Multi-parameter collaborative calculation method for water treatment process design

Abstract

This invention discloses a multi-parameter collaborative calculation method for water treatment process design, belonging to the field of water treatment computing technology. It addresses the problems of wasted computing resources and increased sensor energy consumption. The method constructs a set of water quality parameters based on wastewater treatment plant monitoring projects, and filters parameters to be measured by combining discharge time characteristics. It statistically analyzes the frequency of collaborative participation of each parameter based on historical data and quantifies their proportion. Through parameter elimination and reenactment analysis of historical exceedance processes, it obtains the number of exceedance triggers and calculates the water quality impact, generating a sensor shutdown command. After shutdown, a feedback verification mechanism is introduced to compare the collaborative calculation results of the complete and trimmed parameter sets, constructing a trimming credibility. The treatment load is assessed by combining influent flow rate and treatment capacity, and then fused with the trimming credibility to generate an operational credibility state. The feedback duration is adjusted based on this state to achieve a dynamic balance between detection frequency and system load, reducing energy consumption and equipment wear while improving operational efficiency and stability.

Description

Technical Field

[0001] This invention relates to the field of water treatment computation technology, and more specifically, to a multi-parameter collaborative calculation method for water treatment process design. Background Technology

[0002] In industrial park wastewater treatment scenarios, due to the diverse types of enterprises, the effluent from different production lines exhibits distinct phased and intermittent characteristics. For example, in the food processing and light industrial stages, organic pollutants dominate the wastewater, while the content of inorganic pollutants such as heavy metals is extremely low or even close to zero; however, in the electroplating and chemical production stages, heavy metal indicators become the key monitoring targets. This results in significant dynamic changes in wastewater quality over time.

[0003] The existing technology has the following shortcomings: Currently, when some water quality parameters remain stable or have low variation during specific discharge stages, existing technologies still perform high-frequency acquisition and calculation on these low-variance or invalid parameters. This lacks a mechanism for identifying the importance of parameters and for dynamic control based on historical operating data, leading to wasted computing resources, increased sensor energy consumption, and shortened equipment lifespan. Consequently, it is difficult to achieve an optimal balance between detection efficiency and system operating load. Therefore, a multi-parameter collaborative calculation method for water treatment process design is proposed.

[0004] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a multi-parameter collaborative calculation method for water treatment process design. This method addresses the problems mentioned in the background art by employing a parameter importance assessment mechanism based on historical collaborative participation analysis, a water quality impact degree calculation mechanism combined with exceedance triggering behavior, a sensor dynamic start-stop control mechanism for low-value parameters, and the introduction of feedback verification and adaptive adjustment mechanism for operating status.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a multi-parameter collaborative calculation method for water treatment process design, comprising the following steps: Step S1: Obtain water quality testing items through the wastewater treatment platform and construct a water quality parameter set. Retrieve discharge time information to mark the water quality parameters in the water quality parameter set to obtain the water quality parameters to be tested. Count the number of historical collaborative participations for the water quality parameters to be tested. Step S2: Calculate the proportion of collaborative participation based on the historical number of collaborative participations and perform out-of-standard detection and processing. Detect the number of out-of-standard triggers based on the processing results, calculate the impact of the water quality to be tested based on the proportion of collaborative participation, and generate a sensor shutdown command based on the impact of the water quality to be tested. Step S3: After executing the sensor shutdown command, set the feedback time. After the feedback time ends, enter the verification mechanism. In the verification mechanism, restart the sensor, collect the complete parameter set and the clipped parameter set, and perform collaborative computing processing. Step S4: Generate the trimming confidence level based on the collaborative computing processing results, collect the current influent flow rate and default treatment flow rate and evaluate the treatment load value, analyze the operational confidence status in combination with the trimming confidence level, and determine whether to adjust the feedback duration based on the operational confidence status.

[0007] In a preferred embodiment, in step S1, all water quality testing items configured in the wastewater treatment system are obtained through the wastewater treatment platform. A wastewater treatment platform refers to a software system used for unified access, data collection, and scheduling control of various operating equipment and monitoring devices in wastewater treatment plants; A wastewater treatment system refers to a process operation system composed of various treatment units, through which pollutants are physically, chemically, and biologically degraded. Water quality testing items include monitoring indicators of water quality parameters obtained periodically by corresponding sensors; Based on water quality testing projects, a set of water quality parameters is constructed. The values ​​of the water quality parameters are the time average values ​​output by the corresponding sensors within a preset sampling time interval.

[0008] In a preferred embodiment, in step S1, discharge time information is retrieved from the historical operation database of the wastewater treatment plant. The discharge time information is a set of discharge intervals for different types of wastewater on the time axis. Based on the matching of the current time with the emission time information, the current emission stage type is determined; Extract the historical water quality data sequence corresponding to the current emission stage type, and calculate the fluctuation range index for each water quality parameter on the historical water quality data sequence, which is defined as the range value; Calculate the mean of the historical water quality data series and construct the normalized fluctuation coefficient; A unified fluctuation judgment threshold is pre-set. When the normalized fluctuation coefficient is greater than or equal to the fluctuation judgment threshold, the water quality parameter is judged to have effective change characteristics in the current discharge stage; otherwise, the water quality parameter is judged to have limited change range in the current discharge stage. Screen and label water quality parameters that exhibit effective change characteristics during the current emission phase; For each water quality parameter to be measured, the number of times it participated in historical collaborative calculations is counted to obtain the historical collaborative participation count.

[0009] In a preferred embodiment, in step S2, based on the set of water quality parameters to be tested and their corresponding historical collaborative participation times, the total number of collaborative calculations recorded in the historical operation database is accessed; The total number of collaborative calculations represents the total number of times the water quality assessment model calculations are performed within a preset statistical period; A water quality assessment model is a computational model used to comprehensively analyze multiple water quality parameters and output water quality status judgment results, including two evaluation results: exceeding the standard and not exceeding the standard. Based on the total number of collaborative calculations, the proportion of collaborative participation for each water quality parameter to be measured is calculated and defined as the ratio of the historical number of collaborative participations to the total number of collaborative calculations. Obtain the out-of-standard calculation records from the historical operation database and construct an out-of-standard sample set; For each water quality parameter to be tested, parameter removal detection is performed in the set of samples that exceed the standard, and a set of trimmed parameters is constructed after removing the parameters.

[0010] In a preferred embodiment, in step S2, the set of trimmed parameters is input into the water quality evaluation model for recalculation to obtain the trimmed evaluation results; The number of samples that meet the criteria of exceeding the standard in the original evaluation but not exceeding the standard after pruning is defined as the number of exceedance triggers; Introducing the influence of the water quality to be tested, defined as follows: ,in, The degree of influence of the water quality to be tested. This is due to exceeding the limit on the number of triggers. To determine the proportion of collaborative participation, This represents the total number of times all tested water quality parameters exceeded the standard. To prevent tiny positive numbers with a denominator of zero; A preset impact threshold is set. When the impact of the water quality being tested is less than the impact threshold, a sensor shutdown command is generated; otherwise, the sensor remains on.

[0011] In a preferred embodiment, in step S3, after executing the sensor shutdown command, a preset feedback time is set, and the verification mechanism is entered after the feedback time ends. In the verification mechanism, the sensor is restarted to collect a set of water quality parameters, and the set of water quality parameters is used as the complete set of parameters. The set of parameters is obtained by removing the water quality parameters corresponding to the sensor being turned off from the complete parameter set.

[0012] In a preferred embodiment, in step S3, each water quality parameter in the complete parameter set is selected and combined into a complete parameter input vector; each water quality parameter in the trimmed parameter set is selected and combined into a trimmed parameter input vector. Input the complete parameter input vector into the water quality assessment model and use the output result as the complete calculation result; Input the clipping parameter input vector into the water quality assessment model, and use the output result as the clipping calculation result.

[0013] In a preferred embodiment, in step S4, the complete calculation results and the clipping calculation results are retrieved and standardized to obtain the complete calculation factor and the clipping calculation factor. The difference is obtained by subtracting the full calculation factor and the trimmed calculation factor and taking the absolute value. The maximum value between the full calculation factor and the trimmed calculation factor is taken as the difference normalization benchmark value. Divide the variance by the normalized variance benchmark to obtain the normalized variance ratio, and calculate the clipping confidence level based on the normalized variance ratio. The current influent flow rate is collected by the influent flow sensor, the default processing flow rate is retrieved from the process configuration table, and the ratio of the current influent flow rate to the default processing flow rate is calculated to obtain the processing load value.

[0014] In a preferred embodiment, in step S4, the operational reliability index is calculated by comprehensively processing the load value and the pruning reliability. The operational trust index is compared with a preset operational trust threshold to analyze the operational trust status. If the running trust index is greater than the preset running trust threshold, the running trust status is determined to be a high trust running status; Conversely, if the operating trust status is not met, the operating trust status is determined to be a low trust operating state; When the operational trust status is high trust status, the feedback duration is adjusted, and the adjusted feedback duration is calculated using the operational trust index and the preset operational trust threshold.

[0015] The technical effects and advantages of this invention are as follows: This invention constructs a set of water quality parameters based on wastewater treatment plant monitoring projects, and selects the water quality parameters to be tested based on discharge time characteristics. Simultaneously, it statistically analyzes the participation frequency of each parameter in collaborative calculations based on historical operational data, quantifying its collaborative participation ratio. Secondly, by performing parameter elimination and reenactment analysis on historical exceedance calculation processes, an exceedance trigger frequency index is constructed, and this index is fused with the collaborative participation ratio to calculate the water quality impact, thereby generating a sensor shutdown command. Subsequently, after executing the sensor shutdown, a feedback verification mechanism is introduced to compare the collaborative calculation results of the complete parameter set and the tailored parameter set, constructing a tailoring credibility index. Finally, the treatment load value is calculated by combining real-time influent flow and design treatment capacity, and this value is fused with the tailoring credibility to generate an operational credibility state. The feedback duration is adjusted according to the operational state to achieve a dynamic balance between detection frequency and system load, thereby reducing energy consumption and equipment wear, and improving overall operational efficiency and stability. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating the implementation of the multi-parameter collaborative calculation method for the water treatment process design of this invention.

[0017] Figure 2 This is a schematic diagram illustrating the steps of the multi-parameter collaborative calculation method for the water treatment process design of this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] This invention constructs a set of water quality parameters based on wastewater treatment plant monitoring projects, and selects the water quality parameters to be tested based on discharge time characteristics. Simultaneously, it statistically analyzes the participation frequency of each parameter in collaborative calculations based on historical operational data, quantifying its collaborative participation ratio. Secondly, by performing parameter elimination and reenactment analysis on historical exceedance calculation processes, an exceedance trigger frequency index is constructed, and this index is fused with the collaborative participation ratio to calculate the water quality impact, thereby generating a sensor shutdown command. Subsequently, after executing the sensor shutdown, a feedback verification mechanism is introduced to compare the collaborative calculation results of the complete parameter set and the tailored parameter set, constructing a tailoring credibility index. Finally, the treatment load value is calculated by combining real-time influent flow and design treatment capacity, and this value is fused with the tailoring credibility to generate an operational credibility state. The feedback duration is adjusted according to the operational state to achieve a dynamic balance between detection frequency and system load, thereby reducing energy consumption and equipment wear.

[0020] Example 1, as Figures 1 to 2As shown, the multi-parameter collaborative calculation method for water treatment process design includes the following steps: Step S1: Obtain water quality testing items through the wastewater treatment platform and construct a water quality parameter set. Retrieve discharge time information to mark the water quality parameters in the water quality parameter set to obtain the water quality parameters to be tested. Count the number of historical collaborative participations for the water quality parameters to be tested. Step S2: Calculate the proportion of collaborative participation based on the historical number of collaborative participations and perform out-of-standard detection and processing. Detect the number of out-of-standard triggers based on the processing results, calculate the impact of the water quality to be tested based on the proportion of collaborative participation, and generate a sensor shutdown command based on the impact of the water quality to be tested. Step S3: After executing the sensor shutdown command, set the feedback time. After the feedback time ends, enter the verification mechanism. In the verification mechanism, restart the sensor, collect the complete parameter set and the clipped parameter set, and perform collaborative computing processing. Step S4: Generate the trimming confidence level based on the collaborative computing processing results, collect the current influent flow rate and default treatment flow rate and evaluate the treatment load value, analyze the operational confidence status in combination with the trimming confidence level, and determine whether to adjust the feedback duration based on the operational confidence status.

[0021] The specific implementation is as follows: In step S1, all water quality testing items configured in the wastewater treatment system are obtained through the wastewater treatment platform. These water quality testing items include monitoring indicators of water quality parameters such as chemical oxygen demand (COD), ammonia nitrogen concentration (NH3-N), total phosphorus (TP), pH value, turbidity, dissolved oxygen (DO), and heavy metal concentration. Each water quality testing item is periodically collected by its corresponding sensor.

[0022] It should be noted that a wastewater treatment platform refers to a software system used for unified access, data collection, and scheduling control of various operating equipment and monitoring devices in a wastewater treatment plant; a wastewater treatment system refers to a process operation system composed of various treatment units, through which pollutants are physically, chemically, and biologically degraded.

[0023] Based on water quality testing projects, a set of water quality parameters is constructed, with values ​​representing the time averages output by the corresponding sensors within a preset sampling time interval. For example, chemical oxygen demand (COD) reflects the amount of organic pollutants in the water body required for oxidation; a higher value indicates a higher content of oxidizable organic matter in the water body. Ammonia nitrogen concentration reflects the level of nitrogen-containing pollutants; a higher value indicates a higher degree of ammonia pollution. Turbidity reflects the concentration of suspended particulate matter in the water body; a higher value indicates a higher degree of turbidity.

[0024] Furthermore, the discharge time information from the wastewater treatment plant's historical operation database is retrieved. This discharge time information is a set of discharge intervals for different types of wastewater along a time axis, with each time interval corresponding to a typical water quality condition. Based on the matching of the current moment with the discharge time information, the current discharge stage type is determined, and each water quality parameter in the water quality parameter set is labeled according to the corresponding historical water quality characteristics. Specifically, the current moment is mapped to its corresponding time interval, and the historical water quality data sequence corresponding to the current discharge stage type is extracted. For each water quality parameter, its fluctuation range index is calculated on the historical water quality data sequence and defined as the range value. ; in, For volatility index, This is the maximum value in the historical water quality data series. It is the minimum value in the historical water quality data series.

[0025] It should be noted that the historical operation database refers to a structured data collection that stores all monitoring data, operation logs, and calculation records generated by the wastewater treatment system during its historical operation.

[0026] Simultaneously, the mean of the historical water quality data series is calculated, and a normalized fluctuation coefficient is further constructed: ; in, The normalized fluctuation coefficient, For volatility index, The mean of the historical water quality data series. To prevent tiny positive numbers with a denominator of zero.

[0027] The normalized fluctuation coefficient is used to characterize the relative variation of each water quality parameter during the discharge stage. The larger the value, the more drastic the fluctuation of the parameter relative to its average level.

[0028] Pre-set a uniform fluctuation judgment threshold ,when When, it is determined that the water quality parameters have effective change characteristics within the current discharge phase; when At that time, it was determined that the variation range of water quality parameters was limited during the current discharge phase.

[0029] Based on the above judgment results, construct a parameter labeling function: ; in, This indicates that water quality parameters are necessary for calculation during the current discharge phase. This indicates that the water quality parameters have not changed significantly in the current period.

[0030] It should be noted that the fluctuation judgment threshold is set based on the statistical results of the normalized fluctuation coefficients of each water quality parameter in the historical operation database. Specifically, for any water quality parameter, its normalized fluctuation coefficient sequence is calculated over the entire historical time interval, and the normalized fluctuation coefficient sequence is sorted, with its quantile value selected as the fluctuation judgment threshold.

[0031] Based on the above labeling results, a set of water quality parameters to be tested was obtained. This involves screening and labeling water quality parameters that exhibit effective change characteristics during the current emission phase.

[0032] Subsequently, the collaborative computing log data recorded in the historical operation database is accessed. This log data includes the set of parameters participating in the water quality assessment model calculation within each historical calculation cycle, along with their corresponding calculation results. For each water quality parameter to be measured, the number of times it participated in historical collaborative calculations is counted, yielding the historical collaborative participation count. This count reflects the frequency with which the water quality parameter participated in collaborative calculations throughout historical operations; a higher count indicates a higher frequency of retrieval of the parameter in multiple water quality assessments, representing its basic participation activity within the system.

[0033] It should be noted that a water quality assessment model is a computational model used to comprehensively analyze multiple water quality parameters and output a water quality status judgment result. The input is a vector of water quality parameters, and the output is the assessment result y. A value of 1 indicates that the standard is exceeded, and a value of 0 indicates that the standard is not exceeded. The water quality assessment model is constructed using a weighted summation method. ,in, Let be the weighting coefficient for the i-th water quality parameter. To correspond to the emission standard limits, To comprehensively determine the threshold, This is an indicator function. The larger the weight coefficient of each water quality parameter in the water quality assessment model, the higher the contribution of that water quality parameter to the determination of exceeding the standard, and the more significant the impact of its numerical change on the final assessment result; historical collaborative calculation refers to the process by which the water quality assessment model performs calculations based on the joint input of multiple water quality parameters during historical operation.

[0034] Through the above process, the construction, dynamic labeling, and quantitative statistics of historical collaborative participation of water quality parameters are achieved, providing a data foundation for subsequent parameter importance assessment and collaborative calculation optimization.

[0035] In step S2, based on the set of water quality parameters to be tested and their corresponding historical collaborative participation times, the total number of collaborative calculations recorded in the historical operation database is further accessed, where the total number of collaborative calculations represents the total number of times the water quality evaluation model calculation is performed within a preset statistical period.

[0036] Based on the total number of collaborative calculations, the collaborative participation ratio of each water quality parameter to be measured is calculated and defined as the ratio of the historical collaborative participation number to the total number of collaborative calculations. The range of the collaborative participation ratio is [0,1], which is used to characterize the frequency of water quality parameters being called in all historical collaborative calculations. The larger the value, the higher the proportion of water quality parameters participating in the calculation in the historical evaluation process, reflecting the stronger their basic participation.

[0037] Furthermore, exceedance calculation records from the historical operational database are obtained, and an exceedance sample set is constructed, denoted as... ,in, This represents the set of water quality parameters used in the k-th historical collaborative computation. This corresponds to the output of the water quality assessment model. This indicates that the calculation result exceeded the limit.

[0038] For each water quality parameter to be tested, a parameter removal detection process is performed in the set of samples that exceed the standard. The specific process is as follows: for each sample that meets the standard... Based on historical calculation samples, construct a set of pruning parameters after removing parameters.

[0039] The trimmed parameter set is input into the water quality assessment model for recalculation, yielding the trimmed assessment results. Based on this, the number of samples that meet the criteria of exceeding the standard in the original result and not exceeding the standard in the trimmed result is counted and defined as the number of exceedance triggers.

[0040] The number of exceedance triggers represents the number of times that various water quality parameters have triggered exceedance judgments in historical exceedance events. The larger the value, the stronger the decisive influence of the water quality parameter on the exceedance result.

[0041] To comprehensively reflect the participation frequency and triggering capability of parameters, the influence degree of the water quality under test is introduced, defined as follows: ,in, The degree of influence of the water quality to be tested. This is due to exceeding the limit on the number of triggers. To determine the proportion of collaborative participation, This represents the total number of times all tested water quality parameters exceeded the standard. To prevent tiny positive numbers with a denominator of zero.

[0042] The water quality impact degree is used to characterize the comprehensive effect of parameters in the collaborative computing system. The larger the value, the higher the participation frequency of the water quality parameter and the higher the triggering ability in the determination of exceeding the standard.

[0043] Based on the impact of the water quality to be tested, a preset impact judgment threshold is established. ,when When the contribution of the corresponding water quality parameter to the collaborative calculation result is determined to be lower than the threshold requirement, a sensor shutdown command is generated; when If it is determined that the water quality parameters are necessary to retain the collaborative calculation results, the sensor should remain on.

[0044] It should be noted that the sensor shutdown command is a control command generated by the wastewater treatment platform based on the calculated impact of the water quality to be measured and sent to the corresponding online monitoring equipment. This command is used to stop the real-time acquisition, data upload, and analysis of specified water quality parameters within a preset time interval. The impact threshold is adaptively set based on the statistical distribution of the impact set of the water quality parameters to be measured. Specifically, the impact of all water quality parameters to be measured is first normalized and sorted to obtain an ordered sequence from smallest to largest. Preset quantiles are then selected, and the corresponding quantile values ​​are used as the impact threshold.

[0045] Through the above calculation process, the degree of influence on each water quality parameter is quantitatively assessed, and a sensor shutdown command is generated based on the quantitative results, thereby reducing the continuous collection and calculation load of low-contribution water quality parameters.

[0046] In step S3, after the sensor shut-off command is executed, the preset feedback duration is used to limit the duration of the sensor shut-off command corresponding to the water quality parameter to be measured; It should be noted that the preset feedback duration can be set based on historical stable operating cycles.

[0047] After the feedback period ends, a verification mechanism is initiated to further validate the effectiveness of the current parameter pruning strategy. In the verification mechanism, the sensor is restarted to collect a set of water quality parameters, which is derived from the set of water quality parameters constructed in step S1. The set of water quality parameters is used as the complete set of parameters. In the complete parameter set, the water quality parameters corresponding to the sensor being turned off are removed to obtain the trimmed parameter set; Select each water quality parameter from the complete parameter set and combine them into a complete parameter input vector; select each water quality parameter from the trimmed parameter set and combine them into a trimmed parameter input vector. Collaborative computation processing is performed based on the complete parameter input vector and the pruned parameter input vector. Specifically, the complete parameter input vector is input into the water quality assessment model in step S1, and the output result is used as the complete computation result. Input the clipping parameter input vector into the water quality assessment model, and use the output result as the clipping calculation result.

[0048] In step S4, the complete calculation results and the clipping calculation results are retrieved and standardized to obtain the complete calculation factor and the clipping calculation factor. The difference is obtained by subtracting the full calculation factor and the trimmed calculation factor and taking the absolute value. The maximum value between the full calculation factor and the trimmed calculation factor is taken as the difference normalization benchmark value. Dividing the variance by the normalized variance baseline yields the normalized variance ratio. The clipping confidence level is then calculated based on the normalized variance ratio. ,in, To normalize the proportion of differences, To improve credibility; A pruning confidence level close to 1 indicates a higher consistency between the calculation results of the pruned parameter set and the complete parameter set, suggesting that parameter pruning has a smaller impact on the collaborative calculation results. The current influent flow rate is collected by the influent flow sensor. The current influent flow rate is the volume of influent entering the sewage treatment system per unit time. Retrieve the default treatment flow rate from the process configuration table. The default treatment flow rate is the influent flow rate benchmark of the wastewater treatment system under stable operating conditions. The current inflow rate is compared with the default treatment flow rate to obtain the treatment load value. A value greater than 1 indicates that the current treatment load exceeds the design treatment baseline, while a value less than 1 indicates that the system is in a low load or normal load state. The operational reliability index is calculated by combining the load value and the pruning reliability. ,in, For preset weighting coefficients, To process load values, To run a credibility index; The operational trust index is compared with a preset operational trust threshold to analyze the operational trust status. If the running trust index is greater than the preset running trust threshold, the running trust status is determined to be a high trust running status; Conversely, if the operating trust status is not met, the operating trust status is determined to be a low trust operating state; When the running trusted state is a low trusted running state, the feedback duration remains unchanged, and the original verification frequency is maintained to continuously verify the effectiveness of parameter pruning; When the operating confidence state is high confidence, the feedback duration is adjusted to appropriately reduce the verification frequency while ensuring computational effectiveness, thereby reducing the sensor's operational burden and computational resource consumption. The formula for adjusting the feedback duration is as follows: ,in, In order to run the credibility index, To preset the trusted operating threshold, The preset adjustment coefficient, For feedback duration, The feedback time after adjustment; The adjusted feedback duration will be used as the verification trigger duration after the next round of sensor shutdown.

[0049] It should be noted that the standardization processing methods include, but are not limited to, standard linear transformation based on interval scaling, Z-Score standardization based on statistics, or normalization based on nonlinear mapping functions. The specific methods of standardization processing will not be elaborated upon here. The inlet flow sensor is a flow metering device installed in the inlet pipeline to measure the inlet volume per unit time in real time. The process configuration table is a configuration data table storing the processing flow benchmark and operating parameters. The preset weighting coefficient can be set based on the historical collaborative calculation sensitivity analysis results. The preset operational confidence threshold can be set based on the consistency statistical distribution and allowable error range of the historical collaborative calculation results. The preset adjustment coefficient can be set according to the required adjustment range based on the feedback duration.

[0050] By jointly calculating the pruning reliability and processing load, adaptive adjustment of the feedback duration is achieved, reducing the sensor's operating burden and computing resource consumption while ensuring the effectiveness of the collaborative calculation results.

[0051] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0052] Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0053] In this document, the singular forms “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that terms such as “comprising / including” or “having” specify the presence of the stated features, integrals, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, integrals, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0054] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0055] The above description of the disclosed embodiments will enable those skilled in the art to make or use various modifications to these embodiments. It will be readily apparent to those skilled in the art that the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-parameter collaborative calculation method for water treatment process design, characterized in that: Includes the following steps: Step S1: Obtain water quality testing items through the wastewater treatment platform and construct a water quality parameter set. Retrieve discharge time information to mark the water quality parameters in the water quality parameter set to obtain the water quality parameters to be tested. Count the number of historical collaborative participations for the water quality parameters to be tested. Step S2: Calculate the proportion of collaborative participation based on the historical number of collaborative participations and perform out-of-standard detection and processing. Detect the number of out-of-standard triggers based on the processing results, calculate the impact of the water quality to be tested based on the proportion of collaborative participation, and generate a sensor shutdown command based on the impact of the water quality to be tested. Step S3: After executing the sensor shutdown command, set the feedback time. After the feedback time ends, enter the verification mechanism. In the verification mechanism, restart the sensor, collect the complete parameter set and the clipped parameter set, and perform collaborative computing processing. Step S4: Generate the trimming confidence level based on the collaborative computing processing results, collect the current influent flow rate and default treatment flow rate and evaluate the treatment load value, analyze the operational confidence status in combination with the trimming confidence level, and determine whether to adjust the feedback duration based on the operational confidence status.

2. The multi-parameter collaborative calculation method for water treatment process design according to claim 1, characterized in that: In step S1, all water quality testing items configured in the wastewater treatment system are obtained through the wastewater treatment platform; A wastewater treatment platform refers to a software system used for unified access, data collection, and scheduling control of various operating equipment and monitoring devices in wastewater treatment plants; A wastewater treatment system refers to a process operation system composed of various treatment units, through which pollutants are physically, chemically, and biologically degraded. Water quality testing items include monitoring indicators of water quality parameters obtained periodically by corresponding sensors; Based on water quality testing projects, a set of water quality parameters is constructed. The values ​​of the water quality parameters are the time average values ​​output by the corresponding sensors within a preset sampling time interval.

3. The multi-parameter collaborative calculation method for water treatment process design according to claim 2, characterized in that: In step S1, the discharge time information in the historical operation database of the wastewater treatment plant is retrieved. The discharge time information is a set of discharge intervals for different types of wastewater on the time axis. Based on the matching of the current time with the emission time information, the current emission stage type is determined; Extract the historical water quality data sequence corresponding to the current emission stage type, and calculate the fluctuation range index for each water quality parameter on the historical water quality data sequence, which is defined as the range value; Calculate the mean of the historical water quality data series and construct the normalized fluctuation coefficient; A unified fluctuation judgment threshold is pre-set. When the normalized fluctuation coefficient is greater than or equal to the fluctuation judgment threshold, the water quality parameter is judged to have effective change characteristics in the current discharge stage; otherwise, the water quality parameter is judged to have limited change range in the current discharge stage. Screen and label water quality parameters that exhibit effective change characteristics during the current emission phase; For each water quality parameter to be measured, the number of times it participated in historical collaborative calculations is counted to obtain the historical collaborative participation count.

4. The multi-parameter collaborative calculation method for water treatment process design according to claim 3, characterized in that: In step S2, based on the set of water quality parameters to be tested and their corresponding historical collaborative participation times, the total number of collaborative calculations recorded in the historical operation database is accessed; The total number of collaborative calculations represents the total number of times the water quality assessment model calculations are performed within a preset statistical period; A water quality assessment model is a computational model used to comprehensively analyze multiple water quality parameters and output water quality status judgment results, including two evaluation results: exceeding the standard and not exceeding the standard. Based on the total number of collaborative calculations, the proportion of collaborative participation for each water quality parameter to be measured is calculated and defined as the ratio of the historical number of collaborative participations to the total number of collaborative calculations. Obtain the out-of-standard calculation records from the historical operation database and construct an out-of-standard sample set; For each water quality parameter to be tested, parameter removal detection is performed in the set of samples that exceed the standard, and a set of trimmed parameters is constructed after removing the parameters.

5. The multi-parameter collaborative calculation method for water treatment process design according to claim 4, characterized in that: In step S2, the set of trimmed parameters is input into the water quality evaluation model for recalculation to obtain the trimmed evaluation results; The number of samples that meet the criteria of exceeding the standard in the original evaluation but not exceeding the standard after pruning is defined as the number of exceedance triggers; Introducing the influence of the water quality to be tested, defined as follows: ,in, The degree of influence of the water quality to be tested. This is due to exceeding the limit on the number of triggers. To determine the proportion of collaborative participation, This represents the total number of times all tested water quality parameters exceeded the standard. To prevent tiny positive numbers with a denominator of zero; A preset impact threshold is set. When the impact of the water quality being tested is less than the impact threshold, a sensor shutdown command is generated; otherwise, the sensor remains on.

6. The multi-parameter collaborative calculation method for water treatment process design according to claim 1, characterized in that: In step S3, after the sensor is turned off, a preset feedback time is set, and the verification mechanism is entered after the feedback time expires. In the verification mechanism, the sensor is restarted to collect a set of water quality parameters, and the set of water quality parameters is used as the complete set of parameters. The set of parameters is obtained by removing the water quality parameters corresponding to the sensor being turned off from the complete parameter set.

7. The multi-parameter collaborative calculation method for water treatment process design according to claim 6, characterized in that: In step S3, select each water quality parameter from the complete parameter set and combine them into a complete parameter input vector; select each water quality parameter from the trimmed parameter set and combine them into a trimmed parameter input vector. Input the complete parameter input vector into the water quality assessment model and use the output result as the complete calculation result; Input the clipping parameter input vector into the water quality assessment model, and use the output result as the clipping calculation result.

8. The multi-parameter collaborative calculation method for water treatment process design according to claim 1, characterized in that: In step S4, the complete calculation results and the clipping calculation results are retrieved and standardized to obtain the complete calculation factor and the clipping calculation factor. The difference is obtained by subtracting the full calculation factor and the trimmed calculation factor and taking the absolute value. The maximum value between the full calculation factor and the trimmed calculation factor is taken as the difference normalization benchmark value. Divide the variance by the normalized variance benchmark to obtain the normalized variance ratio, and calculate the clipping confidence level based on the normalized variance ratio. The current influent flow rate is collected by the influent flow sensor, the default processing flow rate is retrieved from the process configuration table, and the ratio of the current influent flow rate to the default processing flow rate is calculated to obtain the processing load value.

9. The multi-parameter collaborative calculation method for water treatment process design according to claim 8, characterized in that: In step S4, the operational reliability index is calculated by combining the load value and the pruning reliability. The operational trust index is compared with a preset operational trust threshold to analyze the operational trust status. If the running trust index is greater than the preset running trust threshold, the running trust status is determined to be a high trust running status; Conversely, if the operating trust status is not met, the operating trust status is determined to be a low trust operating state; When the operational trust status is high trust status, the feedback duration is adjusted, and the adjusted feedback duration is calculated using the operational trust index and the preset operational trust threshold.

Images