Intelligentized method and system for processing and energy conversion of farm waste

Abstract

The application relates to the technical field of fecal water treatment, and discloses an intelligent farm waste treatment and energy conversion method and system.The method comprises the following steps: performing normalization processing on the fecal water detection data of a farm to obtain standardization detection data of the fecal water detection data; performing weight distribution on the standardization detection data and historical fecal water treatment data in a sliding window; performing time sequence fusion on the standardization detection data and the historical fecal water treatment data according to the weight distribution result to obtain a fusion data set of the farm; evaluating the equivalent of the convertible organic matter in the farm according to the fusion data set, and evaluating the energy potential of the farm according to the equivalent of the convertible organic matter to obtain an energy conversion potential index of the farm; and generating the regulation and control parameters of the fecal water treatment equipment in the farm based on the deviation amount of the energy conversion potential index and an energy conversion threshold value; and the application can improve the efficiency of the fecal water treatment in the farm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of manure treatment, and particularly relates to an intelligent farm waste treatment and energy conversion method and system. BACKGROUND

[0002] In the field of farm waste treatment and energy conversion, the prior art lacks systematic optimization of manure detection data processing, cannot effectively eliminate missing values and format error data points in the data, and cannot accurately filter values deviating from the normal mode, resulting in uneven quality of raw data. At the same time, when integrating real-time detection data and historical processing data, the prior art does not consider the time effectiveness difference of the data for reasonable weight distribution, cannot realize efficient time sequence fusion of the two, and thus cannot provide reliable data support for subsequent convertible organic matter equivalent evaluation based on the data, affects the accuracy of the evaluation results, and buries hidden dangers for energy conversion potential analysis, and it is difficult to guarantee the scientificity and effectiveness of subsequent energy conversion related analysis.

[0003] The prior art also has obvious deficiencies in the energy conversion potential evaluation and equipment control links. In the energy conversion potential evaluation, it cannot dynamically correct the organic matter baseline degradation rate by combining real-time microbial activity indicator parameters, and cannot fully incorporate equipment operation efficiency factors and environmental heat loss coefficients to modify the basic energy output data, resulting in a deviation between the generated energy conversion potential indicators and the actual situation, and the inability to truly reflect the energy conversion capacity of the farm. In terms of manure treatment equipment control, the prior art mostly sets parameters based on fixed thresholds, does not adaptively adjust the preliminary control parameters based on the real-time running state of the equipment, and cannot match the treatment needs under different working conditions, ultimately resulting in low manure treatment efficiency, suboptimal energy conversion effect, and the inability to meet the intelligent and efficient needs of the farm for waste treatment and energy recovery. SUMMARY

[0004] The present application provides an intelligent farm waste treatment and energy conversion method and system to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the intelligent farm waste treatment and energy conversion method provided by the present application comprises:

[0006] S1, normalizing the manure detection data of the farm to obtain standardized detection data of the manure detection data;

[0007] S2, assigning weights to the standardized detection data and historical manure treatment data in a sliding window;

[0008] S3, time series fusion of the standardized detection data and the historical fecal water treatment data according to a result of the weight distribution, to obtain a fusion data set of the farm;

[0009] S4, evaluating a convertible organic matter equivalent in the farm according to the fusion data set, and energy potential evaluation of the farm according to the convertible organic matter equivalent, to obtain an energy conversion potential index of the farm;

[0010] S5, generating a regulation parameter of the fecal water treatment equipment in the farm based on a deviation amount of the energy conversion potential index and an energy conversion threshold value.

[0011] In a preferred embodiment, the normalization processing of the fecal water detection data of the farm to obtain the standardized detection data of the fecal water detection data comprises:

[0012] Eliminating data points with missing and format errors of multiple monitoring parameters in the fecal water detection data to obtain a preliminary valid data set of the fecal water detection data;

[0013] Removing values deviating from the normal mode in the preliminary valid data set based on a predefined data distribution range to obtain a purified data set of the fecal water detection data;

[0014] Adjusting the value range of the monitoring parameters in the purified data set to obtain the standardized detection data of the fecal water detection data.

[0015] In a preferred embodiment, the weight distribution of the standardized detection data and the historical fecal water treatment data in the sliding window comprises:

[0016] According to the time span of the sliding window, the historical fecal water treatment data is divided into a window-in historical data segment;

[0017] A preset timeliness priority strategy is set to assign a basic weight to the standardized detection data and a decreasing weight to the window-in historical data segment;

[0018] According to the recent operation stability index of the fecal water treatment equipment, the relative proportion of the basic weight and the decreasing weight is dynamically adjusted to generate a weight distribution strategy of the farm.

[0019] In a preferred embodiment, the time series fusion of the standardized detection data and the historical fecal water treatment data according to the result of the weight distribution to obtain the fusion data set of the farm comprises:

[0020] From the historical fecal water treatment data, a key data segment associated with the strategy standardized detection data period is screened out;

[0021] According to the weight distribution strategy, the time series aligned standardized detection data and the key data segment are weighted and fused in time sequence to obtain an initial fusion data set of the farm;

[0022] Eliminate data conflicts in the initial fusion data set caused by time sequence misalignment and weight distribution deviation to obtain a fusion data set of the farm;

[0023] Update the fusion data set to the historical manure water treatment database.

[0024] In a preferred embodiment, the evaluation of the convertible organic matter equivalent in the farm according to the fusion data set comprises:

[0025] Separate the organic matter concentration data sequence and the corresponding environmental parameter sequence from the fusion data set to obtain an organic matter conversion analysis data set of the farm;

[0026] Match and query the organic matter conversion analysis data set with a pre-established organic matter degradation characteristic library to obtain a baseline degradation rate of the farm under the current environmental conditions;

[0027] Introduce a real-time monitored microbial activity indicating parameter of the farm to dynamically correct the baseline degradation rate to obtain an effective degradation rate of the farm;

[0028] Determine the convertible organic matter equivalent in the farm based on the manure water flow data and the effective degradation rate.

[0029] In a preferred embodiment, the energy potential evaluation of the farm according to the convertible organic matter equivalent comprises:

[0030] Determine the basic energy output data of the farm based on the convertible organic matter equivalent and the gas production characteristic parameters of the microorganisms in the farm;

[0031] Introduce the equipment operation efficiency factor and the environmental heat loss coefficient to correct the basic energy output data, and obtain the net available energy output of the farm;

[0032] Convert the net available energy output into standard coal equivalent and equivalent electric energy equivalent to obtain the standardized energy output index of the farm;

[0033] Quantify the standardized energy output index into an economic value evaluation result in combination with the current energy market price parameters;

[0034] Map the standardized energy output index and the economic value evaluation result to the energy conversion potential index of the farm.

[0035] In a preferred embodiment, the calculation formula of the energy conversion potential index is as follows:

[0036] ;

[0037] In the formula, is the energy conversion potential index, is the technical value dimension weight coefficient, is the quantitative value of the standardized energy output index, is the quantitative value of the economic value assessment result, is the economic value dimension weight coefficient, is the natural logarithm function, is the hyperbolic tangent function.

[0038] In a preferred embodiment, the generation of the regulation parameter of the manure treatment equipment in the farm based on the deviation amount of the energy conversion potential index and the energy conversion threshold value comprises:

[0039] Comparing and analyzing the energy conversion potential index and the energy conversion threshold value, the positive or negative direction and the size level of the deviation amount between the energy conversion potential index and the energy conversion threshold value are determined;

[0040] According to the positive or negative direction of the deviation amount, the basic adjustment direction corresponding to the energy conversion potential index is matched from the preset regulation strategy library;

[0041] Combining the size level of the deviation amount, the regulation intensity is determined based on the basic adjustment direction, and a preliminary regulation parameter set of the farm is obtained;

[0042] The real-time data of the operating state of the manure treatment equipment in the farm are introduced, and the preliminary regulation parameter set is adaptively adjusted to obtain the regulation parameter of the manure treatment equipment in the farm.

[0043] In a preferred embodiment, the introduction of the real-time data of the operating state of the manure treatment equipment in the farm to adaptively adjust the preliminary regulation parameter set to obtain the regulation parameter of the manure treatment equipment in the farm comprises:

[0044] The key operating state parameters of the manure treatment equipment are collected in real time;

[0045] Comparing and analyzing the key operating state parameters and the rated operating parameters of the manure treatment equipment, the equipment operating state evaluation result of the manure treatment equipment is obtained;

[0046] Matching the parameter adjustment factor corresponding to the device running state evaluation result from the device adaptability rule base;

[0047] The parameter adjustment factor is used to cooperatively modify the stirring frequency set value, temperature control target value and medicament dosage in the preliminary control parameter set;

[0048] The preliminary control parameters after the cooperative modification are subjected to logical consistency verification, and the control parameters of the manure water treatment equipment in the farm are obtained.

[0049] In order to solve the above problems, the application also provides an intelligent farm waste treatment and energy conversion system, which comprises:

[0050] A data processing module is configured to normalize the manure water detection data of the farm to obtain standardized detection data of the manure water detection data;

[0051] A weight distribution module is configured to distribute weights to the standardized detection data and historical manure water treatment data in a sliding window;

[0052] A time series fusion module is configured to perform time series fusion on the standardized detection data and the historical manure water treatment data according to the weight distribution result to obtain a fusion data set of the farm;

[0053] An energy conversion potential index generation module is configured to evaluate the equivalent organic matter that can be converted in the farm according to the fusion data set, and evaluate the energy potential of the farm according to the equivalent organic matter that can be converted to obtain an energy conversion potential index of the farm;

[0054] A control parameter conversion module is configured to generate control parameters of a manure water treatment equipment in the farm based on the deviation amount of the energy conversion potential index and an energy conversion threshold.

[0055] Compared with the prior art, the application has the following beneficial effects:

[0056] 1. The application can obtain high-quality standardized detection data by systematically normalizing the manure water detection data of the farm, removing missing and format error data points, removing values deviating from the normal mode and adjusting the parameter value range; meanwhile, the application assigns basic weights and decreasing weights in a sliding window according to a time effectiveness priority strategy, and dynamically adjusts the weight proportion in combination with a recent running stability index of the manure water treatment equipment, thereby realizing accurate time series fusion of the standardized detection data and the historical manure water treatment data, obtaining reliable fusion data set after eliminating data conflicts, updating to the historical database, and providing accurate and comprehensive data support for subsequent convertible organic matter equivalent evaluation, and guaranteeing the accuracy of the evaluation link.

[0057] 2. In the energy conversion potential evaluation, the application introduces a real-time microbial activity indicator parameter of the farm to dynamically correct the baseline degradation rate, combines with the fecal water flow data to determine the equivalent of convertible organic matter, and then corrects the basic energy output data through the equipment operation efficiency factor and the environmental heat loss coefficient, and also quantifies the economic value evaluation result to generate an accurate energy conversion potential index; the subsequent deviation amount matching adjustment direction and determination of the control intensity are based on the deviation amount of the index and the energy conversion threshold, and the control parameters are cooperatively corrected and logically consistent verification is performed in combination with the real-time operation state data of the equipment, so that the generated control parameters are highly adapted to the equipment working condition, and finally the fecal water treatment efficiency of the farm can be effectively improved, the energy conversion effect is optimized, and efficient cooperation of waste treatment and energy recovery is realized. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 The flowchart of the intelligent farm waste treatment and energy conversion method provided by an embodiment of the application is shown.

[0059] Figure 2 The functional module diagram of the intelligent farm waste treatment and energy conversion system provided by an embodiment of the application is shown.

[0060] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0061] It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0062] The embodiments of the application provide an intelligent farm waste treatment and energy conversion method. The execution subject of the intelligent farm waste treatment and energy conversion method includes but is not limited to at least one of electronic devices such as a server and a terminal which can be configured to execute the method provided by the embodiments of the application. In other words, the intelligent farm waste treatment and energy conversion method can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and big data and artificial intelligence platforms, etc. basic cloud computing services.

[0063] REFERENCE Figure 1As shown, it is a flowchart of the intelligent farm waste treatment and energy conversion method provided by an embodiment of the present application. In this embodiment, the intelligent farm waste treatment and energy conversion method comprises:

[0064] S1, normalizing the manure detection data of the farm to obtain standardized detection data of the manure detection data;

[0065] In the embodiment of the present application, the normalization of the manure detection data of the farm to obtain the standardized detection data of the manure detection data comprises:

[0066] Eliminate data points with missing and format errors in multiple monitoring parameters in the manure detection data to obtain a preliminary valid data set of the manure detection data;

[0067] Remove values deviating from the normal mode in the preliminary valid data set based on a predefined data distribution range to obtain a purified data set of the manure detection data;

[0068] Adjust the value range of the monitoring parameters in the purified data set to obtain the standardized detection data of the manure detection data.

[0069] Specifically, each data point in the original manure detection data is checked one by one, all monitoring parameters contained in the data point are checked, if there is no any record in the position corresponding to a monitoring parameter, it is determined that the parameter is missing, and the format of each monitoring parameter is checked, for example, date type parameters need to conform to the pre-set year-month-day form, value type parameters need to contain only numbers and decimal points (no letters, symbols, etc. Irrelevant characters), as long as there is any missing monitoring parameter or any monitoring parameter format error in a data point, the data point is removed from the original manure detection data, and all the remaining data points that are not removed together constitute the preliminary valid data set of the manure detection data.

[0070] Further, according to the common value of each monitoring parameter in the same type of manure normal detection scene, the predefined data distribution range of each monitoring parameter is determined, and then each data in the preliminary valid data set is extracted one by one, and it is checked whether the value of each monitoring parameter in the data falls within the predefined data distribution range of the corresponding parameter, if the value of any monitoring parameter in a data exceeds its corresponding predefined data distribution range, the data is removed from the preliminary valid data set, and all the remaining data together constitute the purified data set of the manure detection data.

[0071] Further, a target value range of all monitoring parameters is determined first, and then for each monitoring parameter of each data in the purification data set, the current value of the parameter is adjusted according to the corresponding relationship between the target value range and the current value, for example, the value range of a certain monitoring parameter in the purification data set is 20-80, and the target value range is 0-100, then the current value of the parameter is subtracted by 20, and the result is used as the adjusted value, so that the values of all monitoring parameters in the purification data set fall within the target value range, and all the data after the above adjustment together constitute the standardized detection data of the fecal water detection data.

[0072] In summary, the data points with missing data and format errors are removed to filter out invalid data interference and form a preliminary valid data set, thereby avoiding misleading of invalid information to subsequent analysis from the source; secondly, the values deviating from the normal mode in the preliminary valid data are removed to further purify the data, reduce the deviation caused by extreme abnormal values, and greatly improve the reliability of the data; finally, the value range of the monitoring parameters in the purification data is adjusted to make the monitoring parameters of different dimensions (such as organic matter concentration, environmental temperature, etc.) in a unified scale, and solve the problem of parameter dimension difference.

[0073] In summary, the standardized detection data generated finally can provide compatible and accurate data basis for subsequent weight allocation in the sliding window and time series fusion with historical fecal water treatment data, ensure the accuracy of data fusion, and then provide reliable data support for subsequent convertible organic matter equivalent evaluation and energy conversion potential analysis, thereby ensuring the analysis accuracy of the entire waste treatment and energy conversion process and helping to improve the effect of subsequent links.

[0074] S2, weight allocation is performed on the standardized detection data and historical fecal water treatment data in the sliding window;

[0075] In the embodiment of the present application, the weight allocation of the standardized detection data and the historical fecal water treatment data in the sliding window comprises:

[0076] According to the time span of the sliding window, the historical fecal water treatment data is divided into a window-in historical data segment;

[0077] A preset timeliness priority strategy is set to allocate a basic weight to the standardized detection data and a decreasing weight to the window-in historical data segment;

[0078] According to the recent running stability index of the fecal water treatment equipment, the relative proportion of the basic weight and the decreasing weight is dynamically adjusted to generate a weight allocation strategy of the farm.

[0079] Specifically, first determine the time span of the sliding window, which is a fixed time length set in advance, from the starting time point of the historical fecal water treatment data, the time span is the length of a single window, all historical fecal water treatment data contained in this time period are classified as the first window historical data segment, then move the window back once according to the fixed moving interval (the moving interval is not more than the time span of the sliding window), the historical fecal water treatment data in the new time period is classified as the next window historical data segment, repeat the window moving and data classification operation until all historical fecal water treatment data are classified into the corresponding window, and finally obtain multiple window historical data segments.

[0080] Further, a preset timeliness priority strategy is set, which clearly indicates that the closer the time is to the current data, the greater the impact on the analysis result should be. Based on this strategy, a fixed basic weight is directly assigned to the standardized detection data (the weight value is clear at the time of setting and does not change with historical data), and then all window historical data segments are sorted by time proximity. The weight of the window historical data segment closest in time is higher than that of other earlier window historical data segments, and the weight of the corresponding window historical data segment decreases from the window closest in time to the window farthest in time, that is, a decreasing weight is formed, and the allocation of the basic weight and the decreasing weight is completed.

[0081] Further, first obtain the recent running stability index of the fecal water treatment equipment, which is determined by statistics of the recent fault-free running time, fault occurrence frequency and normal running time after fault repair and other information. If the recent running stability index of the equipment is high, it means that the historical data has high reference value for current fecal water treatment analysis, so the proportion of the decreasing weight in the overall weight is increased, and the proportion of the basic weight is decreased. If the recent running stability index of the equipment is low, it means that the recent standardized detection data can better reflect the current equipment processing state, so the proportion of the basic weight in the overall weight is increased, and the proportion of the decreasing weight is decreased. After the above dynamic adjustment, the specific values and relative proportion relationship of the basic weight and the decreasing weight determined together constitute the weight allocation strategy of the farm.

[0082] In general, the historical fecal water treatment data is divided into window historical data segments according to the time span of the sliding window, which can accurately focus on the historical data with high correlation to the current analysis period, avoid irrelevant historical data interference, ensure the pertinence of data selection, and provide a reasonable data range for weight allocation.

[0083] In general, the preset timeliness priority strategy is used to allocate the basic weight to the standardized detection data with stronger real-time performance and to allocate the decreasing weight to the historical data segment in the window, which highlights the guiding value of real-time data for current processing demand, fully utilizes the reference significance of historical data, balances the effects of data timeliness and historical experience, and avoids the deviation caused by single dependence on a certain type of data.

[0084] In general, the relative proportion of the basic weight and the decreasing weight is dynamically adjusted in combination with the recent operation stability index of the manure treatment equipment, so that the weight allocation can adapt to the actual working condition of the equipment.

[0085] S3, time series fusion is performed on the standardized detection data and the historical manure treatment data according to the weight allocation result, and a fusion data set of the farm is obtained;

[0086] In the embodiment of the present application, the time series fusion is performed on the standardized detection data and the historical manure treatment data according to the weight allocation result, and a fusion data set of the farm is obtained, which comprises:

[0087] The key data segments associated with the strategy standardized detection data period are filtered from the historical manure treatment data;

[0088] According to the weight allocation strategy, the standardized detection data and the key data segments are weighted and fused in time sequence after time alignment, and an initial fusion data set of the farm is obtained;

[0089] The data conflicts caused by time sequence misalignment and weight allocation deviation in the initial fusion data set are eliminated, and a fusion data set of the farm is obtained;

[0090] The fusion data set is updated to the historical manure treatment database.

[0091] Specifically, the specific period of the strategy standardized detection data is first determined, which is a pre-determined continuous time interval. The time range of each historical data segment is checked one by one in the historical manure treatment data, and the historical data segments whose time range is completely within the period, or whose time start point and end point overlap with the period and whose core data points are all within the period are all extracted. These extracted historical data segments are the key data segments associated with the strategy standardized detection data period.

[0092] Further, the standardized detection data and the key data segment are first time-aligned, the time axes of the two are unified to the same time interval (such as one time node per hour), and it is ensured that there are corresponding values of the standardized detection data and corresponding values of the key data segment under each time node. Then, according to the weight distribution strategy, each value of the standardized detection data is multiplied by the corresponding basic weight, and the values of the key data segment at different time nodes are respectively multiplied by the corresponding decreasing weight (the closer the time, the higher the decreasing weight corresponding to the value of the key data segment), and then the weighted value of the standardized detection data at each time node is added to the weighted value of the key data segment to obtain the fusion value of the time node. The fusion values of all time nodes are arranged in time sequence to form the initial fusion data set of the farm.

[0093] Further, the fusion values of each time node in the initial fusion data set are checked one by one. If the fusion value of a time node is more than the normal fluctuation range from the fusion values of the adjacent previous time node and the adjacent next time node, it is determined that there is a data conflict caused by time sequence misalignment or weight distribution deviation. For the conflict data, the original data of the standardized detection data and the key data segment corresponding to the time node are first checked to confirm whether the time alignment is accurate. If the time sequence is misaligned, the time corresponding relationship of the original data is adjusted again to calculate the fusion value. If the time sequence is correct, the basic weight or the decreasing weight corresponding to the time node is fine-tuned within the small adjustment range allowed by the weight distribution strategy to recalculate the fusion value, so that the fluctuation of the adjusted fusion value and the adjacent node value conforms to the normal range. After all data conflicts are processed, the obtained data set is the fusion data set of the farm.

[0094] Further, the historical manure water treatment database is opened, and the storage partition corresponding to the time range of the fusion data set in the database is found. If there are old data overlapping the time range of the fusion data set in the partition, the old data is first completely deleted, and then all the data in the fusion data set is sequentially written into the storage partition in time sequence. If there is no corresponding old data in the partition, the fusion data is directly written in time sequence. After writing is completed, the values and time indexes of the data stored in the database and the fusion data set are checked row by row to confirm whether they are completely consistent. After confirming that there is no error, the update of the fusion data set to the historical manure water treatment database is completed.

[0095] In summary, by screening key data segments associated with standardized testing data time periods, irrelevant historical data can be eliminated, ensuring strong correlation among the data participating in the fusion and avoiding interference from redundant information, thus laying the foundation for fusion quality. Secondly, weighted fusion after time-series alignment allows for the combination of more real-time standardized testing data with valuable historical data according to a preset importance ratio. This highlights the guiding significance of real-time data for the current operating conditions while fully leveraging the experiential value of historical data, making the initial fused data more closely aligned with actual processing needs.

[0096] In summary, eliminating data conflicts caused by temporal misalignment and weighting bias can correct errors in the fusion process, further improving the accuracy and reliability of the fused dataset. Finally, updating the fused dataset to the historical database provides higher-quality historical data support for subsequent processing, forming a data optimization loop. Ultimately, this provides a precise data foundation for convertible organic matter equivalent assessment and energy conversion potential analysis, ensuring the accuracy of subsequent analytical steps.

[0097] S4. Evaluate the convertible organic matter equivalent in the farm based on the fused dataset, and evaluate the energy potential of the farm based on the convertible organic matter equivalent to obtain the energy conversion potential index of the farm.

[0098] In this embodiment of the invention, the step of evaluating the convertible organic equivalent in the farm based on the fused dataset includes:

[0099] Organic matter concentration data sequences and corresponding environmental parameter sequences are separated from the fused dataset to obtain the organic matter transformation analysis dataset of the farm.

[0100] The organic matter conversion analysis dataset is matched and queried with the pre-established organic matter degradation characteristic library to obtain the baseline degradation rate of the farm under the current environmental conditions;

[0101] By introducing the microbial activity indicator parameters monitored in real time at the farm, the baseline degradation rate is dynamically corrected to obtain the effective degradation rate of the farm.

[0102] Based on the manure flow data and the effective degradation rate, the convertible organic matter equivalent in the farm is determined.

[0103] In this embodiment of the invention, the step of assessing the energy potential of the farm based on the convertible organic matter equivalent to obtain the energy conversion potential index of the farm includes:

[0104] Based on the convertible organic matter equivalent and the gas production characteristic parameters of the microorganisms in the farm, the basic energy output data of the farm is determined;

[0105] introducing a device operation efficiency factor and an environmental heat loss coefficient to correct the basic energy output data, the net available energy output of the farm;

[0106] converting the net available energy output into standard coal equivalent and equivalent electric energy equivalent to obtain a standardized energy output index of the farm;

[0107] quantifying the standardized energy output index into an economic value evaluation result in combination with current energy market price parameters;

[0108] mapping the standardized energy output index and the economic value evaluation result into an energy conversion potential index of the farm.

[0109] In the embodiment of the present application, the calculation formula of the energy conversion potential index is as follows:

[0110] ;

[0111] In the formula, is the energy conversion potential index, is a technical value dimension weight coefficient, is a quantitative value of the standardized energy output index, is a quantitative value of the economic value evaluation result, is an economic value dimension weight coefficient, is a natural logarithm function, is a hyperbolic tangent function.

[0112] Specifically, first, the identification information of each data in the fusion data set is viewed, the field data labeled as "organic matter concentration" and the field data labeled as environmental parameters (such as temperature, pH value, and dissolved oxygen content) are identified, all "organic matter concentration" field data are extracted in chronological order to form a continuous organic matter concentration data sequence, and all corresponding environmental parameter field data are extracted in the same time sequence to form a continuous environmental parameter sequence, the two sequences are integrated one by one according to the time nodes to obtain an organic matter conversion analysis data set of the farm.

[0113] Further, in the pre-established organic matter degradation characteristic library, the corresponding reference degradation rate has been classified and stored according to different environmental parameter combinations (such as the combination of a specific temperature interval and a specific pH value interval), the specific values of the current environmental parameters (such as the current temperature value and the current pH value) are extracted from the organic matter conversion analysis data set, the environmental parameter combinations under each classification item in the organic matter degradation characteristic library are compared one by one, and the classification item that completely matches the current environmental parameter values is found. The degradation rate recorded under this item is the reference degradation rate of the farm under the current environmental conditions.

[0114] Further, the real-time acquisition of the microbial activity indicator parameters in the fecal water treatment system of the farm, the parameters including the microbial quantity, microbial enzyme activity and other directly observable indicators. If the real-time monitoring of the microbial quantity is more than the default microbial quantity under the corresponding environmental conditions in the organic matter degradation characteristic library, or the microbial enzyme activity is higher than the default value, the baseline degradation rate is increased by a fixed amplitude (such as the baseline degradation rate is increased by 8% for every 20% increase in microbial quantity); if the real-time microbial quantity or enzyme activity is lower than the default value, the baseline degradation rate is decreased by a fixed amplitude (such as the baseline degradation rate is decreased by 6% for every 15% decrease in microbial enzyme activity). The degradation rate obtained after the above adjustment is the effective degradation rate of the farm.

[0115] Further, the fecal water flow data (such as the hourly fecal water outflow volume) of the farm per unit time is obtained, the fecal water flow data per unit time in a continuous time period (such as 24 hours a day) is added to obtain the total fecal water volume in the time period, and the total fecal water volume is multiplied by the effective degradation rate to obtain the equivalent of the convertible organic matter in the farm in the time period.

[0116] Specifically, the gas production characteristic parameters of the microorganisms in the farm are obtained, the parameters being the volume or heat value of a specific energy form (such as biogas) that can be produced per unit of convertible organic matter equivalent, and the specific value of the convertible organic matter equivalent is multiplied by the corresponding unit output value in the gas production characteristic parameters to obtain the total energy calculated as the basic energy output data of the farm.

[0117] Further, the device operation efficiency factor and the environmental heat loss coefficient are determined. The device operation efficiency factor is the ratio of the actual output energy of the fecal water treatment energy conversion device to the theoretical output energy (such as the device can theoretically output 100 units of basic energy completely, but actually only outputs 80 units, so the efficiency factor is 0.8), and the environmental heat loss coefficient is the proportion of the energy lost due to environmental influence in the transmission or storage process (such as 2 units of energy are lost due to heat dissipation in 10 units of energy, so the heat loss coefficient is 0.2). The basic energy output data is multiplied by the device operation efficiency factor to obtain the actual output energy of the device, and the actual output energy is multiplied by (1 minus the environmental heat loss coefficient) to deduct the environmental heat loss part, and the obtained energy is the net available energy yield of the farm.

[0118] Further, the conversion basis of the standard coal equivalent and the equivalent electric energy equivalent is determined, the standard coal equivalent is based on the standard coal heat value stipulated by the state (such as a fixed heat value corresponding to per kilogram of standard coal), and the equivalent electric energy equivalent is based on the fixed efficiency of energy conversion into electric energy (such as a fixed number of electric energy that can be converted from per unit volume of biogas), the heat value of the net available energy output is divided by the fixed heat value of the standard coal to obtain the corresponding standard coal equivalent; the net available energy output (such as the volume of biogas) is multiplied by the fixed electric energy conversion efficiency to obtain the corresponding equivalent electric energy equivalent; the standard coal equivalent and the equivalent electric energy equivalent are integrated to form the standardized energy output index of the farm.

[0119] Further, the current energy market price parameters are collected, which include the unit price of standard coal and the unit price of electric energy on the market, the standard coal equivalent in the standardized energy output index is multiplied by the unit price of standard coal to calculate the economic value corresponding to the standard coal equivalent; the equivalent electric energy equivalent in the standardized energy output index is multiplied by the unit price of electric energy to calculate the economic value corresponding to the equivalent electric energy equivalent; the sum of the two economic values is the economic value evaluation result of the farm.

[0120] Further, a mapping rule is first set, which clearly defines the correspondence between the numerical range of the standardized energy output index and the energy conversion potential level, and the correspondence between the numerical range of the economic value evaluation result and the energy conversion potential level (such as when the standardized energy output index reaches a certain value and the economic value evaluation result reaches a certain value, the corresponding energy conversion potential index is A level), the specific numerical value of the standardized energy output index and the specific numerical value of the economic value evaluation result are compared, and the matching level or value is found in the mapping rule, which is the energy conversion potential index of the farm.

[0121] Specifically, As the energy conversion potential index, it is calculated by combining the technical value dimension and the economic value dimension data through the formula, and the index is the quantitative result of the energy conversion potential of the farm, which is completely consistent with the energy conversion potential index of the farm generated in the previous step. As the technical value dimension weight coefficient, it is a fixed numerical value set in advance according to the importance of technical factors (such as the advancement of equipment and the stability of standardized energy output) in the energy conversion process of the farm, and when setting, the general situation of the influence of similar farm technologies on energy conversion in the industry should be referred to to ensure that the weight can accurately reflect the contribution proportion of the technical dimension. As a quantitative value of standardized energy output indicators, it is derived from processing the standardized energy output indicators of the farm obtained in the previous steps. The standard coal equivalent and equivalent electrical energy equivalent contained in the standardized energy output indicators are converted into specific values ​​according to preset unified quantification rules (such as converting the standard coal equivalent to a fixed unit value and the equivalent electrical energy equivalent to a fixed unit value and then summing them). As a quantitative value of the economic value assessment result, it is derived directly from the specific numerical value of the economic value assessment result of the farm obtained in the previous steps. This value is the sum of economic value calculated by combining standardized energy output indicators with current energy market price parameters. As a weighting coefficient for the economic value dimension, it is a fixed value pre-set based on the importance of economic factors (such as the impact of energy market price fluctuations and the stability of economic value returns) during the energy conversion process of the farm. When setting it, the impact of economic returns on energy conversion assessments of similar farms within the industry must be referenced to ensure that the weight accurately reflects the contribution proportion of the economic dimension. (Natural logarithm function) The source of this function is a commonly used function in mathematics to handle the rate of numerical growth. Using this function in the formula is for the purpose of reasonably adjusting... right The magnitude of its influence. Hyperbolic tangent function. The origin of this term is a commonly used function in mathematics to limit the range of values. Using this function in a formula is to control... right The boundary of influence.

[0122] Furthermore, the significance of this formula lies in its ability to quantify the energy conversion potential by comprehensively considering both the technological and economic value dimensions of energy conversion in livestock farms, thereby obtaining an energy conversion potential index. Among them, the quantification value of the standardized energy output index is processed using the natural logarithm function. The characteristic of the natural logarithmic function is that when When the value is small, the function result grows faster; when... As the numerical value increases to a certain extent, the rate of increase of the function result gradually slows down. This processing can avoid... If the value is too large, it will have an excessive impact on P. The processed result is then multiplied by the weighting coefficient of the technical value dimension. This reflects the contribution of technological value to energy conversion potential; the quantitative value of the economic value assessment results is processed using a hyperbolic tangent function. The characteristic of the hyperbolic tangent function is that its result always lies between -1 and 1, regardless of... Regardless of how the value changes, after being processed by this function, it can be confined to this fixed range, effectively avoiding... When extreme values ​​occur The unreasonable interference is caused, and the processed result is multiplied by the economic value dimension weight coefficient . The contribution of the economic value dimension to the energy conversion potential is reflected. Finally, the contribution of the technical value dimension is added to the contribution of the economic value dimension, and the result is the energy conversion potential index , which realizes the comprehensive evaluation of the energy conversion potential of the farm.

[0123] Further, when the quantitative value of the standardized energy output index increases, the natural logarithm function is substituted, and the function result will increase accordingly. However, with the continuous increase of , the growth rate of the function result will gradually decrease. After being multiplied by the fixed technical value dimension weight coefficient , the contribution of this part to the energy conversion potential index will increase but slow down, so will increase with the increase of , and the growth rate will gradually decrease. When the quantitative value of the economic value evaluation result increases, the hyperbolic tangent function is substituted, and the function result will increase accordingly. When increases to a certain extent, the function result will gradually tend to 1. After being multiplied by the fixed economic value dimension weight coefficient , the contribution of this part to will increase and gradually tend to , so P will increase with the increase of , and finally tend to . When the technical value dimension weight coefficient increases, the result of will increase under the condition that S_tech is unchanged, which leads to the increase of the contribution of the technical value dimension to , so will increase with the increase of . When the economic value dimension weight coefficient increases, the result of will increase under the condition that is unchanged, which leads to the increase of the contribution of the economic value dimension to , so will increase with the increase of .

[0124] In summary, separating organic matter concentration and environmental parameter sequences from the fused dataset allows for precise targeting of core influencing factors of organic matter transformation, avoiding interference from irrelevant data and laying a precise analytical foundation for equivalent assessment. By matching the baseline degradation rate with a pre-built organic matter degradation characteristic library, the accuracy of the assessment starting point can be ensured by relying on mature characteristic data. Furthermore, the introduction of real-time microbial activity parameters to correct the baseline degradation rate allows the effective degradation rate to dynamically adapt to the real-time operating conditions of the farm, significantly improving the accuracy of degradation rate calculation.

[0125] In summary, by combining the convertible organic matter equivalent determined by the sewage flow rate with multi-dimensional data on concentration, environment, microorganisms, and flow rate, the results more closely reflect the actual conversion potential. Subsequently, based on the equivalent and microbial gas production characteristics, the basic energy output is derived. After correction by equipment efficiency factors and environmental heat loss coefficients, the net usable energy output more closely reflects the actual scenario. Converting this to standard coal and equivalent electrical energy equivalents, and quantifying the economic value by incorporating market prices, the final mapped energy conversion potential index comprehensively reflects both technical and economic value. This provides a precise decision-making basis for subsequent sewage treatment equipment control, ensuring the scientific rigor and practicality of the energy conversion analysis.

[0126] S5. Based on the deviation between the energy conversion potential index and the energy conversion threshold, generate the control parameters for the manure treatment equipment in the farm.

[0127] In this embodiment of the invention, generating the control parameters for the manure treatment equipment in the farm based on the deviation between the energy conversion potential index and the energy conversion threshold includes:

[0128] The energy conversion potential index is compared and analyzed with the energy conversion threshold to determine the positive or negative direction and magnitude of the deviation between the energy conversion potential index and the energy conversion threshold.

[0129] Based on the positive or negative direction of the deviation, the basic adjustment direction corresponding to the energy conversion potential index is matched from the preset control strategy library;

[0130] Based on the magnitude of the deviation, the intensity of regulation is determined according to the basic adjustment direction, thus obtaining a preliminary set of regulation parameters for the farm.

[0131] By introducing real-time operating data of the manure treatment equipment in the farm, the initial set of control parameters is adjusted to obtain the control parameters of the manure treatment equipment in the farm.

[0132] In this embodiment of the invention, the step of introducing real-time operating status data of the manure treatment equipment in the farm and adaptively adjusting the preliminary set of control parameters to obtain the control parameters of the manure treatment equipment in the farm includes:

[0133] Real-time acquisition of key operating state parameters of the manure treatment equipment;

[0134] Comparative analysis of the key operating state parameters and the rated operating parameters of the manure treatment equipment to obtain the equipment operating state evaluation result of the manure treatment equipment;

[0135] Matching the parameter adjustment factor corresponding to the equipment operating state evaluation result from the equipment adaptability rule base;

[0136] Synergistically modifying the stirring frequency set value, temperature control target value and medicament dosage in the preliminary control parameter set by the parameter adjustment factor;

[0137] Logical consistency verification of the synergistically modified preliminary control parameters to obtain the control parameters of the manure treatment equipment in the farm.

[0138] Specifically, a preset energy conversion threshold is first obtained, which is a fixed value preset according to the reasonable level of energy conversion of similar farms in the industry. The deviation amount is obtained by subtracting the energy conversion threshold from the specific value of the energy conversion potential index. If the deviation amount result is greater than 0, it is determined that the positive and negative direction of the deviation amount is positive. If the deviation amount result is less than 0, it is determined that the positive and negative direction of the deviation amount is negative. If the deviation amount result is equal to 0, the positive and negative direction is zero. At the same time, the division interval of the size level of the deviation amount is preset (such as the absolute value of the deviation amount between 0 and 10 is first level, 10 to 20 is second level, and above 20 is third level). The size level of the deviation amount is determined by comparing the interval into which the absolute value of the deviation amount falls.

[0139] Further, the preset control strategy library has stored corresponding basic adjustment directions classified by the positive and negative directions of the deviation amount. The basic adjustment direction corresponding to the positive direction deviation is to maintain the current energy conversion related operation or to make a small optimization. The basic adjustment direction corresponding to the negative direction deviation is to enhance the energy conversion related control intensity. The basic adjustment direction corresponding to the zero direction deviation is to keep the current operation unchanged. According to the positive and negative direction of the deviation amount determined in the first step, the corresponding adjustment direction is found and extracted in the preset control strategy library. The extracted adjustment direction is the basic adjustment direction corresponding to the energy conversion potential index.

[0140] Further, a preset control intensity standard corresponding to each deviation level is set (for example, a first-level deviation corresponds to a weak control intensity, a second-level deviation corresponds to a medium control intensity, and a third-level deviation corresponds to a strong control intensity), and the corresponding control intensity is extracted according to the deviation level determined in the first step; the control intensity is combined with the basic adjustment direction obtained in the second step, for example, when the basic adjustment direction is to strengthen the control intensity and the deviation level is second level, the control intensity is determined to be medium, and the specific control content (such as the amplitude of adjusting the amount of microorganisms added or the change range of the equipment operating power) is determined, and the specific control content is integrated to obtain the preliminary control parameter set of the farm.

[0141] Further, the operating state data of the fecal water treatment equipment in the farm is collected in real time, including the current operating temperature, operating pressure, motor speed, fault record and other information of the equipment; each parameter in the preliminary control parameter set is checked one by one, if a control parameter requires to increase the equipment speed, but the real-time data shows that the current temperature of the equipment is close to the warning value, then the increase amplitude of the speed in the control parameter is appropriately reduced, if a control parameter requires to increase the amount of microorganisms added, and the real-time data shows that the activity of the microorganisms in the equipment is within the normal range, then the parameter or the amount of microorganisms added is retained, and after all the parameters are checked and adjusted, the obtained parameter set is the control parameter of the fecal water treatment equipment in the farm.

[0142] Specifically, through the sensors (such as temperature sensors, current sensors, and flow sensors) installed at the key positions of the fecal water treatment equipment, the operating temperature, the stirring motor working current, the reagent dosing pump output flow, and the internal pressure of the equipment during the operation of the equipment are read in real time, and the specific values of these parameters are recorded every fixed time (such as 1 minute), so that the collected parameters can reflect the current operation of the equipment in real time, and finally the real-time key operating state parameters are obtained.

[0143] Further, the rated operating parameters of the equipment are obtained from the factory technical documents of the fecal water treatment equipment, which include the rated temperature range, the rated stirring motor current value, the rated reagent dosing flow range, and the rated working pressure interval of the equipment during normal operation, and the fixed standard values are compared with each value in the real-time collected key operating state parameters, if all the values of the key operating state parameters are within the corresponding rated operating parameter range, then the equipment operating state evaluation result is normal operation; if a value of a key operating state parameter exceeds or is lower than the corresponding rated operating parameter range (such as the operating temperature is higher than the upper limit of the rated temperature or the stirring motor current is lower than the lower limit of the rated current), then the parameter category and the specific deviation are marked in the evaluation result, and finally the equipment operating state evaluation result of the fecal water treatment equipment is obtained.

[0144] Further, the device adaptability rule base has pre-stored parameter adjustment factors corresponding to different types of device running state evaluation results (for example, when the evaluation result is that the operating temperature is higher than the upper limit of the rated value, the corresponding parameter adjustment factor is to lower the temperature control target value by 2°C and reduce the stirring frequency by 5%; when the evaluation result is that the stirring motor current is lower than the lower limit of the rated value, the corresponding parameter adjustment factor is to increase the stirring frequency by 8% and increase the medicament dosage by 3%). According to the specific type of the device running state evaluation result obtained in the second step, the entry that completely matches the device running state evaluation result is found in the device adaptability rule base, and all parameter adjustment factors recorded in the entry are extracted to obtain the parameter adjustment factors corresponding to the current device running state evaluation result.

[0145] Further, the extracted parameter adjustment factors are applied to the stirring frequency set value, the temperature control target value and the medicament dosage in the preliminary control parameter set respectively, and the values of these parameters are modified according to the requirements of the adjustment factors (for example, if the adjustment factor is to reduce the stirring frequency by 5%, the modified stirring frequency is obtained by multiplying the stirring frequency set value in the preliminary control parameter set by 95%; if the adjustment factor is to lower the temperature control target value by 2°C, the modified temperature control target value is obtained by subtracting 2°C from the temperature control target value in the preliminary control parameter set). After the collaborative correction is completed, it is checked whether there is a logical contradiction among the modified stirring frequency set value, the temperature control target value and the medicament dosage (for example, if the modified temperature control target value is too low to cause the medicament reaction efficiency to decrease, and the modified medicament dosage is increased, at this time, the parameters need to be fine-tuned again to eliminate the contradiction), so as to ensure that all parameters are logically matched and meet the device running logic. The parameter set after the logical consistency verification is the control parameter of the fecal water treatment device in the farm.

[0146] In summary, by comparing the energy conversion potential index with the threshold value, the positive or negative direction and the size level of the deviation are determined, the gap between the current energy conversion state and the target is accurately positioned, and it is determined whether the threshold value needs to be improved or the threshold value needs to be optimized, and the degree of the gap is quantified to avoid the problems of blind adjustment direction and fuzzy adjustment intensity.

[0147] In summary, by matching the basic adjustment direction according to the deviation direction and determining the adjustment intensity according to the deviation size, the preliminary control parameters can not only meet the core needs of “complementing the short board” or “improving the efficiency”, but also avoid excessive or insufficient adjustment, so as to ensure the pertinence and appropriateness of the adjustment.

[0148] In summary, the preliminary parameters are corrected by introducing the real-time device running state data, so that the control parameters can adapt to the actual working conditions of the device, and the risk of low efficiency or failure caused by the disconnection between the parameters and the device capacity is avoided. The subsequent logical consistency verification can also ensure that the parameters such as stirring frequency and temperature control target value are coordinated without conflict, so that the finally generated control parameters are accurate and feasible, which can effectively guide the device running and ensure the stable improvement of the fecal water treatment efficiency and the energy conversion effect.

[0149] As Figure 2 shown is a functional module diagram of an intelligent farm waste treatment and energy conversion system provided by an embodiment of the present application.

[0150] The intelligent farm waste treatment and energy conversion system 100 can be installed in an electronic device. According to the functions to be implemented, the intelligent farm waste treatment and energy conversion system 100 can include a data processing module 101, a weight distribution module 102, a time series fusion module 103, an energy conversion potential index generation module 104, and a regulation parameter conversion module 105. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0151] In the present embodiment, the functions of each module / unit are as follows:

[0152] The data processing module 101 is configured to normalize the manure water detection data of the farm to obtain standardized detection data of the manure water detection data.

[0153] The weight distribution module 102 is configured to distribute weights to the standardized detection data and historical manure treatment data in a sliding window.

[0154] The time series fusion module 103 is configured to perform time series fusion on the standardized detection data and the historical manure treatment data according to the weight distribution result to obtain a fusion data set of the farm.

[0155] The energy conversion potential index generation module 104 is configured to evaluate the equivalent organic matter that can be converted in the farm according to the fusion data set, and perform energy potential evaluation on the farm according to the equivalent organic matter that can be converted to obtain an energy conversion potential index of the farm.

[0156] The regulation parameter conversion module 105 is configured to generate a regulation parameter of a manure treatment device in the farm based on a deviation amount of the energy conversion potential index and an energy conversion threshold value.

[0157] In several embodiments provided by the present application, it should be understood that the disclosed method and system can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical functional division, and other division methods can be used in actual implementation.

[0158] The modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0159] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0160] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0161] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence is to use digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, obtain knowledge and use knowledge to obtain the best results.

[0162] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for intelligentized farm waste treatment and energy conversion, characterized in that, The method comprises: S1, normalizing the manure detection data of the farm to obtain standardized detection data of the manure detection data; S2, weight distribution of the standardized detection data and historical manure treatment data in the sliding window; S3, time series fusion of the standardized detection data and the historical manure treatment data according to the weight distribution result, to obtain the fusion data set of the farm; S4, according to the fusion data set, the equivalent of the convertible organic matter in the farm is evaluated, and the energy potential of the farm is evaluated according to the equivalent of the convertible organic matter, to obtain the energy conversion potential index of the farm, including: Separate the organic matter concentration data sequence and the corresponding environmental parameter sequence from the fusion data set to obtain the organic matter conversion analysis data set of the farm; Match and query the organic matter conversion analysis data set with the pre-established organic matter degradation characteristic library to obtain the baseline degradation rate of the farm under the current environmental conditions; Introduce the real-time monitoring of the microbial activity indicating parameter of the farm to dynamically correct the baseline degradation rate to obtain the effective degradation rate of the farm; Based on the manure flow data and the effective degradation rate, the equivalent of the convertible organic matter in the farm is determined; Based on the equivalent of the convertible organic matter and the gas production characteristic parameters of the microorganisms in the farm, the basic energy output data of the farm is determined; Introduce the equipment operation efficiency factor and the environmental heat loss coefficient to correct the basic energy output data, and the net available energy output of the farm; Convert the net available energy output into standard coal equivalent and equivalent electric energy equivalent to obtain the standardized energy output index of the farm; Combine the current energy market price parameters to quantify the standardized energy output index into economic value evaluation results; Map the standardized energy output index and the economic value evaluation results to the energy conversion potential index of the farm, wherein the calculation formula of the energy conversion potential index is as follows ； In the formula, is the energy conversion potential index, is the technical value dimension weight coefficient, is the quantitative value of the standardized energy output index, is the quantitative value of the economic value evaluation result, is the economic value dimension weight coefficient, is a natural logarithm function, is a hyperbolic tangent function; S5, based on the deviation amount of the energy conversion potential index and the energy conversion threshold value, the regulation parameters of the manure treatment equipment in the farm are generated.

2. The intelligent farm waste treatment and energy conversion method of claim 1, wherein, The normalization of the manure detection data of the farm to obtain the standardized detection data of the manure detection data comprises: Remove the data points with missing and format errors of multiple monitoring parameters in the manure detection data to obtain the preliminary effective data set of the manure detection data; Remove the values deviating from the normal mode in the preliminary effective data set based on the pre-defined data distribution range to obtain the purified data set of the manure detection data; Adjust the value range of the monitoring parameters in the purified data set to obtain the standardized detection data of the manure detection data.

3. The intelligent farm waste treatment and energy conversion method of claim 1, wherein, The weight distribution of the standardized detection data and historical manure treatment data in the sliding window comprises: According to the time span of the sliding window, the historical manure treatment data is divided into window historical data segments; Set a preset timeliness priority strategy, assign a basic weight to the standardized detection data, and assign a decreasing weight to the historical data segment in the window; According to the recent operation stability index of the fecal water treatment equipment, the relative proportion of the basic weight and the decreasing weight is dynamically adjusted to generate a weight distribution strategy of the farm.

4. The intelligent farm waste treatment and energy conversion method of claim 3, wherein, According to the weight distribution result, the standardized detection data and the historical fecal water treatment data are time series fused to obtain a fusion data set of the farm, which includes: From the historical fecal water treatment data, the key data segment associated with the strategy standardized detection data period is screened out; According to the weight distribution strategy, the standardized detection data and the key data segment are time series fused to obtain an initial fusion data set of the farm; Eliminate the data conflicts in the initial fusion data set caused by time sequence misalignment and weight distribution deviation to obtain a fusion data set of the farm; Update the fusion data set to the historical fecal water treatment database.

5. The intelligent farm waste treatment and energy conversion method of claim 1, wherein, Based on the deviation amount of the energy conversion potential index and the energy conversion threshold, the control parameters of the fecal water treatment equipment in the farm are generated, which includes: Compare and analyze the energy conversion potential index and the energy conversion threshold to determine the positive or negative direction and size level of the deviation amount between the energy conversion potential index and the energy conversion threshold; According to the positive or negative direction of the deviation amount, the basic adjustment direction corresponding to the energy conversion potential index is matched from the preset control strategy library; Combined with the size level of the deviation amount, the control strength is determined based on the basic adjustment direction to obtain a preliminary control parameter set of the farm; Introduce the real-time data of the operating state of the fecal water treatment equipment in the farm to adaptively adjust the preliminary control parameter set to obtain the control parameters of the fecal water treatment equipment in the farm.

6. The intelligent farm waste treatment and energy conversion method of claim 5, wherein, Introducing the real-time data of the operating state of the fecal water treatment equipment in the farm to adaptively adjust the preliminary control parameter set to obtain the control parameters of the fecal water treatment equipment in the farm, which includes: Real-time acquisition of key operating state parameters of the fecal water treatment equipment; Compare and analyze the key operating state parameters with the rated operating parameters of the fecal water treatment equipment to obtain the equipment operating state evaluation result of the fecal water treatment equipment; Match the parameter adjustment factor corresponding to the equipment operating state evaluation result from the equipment adaptability rule library; The parameter adjustment factor is used to cooperatively correct the stirring frequency set value, temperature control target value and reagent dosage in the preliminary control parameter set; Logical consistency verification is performed on the cooperatively corrected preliminary control parameters to obtain the control parameters of the fecal water treatment equipment in the farm.

7. An intelligent farm waste treatment and energy conversion system for implementing the intelligent farm waste treatment and energy conversion method of claim 1, the system comprising: A data processing module for normalizing the fecal water detection data of the farm to obtain standardized detection data of the fecal water detection data; a weight distribution module configured to distribute weights to the standardized detection data and the historical fecal water treatment data in a sliding window; a time series fusion module configured to perform time series fusion on the standardized detection data and the historical fecal water treatment data according to a result of the weight distribution to obtain a fusion data set of the farm; an energy conversion potential index generation module configured to evaluate an equivalent amount of convertible organic matter in the farm according to the fusion data set, and perform energy potential evaluation on the farm according to the equivalent amount of convertible organic matter to obtain an energy conversion potential index of the farm; a regulation parameter conversion module configured to generate a regulation parameter of a fecal water treatment device in the farm based on a deviation amount of the energy conversion potential index and an energy conversion threshold value.

Images