Optimization control method and system for agricultural waste composting, medium and product

Abstract

The invention discloses an optimal control method and system for agricultural waste compost, a medium and a product, and the method comprises the steps: monitoring temperature data, ethanol concentration data, acetic acid concentration data and pH values of a plurality of preset detection regions in a target compost body; calculating a first risk index of each preset detection area; determining a first regulation and control parameter of the first preset detection area based on the first risk index; controlling a ventilation module to ventilate the first preset detection area based on the first regulation and control parameter; determining an acetification potential index of each first preset detection area; calculating a second risk index of each first preset detection area based on the acetification potential index; determining a second regulation and control parameter of the second preset detection area based on the second risk index; and controlling the pH value regulation and control module to carry out pH value regulation and control on the second preset detection area based on the second regulation and control parameter. The agricultural waste composting efficiency can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of optimization of agricultural waste composting, in particular to an optimization control method and system for agricultural waste composting, a medium and a product. BACKGROUND

[0002] With the intensive development of modern agriculture, a large amount of agricultural waste (such as crop straw, livestock and poultry manure, etc.) is generated every year. Composting is an important way to realize the resource utilization and harmlessness of these organic waste. It uses microorganisms in nature to decompose and transform organic matter into stable and efficient organic fertilizer, which is a key link in building an ecological circular agriculture.

[0003] The prior art uses multiple temperature sensors and oxygen concentration sensors inside the pile to monitor the temperature and oxygen data of the pile in real time, and uses the temperature and oxygen data to feedback control the start and stop of the ventilation module (such as a blower) and the air volume to achieve the purpose of cooling and oxygen supplementation, so as to maintain a suitable growth environment for microorganisms.

[0004] However, in the face of complex biochemical reaction paths inside the pile, due to the uneven physical properties of the materials inside the pile, local anaerobic microzones are easily formed. In these microzones, once the oxygen supply is insufficient, the metabolic pathway of microorganisms will deviate from normal aerobic decomposition, and a chain reaction of alcohol fermentation-acetic acid acidification will occur. This chain reaction will cause the pile to undergo rapid acidification, completely inhibit or even kill the beneficial microbial communities such as cellulose-decomposing bacteria that play a core role in normal composting and are adapted to neutral to weakly alkaline environments, and reduce the efficiency of agricultural waste composting. SUMMARY

[0005] The present application provides an optimization control method and system for agricultural waste composting, a medium and a product, which are used to solve the technical problem of low efficiency of agricultural waste composting caused by the chain reaction of alcohol fermentation-acetic acid acidification during the composting process.

[0006] In a first aspect of the present application, an optimization control method for agricultural waste composting is provided, which is applied to a composting device including a ventilation module and an acid-base regulation module. The method includes: monitoring temperature data, ethanol concentration data, acetic acid concentration data and pH value in a plurality of preset detection regions in a target composting pile; based on the temperature data and the ethanol concentration data, calculating a first risk index of each of the preset detection regions, the first risk index being used to represent the alcohol fermentation intensity of the preset detection region; determining a first regulation parameter of a first preset detection region based on the first risk index, the first preset detection region being the preset detection region with the first risk index greater than a fermentation intervention threshold, the first regulation parameter being used to inhibit anaerobic fermentation in the first preset detection region; controlling the ventilation module to ventilate the first preset detection region based on the first regulation parameter; determining a potential acetification index of each of the first preset detection regions based on the ethanol concentration data, the acetic acid concentration data and the pH value, the potential acetification index being used to represent a fermentation activity of conversion from ethanol to acetic acid in the first preset detection region; calculating a second risk index of each of the first preset detection regions based on the potential acetification index, the second risk index being used to represent an acetic acid accumulation degree of the first preset detection region; determining a second regulation parameter of a second preset detection region based on the second risk index, the second preset detection region being the first preset detection region with the second risk index greater than a pH intervention threshold, the second regulation parameter being used to adjust the pH of the second preset detection region; controlling the pH regulation module to regulate the pH of the second preset detection region based on the second regulation parameter.

[0007] Optionally, a first risk index of each of the preset detection regions is calculated based on the temperature data and the ethanol concentration data, specifically including: establishing a two-dimensional plane coordinate system with temperature as the abscissa and ethanol concentration as the ordinate, determining the temperature data and the ethanol concentration data of a target time point in a first preset time period as data points, and mapping a plurality of the data points to the two-dimensional plane coordinate system to obtain a temperature-ethanol state trajectory curve, the target time point being any time point in the first preset time period; calculating a deviation degree value of the temperature-ethanol state trajectory curve from a preset standard state region, the preset standard state region being a paired range of temperature and ethanol concentration in an aerobic fermentation process; calculating a deviation rate of the temperature-ethanol state trajectory curve from the preset standard state region, and calculating the first risk index based on the deviation degree value and the deviation rate.

[0008] Optionally, a deviation rate of the temperature-ethanol state trajectory curve from the preset standard state region is calculated, and the first risk index is calculated based on the deviation degree value and the deviation rate, specifically including: calculate a first state change vector between a first data point corresponding to a first time point and a second data point corresponding to a second time point, the first time point and the second time point being adjacent time points within the first preset time period; calculate a second state change vector between the second data point and a third data point corresponding to a third time point, the third time point being a time point adjacent to the second time point and after the second time point within the first preset time period; vector sum the first state change vector and the second state change vector to obtain a third state change vector, the third state change vector being used to represent an average state transition trend during the period from the first time point to the third time point; calculate a state deviation vector based on the second data point and a preset standard state center coordinate, the state deviation vector being used to represent a deviation direction of the temperature-ethanol state trajectory curve relative to the standard state center coordinate at the second time point; calculate a dot product of the third state change vector and the state deviation vector, when the dot product is greater than zero, determine that the change trend of the temperature-ethanol state trajectory curve is deviating from the standard state center coordinate, and determine the modulus value of the third state change vector as a deviation rate; multiply the deviation degree value and the deviation rate to obtain the first risk index.

[0009] Optionally, based on the first risk index, a first regulation parameter of a first preset detection area is determined, specifically including: calculate the difference between the first risk index of each first preset detection area and the fermentation intervention threshold, calculate the ratio of the difference and the fermentation intervention threshold to obtain a risk over-standard rate; determine the first preset detection area with the largest risk over-standard rate as a master control point, and determine the risk over-standard rate of the master control point as a master control risk rate; within a preset range of the master control point, count the number of detection areas of the first preset detection area except the master control point, calculate the ratio of the number of detection areas and the number of all first preset detection areas to obtain a risk concentration degree, and there are at least three first preset detection areas in the preset range except the master control point; calculate the product of the master control risk rate and the risk concentration degree to obtain a regional regulation coefficient; determine the first regulation parameter based on the regional regulation coefficient and the risk over-standard rate.

[0010] Optionally, the first regulation parameter is determined based on the regional regulation coefficient and the risk over-standard rate, specifically including: An average of the first risk over-standard rate, the second risk over-standard rate and the third risk over-standard rate is calculated to obtain a neighborhood risk value, the first risk over-standard rate, the second risk over-standard rate and the third risk over-standard rate being the risk over-standard rates corresponding to the first preset detection region in a preset range, except the main control point, sorted from large to small. A product of the area regulation coefficient and the neighborhood risk value is multiplied by a preset reference ventilation amount to obtain the first regulation parameter.

[0011] Optionally, based on the ethanol concentration data, the acetic acid concentration data and the pH value, a vinegarization potential index of each first preset detection region is determined, specifically including: Based on the ethanol concentration data and the acetic acid concentration data, an ethanol concentration decrease amount and an acetic acid concentration increase amount of the first preset detection region in a second preset time period are calculated respectively; A ratio of the acetic acid concentration increase amount to the ethanol concentration decrease amount is calculated to obtain an instantaneous conversion coefficient; A pH value decrease rate of the first preset detection region in the second preset time period is calculated; When the instantaneous conversion coefficient is greater than a preset conversion threshold value, and the pH value decrease rate is greater than a preset decrease rate threshold value, it is determined that the first preset detection region is in an acidification acceleration state; A first duration of the acidification acceleration state is counted, and a product of the first duration and the instantaneous conversion coefficient is determined as the vinegarization potential index.

[0012] Optionally, based on the vinegarization potential index, a second risk index of each first preset detection region is calculated, specifically including: A ratio of the instantaneous conversion coefficient to a preset conversion standard value is calculated to obtain a standard conversion coefficient, and a ratio of the pH value decrease rate to a preset decrease standard value is calculated to obtain a standard pH value decrease rate; A product of the standard conversion coefficient and the standard pH value decrease rate is calculated to obtain an acidification expansion factor; A temperature fluctuation amplitude of the first preset detection region is analyzed, and when the temperature fluctuation amplitude is greater than a preset temperature fluctuation threshold value, it is determined that the first preset detection region is in a temperature unstable state; A second duration of the temperature unstable state is counted, and a product of the second duration and the acidification expansion factor is determined as the second risk index.

[0013] In a second aspect, the embodiments of the present application provide an agricultural waste compost optimization control system, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is configured to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors are configured to invoke the computer instructions to enable the agricultural waste compost optimization control system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0014] In a third aspect, the embodiments of the present application provide a computer readable storage medium comprising instructions which, when executed on an agricultural waste compost optimization control system, cause the agricultural waste compost optimization control system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0015] In a fourth aspect, the embodiments of the present application provide a computer program product comprising instructions which, when executed on an agricultural waste compost optimization control system, cause the agricultural waste compost optimization control system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0016] In summary, the one or more technical solutions provided by the present application have at least the following technical effects or advantages: 1. By monitoring the temperature, ethanol concentration, acetic acid concentration and pH value of the multiple preset detection regions of the pile in real time, the high-risk regions in which alcohol fermentation and acetic acid accumulation may occur inside the pile can be accurately identified, and the first preset detection region in which the alcohol fermentation intensity is high, i.e., there is an anaerobic fermentation risk, can be distinguished based on the first risk index, and then the first control parameter for inhibiting the fermentation behavior can be determined, and the ventilation module can be controlled to perform directional ventilation intervention on the region, thereby blocking the anaerobic metabolic path deviation caused by insufficient oxygen supply from the source; further, in the first preset detection region, the acetic potential index can be calculated by comprehensively considering the ethanol concentration, acetic acid concentration and pH value, and the second risk index can be derived accordingly, so as to identify the second preset detection region in which there is an acid accumulation risk due to the conversion of ethanol into acetic acid, and the second control parameter for adjusting the acid-base environment thereof can be determined, and the pH value adjustment of the acid-base regulation module on the target region can be controlled, thereby effectively inhibiting the acidification trend of the local pile, protecting the survival environment of the key aerobic microorganisms such as acid-sensitive cellulolytic bacteria, avoiding the inhibition or death of the activity thereof, and ensuring the stability of the microbial community structure and the continuous aerobic operation of the metabolic path in the composting process, thereby overcoming the technical problem of low composting efficiency caused by the alcohol fermentation-acidification chain reaction due to local anaerobic in the prior art, and improving the agricultural waste composting efficiency.

[0017] 2、By mapping the multiple sets of temperature and ethanol concentration data points of the target composting area in the first preset time period in the two-dimensional temperature-ethanol coordinate system, a continuously changing state trajectory curve is formed, which not only intuitively reflects the fermentation evolution path of the area in the time dimension, but also accurately quantifies the static deviation between the current state and the ideal aerobic fermentation state by calculating the deviation degree value of the trajectory curve relative to the standard state area of aerobic fermentation. Further, by introducing the analysis method of state change vector, the state change trend between consecutive time points is extracted, and the average state transfer vector is constructed. The deviation vector of the current state relative to the center of the standard state is analyzed by dot product, so as to judge whether the trajectory change trend is away from the standard state area, and determine the deviation rate. When the deviation trend is confirmed to be away from the aerobic standard state, the deviation degree value is multiplied by the deviation rate to obtain the first risk index which dynamically represents the risk of fermentation abnormality. Not only the static deviation is considered, but also the dynamic evolution feature of the state change trend is integrated, making the detection of local anaerobic fermentation risk more timely and accurate, so that the abnormal fermentation area can be identified earlier and more accurately, providing a scientific basis for subsequent ventilation intervention, improving the response speed of the composting process to abnormal fermentation state, and further enhancing the intelligence and refinement level of the environmental regulation of the pile.

[0018] 3、By difference and normalization processing of the first risk index of all first preset detection areas and the fermentation intervention threshold, a quantifiable risk over-standard rate is obtained, so as to identify the main control point with the most serious fermentation abnormality, and take its risk over-standard rate as the main control risk rate. Further, combined with the distribution density of the abnormal detection areas in the preset range around the main control point, the risk concentration degree is calculated, which effectively reflects the spatial aggregation degree of abnormal risk in the pile. By multiplying the main control risk rate and the risk concentration degree, the regional regulation coefficient is formed, which comprehensively reflects the severity of the current abnormal risk and its spatial diffusion trend. On this basis, by extracting the top three detection areas in the risk over-standard rate in the neighborhood of the main control point, and calculating their average value, the neighborhood risk value is obtained, which further reflects the risk gradient change trend of the abnormal area in space. Finally, the regional regulation coefficient and the neighborhood risk value are multiplied, and the preset benchmark ventilation volume is weighted to obtain the first regulation parameter, which realizes the dynamic response of the overall risk level of the main control area and its surrounding area and the fine setting of the ventilation volume. Not only the quantitative identification and grade division of the risk area in the pile are realized, but also the adaptive and high-response regulation parameter generation mechanism is established by coupling the factors of spatial aggregation and local risk intensity, so that the ventilation regulation is no longer dependent on single-point data, but based on multi-point cooperation and regional linkage for intervention, effectively improving the identification accuracy and regulation efficiency of local anaerobic fermentation of the composting system, and significantly enhancing the scientificity, rationality of ventilation regulation and stability of the overall composting environment. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 is a flowchart of an agricultural waste composting optimization control method in an embodiment of the present application; Figure 2 is a structural diagram of an agricultural waste composting optimization control system provided in an embodiment of the present application.

[0020] Legend: 201, central processing unit; 202, read-only memory; 203, random access memory; 204, bus; 205, input / output interface; 206, input part; 207, output part; 208, storage part; 209, communication part; 210, drive; 211, detachable medium. DETAILED DESCRIPTION

[0021] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in conjunction with the drawings in the embodiments of the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments.

[0022] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0023] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used for description purposes only, and should not be interpreted as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more of the features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0024] Figure 1 is a flowchart of an agricultural waste composting optimization control method in an embodiment of the present application.

[0025] Referring to Figure 1 , the agricultural waste composting optimization control method in an embodiment of the present application is applied to a composting device, and the composting device includes a ventilation module and an acid-base degree control module. The composting device can be a static fermentation system, a tank turning system, a closed fermentation cabin, an air blowing composting system, and the like, and the specific structure can be determined according to the application scene.

[0026] The ventilation module is used for adjusting the oxygen supply state in the heap body, and generally includes a fan, a wind pipe, an adjustable air valve, an air distributor and the like, can realize directional air supply and ventilation intensity control of the whole heap body, and the ventilation mode can be positive pressure air supply, negative pressure air exhaust or intermittent pulse air supply, and the like, aims to intervene in the anaerobic fermentation trend and improve the aerobic fermentation efficiency.

[0027] The pH value control module is used for accurately adjusting the abnormal pH value area in the heap body, and controls the pH value to be maintained in a range suitable for microbial fermentation. The module can include an alkaline material adding device, a liquid alkali spraying system, a pH sensor, a nozzle positioning system and an automatic control unit, and can adjust the pH value by spraying alkali (such as sodium hydroxide solution and sodium carbonate liquid), and can also realize slow-release neutralization adjustment by adding solid alkaline conditioner (such as slaked lime and wood ash).

[0028] It should be noted that the structure, arrangement form, module composition and implementation mode of the composting device are not specifically limited, and can be freely selected according to different types of agricultural waste, composting scale and production process, as long as the functions of data acquisition, risk identification and environmental control in the method are realized. The composting device can be fixed or mobile, and can also be integrated into an intelligent processing platform, and is used for various application scenes such as field planting base, organic fertilizer production line and rural resource utilization center.

[0029] Figure 1 The agricultural waste composting optimization control method in the embodiment of the application comprises: S101, monitoring temperature data, ethanol concentration data, acetic acid concentration data and pH value of a plurality of preset detection areas in the target composting heap body; Step S101 is to obtain key parameters that can reflect the metabolic state of microorganisms and the evolution trend of fermentation path in the composting process, so as to provide real-time and accurate data support for subsequent risk assessment and control strategy. The technical features corresponding to each monitoring data have clear physical or chemical meaning. Among them, the temperature data are mainly used to reflect the microbial activity level and heat release intensity in the heap body, which is the first index for measuring whether the aerobic fermentation is normal; the ethanol concentration data reflect whether there is an anaerobic metabolic path deviation in the heap body. Under the condition of insufficient oxygen supply, part of the microorganisms will convert sugar substances into ethanol, resulting in alcohol fermentation in the heap body, which is an important index for judging the local anaerobic state; the acetic acid concentration data are used to characterize whether the process of ethanol being oxidized to acetic acid is active. This process belongs to the next stage of the chain reaction of alcohol fermentation, and once it accumulates in excess, it will cause the pH value of the heap body to drop sharply; the pH value is used to comprehensively reflect the change of the acid-base environment of the heap body, which is an important environmental factor affecting the microbial community structure and metabolic path selection.

[0030] To realize the real-time monitoring of the above-mentioned multiple parameters, a plurality of spatial positions in the composting heap body are pre-divided as preset detection areas, and a set of composite sensing units are arranged in each detection area. The sensing unit includes a thermistor temperature sensor, an electrochemical ethanol concentration sensor, an electric conductivity or gas absorption type acetic acid concentration sensor, and a pH electrode sensor. Among them, the temperature sensor selects NTC type thermistor with fast response and high humidity resistance, which can sense the local thermal environment change of the heap body in real time; the ethanol sensor generally adopts electrochemical detection principle based on solid-state electrolyte or metal oxide semiconductor, generates electric signal through oxidation-reduction reaction of ethanol molecules on the electrode surface, and then calculates the ethanol concentration; the acetic acid monitoring can use high selectivity gas sensitive element or liquid sampling combined with ion selective electrode to realize real-time detection of the accumulation trend of fermentation by-products; the pH sensor adopts glass electrode or solid electrode structure, and uses the relationship between hydrogen ion activity and potential to obtain the local pH level of the heap body.

[0031] The acquisition process is realized by an embedded data acquisition terminal, and the system periodically acquires the sensor data of each detection area and transmits the data to the central processing unit through a wireless communication module (such as LoRa, NB-IoT, etc.). In order to ensure the stability and accuracy of the data, the acquisition system sets a signal calibration mechanism and a data filtering algorithm to filter out abnormal values caused by transient interference or sensor drift.

[0032] By establishing a monitoring network at multiple distributed points of the heap body, not only can the multi-dimensional and real-time dynamic monitoring of the whole composting process be realized, but also the space-time state mapping of the heap body can be constructed, which provides a high-resolution data basis for subsequent risk index calculation, fermentation state identification and control strategy formulation.

[0033] S102. Based on temperature data and ethanol concentration data, calculate the first risk index for each preset detection area. The first risk index is used to characterize the alcohol fermentation intensity of the preset detection area. The purpose of step S102 is to identify and quantify the intensity of potential alcohol fermentation in localized areas based on temperature and ethanol concentration data from pre-defined detection zones within the compost pile, thereby providing a preliminary basis for determining whether ventilation intervention is necessary. Since alcohol fermentation typically occurs under localized hypoxic conditions and is an early signal of the pile transitioning from an aerobic to an anaerobic state, constructing a risk assessment model that dynamically reflects the relationship between temperature and ethanol concentration can more accurately identify abnormal fermentation trends. Specifically, this can include steps S1021-S1023: S1021. Establish a two-dimensional plane coordinate system with temperature as the horizontal axis and ethanol concentration as the vertical axis. Determine the temperature data and ethanol concentration data corresponding to the target time point within the first preset time period as data points, and map multiple data points to the two-dimensional plane coordinate system to obtain a temperature-ethanol state trajectory curve. The target time point is any time point within the first preset time period. In step S1021, a two-dimensional coordinate system is established with temperature as the abscissa and ethanol concentration as the ordinate. The purpose is to construct a state-space map that can intuitively reflect the dynamic changes in the fermentation state within the pile. Temperature and ethanol concentration are two key parameters reflecting the intensity of microbial metabolism and the selection of fermentation pathways, respectively. By combining them to form state points, the fermentation behavior of the pile at different time points can be effectively captured. Temperature, as a direct result of microbial activity, characterizes the release of metabolic heat; while ethanol concentration is a typical representative of anaerobic fermentation products, indicating whether a metabolic shift occurs in the pile under hypoxic conditions. Therefore, mapping these two parameters to a two-dimensional coordinate system not only displays their numerical changes but also reveals the evolutionary trend of their coupling relationship over time.

[0034] In the specific implementation process, the system sets a first preset time period, such as the past 24 hours or 48 hours, as the analysis window. Within this time period, temperature data and ethanol concentration data are acquired from multiple preset detection areas at fixed time intervals (such as every 15 minutes or every 30 minutes). Each time point corresponds to a pair of temperature and ethanol concentration values, called a data point. For example, if the temperature of a detection area is 58°C and the ethanol concentration is 0.45% at a certain time point, then the data point is (58, 0.45). This data point is mapped onto a two-dimensional coordinate system with temperature as the X-axis and ethanol concentration as the Y-axis, serving as the state point at that time point.

[0035] With the passage of time, all data points in this time period are connected in time sequence in the coordinate system to form a continuous trajectory curve, i.e. the temperature-ethanol state trajectory curve, which can dynamically reflect the fermentation state change path of the pile in the detection area. If the trajectory is always in an area, it means that the pile state is relatively stable; if the trajectory deviates obviously or deviates to the high ethanol direction, it may mean that insufficient oxygen supply occurs locally and the microbial metabolic path tends to anaerobic conversion.

[0036] For example, in a detection area, 24 data points are continuously collected in the past 12 hours, and after being mapped into a two-dimensional coordinate system respectively, it is found that the trajectory curve gradually deviates from the initial (55, 0.2) to (60, 0.5), indicating that the temperature rise in this area is accompanied by ethanol accumulation, and there may be a tendency of local anaerobic fermentation. The identification of this trend depends on the overall trend of the trajectory curve, not just the abnormality of a single point, so the trajectory construction can more comprehensively reflect the change of fermentation state, providing necessary data basis and visual basis for subsequent calculation of deviation degree value and deviation rate.

[0037] S1022, calculate the deviation degree value of the temperature-ethanol state trajectory curve from the preset standard state area, and the preset standard state area is the paired range of temperature and ethanol concentration in the aerobic fermentation process; The preset standard state area refers to the reasonable pairing range of pile temperature and ethanol concentration under normal aerobic fermentation conditions, which is usually obtained based on a large amount of experimental data or normal operation data in historical composting process. For example, in the active aerobic fermentation stage, the pile temperature is usually maintained at 55-65℃, and the ethanol concentration should be less than 0.3%, so this range can be defined as a closed area in the two-dimensional temperature-ethanol coordinate system, such as an elliptical envelope area or a rectangular judgment area, which is called a standard state area.

[0038] In the specific implementation process, according to the temperature-ethanol state trajectory curve constructed in step S1021, it is regarded as a continuous data point path. The system judges each data point one by one to analyze whether it falls within the standard state area. If the data point falls outside the area, it means that the state at this time point has deviated from the ideal condition of aerobic fermentation, which needs to be quantitatively evaluated. For this purpose, the system uses a spatial distance algorithm to calculate the minimum Euclidean distance from the data point to the boundary of the standard state area as the deviation value of the point. Then the deviation values of all data points outside the standard area in the whole time period are accumulated or weighted averaged to obtain the deviation degree value of the detection area in the time period.

[0039] For example, assume that the standard state region is defined as a rectangular region with temperature between 55-65℃ and ethanol concentration less than 0.3%, and a detected region has 8 out of 24 data points in the past 12 hours falling outside the region, one of which is (62, 0.45) with the shortest Euclidean distance to the boundary being 0.15. Calculate the deviation distance for each of the 8 points and take the average, assume the final average deviation value is 0.12, then this value is the average deviation degree of the current temperature-ethanol state trajectory curve relative to the standard state region. In this way, the abstract state trajectory can be converted into a quantifiable deviation degree value, so that the system can objectively identify whether the fermentation state has entered an abnormal state, and provide the necessary static criterion for subsequent trend judgment and risk index calculation.

[0040] S1023, calculate the deviation rate of the temperature-ethanol state trajectory curve from the preset standard state region, and calculate the first risk index based on the deviation degree value and the deviation rate.

[0041] The core purpose of step S1023 is to introduce the judgment dimension of dynamic change trend on the basis of static judgment of deviation degree, so as to comprehensively evaluate whether the current detection area exists the risk of continuously developing to abnormal state. Since the composting process has strong time evolution characteristics, a single deviation degree value can only reflect the abnormal degree of instantaneous state, and if the directionality and speed of state change are not considered, potential fermentation trend abnormality may be missed. Therefore, by constructing a state change vector, the state transition trend between consecutive time points is extracted, and the angle relationship between the trend and the current state deviation direction is combined to judge whether the fermentation state is accelerating deviation from the standard state, to determine the deviation rate, and to multiply it by the deviation degree value to quantify a first risk index, so that the risk assessment is more forward-looking and time-efficient. Specifically, it can include the following steps: calculating a first state change vector between a first data point corresponding to a first time point and a second data point corresponding to a second time point, the first time point and the second time point being adjacent time points within the first preset time period; calculating a second state change vector between the second data point and a third data point corresponding to a third time point, the third time point being a time point adjacent to the second time point after the second time point within the first preset time period; performing vector summation on the first state change vector and the second state change vector to obtain a third state change vector, the third state change vector being used to represent the average state transition trend during the period from the first time point to the third time point; calculating a state deviation vector based on the second data point and a preset standard state center coordinate, the state deviation vector being used to represent the deviation direction of the temperature-ethanol state trajectory curve relative to the standard state center coordinate at the second time point; calculating the dot product of the third state change vector and the state deviation vector, when the dot product is greater than zero, determining that the change trend of the temperature-ethanol state trajectory curve is deviating from the standard state center coordinate, and determining the modulus value of the third state change vector as the deviation rate; multiplying the deviation degree value and the deviation rate to obtain the first risk index.

[0042] In the specific implementation process, the first state change vector between the first data point corresponding to the first time point and the second data point corresponding to the second time point is calculated, so as to obtain the joint change trend of the temperature and the ethanol concentration of the heap in a short time. Since the temperature and the ethanol concentration jointly constitute a two-dimensional description space of the fermentation state of the heap, the data points between two adjacent time points can be regarded as two-dimensional coordinate points, and the directed line segment connecting the two points is the state change vector, which reflects the change direction and change amplitude of the state of the heap in the time period. In the specific implementation, the system extracts the data point pair corresponding to the first time point and the second time point adjacent to the first time point from the collected temperature-ethanol data sequence, for example, the first point is (58℃, 0.35%), and the second point is (59℃, 0.40%). The coordinate difference operation is performed on the two points, that is, (59-58, 0.40-0.35)=(1, 0.05), and the result is the first state change vector, which indicates that the temperature of the detection area increases by 1℃ and the ethanol concentration increases by 0.05% in this time period.

[0043] The second state change vector between the second time point and the third time point is calculated, and the extraction of the state change trend is further continued. The purpose of this operation is to provide continuous data support for subsequent construction of the average state trend. As in the previous step, the third time point is the adjacent time point after the second time point, and the corresponding data point pair can also be represented as a two-dimensional coordinate, for example, (60℃, 0.45%), and the change vector compared with the second point (59℃, 0.40%) is (1, 0.05). In this way, the trend of the state change can be represented by the combination of two adjacent vectors, avoiding the interference of single-point fluctuations on the overall judgment.

[0044] In order to extract a more representative trend direction, the first state change vector and the second state change vector are summed to obtain the third state change vector, so as to construct the average state transition trend from the first time point to the third time point. In a mathematical sense, the sum of two vectors is a new vector representing a weighted superposition of the overall direction. Based on the example, if the two previous vectors are both (1, 0.05), the sum is (2, 0.1), which can be further standardized to the average change vector (1, 0.05) per unit time. The vector not only represents the total offset direction of the state of the heap, but also embodies the cooperative change trend of the temperature and the ethanol concentration.

[0045] Based on the difference between the second data point pair and the preset standard state center coordinates, a state deviation vector is calculated to determine the direction of the current pile state's deviation relative to the ideal aerobic fermentation state. The standard state center coordinates refer to the geometric center of the standard state region, usually taken as the average of its temperature and ethanol concentration, for example, (60℃, 0.2%). If the second data point is (59℃, 0.40%), then the state deviation vector is (59−60, 0.40−0.2)=(-1, 0.2). This vector points to the direction of the pile state's deviation relative to the center of the standard region, and is used to subsequently determine whether the deviation trend is increasing.

[0046] Calculating the dot product of the third state change vector and the state deviation vector can determine whether the state change of the heap continues to expand along the deviation direction. When the angle between the two vectors is less than 90 degrees, their dot product is positive, indicating that the state change trend is consistent with the deviation direction, that is, the heap is further deviating from the standard state; conversely, if the dot product is negative, it indicates that the state change direction tends to return to the standard state. When the dot product is positive, the magnitude of the third state change vector, i.e., its vector length, can be determined as the deviation rate. For example, if the third state change vector is (1, 0.05), its magnitude is... This indicates that the state of the heap is shifting in the abnormal direction at a rate of approximately 1.001 per unit time.

[0047] Multiplying the calculated deviation value by the deviation rate yields the first risk index, enabling a quantitative assessment of fermentation anomalies. The deviation value reflects the extent of deviation from the current state, while the deviation rate reflects whether the deviation trend is continuing. Combining these two values ​​constructs a composite risk index that simultaneously reflects spatial distance and temporal variation characteristics. For example, if the deviation value of the detected area is 0.15 and the deviation rate is 1.001, then the first risk index is 0.15 × 1.001 ≈ 0.15015. The larger this value, the higher the intensity of alcohol fermentation in that area, requiring priority ventilation intervention. Through these steps, not only can the abnormal state of local compost piles be accurately identified, but their changing trends can also be grasped in real time, providing a highly responsive and precise dynamic control basis for the composting process.

[0048] S103. Determine the first control parameter of the first preset detection area based on the first risk index. The first preset detection area is a preset detection area where the first risk index is greater than the fermentation intervention threshold. The first control parameter is used to inhibit anaerobic fermentation in the first preset detection area. In step S103, the first control parameter for the first preset detection area is determined based on the first risk index. The purpose is to further classify and finely intervene in these abnormal areas after identifying those with a strong tendency for alcohol fermentation within the compost pile. Since the first risk index may differ between different detection areas, and abnormal areas may be dispersed or clustered, it is necessary to comprehensively consider both risk intensity and spatial distribution characteristics to ensure that ventilation intervention is both targeted and coordinated. Therefore, this method introduces parameters such as risk exceedance rate, main control point identification, risk concentration calculation, and regional control coefficient. These parameters quantify the potential impact of each abnormal area on the overall fermentation state of the compost pile, and determine the optimal first control parameter accordingly, thereby achieving precise and differentiated ventilation management for abnormal areas of alcohol fermentation. This may include steps S1031-S1035: S1031. Calculate the difference between the first risk index and the fermentation intervention threshold for each first preset detection area, and calculate the ratio of the difference to the fermentation intervention threshold to obtain the risk exceedance rate; The purpose of step S1031 is to classify the areas identified as abnormal across multiple detection zones into risk levels. Although the first risk index of these areas all exceeds the fermentation intervention threshold, the degree of exceedance differs, and the intensity of interference with the composting process also varies. Therefore, it is necessary to standardize the exceedance range. In practice, the system iterates through all the first preset detection zones, obtains their first risk index one by one, and calculates the difference between the risk index and the threshold using a set fermentation intervention threshold (e.g., 0.8) as a benchmark. This difference is then divided by the threshold itself to obtain the risk exceedance rate. The fermentation intervention threshold can be a critical risk value derived from statistical analysis based on a large amount of composting experimental data, effectively predicting that the intensity of alcohol fermentation will significantly affect composting efficiency. For example, if the first risk index of a detection zone is 1.0, its exceedance difference is 0.2, and the risk exceedance rate is 0.2 / 0.8 = 0.25. This value can serve as a standardized quantitative indicator of the degree of abnormality in the area, providing a basis for subsequently determining the main control point and the intensity of regulation.

[0049] S1032. The first preset detection area with the highest risk exceedance rate is determined as the main control point, and the risk exceedance rate of the main control point is determined as the main control risk rate. The primary control point is determined by identifying the first pre-set detection area with the highest risk exceedance rate, and its risk exceedance rate is used as the primary control risk rate. The aim is to select the core risk area in the current reactor structure that requires priority intervention. Establishing the primary control point not only helps to accurately locate the center of fermentation anomalies but also serves as a reference point for subsequent spatial clustering assessments. Spatially, the primary control point represents the area with the most significant risk and plays a guiding role in the control strategy. In practice, the system compares the risk exceedance rates of all first pre-set detection areas and selects the area with the highest value as the primary control point. For example, if the risk exceedance rate of an area is 0.35, which is higher than all other areas, then that area is marked as the primary control point, and its primary control risk rate is 0.35.

[0050] S1033. Within the preset range of the main control point, count the number of detection areas in the first preset detection area other than the main control point, calculate the ratio of the number of detection areas to the total number of the first preset detection areas, and obtain the risk concentration. There are at least 3 first preset detection areas in the preset range other than the main control point. Centered on the identified master control point, the system counts the number of first-preset detection areas (excluding the master control point) within a preset spatial range (e.g., a radius of 1 or 2 meters). The ratio of these first-preset detection areas to the total number of all first-preset detection areas is calculated to obtain the risk concentration index. This concentration index measures whether the master control point is located in a highly risk-concentrated area, and its significance lies in identifying whether the problem is a localized isolated phenomenon or a regional anomaly. The preset range can be flexibly adjusted according to the stack size and sensor density to ensure the representativeness of the statistical results. The system locates all first-preset detection areas using a spatial coordinate system, performs a spatial query within the set range around the master control point, excludes the master control point itself, and counts the number of remaining first-preset detection areas. If this number is not less than 3, it is included in the concentration calculation. For example, if there are 4 other first-preset detection areas within 2 meters of the master control point, and there are currently a total of 10 first-preset detection areas, the risk concentration index is 4 / 10 = 0.4, indicating a certain degree of risk concentration around the master control point.

[0051] S1034. Calculate the product of the main control risk rate and the risk concentration to obtain the regional control coefficient; In step S1034, the product of the main control risk rate and the risk concentration is calculated to obtain the regional control coefficient. This coefficient comprehensively reflects the risk intensity of the main control point and the concentration of risk distribution in its surrounding area, and is a key parameter for formulating ventilation control strategies. This product method couples information from two dimensions into a single indicator, making subsequent control decisions more efficient and quantifiable. The larger the regional control coefficient, the higher the risk level in the area, and the more spatially clustered the fermentation anomaly, requiring a priority increase in ventilation intervention. Continuing the example above, if the main control risk rate is 0.35 and the concentration is 0.4, then the regional control coefficient is 0.35 × 0.4 = 0.14. This value will serve as an important reference for determining the first control parameter, used to adjust the airflow or frequency of the ventilation module to achieve localized enhanced intervention and prevent the spread of abnormal conditions.

[0052] S1035. Determine the first control parameter based on the regional control coefficient and the risk exceedance rate.

[0053] Step S1035, based on identifying the main control risk area and quantifying its risk intensity and spatial clustering characteristics, calculates a ventilation control value that is both locally responsive and holistically coordinated, taking into account the risk situation of surrounding abnormal areas. Since in actual composting processes, single-point anomalies are often correlated with their neighboring areas, control decisions cannot be made solely based on the risk level of the main control point itself. Instead, the exceedance of standards at other high-risk points in its vicinity should be comprehensively considered to improve the accuracy of intervention and the effectiveness of group response. Specifically, this may include the following steps: Calculate the average of the first risk exceedance rate, the second risk exceedance rate, and the third risk exceedance rate to obtain the neighborhood risk value. The first risk exceedance rate, the second risk exceedance rate, and the third risk exceedance rate are the risk exceedance rates of the top three first preset detection areas, excluding the main control point, within the preset range, sorted from largest to smallest. The first control parameter is obtained by multiplying the product of the regional control coefficient and the neighborhood risk value by the preset benchmark ventilation volume.

[0054] To further enhance the local responsiveness and risk adaptability of the control strategy, the system, based on the established control point and its regional control coefficient, introduces the calculation of a neighborhood risk value as a comprehensive quantification of the risk environment surrounding the control point. This neighborhood risk value is calculated by extracting the top three areas with the highest risk exceedance rates from all first-preset detection areas within the control point's preset range (excluding itself), and calculating the average of their exceedance rates. This reflects the overall risk level of high-risk points within the local area. The logic behind this step is that although the control point is currently the highest-risk point, the existence of multiple high-risk areas around it indicates that the anomaly in this local area is not an isolated phenomenon but possesses a certain degree of systemicity and persistence, thus requiring a stronger response during control measures. In practice, the system first filters out other first-preset detection areas within the spatial range of the main control point, sorts them from high to low according to their respective risk exceedance rates, selects the risk exceedance rates of the top three areas, for example, 0.22, 0.18, and 0.16, and calculates their average value as the neighborhood risk value: (0.22+0.18+0.16) / 3=0.1867. This value will serve as an important parameter reflecting the degree of risk resonance around the main control point.

[0055] After obtaining the neighborhood risk value, the system multiplies the neighborhood risk value with the regional control coefficient calculated in the previous step, and then multiplies the result by a preset baseline ventilation volume to determine the final first control parameter. This parameter is directly used to guide the operating intensity of the ventilation module. The core principle of this calculation method is to couple the assessment of the main control point risk and the neighborhood risk, then dynamically amplify or reduce it through the control coefficient, and finally map it to the actual control quantity, i.e., the ventilation volume. The baseline ventilation volume is a basic ventilation parameter set by the system based on the reactor properties, equipment performance, and ventilation requirements, for example, 1.5 m³ / min. It is used to ensure that the minimum aerobic fermentation conditions are maintained under risk-free or low-risk conditions, and the final calculated first control parameter is a risk-weighted adjustment based on this. For example, if the regional control coefficient is 0.14, the neighborhood risk value is 0.1867, and the baseline ventilation volume is 1.5 m³ / min, then the first control parameter is 0.14 × 0.1867 × 1.5 ≈ 0.0392 m³ / min. The system will adjust the local air volume output of the ventilation module in the main control point area accordingly, thereby achieving precise intervention in high-risk areas, reducing the risk of alcohol fermentation diffusion, and improving the overall stability and product quality of the composting process.

[0056] S104. The ventilation control module ventilates the first preset detection area based on the first control parameter; In step S104, the ventilation module controls the ventilation of the first preset detection area based on the first control parameter. This is a crucial step in this method to inhibit the alcohol fermentation process and maintain the compost pile in an aerobic state. The ventilation module refers to an air delivery system installed inside or at the bottom of the composting device. It typically consists of components such as a fan, duct, and ventilation controller, and is used to deliver oxygen into the pile to meet the aerobic metabolic requirements of microorganisms and prevent anaerobic fermentation caused by oxygen deficiency. The first control parameter is a ventilation control quantity obtained in the previous steps by comprehensively calculating the first risk index, risk exceedance rate, regional control coefficient, and neighboring risk value. It is used to indicate the ventilation intensity or frequency of the ventilation module in a specific detection area, thereby achieving quantitative control of areas with abnormal fermentation. The first preset detection area refers to a spatial sub-unit in the pile where the alcohol fermentation intensity has been determined to exceed the fermentation intervention threshold. Its location and range are usually obtained by dividing the area using a distributed sensor network.

[0057] The fundamental purpose of this step is to introduce sufficient oxygen into the first preset detection area, thereby disrupting the anaerobic metabolic chain induced by the high concentration of ethanol accumulation, inhibiting the alcohol fermentation reaction dominated by miscellaneous bacteria and yeast, restoring the local aerobic microecological environment of the compost pile, and thus promoting the normal aerobic degradation process of the target organic matter. In specific implementation, the system uses the first control parameter as an input signal, sending it to the ventilation module controller through the compost control module. The controller adjusts the operating status of the ventilation module according to this parameter. For example, when the first control parameter is large, the controller can increase the fan speed, extend the running time, or shorten the ventilation cycle interval, thereby enhancing the local ventilation intensity; conversely, if the first control parameter is small, a low ventilation level is maintained to preserve stability. The ventilation mode can be continuous ventilation or pulsed ventilation, and the system can dynamically switch according to real-time sensor data to achieve a balance between energy saving and efficient control.

[0058] In practical applications, if the first risk index of a detection area is 1.2, which is much higher than the set fermentation intervention threshold of 0.8, the system calculates the first control parameter as 0.045 m³ / min based on the main control risk rate, the neighboring risk value, and the regional control coefficient in the preceding calculations. The control command will drive the ventilation module to open the ducts near the area for local ventilation, and the fan will deliver air evenly into the pile at a specified flow rate, increasing the oxygen concentration in the area. After the ventilation continues for a period of time, the sensor reports that the ethanol concentration in the area has decreased significantly and the temperature has returned to the normal range. The system can automatically adjust the first control parameter based on the feedback data, gradually reducing the ventilation intensity and eventually restoring it to the baseline ventilation state.

[0059] Through the above methods, the ventilation module achieves responsive and differentiated fine ventilation control of the first preset detection area, which can effectively curb the trend of alcohol fermentation and avoid the energy waste and moisture loss caused by indiscriminate ventilation of the entire pile, thus significantly improving the stability and energy utilization efficiency of the composting process.

[0060] S105. Based on ethanol concentration data, acetic acid concentration data and pH value, determine the acetic acid potential index of each first preset detection area. The acetic acid potential index is used to characterize the fermentation activity of ethanol to acetic acid conversion in the first preset detection area. Step S105, after identifying the risk of alcohol fermentation and implementing ventilation intervention, further identifies areas within the compost pile where fermentation activity is enhanced, leading to the continuous conversion of ethanol into acetic acid. Since the large accumulation of acetic acid not only stems from the natural conversion after ethanol fermentation but is also closely related to abnormal changes in the local microecological environment, failure to identify and regulate it in a timely manner can lead to a continuous decrease in pH, acidification of the compost pile, delayed maturation, and even inhibition of beneficial microbial growth, severely impacting compost quality. Therefore, it is necessary to construct a parameter that can dynamically characterize the activity of ethanol-acetic acid conversion, namely the acetic acid potential index, to determine whether the pile has entered the acidification acceleration stage and assess its risk intensity. Specifically, it can include the following steps: based on the ethanol concentration data and the acetic acid concentration data, calculate the decrease in ethanol concentration and the increase in acetic acid concentration in the first preset detection area within a second preset time period; calculate the ratio of the increase in acetic acid concentration to the decrease in ethanol concentration to obtain the instantaneous conversion coefficient; calculate the pH value decrease rate in the first preset detection area within the second preset time period; when the instantaneous conversion coefficient is greater than a preset conversion threshold and the pH value decrease rate is greater than a preset decrease rate threshold, determine that the first preset detection area is in the acidification acceleration state; count the first duration of the acidification acceleration state, and determine the acetic acid potential index by multiplying the first duration by the instantaneous conversion coefficient.

[0061] The system calculates the decrease in ethanol concentration and the increase in acetic acid concentration in the first preset detection area within a second preset time period based on ethanol and acetic acid concentration data, respectively. The purpose is to obtain the dynamic changes in ethanol metabolism by microorganisms to produce acetic acid, serving as a fundamental parameter for subsequent evaluation of fermentation activity. This calculation relies on a multi-point chemical sensor network deployed in the composting device. This network can collect ethanol and acetic acid concentrations in the target area in real time or at regular intervals and upload the data on their changes over time to the control system. The control system extracts ethanol and acetic acid concentration data at the start and end times of a time window defined as the second preset time period and calculates the difference between them. The length of the second preset time period is determined based on the typical timescale of the ethanol-to-acetic acid metabolism reaction during composting, typically set to 12 to 24 hours, to balance the observability of the fermentation reaction with the significance of data changes. Choosing a specific time period rather than a single point judgment is to avoid judgment bias caused by environmental disturbances or instantaneous fluctuations, and to more accurately reflect the overall microbial metabolic activity through the trend of changes within a time period. For example, within a continuous 24-hour period, the ethanol concentration in the first preset detection area decreased from 2.4% to 1.7%, while the acetic acid concentration increased from 0.5% to 1.1%. Based on this, the system calculated the decrease in ethanol concentration to be 0.7% and the increase in acetic acid concentration to be 0.6%. This result indicates that ethanol was being significantly metabolized during this period, accompanied by a rapid accumulation of acetic acid, suggesting the possible presence of active acetic acid bacteria or other microbial communities involved in the ethanol oxidation reaction in this area. Obtaining these two parameters not only provides prerequisite data for subsequent calculations of the instantaneous conversion coefficient but also establishes a preliminary basis for determining whether an area has entered an abnormal acetification process, thus improving the system's sensitivity to the dynamic state of compost fermentation.

[0062] After calculating the decrease in ethanol concentration and the increase in acetic acid concentration within the second preset time period, the system further calculates the ratio of the increase in acetic acid concentration to the decrease in ethanol concentration to obtain the instantaneous conversion coefficient. This coefficient aims to assess the relative efficiency of ethanol conversion to acetic acid within this time period, thereby determining whether acetic acid fermentation-dominated metabolic activity exists within the preset detection area. The ratio is calculated as: Instantaneous Conversion Coefficient = Increase in Acetic Acid Concentration ÷ Decrease in Ethanol Concentration. It is a dimensionless indicator used to measure the acetic acid yield per unit of ethanol loss. This parameter is called "instantaneous" because it reflects the immediate state of material conversion efficiency within the current set time window, rather than a long-term accumulated value. The system automatically retrieves the data obtained in the previous calculation step through the control module, performs the ratio calculation, and compares the result with historical data for trend analysis or with a threshold. The closer the instantaneous conversion coefficient is to 1, the more likely it is that ethanol metabolism is primarily directed towards acetic acid, indicating a relatively simple and efficient metabolic pathway, potentially due to enhanced acetic acid bacteria activity or a stable oxidative environment. If the coefficient deviates significantly from 1, other metabolic pathways or material loss mechanisms may exist, such as ethanol escape or partial acetic acid neutralization. Taking a specific testing area as an example, if the ethanol concentration decreases by 0.8% and the acetic acid concentration increases by 0.64% within 24 hours, the instantaneous conversion coefficient is calculated to be 0.64 ÷ 0.8 = 0.8. This value is close to the empirical threshold (e.g., 0.75~0.85), indicating significant ethanol-to-acetic acid conversion activity in this area. This result not only provides strong quantitative evidence for subsequent acidification status assessment but also serves as an important intermediate parameter for the system to automatically identify potential acidification risks, improving the scientific rigor and response speed of composting process control.

[0063] After calculating the instantaneous conversion coefficient, the system continues to calculate the pH decrease rate of the first preset detection area within the second preset time period. The purpose is to further assess the impact of the ethanol-to-acetic acid conversion process on the local acid-base balance, thereby comprehensively judging whether the area is in a harmful acidification trend. The pH decrease rate refers to the average decrease in pH value per unit time, reflecting the speed of environmental acidity change and is an important dynamic indicator for measuring the impact of organic acid accumulation on the micro-ecosystem. This step relies on pH sensors deployed in the composting device, which periodically collect pH data from monitoring points and upload it to the control system. The system selects the same second preset time period as the concentration change analysis, reads the pH data at the start (t0) and end (t1) of this time period, calculates the total pH decrease, and divides it by the time difference to obtain the pH decrease rate, i.e., pH decrease rate = (pHt0 − pHt1) ÷ (t1 − t0), where pHt0 represents the pH data at the start time and pHt1 represents the pH data at the end time. This indicator effectively reflects whether organic acids such as acetic acid accumulate rapidly in the pile and cause environmental acidification. Once the rate of decrease exceeds a set threshold, it indicates that a local area may be in a period of rising acidification risk. By introducing the pH decrease rate, not only can the sensitivity to the impact of acetic acid accumulation be enhanced, but it can also form a synergistic judgment mechanism with the instantaneous conversion coefficient, providing a more reliable basis for subsequent identification of accelerated acidification and improving the accuracy of dynamic identification of abnormal fermentation in the pile.

[0064] After calculating the instantaneous conversion coefficient and pH decrease rate, the system combines these two values ​​with their respective preset thresholds to determine whether the first preset detection area is in an accelerated acidification state. This is to identify potentially high-risk acidification areas within the compost pile, thereby enabling early warning and timely intervention for unfavorable fermentation trends. An accelerated acidification state refers to the process where ethanol significantly converts to acetic acid within a certain timeframe, causing a rapid decrease in the environmental pH. If this state persists, it may lead to microecological imbalance in the compost pile, delayed maturation, or even composting failure. Therefore, to accurately identify such risks, this step employs a dual threshold determination mechanism: the area is considered to have entered an accelerated acidification state only when the instantaneous conversion coefficient exceeds a preset conversion threshold and the pH decrease rate exceeds a preset decrease rate threshold. The preset conversion threshold is typically set based on historical data and experimental statistical experience; for example, a value of 0.75 indicates that a conversion efficiency of ethanol to acetic acid exceeding 75% is considered significant. The preset decrease rate threshold reflects the sensitive threshold of acidity changes; for example, a value of 0.02 pH / hour represents the critical rate of rapid pH decrease. The preset degradation rate threshold is a critical acidification rate determined by microbiology research that can significantly inhibit or even inactivate the community activity of key aerobic microorganisms (such as cellulose-decomposing bacteria). During operation, the system automatically compares the currently calculated instantaneous conversion coefficient and pH degradation rate with the aforementioned threshold, and uses a logic judgment module to determine the results. If both exceed the threshold, the system records the current state of the first preset detection area as accelerated acidification and marks it for continuous monitoring. For example, if a detection area experiences a 0.9% decrease in ethanol concentration, a 0.81% increase in acetic acid concentration, an instantaneous conversion coefficient of 0.9, and a pH decrease from 6.3 to 5.7 within 24 hours (a degradation rate of 0.025 pH / hour), all exceeding their respective thresholds, the system automatically identifies the area as experiencing accelerated acidification. Through this judgment mechanism, the system can effectively screen out key areas with potential acidification risks, providing precise basis for subsequent control measures such as ventilation and alkaline material preparation, thereby ensuring the stable progress of the composting process and the final product quality meeting standards.

[0065] After identifying the first preset detection area as being in an accelerated acidification state, the system continues to dynamically count the duration of this state to obtain the first duration. This duration is then multiplied by the instantaneous conversion coefficient within the corresponding time period to determine the acetic acidification potential index for that area. The purpose is to comprehensively reflect the intensity and persistence of the ethanol-to-acetic acid conversion process in this area, thereby quantifying its potential contribution to the reactor's acidification risk. The first duration refers to the continuous time period, measured in hours or minutes, from the first time the system determines that the area has entered an accelerated acidification state until the state ends (i.e., any judgment indicator falls below a threshold). The system continuously monitors and records the duration of this state. To avoid misjudgments due to short-term fluctuations, the system introduces state-maintaining logic, accumulating the duration for which both the instantaneous conversion coefficient > preset conversion threshold and the pH decrease rate > preset decrease rate threshold. If the state is interrupted, the timing is reset. Subsequently, the system calculates the acetization potential index by multiplying the first duration of acidification by the instantaneous conversion coefficient within the corresponding time period: Acetic Acidification Potential Index = First Duration of Acidification × Instantaneous Conversion Coefficient. This yields a comprehensive dimensional index; a higher value indicates that the area continuously accumulates high levels of acetic acid per unit time, and the risk of environmental acidification is higher. For example, if an area experiences accelerated acidification for 48 hours, and the instantaneous conversion coefficient during this period is 0.85, then the acetization potential index is 48 × 0.85 = 40.8. This result not only quantifies the strength of the acidification trend but also provides an important basis for the system to determine whether acid-base regulation is necessary, demonstrating good risk identification and early warning value. By introducing the acetization potential index, the system can achieve refined regional management, improving the stability of the composting process and the consistency of product quality.

[0066] S106. Calculate the second risk index for each first preset detection area based on the acetic acid potential index. The second risk index is used to characterize the degree of acetic acid accumulation in the first preset detection area. Step S106: After obtaining the acetic acid potential index for each first preset detection area, the system calculates a second risk index for each first preset detection area based on this index, which characterizes the degree of acetic acid accumulation in that area. For areas with a high risk of acetic acid accumulation, a differentiated pH control strategy is implemented to prevent localized excessive acidification from adversely affecting the microecology and fermentation balance of the pile. Specifically, this may include the following steps: calculating the ratio of the instantaneous conversion coefficient to a preset conversion standard value to obtain a standard conversion coefficient; calculating the ratio of the pH decrease rate to a preset decrease standard value to obtain a standard pH decrease rate; calculating the product of the standard conversion coefficient and the standard pH decrease rate to obtain an acidification expansion factor; analyzing the temperature fluctuation amplitude of the first preset detection area; when the temperature fluctuation amplitude is greater than a preset temperature fluctuation threshold, determining that the first preset detection area is in a temperature unstable state; and calculating the second duration of the temperature unstable state, determining the product of the second duration and the acidification expansion factor as the second risk index.

[0067] After calculating the acetic acidification potential index, the system performs further standardization processing on this value to eliminate numerical deviations caused by environmental differences between different detection areas and enhance the consistency of the assessment. Specifically, the system obtains the standard conversion coefficient by calculating the ratio of the instantaneous conversion coefficient to the preset conversion standard value. The preset conversion standard value is usually derived from the ideal efficiency of ethanol to acetic acid conversion in a laboratory fermentation model (e.g., 0.85), and is used to measure the degree of deviation of the ethanol conversion activity in the current detection area from the standard state. The calculation method for this ratio is: Standard conversion coefficient = Measured instantaneous conversion coefficient ÷ Preset conversion standard value. The result is a dimensionless value. The closer it is to 1, the closer the conversion efficiency is to the ideal state. If it is significantly higher than 1, it indicates that the acetic acid formation rate in the area is abnormally active, which may indicate an increased risk of acidification. For example, if the instantaneous conversion coefficient of the detection area is 0.95, while the conversion standard value is 0.85, then the standard conversion coefficient is 1.12, indicating that the conversion intensity is too high.

[0068] The system standardizes the pH decrease rate using the same logic, calculating the ratio of the pH decrease rate to a preset standard decrease value to obtain the standard pH decrease rate. This operation aims to assess whether the drastic pH change in the detection area exceeds the normal fermentation range, thereby determining if there is an anomaly in the rate of organic acid accumulation. The preset standard decrease value can be set based on the average rate of pH decrease during historical mature composting processes (e.g., 0.02 pH / hour). The standard pH decrease rate = measured pH decrease rate ÷ standard decrease value. The larger this ratio, the faster the acidification rate in the area, allowing the system to identify potential pH imbalance trends. For example, if the measured pH decrease rate is 0.03 pH / hour, the standard pH decrease rate is 1.5, indicating a significantly accelerated acidification rate.

[0069] The system calculates the acidification expansion factor by multiplying the standard conversion coefficient by the standard pH decrease rate. This factor comprehensively reflects the intensity of the ethanol-to-acetic acid conversion and the magnitude of changes in environmental acidity, and is a key indicator for measuring whether a local acidification state has an expanding trend. The calculation formula is: Acidification Expansion Factor = Standard Conversion Coefficient × Standard pH Decrease Rate. The larger this product, the faster the acid formation rate and the more drastic the acidity changes in the detection area, indicating a wider potential acidification range and higher risk. For example, if the standard conversion coefficient is 1.12 and the standard pH decrease rate is 1.5, the acidification expansion factor is 1.68, significantly higher than the safety reference value (e.g., 1.0), and the system identifies this as a point where the acidification trend is spreading.

[0070] Building upon this foundation, to further enhance the dynamic response capability of risk assessment, the system introduces a temperature fluctuation analysis mechanism to analyze the temperature fluctuation amplitude of the first preset detection area. The temperature fluctuation amplitude refers to the difference between the maximum and minimum temperature values ​​in that area within a set time period. The system continuously records temperature changes using temperature sensors and calculates the fluctuation value. When the temperature fluctuation amplitude exceeds the system's preset temperature fluctuation threshold (e.g., ±3°C), the system determines that the area is in a temperature unstable state. The preset temperature fluctuation threshold is statistically derived from the temperature change amplitudes corresponding to significant fluctuations in microbial activity observed in a large amount of composting process experimental data, and is used to identify abnormal temperature fluctuations affecting fermentation stability. This judgment is necessary because temperature instability is often accompanied by changes in microbial community activity, which may exacerbate the uncertainty of acidification reactions and affect fermentation steady state. For example, if the temperature in the detection area drops from 58°C to 52°C and then rises back to 59°C within 24 hours, the fluctuation amplitude is 7°C, exceeding the 3°C threshold, and the system determines it to be in a temperature unstable state.

[0071] After identifying a temperature instability state, the system further calculates the second duration of this instability state, which is the continuous time from the first time the fluctuation threshold is met until the fluctuation returns to normal. This duration is obtained through time-series analysis of temperature data, using a rolling window algorithm to continuously assess the fluctuation state and automatically accumulate the continuous fluctuation time. Subsequently, the system multiplies this second duration with the previously calculated acidification expansion factor to obtain a second risk index for the first preset detection area. This index is used to comprehensively assess the combined risk level of acetic acid accumulation intensity, rate, and instability in the area. The calculation formula is: Second Risk Index = Acidification Expansion Factor × Second Duration of Temperature Instability State. For example, if the acidification expansion factor is 1.68 and the duration of the temperature instability state is 36 hours, then the second risk index is 1.68 × 36 = 60.48, indicating that the acidification risk in this area has reached a high level, requiring priority intervention for pH regulation.

[0072] S107. Determine the second control parameter of the second preset detection area based on the second risk index. The second preset detection area is the first preset detection area where the second risk index is greater than the acid-base intervention threshold. The second control parameter is used to adjust the acid-base of the second preset detection area. Step S107 identifies a first preset detection area exceeding the pH intervention threshold, forming a second preset detection area, and determines the corresponding second control parameter based on this. When the second risk index of the first preset detection area is greater than the pH intervention threshold, the system marks this area as the second preset detection area, i.e., the target area requiring pH control. The pH intervention threshold is a judgment standard empirically set by the system based on the relationship between pH changes and the risk of acetic acid accumulation during composting, used to determine whether pH adjustment is needed for a specific area.

[0073] The calculation logic of the second control parameter is consistent with that of the first risk index. Its purpose is to quantify the risk of acetic acid accumulation, enabling the system to identify differences in acidification trends across different regions and providing a basis for subsequent zonal control. Specifically, the system first uses the second risk index of each first preset detection area as input, calculates the difference with the system's preset acid-base intervention threshold, and then divides this difference by the acid-base intervention threshold to obtain the acidification exceedance rate for that area: Acidification exceedance rate = (Second risk index - Acid-base intervention threshold) ÷ Acid-base intervention threshold. This ratio reflects the degree of deviation of the current acetic acid accumulation from the acceptable upper limit. Based on this, the system marks the detection area with the highest acidification exceedance rate as the main acidification point and uses its acidification exceedance rate as the main control acidification rate. Next, within the preset spatial range of the main acidification point (which must include at least three other first preset detection areas), the system counts the number of detection areas other than the main acidification point and calculates a ratio with the total number of all detection areas to obtain the acidification concentration, which is used to measure the spatial clustering of high-risk areas. Subsequently, the system calculates the product of the main acidification rate and the acidification concentration to obtain the regional acidification coefficient, which is used to comprehensively characterize the intensity and distribution trend of acidification risk. Finally, the system selects the three detection areas with the highest acidification exceedance rates in the surrounding area of ​​the main acidification point, calculates the average of their acidification exceedance rates as the neighborhood acidification value, and multiplies it with the regional acidification coefficient and the preset baseline control amount to obtain the second control parameter, which is used to guide pH-based fermentation process interventions, such as adding alkaline substances or adjusting moisture.

[0074] For example, if the second risk index of the detection area is 42 and the pH intervention threshold is 30, then the acidification exceedance rate is (42−30) / 30=0.4; if the area is the main acidification point and there are 6 detection areas within its range besides itself, accounting for 20% of the total number of areas, then the acidification concentration is 0.2 and the regional acidification coefficient is 0.4×0.2=0.08; if the neighboring acidification value is 0.35 and the baseline control amount is 100L / min, then the second control parameter is 0.08×0.35×100=2.8L / min. Based on this, the system can automatically adjust the alkaline spraying amount or ventilation increment in the area, thereby achieving targeted acidification risk suppression.

[0075] S108, The pH control module adjusts the pH of the second preset detection area based on the second control parameter.

[0076] Step S108 aims to alleviate the acidification trend caused by acetic acid accumulation in a specific area, restore the pH balance of the compost pile's microenvironment, and maintain the activity of the aerobic microbial community, thereby ensuring the stable progress of the composting process. The "pH control module" is a functional unit in the composting device, typically including an alkaline material spraying system, liquid alkaline solution nozzles, pH adjuster storage tanks, and a delivery control unit, used to achieve precise pH adjustment in different areas of the compost pile. The second control parameter is a quantitative control index calculated by the system based on the second risk index, reflecting the required adjustment intensity for each second preset detection area. Its unit can be the alkaline solution spraying rate (e.g., L / min) or the amount of alkaline solid material added (e.g., kg / m³). The second preset detection area is a risk area selected from the first preset detection area, meeting the condition that the second risk index is greater than the pH intervention threshold, representing an area where acetic acid accumulation has reached the level requiring intervention.

[0077] During implementation, the system sends the second control parameter to the corresponding pH control module control unit. Then, based on the spatial location information of the area, it activates the control device corresponding to the detection area. For example, if the control method is spraying liquid alkali, the control system adjusts the nozzle opening time and flow rate to match the actual spray volume with the second control parameter. If solid alkaline materials (such as quicklime or wood ash) are added, they are added proportionally to the surface or mixing layer of the pile via an automatic feeding mechanism to ensure effective local acid neutralization. Before adding materials, the system first confirms the current state by taking another pH reading to ensure consistency between the control strategy and real-time data. After control, it continuously monitors pH changes to form a closed-loop control mechanism.

[0078] The principle behind this control strategy is to utilize alkaline substances to neutralize the acetic acid accumulated in the compost pile, inhibiting the continuous decline of pH and restoring a suitable fermentation acid-base environment (generally pH 6.5~8.0), thereby preventing the overgrowth of anaerobic microorganisms and the inactivation of beneficial aerobic microorganisms. By introducing a second control parameter as the basis for adjustment, the system can achieve quantitative and regionally differentiated acid-base regulation, avoiding the problems of excessive alkalization or control lag caused by inaccurate regulation in traditional composting.

[0079] Please see Figure 2 This is a schematic diagram of the structure of an optimized control system for agricultural waste composting in an embodiment of this application.

[0080] It should be noted that, Figure 2 The structure of an optimized control system for agricultural waste composting shown is merely an example and should not impose any limitations on the functionality and scope of application of the embodiments of the present invention.

[0081] like Figure 2 As shown, an optimized control system for agricultural waste composting includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 202 or a program loaded from storage section 208 into random access memory (RAM) 203, such as executing the methods described in the above embodiments. The RAM 203 also stores various programs and data required for system operation. The CPU 201, ROM 202, and RAM 203 are interconnected via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0082] The following components are connected to I / O interface 205: input section 206 including audio input devices, push-button switches, etc.; output section 207 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 208 including a hard disk, etc.; and communication section 209 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 209 performs communication processing via a network such as the Internet. Drive 210 is also connected to I / O interface 205 as needed. Removable media 211, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 210 as needed so that computer programs read from them can be installed into storage section 208 as needed.

[0083] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 209, and / or installed from removable medium 211. When the computer program is executed by central processing unit (CPU) 201, it performs the various functions defined in the present invention.

[0084] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0086] Specifically, the optimized control system for agricultural waste composting in this embodiment includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, it implements the optimized control method for agricultural waste composting provided in the above embodiment.

[0087] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the optimized control system for agricultural waste composting described in the above embodiments; or it may exist independently and not incorporated into the optimized control system for agricultural waste composting. The storage medium carries one or more computer programs, which, when executed by a processor of the optimized control system for agricultural waste composting, cause the optimized control system to implement the optimized control method for agricultural waste composting provided in the above embodiments.

Claims

1. An optimized control method for agricultural waste composting, characterized in that, Applied to a composting device, the composting device including a ventilation module and a pH control module, the method includes: Monitor temperature, ethanol concentration, acetic acid concentration, and pH value in multiple preset detection areas within the target compost pile; Based on the temperature data and the ethanol concentration data, a first risk index is calculated for each preset detection area. The first risk index is used to characterize the alcohol fermentation intensity of the preset detection area. Based on the first risk index, a first control parameter is determined for the first preset detection area. The first preset detection area is the preset detection area where the first risk index is greater than the fermentation intervention threshold. The first control parameter is used to inhibit anaerobic fermentation in the first preset detection area. The ventilation module is controlled to ventilate the first preset detection area based on the first control parameter. Based on the ethanol concentration data, the acetic acid concentration data, and the pH value, an acetic acid potential index is determined for each of the first preset detection areas. The acetic acid potential index is used to characterize the fermentation activity of ethanol to acetic acid conversion in the first preset detection area. A second risk index is calculated for each of the first preset detection areas based on the acetic acid potential index. The second risk index is used to characterize the degree of acetic acid accumulation in the first preset detection area. Based on the second risk index, a second control parameter is determined for the second preset detection area. The second preset detection area is the first preset detection area where the second risk index is greater than the acid-base intervention threshold. The second control parameter is used to adjust the acid-base of the second preset detection area. The pH control module controls the pH of the second preset detection area based on the second control parameter.

2. The method according to claim 1, characterized in that, The step of calculating a first risk index for each preset detection area based on the temperature data and the ethanol concentration data specifically includes: A two-dimensional plane coordinate system is established with temperature as the horizontal axis and ethanol concentration as the vertical axis. The temperature data and ethanol concentration data corresponding to the target time point within the first preset time period are determined as data points. Multiple data points are mapped to the two-dimensional plane coordinate system to obtain the temperature-ethanol state trajectory curve. The target time point is any time point within the first preset time period. Calculate the deviation value between the temperature-ethanol state trajectory curve and the preset standard state region, where the preset standard state region is the paired range of temperature and ethanol concentration during aerobic fermentation. Calculate the deviation rate of the temperature-ethanol state trajectory curve from the preset standard state region, and calculate the first risk index based on the deviation degree value and the deviation rate.

3. The method according to claim 2, characterized in that, The calculation of the deviation rate of the temperature-ethanol state trajectory curve from the preset standard state region, and the calculation of the first risk index based on the deviation degree value and the deviation rate, specifically includes: Calculate the first state change vector between the first data point corresponding to the first time point and the second data point corresponding to the second time point, where the first time point and the second time point are adjacent time points within the first preset time period; Calculate the second state change vector between the second data point and the third data point corresponding to the third time point, wherein the third time point is a time point within the first preset time period that is after the second time point and adjacent to the second time point; The first state change vector and the second state change vector are vector summed to obtain the third state change vector, which is used to characterize the average state transition trend from the first time point to the third time point. The state deviation vector is calculated based on the second data point and the preset standard state center coordinates. The state deviation vector is used to characterize the deviation direction of the temperature-ethanol state trajectory curve relative to the standard state center coordinates at the second time point. Calculate the dot product of the third state change vector and the state deviation vector. When the dot product is greater than zero, determine that the change trend of the temperature-ethanol state trajectory curve is a deviation from the standard state center coordinates, and determine the magnitude of the third state change vector as the deviation rate. The first risk index is obtained by multiplying the deviation degree value by the deviation rate.

4. The method according to claim 1, characterized in that, The first control parameter for determining the first preset detection area based on the first risk index specifically includes: Calculate the difference between the first risk index and the fermentation intervention threshold for each first preset detection area, and calculate the ratio of the difference to the fermentation intervention threshold to obtain the risk exceedance rate; The first preset detection area with the highest risk exceedance rate is determined as the main control point, and the risk exceedance rate of the main control point is determined as the main control risk rate. Within the preset range of the main control point, the number of detection areas in the first preset detection area other than the main control point is counted, and the ratio of the number of detection areas to the total number of the first preset detection areas is calculated to obtain the risk concentration. There are at least 3 first preset detection areas in the preset range other than the main control point. The regional control coefficient is obtained by multiplying the main control risk rate and the risk concentration. The first control parameter is determined based on the regional control coefficient and the risk exceedance rate.

5. The method according to claim 4, characterized in that, The determination of the first control parameter based on the regional control coefficient and the risk exceedance rate specifically includes: Calculate the average of the first risk exceedance rate, the second risk exceedance rate, and the third risk exceedance rate to obtain the neighborhood risk value. The first risk exceedance rate, the second risk exceedance rate, and the third risk exceedance rate are the risk exceedance rates of the top three first preset detection areas, excluding the main control point, within the preset range, sorted from largest to smallest. The first control parameter is obtained by multiplying the product of the regional control coefficient and the neighborhood risk value by the preset benchmark ventilation volume.

6. The method according to claim 1, characterized in that, The determination of the acetic acid potential index for each of the first preset detection areas based on the ethanol concentration data, the acetic acid concentration data, and the pH value specifically includes: Based on the ethanol concentration data and the acetic acid concentration data, calculate the decrease in ethanol concentration and the increase in acetic acid concentration in the first preset detection area within the second preset time period; The instantaneous conversion coefficient is obtained by calculating the ratio of the increase in acetic acid concentration to the decrease in ethanol concentration. Calculate the pH decrease rate of the first preset detection area within the second preset time period; When the instantaneous conversion coefficient is greater than a preset conversion threshold and the pH decrease rate is greater than a preset decrease rate threshold, it is determined that the first preset detection area is in an accelerated acidification state. The first duration of the accelerated acidification state is statistically analyzed, and the product of the first duration and the instantaneous conversion coefficient is determined as the acetic acidification potential index.

7. The method according to claim 6, characterized in that, The calculation of the second risk index for each of the first preset detection areas based on the acetylation potential index specifically includes: Calculate the ratio of the instantaneous conversion coefficient to the preset conversion standard value to obtain the standard conversion coefficient; calculate the ratio of the pH decrease rate to the preset decrease standard value to obtain the standard pH decrease rate. The acidification expansion factor is obtained by multiplying the standard conversion coefficient by the standard pH decrease rate. Analyze the temperature fluctuation range of the first preset detection area. When the temperature fluctuation range is greater than the preset temperature fluctuation threshold, it is determined that the first preset detection area is in a temperature unstable state. The second duration of the temperature instability state is statistically analyzed, and the product of the second duration and the acidification expansion factor is determined as the second risk index.

8. An optimized control system for agricultural waste composting, characterized in that, The optimized control system for agricultural waste composting includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code including computer instructions, and the one or more processors invoke the computer instructions to cause the optimized control system for agricultural waste composting to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on the optimized control system for agricultural waste composting, the optimized control system for agricultural waste composting performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the optimization control system for agricultural waste composting, the optimization control system for agricultural waste composting performs the method as described in any one of claims 1-7.

Images