas chromatography-mass spectrometry. Ultimately, these data are integrated to generate a set of environmental parameters, providing data support for subsequent operational strategies.

[0066] In the solid waste treatment process at a large-scale livestock farm, technicians first evenly arranged 15 high-precision temperature sensors, 8 pH probes, and 5 gas chromatographs / mass spectrometers at different depths within the pile (surface, middle, and deep layers) to comprehensively monitor the temperature gradient, pH fluctuation range, and changes in volatile organic compound (VOC) concentrations within the pile. The temperature sensors use multi-point temperature measurement technology, collecting data every 30 minutes, covering the temperature distribution from the surface to the deep layers of the pile. The pH probes record the pH value every hour through an online monitoring system to ensure real-time and accurate data. The gas chromatograph / mass spectrometer analyzes gas samples from the pile every two hours to detect changes in the types and concentrations of VOCs. After 10 days of continuous monitoring, data showed that the temperature difference between the surface and deeper layers of the pile reached a maximum of 30°C (surface temperature: 35°C, deep temperature: 65°C), pH values ​​fluctuated between 6.5 and 8.5, and volatile organic compound concentrations varied between 0.5 and 3.0 mg / m³, primarily composed of organic acids such as acetic acid, propionic acid, and butyric acid. After preprocessing and integration, this data generated a set of environmental parameters, providing accurate data support for subsequent inoculant addition and compost turning operations, ensuring dynamic monitoring and optimized regulation of microbial metabolic intensity.

[0067] 102. Dynamically matching the microbial agent injection rate and the bacterial colony activity attenuation curve according to the change trend of the environmental parameter set;

[0068] In this step, the inoculum contains a complex of thermophilic cellulolytic and nitrogen-fixing bacteria, and the dosage is adjusted based on the oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold within the biomass. Dynamic matching involves adjusting the relationship between the inoculum dosage rate and the bacterial activity decay curve based on the changing trends of a set of environmental parameters, ensuring that the dosage matches the microbial metabolic needs.

[0069] The carbon-nitrogen ratio imbalance threshold refers to the critical value where the ratio of carbon to nitrogen elements inside the pile exceeds the suitable range for microbial metabolism (usually 20:1 to 30:1), affecting the efficiency of microbial degradation.

[0070] Reverse compensation regulation is a dynamic optimization strategy that adjusts the inoculum dosage rate according to changes in oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold to ensure the stability and efficiency of microbial metabolism.

[0071] The temperature gradient, pH fluctuation range, and volatile organic compound concentration change in the environmental parameter set were decomposed into trend and fluctuation components, respectively. The trend component was characterized by the cumulative rate of parameter change within a sliding window, and the fluctuation component was extracted by the difference between the extreme points of the parameters within adjacent windows. Based on the cumulative rate change characteristics of the trend component, a bacterial activity decay curve was fitted, and the decay slope was calibrated through a preset microbial dosing experiment. Based on the decay slope and the extreme point distribution characteristics of the fluctuation component, a dynamic response model for the microbial dosing acceleration rate was established, setting an inverse proportional constraint relationship between the activity maintenance threshold and the decay slope, and introducing a correction coefficient for the oxygen diffusion efficiency due to the change in pile volume. When the oxygen diffusion efficiency falls below the preset critical threshold and the carbon-nitrogen ratio imbalance threshold reaches the segmented compensation interval, the reverse compensation regulation rule is triggered to dynamically adjust the incremental gradient of the microbial dosing acceleration rate.

[0072] Based on the environmental parameter set obtained in the previous case study, technicians used machine learning algorithms (such as random forest regression) to predict the decay curve of bacterial activity. Combined with data collected by an oxygen sensor and a carbon-nitrogen ratio detector (oxygen diffusion efficiency of 75% and carbon-nitrogen ratio imbalance threshold of 28:1), they dynamically adjusted the inoculum dosage rate using an inverse compensation adjustment algorithm. In practice, technicians collected oxygen diffusion efficiency and carbon-nitrogen ratio data every two hours and, based on the changing trends of the environmental parameter set, adjusted the inoculum dosage rate in real time. For example, when the pile temperature reached 55°C, the dosage rate was adjusted to 0.7 kg per hour; when the temperature dropped to 45°C, the dosage rate was reduced to 0.5 kg per hour. Simultaneously, technicians adjusted the ratio of thermophilic cellulolytic bacteria to nitrogen-fixing bacteria in the inoculum based on changes in volatile organic compound concentrations to ensure that the carbon-nitrogen ratio imbalance was effectively controlled. After 21 days of dynamic adjustment, the activity of the composite bacterial community remained at an optimal level, and the metabolic intensity of the microorganisms within the pile was stable, providing a strong foundation for bacterial activity in the subsequent aerobic fermentation stage and significantly improving treatment efficiency.

[0073] 103. During the aerobic fermentation stage of the pile, the activity distribution of the composite bacterial community in the surface and deep regions of the pile is maintained balanced by the coordinated control of the pile turning operation and the microbial agent dosing strategy. At the same time, the discrete interval of the microbial agent dosing time window is modified based on the historical data of the external environmental humidity and light intensity.

[0074] The aerobic fermentation phase, during this step, refers to the phase during the waste treatment process where oxygen is the primary condition, and the metabolic activity of aerobic microorganisms decomposes organic matter into stable humus. This phase requires an adequate oxygen supply and suitable temperature and humidity conditions to promote efficient microbial degradation of organic waste.

[0075] The microbial agent addition strategy refers to an optimization plan that dynamically adjusts the addition rate, addition location and time window of the complex bacterial community (such as high-temperature cellulose-decomposing bacteria and nitrogen-fixing bacteria) according to the distribution of microbial activity inside the pile and changes in environmental parameters, aiming to maintain the balance and efficiency of microbial activity.

[0076] Linkage control refers to maintaining the balanced distribution of bacterial activity in the surface and deep areas of the pile through the synergistic effect of the pile turning operation and the microbial agent addition strategy, and correcting the time window for microbial agent addition.

[0077] The balanced distribution of bacterial activity means that the activity difference of the complex bacterial community in the surface area and deep area of ​​the pile is controlled within a reasonable range, ensuring that the metabolic intensity of microorganisms in each area of ​​the pile is consistent, and avoiding excessive or low local activity that affects the overall treatment efficiency.

[0078] During the aerobic fermentation stage, the surface bacterial activity compensation coefficient and the deep oxygen diffusion correction coefficient are calculated based on the temperature gradient difference between the surface and deep regions and the change in volatile organic compound concentration. The surface bacterial activity compensation coefficient is dynamically calibrated by the cumulative temperature change rate within the sliding window and the attenuation slope of the preset bacterial activity attenuation curve. The deep oxygen diffusion correction coefficient is calculated by correcting the oxygen diffusion efficiency due to the change in pile volume. Based on the nonlinear relationship between the two, coordinated control instructions are generated for the frequency of pile turning operation triggering and the microbial agent injection acceleration rate, and the weight distribution ratio of surface and deep bacterial activity is set. At the same time, combined with historical data on external environmental humidity and light intensity, the discrete interval offset of the microbial agent injection time window is calculated by the cumulative difference between the humidity and light coupling parameters in adjacent time windows. Based on the extreme point distribution characteristics of the surface temperature change sequence, a dynamic mapping relationship between the trigger moment of the pile turning operation and the microbial agent injection time window is constructed.

[0079] In the aforementioned scenario, during the aerobic fermentation phase of the pile, technicians use automated mechanical turning equipment to turn the pile every six hours and adjust the inoculant dosing strategy based on bacterial activity distribution data. This turning operation utilizes fully automated equipment to ensure even oxygen distribution between the surface and deeper layers of the pile. Turning depth and frequency are optimized by real-time monitoring of temperature gradients and pH changes within the pile. The inoculant dosing strategy is dynamically adjusted based on bacterial activity distribution data. When surface bacterial activity is lower than that in deeper layers, the inoculant dosage is increased, and the ratio of thermophilic cellulolytic bacteria to nitrogen-fixing bacteria in the inoculant is adjusted. Furthermore, technicians, using historical data on external ambient humidity (70%) and light intensity (5000 lux), employ a time series analysis algorithm to adjust the discrete intervals of the inoculant dosing window, adjusting it from every six hours to every four hours. After optimization, the difference in bacterial activity distribution between the surface and deep areas of the pile was controlled within 8%, achieving a balanced distribution of bacterial activity, ensuring the smooth progress of aerobic fermentation, and significantly shortening the processing cycle.

[0080] 104. Establish a quantitative model of the synergistic effect of pollution reduction and carbon reduction with the carbon-nitrogen ratio imbalance threshold as a constraint condition, so as to iteratively optimize the nonlinear correlation between the microbial agent addition rate and the compost turning operation frequency through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and output the effect evaluation results of the whole cycle of agricultural solid waste treatment.

[0081] In this step, the quantitative model of the synergistic effect of pollution reduction and carbon reduction refers to a mathematical model that uses the carbon-nitrogen ratio imbalance threshold as a constraint condition, iteratively optimizes the nonlinear correlation between the microbial agent injection acceleration rate and the frequency of compost turning operations, and outputs the full-cycle synergistic effect evaluation results.

[0082] The threshold of microbial agent activity, the mechanical energy efficiency coefficient of compost turning, and the threshold of sudden pH drop in the deep region of the pile are obtained through sensors and used as input parameters of the quantitative model to generate a set of candidate solutions for the microbial agent injection acceleration rate and the compost turning frequency. The partial derivatives of the objective functions of the microbial agent injection acceleration rate and the compost turning frequency in the candidate solution set are calculated, and the operating parameters are dynamically adjusted by combining near-infrared spectroscopy and gas chromatography-mass spectrometry real-time data to generate a three-dimensional response surface that characterizes the nonlinear correlation between the two. The three-dimensional response surface is fused with UAV remote sensing and thermal infrared imaging data, and the threshold of sudden pH drop in the deep region of the pile is used as a constraint condition to screen abnormal working conditions that deviate from the optimized path, and update the discrete interval of the microbial agent injection time window. Based on the updated discrete interval, the dynamic programming algorithm is used to segmentally calculate the synergistic effect index of the pollution reduction contribution and the carbon reduction contribution, and the optimal microbial agent injection acceleration rate, compost turning frequency, and synergistic effect evaluation matrix are output.

[0083] Based on a carbon-nitrogen ratio imbalance threshold (28:1), researchers established a quantitative model for the synergistic effects of pollution and carbon reduction. Using the NSGA-II multi-objective optimization algorithm, they iteratively optimized the nonlinear relationship between microbial inoculant dosage rate and compost turning frequency. In practice, the model simulated the effects of varying microbial inoculant dosage rates and compost turning frequencies on pollution and carbon reduction, and used actual monitoring data to calibrate the parameters. For example, when the microbial inoculant dosage rate was 0.7 kg per hour and the compost turning frequency was once every six hours, the best pollution and carbon reduction results were achieved, with treatment efficiency increasing by 30% and carbon emissions decreasing by 20%. In actual application, the researchers adjusted the operating parameters based on the optimization results, ultimately shortening the treatment cycle from 35 days to 25 days, significantly improving treatment efficiency and reducing pollutant emissions. Furthermore, the model outputs effect evaluation results for the entire agricultural solid waste treatment cycle, providing a scientific basis for optimizing subsequent treatment processes and achieving a win-win situation for both economic and environmental benefits.

[0084] Through the coordinated implementation of the above steps, the solid waste treatment of this large-scale farm has achieved efficient and stable microbial metabolic regulation. Step 101 monitors the environmental parameter set in real time, providing accurate data support for subsequent steps; Step 102 dynamically matches the microbial agent addition rate to ensure that the bacterial community activity is maintained at an optimal level; Step 103 achieves a balanced distribution of bacterial community activity through the linkage control of the turning operation and the microbial agent addition strategy; Step 104 establishes a quantitative model for the synergistic effect of pollution reduction and carbon reduction to optimize the effect evaluation of the entire treatment cycle. Ultimately, the treatment cycle was shortened to 25 days, the treatment efficiency was increased by 30%, carbon emissions were reduced by 20%, and pollutant emissions were significantly reduced, providing a scientific basis and successful example for the resource utilization of agricultural waste, achieving a win-win situation in economic and environmental benefits.

[0085] In order to achieve the coordinated optimization of microbial metabolic efficiency and environmental benefits in the process of agricultural solid waste treatment, and to solve the problems of low treatment efficiency and high carbon emissions in traditional methods due to uneven distribution of microbial activity and difficulty in quantifying the correlation between organic matter degradation rate and greenhouse gas emission reduction, this application simultaneously calculates the dynamic coupling coefficient of organic matter degradation rate and greenhouse gas emission reduction based on the balance of microbial activity distribution and the phased product characteristics of the pile, and dynamically adjusts the nonlinear correlation between the microbial agent addition rate and the frequency of pile turning operations based on this coefficient, thereby optimizing the effect evaluation results of the entire treatment cycle, maximizing the synergistic effect of pollution reduction and carbon reduction, and providing a more scientific and sophisticated solution for agricultural solid waste treatment.

[0086] In some embodiments, the method further comprises:

[0087] 201. Based on the distribution balance of the bacterial community activity and the phased product characteristics of the pile, the dynamic coupling coefficient of the organic matter degradation rate and the greenhouse gas emission reduction is simultaneously calculated;

[0088] In this step, the balance of microbial activity distribution refers to whether the activity of the microbial communities in different areas of the compost pile is evenly distributed during the composting process. A balanced distribution of microbial activity helps improve the degradation efficiency of organic matter and avoids localized overheating or incomplete degradation. The distribution of microbial activity can be assessed by monitoring parameters such as temperature, pH, and volatile organic compound concentrations.

[0089] The phased product characteristics of a composting pile refer to the changes in the types and concentrations of intermediate or final products produced at different stages of the composting process. For example, a large amount of volatile organic compounds may be produced in the early stages of composting, while stable humus may be produced in the later stages. These characteristics reflect the stage-by-stage nature of the composting process and its degradation efficiency.

[0090] The organic matter degradation rate refers to the rate and extent to which organic matter in a composting pile is broken down by microorganisms during the composting process. It is typically calculated by monitoring parameters such as the weight change of the compost pile, the concentration of volatile organic compounds (VOCs), and the carbon-nitrogen ratio. A high degradation rate indicates an efficient composting process, with the organic matter being fully converted into stable products.

[0091] Greenhouse gas emission reduction refers to the reduction of greenhouse gases (such as By monitoring gas emission concentrations and combining them with compost parameters, the amount of emissions reduction can be calculated. The higher the emission reduction, the better the environmental benefits of the composting process.

[0092] The dynamic coupling coefficient (DCC) is a parameter that dynamically correlates the organic matter degradation rate with greenhouse gas emissions reductions. It quantifies the synergistic relationship between degradation efficiency and environmental benefits during the composting process. Calculated through a mathematical model, this coefficient helps optimize composting management and achieve the dual goals of efficient degradation and low carbon emissions.

[0093] In the embodiment of the present application, the temperature, pH value, volatile organic compound concentration and other parameters of the compost body are monitored in real time, and the balance of bacterial activity distribution is evaluated in combination with the bacterial community activity distribution data. Based on the phased product characteristics of the compost body (such as volatile organic compound concentration, humus production and carbon-nitrogen ratio changes), the phased nature of the composting process and the degradation efficiency are determined. Then, the greenhouse gas emissions from the compost body (such as ) concentration and calculate greenhouse gas emission reductions. Using machine learning algorithms (such as multivariate linear regression or neural networks), a dynamic model of organic matter degradation rate and greenhouse gas emission reduction is established, and the dynamic coupling coefficient between the two is calculated. Ultimately, this coefficient is used to evaluate the overall efficiency and environmental benefits of the composting process.

[0094] 202. Based on the dynamic coupling coefficient, the nonlinear correlation between the microbial agent injection acceleration rate and the compost turning operation frequency is adjusted to optimize the effect evaluation results of the entire cycle of agricultural solid waste treatment.

[0095] In this step, the inoculant dosage rate refers to the frequency and amount of microbial inoculant added to the composting pile during the composting process. The inoculant contains microorganisms that efficiently degrade organic matter, and its dosage rate directly affects the microbial activity and degradation efficiency of the composting pile. By dynamically adjusting the inoculant dosage rate, the composting process can be optimized, organic matter degradation rates can be increased, and greenhouse gas emissions can be reduced.

[0096] Compost turning frequency refers to how often the compost pile is turned during the composting process to improve aeration and uniformity. Turning helps regulate temperature, humidity, and oxygen supply, promoting even distribution and increased activity of microorganisms. By optimizing the frequency of compost turning, localized overheating and anaerobic conditions can be avoided, improving composting efficiency.

[0097] Full-cycle evaluation of agricultural solid waste treatment involves a comprehensive assessment of the efficiency, environmental benefits, and economic viability of each step in the composting process. This includes indicators such as organic matter degradation rate, greenhouse gas emissions reduction, energy consumption, and costs. By optimizing the inoculant dosage rate and compost turning frequency through a dynamic coupling coefficient, the overall composting effect can be enhanced, achieving efficient, environmentally friendly, and economical waste treatment.

[0098] In this embodiment of the present application, the dynamic coupling coefficient obtained in step 201 is first used to analyze the matching degree between the inoculum addition rate and the compost turning frequency during the current composting process. An optimization algorithm (such as a genetic algorithm or particle swarm optimization) is then used to adjust the inoculum addition rate and compost turning frequency to achieve optimal matching. In specific implementations, the inoculum addition rate is dynamically adjusted based on compost temperature, pH, and compost activity data, while the compost turning frequency is optimized based on the compost temperature gradient and changes in volatile organic compound concentration. Ultimately, through a real-time feedback mechanism, the composting process is continuously optimized, improving both processing efficiency and environmental benefits.

[0099] Here's a specific example:

[0100] At a certain agricultural solid waste treatment site, the composting object is a mixture of livestock and poultry manure and straw, with a pile size of 100 cubic meters and a composting cycle of 30 days. First, in step 201, the internal parameters of the pile are monitored in real time using temperature sensors, pH sensors, and gas sensors. Combined with the bacterial activity data, the organic matter degradation rate is calculated to be 75% and the greenhouse gas emission reduction is 30%. The dynamic coupling coefficient between the two is established using a neural network model, which is 0.85, indicating that there is a strong positive correlation between the organic matter degradation rate and the greenhouse gas emission reduction during the current composting process. Subsequently, in step 202, based on the dynamic coupling coefficient, the nonlinear correlation between the microbial agent addition rate and the frequency of compost turning operations is optimized through a genetic algorithm to optimize the effect evaluation results of the entire agricultural solid waste treatment cycle. Specifically, the genetic algorithm used a dynamic coupling coefficient (0.85) as a benchmark, setting the optimization objectives to improve organic matter degradation and greenhouse gas emission reduction while reducing energy consumption and costs. The inoculant dosage rate and compost turning frequency were used as optimization variables, establishing a nonlinear correlation model. Through iterative calculations, the optimal combination of inoculant dosage rate and compost turning frequency was found. Based on the optimization results, the inoculant dosage rate was adjusted to once every 24 hours to ensure sustained and efficient microbial activity, and the compost turning frequency was adjusted to once every 48 hours to improve compost aeration and avoid localized overheating or anaerobic conditions. After implementing the optimization plan, compost parameters were re-monitored and organic matter degradation and greenhouse gas emission reductions were calculated. The results showed that the organic matter degradation rate increased to 85% and the greenhouse gas emission reduction increased to 40%. The overall efficiency and environmental benefits of the composting process were significantly improved, providing scientific basis and technical support for the resource utilization of agricultural solid waste and greenhouse gas emission reduction.

[0101] In order to solve the problems of accelerated decay of bacterial activity, decreased treatment efficiency and greenhouse gas emissions caused by uneven temperature distribution of the pile, low oxygen diffusion efficiency and imbalance of carbon-nitrogen ratio in the treatment of solid waste in large-scale farms, this method analyzes the temperature gradient of the pile, pH fluctuation and the change pattern of volatile organic compound concentration, decomposes them into trend components and fluctuation components, fits the bacterial activity decay curve based on the cumulative rate of the trend component, establishes a dynamic response model based on the carbon-nitrogen ratio imbalance threshold, triggers the reverse compensation regulation rule to dynamically adjust the bacterial agent injection acceleration rate, and at the same time couples the surface and deep temperature gradient differences to update the control instructions in real time. In the specific implementation, step 102 dynamically matches the bacterial agent injection acceleration rate with the bacterial activity decay curve according to the change trend of the environmental parameter set, and also includes:

[0102] 301. Decompose the temperature gradient, pH value fluctuation range, and volatile organic compound concentration change in the environmental parameter set into a trend component and a fluctuation component respectively;

[0103] In step 301, the trend component refers to the trend of environmental parameter changes represented by the cumulative rate of parameter changes in the sliding window, which is used to reflect the long-term change pattern of bacterial community activity.

[0104] The fluctuation component refers to the short-term fluctuation of environmental parameters extracted by the difference between the extreme points of the parameters in adjacent windows, which is used to capture the impact of sudden working conditions on bacterial activity.

[0105] In this embodiment, temperature sensors, pH probes, and volatile organic compound (VOC) detectors are deployed to collect real-time data on the temperature gradient, pH fluctuation range, and VOC concentration changes within the biomass. A sliding window method is used to calculate the trend component (e.g., a temperature gradient accumulation rate ≥ 0.5°C / h), and the fluctuation component (e.g., a pH fluctuation range ≥ 0.3) is extracted by taking the difference between the extreme points of adjacent windows. Ultimately, the set of environmental parameters is decomposed into trend and fluctuation components, providing the data foundation for subsequent fitting of the bacterial activity decay curve.

[0106] 302. Fitting a bacterial community activity decay curve of the composite bacterial community in the pile based on the cumulative rate change characteristics of the trend component;

[0107] In step 302, the cumulative rate change characteristic of the trend component refers to the long-term change trend of the environmental parameters during the composting process. It is characterized by the cumulative rate of parameter change in the sliding window, reflecting the speed of parameter change over time, and providing data support for fitting the microbial activity decay curve.

[0108] The bacterial community activity decay curve refers to a curve fitted by the cumulative rate change characteristics of the trend component, which is used to characterize the change pattern of the metabolic rate of the composite bacterial community in the pile over time. Its decay slope is calibrated by the preset bacterial agent addition experiment.

[0109] In the embodiment of the present application, the least squares method was used to fit the decay curve of bacterial activity based on the trend component of temperature gradient and pH fluctuation, and the decay slope under different oxygen diffusion efficiencies was calibrated by a preset microbial agent addition experiment (for example, when the oxygen diffusion efficiency is <5%, the decay slope is ). Finally, the bacterial community activity decay curve is generated, which provides a basis for establishing a dynamic response model.

[0110] 303. Establish a dynamic response model of the microbial agent dosage acceleration rate based on the attenuation slope of the microbial activity attenuation curve and the extreme point distribution characteristics of the fluctuation component.

[0111] In step 303, the dynamic response model is a mathematical model established based on the attenuation slope of the bacterial activity attenuation curve and the distribution characteristics of the extreme points of the fluctuation component. It is used to dynamically adjust the inoculum dosage rate. The inverse proportional constraint relationship between the activity maintenance threshold and the attenuation slope ensures stable bacterial activity, and the correction factor for the oxygen diffusion efficiency due to the change in the pile volume is used to optimize model accuracy. The dynamic response model sets an inverse proportional constraint relationship between the activity maintenance threshold and the attenuation slope, and introduces a correction factor for the oxygen diffusion efficiency due to the change in the pile volume.

[0112] In the embodiment of the present application, according to the attenuation slope of the bacterial colony activity attenuation curve (such as ) and the extreme value distribution characteristics of the fluctuation component (e.g., pH fluctuation range ≥ 0.3), establish an inverse proportional constraint relationship between the activity maintenance threshold (e.g., bacterial activity ≥ 80%) and the decay slope, and introduce a correction factor for the oxygen diffusion efficiency due to changes in the pile volume (e.g., for every 10% increase in volume, the correction factor increases by 0.1). Then, based on these parameters and constraints, a dynamic response model is established to support reverse compensation regulation.

[0113] 304. When the oxygen diffusion efficiency inside the stack is lower than a preset critical threshold and the carbon-nitrogen ratio imbalance threshold reaches a segmented compensation interval, a reverse compensation regulation rule based on the dynamic response model is triggered to dynamically adjust the incremental gradient of the microbial agent injection rate;

[0114] In step 304, the segmented compensation intervals refer to the different adjustment ranges during the composting process, divided according to the degree of imbalance in the carbon-nitrogen ratio. The carbon-nitrogen ratio is a key parameter affecting microbial activity and composting efficiency. When the carbon-nitrogen ratio is imbalanced, appropriate compensation measures are required based on the degree of imbalance (e.g., mild, moderate, or severe). The segmented compensation intervals provide a clear basis for dynamically adjusting the inoculant dosage rate, ensuring the stability and efficiency of the composting process.

[0115] The reverse compensation regulation rule refers to the rule of dynamically adjusting the incremental gradient of the microbial agent injection rate when the oxygen diffusion efficiency inside the pile is lower than the preset critical threshold and the carbon-nitrogen ratio imbalance threshold reaches the segmented compensation interval, which is used to compensate for the attenuation of bacterial activity.

[0116] In this embodiment, the oxygen diffusion efficiency and carbon-nitrogen ratio changes within the compost pile are first monitored in real time. When the oxygen diffusion efficiency falls below a preset critical threshold (e.g., 5%) and the carbon-nitrogen ratio imbalance threshold reaches a segmented compensation range (e.g., C / N ≥ 25), the reverse compensation adjustment rule is triggered. Using a dynamic response model, the incremental gradient of the inoculant dosage rate is calculated (e.g., increasing by 0.5 L / h every 6 hours), and the inoculant dosage rate is dynamically adjusted to ensure stable bacterial activity. Simultaneously, the incremental gradient of the inoculant dosage rate is further optimized by combining the compost pile temperature gradient and the change in volatile organic compound concentration, thereby improving composting efficiency and environmental benefits.

[0117] 305. The dynamic control instruction of the microbial inoculant injection acceleration rate is updated in real time through the coupling effect of the reverse compensation regulation rule and the temperature gradient difference between the surface area and the deep area of ​​the pile.

[0118] In step 305, the dynamic control instruction achieves precise control of the microbial agent injection rate and optimizes the distribution of bacterial activity by combining the reverse compensation adjustment rule with the difference in the temperature gradient of the pile.

[0119] The coupling effect of the reverse compensation regulation rule and the temperature gradient difference means that the temperature gradient difference is used as an important parameter for dynamically adjusting the microbial agent injection acceleration rate, and the reverse compensation regulation rule is combined to optimize the dynamic control instructions of the microbial agent injection acceleration rate in real time.

[0120] In this embodiment, the temperature gradient difference between the surface and deeper regions of the composting pile is first monitored in real time. The surface region, due to direct contact with air, is cooler and has an ample oxygen supply, while the deeper regions, due to heat accumulation and restricted oxygen diffusion, are hotter and potentially hypoxic. This temperature gradient difference reflects the uneven distribution of heat and microbial activity within the composting pile. Subsequently, combined with a reverse compensation regulation rule, this temperature gradient difference serves as a key parameter for dynamically adjusting the inoculum addition rate. When the temperature in the deeper region is too high and oxygen diffusion efficiency is insufficient, the reverse compensation regulation rule increases the inoculum addition rate (e.g., by 0.3 L / h every four hours) to promote microbial activity and improve degradation efficiency in the deeper region. Simultaneously, taking into account the lower temperature and ample oxygen supply in the surface region, the inoculum addition rate is appropriately adjusted (e.g., by reducing it by 0.2 L / h every six hours) to avoid excessive addition and resource waste. This coupled effect achieves a balanced distribution of bacterial activity between the surface and deeper regions of the composting pile, allowing for real-time updates of dynamic control instructions for the inoculum addition rate, ensuring the overall efficiency and stability of the composting process.

[0121] Here's a specific example:

[0122] At an agricultural solid waste treatment site, the composting process consists of a mixture of livestock and poultry manure and straw, with a 100-cubic-meter pile size and a 30-day composting cycle. First, in step 301, the temperature gradient, pH fluctuation range, and volatile organic compound concentration variation are decomposed using a sliding window method to calculate the trend and fluctuation components. Subsequently, in step 302, a microbial activity decay curve is fitted based on the cumulative rate variation characteristics of the trend component, and the decay slope is calibrated. In step 303, a dynamic response model is established based on the extreme point distribution characteristics of the decay slope and the fluctuation component, setting an inverse proportional constraint relationship between the activity maintenance threshold and the decay slope. In step 304, when the oxygen diffusion efficiency falls below the critical threshold and the carbon-nitrogen ratio is unbalanced, the reverse compensation regulation rule is triggered to dynamically adjust the microbial inoculant dosage rate. Finally, in step 305, the dynamic control instructions for the microbial inoculant dosage rate are updated in real time based on the temperature gradient differences in the pile, ensuring stable microbial activity and improving composting efficiency.

[0123] Through the above steps, precise control of the inoculant dosage rate and dynamic matching of bacterial activity during the treatment of agricultural solid waste were achieved. By real-time monitoring of environmental parameter changes, combined with a dynamic response model and reverse compensation regulation rules, this method significantly improved composting efficiency and the stability of bacterial activity, providing a scientific basis and technical support for the efficient treatment of agricultural solid waste.

[0124] To address the problems of uneven bacterial activity distribution, large fluctuations in organic matter degradation rates, and excessive greenhouse gas emissions caused by significant temperature gradient differences between the surface and deep layers, oxygen diffusion efficiency limited by material bulk density, and imbalanced carbon-nitrogen ratios in the process of treating livestock and poultry manure and straw mixtures on large-scale farms, this method monitors the temperature changes of the pile in layers and calculates a dynamic offset. It then determines a dynamic compensation coefficient based on the activity equilibrium threshold (quadratically weighted after correcting the oxygen diffusion efficiency based on the pile volume change). A nonlinear mapping model between the temperature gradient difference and the microbial agent increment is constructed and the trigger time window is calibrated. When the temperature difference exceeds the limit, a segmented compensation mechanism is activated to generate dynamic instructions. The weight distribution is adjusted by coupling the real-time feedback of volatile organic compound concentrations. Furthermore, the instruction timing and window calculation period are iteratively optimized through feedback from oxygen diffusion efficiency, achieving precise control of the microbial agent injection acceleration rate. Specifically, in step 305, the dynamic control instructions for the microbial agent injection acceleration rate are updated in real time by coupling the reverse compensation adjustment rule with the temperature gradient difference between the surface and deep layers of the pile. The method also includes:

[0125] 401. Set up layered temperature monitoring nodes in the surface area and deep area of ​​the stack respectively, obtain surface temperature change sequence and deep temperature change sequence, and calculate the dynamic offset of the temperature gradient difference by the accumulated temperature difference in the sliding window;

[0126] In step 401 , the temperature change sequence refers to a sequence of temperature data of the surface area and the deep area of ​​the pile at different time points, which is used to reflect the dynamic change of the temperature inside the pile.

[0127] The cumulative temperature difference within the sliding window refers to the cumulative value of the temperature difference between the surface and deep areas of the pile within the sliding time window. It is used to quantify the changing trend of the temperature gradient difference. The obtained dynamic offset is used to characterize the imbalance of heat distribution and microbial activity distribution inside the pile.

[0128] Layered temperature monitoring nodes refer to temperature sensors distributed in the surface and deep areas of the pile, which are used to monitor temperature changes in real time; the dynamic offset is a parameter calculated by the cumulative temperature difference within the sliding window, which is used to quantify the changing trend of the temperature gradient difference.

[0129] In an embodiment of the present application, layered temperature monitoring nodes are first deployed in the surface and deep areas of the pile, for example, a temperature sensor is set per square meter to collect the surface temperature change sequence and the deep temperature change sequence in real time. Subsequently, the sliding window method (window length is 1 hour) is used to calculate the cumulative difference between the surface and deep temperatures in the window to obtain a dynamic offset. In a specific implementation, the cumulative temperature difference in the sliding window is obtained by subtracting the deep temperature from the surface temperature at each time point in the window, and then adding up all the differences. The dynamic offset reflects the imbalance of heat distribution and microbial activity distribution inside the pile, and provides data support for the subsequent adjustment of the microbial agent injection rate.

[0130] 402. Determine a dynamic compensation coefficient in the reverse compensation adjustment rule based on the dynamic offset and a preset bacterial colony activity distribution equilibrium threshold, wherein the dynamic compensation coefficient is obtained by performing a quadratic weighting on the correction value of the oxygen diffusion efficiency by the change in the stack volume;

[0131] In step 402, the dynamic compensation coefficient refers to a parameter calculated based on the temperature gradient difference and the balance threshold of the bacterial activity distribution, which is used to dynamically adjust the microbial agent injection acceleration rate; the correction value of the pile volume change on the oxygen diffusion efficiency is a parameter obtained by quantifying the impact of the pile volume change on the oxygen diffusion efficiency.

[0132] In the embodiment of the present application, the dynamic compensation coefficient is first calculated through a preset mathematical model based on the dynamic offset and the preset bacterial activity distribution equilibrium threshold (such as compensation is triggered when the dynamic offset exceeds 5°C). The mathematical model takes the dynamic offset as input, combines it with the bacterial activity distribution equilibrium threshold, and outputs the initial dynamic compensation coefficient. Then, the dynamic compensation coefficient is quadratically weighted in combination with the correction value of the oxygen diffusion efficiency due to the change in the volume of the pile. In a specific implementation, the correction value of the oxygen diffusion efficiency due to the change in the volume of the pile is obtained by fitting the experimental data, and is used to further optimize the accuracy of the dynamic compensation coefficient. Finally, the dynamic compensation coefficient is used to guide the dynamic adjustment of the microbial agent injection rate to ensure that the bacterial activity is evenly distributed in all areas of the pile.

[0133] 403. Based on the correlation between the dynamic compensation coefficient and the carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the pile, a nonlinear mapping relationship between the temperature gradient difference and the microbial agent injection rate increment is constructed, and historical fluctuation data of the external environmental humidity is introduced to discretize and calibrate the triggering time window of the mapping relationship;

[0134] In step 403, the phased product characteristics refer to the type and concentration changes of intermediate products or final products produced at different stages of the composting process. For example, the concentration of volatile organic compounds is high in the early stage of composting, and gradually decreases in the later stage to generate stable humus.

[0135] The nonlinear mapping relationship refers to the complex correlation model between the temperature gradient difference and the microbial agent injection acceleration rate increment; the historical fluctuation data of the external environmental humidity refers to the historical change data of the environmental humidity of the pile, which is used to calibrate the trigger time window of the mapping relationship.

[0136] The trigger time window refers to the time interval after the trigger time range of the nonlinear mapping relationship is calibrated based on the historical fluctuation data of the external environmental humidity, which is used to ensure the accuracy and applicability of the mapping relationship.

[0137] In the embodiment of the present application, first, by analyzing the correlation between the dynamic compensation coefficient and the carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the pile, the nonlinear influence of the temperature gradient difference on the microbial agent addition acceleration rate increment is determined. Then, the support vector machine or neural network model is trained using historical data, and the temperature gradient difference and the carbon-nitrogen ratio imbalance threshold are used as input features, and the microbial agent addition acceleration rate increment is used as the output target to construct a nonlinear mapping relationship. Subsequently, the trigger time window of the mapping relationship is discretized and calibrated in combination with the historical fluctuation data of the external environmental humidity. For example, when the humidity fluctuates greatly, the trigger time window is shortened to 30 minutes to adapt to rapidly changing environmental conditions. Finally, the calibrated nonlinear mapping relationship is used to dynamically adjust the microbial agent addition acceleration rate to ensure the efficiency and stability of the composting process.

[0138] 404. When the temperature gradient difference exceeds the critical interval of the activity distribution equilibrium threshold, the segmented compensation mechanism of the reverse compensation adjustment rule is activated, a dynamic control instruction for the microbial agent injection acceleration rate is generated based on the nonlinear mapping relationship, and the weight distribution of the dynamic compensation coefficient is updated by coupling with the real-time monitoring data of the volatile organic compound concentration change of the pile body;

[0139] In step 404, the segmented compensation mechanism refers to a regulation rule that adopts different compensation strategies according to different intervals of temperature gradient difference; the dynamic control instruction is an instruction for adjusting the microbial agent injection acceleration rate generated based on a nonlinear mapping relationship.

[0140] The change in the volatile organic compound concentration of the pile refers to the change in the volatile organic compound (VOCs) concentration inside the pile over time or space during the composting process, which directly reflects the rate and degree of organic matter degradation.

[0141] In the embodiment of the present application, the temperature gradient difference is first monitored in real time. When the temperature gradient difference exceeds the critical interval of the activity distribution equilibrium threshold (such as the dynamic offset exceeds 5°C), the segmented compensation mechanism of the reverse compensation adjustment rule is activated. Subsequently, a dynamic control instruction for the microbial agent injection acceleration rate is generated based on the nonlinear mapping relationship, for example, an increase of 0.3 L / h every 4 hours. At the same time, the real-time monitoring data of the change in the volatile organic compound concentration of the coupled pile is used to update the weight distribution of the dynamic compensation coefficient. In the specific implementation, the change in the volatile organic compound concentration is monitored in real time by a gas sensor and used as an important parameter for weight distribution to ensure that the microbial agent injection acceleration rate is accurately matched to the actual needs of the pile.

[0142] 405. Through the segmented compensation mechanism and the real-time feedback of the stack oxygen diffusion efficiency, the execution timing of the dynamic control instruction is iteratively adjusted, and the sliding window cumulative difference calculation period of the temperature gradient difference is synchronously corrected.

[0143] In step 405 , the execution sequence refers to the execution time arrangement of the dynamic control instruction; the sliding window cumulative difference calculation period refers to the time window length for calculating the dynamic offset.

[0144] In this embodiment, the execution timing of dynamic control instructions is iteratively adjusted through a segmented compensation mechanism and real-time feedback from the oxygen diffusion efficiency of the stack. For example, when the oxygen diffusion efficiency falls below a preset critical threshold, the execution interval of the dynamic control instructions is shortened to 2 hours. Simultaneously, the sliding window cumulative difference calculation period for temperature gradient differences is simultaneously modified, for example, by adjusting the window length from 1 hour to 30 minutes. This further improves the calculation accuracy of the dynamic offset and provides a reliable basis for dynamic adjustment of the inoculant dosage rate.

[0145] Here's a specific example:

[0146] At a certain agricultural solid waste treatment site, the composting object is a mixture of livestock and poultry manure and straw, with a pile size of 100 cubic meters and a composting cycle of 30 days. First, in step 401, layered temperature monitoring nodes are deployed in the surface and deep areas of the pile respectively, and the surface temperature change series and the deep temperature change series are collected in real time. The dynamic offset is calculated using the sliding window method. Subsequently, in step 402, the dynamic compensation coefficient is determined based on the dynamic offset and the balance threshold of the bacterial community activity distribution, and the correction value of the oxygen diffusion efficiency is quadratically weighted in combination with the change in the pile volume. In step 403, based on the correlation between the dynamic compensation coefficient and the carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the pile, a nonlinear mapping relationship is constructed, and historical fluctuation data of the external environmental humidity is introduced for calibration. In step 404, when the temperature gradient difference exceeds the critical interval, the segmented compensation mechanism is activated, dynamic control instructions are generated, and the weight distribution of the dynamic compensation coefficient is updated by coupling with the real-time monitoring data of the change in volatile organic compound concentration. Finally, in step 405, through the segmented compensation mechanism and real-time feedback of the oxygen diffusion efficiency of the compost body, the execution timing of the dynamic control instructions is iteratively adjusted, and the sliding window cumulative difference calculation cycle is synchronously corrected to ensure the precise control of the inoculant injection rate and the dynamic optimization of the composting process.

[0147] Through the above steps, precise control of the inoculant addition rate and optimization of bacterial activity distribution during the composting process were achieved, significantly improving composting efficiency and stability. This method, through real-time monitoring of temperature gradient differences, dynamic compensation coefficients, and nonlinear mapping relationships, combined with a segmented compensation mechanism and real-time feedback on oxygen diffusion efficiency, ensures that the inoculant addition rate is precisely matched to the actual needs of the compost, ultimately achieving the combined goals of improving composting efficiency, reducing greenhouse gas emissions, and optimizing resource utilization.

[0148] To further improve the balance of bacterial activity distribution and composting efficiency during the aerobic fermentation process, a surface bacterial activity compensation coefficient and a deep oxygen diffusion correction coefficient were calculated based on real-time monitoring data of temperature gradient differences and volatile organic compound concentration changes between the surface and deep regions during the aerobic fermentation stage. The surface bacterial activity compensation coefficient was dynamically calibrated by the cumulative temperature change rate within a sliding window and the attenuation slope of a preset bacterial activity attenuation curve. Based on the nonlinear relationship between the surface bacterial activity compensation coefficient and the deep oxygen diffusion correction coefficient, coordinated control instructions for the frequency of compost turning and the rate of microbial agent injection were generated to maintain a balanced distribution of composite bacterial activity in the surface and deep regions of the compost. The coordinated control instructions set a weighted distribution ratio for surface and deep bacterial activity. By adjusting the compost turning operation and microbial agent injection rate in real time, the uniform distribution of bacterial activity in all regions of the compost was ensured, thereby improving composting efficiency and stability.

[0149] In some embodiments, in step 103, during the aerobic fermentation stage of the pile, the balanced distribution of bacterial activity of the composite bacterial community in the surface and deep regions of the pile is maintained by linkage control of the pile turning operation and the microbial agent addition strategy, including:

[0150] 501. During the aerobic fermentation stage of the pile, based on the real-time monitoring data of the temperature gradient difference between the surface area and the deep area and the change in the concentration of volatile organic compounds, respectively calculate the surface bacterial community activity compensation coefficient and the deep oxygen diffusion correction coefficient;

[0151] In step 501, the surface flora activity compensation coefficient is dynamically calibrated by the cumulative temperature change rate in the sliding window and the attenuation slope of the preset flora activity attenuation curve. The surface flora activity compensation coefficient refers to a parameter calculated based on the temperature gradient difference in the surface area and the change in volatile organic compound concentration, and is used to dynamically adjust the surface flora activity; the deep oxygen diffusion correction coefficient refers to a parameter calculated based on the oxygen diffusion efficiency in the deep area, and is used to optimize the flora activity in the deep area; the cumulative temperature change rate in the sliding window refers to the cumulative rate of temperature change between the surface and deep layers within a certain time window, and is used to reflect the changing trend of the temperature gradient difference.

[0152] In this embodiment, temperature sensors and gas sensors are first deployed at the surface and deep layers of the compost pile, respectively, to collect temperature gradient differences and changes in volatile organic compound concentrations in real time. Subsequently, a sliding window method (with a window length of one hour) is used to calculate the cumulative rate of change of surface temperature within the window. This is combined with the decay slope of a preset bacterial activity decay curve to dynamically calibrate the surface bacterial activity compensation coefficient. Simultaneously, a deep oxygen diffusion correction coefficient is calculated based on the oxygen diffusion efficiency in the deep layer. Ultimately, the surface bacterial activity compensation coefficient and the deep oxygen diffusion correction coefficient are used to guide the coordinated control of subsequent compost turning operations and the inoculant dosage rate.

[0153] 502. Based on the nonlinear correlation between the surface bacterial community activity compensation coefficient and the deep oxygen diffusion correction coefficient, a collaborative control instruction for the triggering frequency of the pile turning operation and the microbial agent injection acceleration rate is generated to maintain the balanced distribution of the bacterial community activity of the composite bacterial community in the surface area and the deep area of ​​the pile body, wherein the collaborative control instruction sets the weight distribution ratio of the surface and deep bacterial community activities.

[0154] In step 502, the collaborative control instruction refers to the adjustment instruction of the turning operation and the microbial agent injection acceleration rate generated based on the nonlinear correlation between the surface microbial community activity compensation coefficient and the deep oxygen diffusion correction coefficient; the weight distribution ratio of the surface and deep microbial community activities refers to the weight distribution of the microbial community activity optimization targets in the surface and deep areas in the collaborative control instruction.

[0155] In the embodiments of the present application, a machine learning algorithm (such as a support vector machine or neural network) is first used to generate coordinated control instructions for the frequency of triggering the compost turning operation and the rate of microbial inoculant injection based on the nonlinear relationship between the surface microbial activity compensation coefficient and the deep oxygen diffusion correction coefficient. For example, when the surface microbial activity compensation coefficient is high, the frequency of triggering the compost turning operation is increased (e.g., once every 12 hours) to improve oxygen supply in the surface area; when the deep oxygen diffusion correction coefficient is low, the rate of microbial inoculant injection is increased (e.g., by 0.2 L / h every 6 hours) to optimize microbial activity in the deep area. Furthermore, a weighted distribution ratio between surface and deep microbial activity is set in the coordinated control instructions (e.g., 60% for the surface and 40% for the deep) to ensure uniform distribution of microbial activity across all regions of the compost.

[0156] Here's a specific example:

[0157] At an agricultural solid waste treatment site, the composting process consists of a mixture of livestock and poultry manure and straw. The composting volume is 100 cubic meters, and the composting cycle is 30 days. First, in step 501, temperature sensors and gas sensors are deployed in the surface and deep layers of the compost. Temperature gradient differences and changes in volatile organic compound concentrations are collected in real time. The cumulative rate of change in surface temperature is calculated using a sliding window method, dynamically calibrating the surface bacterial activity compensation coefficient. Simultaneously, a deep oxygen diffusion correction coefficient is calculated based on the oxygen diffusion efficiency of the deep layer. Subsequently, in step 502, based on the nonlinear relationship between the surface bacterial activity compensation coefficient and the deep oxygen diffusion correction coefficient, coordinated control instructions are generated for the frequency of compost turning and the rate of microbial inoculant injection. For example, turning is performed every 12 hours, and the rate of microbial inoculant injection is increased by 0.2 L / h every 6 hours. The weighted distribution of surface and deep bacterial activity is set at 60% and 40% respectively. By adjusting the compost turning and microbial inoculant injection rates in real time, the uniform distribution of bacterial activity across the compost is ensured, improving composting efficiency and stability.

[0158] Through the above steps, the balanced distribution of bacterial activity during the composting process and a significant improvement in composting efficiency were achieved. This method dynamically calibrates the surface bacterial activity compensation coefficient and the deep oxygen diffusion correction coefficient by real-time monitoring of temperature gradient differences and changes in volatile organic compound concentrations. It also generates coordinated control instructions for compost turning and inoculant injection acceleration, ensuring uniform distribution of bacterial activity across all regions of the compost, ultimately achieving the combined goals of improving composting efficiency, reducing greenhouse gas emissions, and optimizing resource utilization.

[0159] In order to solve the problems of sudden increase in pile humidity and imbalance of carbon-nitrogen ratio, local anaerobic fermentation and odor release caused by insufficient light during rainy seasons in agricultural solid waste treatment sites in the south, the present invention proposes a dynamic coordinated control method. By integrating the humidity fluctuations in the rainy season with the historical data of intermittent light, the offset of the microbial agent addition window is calculated to match the pile stage characteristics; based on the deep oxygen diffusion efficiency threshold and the surface volatile organic compound concentration feedback, an adaptive mapping relationship between the pile turning trigger and the microbial agent compensation is constructed; when it is monitored that the oxygen mass transfer efficiency is lower than the critical value or the bacterial community activity is abnormal, the pile turning gradient and the microbial agent weight are adjusted synchronously, and the real-time iterative control sequence is controlled by using the change in pile volume to solve the pain points such as pile overheating and oxygen mass transfer lag in high humidity environments, and finally achieve dynamic coordination of microbial agent addition and pile turning strategy to improve compost stability and degradation efficiency. In the specific implementation, it is reflected in the simultaneous combination of the historical data of external environmental humidity and light intensity to correct the discrete interval of the microbial agent addition time window, including:

[0160] 601. Extract historical data on the rate of change of external environmental humidity and the amplitude of light intensity fluctuations, and calculate a discrete interval offset of the inoculum addition time window based on the cumulative difference between the humidity and light coupling parameters in adjacent time windows. The discrete interval offset is dynamically matched with a carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the biomass.

[0161] In step 601, the humidity and light coupling parameter refers to a dynamic correlation parameter generated by fusing historical data of the external environment humidity change rate and the light intensity fluctuation amplitude, which is used to quantify the impact of environmental disturbances in adjacent time windows on the pile metabolism.

[0162] The discrete interval offset is calculated through the cumulative difference of the coupling parameters to obtain the adjustment amount of the inoculant addition time window, which dynamically matches the current carbon-nitrogen ratio imbalance threshold of the pile.

[0163] In an embodiment of the present application, first, the humidity change rate and light fluctuation amplitude data within the past 24 hours are collected by temperature and humidity sensors and light sensors. Next, the data is normalized, and the weighted sliding window method is used to generate humidity and light coupling parameters. Then, the cumulative difference of the coupling parameters in adjacent time windows is calculated. When the difference exceeds a preset threshold, the calculation of the discrete interval offset is triggered, and the offset is dynamically adjusted according to the current carbon-nitrogen ratio imbalance threshold of the pile. Finally, the carbon-nitrogen ratio of the pile product is monitored in real time by an online near-infrared spectrometer. When the carbon-nitrogen ratio deviates from the target range, the offset parameter is automatically corrected.

[0164] 602. Based on the discrete interval offset and the extreme point distribution characteristics of the surface temperature change sequence, a dynamic mapping relationship between the triggering time of the compost turning operation and the time window for adding the inoculant is constructed;

[0165] In step 602, a critical threshold of oxygen diffusion efficiency is set in the dynamic mapping relationship as a segmentation trigger condition, and the constraint boundary of the mapping relationship is updated in conjunction with the real-time feedback data of the change in volatile organic compound concentration.

[0166] In an embodiment of the present application, first, an infrared thermal imager is used to collect the surface temperature sequence of the pile, and a filtering algorithm is used to smooth the data, and the temperature extreme points are extracted to determine the potential triggering moment of the turning operation. Then, the discrete interval offset and the temperature extreme points are input into the time series prediction model, and the dynamic mapping relationship between the turning trigger moment and the microbial agent addition window is output. In this process, the real-time change data of the volatile organic compound concentration is used as a feedback coefficient to dynamically adjust the constraint boundary of the mapping relationship. Then, when the dissolved oxygen in the deep layer of the pile is lower than the critical value, the forced turning instruction is triggered, and the feedback coefficient is dynamically adjusted by the controller to ensure that the volatile organic compound concentration is within the target range. Finally, the dynamic mapping relationship is used to optimize the time window of the turning operation and the microbial agent addition, thereby improving the efficiency and stability of the composting process.

[0167] 603. When the oxygen diffusion efficiency in the deep layer of the pile is lower than the preset critical value or the surface bacterial community activity compensation coefficient deviates from the equilibrium range, the compensation weights of the incremental gradient of the pile turning operation frequency and the microbial agent injection acceleration rate are synchronously adjusted based on the dynamic mapping relationship, and the execution timing of the collaborative control instruction is iteratively updated through the real-time correction value of the oxygen diffusion efficiency based on the change in the pile volume.

[0168] In step 603, the compensation weight refers to the adjustment weight of dynamically allocating the increase in the frequency of turning the pile and the acceleration rate of microbial agent addition according to the deep oxygen mass transfer efficiency and the abnormal degree of microbial activity.

[0169] The preset critical value refers to the minimum allowable value of the deep oxygen mass transfer efficiency of the pile, which is used to determine whether the pile is in an oxygen-deficient state. It is usually set according to the composting process requirements and microbial activity requirements. For example, the compensation mechanism is triggered when the deep dissolved oxygen concentration is lower than 2 mg / L.

[0170] The volume change of the pile refers to the volume reduction or expansion of the pile due to factors such as material degradation and water evaporation during the composting process. It is monitored in real time by a three-dimensional laser scanner and is used to evaluate the changes in the internal pore structure and oxygen diffusion efficiency of the pile.

[0171] In an embodiment of the present application, first, when the oxygen mass transfer efficiency in the deep layer of the pile is lower than a preset critical value (such as the dissolved oxygen concentration is lower than 2 mg / L) or the bacterial activity deviates from the equilibrium range (such as the ATP concentration is lower than 1.2 or higher than 1.8), the compensation mechanism is triggered. Next, a fuzzy control rule library is used to output the weight ratio of the pile turning frequency increment and the microbial agent injection acceleration rate based on the oxygen mass transfer efficiency and the bacterial activity deviation. Then, a three-dimensional laser scanner is used to monitor the volume change of the pile in real time. For example, if the volume of the pile is reduced by 8% due to material degradation, a correction factor is calculated based on the regression model of volume change and oxygen diffusion efficiency, for example, the correction factor is 1.4. Finally, the execution timing of the collaborative control instructions is iteratively updated, for example, the turning interval is compressed from 6 hours to 4.2 hours to ensure that the metabolic process of the pile is stable and efficient.

[0172] Here's a specific example:

[0173] At an agricultural solid waste treatment site in southern China, continuous rain during the rainy season caused the ambient humidity to surge from 50% to 85%, light intensity to drop from 1000 lx to 200 lx, and peak surface temperature to be delayed from 2:00 PM to 4:30 PM. Due to the high humidity, oxygen transfer efficiency in the deep layers of the waste pile decreased significantly, and the dissolved oxygen concentration dropped from 3.0 mg / L to 1.5 mg / L, below the preset critical value (2 mg / L), triggering a compensation mechanism. Simultaneously, the compensation coefficient for bacterial activity deviated from the equilibrium range, with ATP concentration dropping from 1.5 to 1.1, indicating that microbial metabolic activity was suppressed.

[0174] Real-time monitoring using a 3D laser scanner revealed that the pile volume had shrunk by 8% due to material degradation and water evaporation, altering its internal pore structure and further affecting oxygen diffusion efficiency. Based on a regression model linking volume change and oxygen diffusion efficiency, a correction factor of 1.4 was calculated.

[0175] After the compensation mechanism is triggered, the system first uses a fuzzy control rule base to dynamically allocate the weighted ratio between the increase in pile turning frequency and the microbial inoculant dosage rate, based on the oxygen mass transfer efficiency and microbial activity deviation. For example, if the pile turning frequency increases from every 8 hours to every 6 hours, the microbial inoculant dosage rate increases from 0.5 L / min to 0.8 L / min, resulting in a weighted ratio of 7:3. Then, based on a correction factor of 1.4, the system compresses the execution interval of the coordinated control instructions from 6 hours to 4.2 hours, ensuring that the pile quickly recovers metabolic balance in an oxygen-deficient state.

[0176] The system also uses feedback from volatile organic compound (VOC) concentrations to adjust the triggering time for compost turning in real time. For example, a rise in VOC concentration from 800ppm to 1200ppm triggers a mandatory compost turning instruction, bringing the turning operation forward to 5:50 PM. After turning, the deep dissolved oxygen concentration gradually rises to 2.8mg / L, the surface temperature peaks at 2:30 PM, and the bacterial activity compensation coefficient returns to the equilibrium range (1.2-1.8), allowing the composting process to return to a stable state.

[0177] Through the above dynamic adjustments, the pile still maintained an efficient degradation rate in the high humidity environment of the rainy season, the carbon-nitrogen ratio fluctuation range was reduced from ±2.5 to ±0.7, and the probability of anaerobic fermentation was reduced by 67%; the composting cycle was shortened from 45 days to 32 days, and the release of volatile organic compounds was reduced by 52%, significantly improving the stability and environmental adaptability of the composting process.

[0178] This embodiment monitors environmental parameters, pile volume changes and microbial activity in real time, dynamically adjusts the microbial agent addition window, pile turning frequency and the execution timing of coordinated control instructions, effectively solving the problems of pile hypoxia, carbon-nitrogen ratio imbalance and excessive release of volatile organic compounds in the high humidity environment of the rainy season, significantly improving the composting efficiency and stability, and providing reliable technical support for the treatment of organic solid waste under complex environmental disturbances.

[0179] In order to solve the problems of carbon-nitrogen ratio imbalance, low oxygen mass transfer efficiency and poor adaptability to environmental disturbances caused by the static operation of microbial agent addition and compost turning in traditional composting process, a collaborative control method based on dynamic environmental parameter coupling feedback is proposed. This method corrects the microbial agent addition window offset by dynamically matching humidity and light historical data with pile characteristics; constructs a dynamic mapping relationship between compost turning trigger and addition based on oxygen diffusion efficiency threshold and volatile organic compound feedback; when oxygen mass transfer is insufficient or bacterial community activity is abnormal, the compost turning frequency and microbial agent rate weight are adaptively adjusted, and the real-time iterative control sequence is combined with the change in pile volume to achieve precise coordination of microbial agent addition and compost turning, thereby improving composting efficiency and stability. In specific implementation, step 104 iteratively optimizes the nonlinear correlation between the microbial agent addition rate and the compost turning operation frequency through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and outputs the effect evaluation results of the whole cycle of agricultural solid waste treatment, including:

[0180] 701. Obtaining a microbial inoculant activity threshold, a mechanical energy efficiency coefficient for compost turning, and a sudden pH drop threshold in the deep region of the compost using sensors installed in the compost pile as input parameters for the quantitative model, and generating a candidate solution set for the microbial inoculant injection rate and the compost turning frequency using the quantitative model;

[0181] In step 701, the solution set satisfies the carbon-nitrogen ratio imbalance threshold constraint and balances the weight conflict between the pollution reduction index and the carbon reduction index through the Lagrange multiplier method.

[0182] The microbial agent activity threshold refers to the minimum microbial agent concentration required for the microbial activity in the pile to achieve optimal degradation efficiency, and is used to quantify the effectiveness of the microbial agent injection rate.

[0183] The mechanical energy efficiency coefficient of pile turning refers to the degree to which the pile turning operation improves the oxygen mass transfer efficiency of the pile body, and is used to evaluate the balance between the frequency of pile turning and energy consumption.

[0184] The pH sudden drop threshold in the deep area of ​​the pile refers to when the pH value in the deep area of ​​the pile is lower than a certain critical value (such as pH <6.5), indicating that the pile may enter the anaerobic fermentation state, which is used to screen abnormal working conditions.

[0185] In this embodiment, microbial inoculant activity sensors, compost turning mechanical efficiency sensors, and pH sensors deployed within the compost pile collect real-time data on the inoculant activity threshold, compost turning mechanical efficiency coefficient, and pH drop threshold in the deep region of the compost pile. These parameters are then input into a quantitative model for the synergistic effects of pollution and carbon reduction, and a genetic algorithm is used to generate candidate solutions for the inoculant dosage rate and compost turning frequency. For example, the inoculant dosage rate ranges from 0.5 to 1.0 L / min, and the compost turning frequency ranges from every 6 to 8 hours.

[0186] 702. Calculate the partial derivatives of the objective function of the microbial agent dosage acceleration rate and the compost turning frequency in the candidate solution set, dynamically adjust the microbial agent dosage acceleration rate and the compost turning frequency by combining real-time data from near-infrared spectroscopy and gas chromatography-mass spectrometry, and generate a three-dimensional response surface representing the nonlinear correlation between the two.

[0187] In step 702, the partial derivative of the objective function refers to the local change rate of the synergistic effect of the microbial agent injection acceleration rate and the compost turning operation frequency on pollution reduction and carbon reduction in the candidate solution set, which is used to optimize the nonlinear correlation between the two.

[0188] The three-dimensional response surface refers to the three-dimensional spatial relationship between the acceleration rate of microbial agent addition, the frequency of compost turning operation and the synergistic effect of pollution reduction and carbon reduction, which is used to intuitively characterize the synergistic effect of the two.

[0189] In this example, the partial derivatives of the objective function (synergistic effects of pollution and carbon reduction) within the candidate solution set were first calculated, and the gradient descent method was used to optimize the inoculant dosage rate and compost turning frequency. Next, by combining real-time data from near-infrared spectroscopy (NIR) and gas chromatography-mass spectrometry (GC-MS), the inoculant dosage rate and compost turning frequency were dynamically adjusted to generate a three-dimensional response surface. For example, the synergistic effect was optimal when the inoculant dosage rate was 0.8 L / min and the compost turning frequency was once every seven hours.

[0190] 703. Fusing the three-dimensional response surface with the acquired UAV remote sensing and thermal infrared imaging data, using the pH sudden drop threshold in the deep layer of the pile as a constraint condition to screen abnormal operating conditions that deviate from the optimized path, and updating the discrete interval of the microbial agent addition time window;

[0191] In step 703, the drone remote sensing and thermal infrared imaging data refers to the data on the pile surface temperature distribution and material degradation status obtained by the remote sensing sensor and thermal infrared camera carried by the drone, which are used to assist in screening abnormal working conditions.

[0192] In this example, a three-dimensional response surface method was first integrated with drone remote sensing and thermal infrared imaging data to identify areas of abnormal surface temperature (e.g., temperatures > 70°C) and areas of uneven material degradation. Next, a pH drop threshold deep within the pile was used as a constraint to screen for abnormal conditions that deviated from the optimized path. For example, a pH < 6.5 triggered an update to the inoculant dosing window.

[0193] 704. Based on the updated discrete intervals, a dynamic programming algorithm is used to segmentally calculate the synergistic effect index of the pollution reduction contribution and the carbon reduction contribution, and the effect evaluation results after multiple rounds of iterative optimization are output, which include the optimal microbial agent injection acceleration rate, the frequency of pile turning operations and the synergistic effect evaluation matrix.

[0194] In step 704, the pollution reduction contribution and carbon reduction contribution refer to the contribution of the microbial agent addition and compost turning operation to reducing pollutant emissions (such as VOCs) and reducing carbon emissions (such as CO2), which are used to quantify the synergistic effect.

[0195] In this example, a dynamic programming algorithm is first used to segmentally calculate the synergistic effect index of pollution reduction and carbon reduction contributions based on the updated discrete intervals. For example, the synergistic effect index is highest when the inoculum dosage rate is 0.8 L / min and the compost turning frequency is once every 7 hours. Next, the effect evaluation results, which have been optimized through multiple rounds of iterative optimization, are output, including the optimal inoculum dosage rate, compost turning frequency, and synergistic effect evaluation matrix, to guide composting process optimization.

[0196] Here's a specific example:

[0197] At an agricultural solid waste treatment site in southern China, sustained rain during the rainy season caused the pH value in the deep layers of the pile to plummet from 7.0 to 6.3, triggering an abnormal operating condition screening mechanism. Using drone remote sensing and thermal infrared imaging data, they identified areas of abnormal surface temperature (temperatures >70°C) and areas of uneven material degradation. Based on the updated discrete intervals, a dynamic programming algorithm was used to calculate the synergistic effect index of pollution reduction and carbon reduction contributions. The optimal inoculant dosage rate of 0.8 L / min and a compost turning frequency of every seven hours were determined. The synergistic effect evaluation matrix showed a 52% reduction in VOC emissions and a 35% reduction in CO2 emissions.

[0198] In summary, the scheme of steps 701 to 704 significantly improves the synergistic efficiency of pollution reduction and carbon reduction in the composting process through sensor data acquisition, candidate solution set generation, three-dimensional response surface construction, abnormal operating condition screening and dynamic programming calculation: VOCs emissions are reduced by 52%, CO2 emissions are reduced by 35%, and the composting cycle is shortened to 32 days. It achieves precise synergistic optimization of microbial agent addition and compost turning operations, providing efficient and reliable technical support for the treatment of agricultural solid waste.

[0199] Figure 2 The present invention provides a structural diagram of a system for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste. Figure 2 As shown, the device includes:

[0200] Monitoring module 21 is used to obtain a set of environmental parameters reflecting the intensity of microbial metabolism by real-time monitoring of the temperature gradient, pH fluctuation range, and volatile organic compound concentration change within a pile of agricultural solid waste, using a mixture of livestock and poultry manure and straw as the treatment object during the treatment process;

[0201] a matching module 22 for dynamically matching the microbial agent dosage rate with the bacterial community activity attenuation curve according to the changing trend of the set of environmental parameters, wherein the microbial agent comprises a composite bacterial community of thermophilic cellulolytic bacteria and nitrogen-fixing bacteria, and the dosage is reversely compensated and adjusted based on the oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold within the pile;

[0202] The control module 23 is configured to maintain a balanced distribution of bacterial activity of the composite bacterial community between the surface and deep regions of the pile during the aerobic fermentation phase of the pile by controlling the compost turning operation in conjunction with the microbial agent dosing strategy, and to modify the discrete interval of the microbial agent dosing time window based on historical data of the external environmental humidity and light intensity;

[0203] The optimization module 24 is used to establish a quantitative model of the synergistic effect of pollution reduction and carbon reduction with the carbon-nitrogen ratio imbalance threshold as a constraint condition, so as to iteratively optimize the nonlinear correlation between the acceleration rate of the microbial agent addition and the frequency of the compost turning operation through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and output the effect evaluation results of the whole cycle of agricultural solid waste treatment.

[0204] Figure 2 The device for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste can perform Figure 1 The implementation principle and technical effects of the method for calculating the synergistic effect of pollution reduction and carbon reduction on agricultural solid waste described in the illustrated embodiment will not be elaborated on here. The specific manner in which each module and unit performs operations in the device for calculating the synergistic effect of pollution reduction and carbon reduction on agricultural solid waste in the above embodiment has been described in detail in the embodiments of the method and will not be elaborated on here.

[0205] In one possible design, Figure 2 The device for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0206] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0207] The processing component 32 is used for the above Figure 1 The embodiment provides a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste.

[0208] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0209] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0210] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0211] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0212] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0213] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0214] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The embodiment shown is a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste.

[0215] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0216] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0217] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0218] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste, characterized in that: include: In the process of agricultural solid waste treatment, a mixture of livestock and poultry manure and straw is used as the treatment object, and the temperature gradient, pH fluctuation range and volatile organic compound concentration change inside the pile composed of the treatment object are monitored in real time to obtain a set of environmental parameters reflecting the intensity of microbial metabolism; Dynamically matching the microbial agent dosage rate with the bacterial community activity attenuation curve according to the changing trend of the environmental parameter set, wherein the microbial agent comprises a composite bacterial community of thermophilic cellulose decomposing bacteria and nitrogen-fixing bacteria, and the dosage is reversely compensated and adjusted based on the oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold within the pile; During the aerobic fermentation stage of the pile, the activity distribution of the composite bacterial community in the surface and deep areas of the pile is maintained balanced through the linkage control of the pile turning operation and the microbial agent addition strategy. At the same time, the discrete interval of the microbial agent addition time window is corrected based on the historical data of the external environmental humidity and light intensity. A quantitative model of the synergistic effect of pollution reduction and carbon reduction is established with the carbon-nitrogen ratio imbalance threshold as a constraint condition, so as to iteratively optimize the nonlinear correlation between the acceleration rate of the microbial agent addition and the frequency of the compost turning operation through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and output the effect evaluation results of the whole cycle of agricultural solid waste treatment.

2. The method according to claim 1, characterized in that Also includes: Based on the distribution balance of the bacterial community activity and the phased product characteristics of the pile, the dynamic coupling coefficient of the organic matter degradation rate and the greenhouse gas emission reduction is calculated simultaneously; Based on the dynamic coupling coefficient, the nonlinear correlation between the microbial agent injection acceleration rate and the compost turning operation frequency is adjusted to optimize the effect evaluation results of the entire cycle of agricultural solid waste treatment.

3. The method according to claim 1, characterized in that The dynamically matching the microbial agent injection acceleration rate and the bacterial colony activity attenuation curve according to the change trend of the environmental parameter set includes: Decomposing the temperature gradient, pH value fluctuation range, and volatile organic compound concentration change in the environmental parameter set into a trend component and a fluctuation component, respectively, wherein the trend component is characterized by the cumulative rate of parameter change within a sliding window, and the fluctuation component is extracted by the difference between the extreme points of the parameters in adjacent windows; Based on the cumulative rate variation characteristics of the trend component, fitting the bacterial community activity decay curve of the composite bacterial community in the pile, wherein the activity decay curve is calibrated by a preset microbial agent addition experiment to determine the decay slope of the bacterial community metabolic rate under different oxygen diffusion efficiencies; Based on the attenuation slope of the bacterial colony activity attenuation curve and the extreme point distribution characteristics of the fluctuation component, a dynamic response model of the microbial agent dosage acceleration rate is established, wherein the dynamic response model sets an inverse proportional constraint relationship between the activity maintenance threshold and the attenuation slope, and introduces a correction coefficient for the oxygen diffusion efficiency due to the change in the pile volume; When the oxygen diffusion efficiency inside the stack is lower than a preset critical threshold and the carbon-nitrogen ratio imbalance threshold reaches a segmented compensation interval, a reverse compensation regulation rule based on the dynamic response model is triggered to dynamically adjust the incremental gradient of the microbial agent injection acceleration rate; The dynamic control instructions for the microbial inoculant injection rate are updated in real time through the coupling effect of the reverse compensation regulation rule and the temperature gradient difference between the surface area and the deep area of ​​the pile.

4. The method according to claim 3, characterized in that The dynamic control instructions for the microbial inoculant injection rate are updated in real time by coupling the reverse compensation regulation rule with the temperature gradient difference between the surface area and the deep area of ​​the pile, including: Layered temperature monitoring nodes are respectively set up in the surface area and deep area of ​​the pile body to obtain the surface temperature change sequence and the deep temperature change sequence, and the dynamic offset of the temperature gradient difference is calculated by the accumulated temperature difference in the sliding window; Determining a dynamic compensation coefficient in the reverse compensation adjustment rule based on the dynamic offset and a preset bacterial colony activity distribution equilibrium threshold, wherein the dynamic compensation coefficient is quadratically weighted by the correction value of the oxygen diffusion efficiency according to the change in the stack volume; Based on the correlation between the dynamic compensation coefficient and the carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the pile, a nonlinear mapping relationship between the temperature gradient difference and the microbial agent injection rate increment is constructed, and the historical fluctuation data of the external environmental humidity is introduced to discretize and calibrate the triggering time window of the mapping relationship; When the temperature gradient difference exceeds the critical interval of the activity distribution equilibrium threshold, the segmented compensation mechanism of the reverse compensation adjustment rule is activated, a dynamic control instruction for the microbial agent injection acceleration rate is generated based on the nonlinear mapping relationship, and the real-time monitoring data of the volatile organic compound concentration change of the pile is coupled to update the weight distribution of the dynamic compensation coefficient; Through the segmented compensation mechanism and the real-time feedback of the stack oxygen diffusion efficiency, the execution timing of the dynamic control instruction is iteratively adjusted, and the sliding window cumulative difference calculation period of the temperature gradient difference is synchronously corrected.

5. The method according to claim 1, wherein During the aerobic fermentation stage of the pile, the activity distribution of the composite bacterial community in the surface area and deep area of ​​the pile is maintained balanced through the linkage control of the pile turning operation and the microbial agent addition strategy, including: During the aerobic fermentation stage of the pile, a surface bacterial community activity compensation coefficient and a deep oxygen diffusion correction coefficient are calculated based on the real-time monitoring data of the temperature gradient difference between the surface area and the deep area and the change in volatile organic compound concentration, wherein the surface bacterial community activity compensation coefficient is dynamically calibrated by the cumulative temperature change rate within the sliding window and the attenuation slope of a preset bacterial community activity attenuation curve; Based on the nonlinear correlation between the surface bacterial community activity compensation coefficient and the deep oxygen diffusion correction coefficient, a collaborative control instruction for the triggering frequency of the turning operation and the microbial agent injection acceleration rate is generated to maintain the balanced distribution of the bacterial community activity of the composite bacterial community in the surface area and the deep area of ​​the pile body, wherein the weight distribution ratio of the surface and deep bacterial community activities is set in the collaborative control instruction.

6. The method according to claim 5, characterized in that The discrete interval of the microbial agent addition time window is corrected by combining historical data of external environmental humidity and light intensity, including: Extract historical data on the rate of change of external environmental humidity and the amplitude of light intensity fluctuations, and calculate the discrete interval offset of the inoculum addition time window by accumulating the difference between the humidity and light coupling parameters in adjacent time windows. The discrete interval offset is dynamically matched with the carbon-nitrogen ratio imbalance threshold of the phased product characteristics of the pile. Based on the discrete interval offset and the extreme point distribution characteristics of the surface temperature change sequence, a dynamic mapping relationship is constructed between the triggering time of the compost turning operation and the time window for adding the inoculant. In this dynamic mapping relationship, a critical threshold of oxygen diffusion efficiency is set as a segmented trigger condition, and the constraint boundary of the mapping relationship is updated by coupling with real-time feedback data on the change in volatile organic compound concentration. When the oxygen diffusion efficiency in the deep layer of the pile is lower than the preset critical value or the surface bacterial community activity compensation coefficient deviates from the equilibrium range, the compensation weights of the incremental gradient of the pile turning operation frequency and the microbial agent injection acceleration rate are synchronously adjusted based on the dynamic mapping relationship, and the execution timing of the collaborative control instruction is iteratively updated through the real-time correction value of the oxygen diffusion efficiency due to the change in the pile volume.

7. The method according to claim 1, characterized in that The nonlinear correlation between the microbial agent dosage rate and the compost turning frequency is iteratively optimized through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and the effect evaluation results of the entire cycle of agricultural solid waste treatment are output, including: The threshold value of microbial inoculant activity, the mechanical energy efficiency coefficient of compost turning, and the sudden drop threshold of pH in the deep region of the compost are obtained by sensors installed in the compost body and used as input parameters of the quantitative model, and a candidate solution set of microbial inoculant injection rate and compost turning operation frequency is generated by the quantitative model; Calculating the partial derivatives of the objective function of the microbial agent dosage acceleration rate and the pile turning frequency in the candidate solution set, dynamically adjusting the microbial agent dosage acceleration rate and the pile turning frequency by combining real-time data from near-infrared spectroscopy and gas chromatography-mass spectrometry, and generating a three-dimensional response surface representing the nonlinear correlation between the two; The three-dimensional response surface is integrated with the acquired UAV remote sensing and thermal infrared imaging data, and the abnormal operating conditions that deviate from the optimized path are screened using the pH sudden drop threshold in the deep layer of the pile as a constraint condition, and the discrete interval of the microbial agent addition time window is updated; Based on the updated discrete intervals, a dynamic programming algorithm is used to segmentally calculate the synergistic effect index of the pollution reduction contribution and the carbon reduction contribution, and output the effect evaluation results after multiple rounds of iterative optimization. The results include the optimal microbial agent addition acceleration rate, the frequency of compost turning operations and the synergistic effect evaluation matrix.

8. A system for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste, characterized by: include: A monitoring module is used to obtain a set of environmental parameters reflecting the intensity of microbial metabolism by real-time monitoring of the temperature gradient, pH fluctuation range, and volatile organic compound concentration change within a pile of agricultural solid waste, using a mixture of livestock and poultry manure and straw as the treatment object during the treatment process; a matching module for dynamically matching a microbial agent dosage rate with a bacterial community activity attenuation curve according to a changing trend of the set of environmental parameters, wherein the microbial agent comprises a composite bacterial community of thermophilic cellulolytic bacteria and nitrogen-fixing bacteria, and the dosage is reversely compensated and adjusted based on the oxygen diffusion efficiency and carbon-nitrogen ratio imbalance threshold within the pile; a control module for maintaining a balanced distribution of bacterial activity of the composite bacterial community in the surface and deep regions of the pile during the aerobic fermentation phase of the pile through the linkage control of the pile turning operation and the microbial agent dosing strategy, and for modifying the discrete interval of the microbial agent dosing time window based on historical data of the external environmental humidity and light intensity; The optimization module is used to establish a quantitative model of the synergistic effect of pollution reduction and carbon reduction with the carbon-nitrogen ratio imbalance threshold as a constraint condition, so as to iteratively optimize the nonlinear correlation between the acceleration rate of the microbial agent addition and the frequency of the compost turning operation through the quantitative model of the synergistic effect of pollution reduction and carbon reduction, and output the effect evaluation results of the whole cycle of agricultural solid waste treatment.

9. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the method for calculating the synergistic effect of pollution reduction and carbon reduction of agricultural solid waste as described in any one of claims 1 to 7 is implemented.

Images