An aerobic fermentation system for organic waste

Abstract

The invention discloses an aerobic fermentation system for organic waste, and relates to the technical field of composting fermentation. After adjusting the proportion of original composting materials according to the carbon-nitrogen ratio, the composting materials are stirred and crushed wood chips are added; environmental condition data in a composting fermentation area are identified, and an environmental abnormality coefficient is generated according to an abnormal state. If the environmental abnormality coefficient exceeds expectations, a sensor network in the compost pile monitors the fermentation state of the compost pile; if there is an abnormality in the fermentation state, a trained fuzzy control model is used to adjust the fermentation index, and according to the density of the abnormalities in the fermentation state, the turning frequency is constrained; the maturity time of the compost pile is predicted, and if the predicted maturity time is inconsistent with expectations, the fermentation control strategy of the compost pile is optimized; various fermentation indicators and condition parameters are adjusted, and the compost maturity time is adjusted, so that the composting effect and the controllability of the composting effect are higher.

Description

Technical Field

[0001] The invention relates to the technical field of composting fermentation, in particular to an aerobic fermentation system for organic waste. Background Art

[0002] Aerobic fermentation of organic waste is an environmentally friendly and sustainable treatment method. It cleverly uses the process of aerobic microorganisms decomposing organic waste under sufficient oxygen conditions to convert waste that may have become an environmental burden into humus fertilizer that is beneficial to plant growth. This process not only reduces the amount of organic waste accumulation, but also generates heat through the respiration of microorganisms, promotes the rapid decomposition of organic matter, and forms stable and harmless fertilizer. Under ideal temperature, humidity, C / N ratio and oxygen supply conditions, aerobic fermentation can be carried out efficiently, and waste can usually be converted into valuable resources within a few months. In addition, the use of advanced film-covered aerobic composting technology can further shorten the fermentation time and improve the treatment efficiency, making this method a highly cost-effective organic waste treatment solution.

[0003] Aerobic fermentation can realize the resource utilization of organic waste, reduce environmental pollution, improve soil quality and promote plant growth. The humus produced in this process is rich in nutrients and microbial communities, which can significantly improve the soil's water retention capacity, air permeability and organic matter content, providing excellent environmental conditions for plant growth.

[0004] In the Chinese invention patent application publication number CN117486645A, an agricultural trough composting reaction system and its control method are disclosed. The method performs data calculation and command control according to the temperature, CO2 concentration, carbon-nitrogen ratio and moisture content data inside the compost body, predicts the compost body parameters at the next sampling moment in advance, and controls the compost turner or aeration device to work according to the calculation results, thereby realizing the automatic control of the trough fermentation process, greatly reducing the probability of misjudgment caused by human judgment, making the fermentation process more complete, and improving the production efficiency of substrate fermentation. The system and method are suitable for application in the large-scale production of agricultural trough composting.

[0005] Combined with the above application and the contents of the prior art:

[0006] After completing the selection of organic waste raw materials and conducting composting fermentation, usually after selecting the composting area, it is necessary to observe the environmental conditions in the composting area, such as whether the temperature and humidity are suitable, whether there are good ventilation conditions, etc. If the environmental conditions are poor or difficult to meet expectations, the composting effect of the organic waste will also be affected to a certain extent.

[0007] However, after completing the collection of organic waste, it is not realistic to wait for better seasonal climatic conditions to start composting. Therefore, if the current climatic conditions are not good, manual adjustment and control are usually chosen; however, after completing the composting fermentation link, if the composting environmental conditions are abnormal, especially the humidity, temperature, wind speed and oxygen concentration and other environmental conditions are abnormal frequently, or even the degree of abnormality is high, the various fermentation indicators of the compost pile may also be frequently abnormal. At this time, if the fermentation indicators during composting are still adjusted manually, not only may the adjustment efficiency be low, but the final fermentation effect and fermentation time of the compost pile may also be affected to a certain extent.

[0008] To this end, the present invention provides an aerobic fermentation system for organic waste. Summary of the invention

[0009] 1. Technical issues to be resolved

[0010] In view of the deficiencies in the prior art, the present invention provides an aerobic fermentation system for organic waste. By identifying environmental condition data in a composting fermentation area, an environmental anomaly coefficient is generated according to an abnormal state. If the environmental anomaly coefficient exceeds expectations, a sensor network in the compost pile monitors the fermentation state of the compost pile. If there is an abnormality in the fermentation state, a trained fuzzy control model is used to adjust the fermentation index, and the frequency of turning the compost pile is constrained according to the density of the abnormalities in the fermentation state; the maturity time of the compost pile is predicted, and if the predicted maturity time is inconsistent with expectations, the fermentation control strategy of the compost pile is optimized; the compost maturity time is adjusted to make the composting effect and the controllability of the composting effect higher, thereby solving the technical problems raised in the background technology.

[0011] (II) Technical solution

[0012] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0013] An aerobic fermentation system for organic waste, comprising:

[0014] The raw material ratio optimization unit builds a composting environment in the composting fermentation area, adjusts the original compost material ratio according to the carbon-nitrogen ratio, stirs the compost material and adds crushed sawdust;

[0015] The abnormal environment recognition unit identifies the environmental condition data in the composting fermentation area. If the environmental condition is abnormal, an environmental abnormality coefficient is generated according to the abnormal state. If the environmental abnormality coefficient exceeds expectations, a compensation control instruction is issued to the outside.

[0016] The fuzzy control unit uses a sensor network inside the compost pile to monitor the fermentation state of the compost pile. If there is an abnormality in the fermentation state, the trained fuzzy control model is used to adjust the fermentation index, and the frequency of turning the compost pile is constrained according to the density of abnormalities in the fermentation state.

[0017] The compost prediction unit uses the trained compost maturity prediction model to predict the maturity time of the compost pile. If the predicted maturity time does not match the expected time, the fermentation control strategy of the compost pile is optimized, and the fermentation index of the compost pile is adjusted according to the optimized fermentation control strategy;

[0018] The maturity assessment unit conducts maturity testing on the fermentation pile and constructs a maturity coefficient based on the maturity of the compost at each sampling point. If the obtained maturity coefficient is lower than the maturity threshold, the fermentation index is re-optimized.

[0019] Furthermore, after the composting fermentation area is selected, a composting environment is constructed in the composting fermentation area, and the shape and size of the compost pile are determined according to the compost pile design; the carbon-nitrogen ratio of the original compost material is estimated, and if the estimated carbon-nitrogen ratio is not within the target range, the proportion of the original compost material is adjusted.

[0020] Furthermore, before the adjusted compost material is uniformly mixed, crushed sawdust is added to the compost material, and a positive correlation is established between the sawdust and the carbon-nitrogen ratio.

[0021] Furthermore, the environmental condition data in the composting fermentation area is collected and monitored in real time, and a real-time environmental condition data set is generated;

[0022] Taking real-time environmental condition data as input, the trained abnormal environment recognition model is used to identify abnormal environments in the composting fermentation area; if there are abnormal environmental conditions, the abnormal proportions of the abnormal condition data are summed up as the abnormality degree, and an abnormal reminder instruction is issued to the outside.

[0023] Furthermore, if the number of abnormal warning instructions issued continuously within the abnormal adjustment period exceeds expectations, an environmental abnormality coefficient is generated based on the time node when the abnormal warning instruction is issued and the degree of abnormality. If the obtained environmental abnormality coefficient exceeds the abnormal threshold, a compensation control instruction is issued to the outside.

[0024] Furthermore, after receiving the compensation control instruction, a sensor network is arranged in the compost pile, and various fermentation indicators of the compost pile are monitored in real time according to the sensor network;

[0025] Taking the real-time fermentation index as input, the trained abnormal data recognition model is used to identify abnormal indicators. If there are abnormal indicators, an abnormal alarm instruction is issued to the outside.

[0026] Furthermore, after receiving the abnormal alarm instruction, the fermentation index is adjusted according to the preset target range using the trained fuzzy control model, and the corresponding composting fermentation control strategy is output.

[0027] Furthermore, the time point at which the abnormal alarm instruction is received is recorded within a preset feedback cycle, the frequency of compost turning is constrained according to the intensity of the alarms, and the compost pile is turned at the time point that meets the constraint conditions.

[0028] Furthermore, the fermentation state data of the compost pile is collected by the sensor network, and the fermentation state data is used as input to predict the maturity time of the compost pile using the trained compost maturity prediction model to obtain the predicted maturity time;

[0029] If the predicted maturity time does not meet expectations, adjustment instructions will be issued externally.

[0030] Furthermore, after receiving the adjustment instruction, the fermentation index of the compost pile is optimized by the pre-trained genetic algorithm with the expected fermentation time as the optimization target, and the optimized fermentation index is obtained and summarized as the fermentation control strategy.

[0031] Furthermore, several sampling points are selected inside the compost pile, sampling and testing are performed at the sampling points, corresponding maturity test data are obtained, and a compost maturity index set is generated by summarizing;

[0032] Taking real-time compost maturity index data as input, the trained maturity recognition model is used to identify the compost maturity of the sampling points, and the sampling points are marked with the compost maturity.

[0033] Furthermore, the maturity coefficient was constructed from the maturity of the compost at each sampling point;

[0034] If the obtained maturity coefficient is lower than the maturity threshold, the fermentation index is optimized again, and secondary composting fermentation is carried out according to the optimized fermentation index until the compost is fully mature;

[0035] If the obtained maturity coefficient is not lower than the maturity threshold, the mature compost is screened to remove undegraded substances and impurities with a volume larger than expected, thus completing the composting fermentation process of the organic waste.

[0036] (III) Beneficial effects

[0037] The present invention provides an aerobic fermentation system for organic waste, which has the following beneficial effects:

[0038] 1. By testing and estimating the carbon-nitrogen ratio, the amount of sawdust added is restricted. When the carbon-nitrogen ratio does not meet expectations, it can be adjusted by adding auxiliary materials to ensure the fermentation effect.

[0039] 2. By identifying real-time environmental condition data, the abnormality of composting environmental conditions can be judged. If the composting environment is abnormal and has large fluctuations, the impact of abnormal environmental conditions on organic waste composting can be reduced by adjusting and controlling the environment.

[0040] 3. Generate an environmental abnormality coefficient through the status of each abnormal reminder instruction, and analyze the abnormality of the current composting environment conditions based on the environmental abnormality coefficient. If the abnormality is high, take auxiliary measures in the composting fermentation area to achieve the effect of organic matter fermentation and composting.

[0041] 4. By arranging a sensor network to monitor and collect various fermentation indicators, the abnormal data can be identified and processed in a timely manner; the corresponding control strategy is given through the trained control model, and the composting process can be automatically controlled according to the control strategy, so as to ensure the composting effect under abnormal environmental conditions.

[0042] 5. Limit and constrain the frequency of compost turning based on the frequency of abnormal indicators, so that the number and frequency of compost turning are consistent with the density of abnormal indicators. By readjusting the compost structure and increasing the contact effect between oxygen and compost, the compost fermentation state and progress can be adjusted to ensure the composting effect.

[0043] 6. The maturity time of the compost pile is predicted by using the trained compost maturity prediction model to grasp the compost maturity time in real time, and the compost maturity time is adjusted on the basis of adjusting various fermentation indicators and condition parameters, so as to make the composting effect and the controllability of the composting effect higher.

[0044] 7. Identify the maturity of the compost through the maturity identification model, screen out the immature areas in the compost pile, and continue composting and fermenting the immature areas; conduct an overall assessment of the compost maturity effect based on the maturity coefficient, and take targeted measures based on the judgment results to ensure the composting effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a schematic diagram of the aerobic fermentation method of organic waste according to the present invention;

[0046] Figure 2 It is a schematic diagram of the aerobic fermentation method system of organic waste of the present invention. DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 The present invention provides an aerobic fermentation method for organic waste, comprising:

[0049] Step 1: Building a composting environment in the composting fermentation area, adjusting the proportion of the original composting materials according to the carbon-nitrogen ratio, stirring the composting materials and adding crushed sawdust;

[0050] The step 1 includes the following contents:

[0051] Step 101: After selecting a composting fermentation area, construct a composting environment in the composting fermentation area, including:

[0052] Lay a permeable foundation, such as gravel or wood strips, to facilitate drainage and prevent water accumulation at the bottom; build a sunshade or rain shelter above the compost pile to prevent direct sunlight and rain erosion; set up windbreaks around the compost pile, such as hedges and mesh fences, to reduce the impact of wind on the pile;

[0053] After selecting the raw materials, such as agricultural waste: such as straw, rice husks, corn cobs, these materials have a high carbon content, which helps to adjust the carbon-nitrogen ratio; municipal sludge: treated sludge, rich in nitrogen and trace elements, can provide necessary nutrients; kitchen waste: including vegetable leaves, food residues, fruit peels, etc., rich in organic matter and moisture; livestock and poultry manure: such as chicken manure, pig manure, cow manure, rich in nitrogen, which helps to increase the fermentation temperature.

[0054] The shape and size of the compost pile are determined according to the compost pile design. For example, the height is 1.5 to 2 meters. Too high will lead to poor internal ventilation, while too low will lead to poor insulation effect. The width is 2 to 3 meters. Too large a width will also affect internal ventilation. The length is determined according to site conditions and operating space.

[0055] Step 102, estimating and obtaining the carbon-nitrogen ratio of the original compost material, if the estimated carbon-nitrogen ratio is not within the target range, wherein the target range is: 20:1 to 30:1, adjusting the proportion of the original compost material according to the carbon-nitrogen ratio, if the carbon-nitrogen ratio is too high, adding nitrogen-rich substances such as livestock and poultry manure to the original compost material; if the carbon-nitrogen ratio is too low, adding carbon-rich substances such as straw;

[0056] Step 103, before evenly mixing the adjusted compost material, adding crushed sawdust to the compost material, and making the sawdust and the carbon-nitrogen ratio positively correlated, stirring the compost material and adding the sawdust, and then completing the construction of the compost pile;

[0057] When using, combine the contents in steps 101 to 103:

[0058] When it is necessary to add sawdust, the porosity of the compost can be increased, ventilation conditions can be improved, the surface area of ​​the raw materials can be increased, and the degradation efficiency of microorganisms can be improved. Before completing the selection of composting materials and starting composting, the amount of sawdust added can be restricted by testing and estimating the carbon-nitrogen ratio. When the carbon-nitrogen ratio does not meet expectations, it can be adjusted by adding auxiliary materials to ensure the fermentation effect.

[0059] However, after completing the collection of organic waste, it is not realistic to wait for better seasonal climatic conditions to start composting. Therefore, if the current climatic conditions are not good, manual adjustment and control are usually chosen; however, after completing the composting fermentation link, if the composting environmental conditions are abnormal, especially the humidity, temperature, wind speed and oxygen concentration and other environmental conditions are abnormal frequently, or even the degree of abnormality is high, the various fermentation indicators of the compost pile may also be frequently abnormal. At this time, if the fermentation indicators during composting are still adjusted manually, not only may the adjustment efficiency be low, but the final fermentation effect and fermentation time of the compost pile may also be affected to a certain extent.

[0060] Step 2: Identify the environmental condition data in the composting fermentation area. If the environmental conditions are abnormal, generate an environmental abnormality coefficient based on the abnormal state. , if the environmental anomaly coefficient If it exceeds expectations, compensatory control instructions will be issued externally;

[0061] The step 2 includes the following contents:

[0062] Step 201: real-time collection and monitoring of environmental condition data in the composting fermentation area, including humidity, temperature, wind speed, oxygen concentration, etc., and aggregation to generate a real-time environmental condition data set;

[0063] The convolutional neural network is trained with the labeled sample data to obtain the trained abnormal environment recognition model; the real-time environmental condition data is used as input, and the trained abnormal environment recognition model is used to identify the abnormal environment in the composting fermentation area; if the environmental condition is abnormal, the abnormal proportion of the abnormal condition data is summed up as the abnormality degree, and an abnormal reminder instruction is issued to the outside;

[0064] When in use, when composting organic waste, after determining the normal environmental conditions, the abnormality of the composting environmental conditions is judged by identifying the real-time environmental condition data. If the composting environment is abnormal and has large fluctuations, the environment is adjusted and controlled, for example, by adding temperature and humidity control equipment, etc., to reduce the impact of abnormal environmental conditions on organic waste composting;

[0065] Step 202: pre-set an abnormal adjustment period for environmental conditions. If the number of abnormal reminder instructions issued continuously during the abnormal adjustment period exceeds the expected number, the environmental abnormality coefficient for evaluating the abnormality of the environment is generated in the following manner based on the time point and abnormality degree of issuing the abnormal reminder instruction: :

[0066]

[0067] Where: The total time for the abnormal adjustment cycle; For in time The total number of abnormal reminder instructions accumulated at all times; The total number of acceptable abnormal reminder instructions within the abnormal adjustment period; For in time The abnormality of the moment;

[0068] is the maximum acceptable abnormality, For in time The accumulated value of abnormal time nodes at the moment, is the time weight coefficient, which is used to adjust the impact of time nodes in abnormality evaluation. ;

[0069] Pre-set abnormality thresholds based on historical data and management expectations of the degree of abnormality of environmental conditions;

[0070] If the environmental anomaly coefficient is obtained If the abnormal threshold is exceeded, it means that the frequency of environmental abnormalities in the composting fermentation area is high, and the abnormal situation is serious, which will have a greater negative impact on the composting process. The current composting fermentation state needs to be adjusted. At this time, a compensation control instruction is issued to the outside;

[0071] When using, combine the contents in steps 201 and 202:

[0072] After receiving multiple environmental abnormality alarms in succession, if the abnormal environmental conditions still cannot be adjusted, the environmental abnormality coefficient is generated by the status of each abnormal reminder instruction, and the abnormality of the current composting environmental conditions is analyzed based on the environmental abnormality coefficient. If the abnormality is high, it means that it may not be suitable for composting at present, or auxiliary measures need to be taken in the composting fermentation area, such as shielding, insulation and ventilation equipment, so as to achieve the effect of organic matter fermentation and composting.

[0073] Step 3: The sensor network in the compost pile monitors the fermentation state of the compost pile. If the fermentation state is abnormal, the trained fuzzy control model is used to adjust the fermentation index, and the frequency of turning the compost pile is constrained according to the density of abnormal fermentation state.

[0074] The step three includes the following contents:

[0075] Step 301: after receiving the compensation control instruction, a sensor network is arranged in the compost pile, including a temperature probe, a hygrometer, a pH meter and an oxygen detector, etc., and various fermentation indicators of the compost pile are monitored in real time according to the sensor network, such as temperature, humidity, oxygen concentration, carbon dioxide concentration, pH value, ammonia and other gas concentrations, and organic matter degradation rate;

[0076] The convolutional neural network is trained with the labeled sample data to obtain a trained abnormal data recognition model; the real-time fermentation index is used as input, and the trained abnormal data recognition model is used to identify abnormal indicators. If there are abnormal indicators, an abnormal alarm instruction is issued to the outside;

[0077] When in use, when there is an abnormality in the composting environment, taking into account that the current composting environment is already abnormal, various fermentation indicators are monitored and collected by arranging a sensor network, and abnormal data therein are identified, so that abnormal indicators can be processed in a timely manner;

[0078] Step 302: After training the machine learning algorithm with the labeled sample data, a trained fuzzy control model is obtained;

[0079] After receiving the abnormal alarm instruction, the fermentation index is adjusted according to the pre-set target range using the trained fuzzy control model, and the corresponding compost fermentation control strategy is output; for example, ventilation, water spraying and other control measures are automatically adjusted to improve ventilation conditions, homogenize the temperature and humidity of the pile, and prevent local overheating or overhumidification.

[0080] For example, ventilation ducts can be arranged inside or at the bottom of the pile to transport air through mechanical equipment. Automatic control systems can be installed to adjust the air volume according to the oxygen concentration and temperature to ensure uniform oxygen supply. Humidity can be increased by spraying water or adding materials with high moisture content (such as fresh hay). Humidity can be reduced by turning the pile and increasing ventilation, and if necessary, using drainage systems to remove excess moisture. The pH value can be adjusted by adding lime, wood ash or other alkaline substances to avoid pH values ​​that are too acidic or too alkaline.

[0081] Among them, the optimal temperature range for fermentation is: 55 to 65°C (the ideal temperature inside the compost); external environment: the temperature is more suitable between 15 and 30°C; the optimal humidity range is: 50% to 60%. Too high or too low humidity will affect the activity of microorganisms and fermentation efficiency;

[0082] When in use, after identifying and obtaining abnormal fermentation indicators, the corresponding control strategy is given through the trained control model. According to the control strategy, the composting process can be automatically controlled to ensure the composting effect under abnormal environmental conditions.

[0083] Step 303: Record the time point when the abnormal alarm instruction is received within the preset feedback cycle, and constrain the frequency of turning the pile according to the intensity of the alarm under dimensionless conditions. , the compost pile is turned at the time node that meets the constraints. The constraints are as follows:

[0084]

[0085] Weight coefficient, , n is the number of abnormal alarm instructions, It is i The abnormal alarm instruction to j The time interval of abnormal alarm instructions, is the time interval average;

[0086] When using, combine the contents in steps 301 to 303:

[0087] On the basis of controlling and adjusting the compost fermentation indicators, as a supplementary measure, the frequency of turning the compost is limited and constrained according to the frequency of occurrence of abnormal indicators, so that the number and frequency of turning the compost are consistent with the density of abnormal indicators. By readjusting the compost structure and increasing the contact effect between oxygen and compost, the compost fermentation state and progress are adjusted to ensure the composting effect.

[0088] Step 4: Use the trained compost maturity prediction model to predict the maturity time of the compost pile. If the predicted maturity time does not match the expected time, optimize the fermentation control strategy of the compost pile, and adjust the fermentation index of the compost pile according to the optimized fermentation control strategy;

[0089] The step 4 includes the following contents:

[0090] Step 401: train a convolutional neural network with the labeled sample data to obtain a trained compost maturity prediction model; collect fermentation state data of the compost pile, such as temperature, humidity, oxygen concentration, carbon dioxide concentration, pH value, ammonia and organic matter degradation rate, etc., and also include the color, smell and texture of the compost pile, etc., through the sensor network;

[0091] Taking fermentation status data as input, the trained compost maturity prediction model is used to predict the maturity time of the compost pile and obtain the predicted maturity time. If the predicted maturity time does not meet the expectation, an adjustment instruction is issued to the outside.

[0092] Step 402: after receiving the adjustment instruction, the fermentation index of the compost pile is optimized by the pre-trained genetic algorithm with the expected fermentation time as the optimization target, such as adjusting the temperature, humidity and pH value of the fermentation pile, obtaining the optimized fermentation index, and summarizing it as the fermentation control strategy; executing the fermentation control strategy and adjusting the fermentation index of the compost pile to adjust the fermentation time;

[0093] When using, combine the contents in steps 401 and 402:

[0094] After real-time monitoring and collection of fermentation status data, the maturity time of the compost pile is predicted by using the trained compost maturity prediction model. The compost maturity time can be grasped in real time, and the compost maturity time can be adjusted on the basis of adjusting various fermentation indicators and condition parameters, so that the composting effect and the controllability of the composting effect are higher, and customized composting can be achieved according to composting needs.

[0095] Step 5: After the maturity test of the fermentation pile, the maturity coefficient is constructed based on the maturity of the compost at each sampling point. , if the obtained maturity coefficient If it is below the maturity threshold, the fermentation index should be re-optimized;

[0096] The step five includes the following contents:

[0097] Step 501: After the predicted maturity time, a compost maturity test is performed. Several sampling points are selected inside the compost pile, and sampling and testing are performed at the sampling points to obtain corresponding maturity test data, including organic matter content, carbon-nitrogen ratio, heavy metal content, etc. of the compost, color, smell, texture and temperature change data of the compost, etc., and the compost maturity index set is generated by summarizing;

[0098] The convolutional neural network is trained with the labeled sample data to obtain the maturity recognition model of the trained compost pile. The real-time compost maturity index data is used as input, and the maturity recognition model is used to identify the compost maturity of the sampling point, and the sampling point is marked with the compost maturity.

[0099] When in use, based on the collected data, the maturity of the compost is identified through the maturity recognition model. Compared with manual experience judgment, it has higher accuracy. With the assistance of real-time data, it can also screen out immature areas in the compost pile and continue composting and fermenting the immature areas.

[0100] Step 502: construct a maturity coefficient based on the compost maturity of each sampling point The maturity coefficient is used to evaluate the maturity of the compost pile in the following way:

[0101]

[0102] in, For the i The maturity of each sampling point, For the i The location of the sampling points; To control the width parameter of the interpolation function, the value is between 0.5 and 2 times the average spacing of the sampling points; is the volume of the compost pile; n is the total number of sampling points;

[0103] Pre-set maturity thresholds based on historical data and management expectations of the maturity of the compost;

[0104] If the maturity coefficient is obtained If the temperature is lower than the maturity threshold, it means that the current fermentation effect of the compost pile has not reached the expected level. At this time, the fermentation index should be optimized again, and secondary composting fermentation should be carried out according to the optimized fermentation index until the compost is fully mature.

[0105] If the maturity coefficient is obtained If the value is not lower than the maturity threshold, it means that the compost pile has been composted. At this time, the mature compost is screened to remove large pieces of undegraded matter and impurities, thus completing the composting and fermentation process of organic waste.

[0106] When using, combine the contents in steps 501 and 502:

[0107] Based on the maturity data of each sampling point, a maturity coefficient is constructed by combining several maturity factors together. , according to the maturity coefficient Conduct a holistic assessment of the maturity of the compost to determine whether the compost is mature. Targeted treatment can be carried out based on the results of the judgment to ensure the composting effect.

[0108] See also Figure 2 The present invention provides an aerobic fermentation system for organic waste, comprising:

[0109] The raw material ratio optimization unit builds a composting environment in the composting fermentation area, adjusts the original compost material ratio according to the carbon-nitrogen ratio, stirs the compost material and adds crushed sawdust;

[0110] The abnormal environment recognition unit identifies the environmental condition data in the composting fermentation area. If the environmental condition is abnormal, an environmental abnormality coefficient is generated according to the abnormal state. If the environmental abnormality coefficient exceeds expectations, a compensation control instruction is issued to the outside.

[0111] The fuzzy control unit uses a sensor network inside the compost pile to monitor the fermentation state of the compost pile. If there is an abnormality in the fermentation state, the trained fuzzy control model is used to adjust the fermentation index, and the frequency of turning the compost pile is constrained according to the density of abnormalities in the fermentation state.

[0112] The compost prediction unit uses the trained compost maturity prediction model to predict the maturity time of the compost pile. If the predicted maturity time does not match the expected time, the fermentation control strategy of the compost pile is optimized, and the fermentation index of the compost pile is adjusted according to the optimized fermentation control strategy;

[0113] The maturity assessment unit conducts maturity testing on the fermentation pile and constructs a maturity coefficient based on the maturity of the compost at each sampling point. If the obtained maturity coefficient is lower than the maturity threshold, the fermentation index is re-optimized.

[0114] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0115] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0116] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0120] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0121] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An aerobic fermentation system for organic waste, characterized in that: include, The raw material ratio optimization unit, after building the composting environment in the composting fermentation area, adjusts the ratio of the original composting materials according to the carbon-nitrogen ratio, stirs the composting materials and adds crushed sawdust; Abnormal environment identification unit, identifies the environmental condition data in the composting fermentation area, and generates an environmental abnormality coefficient based on the abnormal state if the environmental condition is abnormal , if the environmental anomaly coefficient If the number of abnormal warning instructions issued continuously during the abnormal adjustment period exceeds expectations, the environmental abnormality coefficient is generated according to the following method based on the time node and abnormality degree of issuing the abnormal warning instruction. : ； Where: The total time for the abnormal adjustment cycle; For in time The total number of abnormal reminder instructions accumulated at all times; The total number of acceptable abnormal reminder instructions within the abnormal adjustment period; For in time The abnormality of the moment; is the maximum acceptable abnormality, For in time The accumulated value of abnormal time nodes at the moment, is the time weight coefficient, which is used to adjust the impact of time nodes in abnormality evaluation. ; The fuzzy control unit uses a sensor network inside the compost pile to monitor the fermentation state of the compost pile. If there is an abnormality in the fermentation state, the trained fuzzy control model is used to adjust the fermentation index, and the frequency of turning the compost pile is constrained according to the density of abnormalities in the fermentation state. The time point when the abnormal alarm instruction is received is recorded within the preset feedback cycle. Under dimensionless conditions, the frequency of turning the pile is constrained according to the intensity of the alarm. , the compost pile is turned at the time node that meets the constraints. The constraints are as follows: ； Weight coefficient, , is the number of abnormal alarm instructions, It is The abnormal alarm instruction to The time interval of abnormal alarm instructions, is the time interval average; The compost prediction unit uses the trained compost maturity prediction model to predict the maturity time of the compost pile. If the predicted maturity time does not match the expected time, the fermentation control strategy of the compost pile is optimized, and the fermentation index of the compost pile is adjusted according to the optimized fermentation control strategy; Maturity assessment unit, after the maturity test of the fermentation pile, the maturity coefficient is constructed based on the maturity of the compost at each sampling point , if the obtained maturity coefficient If the compost is below the maturity threshold, the fermentation index is re-optimized; the maturity coefficient is constructed based on the maturity of the compost at each sampling point. , as follows: ； in, For the The maturity of each sampling point, For the The location of the sampling points; To control the width parameter of the interpolation function, the value is between 0.5 and 2 times the average spacing of the sampling points; is the volume of the compost pile; is the total number of sampling points; If the maturity coefficient is obtained If the temperature is below the maturity threshold, the fermentation index is optimized again, and the compost pile is fermented again according to the optimized fermentation index until the compost is fully mature. If the maturity coefficient is obtained Not less than the maturity threshold, the mature compost is screened to remove large pieces of undegraded matter and impurities, completing the composting fermentation process of organic waste.

2. The aerobic fermentation system for organic waste according to claim 1, characterized in that: After selecting the composting fermentation area, build the composting environment in the composting fermentation area, and determine the shape and size of the compost pile according to the compost pile design; estimate the carbon-nitrogen ratio of the original compost material. If the estimated carbon-nitrogen ratio is not within the target range, adjust the proportion of the original compost material according to the carbon-nitrogen ratio; Before the adjusted compost material is uniformly mixed, crushed wood chips are added to the compost material, and a positive correlation is established between the wood chips and the carbon-nitrogen ratio.

3. The aerobic fermentation system for organic waste according to claim 2, characterized in that: Collect and monitor environmental condition data in the composting fermentation area in real time, and generate a real-time environmental condition data set; Taking real-time environmental condition data as input, the trained abnormal environment recognition model is used to identify abnormal environments in the composting fermentation area; if there are abnormal environmental conditions, the abnormal proportions of the abnormal condition data are summed up as the abnormality degree, and an abnormal reminder instruction is issued to the outside.

4. The aerobic fermentation system for organic waste according to claim 3, characterized in that: After receiving the compensation control instruction, a sensor network is arranged in the compost pile, and various fermentation indicators of the compost pile are monitored in real time based on the sensor network; the real-time fermentation indicator is used as input, and the trained abnormal data recognition model is used to identify abnormal indicators. If there is an abnormal indicator, an abnormal alarm instruction is issued to the outside; After receiving the abnormal alarm instruction, the fermentation index is adjusted according to the pre-set target range using the trained fuzzy control model, and the corresponding compost fermentation control strategy is output; After receiving the adjustment instruction, the fermentation index of the compost pile is optimized by the pre-trained genetic algorithm with the expected fermentation time as the optimization target, and the optimized fermentation index is obtained and summarized as the fermentation control strategy.

5. The aerobic fermentation system for organic waste according to claim 4, characterized in that: Select several sampling points inside the compost pile, perform sampling and testing at the sampling points, obtain corresponding maturity test data, and summarize and generate a compost maturity index set; Taking real-time compost maturity index data as input, the trained maturity recognition model is used to identify the compost maturity of the sampling points, and the sampling points are marked with the compost maturity.

Images