Nitrogen violation elimination sewage treatment control method and system based on multi-time scale decision

Abstract

The invention discloses a nitrogen violation elimination sewage treatment control method and system based on multi-time scale decision, and relates to the technical field of sewage treatment, and the method comprises the steps: collecting sewage state data in real time according to a state sampling interval, and judging whether the sewage state data meets a first time scale or a second time scale, cooperative optimization control of multi-time scale and nitrogen violation elimination is carried out based on sewage state data to determine a control parameter set value, and tracking control is carried out according to the control parameter set value through a non-singular fast terminal sliding mode controller based on an extended state observer. Based on the scheme, in the sewage treatment control process, nitrogen violation elimination is met, and meanwhile energy consumption and effluent quality are improved synchronously.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage treatment, and in particular to a method and system for eliminating nitrogen violations in sewage treatment based on multi-time scale decision-making. Background Art

[0002] Every day, a large amount of fresh water is used and converted into sewage. Direct discharge of untreated sewage will pollute the environment. Therefore, sewage treatment plants are responsible for maintaining water quality at an appropriate level and protecting the environment. As sewage discharge standards in various countries become increasingly stringent, sewage treatment plants often rely on excessive aeration and a large amount of chemicals to promote nitrification and other reactions in sewage, resulting in high energy consumption and operating costs. Therefore, while ensuring that the water quality of sewage treatment plants is not violated, it is necessary to balance energy consumption and operating costs.

[0003] In order to improve energy consumption and effluent quality in the sewage treatment process at the same time, domestic and foreign scholars have considered adopting a hierarchical control strategy. The strategy is divided into two layers. The upper layer is an optimization layer that uses a multi-objective optimization algorithm to optimize energy consumption and effluent quality to determine the set values ​​of related control variables, and the lower layer is a control layer responsible for tracking and controlling these control variables. It has achieved certain results in energy consumption and effluent quality, but it does not take into account the problem that the peak values ​​of effluent ammonia nitrogen and effluent total nitrogen violate the effluent limit. In order to eliminate the violation of nitrogen in the sewage treatment process, the prior art proposes a decision-making method to suppress the peak violation of effluent ammonia nitrogen and effluent total nitrogen. However, the optimization control method used in conjunction with the existing violation elimination strategy is a fixed time scale optimization, that is, it is a periodic optimization with a cycle of 2h or 3h. However, energy consumption and effluent quality are a pair of conflicting indicators. Good effluent quality usually requires high energy consumption, and the time scales of the two indicators of energy consumption and effluent quality are different. Therefore, in the process of sewage treatment optimization control, it is necessary to improve the balance effect of energy consumption and effluent quality while satisfying the elimination of nitrogen violations. Summary of the invention

[0004] The present invention provides a sewage treatment control method and system for nitrogen violation elimination based on multi-time scale decision-making. In the sewage treatment optimization control process, the balance effect of energy consumption and effluent water quality is improved while satisfying nitrogen violation elimination.

[0005] The first aspect of the present invention provides a nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making, comprising:

[0006] Collect sewage status data in real time according to the status sampling interval, and determine whether the sewage status data meets the first time scale or the second time scale;

[0007] When the sewage state data only meets the first time scale, a first control parameter setting value is generated based on the sewage state data by using a single-objective grey wolf optimization algorithm and a pumping energy consumption optimization objective function;

[0008] Using an effluent ammonia nitrogen prediction model and an effluent total nitrogen prediction model, determining a first effluent ammonia nitrogen prediction concentration and a first effluent total nitrogen prediction concentration of the first control parameter setting value;

[0009] Determining whether a nitrogen violation elimination condition is met according to the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration, and if so, performing nitrogen violation elimination until the nitrogen violation elimination condition is no longer met, and regenerating a first control parameter setting value when the sewage state data only meets the first time scale;

[0010] When the sewage state data meets the second time scale, the multi-objective Grey Wolf optimization algorithm is used to perform multi-objective optimization based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function, and the Pareto solution set of the control parameter setting value is constructed;

[0011] The effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model are used to determine the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution of the control parameter setting value Pareto solution set;

[0012] Determine the second control parameter setting value according to whether any second effluent ammonia nitrogen predicted concentration or the second effluent total nitrogen predicted concentration meets the nitrogen violation elimination condition, or / and, perform nitrogen violation elimination until the nitrogen violation elimination condition is not met, and redetermine the second control parameter setting value when the sewage state data meets the second time scale;

[0013] Tracking control is performed according to a first control parameter setting value or a second control parameter setting value through a non-singular fast terminal sliding mode controller based on an extended state observer.

[0014] Optionally, the determining of the second control parameter setting value according to whether any second effluent ammonia nitrogen predicted concentration or the second effluent total nitrogen predicted concentration satisfies the nitrogen violation elimination condition, or / and, performing nitrogen violation elimination until the nitrogen violation elimination condition is not satisfied, and redetermining the second control parameter setting value when the sewage state data satisfies the second time scale, comprises:

[0015] Determine whether there is any violation of the second effluent ammonia nitrogen predicted concentration and the second effluent total nitrogen predicted concentration;

[0016] If there are multiple non-dominated solutions that are not violated, the non-dominated solution with the highest comprehensive satisfaction is determined as the second control parameter setting value based on the satisfaction fuzzy membership function;

[0017] If there is no non-nitrogen violation, determine whether there is a predicted total nitrogen concentration of the second effluent that is not nitrogen violated;

[0018] When there is a predicted total nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted ammonia nitrogen concentration of the second effluent is selected from the predicted total nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of effluent ammonia nitrogen;

[0019] If the nitrogen violation elimination of effluent ammonia nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met;

[0020] If the nitrogen violation elimination of the outlet ammonia nitrogen is not performed, the non-dominated solution associated with the minimum second outlet ammonia nitrogen predicted concentration is used as the second control parameter setting value;

[0021] When there is no predicted total nitrogen concentration of the second effluent without nitrogen violation, determining whether there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation;

[0022] If there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted total nitrogen concentration of the second effluent is selected from the predicted ammonia nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of the total nitrogen in the effluent;

[0023] If the nitrogen violation elimination of the effluent total nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met;

[0024] If the nitrogen violation elimination of the effluent total nitrogen is not performed, the non-dominated solution associated with the minimum second effluent total nitrogen predicted concentration is used as the second control parameter setting value;

[0025] If there is no predicted second effluent ammonia nitrogen concentration without nitrogen violation, the dissolved oxygen concentration of the three aerobic partitions determined by the fuzzy controller based on the ammonia nitrogen concentration of the fifth partition is used as the second control parameter setting value, and the nitrogen violation elimination of the effluent total nitrogen and effluent ammonia nitrogen is performed until the nitrogen violation elimination conditions are no longer met. When the sewage status data meets the second time scale, the second control parameter setting value is redetermined.

[0026] Optionally, the process of determining whether the nitrogen violation elimination condition is satisfied comprises:

[0027] Matching the current judged operating conditions based on the historical operating condition knowledge base;

[0028] If the matching level of the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent ammonia nitrogen concentration, it is determined that the predicted effluent ammonia nitrogen concentration meets the nitrogen violation elimination condition;

[0029] If the matching level of the predicted effluent total nitrogen concentration meets the effluent total nitrogen elimination level, or the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, it is determined that the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions.

[0030] Optionally, the process of performing nitrogen violation elimination until the nitrogen violation elimination condition is no longer satisfied comprises:

[0031] If the predicted concentration of effluent ammonia nitrogen meets the nitrogen violation elimination condition, the generation of the control parameter set value is stopped, and the internal reflux flow is adjusted until the predicted concentration of effluent ammonia nitrogen meets the effluent ammonia nitrogen non-elimination level;

[0032] If the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions, the generation of control parameter set values ​​is stopped, and the flow rate of the added carbon source in the anaerobic partition is adjusted until the predicted effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

[0033] Optionally, the step of adjusting the internal reflux flow rate until the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen non-elimination level includes:

[0034] Adjust the internal recycle flow rate to the maximum until the predicted concentration of effluent ammonia nitrogen meets the internal recycle effluent ammonia nitrogen elimination level;

[0035] The internal reflux volume is adjusted according to the ammonia nitrogen elimination function until the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen non-elimination level.

[0036] Optionally, if the predicted effluent total nitrogen concentration meets the nitrogen violation elimination condition, then stop generating the control parameter set value, and adjust the added carbon source flow of the anaerobic partition until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level, including:

[0037] If the matching level of the predicted effluent total nitrogen concentration meets the first sub-effluent total nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, then stop generating the control parameter set value, and adjust the added carbon source flow rate of the first partition and the second partition to the maximum until the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level;

[0038] When the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level, the total amount of added carbon source is determined according to the total nitrogen elimination function;

[0039] If the total amount of the added carbon source is less than or equal to the maximum amount of the external carbon source flow rate in the first partition, then the external carbon source flow rate of the first partition is adjusted to be the total amount of the added carbon source;

[0040] If the total amount of the added carbon source is greater than the maximum recirculation amount of the added carbon source flow in the first partition, the added carbon source flow of the first partition is adjusted to the maximum, and the added carbon source flow of the second partition is adjusted until the total amount of the added carbon source is met, until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

[0041] The second aspect of the present invention provides a nitrogen violation elimination sewage treatment control system based on multi-time scale decision-making, comprising:

[0042] A data acquisition module, used to collect sewage status data in real time according to the status sampling interval, and determine whether the sewage status data meets the first time scale or the second time scale;

[0043] A first time scale optimization control module, for generating a first control parameter setting value based on the sewage state data by using a single objective grey wolf optimization algorithm and a pumping energy consumption optimization objective function when the sewage state data only meets the first time scale;

[0044] A first time scale effluent prediction module, for determining a first effluent ammonia nitrogen predicted concentration and a first effluent total nitrogen predicted concentration of the first control parameter setting value by using an effluent ammonia nitrogen prediction model and an effluent total nitrogen prediction model;

[0045] A first time scale nitrogen violation elimination module, used for judging whether a nitrogen violation elimination condition is met according to the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration, and if so, performing nitrogen violation elimination until the nitrogen violation elimination condition is not met, and regenerating a first control parameter setting value when the sewage state data only meets the first time scale;

[0046] The second time scale optimization control module is used to construct a Pareto solution set of control parameter setting values ​​by using the sewage state data to perform multi-objective optimization based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function through a multi-objective grey wolf optimization algorithm when the sewage state data meets the second time scale;

[0047] A second time scale effluent prediction module, for determining the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution of the control parameter setting value Pareto solution set by using the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model;

[0048] A second time scale nitrogen violation elimination module, used to determine a second control parameter setting value according to whether any second effluent ammonia nitrogen predicted concentration or second effluent total nitrogen predicted concentration meets the nitrogen violation elimination condition, or / and, perform nitrogen violation elimination until the nitrogen violation elimination condition is not met, and redetermine the second control parameter setting value when the sewage state data meets the second time scale;

[0049] The tracking control module is used to perform tracking control according to the first control parameter setting value or the second control parameter setting value through a non-singular fast terminal sliding mode controller based on an extended state observer.

[0050] A third aspect of the present invention provides a computer device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making as described in any one of the above items.

[0051] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making as described in any one of the above.

[0052] A fifth aspect of the present invention provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the nitrogen violation elimination wastewater treatment control method based on multi-time scale decision-making as described in any one of the above.

[0053] It can be seen from the above technical solutions that the present invention has the following advantages:

[0054] The above scheme of the present invention provides a sewage treatment control method for nitrogen violation elimination based on multi-time scale decision-making, including: collecting sewage state data in real time according to the state sampling interval, and judging whether the sewage state data meets the first time scale or the second time scale; when the sewage state data only meets the first time scale, using the single-objective grey wolf optimization algorithm to adopt the pumping energy consumption optimization objective function to generate a first control parameter setting value based on the sewage state data; using the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model to determine the first effluent ammonia nitrogen prediction concentration and the first effluent total nitrogen prediction concentration of the first control parameter setting value; judging whether the nitrogen violation elimination condition is met according to the first effluent ammonia nitrogen prediction concentration and the first effluent total nitrogen prediction concentration, if so, performing nitrogen violation elimination until the nitrogen violation elimination condition is not met, and regenerating the first control parameter setting value when the sewage state data only meets the first time scale; when the sewage When the state data meets the second time scale, the sewage state data is used for multi-objective optimization through the multi-objective grey wolf optimization algorithm based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function to construct a Pareto solution set of control parameter setting values; the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model are used to determine the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution of the Pareto solution set of the control parameter setting value; according to whether any second effluent ammonia nitrogen prediction concentration or second effluent total nitrogen prediction concentration meets the nitrogen violation elimination condition, the second control parameter setting value is determined, or / and, nitrogen violation elimination is performed until the nitrogen violation elimination condition is not met, and the second control parameter setting value is re-determined when the sewage state data meets the second time scale; tracking control is performed according to the first control parameter setting value or the second control parameter setting value through a non-singular fast terminal sliding mode controller based on an extended state observer. Based on the above scheme, the physical properties of the sensor and the inherent dynamic characteristics of the urban sewage treatment process are fully considered. The selection process of the control parameter setting values ​​is collaboratively optimized at different time scales for different indicators. The satisfaction of the nitrogen violation elimination conditions is judged based on the predicted values ​​of the effluent total nitrogen and effluent ammonia nitrogen. The switching timing of the nitrogen violation elimination is determined to facilitate the early execution of the corresponding violation elimination strategy to avoid nitrogen peak violations. In the sewage treatment control process, energy consumption and effluent water quality are simultaneously improved while satisfying the nitrogen violation elimination. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0056] Figure 1A flowchart of the steps of a sewage treatment control method for nitrogen violation elimination based on multi-time scale decision-making provided by an embodiment of the present invention;

[0057] Figure 2 A data processing framework diagram of a sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making provided by an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of data processing for operating condition identification and nitrogen violation elimination provided in an embodiment of the present invention;

[0059] Figure 4 A schematic diagram of multi-time scale collaborative optimization provided by an embodiment of the present invention;

[0060] Figure 5 A schematic diagram of the hierarchical structure of the concentration level matching strategy provided in an embodiment of the present invention;

[0061] Figure 6 A schematic diagram of the comparison before and after adding the violation elimination strategy provided in an embodiment of the present invention;

[0062] Figure 7 A flow chart of the steps of a sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The embodiment of the present invention provides a sewage treatment control method and system for nitrogen violation elimination based on multi-time scale decision-making, which is used to improve the balance between energy consumption and effluent water quality while satisfying nitrogen violation elimination during the sewage treatment optimization control process.

[0064] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0065] See also Figure 1 , Figure 1 A flow chart of the steps of a sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making is provided in an embodiment of the present invention.

[0066] The present invention provides a nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making, comprising:

[0067] Step 101: collect sewage status data in real time according to the status sampling interval, and determine whether the sewage status data meets the first time scale or the second time scale.

[0068] The state sampling interval refers to the interval for collecting sewage state data during the sewage treatment process.

[0069] Sewage status data refers to data that characterizes the operating status and treatment effect during the sewage treatment control process, including but not limited to the nitrate nitrogen concentration in the second zone , dissolved oxygen concentration in three aerobic zones (including the third zone dissolved oxygen concentration , Dissolved oxygen concentration in the fourth zone , Dissolved oxygen concentration in the fifth zone ), total nitrogen concentration in influent , Influent ammonia nitrogen concentration , water flow , effluent ammonia nitrogen concentration , total nitrogen concentration in effluent and the ammonia nitrogen concentration in the fifth zone wait.

[0070] It should be noted that, in specific implementation, the sewage treatment benchmark simulation model No. 1 can be used to collect sewage status data according to a preset status sampling interval. For example, the status sampling interval can be set to 15 minutes. The sewage treatment benchmark simulation model No. 1 (BSM1) was jointly developed by the International Water Association and the European Union. Figure 2 As shown, BSM1 mainly includes two parts: a biochemical reaction tank and a secondary sedimentation tank. The biochemical reaction tank includes an anaerobic tank and an aerobic tank. The anaerobic tank includes two anaerobic partitions, namely the first partition Unit1 and the second partition Unit2. The aerobic tank includes three aerobic zones, namely the third partition Unit3, the fourth partition Unit4 and the fifth partition Unit5.

[0071] In order to construct the multi-time scale optimization problem of the sewage treatment process, in view of the sensor characteristics and the dynamic characteristics of sewage treatment, the optimal sampling interval of the variables related to pumping energy (PE) is selected as minutes, while the optimal sampling interval of the variables related to effluent quality (EQ) and aeration energy (AE) is hours. Therefore, PE is suitable for using a shorter first time scale sampling interval as the optimization control period, and EQ and AE are suitable for a longer second time scale sampling interval. The time scale can be understood as a specific time range that describes the changes in sewage state data. In this way, the multi-objective optimization problem description of the sewage treatment process can be described in two time scales of minutes and hours, and the sewage state data satisfies the first time scale or the second time scale mainly to emphasize the adaptability of the sewage state data to the specific time scale in the time dimension, so as to ensure that the corresponding sewage state data is applied at the corresponding time scale to achieve multi-time scale sewage optimization control.

[0072] Step 102: When the sewage state data only meets the first time scale, a first control parameter setting value is generated based on the sewage state data by using a single-objective grey wolf optimization algorithm and a pumping energy consumption optimization objective function.

[0073] The control parameter set value refers to the set value of the key indicator used to guide and regulate the sewage treatment operation to achieve the expected treatment effect during the sewage treatment process.

[0074] It should be noted that the recursive fuzzy neural network (RFNN) is used to establish the pumping energy consumption optimization objective function of PE After that, when the timestamp of the sewage status data meets the first time scale, that is, when When, for example The time is also set to 15 minutes. The description of the optimization problem of PE, that is, the single-objective optimization objective function of the single-objective grey wolf optimization algorithm, can be expressed as:

[0075] ;

[0076] in, ;

[0077] In the formula, For single-objective optimization, The objective function for optimizing pumping energy consumption is: is the first time scale, is the water inlet flow rate, is the nitrate nitrogen concentration in the second zone, is the dissolved oxygen concentration in the third zone, is the dissolved oxygen concentration in the fourth zone, is the dissolved oxygen concentration in the fifth zone, is the decision parameter, is the current state sampling interval, is the solid mixture concentration;

[0078] Therefore, if the collected sewage state data conforms to the first time scale, the single objective optimization objective function based on the pumping energy consumption optimization objective function is adopted through the single objective grey wolf optimization algorithm (GWO), and the sewage state data is used as input to generate the first control parameter setting value .

[0079] Step 103: Use the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model to determine the first effluent ammonia nitrogen prediction concentration and the first effluent total nitrogen prediction concentration of the first control parameter setting value.

[0080] It should be noted that two RFNNs are used to establish the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model. In this embodiment, the input of the effluent ammonia nitrogen prediction model is set as , , as well as , the input of the effluent total nitrogen prediction model is set as , , as well as , extract corresponding parameters from the sewage state data, and input the prediction model in combination with the first control parameter setting value, so as to obtain the first effluent ammonia nitrogen prediction concentration and the first effluent total nitrogen prediction concentration of the first control parameter setting value.

[0081] Step 104: determine whether the nitrogen violation elimination condition is met based on the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration. If so, perform nitrogen violation elimination until the nitrogen violation elimination condition is no longer met, and regenerate the first control parameter setting value when the sewage status data only meets the first time scale.

[0082] Nitrogen violation refers to the situation where the effluent ammonia nitrogen concentration exceeds the peak effluent ammonia nitrogen concentration and thus fails to meet the standard, resulting in a violation of the effluent restriction; or the effluent total nitrogen concentration exceeds the peak effluent total nitrogen concentration and thus fails to meet the standard, resulting in a violation of the effluent restriction; nitrogen violation elimination conditions refer to the conditions used for the situation where there is a nitrogen violation in the effluent ammonia nitrogen concentration or the effluent total nitrogen concentration and the need to execute nitrogen violation elimination is met.

[0083] It should be noted that whether the nitrogen violation elimination condition is met is determined based on the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration of the first control parameter setting value. If not, the current first control parameter setting value is retained. If satisfied, nitrogen violation elimination is performed. During the nitrogen violation elimination period, the generation of control parameter setting values ​​according to multi-time scale optimization control is suspended until the nitrogen violation elimination condition is no longer met. When the new sewage status data meets the first time scale, the first control parameter setting value is regenerated.

[0084] In one embodiment, the process of determining whether the nitrogen violation elimination condition is met includes:

[0085] Matching the current judged operating conditions based on the historical operating condition knowledge base;

[0086] If the matching level of the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent ammonia nitrogen concentration, it is determined that the predicted effluent ammonia nitrogen concentration meets the nitrogen violation elimination condition;

[0087] If the matching level of the predicted effluent total nitrogen concentration meets the effluent total nitrogen elimination level, or the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, it is determined that the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions.

[0088] The historical operating conditions knowledge base is a database built on the historical operating conditions of the sewage treatment process. The operating conditions include but are not limited to , , , , , and The sewage state data are taken as the key variables, and inspired by the fuzzy control idea, the sewage state data of each operating condition is graded, for example, it can be divided into one of the six levels of ultra-high concentration, high concentration, medium concentration, relatively good, good and excellent; in a preferred implementation, the key variables are , and These three are the main ones.

[0089] The current judgment operating condition refers to the operating condition that is currently required to judge whether to execute the nitrogen violation elimination strategy.

[0090] The effluent ammonia nitrogen elimination level refers to the level at which effluent ammonia nitrogen nitrogen violation elimination needs to be implemented; in contrast, the effluent ammonia nitrogen non-elimination level refers to the level at which effluent ammonia nitrogen nitrogen violation elimination does not need to be implemented.

[0091] The effluent total nitrogen elimination level refers to the level at which effluent total nitrogen violation elimination needs to be implemented; in contrast, the effluent total nitrogen non-elimination level refers to the level at which effluent total nitrogen violation elimination does not need to be implemented.

[0092] It should be noted that if Figure 3 As shown, this embodiment performs operating condition identification by matching the operating conditions to determine whether to execute the nitrogen violation elimination strategy:

[0093] First, the current judged operating condition is matched with the historical operating condition pre-modeled in the historical operating condition knowledge base by calculating the similarity. The similarity calculation process includes:

[0094] ;

[0095] in, ;

[0096] In the formula, For the Historical operating conditions, The historical operating condition knowledge base Historical operating conditions, To judge the current operating conditions, To judge the current operating conditions and The similarity of historical operating conditions, For the The key variables, is the number of key variables in the operating conditions, The first The weight parameters of the key variables, The first The key variables, For the Under the historical operating conditions The key variables, For the Under the historical operating conditions The maximum value of the key variable, For the Under the historical operating conditions Minimum value of key variables;

[0097] If the key variable for judging the operating conditions is If the difference between the historical operating conditions is small, Larger, indicating that the current working condition is different from the The historical conditions are similar, otherwise Small, indicating that the current working condition is different from the The historical operating conditions are not similar; therefore, the current operating conditions in the knowledge base are different from the The matching condition of historical operation conditions can be expressed as ,in, is the matching threshold, if its similarity Greater than The match is considered successful if it is less than , then the current operating conditions are added to the historical operating conditions knowledge base and directly based on the corresponding Exceeding or If the standard is exceeded, corresponding suppression and elimination strategies shall be implemented;

[0098] If the current operating condition is successfully matched and the matching level of the outlet ammonia nitrogen concentration meets the outlet ammonia nitrogen elimination level, illustratively, the outlet ammonia nitrogen elimination level is set to relatively good or below, or the match fails and the outlet ammonia nitrogen concentration of the current operating condition is in violation of the outlet water restriction, it is determined that the outlet ammonia nitrogen predicted concentration meets the nitrogen violation elimination condition;

[0099] If the current operating conditions are judged to match successfully and the matching level of the outlet water total nitrogen concentration meets the outlet water total nitrogen elimination level, illustratively, the outlet water total nitrogen elimination level is set to relatively good and below, or the match fails and the outlet water total nitrogen concentration of the current operating conditions is judged to violate the outlet water restriction, then it is determined that the outlet water total nitrogen predicted concentration meets the nitrogen violation elimination conditions.

[0100] In one embodiment, the process of performing nitrogen violation elimination until the nitrogen violation elimination condition is not satisfied comprises:

[0101] If the predicted concentration of effluent ammonia nitrogen meets the nitrogen violation elimination condition, the generation of the control parameter set value is stopped, and the internal reflux flow is adjusted until the predicted concentration of effluent ammonia nitrogen meets the effluent ammonia nitrogen non-elimination level;

[0102] If the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions, the generation of control parameter set values ​​is stopped, and the flow rate of the added carbon source in the anaerobic partition is adjusted until the predicted effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

[0103] It should be noted that if the predicted effluent ammonia nitrogen concentration meets the nitrogen violation elimination conditions, the multi-time scale optimization control is stopped and switched to the ammonia nitrogen inhibition strategy based on adjusting the internal reflux flow, and braking is performed in advance to avoid exceeding the standard until the predicted effluent ammonia nitrogen concentration of the current operating conditions meets the effluent ammonia nitrogen non-elimination level. Exemplarily, the effluent ammonia nitrogen non-elimination level is set to a good or excellent level, and the multi-time scale optimization control is restored; if the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions, the multi-time scale optimization control is stopped and switched to the total nitrogen inhibition strategy based on adjusting the external carbon source flow of the anaerobic partition, i.e., the first partition and the second partition, until the predicted effluent total nitrogen concentration of the current operating conditions meets the effluent total nitrogen non-elimination level. Exemplarily, the effluent total nitrogen non-elimination level is set to a good or excellent level, and the multi-time scale optimization control is restored.

[0104] In a more specific embodiment, adjusting the internal reflux amount until the predicted concentration of effluent ammonia nitrogen meets the effluent ammonia nitrogen non-elimination level comprises:

[0105] Adjust the internal recycle flow rate to the maximum until the predicted concentration of effluent ammonia nitrogen meets the internal recycle effluent ammonia nitrogen elimination level;

[0106] The internal reflux volume is adjusted according to the ammonia nitrogen elimination function until the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen non-elimination level.

[0107] The internal recycle effluent ammonia nitrogen elimination level refers to the level of effluent ammonia nitrogen elimination level that requires reducing internal recycle to increase hydraulic retention time.

[0108] It should be noted that in the part of effluent ammonia nitrogen suppression, first when the level is relatively good, the internal reflux volume Open to the maximum, i.e. 92230, to dilute the ammonia nitrogen, and continue until When the concentration reaches the medium level, or when the concentration reaches the medium level, the internal reflow is reduced and the hydraulic retention time is increased to promote denitrification and reduce nitrogen. After many experiments, it is known that after multi-time scale optimization, Will not exceed , so adjusting to increase the hydraulic retention time can be adjusted through the ammonia nitrogen elimination function shown: ,when Restore multi-timescale optimization control when the rating is good or excellent.

[0109] In a more specific embodiment, if the predicted effluent total nitrogen concentration meets the nitrogen violation elimination condition, the generation of the control parameter set value is stopped, and the added carbon source flow of the anaerobic partition is adjusted until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level, including:

[0110] If the matching level of the predicted effluent total nitrogen concentration meets the first sub-effluent total nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, then stop generating the control parameter set value, and adjust the added carbon source flow rate of the first partition and the second partition to the maximum until the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level;

[0111] When the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level, the total amount of added carbon source is determined according to the total nitrogen elimination function;

[0112] If the total amount of the added carbon source is less than or equal to the maximum amount of the external carbon source flow rate in the first partition, then the external carbon source flow rate of the first partition is adjusted to the total amount of the external carbon source;

[0113] If the total amount of the added carbon source is greater than the maximum external carbon source flow recirculation amount in the first partition, the external carbon source flow of the first partition is adjusted to the maximum, and the external carbon source flow of the second partition is adjusted until the total amount of the added carbon source is met, until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

[0114] The first sub-effluent total nitrogen elimination level refers to the level with relatively high denitrification requirements among the effluent total nitrogen elimination levels; in contrast, the second sub-effluent total nitrogen elimination level refers to the level with relatively low denitrification requirements among the effluent total nitrogen elimination levels; the second sub-effluent total nitrogen elimination level is better than the first sub-effluent total nitrogen elimination level, that is, the effluent total nitrogen concentration corresponding to the second sub-effluent total nitrogen elimination level is lower than the effluent total nitrogen concentration corresponding to the first sub-effluent total nitrogen elimination level.

[0115] It should be noted that in the effluent total nitrogen suppression part, if the matching level of the effluent total nitrogen predicted concentration meets the first sub-effluent total nitrogen elimination level, the first sub-effluent total nitrogen elimination level is exemplarily set to medium concentration and below, or the matching fails and the effluent total nitrogen predicted concentration violates the effluent limit, then the denitrification requirement of the denitrification process is very high, and the external carbon source flow rate of the first partition needs to be increased. and the additional carbon source flow in the second partition Set to its upper limit value, that is, set ; When the matching level of the predicted concentration of total nitrogen in the effluent water meets the second sub-effluent total nitrogen elimination level, illustratively, the second sub-effluent total nitrogen elimination level is set to be relatively good, then according to the total nitrogen elimination function Determine the total amount of added carbon source That is, the sum of the added carbon source flow in the first partition and the added carbon source flow in the second partition. The value range of the total amount of added carbon source is ,like Less than ,but ;like Greater than ,but , ,when Restore multi-timescale optimization control when rated Good or Excellent.

[0116] Step 105: When the sewage state data meets the second time scale, a multi-objective Grey Wolf optimization algorithm is used to perform multi-objective optimization based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function using the sewage state data to construct a Pareto solution set of control parameter setting values.

[0117] It should be noted that the recursive fuzzy neural network is used to establish the aeration energy consumption optimization objective function of AE. And the EQ water quality optimization objective function ,when When, for example It can be set to multiples of 15 minutes, such as 2 hours, focusing on optimizing EQ and AE, such as Figure 4 As shown, stop at this moment GWO is always used to optimize PE, and the multi-objective gray wolf optimization algorithm is used to optimize EQ and AE. The description of the optimization problem of EQ and AE, that is, the multi-objective optimization objective function of the multi-objective gray wolf optimization algorithm, can be expressed as:

[0118] ;

[0119] in, ;

[0120] In the formula, For multi-objective optimization objective function, The objective function for optimizing aeration energy consumption is: Optimize the objective function for effluent quality;

[0121] Therefore, if the collected sewage state data conforms to the second time scale, the multi-objective gray wolf optimization algorithm is used to solve the multi-objective optimization objective function based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function, with the sewage state data as input. Since it is a multi-objective optimization at this time, the solution result is a Pareto solution set composed of control parameter setting values, that is, the control parameter setting value Pareto solution set. This solution set contains multiple non-dominated solutions that can coordinate the conflicting variables of energy consumption and effluent water quality. Therefore, we need to select a set of suitable preference solutions from them as as well as The setting value of

[0122] In a preferred implementation, the multi-objective grey wolf optimization algorithm is the MOGWO-SM algorithm, which is a multi-objective grey wolf optimization algorithm based on subpopulation and multi-strategy exploration. The algorithm has better optimization capabilities and can obtain more evenly distributed and excellent solutions when optimizing energy consumption and effluent water quality. For details, please refer to the prior art and will not be repeated here.

[0123] Step 106: Use the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model to determine the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution of the control parameter setting value Pareto solution set.

[0124] It should be noted that based on the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model in step 103, the corresponding parameters are extracted from the sewage state data, and the prediction model is input into the prediction model in combination with the non-dominated solutions of the Pareto solution set of the control parameter setting value, so as to obtain the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution.

[0125] Step 107, determine the second control parameter setting value according to whether any second effluent ammonia nitrogen predicted concentration or the second effluent total nitrogen predicted concentration meets the nitrogen violation elimination condition, or / and, perform nitrogen violation elimination until the nitrogen violation elimination condition is no longer met, and redetermine the second control parameter setting value when the sewage status data meets the second time scale.

[0126] It can be understood that the process of determining whether the nitrogen violation elimination condition is met in step 107 and the process of performing nitrogen violation elimination until the nitrogen violation elimination condition is no longer met can refer to the aforementioned steps and will not be repeated here.

[0127] Step 105 includes the following sub-steps:

[0128] Determine whether there is any violation of the second effluent ammonia nitrogen predicted concentration and the second effluent total nitrogen predicted concentration;

[0129] If there are multiple non-dominated solutions that are not violated, the non-dominated solution with the highest comprehensive satisfaction is determined as the second control parameter setting value based on the satisfaction fuzzy membership function;

[0130] If there is no non-nitrogen violation, determine whether there is a predicted total nitrogen concentration of the second effluent that is not nitrogen violated;

[0131] When there is a predicted total nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted ammonia nitrogen concentration of the second effluent is selected from the predicted total nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of effluent ammonia nitrogen;

[0132] If the nitrogen violation elimination of effluent ammonia nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met;

[0133] If the nitrogen violation elimination of the effluent ammonia nitrogen is not performed, the non-dominated solution associated with the minimum second effluent ammonia nitrogen predicted concentration is used as the second control parameter setting value;

[0134] When there is no predicted total nitrogen concentration of the second effluent without nitrogen violation, determining whether there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation;

[0135] If there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted total nitrogen concentration of the second effluent is selected from the predicted ammonia nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of the total nitrogen in the effluent;

[0136] If the nitrogen violation elimination of the effluent total nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met;

[0137] If the nitrogen violation elimination of the effluent total nitrogen is not performed, the non-dominated solution associated with the minimum second effluent total nitrogen predicted concentration is used as the second control parameter setting value;

[0138] If there is no predicted second effluent ammonia nitrogen concentration without nitrogen violation, the dissolved oxygen concentration of the three aerobic partitions determined by the fuzzy controller based on the ammonia nitrogen concentration of the fifth partition is used as the second control parameter setting value, and the nitrogen violation elimination of the effluent total nitrogen and effluent ammonia nitrogen is performed until the nitrogen violation elimination conditions are no longer met. When the sewage status data meets the second time scale, the second control parameter setting value is redetermined.

[0139] It should be noted that, in this embodiment, whether to eliminate nitrogen violation and determine the second control parameter setting value is determined according to whether the second effluent ammonia nitrogen predicted concentration or the second effluent total nitrogen predicted concentration has nitrogen violation, and a concentration level matching strategy is adopted. and The forecast is classified into Figure 5 In the level shown, there are 4 levels in total, and level 1 (Rank 1) stores and All qualified solutions; Rank 2 stores Meet the standard, The unsatisfactory solution, Rank 3 is the opposite of Rank 2, and Rank 4 is and The specific steps for selecting the preferred solution are as follows:

[0140] (1) If Rank 1 is not empty at this time, the following method based on the fuzzy membership function of satisfaction is used to find the solution with the highest comprehensive satisfaction of Rank 1 as the control parameter setting value of the controller:

[0141] ;

[0142] ;

[0143] In the formula, the objective function for or ( for as well as of and), For the The objective function, For the The maximum value of the objective function, For the The minimum value of the objective function, For the Non-dominated solutions About The satisfaction of the objective function, For the Non-dominated solutions Overall satisfaction, is the number of objective functions, is the number of non-dominated solutions in Rank 1, i.e., the number of non-dominated solutions where both the predicted effluent ammonia nitrogen concentration and the predicted effluent total nitrogen concentration are not violated by nitrogen;

[0144] (2) If Rank 1 is empty at this time, it means that there is no Pareto solution set. and For all the solutions that meet the criteria, check whether Rank 2 and Rank 3 are empty. If both are not empty, the solution in Rank 2 is selected as the preferred solution. If Rank 2 is empty, the preferred solution is selected from Rank 3.

[0145] In Rank 2, due to Neither of them meet the criteria, so choose The lowest solution is taken as the preferred solution, and whether to adopt it is determined based on the working condition identification situation. Violation elimination control, if no violation elimination is performed, it will be retained The lowest solution is used as the second control parameter setting value. Otherwise, if the violation elimination is performed until the nitrogen violation elimination condition is not met, the second control parameter setting value is re-determined when the sewage state data meets the second time scale;

[0146] Similarly, in Rank 3, select The lowest solution is taken as the preferred solution, and whether to adopt it is determined based on the working condition identification situation. Violation elimination control, if no violation elimination is performed, it will be retained The lowest solution is used as the second control parameter setting value. Otherwise, if the violation elimination is performed until the nitrogen violation elimination condition is not met, the second control parameter setting value is re-determined when the sewage state data meets the second time scale;

[0147] (3) If Rank 1 to Rank 3 are all empty, that is, there is no Pareto solution set and The main goal of the solution is to suppress the pollutants in the effluent; start and Violation elimination strategy, at the same time, during this period, the dissolved oxygen concentration in the three aerobic zones The control parameter set value is generated based on the ammonia nitrogen concentration in the fifth zone. As input the fuzzy controller provides the set point value of dissolved oxygen, The maximum setting values ​​of are the upper limits of their maximum optimization setting values; the input and output of the fuzzy controller include three concentration levels: low, medium and high, which are represented by L, M and H respectively. The fuzzy rules are:

[0148] ;

[0149] in, The value range is , dissolved oxygen concentration The value range is ;

[0150] when and The violation is eliminated until the nitrogen violation elimination condition is no longer met, and then the second control parameter setting value is redetermined when the sewage status data meets the second time scale.

[0151] Step 108: Perform tracking control according to the first control parameter setting value or the second control parameter setting value through a non-singular fast terminal sliding mode controller based on an extended state observer.

[0152] It should be noted that if Figure 2 As shown in the figure, the control parameter setting values ​​obtained through multi-time scale optimization decision-making will be tracked and controlled by the lower-level controller, and its controlled objects include as well as The lower-level controller used is a non-singular fast terminal sliding mode controller based on an extended state observer. In a preferred implementation, a MNFTSMC-ESO controller is specifically used. This controller can track the dynamically changing set value within a finite time, thereby ensuring the effectiveness of the optimization algorithm. The specific implementation process can refer to the prior art and will not be repeated here.

[0153] In order to verify the effectiveness and superiority of the proposed strategy through experiments, the above method was applied to BSM1 to verify its effectiveness, and the overall energy consumption (Overall Cost Index, OCI) and effluent water quality (Effluent Quality Index, EQI) under this method were calculated. At the same time, it was compared with the existing research methods. The effect comparison is shown in Table 1:

[0154] Table 1 Different and Comparison of peak suppression methods

[0155]

[0156] From Table 1 and Figure 6 The comparison before and after adding the violation elimination strategy shows that, compared with existing research, while satisfying the nitrogen violation elimination, the total energy consumption is lower and the effluent quality is better, which verifies the superiority of this method.

[0157] In the embodiment of the present invention, the physical properties of the sensor and the inherent dynamic characteristics of the urban sewage treatment process are fully considered, the selection process of the control parameter setting value is collaboratively optimized at different time scales for different indicators, and the operating conditions are matched according to the predicted values ​​of the effluent total nitrogen and the effluent ammonia nitrogen, and the historical operating condition knowledge base is used to judge whether the nitrogen violation elimination conditions are satisfied, and the switching timing of the nitrogen violation elimination is determined. The corresponding violation elimination strategy can be executed in advance to avoid nitrogen peak violation, and excessive reliance on expert knowledge can be avoided. While simultaneously improving energy consumption and effluent water quality, it is avoided. and Peak violation.

[0158] See also Figure 7 , Figure 7 A structural block diagram of nitrogen violation elimination sewage treatment control based on multi-time scale decision-making provided in an embodiment of the present invention.

[0159] The present invention provides a nitrogen violation elimination sewage treatment control system based on multi-time scale decision-making, comprising:

[0160] The data collection module 701 is used to collect sewage status data in real time according to the status sampling interval, and determine whether the sewage status data meets the first time scale or the second time scale;

[0161] The first time scale optimization control module 702 is used to generate a first control parameter setting value based on the sewage state data by using a single-objective grey wolf optimization algorithm and a pumping energy consumption optimization objective function when the sewage state data only meets the first time scale;

[0162] The first time scale effluent prediction module 703 is used to determine the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration of the first control parameter setting value by using the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model;

[0163] The first time scale nitrogen violation elimination module 704 is used to determine whether the nitrogen violation elimination condition is met according to the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration, and if so, perform nitrogen violation elimination until the nitrogen violation elimination condition is not met, and regenerate the first control parameter setting value when the sewage state data only meets the first time scale;

[0164] The second time scale optimization control module 705 is used to construct a Pareto solution set of control parameter setting values ​​by using the sewage state data to perform multi-objective optimization based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function through a multi-objective grey wolf optimization algorithm when the sewage state data meets the second time scale;

[0165] The second time scale effluent prediction module 706 is used to determine the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution of the control parameter setting value Pareto solution set by using the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model;

[0166] A second time scale nitrogen violation elimination module 707, for determining a second control parameter setting value according to whether any second effluent ammonia nitrogen predicted concentration or second effluent total nitrogen predicted concentration meets the nitrogen violation elimination condition, or / and, performing nitrogen violation elimination until the nitrogen violation elimination condition is not met, and re-determining the second control parameter setting value when the sewage state data meets the second time scale;

[0167] The tracking control module 708 is used to perform tracking control according to the first control parameter setting value or the second control parameter setting value through a non-singular fast terminal sliding mode controller based on an extended state observer.

[0168] Optionally, the second time scale nitrogen violation elimination module 707 is specifically configured to:

[0169] Determine whether there is any violation of the second effluent ammonia nitrogen predicted concentration and the second effluent total nitrogen predicted concentration;

[0170] If there are multiple non-dominated solutions that are not violated, the non-dominated solution with the highest comprehensive satisfaction is determined as the second control parameter setting value based on the satisfaction fuzzy membership function;

[0171] If there is no non-nitrogen violation, determine whether there is a predicted total nitrogen concentration of the second effluent that is not nitrogen violated;

[0172] When there is a predicted total nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted ammonia nitrogen concentration of the second effluent is selected from the predicted total nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of effluent ammonia nitrogen;

[0173] If the nitrogen violation elimination of effluent ammonia nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met;

[0174] If the nitrogen violation elimination of the effluent ammonia nitrogen is not performed, the non-dominated solution associated with the minimum second effluent ammonia nitrogen predicted concentration is used as the second control parameter setting value;

[0175] When there is no predicted total nitrogen concentration of the second effluent without nitrogen violation, determining whether there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation;

[0176] If there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted total nitrogen concentration of the second effluent is selected from the predicted ammonia nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of the total nitrogen in the effluent;

[0177] If the nitrogen violation elimination of the effluent total nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met;

[0178] If the nitrogen violation elimination of the effluent total nitrogen is not performed, the non-dominated solution associated with the minimum second effluent total nitrogen predicted concentration is used as the second control parameter setting value;

[0179] If there is no predicted second effluent ammonia nitrogen concentration without nitrogen violation, the dissolved oxygen concentration of the three aerobic partitions determined by the fuzzy controller based on the ammonia nitrogen concentration of the fifth partition is used as the second control parameter setting value, and the nitrogen violation elimination of the effluent total nitrogen and effluent ammonia nitrogen is performed until the nitrogen violation elimination conditions are no longer met. When the sewage status data meets the second time scale, the second control parameter setting value is redetermined.

[0180] Optionally, the process of determining whether the nitrogen violation elimination condition is satisfied comprises:

[0181] Matching the current judged operating conditions based on the historical operating condition knowledge base;

[0182] If the matching level of the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent ammonia nitrogen concentration, it is determined that the predicted effluent ammonia nitrogen concentration meets the nitrogen violation elimination condition;

[0183] If the matching level of the predicted effluent total nitrogen concentration meets the effluent total nitrogen elimination level, or the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, it is determined that the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions.

[0184] Optionally, the process of performing nitrogen violation elimination until the nitrogen violation elimination condition is not satisfied comprises:

[0185] If the predicted concentration of effluent ammonia nitrogen meets the nitrogen violation elimination condition, the generation of the control parameter set value is stopped, and the internal reflux flow is adjusted until the predicted concentration of effluent ammonia nitrogen meets the effluent ammonia nitrogen non-elimination level;

[0186] If the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions, the generation of control parameter set values ​​is stopped, and the flow rate of the added carbon source in the anaerobic partition is adjusted until the predicted effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

[0187] Optionally, the internal reflux volume is adjusted until the predicted concentration of effluent ammonia nitrogen meets the non-elimination level of effluent ammonia nitrogen, including:

[0188] Adjust the internal recycle flow rate to the maximum until the predicted concentration of effluent ammonia nitrogen meets the internal recycle effluent ammonia nitrogen elimination level;

[0189] The internal reflux volume is adjusted according to the ammonia nitrogen elimination function until the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen non-elimination level.

[0190] Optionally, if the predicted effluent total nitrogen concentration meets the nitrogen violation elimination condition, the generation of the control parameter set value is stopped, and the added carbon source flow of the anaerobic partition is adjusted until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level, including:

[0191] If the matching level of the predicted effluent total nitrogen concentration meets the first sub-effluent total nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, then stop generating the control parameter set value, and adjust the added carbon source flow rate of the first partition and the second partition to the maximum until the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level;

[0192] When the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level, the total amount of added carbon source is determined according to the total nitrogen elimination function;

[0193] If the total amount of the added carbon source is less than or equal to the maximum amount of the external carbon source flow rate in the first partition, then the external carbon source flow rate of the first partition is adjusted to the total amount of the external carbon source;

[0194] If the total amount of the added carbon source is greater than the maximum external carbon source flow recirculation amount in the first partition, the external carbon source flow of the first partition is adjusted to the maximum, and the external carbon source flow of the second partition is adjusted until the total amount of the added carbon source is met, until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

[0195] An embodiment of the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory; when the computer program is executed by the processor, the processor executes the steps of the sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making as in any of the above embodiments.

[0196] An embodiment of the present invention also provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the steps of the sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making as in any of the above embodiments are implemented.

[0197] An embodiment of the present invention also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making as in any of the above embodiments.

[0198] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system and module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0199] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0200] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0201] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0202] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0203] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A nitrogen violation elimination wastewater treatment control method based on multi-time scale decision-making, characterized in that: include: Collect sewage status data in real time according to the status sampling interval, and determine whether the sewage status data meets the first time scale or the second time scale; When the sewage state data only meets the first time scale, a first control parameter setting value is generated based on the sewage state data by using a single-objective grey wolf optimization algorithm and a pumping energy consumption optimization objective function; Using an effluent ammonia nitrogen prediction model and an effluent total nitrogen prediction model, determining a first effluent ammonia nitrogen prediction concentration and a first effluent total nitrogen prediction concentration of the first control parameter setting value; Determining whether a nitrogen violation elimination condition is met according to the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration, and if so, performing nitrogen violation elimination until the nitrogen violation elimination condition is no longer met, and regenerating a first control parameter setting value when the sewage state data only meets the first time scale; When the sewage state data meets the second time scale, the multi-objective Grey Wolf optimization algorithm is used to perform multi-objective optimization based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function, and the Pareto solution set of the control parameter setting value is constructed; The effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model are used to determine the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution of the control parameter setting value Pareto solution set; Determine the second control parameter setting value according to whether any second effluent ammonia nitrogen predicted concentration or the second effluent total nitrogen predicted concentration meets the nitrogen violation elimination condition, or / and, perform nitrogen violation elimination until the nitrogen violation elimination condition is not met, and redetermine the second control parameter setting value when the sewage state data meets the second time scale; Tracking control is performed according to a first control parameter setting value or a second control parameter setting value through a non-singular fast terminal sliding mode controller based on an extended state observer.

2. The nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making according to claim 1 is characterized in that: The second control parameter setting value is determined according to whether any second effluent ammonia nitrogen predicted concentration or the second effluent total nitrogen predicted concentration meets the nitrogen violation elimination condition, or / and, nitrogen violation elimination is performed until the nitrogen violation elimination condition is not met, and the second control parameter setting value is re-determined when the sewage state data meets the second time scale, including: Determine whether there is any violation of the second effluent ammonia nitrogen predicted concentration and the second effluent total nitrogen predicted concentration; If there are multiple non-dominated solutions that are not violated, the non-dominated solution with the highest comprehensive satisfaction is determined as the second control parameter setting value based on the satisfaction fuzzy membership function; If there is no non-nitrogen violation, determine whether there is a predicted total nitrogen concentration of the second effluent that is not nitrogen violated; When there is a predicted total nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted ammonia nitrogen concentration of the second effluent is selected from the predicted total nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of effluent ammonia nitrogen; If the nitrogen violation elimination of effluent ammonia nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met; If the nitrogen violation elimination of the outlet ammonia nitrogen is not performed, the non-dominated solution associated with the minimum second outlet ammonia nitrogen predicted concentration is used as the second control parameter setting value; When there is no predicted total nitrogen concentration of the second effluent without nitrogen violation, determining whether there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation; If there is a predicted ammonia nitrogen concentration of the second effluent without nitrogen violation, the minimum predicted total nitrogen concentration of the second effluent is selected from the predicted ammonia nitrogen concentration of the second effluent without nitrogen violation to perform working condition identification to determine whether to perform nitrogen violation elimination of the total nitrogen in the effluent; If the nitrogen violation elimination of the effluent total nitrogen is performed, the second control parameter setting value is re-determined when the sewage state data meets the second time scale until the nitrogen violation elimination condition is no longer met; If the nitrogen violation elimination of the effluent total nitrogen is not performed, the non-dominated solution associated with the minimum second effluent total nitrogen predicted concentration is used as the second control parameter setting value; If there is no predicted second effluent ammonia nitrogen concentration without nitrogen violation, the dissolved oxygen concentration of the three aerobic partitions determined by the fuzzy controller based on the ammonia nitrogen concentration of the fifth partition is used as the second control parameter setting value, and the nitrogen violation elimination of the effluent total nitrogen and effluent ammonia nitrogen is performed until the nitrogen violation elimination conditions are no longer met. When the sewage status data meets the second time scale, the second control parameter setting value is redetermined.

3. The nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making according to claim 1 is characterized in that: The process for determining whether the nitrogen violation elimination conditions have been met includes: Matching the current judged operating conditions based on the historical operating condition knowledge base; If the matching level of the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent ammonia nitrogen concentration, it is determined that the predicted effluent ammonia nitrogen concentration meets the nitrogen violation elimination condition; If the matching level of the predicted effluent total nitrogen concentration meets the effluent total nitrogen elimination level, or the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, it is determined that the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions.

4. The nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making according to claim 1 is characterized in that: The process of performing nitrogen violation elimination until the nitrogen violation elimination conditions are no longer met includes: If the predicted concentration of effluent ammonia nitrogen meets the nitrogen violation elimination condition, the generation of the control parameter set value is stopped, and the internal reflux flow is adjusted until the predicted concentration of effluent ammonia nitrogen meets the effluent ammonia nitrogen non-elimination level; If the predicted effluent total nitrogen concentration meets the nitrogen violation elimination conditions, the generation of control parameter set values ​​is stopped, and the flow rate of the added carbon source in the anaerobic partition is adjusted until the predicted effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

5. The nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making according to claim 4 is characterized in that: The method of adjusting the internal reflux flow rate until the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen non-elimination level includes: Adjust the internal recycle flow rate to the maximum until the predicted concentration of effluent ammonia nitrogen meets the internal recycle effluent ammonia nitrogen elimination level; The internal reflux volume is adjusted according to the ammonia nitrogen elimination function until the predicted effluent ammonia nitrogen concentration meets the effluent ammonia nitrogen non-elimination level.

6. The nitrogen violation elimination sewage treatment control method based on multi-time scale decision-making according to claim 4 is characterized in that: If the predicted effluent total nitrogen concentration meets the nitrogen violation elimination condition, the generation of the control parameter set value is stopped, and the added carbon source flow of the anaerobic partition is adjusted until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level, including: If the matching level of the predicted effluent total nitrogen concentration meets the first sub-effluent total nitrogen elimination level, or if the matching fails and there is a nitrogen violation in the predicted effluent total nitrogen concentration, then stop generating the control parameter set value, and adjust the added carbon source flow rate of the first partition and the second partition to the maximum until the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level; When the predicted effluent total nitrogen concentration meets the second sub-effluent total nitrogen elimination level, the total amount of added carbon source is determined according to the total nitrogen elimination function; If the total amount of the added carbon source is less than or equal to the maximum amount of the external carbon source flow rate in the first partition, then the external carbon source flow rate of the first partition is adjusted to be the total amount of the added carbon source; If the total amount of the added carbon source is greater than the maximum recirculation amount of the added carbon source flow in the first partition, the added carbon source flow of the first partition is adjusted to the maximum, and the added carbon source flow of the second partition is adjusted until the total amount of the added carbon source is met, until the effluent total nitrogen concentration meets the effluent total nitrogen non-elimination level.

7. A nitrogen violation elimination sewage treatment control system based on multi-time scale decision making, characterized in that, include: A data acquisition module, used to collect sewage status data in real time according to the status sampling interval, and determine whether the sewage status data meets the first time scale or the second time scale; A first time scale optimization control module, for generating a first control parameter setting value based on the sewage state data by using a single objective grey wolf optimization algorithm and a pumping energy consumption optimization objective function when the sewage state data only meets the first time scale; A first time scale effluent prediction module, for determining a first effluent ammonia nitrogen predicted concentration and a first effluent total nitrogen predicted concentration of the first control parameter setting value by using an effluent ammonia nitrogen prediction model and an effluent total nitrogen prediction model; A first time scale nitrogen violation elimination module, used for judging whether a nitrogen violation elimination condition is met according to the first effluent ammonia nitrogen predicted concentration and the first effluent total nitrogen predicted concentration, and if so, performing nitrogen violation elimination until the nitrogen violation elimination condition is not met, and regenerating a first control parameter setting value when the sewage state data only meets the first time scale; The second time scale optimization control module is used to construct a Pareto solution set of control parameter setting values ​​by using the sewage state data to perform multi-objective optimization based on the aeration energy consumption optimization objective function and the effluent quality optimization objective function through a multi-objective grey wolf optimization algorithm when the sewage state data meets the second time scale; A second time scale effluent prediction module, for determining the second effluent ammonia nitrogen prediction concentration and the second effluent total nitrogen prediction concentration of each non-dominated solution of the control parameter setting value Pareto solution set by using the effluent ammonia nitrogen prediction model and the effluent total nitrogen prediction model; A second time scale nitrogen violation elimination module, used to determine a second control parameter setting value according to whether any second effluent ammonia nitrogen predicted concentration or second effluent total nitrogen predicted concentration meets the nitrogen violation elimination condition, or / and, perform nitrogen violation elimination until the nitrogen violation elimination condition is not met, and redetermine the second control parameter setting value when the sewage state data meets the second time scale; The tracking control module is used to perform tracking control according to the first control parameter setting value or the second control parameter setting value through a non-singular fast terminal sliding mode controller based on an extended state observer.

8. A computer device, characterized in that: It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the sewage treatment control method for eliminating nitrogen violations based on multi-time scale decision-making as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by the processor, the steps of the nitrogen violation elimination wastewater treatment control method based on multi-time scale decision-making as described in any one of claims 1-6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by the processor, the steps of the nitrogen violation elimination wastewater treatment control method based on multi-time scale decision-making as described in any one of claims 1-6 are implemented.

Images