Organic waste resource processing method and system based on biological fermentation

Abstract

The present application relates to waste treatment technical field, especially to a kind of based on organic waste resource processing method and system of biological fermentation, comprising: to be treated organic waste executes pretreatment modulation operation, and executes anaerobic fermentation, obtains fermentation liquor, ammonia stripping treatment is executed to fermentation liquor and pH back call, obtains back call biogas slurry, back call biogas slurry is introduced into the fermentation liquor executes anaerobic fermentation, obtains fermentation environment, based on pre-constructed multiple sampling points to fermentation environment executes environment parameter collection, and based on the multiple environment parameter group set of collection identifies ammonia inhibition precursor area, and then predict the multiple free ammonia concentrations of ammonia inhibition precursor area, based on multiple free ammonia concentrations complete organic waste resource processing.The present application guarantees the efficient resource processing of organic waste at the same time, realizes the biological fermentation processing method of free ammonia concentration grading control, to improve system operation stability and reduce ammonia inhibition risk.

Description

Technical Field

[0001] This invention relates to the field of waste treatment technology, and in particular to a method and system for the resource-based treatment of organic waste based on bio-fermentation. Background Technology

[0002] With the increasing demand for the resource utilization of organic waste, anaerobic treatment technology based on bio-fermentation has been widely used for the reduction and energy conversion of organic waste. However, under conditions of high-nitrogen organic waste or high-load operation, ammonia nitrogen accumulates continuously in the fermentation system, especially the concentration of free ammonia increases, which can easily inhibit functional microorganisms such as methanogens, leading to a decrease in fermentation efficiency or even system instability.

[0003] In existing technologies, methods such as adjusting the carbon-to-nitrogen ratio, dilution treatment, adding exogenous additives, or ammonia stripping are commonly used to alleviate ammonia inhibition. Among these, ammonia stripping, as a common ammonia removal method, often employs a fixed operating mode, i.e., continuous gas-liquid mass transfer during fermentation to reduce ammonia concentration. However, this method often lacks a dynamic adjustment mechanism for changes in ammonia concentration. Continuing high-intensity operation when ammonia concentration is within a safe range easily increases energy consumption; and when ammonia concentration rises rapidly, there is a lack of staged enhancement measures, making it difficult to promptly suppress the risk of ammonia inhibition.

[0004] In addition, existing fermentation control methods mostly adopt single-parameter adjustment or empirical control strategies, lacking a dynamic hierarchical control mechanism based on multiple operating parameters, and failing to take differentiated treatment measures under different ammonia risk levels, resulting in insufficient system stability under high load operating conditions.

[0005] Therefore, there is an urgent need for a bio-fermentation treatment method that can achieve graded control of free ammonia concentration while ensuring efficient resource utilization of organic waste, so as to improve system operation stability and reduce the risk of ammonia inhibition. Summary of the Invention

[0006] This invention provides a method for the resource-based treatment of organic waste based on bio-fermentation and a computer-readable storage medium. Its main purpose is to improve the system's operational stability and reduce the risk of ammonia inhibition by achieving a bio-fermentation treatment method with graded control of free ammonia concentration while ensuring efficient resource-based treatment of organic waste.

[0007] To achieve the above objectives, the present invention provides a method for the resource-based treatment of organic waste based on bio-fermentation, comprising:

[0008] Acquire organic waste to be processed;

[0009] The organic waste to be treated is pretreated and prepared to obtain fermentation substrate;

[0010] Anaerobic fermentation was performed on the fermentation substrate to obtain the fermentation broth;

[0011] The fermentation broth was subjected to ammonia stripping treatment to obtain stripped biogas slurry;

[0012] A pH adjustment process is performed on the stripped biogas slurry to obtain adjusted biogas slurry;

[0013] The recycled biogas slurry is introduced into the fermentation broth to perform anaerobic fermentation, thus obtaining the fermentation environment;

[0014] Environmental parameters were collected from the fermentation environment based on multiple pre-constructed sampling points, resulting in multiple sets of environmental parameters. Each set of environmental parameters corresponds to a sampling point and includes sets of pH, total ammonia nitrogen, redox potential, and temperature.

[0015] A three-dimensional map of fermentation status was constructed based on multiple sets of environmental parameters;

[0016] Identification of ammonia inhibition precursor regions based on three-dimensional fermentation state maps;

[0017] Based on the ammonia suppression precursor region, multiple ammonia suppression parameter sets are extracted from multiple environmental parameter sets. Based on the multiple ammonia suppression parameter sets, multiple free ammonia concentrations are predicted using a pre-constructed free ammonia concentration prediction model.

[0018] Organic waste is recycled based on multiple free ammonia concentrations.

[0019] Optionally, the identification of ammonia inhibition precursor regions based on the three-dimensional map of fermentation state includes:

[0020] Calculate the rate of change of redox potential at each of the multiple sampling points to obtain multiple rates of change of redox potential.

[0021] Spatial interpolation was performed on the rate of change of multiple redox potentials based on the three-dimensional map of fermentation state to obtain the rate of change distribution.

[0022] Candidate regions for ammonia suppression precursors were identified based on the rate of change distribution;

[0023] Set a time window, and monitor the rate of change of candidate regions for ammonia inhibition precursors based on the time window to obtain a rate of change map;

[0024] Based on the rate of change map, the ammonia suppression precursor region was identified from the candidate regions of ammonia suppression precursor.

[0025] Optionally, the prediction of multiple free ammonia concentrations based on multiple ammonia suppression parameter sets and using a pre-built free ammonia concentration prediction model includes:

[0026] Historical ammonia suppression parameter sets are obtained based on multiple ammonia suppression parameter sets, wherein the historical ammonia suppression parameter sets include multiple historical ammonia suppression parameter sets;

[0027] Extract one historical ammonia suppression parameter set sequentially from the historical ammonia suppression parameter set to obtain the target ammonia suppression parameter set. Perform the following operations on the target ammonia suppression parameter set:

[0028] Perform parameter denoising on the target ammonia suppression parameter set to obtain a denoised parameter sequence;

[0029] Summarize the denoising parameter sequences to obtain a denoising parameter sequence set;

[0030] A free ammonia concentration prediction model is constructed based on a denoised parameter sequence set and a pre-built initial free ammonia concentration prediction model.

[0031] Perform parameter denoising operation on multiple ammonia suppression parameter sets to obtain multiple ammonia suppression parameter sequence sets;

[0032] Multiple free ammonia concentrations are predicted based on a set of multiple ammonia suppression parameter sequences and a free ammonia concentration prediction model.

[0033] Optionally, the step of performing parameter denoising on the target ammonia suppression parameter set to obtain a denoised parameter sequence includes:

[0034] Obtain multiple noise parameter sequences;

[0035] Multiple ammonia-suppressed noise sequences were obtained based on multiple noise parameter sequences and a target ammonia suppression parameter set;

[0036] For each of the multiple ammonia-suppressed noise sequences, perform the following operation:

[0037] Multi-scale decomposition was performed on the ammonia-suppressed noise sequence to obtain multiple ammonia-suppressed scale sequences;

[0038] By summing up multiple ammonia-suppressed scale sequences, multiple sets of ammonia-suppressed scale sequences are obtained;

[0039] Denoising parameter sequences were obtained based on multiple ammonia-suppressed scale sequence sets.

[0040] Optionally, obtaining the denoising parameter sequence based on multiple ammonia suppression scale sequence sets includes:

[0041] Set an initial particle swarm, which consists of multiple initial particles.

[0042] Extract one initial particle sequentially from multiple initial particles to obtain the target initial particle, and perform the following operations on the target initial particle:

[0043] Sequence sorting was performed on multiple ammonia suppression scale sequence sets to obtain an ammonia suppression sorted sequence set;

[0044] Based on the target initial particle ammonia suppression sorting sequence set, a sequence retention operation is performed to obtain the historical retained sequence set;

[0045] Construct a historical retention parameter set based on the historical retention sequence set;

[0046] Calculate the fitness function values ​​between the target ammonia suppression parameter set and the historical retention parameter set;

[0047] Summarize the fitness function values ​​to obtain multiple fitness function values;

[0048] The particle parameters of the initial particle swarm are updated based on multiple fitness function values ​​to obtain the updated particle swarm.

[0049] A denoising parameter sequence is constructed based on the updated particle swarm and ammonia-suppressed sorted sequence set.

[0050] Optionally, the construction of the free ammonia concentration prediction model based on the denoised parameter sequence set and the pre-constructed initial free ammonia concentration prediction model includes:

[0051] Obtain the initial concentration prediction parameter set of the initial free ammonia concentration prediction model, wherein the initial concentration prediction parameter set includes multiple initial concentration prediction parameter sets;

[0052] Multiple initial prediction fitnesss are calculated based on the initial concentration prediction parameter set and the denoised parameter sequence set;

[0053] Perform a parameter update operation on the initial concentration prediction parameter set to obtain an updated concentration prediction parameter set. The updated concentration prediction parameter set includes multiple updated concentration prediction parameter sets, and each updated concentration prediction parameter set corresponds one-to-one with the initial concentration prediction parameter set.

[0054] Multiple updated prediction fitnesss are calculated based on the updated concentration prediction parameter set and the denoised parameter sequence set;

[0055] Calculate multiple fitness changes based on multiple initial predicted fitness and multiple updated predicted fitness;

[0056] If among multiple fitness changes there is a fitness change that is less than or equal to a pre-built change threshold, then the minimum value among the multiple fitness changes is extracted to obtain the minimum change, and the updated concentration prediction parameter set corresponding to the minimum change is determined to obtain the concentration prediction parameter set.

[0057] A free ammonia concentration prediction model was constructed based on the concentration prediction parameter set.

[0058] Optionally, the process of recycling organic waste based on multiple free ammonia concentrations includes:

[0059] Obtain the normal concentration threshold, emergency concentration threshold, and critical concentration threshold, wherein the normal concentration threshold is less than the emergency concentration threshold, and the emergency concentration threshold is less than the critical concentration threshold;

[0060] Multiple free ammonia concentrations are compared with normal concentration thresholds, emergency concentration thresholds, and critical concentration thresholds to obtain multiple comparison results. Based on these multiple comparison results and the set of multiple ammonia inhibition parameters, the resource utilization treatment of organic waste is completed.

[0061] Optionally, the step of completing the resource utilization treatment of organic waste based on multiple comparison results and the multiple sets of ammonia inhibition parameters includes:

[0062] The results of multiple comparisons are classified to obtain four sets of classification results;

[0063] Extract the target classification set from the four classification result sets. The target classification set is the set of classification result sets where the free ammonia concentration is greater than the normal concentration threshold and less than or equal to the emergency concentration threshold.

[0064] Based on the target classification set, connected component analysis is performed on multiple ammonia suppression parameter sets to obtain multiple connected ammonia suppression parameter sets. Then, one connected ammonia suppression parameter set is extracted sequentially from each of these sets to obtain the target connected parameter set. The following operations are then performed on the target connected parameter set:

[0065] Construct an organic load objective function, and obtain a set of ammonia suppression environment parameter values ​​based on the organic load objective function and the objective connectivity parameter set;

[0066] By summarizing the sets of ammonia suppression environmental parameter values, multiple sets of ammonia suppression environmental parameter values ​​are obtained;

[0067] Organic waste resource utilization was achieved based on multiple sets of ammonia inhibition environmental parameter values.

[0068] Optionally, the process of completing the resource utilization treatment of organic waste based on multiple sets of ammonia inhibition environmental parameters includes:

[0069] For each set of ammonia suppression environmental parameter values ​​from multiple sets of values, the following operation is performed:

[0070] Temperature values ​​were extracted from the set of ammonia suppression environmental parameters.

[0071] If the temperature value is a pre-constructed positive number, then the heat storage operation is performed based on the pre-constructed solar thermal collector unit to obtain the energy storage heat unit. The fermentation environment is then heated based on the energy storage heat unit to obtain the heated fermentation environment.

[0072] By summarizing the heating and fermentation environments, multiple heating and fermentation environments were obtained, and the resource utilization of organic waste was completed based on these multiple heating and fermentation environments.

[0073] To achieve the above objectives, the present invention also provides an organic waste resource utilization system based on bio-fermentation, comprising:

[0074] The biological fermentation module is used to acquire organic waste to be treated, perform pretreatment and conditioning operations on the organic waste to be treated to obtain fermentation substrate, perform anaerobic fermentation on the fermentation substrate to obtain fermentation broth, perform ammonia stripping treatment on the fermentation broth to obtain stripped biogas slurry, perform pH adjustment on the stripped biogas slurry to obtain adjusted biogas slurry, and introduce the adjusted biogas slurry into the fermentation broth for anaerobic fermentation to obtain a fermentation environment;

[0075] The region identification module is used to collect environmental parameters of the fermentation environment based on multiple pre-constructed sampling points, and obtain multiple sets of environmental parameters. Each set of environmental parameters corresponds one-to-one with a sampling point. The environmental parameter sets include pH, total ammonia nitrogen, redox potential and temperature. A three-dimensional map of the fermentation state is constructed based on the multiple sets of environmental parameters, and the ammonia inhibition precursor region is identified based on the three-dimensional map of the fermentation state.

[0076] The concentration prediction module is used to extract multiple ammonia inhibition parameter sets from multiple environmental parameter sets based on the ammonia inhibition precursor region, and to predict multiple free ammonia concentrations based on the multiple ammonia inhibition parameter sets using a pre-built free ammonia concentration prediction model.

[0077] The concentration control module is used to complete the resource recovery treatment of organic waste based on multiple free ammonia concentrations.

[0078] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0079] A memory for storing at least one instruction; and a processor for executing the instructions stored in the memory to implement the above-described method for the resource recovery of organic waste based on bio-fermentation.

[0080] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the above-described method for the resource recovery of organic waste based on bio-fermentation.

[0081] To address the problems described in the background art, this invention obtains organic waste to be treated, performs pretreatment and conditioning operations on the organic waste to obtain a fermentation substrate, performs anaerobic fermentation on the fermentation substrate to obtain a fermentation broth, performs ammonia stripping treatment on the fermentation broth to obtain stripped biogas slurry, performs pH adjustment on the stripped biogas slurry to obtain adjusted biogas slurry, and introduces the adjusted biogas slurry into the fermentation broth for anaerobic fermentation to obtain a fermentation environment. This invention couples the ammonia stripping treatment with the fermentation process to achieve online ammonia removal and reuse of the fermentation broth, reducing the amount of external dilution water used and improving the treatment efficiency of organic waste. Simultaneously, this invention collects environmental parameters from multiple pre-constructed sampling points to obtain multiple sets of environmental parameters. Each set of environmental parameters corresponds one-to-one with a sampling point and includes pH, total ammonia nitrogen, redox potential, and temperature sets. A three-dimensional map of the fermentation state is constructed based on these multiple sets of environmental parameters, and the precursory regions of ammonia inhibition are identified based on this three-dimensional map. This invention utilizes the sensitive response characteristics of redox potential to ammonia inhibition to achieve early identification and spatial localization of precursory ammonia inhibition. Furthermore, this invention extracts multiple ammonia inhibition parameter sets from multiple environmental parameter sets based on the ammonia inhibition precursor region. Based on these multiple ammonia inhibition parameter sets, a pre-constructed free ammonia concentration prediction model is used to predict multiple free ammonia concentrations. Based on these multiple free ammonia concentrations, the organic waste is then processed for resource recovery. This invention employs a combination of multi-scale decomposition and particle swarm optimization. First, parameter denoising is performed on the target ammonia inhibition parameter sets to obtain a denoised parameter sequence. Then, the prediction model parameters are optimized based on the denoised parameter sequence set, thereby improving the accuracy of free ammonia concentration prediction and providing a foundation for subsequent free ammonia concentration regulation. Simultaneously, this invention also uses an organic load objective function to perform graded regulation of free ammonia concentration while maximizing the organic load rate, reducing the free ammonia concentration to the normal concentration threshold, improving system stability and reducing the risk of ammonia inhibition. Therefore, this invention can achieve graded regulation of free ammonia concentration in a bio-fermentation treatment method while ensuring efficient resource recovery of organic waste, thereby improving system stability and reducing the risk of ammonia inhibition. Attached Figure Description

[0082] Figure 1 This is a schematic flowchart of an organic waste resource utilization method based on bio-fermentation provided in an embodiment of the present invention.

[0083] Figure 2 A functional block diagram of an organic waste resource utilization system based on bio-fermentation provided in an embodiment of the present invention;

[0084] Figure 3 This is a schematic diagram of the structure of an electronic device for implementing the organic waste resource utilization method based on bio-fermentation, according to an embodiment of the present invention.

[0085] Explanation of reference numerals in the attached figures:

[0086] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0087] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0088] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0089] This application provides a method for the resource recovery and treatment of organic waste based on bio-fermentation. The executing entity of the method includes, but is not limited to, at least one electronic device that can be configured to execute the method provided in this application, such as a server or a terminal. In other words, the method can be executed by software or hardware installed on a terminal device or a server device, and the software may be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0090] Reference Figure 1 The diagram shown is a schematic flow chart of an organic waste resource recovery method based on bio-fermentation provided by an embodiment of the present invention. In this embodiment, the organic waste resource recovery method based on bio-fermentation includes:

[0091] S1. Obtain the organic waste to be treated, perform pretreatment and conditioning operations on the organic waste to be treated to obtain fermentation substrate, perform anaerobic fermentation on the fermentation substrate to obtain fermentation broth, perform ammonia stripping treatment on the fermentation broth to obtain stripped biogas slurry, perform pH adjustment on the stripped biogas slurry to obtain adjusted biogas slurry, and introduce the adjusted biogas slurry into the fermentation broth to perform anaerobic fermentation to obtain a fermentation environment.

[0092] It should be noted that the organic waste to be treated refers to organic waste that needs to be treated, such as agricultural organic waste (mainly including crop straw and vines, livestock and poultry manure, etc.), industrial organic waste (mainly including organic waste residue, etc.), and municipal organic waste (mainly including garden and greening waste, municipal sludge, animal contents from slaughterhouses, kitchen waste, etc.).

[0093] Specifically, the pretreatment and conditioning operation of the organic waste to be treated is a series of operations performed to make the organic waste suitable for fermentation, including crushing and removing impurities. The crushing refers to using a crusher (e.g., a straw crusher or a wet crusher) to crush the organic waste to be treated into organic waste with a smaller particle diameter, thereby increasing the contact area between the organic waste and microorganisms, improving the decomposition rate, and achieving efficient utilization of the organic waste.

[0094] It should be understood that impurities need to be removed in order to prevent sand or pebbles from settling at the bottom of the tank, occupying effective volume (commonly known as sedimentation), to prevent plastic or fabric from entangled in the agitator (causing motor overload and burnout), to prevent hard objects from clogging pipes and valves, and to remove impurities that may contain heavy metals or toxins, thus preventing impurities from entering the fermentation environment and poisoning microorganisms. The specific process for removing impurities involves using an impurity removal machine to screen out organic waste free of impurities. For example, for lightweight impurities such as plastic bags, fabrics, and paper, an impurity removal machine (such as an air separator) uses airflow to blow away lightweight plastic films and paper, while heavier organic matter falls. For heavy impurities such as pebbles, glass, sand, and shells, an impurity removal machine (such as a hydraulic pulper) is used. After adding water, it rotates at high speed, using hydraulic friction to pulverize the organic waste into a pulp, while heavy objects (such as bottle caps and bowl fragments) sink to the bottom and are periodically discharged. For other types of waste (such as medicinal residue), there are existing machines for impurity removal, which will not be elaborated upon here. It is clear that if there are multiple different types of impurities (a mixture of light and heavy impurities), the impurities can be removed by combining multiple impurity removal machines.

[0095] In detail, the anaerobic fermentation of the fermentation substrate refers to the process by which microorganisms (such as methanogens and clostridium) convert the fermentation substrate into combustible gases (such as methane and carbon dioxide) under anaerobic conditions. Therefore, the anaerobic fermentation is also known as biogas fermentation, thereby realizing the resource-based treatment of organic waste.

[0096] Importantly, the fermentation broth is the product of anaerobic fermentation of the fermentation substrate, containing incompletely degraded fermentation substrate, ammonia, nutrients, etc. Therefore, the fermentation broth can be treated with ammonia stripping and other methods, maximizing the resource utilization of organic waste through secondary use of the fermentation broth.

[0097] It should be explained that, according to the basic theory of existing biological fermentation, during anaerobic fermentation, free ammonia inhibits the efficiency of converting organic waste into combustible gases. The higher the concentration of free ammonia, the lower the survival rate of microorganisms, resulting in a lower efficiency of converting organic waste into combustible gases. Since free ammonia exists in the fermentation broth, it is necessary to perform ammonia stripping treatment on the fermentation broth to remove the ammonia and prevent the ammonia from decomposing into free ammonia during the secondary use of the fermentation broth, thus reducing the efficiency of anaerobic fermentation.

[0098] Specifically, the ammonia stripping treatment of the fermentation broth involves using a gas (usually air or nitrogen) to strip ammonia from the fermentation broth, thereby reducing the ammonia concentration in the liquid and obtaining stripped biogas slurry. Since the ammonia stripping process causes a change in the pH of the fermentation broth, making the stripped biogas slurry unsuitable for microbial growth, a pH adjustment operation is required. This involves adding an acid (e.g., hydrochloric acid) or an alkali (e.g., sodium hydroxide solution) to the stripped biogas slurry to obtain a adjusted biogas slurry, thus adjusting the pH to the target range (the range of pH suitable for microbial survival).

[0099] It is clear that the fermentation environment refers to the fermentation broth in which the biogas slurry is introduced and anaerobic fermentation is performed.

[0100] S2. Based on multiple pre-constructed sampling points, environmental parameters are collected from the fermentation environment to obtain multiple sets of environmental parameters. Each set of environmental parameters corresponds to a sampling point and includes a pH set, a total ammonia nitrogen set, a redox potential set, and a temperature set.

[0101] It is understood that the sampling points are artificially preset locations used to collect values ​​of multiple environmental parameters related to the fermentation environment. The environmental parameter set includes a pH group, a total ammonia nitrogen group, a redox potential group, and a temperature group. The pH group is a collection of multiple pH values ​​from multiple samples at a single sampling point; the total ammonia nitrogen group is a collection of multiple total ammonia nitrogen values ​​from multiple samples at a single sampling point; the redox potential group is a collection of multiple redox potential values ​​from multiple samples at a single sampling point; and the temperature group is a collection of multiple temperatures from multiple samples at a single sampling point. Each sampling corresponds to a sampling time, and the sampling frequencies for the pH group, total ammonia nitrogen group, redox potential group, and temperature group are the same. The sampling frequency refers to the number of times environmental parameters are collected per unit time. For example, if the unit time is set to 1 hour and the number of times is set to 60, then the sampling frequency is 60 times / hour, and each sampling time is considered a sampling time. pH, total ammonia nitrogen, and temperature are all known factors affecting free ammonia concentration. Oxidation-reduction potential is an indicator reflecting changes in free ammonia concentration. The detection of pH, total ammonia nitrogen, oxidation-reduction potential, and temperature are all performed using existing instruments (such as industrial online pH meters and online ammonia nitrogen analyzers), which will not be elaborated upon here.

[0102] Importantly, the set of multiple environmental parameters is used to identify ammonia suppression precursor regions and predict free ammonia concentrations, among other operations.

[0103] S3. Construct a three-dimensional map of fermentation state based on multiple sets of environmental parameters, and identify the precursor region of ammonia inhibition based on the three-dimensional map of fermentation state.

[0104] It should be noted that the construction of a three-dimensional map of fermentation state based on multiple sets of environmental parameters refers to constructing a three-dimensional model of the surface of the fermentation environment based on the spatial coordinates of multiple sampling points, and then marking the surface and interior of the three-dimensional model based on the three-dimensional spatial coordinates of the surface model and the three-dimensional spatial coordinates of each environmental parameter collected from multiple sets of environmental parameters, thereby constructing a three-dimensional map of fermentation state.

[0105] It is clear that the organic waste is solid, and the bio-fermentation is the fermentation of solid matter in a fermentation tank or biogas digester. Therefore, a three-dimensional model of the surface of the fermentation environment is constructed based on the spatial coordinates of the multiple sampling points.

[0106] Furthermore, the identification of ammonia inhibition precursor regions based on the three-dimensional map of fermentation state includes:

[0107] Calculate the rate of change of redox potential at each of the multiple sampling points to obtain multiple rates of change of redox potential.

[0108] Spatial interpolation was performed on the rate of change of multiple redox potentials based on the three-dimensional map of fermentation state to obtain the rate of change distribution.

[0109] Candidate regions for ammonia suppression precursors were identified based on the rate of change distribution;

[0110] Set a time window, and monitor the rate of change of candidate regions for ammonia inhibition precursors based on the time window to obtain a rate of change map;

[0111] Based on the rate of change map, the ammonia suppression precursor region was identified from the candidate regions of ammonia suppression precursor.

[0112] It should be noted that the rate of change of redox potential refers to the rate at which the redox potential changes. It is calculated by dividing the difference between the redox potential sampled at the current moment and the redox potential sampled at the previous moment by the difference between the current and previous moments. For example, if the sampling frequency is 60 times / hour, then a sample is collected every minute. If the current moment is 9:01, then the previous moment was 9:00, with a time difference of 1 minute. If the redox potential sampled at the current moment is the second redox potential, and the redox potential sampled at the previous moment is the first redox potential, then the rate of change of redox potential is (second redox potential - first redox potential) / 1 minute.

[0113] It should be understood that the aforementioned rate of change distribution refers to the distribution of redox potential change rates obtained after spatial interpolation of multiple redox potential change rates in the three-dimensional fermentation state map. This avoids the inability to identify spatial locations where no sampling points exist, which may be precursory regions of ammonia inhibition. The specific process of spatial interpolation involves interpolating multiple redox potential change rates using three-dimensional kriging interpolation in the three-dimensional fermentation state map. Three-dimensional kriging interpolation is existing technology and will not be elaborated upon here.

[0114] Importantly, the identification of ammonia inhibition precursor candidate regions based on the rate of change distribution involves determining ammonia inhibition candidate sites by comparing the absolute values ​​of multiple redox potential change rates in the rate of change distribution with a preset rate of change threshold. If the absolute value of a redox potential change rate is greater than the rate of change threshold, the corresponding spatial location is confirmed as an ammonia inhibition candidate site; otherwise, it is not marked as an ammonia inhibition candidate site. A set of ammonia inhibition candidate sites can be identified based on multiple redox potential change rates, and this set is confirmed as ammonia inhibition precursor candidate region. It should be noted that the rate of change threshold is set based on historical experience, using the redox potential change rates of historical ammonia inhibition regions; that is, the average value of multiple redox potential change rates in historical biofermentation environments that were ammonia inhibition regions is calculated as the rate of change threshold.

[0115] It should be explained that the time window is a pre-defined time range. The monitoring of the rate of change in ammonia inhibition precursor candidate regions based on the time window involves obtaining a set of redox potential (OPP) change rates for the candidate regions from multiple environmental parameter sets. Specifically, obtaining the OPP change rate set for the candidate regions involves extracting the corresponding OPP sets from multiple environmental parameter sets and calculating the OPP change rate set based on these sets. For example, if the time window is set to 1 hour, then the monitoring of the rate of change in ammonia inhibition precursor candidate regions based on the time window involves obtaining the OPP change rate within the candidate regions within 1 hour, resulting in a rate of change map. The rate of change map is a three-dimensional spatial model, which is a line graph showing the rate of change of OPP associated with ammonia inhibition candidate points within one hour. The horizontal axis of the line graph represents time, and the vertical axis represents the rate of change of OPP.

[0116] In detail, the calculation of the redox potential change rate set based on the redox potential set involves determining the redox potential set corresponding to each ammonia suppression candidate point in the ammonia suppression precursor candidate region, using two redox potentials as sliding windows with a step size of one redox potential to slide and truncate the redox potential set, obtaining multiple redox potential windows, calculating the redox potential change rate of each redox potential window in the multiple redox potential windows, and obtaining the redox potential change rate set. One redox potential change rate set can be calculated for one ammonia suppression candidate point. If there are multiple ammonia suppression candidate points in the ammonia suppression precursor candidate region, multiple redox potential change rate sets can be calculated, and the multiple redox potential change rate sets are denoted as the redox potential change rate set.

[0117] For example, there exists a set of redox potentials [first redox potential, second redox potential, third redox potential]. Multiple redox potential windows after sliding truncation are designated as the first redox potential window: [first redox potential, second redox potential] and the second redox potential window: [second redox potential, third redox potential]. Similar to the example above, the rate of change of redox potential is (second redox potential - first redox potential) / 1 minute. The first redox rate of change in the first redox potential window and the second redox rate of change in the second redox potential window can be calculated separately, and these two rates are recorded as a group of redox potential rates.

[0118] Furthermore, since the environmental parameters in the bio-fermentation process need to be strictly controlled at the optimal values ​​for bio-fermentation, the environmental parameters and redox potential in the bio-fermentation process do not change instantaneously and drastically, but rather exhibit slow changes with each change lasting for a long time. Under these circumstances, the rate of change of redox potential can continuously characterize the trend of changes in the fermentation state and reflect abnormal change characteristics before ammonia inhibition actually occurs. Therefore, the ammonia inhibition point can be inferred by monitoring the rate of change of redox potential. The process of identifying the ammonia inhibition precursor region from the candidate region based on the rate of change map is based on the rate of change map. The absolute value of the rate of change of redox potential in each group of redox potential changes for each ammonia inhibition candidate point is calculated to obtain the cumulative rate of change. If the cumulative rate of change is greater than the cumulative rate threshold, the ammonia inhibition candidate point is confirmed as an ammonia inhibition point. The ammonia inhibition points are then summarized to obtain the ammonia inhibition precursor region.

[0119] Importantly, the cumulative rate threshold is the average of multiple cumulative change rates in the historical ammonia suppression precursor region.

[0120] S4. Based on the ammonia inhibition precursor region, extract multiple ammonia inhibition parameter sets from multiple environmental parameter sets. Based on the multiple ammonia inhibition parameter sets, use a pre-constructed free ammonia concentration prediction model to predict multiple free ammonia concentrations.

[0121] It is understood that the extraction of multiple ammonia inhibition parameter sets from multiple environmental parameter sets based on the ammonia inhibition precursor region refers to extracting the ammonia inhibition parameter set corresponding to each ammonia inhibition point in the ammonia inhibition precursor region from multiple environmental parameter sets. The ammonia inhibition parameter set includes temperature set, total ammonia nitrogen set, and pH set.

[0122] Furthermore, the prediction of multiple free ammonia concentrations based on multiple ammonia suppression parameter sets and using a pre-built free ammonia concentration prediction model includes:

[0123] Historical ammonia suppression parameter sets are obtained based on multiple ammonia suppression parameter sets, wherein the historical ammonia suppression parameter sets include multiple historical ammonia suppression parameter sets;

[0124] Extract one historical ammonia suppression parameter set sequentially from the historical ammonia suppression parameter set to obtain the target ammonia suppression parameter set. Perform the following operations on the target ammonia suppression parameter set:

[0125] Perform parameter denoising on the target ammonia suppression parameter set to obtain a denoised parameter sequence;

[0126] Summarize the denoising parameter sequences to obtain a denoising parameter sequence set;

[0127] A free ammonia concentration prediction model is constructed based on a denoised parameter sequence set and a pre-built initial free ammonia concentration prediction model.

[0128] Perform parameter denoising operation on multiple ammonia suppression parameter sets to obtain multiple ammonia suppression parameter sequence sets;

[0129] Multiple free ammonia concentrations are predicted based on a set of multiple ammonia suppression parameter sequences and a free ammonia concentration prediction model.

[0130] It is clear that obtaining historical ammonia inhibition parameter sets based on multiple ammonia inhibition parameter sets involves acquiring historical data for each of the multiple environmental parameters included in the multiple ammonia inhibition parameter sets, thus obtaining historical ammonia inhibition parameter sets. Multiple environmental parameters can thus yield multiple historical ammonia inhibition parameter sets. It should be noted that the historical data refers to environmental parameters collected during previous bio-fermentation processes prior to the current bio-fermentation process.

[0131] It should be understood that during anaerobic fermentation, environmental parameters are collected in real time using online monitoring equipment, such as online pH meters, ammonia nitrogen analyzers, redox potential sensors, and temperature sensors. However, in actual operation, the collected environmental parameter data may contain noise interference due to various factors.

[0132] Specifically, the noise interference mainly originates from the following aspects: Firstly, online monitoring equipment is susceptible to electromagnetic interference, sensor aging, signal transmission errors, and other factors during long-term operation, leading to random fluctuations in the collected data. Secondly, within the anaerobic fermentation reactor, phenomena such as stirring, gas release, and material flow cause short-term fluctuations in the local environmental conditions, resulting in high-frequency disturbances in the collected environmental parameter data. Furthermore, when the sampling frequency is high, these random fluctuations are further amplified, leading to numerous abnormal fluctuation points in the environmental parameter sequence.

[0133] Importantly, directly using the target ammonia inhibition parameter set, which includes noise interference, for subsequent free ammonia concentration prediction will reduce the accuracy of the prediction model, leading to deviations in the ammonia inhibition state identification results and thus affecting the regulation of the fermentation process. Therefore, to improve the stability and reliability of the target ammonia inhibition parameter set and reduce the impact of noise interference on subsequent data analysis and prediction, this invention requires performing parameter denoising on the target ammonia inhibition parameter set to obtain a smoother denoised parameter sequence that can truly reflect the changing trends of the fermentation environment, providing a reliable data foundation for subsequent free ammonia concentration prediction and fermentation process regulation.

[0134] Furthermore, the parameter denoising operation performed on the target ammonia suppression parameter set to obtain a denoised parameter sequence includes:

[0135] Obtain multiple noise parameter sequences;

[0136] Multiple ammonia-suppressed noise sequences were obtained based on multiple noise parameter sequences and a target ammonia suppression parameter set;

[0137] For each of the multiple ammonia-suppressed noise sequences, perform the following operation:

[0138] Multi-scale decomposition was performed on the ammonia-suppressed noise sequence to obtain multiple ammonia-suppressed scale sequences;

[0139] By summing up multiple ammonia-suppressed scale sequences, multiple sets of ammonia-suppressed scale sequences are obtained;

[0140] Denoising parameter sequences were obtained based on multiple ammonia-suppressed scale sequence sets.

[0141] It should be explained that obtaining multiple noise parameter sequences involves generating two sets of random number sequences composed of multiple random values ​​using a linear congruence generator. The length of each random number sequence is the same as the length of the target ammonia suppression parameter set (containing the same number of data points). Then, a Box-Muller transformation is performed on the two sets of random number sequences to obtain the noise parameter sequences. The linear congruence generator and Box-Muller transformation are performed multiple times according to a preset number of noise sequences to obtain multiple noise parameter sequences. The linear congruence generator and Box-Muller transformation are existing technologies and will not be described in detail here. Specifically, the number of noise sequences can be manually set according to the required precision of the denoising parameter sequences; the larger the number of noise sequences, the higher the precision of the denoising parameter sequences.

[0142] For example, when constructing the denoising parameter sequence, several sets of noise sequences can be artificially generated and summed with the original parameter sequence. The corresponding denoised ammonia suppression scale sequence set is obtained through multiple multi-scale decompositions. When the number of noise sequences is set to 10, 10 sets of ammonia suppression scale sequences are obtained. By summing these 10 sets, the final denoised parameter sequence is obtained. If the number of noise sequences is increased to 50 or 100, more denoised ammonia suppression scale sequence sets can be generated. Multiple averaging processes can effectively offset the influence of random noise on the results, thereby further improving the accuracy of the denoised parameter sequence. The summation is similar to vector addition, which is existing technology and will not be elaborated upon here.

[0143] It should be understood that in practical applications, the number of noise sequences can be determined comprehensively based on the computational complexity and the requirements for denoising accuracy. For example, when the efficiency requirements of biological fermentation are high, 10 to 30 noise sequences can be selected, and when the requirements for denoising accuracy are high, 50 to 100 noise sequences can be selected. Under the premise of meeting the requirements for denoising accuracy, priority should be given to selecting the number of noise sequences that can also take into account computational efficiency.

[0144] In detail, the ammonia suppression noise sequence is the sum of the noise parameter sequence and the target ammonia suppression parameter set.

[0145] Specifically, both the noise parameter sequence and the target ammonia suppression parameter group are sets of environmental parameter values. For example, if the noise parameter sequence is {first environmental parameter value, second environmental parameter value} and the target ammonia suppression parameter group is {third environmental parameter value, fourth environmental parameter value}, then the ammonia suppression noise sequence is {first environmental parameter value + third environmental parameter value, second environmental parameter value + fourth environmental parameter value}.

[0146] It should be noted that the multi-scale decomposition of the ammonia-suppressed noise sequence is performed using the empirical mode decomposition method to obtain multiple ammonia-suppressed scale sequences. The empirical mode decomposition is a prior art and will not be described in detail here.

[0147] Furthermore, the step of obtaining the denoising parameter sequence based on multiple ammonia suppression scale sequence sets includes:

[0148] Set an initial particle swarm, which consists of multiple initial particles.

[0149] Extract one initial particle sequentially from multiple initial particles to obtain the target initial particle, and perform the following operations on the target initial particle:

[0150] Sequence sorting was performed on multiple ammonia suppression scale sequence sets to obtain an ammonia suppression sorted sequence set;

[0151] Based on the target initial particle ammonia suppression sorting sequence set, a sequence retention operation is performed to obtain the historical retained sequence set;

[0152] Construct a historical retention parameter set based on the historical retention sequence set;

[0153] Calculate the fitness function values ​​between the target ammonia suppression parameter set and the historical retention parameter set;

[0154] Summarize the fitness function values ​​to obtain multiple fitness function values;

[0155] The particle parameters of the initial particle swarm are updated based on multiple fitness function values ​​to obtain the updated particle swarm.

[0156] A denoising parameter sequence is constructed based on the updated particle swarm and ammonia-suppressed sorted sequence set.

[0157] It should be noted that the ammonia-suppressed sorting sequence set is a collection of sequences obtained by sorting the ammonia-suppressed scale sequences in each ammonia-suppressed scale sequence set according to their order of appearance in the ammonia-suppressed scale sequence set. The initial particle swarm is a collection of multiple initial particles, each of which represents a sequence preservation scheme used to remove ammonia-suppressed scale sequences containing noise.

[0158] For example, given the existence of a first ammonia-suppressed noise sequence, a second ammonia-suppressed noise sequence, and a third ammonia-suppressed noise sequence, a multi-scale decomposition is performed on each of the three sequences to obtain a first ammonia-suppressed scale sequence set {first ammonia-suppressed scale sequence, second ammonia-suppressed scale sequence}, a second ammonia-suppressed scale sequence set {third ammonia-suppressed scale sequence, fourth ammonia-suppressed scale sequence}, and a third ammonia-suppressed scale sequence set {fifth ammonia-suppressed scale sequence, sixth ammonia-suppressed scale sequence}. Then, after sorting these multiple ammonia-suppressed scale sequence sets, an ammonia-suppressed sorted sequence set {first ammonia-suppressed scale sequence, second ammonia-suppressed scale sequence, third ammonia-suppressed scale sequence, fourth ammonia-suppressed scale sequence, fifth ammonia-suppressed scale sequence, sixth ammonia-suppressed scale sequence} can be obtained.

[0159] As a further example, if the target initial particle is {0,1,1,0,0,0}, the sequence preservation scheme is {0,1,1,0,0,0}, where 0 indicates deletion of the sequence at the corresponding position and 1 indicates retention of the sequence at the corresponding position. Then, after performing the sequence preservation operation on the ammonia-suppressed sorted sequence set based on the target initial particle, the historically preserved sequence set can be obtained as {second ammonia-suppressed scale sequence, third ammonia-suppressed scale sequence}.

[0160] It should be understood that the construction of the historical retention parameter set based on the historical retention sequence set involves calculating the sum of the historical retention sequence set, determining the number of ammonia-suppressed noise sequences contained in the historical retention sequence set, and then dividing the sum of the historical retention sequence set by the number of ammonia-suppressed noise sequences contained therein to obtain the historical retention parameter set.

[0161] Specifically, the operation of calculating the sum of the historically preserved sequence set is as follows: Each historically preserved sequence in the set is treated as a vector, and the sums of these sequences are obtained. This sum is denoted as the historically preserved sum sequence, and the historically preserved parameter set is a vector obtained by dividing each element of the historically preserved sum sequence by the number of ammonia-suppressed noise sequences. The summation operation for any sequence in this invention is similar to the operation of calculating the sum of the historically preserved sequence set and achieves the same effect.

[0162] For example, following the above example, the historical retained sequence set is {second ammonia-suppressed scale sequence, third ammonia-suppressed scale sequence}, where the second ammonia-suppressed scale sequence corresponds to the first ammonia-suppressed noise sequence, the third ammonia-suppressed scale sequence corresponds to the second ammonia-suppressed noise sequence, and the historical retained sequence set does not have an ammonia-suppressed scale sequence corresponding to the third ammonia-suppressed noise sequence. Therefore, the number of ammonia-suppressed noise sequences contained in the historical retained sequence set is 2, and the historical retained parameter set is (second ammonia-suppressed scale sequence + third ammonia-suppressed scale sequence) / 2.

[0163] Understandably, the specific process of calculating the sum of the historically preserved sequence set, i.e., calculating the sum of multiple ammonia suppression scale sequences included in the historically preserved sequence set, is as follows: Extract an ammonia suppression scale sequence from the multiple ammonia suppression scale sequences at this time; sequentially extract an ammonia suppression scale parameter value from the ammonia suppression scale sequence to obtain the target corresponding parameter value; and perform the following operations on the target corresponding parameter value:

[0164] Based on the target corresponding parameter value, multiple corresponding ammonia suppression scale parameter values ​​are extracted from multiple ammonia suppression scale sequences at this time. The sum of multiple corresponding ammonia suppression scale parameter values ​​is calculated to obtain the corresponding ammonia suppression sum value. The corresponding ammonia suppression sum values ​​are summarized to obtain multiple corresponding ammonia suppression sum values ​​corresponding to multiple ammonia suppression scale parameter values ​​in the ammonia suppression scale sequence. According to the correspondence between the ammonia suppression scale parameter values ​​and the corresponding ammonia suppression sum values ​​in the ammonia suppression scale sequence, the multiple corresponding ammonia suppression sum values ​​are arranged in order according to the order of the ammonia suppression scale parameter values ​​in the ammonia suppression scale sequence to obtain the sum of the historical retained sequence set.

[0165] It is understood that the target corresponding parameter value corresponds to a sampling time, and there is a parameter value corresponding to it in multiple ammonia suppression scale sequences at the same sampling time. Therefore, the extraction of multiple corresponding ammonia suppression scale parameter values ​​based on the target corresponding parameter value from multiple ammonia suppression scale sequences at this time can be based on the sampling time, and a parameter value can be extracted from each of the multiple ammonia suppression scale sequences at this time as the corresponding ammonia suppression scale parameter value, thereby obtaining multiple corresponding ammonia suppression scale parameter values.

[0166] Specifically, the fitness function value between the target ammonia suppression parameter group and the historical retention parameter group is calculated using the fitness function value calculation formula. The fitness function value calculation formula is as follows:

[0167]

[0168] in, This represents the fitness function value. This represents the target ammonia suppression parameter set. Indicates the historical parameter group, This represents the mean square error between the target ammonia suppression parameter set and the historically retained parameter set. The entropy of the sequence samples in the historical retention parameter group is represented by . The mean squared error is calculated by taking the average of the squared differences between the squared differences of each target ammonia suppression parameter value in the target ammonia suppression parameter group and the corresponding historical retention parameter value in the historical retention parameter group.

[0169] It is understood that the sequence sample entropy is the sample entropy of the historically retained parameter set. The calculation of sample entropy is a prior art technique, and will not be elaborated upon here. Sample entropy characterizes the amount of noise contained in the historically retained parameter set; the larger the sample entropy, the more noise there is in the historically retained parameter set.

[0170] It should be understood that the updated particle swarm is the particle swarm after updating the particle parameters of the initial particle swarm based on multiple fitness function values. Updating the particle parameters of the initial particle swarm in this invention is a conventional method for updating particles in particle swarm optimization, and will not be elaborated further here. The updated particle swarm is also a sequence preservation scheme.

[0171] In detail, the initial particle swarm is updated by randomly generating a set of particle velocities (a set of changes in multiple initial particles), and the minimum value among multiple fitness function values ​​is determined to obtain the minimum fitness function value. The initial particle corresponding to the minimum fitness function value is identified to obtain the minimum initial particle. The minimum initial particle is identified as the optimal particle. Based on the optimal particle, the changes in the initial particles in the initial particle swarm are added to the initial particles corresponding to the initial particles in the particle velocity set, so that the updated particles are close to the optimal particles, and the updated particles are obtained. The updated particles are then summarized to obtain the updated particle swarm. Here, the change is the adjustment amount of the initial particle. In particular, since the initial particle is the sequence preservation scheme, the adjustment amount is -1, +0, or +1. After adding the change amount to the initial particle, a binary constraint needs to be applied to the initial particle with the added change amount so that each bit of the updated particle is 0 or 1. Otherwise, it may be that what was originally 0 becomes -1 after adding -1, and what was originally 1 becomes 2 after adding 1.

[0172] Importantly, the construction of the denoising parameter sequence based on the updated particle swarm and ammonia-suppressed sorting sequence set involves performing a sequence retention operation on the ammonia-suppressed sorting sequence set based on the updated particle swarm and constructing a new historical retention parameter set. This process involves calculating multiple updated fitness function values, then calculating multiple particle fitness changes between these updated fitness function values ​​and the multiple fitness function values. Finally, the final historical retention sequence set is selected based on the multiple particle fitness changes, and the final historical retention parameter set is constructed based on this final historical retention sequence set. This final historical retention parameter set is denoted as the denoising parameter sequence.

[0173] Understandably, the final historical retention parameter set is as follows: when there is a particle fitness change threshold less than or equal to a preset particle fitness change threshold among multiple particle fitness change values, then the particle fitness change value less than or equal to the preset particle fitness change threshold is extracted from the multiple particle fitness change values ​​to obtain multiple target fitness change values. The minimum value among the multiple target fitness change values ​​is identified to obtain the minimum target fitness change value. The updated particle corresponding to the minimum target fitness change value is determined to obtain the corresponding updated particle. Then, the historical retention sequence set corresponding to the corresponding updated particle is identified, and the historical retention sequence set at this time is used as the final historical retention sequence set, thereby constructing the final historical retention parameter set.

[0174] It should be noted that the particle change threshold is a manually set threshold for particle fitness changes, used to select the optimal particles, and then determine the final historical retention sequence set based on the optimal particles. The smaller the particle change threshold, the smaller the minimum target fitness change, and the smaller the gap between the selected updated particles and the theoretically optimal particles, resulting in better denoising of the final historical retention parameter set. The particle change threshold is preset according to denoising accuracy requirements and computational complexity requirements; when denoising accuracy needs to be improved, the particle change threshold is decreased; when computational efficiency needs to be considered, the particle change threshold is increased. Specifically, the average value of multiple particle fitness changes in historical experience can be used as a reference, and then set according to denoising accuracy requirements and computational complexity, choosing to increase or decrease the average value of multiple particle fitness changes.

[0175] It is clear that the process of performing sequence retention operations on the ammonia suppression sorting sequence set based on the updated particle swarm and constructing a new historical retention parameter set to calculate multiple updated fitness function values ​​is consistent with the process of calculating multiple fitness function values ​​based on the initial particle swarm, and will not be elaborated further here. The process of constructing the final historical retention parameter set based on the final multiple historical retention sequences is consistent with the process of constructing the historical retention parameter set based on multiple historical retention sequences, and will not be elaborated further here.

[0176] Furthermore, the construction of the free ammonia concentration prediction model based on the denoised parameter sequence set and the pre-constructed initial free ammonia concentration prediction model includes:

[0177] Obtain the initial concentration prediction parameter set of the initial free ammonia concentration prediction model, wherein the initial concentration prediction parameter set includes multiple initial concentration prediction parameter sets;

[0178] Multiple initial prediction fitnesss are calculated based on the initial concentration prediction parameter set and the denoised parameter sequence set;

[0179] Perform a parameter update operation on the initial concentration prediction parameter set to obtain an updated concentration prediction parameter set. The updated concentration prediction parameter set includes multiple updated concentration prediction parameter sets, and each updated concentration prediction parameter set corresponds one-to-one with the initial concentration prediction parameter set.

[0180] Multiple updated prediction fitnesss are calculated based on the updated concentration prediction parameter set and the denoised parameter sequence set;

[0181] Calculate multiple fitness changes based on multiple initial predicted fitness and multiple updated predicted fitness;

[0182] If among multiple fitness changes there is a fitness change that is less than or equal to a pre-built change threshold, then the minimum value among the multiple fitness changes is extracted to obtain the minimum change, and the updated concentration prediction parameter set corresponding to the minimum change is determined to obtain the concentration prediction parameter set.

[0183] A free ammonia concentration prediction model was constructed based on the concentration prediction parameter set.

[0184] It should be noted that the initial free ammonia concentration prediction model is a support vector regression model, and the initial concentration prediction parameter set is a collection of multiple initial concentration prediction parameter sets, which are the sets of values ​​for multiple model parameters (e.g., kernel function parameters and penalty coefficients) of the initial free ammonia concentration prediction model. Support vector regression is existing technology, and will not be elaborated upon here.

[0185] Specifically, the initial concentration prediction parameter set of the initial free ammonia concentration prediction model is obtained by randomly generating multiple initial concentration prediction parameter sets, which can be achieved through existing technologies such as Latin hypercube sampling, and will not be elaborated here.

[0186] Importantly, the calculation of multiple initial prediction fitnesss based on the initial concentration prediction parameter set and the denoised parameter sequence set refers to generating multiple candidate free ammonia concentration prediction models based on multiple initial concentration prediction parameter sets, substituting the denoised parameter sequence set into the multiple candidate free ammonia concentration prediction models to predict multiple candidate free ammonia concentration sets, obtaining multiple historical free ammonia concentrations corresponding to the denoised parameter sequence sets, and then calculating the mean square error between each free ammonia concentration set in the multiple candidate free ammonia concentration sets and multiple historical free ammonia concentrations to obtain multiple initial prediction fitnesss. Each initial prediction fitness corresponds to the mean square error between a free ammonia concentration set and multiple historical free ammonia concentrations. Each candidate free ammonia concentration set corresponds to a candidate free ammonia concentration prediction model, including candidate free ammonia concentrations at multiple historical sampling times.

[0187] It should be explained that the parameter update operation on the initial concentration prediction parameter set refers to updating the initial concentration prediction parameter set using a particle swarm optimization algorithm to obtain an updated concentration prediction parameter set. The particle swarm optimization algorithm is existing technology and will not be described in detail here.

[0188] In detail, the process of updating the initial concentration prediction parameter set using the particle swarm optimization algorithm is as follows: The initial concentration prediction parameter set is used as the initial particle positions in the particle swarm, and particle velocities (the change between the initial and updated concentration prediction parameter sets) are randomly generated; a fitness function is constructed based on the error between the predicted and actual free ammonia concentration values; the optimal position for each particle and the optimal position for the entire swarm are determined by calculating the fitness value of each particle, and the parameter values ​​for each particle are iteratively updated according to the velocity and position update formulas of the particle swarm optimization algorithm; after multiple iterations, when the change in fitness is less than or equal to the change threshold or the maximum number of iterations is reached, the iteration stops, and the parameter set corresponding to the optimal fitness is determined as the updated concentration prediction parameter set. This step can be implemented using existing technologies and will not be elaborated further here.

[0189] It is understood that the process of calculating multiple updated prediction fitnesss based on the updated concentration prediction parameter set and the denoised parameter sequence set is the same as the process of calculating multiple initial prediction fitnesss based on the initial concentration prediction parameter set and the denoised parameter sequence set, and will not be described again here.

[0190] It is clear that, based on the correspondence between the initial concentration prediction parameter set and the updated concentration prediction parameter set, the calculation of multiple fitness changes based on multiple initial prediction fitnesss and multiple updated prediction fitnesss refers to calculating the difference between each initial prediction fitness and its corresponding updated prediction fitness to obtain multiple fitness changes.

[0191] It should be understood that the change threshold is a manually set threshold for the change in fitness, which can be determined based on the required accuracy of the free ammonia concentration prediction model. The smaller the change threshold, the higher the accuracy of the free ammonia concentration prediction model. When the change in fitness is less than or equal to the change threshold, it indicates that the corresponding updated concentration prediction parameter set is close to the optimal values ​​of multiple model parameters. The free ammonia concentration prediction model constructed based on this updated concentration prediction parameter set can accurately predict the free ammonia concentration based on multiple environmental parameters. Furthermore, the smaller the change in fitness, the higher the accuracy of the free ammonia concentration prediction model constructed based on the corresponding updated concentration prediction parameter set. Therefore, this invention extracts the minimum value among multiple fitness changes to obtain the minimum change, and uses the updated concentration prediction parameter set corresponding to the minimum change as the concentration prediction parameter set, and then constructs a free ammonia concentration prediction model based on the concentration prediction parameter set.

[0192] Specifically, the step of constructing a free ammonia concentration prediction model based on the concentration prediction parameter set involves substituting the concentration prediction parameter set into the initial free ammonia concentration prediction model, using the values ​​of multiple model parameters of the initial free ammonia concentration prediction model, and then constructing the free ammonia concentration prediction model.

[0193] It is understood that performing parameter denoising on multiple ammonia suppression parameter sets refers to performing parameter denoising on each ammonia suppression parameter set (such as a temperature set) within the multiple ammonia suppression parameter set sets to obtain multiple ammonia suppression parameter sequence sets. The specific process of performing parameter denoising on the ammonia suppression parameter set is consistent with the process of performing parameter denoising on the target ammonia suppression parameter set, and will not be elaborated further here.

[0194] It should be understood that the prediction of multiple free ammonia concentrations based on multiple ammonia suppression parameter sequence sets and free ammonia concentration prediction model involves importing multiple ammonia suppression and denoising sequence sets into the free ammonia concentration prediction model to predict multiple free ammonia concentrations corresponding to multiple ammonia suppression points.

[0195] S5. Complete the resource utilization treatment of organic waste based on multiple free ammonia concentrations.

[0196] Furthermore, the process of completing the resource recovery treatment of organic waste based on multiple free ammonia concentrations includes:

[0197] Obtain the normal concentration threshold, emergency concentration threshold, and critical concentration threshold, wherein the normal concentration threshold is less than the emergency concentration threshold, and the emergency concentration threshold is less than the critical concentration threshold;

[0198] Multiple free ammonia concentrations are compared with normal concentration thresholds, emergency concentration thresholds, and critical concentration thresholds to obtain multiple comparison results. Based on these multiple comparison results and the set of multiple ammonia inhibition parameters, the resource utilization treatment of organic waste is completed.

[0199] It should be understood that the normal concentration threshold, emergency concentration threshold, and emergency concentration threshold correspond to the free ammonia concentration thresholds under different conditions.

[0200] In detail, the acquisition of the normal concentration threshold, emergency concentration threshold, and critical concentration threshold refers to the threshold for determining the concentration of free ammonia based on a single-factor experiment. The single-factor experiment is existing technology and will not be elaborated upon here. The specific process of the single-factor experiment is as follows: the concentration of free ammonia is set as the independent variable. Microbial activity is detected based on different values ​​of the independent variable. When microbial activity begins to decrease, the free ammonia concentration is the normal concentration threshold. When microbial activity decreases to its lowest point, the free ammonia concentration is the emergency concentration threshold. Based on the critical concentration threshold, the free ammonia concentration is further increased until microbial activity cannot be increased by fine-tuning environmental parameters or other means of reducing free ammonia concentration. At this point, the free ammonia concentration is the critical concentration threshold. Microbial activity is detected through the chemical oxygen demand (COD); the higher the microbial activity, the greater the COD.

[0201] It is understood that the comparison results are the result of comparing the free ammonia concentration with the normal concentration threshold, the emergency concentration threshold, and the emergency concentration threshold.

[0202] Furthermore, the process of completing the resource utilization treatment of organic waste based on multiple comparison results and the multiple sets of ammonia inhibition parameters includes:

[0203] The results of multiple comparisons are classified to obtain four sets of classification results;

[0204] Extract the target classification set from the four classification result sets. The target classification set is the set of classification result sets where the free ammonia concentration is greater than the normal concentration threshold and less than or equal to the emergency concentration threshold.

[0205] Based on the target classification set, connected component analysis is performed on multiple ammonia suppression parameter sets to obtain multiple connected ammonia suppression parameter sets. Then, one connected ammonia suppression parameter set is extracted sequentially from each of these sets to obtain the target connected parameter set. The following operations are then performed on the target connected parameter set:

[0206] Construct an organic load objective function, and obtain a set of ammonia suppression environment parameter values ​​based on the organic load objective function and the objective connectivity parameter set;

[0207] By summarizing the sets of ammonia suppression environmental parameter values, multiple sets of ammonia suppression environmental parameter values ​​are obtained;

[0208] Organic waste resource utilization was achieved based on multiple sets of ammonia inhibition environmental parameter values.

[0209] Understandably, each comparison result corresponds to an ammonia inhibition point and a free ammonia concentration. Based on the magnitude of the free ammonia concentration relative to the normal, emergency, and critical concentration thresholds, multiple comparison results can be categorized into four types: The first type is where the free ammonia concentration is less than or equal to the normal concentration threshold; the second type is where the free ammonia concentration is greater than the normal concentration threshold and less than or equal to the emergency concentration threshold; the third type is where the free ammonia concentration is greater than the emergency concentration threshold and less than or equal to the critical concentration threshold; and the fourth type is where the free ammonia concentration is greater than the critical concentration threshold. Therefore, four classification result sets can be obtained. Specifically, the first classification result set is the set of comparison results corresponding to free ammonia concentrations less than or equal to the normal concentration threshold; the second classification result set is the set of comparison results corresponding to free ammonia concentrations greater than the normal concentration threshold and less than or equal to the emergency concentration threshold; the third classification result set is the set of comparison results corresponding to free ammonia concentrations greater than the emergency concentration threshold and less than or equal to the critical concentration threshold; and the fourth classification result set is the set of comparison results corresponding to free ammonia concentrations greater than the critical concentration threshold.

[0210] It should be noted that the normal concentration threshold refers to the concentration of free ammonia under normal conditions. Below this threshold, the concentration of free ammonia has little or no impact on bio-fermentation and can be ignored. The emergency concentration threshold refers to the concentration of free ammonia under emergency conditions. Below this threshold, the concentration of free ammonia has a significant impact on bio-fermentation, reducing the treatment efficiency of organic waste, but it will not destroy microbial fermentation. This can be adjusted through specific concentration reduction measures to lower the free ammonia concentration below the normal concentration threshold. The critical emergency concentration threshold refers to the concentration of free ammonia under emergency conditions. Below this threshold, the concentration of free ammonia will destroy microbial fermentation, causing the fermentation environment to collapse and fermentation to cease.

[0211] It is clear that no operation needs to be performed on the ammonia inhibition sites corresponding to the first classification result set, and no adjustment of environmental parameter values ​​is required. The target classification set is the second classification result set.

[0212] Specifically, the connected component analysis operation based on the target classification set for multiple ammonia suppression parameter sets is performed using existing techniques such as two-pass scanning and seed filling. This involves treating spatially adjacent ammonia suppression points corresponding to the target classification set within the multiple ammonia suppression parameter sets as a connected region. The average value of the multiple ammonia suppression parameter sets corresponding to the multiple ammonia suppression points within the connected region is then considered as a connected ammonia suppression parameter set. It should be noted that since a connected region consists of a set of multiple adjacent ammonia suppression points, the multiple ammonia suppression parameter sets within the connected region exhibit numerical similarity. Therefore, the average value of the multiple ammonia suppression parameter sets can be calculated as a single connected ammonia suppression parameter set.

[0213] It should be noted that the objective function for the organic load is as follows:

[0214]

[0215] in, Indicates organic loading rate, Indicates the feed flow rate. This indicates the oxygen demand concentration. This indicates the reactor volume.

[0216] It should be explained that the organic loading rate is the organic loading rate of the bio-fermentation, the feed flow rate is the feed flow rate of the organic waste to be treated, the oxygen demand concentration is the concentration of oxygen required by the microorganisms to carry out bio-fermentation, and the reactor volume is the volume of the bio-fermentation reactor (such as a fermenter or biogas digester).

[0217] It should be understood that obtaining the set of ammonia suppression environmental parameters based on the organic load objective function and the target connectivity parameter set refers to using the organic load objective function as the fitness function of particle swarm optimization (PSO). PSO is used to obtain multiple environmental parameter values ​​that maximize the organic load rate while ensuring that the free ammonia concentration is less than or equal to the normal concentration threshold. Multiple detection values ​​of the last detected environmental parameters are extracted from the target connectivity parameter set. The set of ammonia suppression environmental parameters is obtained by subtracting the corresponding detection values ​​from the multiple environmental parameter values. PSO is a prior art technique and will not be elaborated upon here.

[0218] Furthermore, the process of completing the resource utilization treatment of organic waste based on multiple sets of ammonia inhibition environmental parameters includes:

[0219] For each set of ammonia suppression environmental parameter values ​​from multiple sets of values, the following operation is performed:

[0220] Temperature values ​​were extracted from the set of ammonia suppression environmental parameters.

[0221] If the temperature value is a pre-constructed positive number, then the heat storage operation is performed based on the pre-constructed solar thermal collector unit to obtain the energy storage heat unit. The fermentation environment is then heated based on the energy storage heat unit to obtain the heated fermentation environment.

[0222] By summarizing the heating and fermentation environments, multiple heating and fermentation environments were obtained, and the resource utilization of organic waste was completed based on these multiple heating and fermentation environments.

[0223] It is understood that the temperature value is the value of the environmental parameter temperature, and the set of environmental parameters for ammonia inhibition includes the value of temperature, the value of pH, and the value of total ammonia nitrogen.

[0224] It is clear that when the temperature value is a pre-constructed positive number, it means that the fermentation temperature is lower than the temperature value, indicating that the fermentation environment needs to be heated. Therefore, a solar thermal collector (such as a Golden Sun vacuum tube solar collector) is used to perform a heat storage operation to obtain a heat storage unit. The heat storage unit is then used to heat the fermentation environment so that the fermentation temperature is equal to the temperature value.

[0225] Importantly, temperature can be achieved by partitioning heating to reach the desired temperature within the connected regions. For pH and total ammonia nitrogen, the average pH and total ammonia nitrogen values ​​from multiple ammonia inhibition environmental parameter sets need to be calculated to obtain the average pH and average total ammonia nitrogen. Then, by adding acid or alkali, the pH of the fermentation environment can be equal to the average pH, and the total ammonia nitrogen can be equal to the average total ammonia nitrogen. It should be noted that the differences between the fermentation temperature, pH, and total ammonia nitrogen and the actual temperature, average pH, and average total ammonia nitrogen values ​​can also be less than a fixed threshold. In this case, the average pH and the average total ammonia nitrogen are considered equal to the average total ammonia nitrogen. The fixed thresholds include temperature threshold, pH threshold, and total ammonia nitrogen threshold. These thresholds are determined based on the degree of influence of temperature, pH, and total ammonia nitrogen on the free ammonia concentration; the greater the influence, the smaller the fixed threshold. If pH has a significant impact on free ammonia and the pH threshold is also high, then even if the temperature is equal to the set temperature and the average total ammonia nitrogen is equal to the average total ammonia nitrogen, it is impossible to reduce the free ammonia concentration to the normal range by adjusting the environmental parameters. Therefore, the aforementioned organic waste resource utilization treatment based on multiple heating fermentation environments refers to adjusting the overall pH and total ammonia nitrogen of multiple heating fermentation environments.

[0226] Furthermore, for the third classification result set, it is necessary to perform a trace element supplementation operation on the fermentation environment to obtain a supplemented fermentation environment, and complete the resource utilization treatment of organic waste based on the supplemented fermentation environment.

[0227] Specifically, the micronutrient supplementation operation for the fermentation environment involves adding micronutrients that promote microbial metabolism, such as iron, manganese, copper, molybdenum, and cobalt. Supplementing with micronutrients can help enhance microbial activity, reduce the inhibitory effect of free ammonia, and improve fermentation efficiency.

[0228] In detail, the organic waste resource utilization treatment based on the supplemented fermentation environment involves, on the basis of supplementing trace elements, strengthening the intensity of the ammonia stripping treatment on the fermentation broth to reduce the concentration of free ammonia in the fermentation broth.

[0229] It should be explained that the enhancement of the intensity of the ammonia stripping treatment on the fermentation broth can be achieved by increasing the gas flow rate through the fermentation broth, or by using a high-efficiency gas pump to provide a larger gas flow rate, thereby promoting the volatilization and removal of more ammonia, and by using a bubble generator or microbubble generator to break the gas into very small bubbles to increase the gas-liquid contact area and improve the ammonia stripping effect. These are all known existing technologies for improving the intensity of ammonia stripping, which can reduce the concentration of free ammonia in a short time.

[0230] Importantly, for the fourth category result set, it is necessary to perform a fermentation termination operation on the fermentation environment to obtain a terminated fermentation environment, and complete the resource utilization treatment of organic waste based on the terminated fermentation environment.

[0231] It should be noted that the fermentation termination operation involves stopping the addition of organic waste to be treated to the fermentation reaction vessel, while simultaneously increasing the intensity of ammonia stripping treatment of the fermentation broth until the free ammonia concentration in the fermentation environment drops below the normal concentration threshold, thus achieving a terminated fermentation environment. The organic waste resource recovery process based on this terminated fermentation environment involves adding the organic waste to be treated to the terminated fermentation environment (where the free ammonia concentration has decreased to below the normal concentration threshold) for a second biological fermentation, thereby achieving the resource recovery of the organic waste.

[0232] To address the problems described in the background art, this invention obtains organic waste to be treated, performs pretreatment and conditioning operations on the organic waste to obtain a fermentation substrate, performs anaerobic fermentation on the fermentation substrate to obtain a fermentation broth, performs ammonia stripping treatment on the fermentation broth to obtain stripped biogas slurry, performs pH adjustment on the stripped biogas slurry to obtain adjusted biogas slurry, and introduces the adjusted biogas slurry into the fermentation broth for anaerobic fermentation to obtain a fermentation environment. This invention couples the ammonia stripping treatment with the fermentation process to achieve online ammonia removal and reuse of the fermentation broth, reducing the amount of external dilution water used and improving the treatment efficiency of organic waste. Simultaneously, this invention collects environmental parameters from multiple pre-constructed sampling points to obtain multiple sets of environmental parameters. Each set of environmental parameters corresponds one-to-one with a sampling point and includes pH, total ammonia nitrogen, redox potential, and temperature sets. A three-dimensional map of the fermentation state is constructed based on these multiple sets of environmental parameters, and the precursory regions of ammonia inhibition are identified based on this three-dimensional map. This invention utilizes the sensitive response characteristics of redox potential to ammonia inhibition to achieve early identification and spatial localization of precursory ammonia inhibition. Furthermore, this invention extracts multiple ammonia inhibition parameter sets from multiple environmental parameter sets based on the ammonia inhibition precursor region. Based on these multiple ammonia inhibition parameter sets, a pre-constructed free ammonia concentration prediction model is used to predict multiple free ammonia concentrations. Based on these multiple free ammonia concentrations, the organic waste is then processed for resource recovery. This invention employs a combination of multi-scale decomposition and particle swarm optimization. First, parameter denoising is performed on the target ammonia inhibition parameter sets to obtain a denoised parameter sequence. Then, the prediction model parameters are optimized based on the denoised parameter sequence set, thereby improving the accuracy of free ammonia concentration prediction and providing a foundation for subsequent free ammonia concentration regulation. Simultaneously, this invention also uses an organic load objective function to perform graded regulation of free ammonia concentration while maximizing the organic load rate, reducing the free ammonia concentration to the normal concentration threshold, improving system stability and reducing the risk of ammonia inhibition. Therefore, this invention can achieve graded regulation of free ammonia concentration in a bio-fermentation treatment method while ensuring efficient resource recovery of organic waste, thereby improving system stability and reducing the risk of ammonia inhibition.

[0233] like Figure 2 The diagram shown is a functional block diagram of an organic waste resource utilization system based on bio-fermentation provided in an embodiment of the present invention.

[0234] The organic waste resource recovery system 100 based on bio-fermentation described in this invention can be installed in an electronic device. Depending on the functions implemented, the organic waste resource recovery system 100 based on bio-fermentation may include a bio-fermentation module 101, a region identification module 102, a concentration prediction module 103, and a concentration control module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0235] The bio-fermentation module 101 is used to acquire organic waste to be treated, perform pretreatment and conditioning operations on the organic waste to be treated to obtain fermentation substrate, perform anaerobic fermentation on the fermentation substrate to obtain fermentation broth, perform ammonia stripping treatment on the fermentation broth to obtain stripped biogas slurry, perform pH adjustment on the stripped biogas slurry to obtain adjusted biogas slurry, and introduce the adjusted biogas slurry into the fermentation broth to perform anaerobic fermentation to obtain a fermentation environment.

[0236] The region identification module 102 is used to collect environmental parameters of the fermentation environment based on multiple pre-constructed sampling points to obtain multiple sets of environmental parameters. Each set of environmental parameters corresponds to a sampling point. The environmental parameter sets include pH, total ammonia nitrogen, redox potential and temperature. A three-dimensional map of the fermentation state is constructed based on the multiple sets of environmental parameters. The three-dimensional map of the fermentation state is used to identify the ammonia inhibition precursor region.

[0237] The concentration prediction module 103 is used to extract multiple ammonia inhibition parameter sets from multiple environmental parameter sets based on the ammonia inhibition precursor region, and to predict multiple free ammonia concentrations based on the multiple ammonia inhibition parameter sets using a pre-constructed free ammonia concentration prediction model.

[0238] The concentration control module 104 is used to complete the resource utilization treatment of organic waste based on multiple free ammonia concentrations.

[0239] In detail, the modules in the organic waste resource utilization system 100 based on bio-fermentation described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method used is the same as the organic waste resource utilization method based on bio-fermentation described above, and can produce the same technical effects, so it will not be repeated here.

[0240] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing a bio-fermentation-based organic waste resource recovery method according to an embodiment of the present invention.

[0241] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a program for a method of resource recovery of organic waste based on bio-fermentation.

[0242] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as code for a method for the resource recovery of organic waste based on bio-fermentation, but also to temporarily store data that has been output or will be output.

[0243] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a program for the resource utilization of organic waste based on bio-fermentation), and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0244] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0245] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0246] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management system, thereby enabling functions such as charging management, discharging management, and power consumption management through the power management system. The power supply may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0247] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0248] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0249] The program for the resource recovery method of organic waste based on bio-fermentation, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0250] Acquire organic waste to be processed;

[0251] The organic waste to be treated is pretreated and prepared to obtain fermentation substrate;

[0252] Anaerobic fermentation was performed on the fermentation substrate to obtain the fermentation broth;

[0253] The fermentation broth was subjected to ammonia stripping treatment to obtain stripped biogas slurry;

[0254] A pH adjustment process is performed on the stripped biogas slurry to obtain adjusted biogas slurry;

[0255] The recycled biogas slurry is introduced into the fermentation broth to perform anaerobic fermentation, thus obtaining the fermentation environment;

[0256] Environmental parameters were collected from the fermentation environment based on multiple pre-constructed sampling points, resulting in multiple sets of environmental parameters. Each set of environmental parameters corresponds to a sampling point and includes sets of pH, total ammonia nitrogen, redox potential, and temperature.

[0257] A three-dimensional map of fermentation status was constructed based on multiple sets of environmental parameters;

[0258] Identification of ammonia inhibition precursor regions based on three-dimensional fermentation state maps;

[0259] Based on the ammonia suppression precursor region, multiple ammonia suppression parameter sets are extracted from multiple environmental parameter sets. Based on the multiple ammonia suppression parameter sets, multiple free ammonia concentrations are predicted using a pre-constructed free ammonia concentration prediction model.

[0260] Organic waste is recycled based on multiple free ammonia concentrations.

[0261] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0262] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0263] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0264] Acquire organic waste to be processed;

[0265] The organic waste to be treated is pretreated and prepared to obtain fermentation substrate;

[0266] Anaerobic fermentation was performed on the fermentation substrate to obtain the fermentation broth;

[0267] The fermentation broth was subjected to ammonia stripping treatment to obtain stripped biogas slurry;

[0268] A pH adjustment process is performed on the stripped biogas slurry to obtain adjusted biogas slurry;

[0269] The recycled biogas slurry is introduced into the fermentation broth to perform anaerobic fermentation, thus obtaining the fermentation environment;

[0270] Environmental parameters were collected from the fermentation environment based on multiple pre-constructed sampling points, resulting in multiple sets of environmental parameters. Each set of environmental parameters corresponds to a sampling point and includes sets of pH, total ammonia nitrogen, redox potential, and temperature.

[0271] A three-dimensional map of fermentation status was constructed based on multiple sets of environmental parameters;

[0272] Identification of ammonia inhibition precursor regions based on three-dimensional fermentation state maps;

[0273] Based on the ammonia suppression precursor region, multiple ammonia suppression parameter sets are extracted from multiple environmental parameter sets. Based on the multiple ammonia suppression parameter sets, multiple free ammonia concentrations are predicted using a pre-constructed free ammonia concentration prediction model.

[0274] Organic waste is recycled based on multiple free ammonia concentrations.

[0275] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0276] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0277] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0278] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0279] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for the resource-based treatment of organic waste based on bio-fermentation, characterized in that, The method includes: Acquire organic waste to be processed; The organic waste to be treated is pretreated and prepared to obtain fermentation substrate; Anaerobic fermentation was performed on the fermentation substrate to obtain the fermentation broth; The fermentation broth was subjected to ammonia stripping treatment to obtain stripped biogas slurry; A pH adjustment process is performed on the stripped biogas slurry to obtain adjusted biogas slurry; The recycled biogas slurry is introduced into the fermentation broth to perform anaerobic fermentation, thus obtaining the fermentation environment; Environmental parameters were collected from the fermentation environment based on multiple pre-constructed sampling points, resulting in multiple sets of environmental parameters. Each set of environmental parameters corresponds to a sampling point and includes sets of pH, total ammonia nitrogen, redox potential, and temperature. A three-dimensional map of fermentation status was constructed based on multiple sets of environmental parameters; Identification of ammonia inhibition precursor regions based on three-dimensional fermentation state maps; Based on the ammonia suppression precursor region, multiple ammonia suppression parameter sets are extracted from multiple environmental parameter sets. Based on the multiple ammonia suppression parameter sets, multiple free ammonia concentrations are predicted using a pre-constructed free ammonia concentration prediction model. Organic waste is recycled based on multiple free ammonia concentrations.

2. The method for resource recovery of organic waste based on bio-fermentation as described in claim 1, characterized in that, The method for identifying ammonia inhibition precursor regions based on three-dimensional fermentation state maps includes: Calculate the rate of change of redox potential at each of the multiple sampling points to obtain multiple rates of change of redox potential. Spatial interpolation was performed on the rate of change of multiple redox potentials based on the three-dimensional map of fermentation state to obtain the rate of change distribution. Candidate regions for ammonia suppression precursors were identified based on the rate of change distribution; Set a time window, and monitor the rate of change of candidate regions for ammonia inhibition precursors based on the time window to obtain a rate of change map; Based on the rate of change map, the ammonia suppression precursor region was identified from the candidate regions of ammonia suppression precursor.

3. The method for resource recovery of organic waste based on bio-fermentation as described in claim 2, characterized in that, The method, based on multiple sets of ammonia suppression parameters, uses a pre-constructed free ammonia concentration prediction model to predict multiple free ammonia concentrations, including: Historical ammonia suppression parameter sets are obtained based on multiple ammonia suppression parameter sets, wherein the historical ammonia suppression parameter sets include multiple historical ammonia suppression parameter sets; Extract one historical ammonia suppression parameter set sequentially from the historical ammonia suppression parameter set to obtain the target ammonia suppression parameter set. Perform the following operations on the target ammonia suppression parameter set: Perform parameter denoising on the target ammonia suppression parameter set to obtain a denoised parameter sequence; Summarize the denoising parameter sequences to obtain a denoising parameter sequence set; A free ammonia concentration prediction model is constructed based on a denoised parameter sequence set and a pre-built initial free ammonia concentration prediction model. Perform parameter denoising operation on multiple ammonia suppression parameter sets to obtain multiple ammonia suppression parameter sequence sets; Multiple free ammonia concentrations are predicted based on a set of multiple ammonia suppression parameter sequences and a free ammonia concentration prediction model.

4. The method for resource recovery of organic waste based on bio-fermentation as described in claim 3, characterized in that, The parameter denoising operation performed on the target ammonia suppression parameter set yields a denoised parameter sequence, including: Obtain multiple noise parameter sequences; Multiple ammonia-suppressed noise sequences were obtained based on multiple noise parameter sequences and a target ammonia suppression parameter set; For each of the multiple ammonia-suppressed noise sequences, perform the following operation: Multi-scale decomposition was performed on the ammonia-suppressed noise sequence to obtain multiple ammonia-suppressed scale sequences; By summing up multiple ammonia-suppressed scale sequences, multiple sets of ammonia-suppressed scale sequences are obtained; Denoising parameter sequences were obtained based on multiple ammonia-suppressed scale sequence sets.

5. The method for resource recovery of organic waste based on bio-fermentation as described in claim 4, characterized in that, The method of obtaining the denoising parameter sequence based on multiple ammonia suppression scale sequence sets includes: Set an initial particle swarm, which consists of multiple initial particles. Extract one initial particle sequentially from multiple initial particles to obtain the target initial particle, and perform the following operations on the target initial particle: Sequence sorting was performed on multiple ammonia suppression scale sequence sets to obtain an ammonia suppression sorted sequence set; Based on the target initial particle ammonia suppression sorting sequence set, a sequence retention operation is performed to obtain the historical retained sequence set; Construct a historical retention parameter set based on the historical retention sequence set; Calculate the fitness function values ​​between the target ammonia suppression parameter set and the historical retention parameter set; Summarize the fitness function values ​​to obtain multiple fitness function values; The particle parameters of the initial particle swarm are updated based on multiple fitness function values ​​to obtain the updated particle swarm. A denoising parameter sequence is constructed based on the updated particle swarm and ammonia-suppressed sorted sequence set.

6. The method for resource recovery of organic waste based on bio-fermentation as described in claim 5, characterized in that, The construction of the free ammonia concentration prediction model based on the denoised parameter sequence set and the pre-constructed initial free ammonia concentration prediction model includes: Obtain the initial concentration prediction parameter set of the initial free ammonia concentration prediction model, wherein the initial concentration prediction parameter set includes multiple initial concentration prediction parameter sets; Multiple initial prediction fitnesss are calculated based on the initial concentration prediction parameter set and the denoised parameter sequence set; Perform a parameter update operation on the initial concentration prediction parameter set to obtain an updated concentration prediction parameter set. The updated concentration prediction parameter set includes multiple updated concentration prediction parameter sets, and each updated concentration prediction parameter set corresponds one-to-one with the initial concentration prediction parameter set. Multiple updated prediction fitnesss are calculated based on the updated concentration prediction parameter set and the denoised parameter sequence set; Calculate multiple fitness changes based on multiple initial predicted fitness and multiple updated predicted fitness; If among multiple fitness changes there is a fitness change that is less than or equal to a pre-built change threshold, then the minimum value among the multiple fitness changes is extracted to obtain the minimum change, and the updated concentration prediction parameter set corresponding to the minimum change is determined to obtain the concentration prediction parameter set. A free ammonia concentration prediction model was constructed based on the concentration prediction parameter set.

7. The method for resource recovery of organic waste based on bio-fermentation as described in claim 6, characterized in that, The process of resource recovery of organic waste based on multiple free ammonia concentrations includes: Obtain the normal concentration threshold, emergency concentration threshold, and critical concentration threshold, wherein the normal concentration threshold is less than the emergency concentration threshold, and the emergency concentration threshold is less than the critical concentration threshold; Multiple free ammonia concentrations are compared with normal concentration thresholds, emergency concentration thresholds, and critical concentration thresholds to obtain multiple comparison results. Based on these multiple comparison results and the set of multiple ammonia inhibition parameters, the resource utilization treatment of organic waste is completed.

8. The method for resource recovery of organic waste based on bio-fermentation as described in claim 7, characterized in that, The process of resource recovery of organic waste based on multiple comparison results and multiple sets of ammonia inhibition parameters includes: The results of multiple comparisons are classified to obtain four sets of classification results; Extract the target classification set from the four classification result sets. The target classification set is the set of classification result sets where the free ammonia concentration is greater than the normal concentration threshold and less than or equal to the emergency concentration threshold. Based on the target classification set, connected component analysis is performed on multiple ammonia suppression parameter sets to obtain multiple connected ammonia suppression parameter sets. Then, one connected ammonia suppression parameter set is extracted sequentially from each of these sets to obtain the target connected parameter set. The following operations are then performed on the target connected parameter set: Construct an organic load objective function, and obtain a set of ammonia suppression environment parameter values ​​based on the organic load objective function and the objective connectivity parameter set; By summarizing the sets of ammonia suppression environmental parameter values, multiple sets of ammonia suppression environmental parameter values ​​are obtained; Organic waste resource utilization was achieved based on multiple sets of ammonia inhibition environmental parameter values.

9. The method for resource recovery of organic waste based on bio-fermentation as described in claim 8, characterized in that, The process of resource recovery of organic waste based on multiple sets of ammonia inhibition environmental parameters includes: For each set of ammonia suppression environmental parameter values ​​from multiple sets of values, the following operation is performed: Temperature values ​​were extracted from the set of ammonia suppression environmental parameters. If the temperature value is a pre-constructed positive number, then the heat storage operation is performed based on the pre-constructed solar thermal collector unit to obtain the energy storage heat unit. The fermentation environment is then heated based on the energy storage heat unit to obtain the heated fermentation environment. By summarizing the heating and fermentation environments, multiple heating and fermentation environments were obtained, and the resource utilization of organic waste was completed based on these multiple heating and fermentation environments.

10. An organic waste resource utilization system based on bio-fermentation, characterized in that, The system includes: The biological fermentation module is used to acquire organic waste to be treated, perform pretreatment and conditioning operations on the organic waste to be treated to obtain fermentation substrate, perform anaerobic fermentation on the fermentation substrate to obtain fermentation broth, perform ammonia stripping treatment on the fermentation broth to obtain stripped biogas slurry, perform pH adjustment on the stripped biogas slurry to obtain adjusted biogas slurry, and introduce the adjusted biogas slurry into the fermentation broth for anaerobic fermentation to obtain a fermentation environment; The region identification module is used to collect environmental parameters of the fermentation environment based on multiple pre-constructed sampling points, and obtain multiple sets of environmental parameters. Each set of environmental parameters corresponds one-to-one with a sampling point. The environmental parameter sets include pH, total ammonia nitrogen, redox potential and temperature. A three-dimensional map of the fermentation state is constructed based on the multiple sets of environmental parameters, and the ammonia inhibition precursor region is identified based on the three-dimensional map of the fermentation state. The concentration prediction module is used to extract multiple ammonia inhibition parameter sets from multiple environmental parameter sets based on the ammonia inhibition precursor region, and to predict multiple free ammonia concentrations based on the multiple ammonia inhibition parameter sets using a pre-built free ammonia concentration prediction model. The concentration control module is used to complete the resource recovery treatment of organic waste based on multiple free ammonia concentrations.

Images