Bio-organic fertilizer production process data system and extraction method

Abstract

The invention relates to the technical field of organic fertilizer production, in particular to a bio-organic fertilizer production process data system and an extraction method. The method comprises the following steps: acquiring a raw material information set and a process parameter set; calculating a reference flora rate based on microbial activity characteristics of the raw material information set; marking a time sequence timestamp for the raw material information set and the process parameter set, and constructing a fermentation behavior track; analyzing the microbial activity characteristics of the fermentation behavior track, and calculating the flora reaction speed; therefore, by constructing a multi-source heterogeneous data-driven fermentation behavior track and quality mapping system, the problems of data isolation, state recognition lag and process deviation and incapability of accurate positioning in traditional bio-organic fertilizer production are solved, and the intelligent diagnosis capability and quality controllability of the production process are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of organic fertilizer production, in particular to a bio-organic fertilizer production process data system and an extraction method. Background Art

[0002] In the existing bio-organic fertilizer production process, data extraction and monitoring methods generally suffer from problems such as a single data dimension, crude process feature extraction, and delayed fermentation status identification. This is especially true when faced with different raw material components and complex process environments. Traditional methods struggle to accurately capture the activity status of microorganisms and dynamically trace production line anomalies. Most systems rely solely on basic environmental parameters such as temperature and humidity, ignoring fine-grained monitoring of reaction data such as bacterial metabolism, heat generation, gas production, and acid-base neutralization. This results in an inability to effectively model fermentation behavior and a lack of data support for process control. At the same time, existing methods fail to adequately explore the correlation between quality results and process behavior during the fermentation process, lack efficient data structures for traceability and deviation identification, and struggle to achieve fusion analysis and quality feedback for multi-source heterogeneous data. Furthermore, the inspection of finished products often focuses on static indicator collection, lacking correlation mapping with historical trajectories and dynamic reaction rates. This makes it difficult to establish a systematic diagnostic mechanism for process quality, limiting the intelligent and refined development of the entire bio-organic fertilizer production process. Summary of the Invention

[0003] Based on this, it is necessary to provide a bio-organic fertilizer production process data system and extraction method to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for extracting data from a bio-organic fertilizer production process comprises the following steps: Step S1: obtaining a raw material information set and a process parameter set; calculating a baseline bacterial population rate based on the microbial activity characteristics of the raw material information set; Step S2: annotate the raw material information set and the process parameter set with time series timestamps and construct a fermentation behavior trajectory; analyze the microbial activity characteristics of the fermentation behavior trajectory and calculate the bacterial community reaction rate; Step S3: After the organic fertilizer production line is completed, the output quality feature set of the organic fertilizer product is collected; the corrosion degree index in the output quality feature set is compared with the baseline bacterial population rate and bacterial population reaction speed, and the fermentation process deviation data is output; Step S4: Trace and associate the fermentation process deviation data and the fermentation behavior trajectory to obtain an organic fertilizer process deviation mapping table; identify the control abnormalities of the fermentation production line based on the organic fertilizer process deviation mapping table, and construct an organic fertilizer production report.

[0005] In this specification, a bio-organic fertilizer production process data extraction system is provided for executing the above-mentioned bio-organic fertilizer production process data extraction method. The bio-organic fertilizer production process data extraction system includes: The raw material analysis module is used to obtain the raw material information set and the process parameter set; based on the microbial activity characteristics of the raw material information set, the baseline bacterial population rate is calculated; The fermentation analysis module is used to annotate the raw material information set and process parameter set with time series timestamps and construct fermentation behavior trajectories; Analyze the microbial activity characteristics of fermentation behavior trajectories and calculate the bacterial community reaction rate; Analyze the microbial activity characteristics of fermentation behavior trajectories and calculate the bacterial community reaction rate; The quality deviation module is used to collect the output quality feature set of the organic fertilizer product after the organic fertilizer production line is completed; compare the corrosion degree index in the output quality feature set with the baseline bacterial population rate and bacterial population reaction speed, and output the fermentation process deviation data; The traceability diagnosis module is used to trace and correlate fermentation process deviation data and fermentation behavior trajectories to obtain an organic fertilizer process deviation mapping table; based on the organic fertilizer process deviation mapping table, it identifies control anomalies of the fermentation production line and constructs an organic fertilizer production report.

[0006] The beneficial effects of the present invention are as follows: by constructing a raw material information set and a process parameter set based on time series annotation, a complete fermentation behavior trajectory is formed, so that the data flow in the fermentation process has a clear time logic and structural hierarchy, thereby providing a high-precision data basis for the subsequent extraction of microbial activity characteristics and reaction rate calculation. By extracting multi-dimensional dynamic data such as temperature and humidity changes, pH fluctuations, gas release rate, heat rate and acid-base neutralization rate, a dynamic coupling model of bacterial community activity and metabolic response is established in the fermentation behavior trajectory, effectively revealing the stage-by-stage change characteristics of the bacterial community reaction. After the production line is completed, the corrosion degree index of the finished product is further collected and compared with the baseline bacterial community rate and bacterial community reaction rate to establish a data association between the quality of the finished product and the process behavior, thereby realizing the quantitative analysis of process deviations. On this basis, the system associates process deviations with behavior tracing through tracing, constructs a deviation mapping table and identifies abnormal items in production line control, forming an end-to-end data closed-loop feedback path, effectively realizing the quality traceability and control optimization of the entire process from raw material input to finished product output. The entire process is data-driven, emphasizing the dynamic adjustment of the temporal fusion of multi-source data and the mapping relationship between indicators, which improves the interpretability and analytical depth of the data and avoids the coarse-grained processing of microbial status assessment and the hysteresis problem of process deviation identification in traditional methods. Therefore, by constructing a fermentation behavior trajectory and quality mapping system driven by multi-source heterogeneous data, the present invention solves the problems of data isolation, state identification lag, and the inability to accurately locate process deviations in traditional bio-organic fertilizer production, thereby improving the intelligent diagnostic capabilities and quality controllability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A schematic flow chart of a method for extracting data from a bio-organic fertilizer production process; Figure 2 This is a schematic diagram of the bio-organic fertilizer production line process; Figure 3 This is a schematic diagram of gas concentration change monitoring in the bio-organic fertilizer production process; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0008] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative work are within the scope of protection of the present invention.

[0009] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0010] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0011] To achieve this, please refer to Figures 1 to 3 , a method for extracting data from a bio-organic fertilizer production process, the method comprising the following steps: Step S1: obtaining a raw material information set and a process parameter set; calculating a baseline bacterial population rate based on the microbial activity characteristics of the raw material information set; Step S2: annotate the raw material information set and the process parameter set with time series timestamps and construct a fermentation behavior trajectory; analyze the microbial activity characteristics of the fermentation behavior trajectory and calculate the bacterial community reaction rate; Step S3: After the organic fertilizer production line is completed, the output quality feature set of the organic fertilizer product is collected; the corrosion degree index in the output quality feature set is compared with the baseline bacterial population rate and bacterial population reaction speed, and the fermentation process deviation data is output; Step S4: Trace and associate the fermentation process deviation data and the fermentation behavior trajectory to obtain an organic fertilizer process deviation mapping table; identify the control abnormalities of the fermentation production line based on the organic fertilizer process deviation mapping table, and construct an organic fertilizer production report.

[0012] In this embodiment, the sensors required to obtain the raw material information set and the process parameter set include but are not limited to Sensors, NDIR Sensors, temperature probes, dissolved / gas phase Sensors, pH electrodes, weighing / gas flow meters and camera / spectral sampling terminals.

[0013] In the embodiment of the present invention, reference Figure 1FIG. 5 is a flow chart showing a method for extracting data from a bio-organic fertilizer production process according to the present invention. In this example, the method comprises the following steps: Step S1: obtaining a raw material information set and a process parameter set; calculating a baseline bacterial population rate based on the microbial activity characteristics of the raw material information set; Of particular importance is the calculation formula for the microbial activity characteristic in step S1: ; in, to is the weight factor, is the baseline bacterial population rate or bacterial population reaction speed.

[0014] In this embodiment, : It represents the baseline bacterial population rate or bacterial population reaction speed at time t, and is a dynamic indicator that comprehensively reflects the metabolic activity of the bacterial population.

[0015] is a weighting factor that reflects the contribution of each monitored variable to the calculation of the bacterial colony rate or reaction speed. These weights can be obtained through regression fitting of historical production data or experimental calibration to balance the impact of different variables.

[0016] : The rate of change of ammonia concentration over time, usually in units of or Reflects the decomposition rate of protein and nitrogen-containing organic matter.

[0017] : The rate of change of carbon dioxide concentration over time, in units of or , is the rate of product of microbial respiratory metabolism during the decomposition of organic matter.

[0018] : The rate of change of the pile temperature over time, in units of , reflecting the dynamic changes of heat release and loss during the fermentation process.

[0019] : The rate of change of oxygen concentration over time, in units of or , reflecting the changing trend of microbial oxygen consumption intensity and ventilation conditions.

[0020] It is particularly important to note that the weighting factor needs to be obtained through a controlled experiment designed based on the type of raw materials. For example, for high nitrogen raw materials (total nitrogen content > 2.5%), the weighting factor should be increased. The weight is increased to 0.4-0.5; for high carbon raw materials (C / N>30), to 0.3~0.4; At least three batches of production verification are carried out for each category, and the weighted optimization benchmark is to determine the humic acid compliance rate of the finished product > 90%. The weight factor of .

[0021] Preferably, step S1 further includes: Sending a data collection request signal to the raw material input unit and the process control unit; Receive the data collection request signal of the current batch of raw material information set and add the raw material sampling timestamp; Obtain the fermentation start and stop times, execution sequence of ventilation or temperature control operations in the process parameter set, and establish a process event timeline.

[0022] In the embodiment of the present invention, four types of dynamic changes are extracted from the raw material information: ammonia ( ),carbon dioxide( ),temperature( ) and dissolved oxygen ( These data need to have a continuous time series change record, so the system needs to perform regular sampling through sensors or sampling ports. Each data includes at least the concentration or value of multiple time points. On this basis, by performing time differentiation on each data (i.e., calculating the rate of change between adjacent time points), the ammonia change rate, rate of change, temperature rise and fall rate, and rate of change, and multiply it by the corresponding weight factor ( to ), and finally a value representing the current activity state of the bacterial community is obtained through weighted summation . This value is defined as the "baseline bacterial population rate" or "bial population reaction rate" and can be used to subsequently judge the stability and abnormal characteristics of the fermentation process. Before sampling, a data collection request will be automatically sent to the raw material input unit and the process control unit, and the corresponding "raw material sampling timestamp" and "process event timeline" will be recorded. The latter includes key nodes such as fermentation start time, ventilation and temperature control operation execution sequence, which will be used to subsequently align and match the bacterial population rate data with the fermentation process behavior trajectory.

[0023] In one implementation of the present invention, it is assumed that a batch of high-temperature composting organic fertilizer is currently being processed, and its raw material data is as follows: Ammonia concentration dropped from 25 ppm to 20 ppm in 1 hour (rate of change -5 ppm / h); CO2 concentration increased from 3000ppm to 3500ppm (rate of change +500ppm / h); Temperature increased from 52°C to 58°C (rate of change +6°C / h); The dissolved oxygen decreased from 6.0 mg / L to 5.4 mg / L (rate of change -0.6 mg / Lh).

[0024] The weight factors are set as follows: n1=0.3, n2=0.2, n3=0.4, n4=0.1 and substituted into the calculation formula of microbial activity characteristics: The system then records a bacterial colony reaction rate of 100.84, which can be used as a numerical indicator of fermentation activity during that time period. Through continuous sampling and calculation, a complete bacterial colony reaction rate curve can be formed for subsequent fermentation behavior trajectory modeling and deviation analysis.

[0025] Step S2: annotate the raw material information set and the process parameter set with time series timestamps and construct a fermentation behavior trajectory; analyze the microbial activity characteristics of the fermentation behavior trajectory and calculate the bacterial community reaction rate; Preferably, step S2 includes the following steps: Step S21: marking the raw material sampling timestamp for the raw material information set and the process parameter set, and performing segmented sampling according to the unified time window of the process event time axis to generate a time window index group; Step S22: performing linear interpolation on the temperature and humidity according to the time window index group to obtain a fertilizer time series data stream; Step S23: segmenting the fertilizer time series data stream according to the nodes of the time series timestamps and the fermentation stage labels to construct a fermentation behavior trajectory; Step S24: extracting the temperature and humidity change gradient and pH fluctuation frequency as microbial metabolism stimulation indicators, and comparing the indicator change rates in the previous and next time windows to generate microbial stimulation indicator data; Step S25: Calculate the bacterial activity conversion rate of the bacterial excitation index data, and combine it with the gas release rate, heat generation rate and acid-base neutralization rate per unit time in the fermentation behavior trajectory to generate the bacterial reaction speed.

[0026] Preferably, step S25 further includes the following: The fermentation behavior trajectory is divided into three stages according to the timestamp: the initial stage, the medium temperature stage, and the gas production stage. The proportions of the acid-base neutralization rate, the heat generation rate, and the gas release rate are adjusted respectively, where: The initial stage uses the acid-base neutralization rate as an indicator; The medium temperature section uses the heating rate as an indicator; The gas production section is indexed by the gas release rate, where the index is 60% of the proportion allocated.

[0027] In an embodiment of the present invention, step S2 forms a reproducible data pipeline from data alignment, gap filling, time series segmentation to feature extraction: all raw material information and process parameters are timestamped and stored in a unified database using a synchronized time source (such as NTP or a gateway clock). Sampling is performed at a fixed or adaptive sampling rate (e.g., 5-15 minutes / time). Metadata registration of the sampling frequency and device ID is performed at the acquisition end for traceability. Based on the process event timeline (including markers such as tank entry, start / stop, ventilation, and temperature rise points), the time series data is segmented with a configured time window width (e.g., 4-8 hours, or as needed) to generate a time window index group. For breakpoints or sparse sampling points within the time window, channels such as temperature and humidity are filled using linear interpolation to form a continuous fertilizer time series data stream and write it into a time window index. The time series stream is segmented based on the time window and process event labels, and fermentation behavior trajectory records are generated (the trajectory table contains the time window index, stage label, and summary statistics for each channel). Basic features are extracted within each time window using numerical methods: the average rate of change and variance of the temperature and humidity gradients are calculated using finite differences (central differences or forward differences), and the pH fluctuation frequency is obtained using threshold zero-crossing counts or short-time energy spectra (peak counts within a short-time window). These are then scalared into standardized bacterial metabolic stimulation indicators (normalized or z-score-standardized based on historical baselines or batch initial values). The rate of change of the stimulation indicator between time windows is calculated by dividing the difference between adjacent windows by the time interval and recorded as the "stimulation change rate." These indicators are written together with the time window system into the stimulation indicator table for subsequent conversion rate and reaction rate calculations.

[0028] It is particularly important to note that the establishment of the historical baseline is based on the fermentation data of nearly 30 batches of the same type of raw materials, and the mean value of each indicator in the same fermentation stage is calculated. If there is a lack of historical data, the mean value of the indicator within 2 hours after the start of fermentation of this batch is used as the standard deviation to obtain the empirical value.

[0029] In the embodiment of the present invention, the entire fermentation trajectory is divided into the initial stage, the medium temperature stage and the gas production stage through event-driven feature detection. The division logic is: the earliest inflection point where the temperature slope continues to rise and exceeds the threshold is detected on the trajectory as the starting point of the medium temperature stage, and the earliest inflection point where the temperature slope continues to rise and exceeds the threshold is detected as the starting point of the medium temperature stage. The local significant peak of the (or total gas production) sequence (the peak value is greater than the window average plus several times the standard deviation is the local maximum) is taken as the starting point of the gas production section, and the section before it is the initial section; in each section, three types of dominant rate sequences are extracted respectively - the acid-base neutralization rate uses the time derivative of pH ) and can be multiplied by the buffer coefficient or corrected by conductivity / alkalinity measurement. The heating rate uses the time derivative of the pile temperature. (Do moving average smoothing on sensor noise first), gas release rate is used Time derivative of concentration or exhaust flow and interval cumulative release as a metric; Several operational indicators are calculated within the segment: average rate of change, peak density (number of peaks per hour), duration of continuous over-threshold (duration of continuously exceeding the set threshold) and standard deviation; weight distribution is set according to the proportion of the dominant indicator in the segment (the proportion of the dominant indicator is 60% in the example), and the stage-by-stage activity conversion parameter is calculated = the dominant indicator value x 0.6 + the remaining 40% after standardization of the other two indicators (or distributed according to empirical weights); finally, each stage is weighted and summarized according to the length of time or preset weights into a microbial community reaction speed sequence for the entire trajectory and stored in the database.

[0030] The specific operational steps include: the device uploads sensor values ​​every 5-15 minutes, the data receiving end first performs time alignment and denoising (moving average window 3-5 times), linear interpolation of missing points, finite difference differentiation to obtain the rate sequence, peak detection uses sliding window local maximum judgment combined with threshold filtering, and the calculation results are stored in time windows and generate alarms / records.

[0031] In one implementation of the present invention, using a batch of high-nitrogen raw materials as an example, the system sets the raw material sampling time at 9:00 AM on August 1st and the fermentation start time at 10:00 AM on August 1st. A time window is set every six hours. During the first two time windows, the pH value slowly decreased from 6.5 to 6.1, and the temperature increased from 31°C to 38°C. The temperature and humidity gradients calculated by the system were small, and the acid-base neutralization rate dominated, thus determining the initial stage.

[0032] During the next three time windows, the temperature rapidly rose to 55°C, which the system identified as the mesothermal stage, with the heat generation rate as the dominant factor. In the following time window, the CO2 concentration suddenly rose to 9000 ppm, with a significant gas release rate, thus establishing the gas production stage. Throughout this process, the system automatically adjusted the weighting of the three indicators to match the fermentation activity logic at different stages, providing stable reference indicators for subsequent quality comparisons and process deviation analysis.

[0033] Step S3: After the organic fertilizer production line is completed, the output quality feature set of the organic fertilizer product is collected; the corrosion degree index in the output quality feature set is compared with the baseline bacterial population rate and bacterial population reaction speed, and the fermentation process deviation data is output; Preferably, step S3 includes the following: When the organic fertilizer production line is completed, the humus scale index is collected through the fertilizer finished product detection unit and the detection timestamp is marked to form an output quality feature set; Among them, the humic scale index is composed of the absorption ratio of humic acid to fulvic acid, and is paired with the raw material information set corresponding to the benchmark bacterial population rate to establish the raw material-humus correspondence; The raw material-humus correspondence is compared with the benchmark bacterial population rate and bacterial population reaction speed to output the fermentation process deviation data. The comparison standard is to calculate the difference in fermentation status within each time window.

[0034] In an embodiment of the present invention, at the end of the production line, a detection unit collects the fertilizer's humic scale indicator. The humic scale, composed of the spectral absorption ratio of humic acid to fulvic acid, reflects the degree of organic matter conversion in the finished product. After detection, the system timestamps the indicator and includes it in the output quality feature set. Then, based on the previous raw material sampling information, the system associates the humic scale indicator with the corresponding raw material batch, forming a set of "raw material-humic" pairings. This is then compared with the previously calculated baseline bacterial population rate and bacterial population reaction rate, time window by time window. This comparison involves dividing the fermentation behavior trajectory into unified time windows, extracting the bacterial population reaction data in each time window and the corresponding window data in the finished product indicator. Using a predefined fermentation state difference function, the system quantifies the degree of deviation between each window, thereby forming a fermentation process deviation dataset, which provides a basis for subsequent anomaly identification and process adjustments. The key to this entire method lies in data label alignment, cross-stage correspondence, and difference quantification, all of which are interconnected and traceable.

[0035] Preferably, comparing the corrosion degree index in the output quality feature set with the baseline bacterial population rate and bacterial population reaction speed includes the following: Extracting corrosion degree indicators from the output quality feature set; The corrosion index, the baseline bacterial population rate, and the bacterial population reaction speed are combined to construct a two-dimensional structure array, and the key node information is nested to obtain the fermentation phase array. The fermentation phase array is graded using a preset deviation threshold to obtain fermentation process deviation data.

[0036] Preferably, the nested key node information includes the following: The nested key node information includes the first node, the second node and the third node; The first node represents the critical point of bacterial activity, which indicates the local maximum value of the baseline bacterial rate or bacterial reaction speed at the critical point of bacterial activity. The second node represents the temperature high plane stability point, that is, the stability point of the temperature peak; The third node represents the abnormal point of oxygen fluctuation in the pile body, which meets the trend of continuous decrease in oxygen content and is accompanied by a sudden increase in ammonia concentration.

[0037] Preferably, constructing the two-dimensional structure array further includes: Construct a two-dimensional structure array, where the horizontal direction represents the key time window in the fermentation behavior trajectory, and the vertical direction represents the fermentation process deviation data composed of corrosion degree indicators; The key time window is based on the moment when the raw materials enter the tank to trace back the abnormal gas release window in the fermentation stage, and a sequence of equal-width time windows is expanded with this window as the center; The corrosion degree indicators form a corresponding sequence in each time window, constituting a unit comparison unit; The fermentation state difference is embedded into the unit comparison unit using the key time window as the index to form a two-dimensional structure array.

[0038] In an embodiment of the present invention, a structured data matrix is ​​constructed to correlate the quality indicators of the final output with the microbial responses during different time windows during the fermentation process to identify process deviations. Specifically, the system first extracts the corrosion index from the finished organic fertilizer product, primarily expressed as the absorption ratio of humic acid to fulvic acid, and matches it with the baseline microbial rate and microbial response rate during the fermentation process. After aligning the time tags, a two-dimensional structure array is constructed, in which the horizontal axis represents the key time window defined centered around the abnormal gas release window, and the vertical axis represents the corrosion index sequence collected in different time windows.

[0039] Each cell in this array represents the mapping relationship between the reaction of the raw materials and the quality of the finished product within a specific time window. To enhance the interpretability of the data, the array also embeds three types of key node information: the first type of node is the critical point of bacterial activity, that is, the moment when the bacterial reaction rate reaches a local extreme value; the second type is the temperature high-plane stability point, corresponding to the time node when the temperature change enters the plateau phase; and the third type is the oxygen fluctuation anomaly point, that is, the abnormal stage where the oxygen level continuously decreases and the ammonia concentration suddenly increases. These nodes are embedded in the array as markers to help highlight the biological activity or environmental response characteristics of different stages. The constructed array is then compared with the set deviation threshold to identify possible process anomaly areas in different fermentation stages. This process not only completes the process state mapping in the spatiotemporal dimension, but also provides an operational method to quantify the volatility and stability of the process.

[0040] In one implementation of the present invention, assuming that the gas release rate suddenly increases within the fourth hour after the raw materials enter the tank, the system sets an equal-width time window sequence from the second hour to the sixth hour based on this.

[0041] During these time windows, the collected humification scale indicators were 2.1, 2.5, 3.0, 2.7, and 2.4, respectively. Meanwhile, the bacterial reaction rates were 0.8, 1.2, 1.5, 1.3, and 1.0, respectively. Combined with the temperature plateau (e.g., the temperature remained above 65°C in the third hour), the ammonia concentration spike (in the fifth hour), and the bacterial reaction rate peak (in the fourth hour), these three key nodes were embedded in the array for this time period. Comparing these values ​​with the set deviation threshold revealed that the fermentation state in the fifth hour window differed from the standard value, thus recording it as a fermentation anomaly window. This process deviation segment was then output for subsequent determination of whether it was due to operational error or insufficient raw material adaptability.

[0042] This example illustrates that the core logic of the entire technical solution lies in connecting the three actions of alignment, nesting, and quantification in series, using structured data to complete process traceability and deviation detection.

[0043] like Figure 2 The figure shows the schematic diagram of the bio-organic fertilizer production line; 101 is the raw material input unit - responsible for obtaining the raw material information set, including the collection of microbial activity characteristic data; 102 is a fermentation reactor - constructing fermentation behavior trajectory and monitoring the bacterial metabolic process; 103 is a process control unit - performs ventilation and temperature control operations and establishes a process event timeline; 104 is a data acquisition sensor - monitoring key parameters such as temperature, humidity, pH, and gas release; 105 is a finished fertilizer testing unit - collecting humus scale indicators to form an output quality feature set.

[0044] Step S4: Trace and associate the fermentation process deviation data and the fermentation behavior trajectory to obtain an organic fertilizer process deviation mapping table; identify the control abnormalities of the fermentation production line based on the organic fertilizer process deviation mapping table, and construct an organic fertilizer production report.

[0045] Preferably, step S4 includes the following steps: Step S41: tracing and associating fermentation process deviation data and fermentation behavior trajectory to obtain production line node abnormal data; constructing an organic fertilizer process deviation mapping table based on the production line node abnormal data; Step S42: Identify abnormal control items of the fermentation production line according to the organic fertilizer process deviation mapping table and generate abnormal items of the whole process nodes; Step S43: If the abnormal item of the whole process node is within the preset range, it is determined that the organic fertilizer production line is in a normal production state, and the whole process monitoring is maintained until the end of the production cycle; if it is not within the preset range, it is determined that the organic fertilizer production line is in an abnormal production state, an audible and visual alarm is used, and an organic fertilizer production report with abnormal nodes is generated.

[0046] In an embodiment of the present invention, the fermentation process deviation data obtained by comparing the output quality characteristics with the fermentation stage data is combined with the time series records in the fermentation behavior trajectory to locate the abnormal time windows and abnormal points on the fermentation time axis. These points are defined as production line node abnormal data. Based on these abnormal data, the system constructs an "organic fertilizer process deviation mapping table" in the data table structure. The table records the time when the abnormality occurred, the corresponding process parameters (such as temperature, ventilation volume, pH, etc.), and the offset of indicators such as the bacterial reaction speed or gas release rate in the corresponding fermentation stage. Afterwards, the system traverses the deviation mapping table to extract all identifiable control abnormalities, such as delayed heat response, excessive pH fluctuations, abnormal ventilation jitter, etc., and summarizes them into "full process node abnormality items", which reflects the set of points that are determined to deviate from the normal control trajectory during the entire production cycle. Finally, the system compares this set of abnormal items against pre-set threshold models (such as the maximum number of allowable deviations, the maximum allowable offset amplitude, and the maximum duration of continuous abnormalities). If the results are within the tolerance range, the system enters normal monitoring. If they are outside the range, an audible and visual alarm is automatically triggered, the abnormal point is recorded, and a production report with an abnormality marker is generated. This process, based on time series data, process status data, and threshold logic, combines structured mapping relationships with multi-dimensional deviation indicators to create an automated closed-loop production line diagnostic method.

[0047] In one implementation of the present invention, on a 48-hour organic fertilizer fermentation production line, the system detected that the bacterial reaction rate decreased by 25%, 30%, and 22% at the 12th, 18th, and 36th hours, respectively. Furthermore, the corresponding pH fluctuations exceeded ±1.8, and the temperature stagnated for over two hours at the 36th hour. These points were identified as "abnormal production line node data." The system then linked these abnormal points with their corresponding original behavior trajectories, temperature, humidity, ventilation rate, and other parameters, marking three high-risk nodes in a deviation mapping table. After a full process scan, the system determined that there were three high-risk abnormal nodes in this fermentation cycle, one of which was a continuous deviation timeout (at the 36th hour), exceeding the preset maximum deviation duration of two hours. The system ultimately determined that the production line status for this batch was "abnormal," triggering an audible and visual alarm. The abnormal node information, along with the corresponding time window and parameter fluctuation value, was also marked in the generated organic fertilizer production report. This completes the entire closed-loop process from data acquisition, anomaly identification, deviation modeling, and alarm output.

[0048] In the overall implementation of the present invention, a batch is set with a sampling interval of 10 minutes and a window width of 6 hours (36 sampling points). In the window from the 18th hour to the 24th hour, From 2500ppm to 5200ppm (regression slope within the window ≈ +74ppm / h), the temperature rises from 45 Rising to 61 (Slope ≈ +2.5 / h), pH fluctuations in this window cross the threshold once. Calculated conversion = 0.12 (unit / window), gas_rate = 74, heat_rate = 2.5, neutralize_rate = -0.05 for this window; The stage is determined to be the gas production stage (gas dominated, ), Then reaction_speed=0.10.12+0.674+0.22.5+0.1(-0.05)≈44.5 (the example value is only used to illustrate the dimensional synthesis logic).

[0049] If the final humus scale value corresponding to the same window is 20% lower than expected (the difference exceeds the threshold), the window will be marked as "deviation", embedded with node information (such as the 20th hour is the peak of bacterial activity, and the temperature platform appears at the 22nd hour), and recorded in the deviation mapping table. If two high-level deviation windows are found cumulatively, an alarm will be automatically triggered and the relevant time window, original sensor curve snapshot and recommended focus points (such as checking the ventilation system or raw material ratio) will be listed in the report.

[0050] like Figure 3 As shown, the method for implementing the change of gas concentration in the fermentation process of the present invention is shown, wherein Concentrations are indicated by red triangles; Concentrations are represented by green circles; Concentrations are represented by blue diamonds.

[0051] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0052] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for extracting data from a bio-organic fertilizer production process, characterized in that: The following steps are involved: Step S1: Obtaining a raw material information set and a process parameter set; Calculate the baseline bacterial population rate based on the microbial activity characteristics of the raw material information set; Step S2: labeling the raw material information set and the process parameter set with time series timestamps, and constructing the fermentation behavior trajectory; Analyze the microbial activity characteristics of fermentation behavior trajectories and calculate the bacterial community reaction rate; Step S3: After the organic fertilizer production line is completed, the output quality feature set of the organic fertilizer product is collected; the corrosion degree index in the output quality feature set is compared with the baseline bacterial population rate and bacterial population reaction speed, and the fermentation process deviation data is output; Step S4: Trace and associate the fermentation process deviation data and the fermentation behavior trajectory to obtain an organic fertilizer process deviation mapping table; identify the control abnormalities of the fermentation production line based on the organic fertilizer process deviation mapping table, and construct an organic fertilizer production report.

2. bio-organic fertilizer production process data extraction method as claimed in claim 1, is characterized in that, Step S1 further includes: Sending a data collection request signal to the raw material input unit and the process control unit; Receive the data collection request signal of the current batch of raw material information set and add the raw material sampling timestamp; Obtain the fermentation start and stop times, execution sequence of ventilation or temperature control operations in the process parameter set, and establish a process event timeline.

3. bio-organic fertilizer production process data extraction method as claimed in claim 1, is characterized in that, Step S2 includes the following steps: Step S21: marking the raw material sampling timestamp for the raw material information set and the process parameter set, and performing segmented sampling according to the unified time window of the process event time axis to generate a time window index group; Step S22: performing linear interpolation on the temperature and humidity according to the time window index group to obtain a fertilizer time series data stream; Step S23: segmenting the fertilizer time series data stream according to the nodes of the time series timestamps and the fermentation stage labels to construct a fermentation behavior trajectory; Step S24: extracting the temperature and humidity change gradient and pH fluctuation frequency as microbial metabolism stimulation indicators, and comparing the indicator change rates in the previous and next time windows to generate microbial stimulation indicator data; Step S25: Calculate the bacterial activity conversion rate of the bacterial excitation index data, and generate the bacterial reaction rate by combining the gas release rate, heat generation rate, and acid-base neutralization rate per unit time in the fermentation behavior trajectory.

4. bio-organic fertilizer production process data extraction method as claimed in claim 1, is characterized in that, Step S25 also includes the following: The fermentation behavior trajectory is divided into three stages according to the timestamp: the initial stage, the medium temperature stage, and the gas production stage. The proportions of the acid-base neutralization rate, the heat generation rate, and the gas release rate are adjusted respectively, where: The initial stage uses the acid-base neutralization rate as an indicator; The heat generation rate is used as an indicator in the medium temperature range; The gas production section is indexed by the gas release rate, where the index is 60% of the proportion allocated.

5. bio-organic fertilizer production process data extraction method as claimed in claim 1, is characterized in that, Step S3 includes the following: When the organic fertilizer production line is completed, the humus scale index is collected through the fertilizer finished product detection unit and the detection timestamp is marked to form an output quality feature set; Among them, the humic scale index is composed of the absorption ratio of humic acid to fulvic acid, and is paired with the raw material information set corresponding to the benchmark bacterial population rate to establish the raw material-humus correspondence; The raw material-humus correspondence is compared with the benchmark bacterial population rate and bacterial population reaction speed to output the fermentation process deviation data. The comparison standard is to calculate the difference in fermentation status within each time window.

6. bio-organic fertilizer production process data extraction method as claimed in claim 5, is characterized in that, Comparison of the corrosion level indicators in the output quality feature set with the baseline bacterial population rate and bacterial population reaction rate includes the following: Extracting corrosion degree indicators from the output quality feature set; The corrosion index, the baseline bacterial population rate, and the bacterial population reaction speed are combined to construct a two-dimensional structure array, and the key node information is nested to obtain the fermentation phase array. The fermentation phase array is graded using a preset deviation threshold to obtain fermentation process deviation data.

7. bio-organic fertilizer production process data extraction method as claimed in claim 6, is characterized in that, Nested key node information includes the following: The nested key node information includes the first node, the second node and the third node; The first node represents the critical point of bacterial activity, which indicates the local maximum value of the baseline bacterial rate or bacterial reaction speed at the critical point of bacterial activity. The second node represents the temperature high plane stability point, that is, the stability point of the temperature peak; The third node represents the abnormal point of oxygen fluctuation in the pile body, which meets the trend of continuous decrease in oxygen content and is accompanied by a sudden increase in ammonia concentration.

8. the bio-organic fertilizer production process data extraction method as claimed in claim 6, is characterized in that, Constructing a two-dimensional structure array also includes: Construct a two-dimensional structure array, where the horizontal direction represents the key time window in the fermentation behavior trajectory, and the vertical direction represents the fermentation process deviation data composed of corrosion degree indicators; The key time window is based on the moment when the raw materials enter the tank to trace back the abnormal gas release window in the fermentation stage, and a sequence of equal-width time windows is expanded with this window as the center; The corrosion degree indicators form a corresponding sequence in each time window, constituting a unit comparison unit; The fermentation state difference is embedded into the unit comparison unit using the key time window as the index to form a two-dimensional structure array.

9. bio-organic fertilizer production process data extraction method as claimed in claim 1, is characterized in that, Step S4 includes the following steps: Step S41: tracing and associating fermentation process deviation data and fermentation behavior trajectory to obtain production line node abnormal data; constructing an organic fertilizer process deviation mapping table based on the production line node abnormal data; Step S42: Identify abnormal control items of the fermentation production line according to the organic fertilizer process deviation mapping table and generate abnormal items of the whole process nodes; Step S43: If the abnormal item of the whole process node is within the preset range, it is determined that the organic fertilizer production line is in a normal production state, and the whole process monitoring is maintained until the end of the production cycle; if it is not within the preset range, it is determined that the organic fertilizer production line is in an abnormal production state, an audible and visual alarm is used, and an organic fertilizer production report with abnormal nodes is generated.

10. A bio-organic fertilizer production process data extraction system, characterized in that: For executing the method for extracting data from the bio-organic fertilizer production process according to claim 1, the bio-organic fertilizer production process data extraction system comprises: The raw material analysis module is used to obtain the raw material information set and the process parameter set; based on the microbial activity characteristics of the raw material information set, the baseline bacterial population rate is calculated; The fermentation analysis module is used to annotate the raw material information set and process parameter set with time series timestamps and construct fermentation behavior trajectories; Analyze the microbial activity characteristics of fermentation behavior trajectories and calculate the bacterial community reaction rate; Analyze the microbial activity characteristics of fermentation behavior trajectories and calculate the bacterial community reaction rate; The quality deviation module is used to collect the output quality feature set of the organic fertilizer product after the organic fertilizer production line is completed; compare the corrosion degree index in the output quality feature set with the baseline bacterial population rate and bacterial population reaction speed, and output the fermentation process deviation data; The traceability diagnosis module is used to trace and correlate fermentation process deviation data and fermentation behavior trajectories to obtain an organic fertilizer process deviation mapping table; based on the organic fertilizer process deviation mapping table, it identifies control anomalies of the fermentation production line and constructs an organic fertilizer production report.

Images