Big data analysis-based intelligent sludge discharge, dehydration and dosing control system for sewage plant

Abstract

The invention discloses a sewage plant intelligent sludge discharge and dehydration dosing control system based on big data analysis. Comprising a big data analysis control platform which is connected with each water quality and quantity monitoring facility, each sludge pump, each sludge flow meter, each microwave method sludge concentration meter, the dehydration equipment, the dosing pump and the dosing flow meter through communication cables; and the big data analysis control platform analyzes and calculates the data obtained from the communication cable and then controls the data. By establishing a big data analysis control platform of sewage plant mechanism and data fusion, the sludge discharge concentration and the sludge dewatering dosage are accurately and dynamically controlled from the whole of sludge discharge, dewatering and dosing, the operation load and dosage of dewatering equipment are reduced, and the intelligent low-carbon operation effect is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sewage and sludge treatment, and in particular to an intelligent sludge discharge and dehydration and dosing control system for a sewage plant based on big data analysis. Background Art

[0002] Sewage treatment plants are important livelihood projects, and the sludge in sewage treatment plants is an inevitable product after sewage treatment. The transportation and treatment of sludge is a key point in sewage treatment plants. Generally speaking, each sedimentation tank and deep treatment unit of a sewage treatment plant will discharge or return part of the sludge, which will be transported to a concentration or sludge storage tank, and then transported to a dehydration or drying incineration equipment through a sludge pump, and then transported to a reduced volume treatment unit for disposal.

[0003] Traditional sludge pumps operate intermittently, starting and stopping according to time settings. This operation method is simple and crude, which can easily lead to untimely sludge discharge and the risk of sludge leakage, affecting the effluent quality of the sewage treatment plant; or excessive sludge discharge, resulting in too low solid content in the sludge, increasing the operating load of the concentration and dehydration equipment, and increasing energy consumption, as well as chemical and labor consumption.

[0004] Moreover, in order to ensure that the moisture content of dewatered sludge meets the standard, traditional sewage treatment plants generally add excessive amounts of flocculants, resulting in serious waste of resources and being inconsistent with my country's dual carbon policy.

[0005] Therefore, how to achieve intelligent and optimal sludge discharge and dehydration dosing from the overall perspective of the entire sludge discharge and dehydration dosing system, improve the sludge discharge and dehydration efficiency and stability, and at the same time save energy and reduce consumption and operate in a low-carbon manner has become a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0006] In view of the above-mentioned defects of the prior art, the present invention provides an intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis. The purpose of the control system is to realize intelligent and optimal sludge discharge and dehydration dosing from the overall perspective of the entire sludge discharge and dehydration dosing system, improve the sludge discharge and dehydration efficiency and stability, and at the same time save energy, reduce consumption, and operate in a low-carbon manner.

[0007] To achieve the above-mentioned purpose, the present invention discloses an intelligent sludge discharge and dehydration dosing control system for a sewage plant based on big data analysis, including sewage and wastewater treatment facilities, microwave sludge concentration online monitoring, sewage water quality and quantity online monitoring, and a sludge flow meter and a dosing flow meter;

[0008] The sewage and wastewater treatment facility is connected to a sludge storage tank, a concentration tank or a conditioning tank through a sludge pipe, and then connected to a dehydration device;

[0009] The sewage water quality and quantity online monitoring is a water quality and quantity monitoring facility installed in the pre-treatment part and the deep treatment part of the sewage treatment facility;

[0010] Between the pretreatment part and the deep treatment part is a biochemical reaction and sedimentation tank;

[0011] The deep treatment part, the biochemical reaction and sedimentation tank, and the pretreatment part are respectively connected to the sludge storage tank, the concentration tank or the conditioning tank through the sludge pipe, and the sludge pipe connected to the sludge storage tank is provided with a sludge pump, a sludge flow meter and a microwave sludge concentration meter;

[0012] The three microwave sludge concentration meters arranged between the deep treatment part, the biochemical reaction and sedimentation tank, the pretreatment part and the sludge storage tank are used for online monitoring of the microwave sludge concentration;

[0013] The sludge pipe between the sludge storage tank and the dehydration equipment is provided with the sludge pump, the sludge flow meter and the microwave sludge concentration meter in sequence;

[0014] The dehydration equipment is connected to the dosing pump through a dosing pipe, and the microwave sludge concentration meter is provided at the sludge outlet;

[0015] The dosing pipe is provided with the dosing flow meter;

[0016] It also includes a big data analysis control platform that connects each of the water quality and quantity monitoring facilities, each of the sludge pumps, each of the sludge flow meters, each of the microwave sludge concentration meters, the dehydration equipment, the dosing pumps, and the dosing flow meters through communication cables;

[0017] The big data analysis and control platform analyzes and calculates the data obtained from the communication cable and then performs control, specifically:

[0018] Step 1: The big data analysis control platform obtains the previous data accumulation;

[0019] The previous data accumulation is historical data or data obtained by simulation of the mechanism model formula 2, specifically including:

[0020] The water volume, SS, pH / ORP, BOD, COD, NH3-N, TP, TN of the inlet / outlet water of each part of the sewage treatment facility,

[0021] The operating status, frequency, and power of the dosing pump, the dehydration equipment, and each of the sludge pumps,

[0022] The instantaneous value of each of the microwave sludge concentration meters and each of the sludge flow meters;

[0023] Step 2: Establish a basic database and store the accumulated early data into the basic database;

[0024] Step 3, searching the basic database to determine whether each set of data is complete; if any set of data has missing values, searching for the next set of data; if any set of data is complete, executing subsequent steps for each complete set of data;

[0025] Step 4: Search the basic database and make distortion and compliance judgments on each complete set of data;

[0026] Step 5: Establish a valid database, and store all the data that are complete and have passed the distortion and compliance judgment into the valid database;

[0027] Step 6: Perform data preprocessing and data dimension reduction on all the data in the valid database;

[0028] Step 7: Perform cluster analysis and association rule analysis;

[0029] Step 8: Establish a machine learning operation model through big data analysis and robot learning methods, and provide a variety of sludge discharge and dehydration dosing control strategies that meet the standards for effluent, sludge discharge and dehydration solid content;

[0030] Step 9: low-carbon evaluation is performed on all the mud discharge and dehydration and dosing control strategies through a low-carbon evaluation model, the carbon emission value of each mud discharge and dehydration and dosing control strategy is given, and the optimal control strategy is given;

[0031] Step 10: Run the optimal control strategy on the big data analysis control platform.

[0032] Preferably, each of the water quality and quantity monitoring facilities is arranged in the corresponding pre-treatment part or the deep treatment part through a sewage sampling pipe;

[0033] The sludge pump, the dewatering equipment, the dosing pump, the sludge flow meter arranged on the sludge pipe between the sludge pump and the dewatering equipment, the microwave sludge concentration meter, the sludge flow meter arranged on the dosing pipe between the dosing pump and the dewatering equipment, and the microwave sludge concentration meter at the mud outlet of the dewatering equipment constitute an intelligent sludge discharge and dewatering dosing control module.

[0034] Preferably, each of the sludge pump and the dosing pump is a variable frequency pump.

[0035] Each of the sludge pump and the dosing pump is a variable frequency pump, which makes it easier to accurately control the amount of sludge discharged and the amount of dosing.

[0036] Preferably, the big data analysis control platform includes a hardware support layer, a data support layer and an application service layer;

[0037] The hardware support layer provides the required supporting hardware for the big data analysis control platform, including servers, storage devices, communication equipment, computers, display devices, and instruments including water quality and quantity, sludge concentration and flow rate, and dosing flow rate;

[0038] The data support layer classifies and stores the collected data, and establishes corresponding models to process, analyze, calculate and evaluate the data, including basic database, effective database, mechanism model, low-carbon assessment model and big data decision optimization control model;

[0039] The application service layer provides data display and interaction for sewage treatment plant supervisors, including calculation result display, energy-saving effect display, monitoring and management of each sludge dehydration and dosing equipment, and human-computer interaction.

[0040] Preferably, step 4 is as follows:

[0041] Step 4.1, judging whether each group of data is distorted refers to judging whether the dosage data Q0 satisfies the following formula; if not, the data is distorted data, and if it is satisfied, continue with the subsequent steps;

[0042]

[0043] Among them, Q y is the dosage value;

[0044] x% and y% are both effective judgment standard coefficients, with values ​​ranging from 10% to 50%;

[0045] Step 4.2: The specific judgment of whether each set of data meets the standard is as follows:

[0046] If one or more of the SS, pH / ORP, BOD, COD, NH3-N, TP, and TN in a set of the data at any sampling time does not meet the standard, the control strategy of the sludge pump at the previous sampling time is not desirable;

[0047] If the microwave sludge concentration meter at the sludge outlet of the dehydration equipment in a set of data at any sampling time detects that the sludge moisture content does not meet the standard, then the dosage control strategy at the previous sampling time is not advisable;

[0048] Step 4.3: Summarize the data of all groups that have passed the distortion and compliance judgments.

[0049] More preferably, the dosage value Q y The calculation is based on the mechanism model formula, as follows:

[0050]

[0051] Among them, Q y tn The instantaneous flow rate of the dosage in the time period, unit: m 3 / h;

[0052] F t is the instantaneous value of the mud flow rate of the dewatering equipment at time t, in units of: m 3 / h;

[0053] D t is the sludge concentration value of the dewatering equipment at time t, in %;

[0054] t n The dry sludge volume of the period;

[0055] D y is the concentration of the prepared drug, unit: %;

[0056] k is the dosing coefficient, which is the ratio of dry mud volume to dosing volume. The general empirical value is 3 to 5.0 and can be adjusted.

[0057] Preferably, in step 6, a discrete standardization processing method is used to perform data preprocessing on all the data in the valid database;

[0058] A random forest algorithm is used to perform data dimension reduction processing on all the data in the effective database.

[0059] Preferably, in step 7, each data object in the valid database that has completed data preprocessing and data dimension reduction is divided into m clusters, and the sum of squares of all data points in each cluster to the cluster center point of the corresponding cluster is minimized;

[0060] The Apriori algorithm is used to mine the correlation between the data after the cluster analysis is completed, and a specific classification boundary is defined for each data after the cluster analysis is completed, and then the minimum support and confidence are analyzed by the association rule analysis algorithm.

[0061] Preferably, in step 8, an LSTM model or a RNN-LSTM model is adopted, and the number of sample hidden layer units, learning rate, and number of iterations are optimized to track the equipment operation status, and based on the intelligent analysis and calculation of the real-time collected production data, a variety of sludge discharge and dehydration dosing control strategies that meet the water output and dehydration rate standards are given, including the control command of the sludge pump, the frequency control command of the sludge pump, the control command of the dosing pump, and the frequency control command of the dosing pump.

[0062] Preferably, in step 9, the control strategy with the lowest comprehensive carbon emission value is selected as the optimal control strategy given by the expert decision optimization model.

[0063] Preferably, the low-carbon assessment model converts the power consumption, drug consumption and greenhouse gas emissions of all the sludge pumps, the dehydration equipment and the dosing pumps into a comprehensive carbon emission value, and evaluates the carbon emission values ​​of various sludge discharge and dehydration dosing control strategies. The specific formula is as follows:

[0064]

[0065] Among them, CE Z It is the comprehensive carbon emission value of the dry basis of sludge treated during the period t0, in kgCO2-eq / TDS;

[0066] p is the carbon emission coefficient of electricity consumption, which is generally set to 1 and is adjustable;

[0067] q is the carbon emission coefficient of drug consumption, which is generally set to 1 and is adjustable;

[0068] r is the greenhouse gas carbon emission coefficient, which is generally set to 1 and is adjustable;

[0069] The total power consumption of all the sludge pumps, the dehydration equipment and the dosing pumps during the period t0, in Kwh;

[0070] EF n is the regional electricity emission factor, unit: kgCO2-eq / kWh;

[0071] The dry weight of sludge treated in time period t0, in TDS;

[0072] The usage of the j-th drug in time period t0, unit: m 3 ;

[0073] EF j is the emission factor of the jth agent, in kgCO2-eq / m 3 ;

[0074] CES qt It is the carbon value of greenhouse gas emissions. Greenhouse gases mainly include CO2, CH4, and N2O, kgCO2-eq. Since CO2, CH4, and N2O are difficult to measure, if the site does not have high requirements for carbon emissions, CES qt It can be ignored or the percentage of dry sludge volume can be taken according to empirical value.

[0075] Beneficial effects of the present invention:

[0076] The present invention takes the whole mud discharge and dehydration dosing system into consideration to realize intelligent optimal mud discharge and dehydration dosing, improve mud discharge and dehydration efficiency and stability, save energy and reduce consumption, and realize low-carbon operation.

[0077] The present invention establishes a big data analysis and control platform for sewage treatment plant mechanism and data fusion, starting from the overall sludge discharge, dehydration and drug addition, accurately and dynamically controls the sludge concentration and sludge dehydration drug addition, reduces the operating load and drug addition of the dehydration equipment, and achieves the effect of intelligent and low-carbon operation.

[0078] The present invention establishes a mechanism model, a low-carbon assessment model and a big data decision-making optimization control model, and realizes the deep integration of the mechanism + data model, making the intelligent low-carbon optimization control system for mud discharge and dehydration and dosing more intelligent and the control strategy more accurate;

[0079] The present invention innovatively proposes and establishes a low-carbon assessment model, implements the dual-carbon policy to the level of mud discharge and dehydration dosing control, and saves energy and reduces consumption from the bottom up, achieving low-carbon and environmental protection;

[0080] The present invention establishes a mechanism model for mud discharge and dehydration and dosing. In the early stage, relevant data can be accumulated through the operation of the model, and the model can also be used to judge whether the data is distorted and valid, which solves the problem of no data analysis and data validity judgment in the early stage of the big data decision-making optimization control model;

[0081] The present invention adopts a microwave sludge concentration meter to measure the sludge concentration online in real time at the sludge discharge pipe, dewatering machine sludge inlet pipe, sludge outlet pipe, etc. This method has high detection accuracy and reliable data, provides reliable real-time data for the big data analysis control platform, optimizes sludge discharge and reflux, saves energy and reduces consumption, and reduces the load on sludge treatment facilities.

[0082] The concept, specific structure and technical effects of the present invention will be further described below in conjunction with the accompanying drawings to fully understand the purpose, characteristics and effects of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 A schematic diagram showing the connection relationship between sewage and wastewater treatment facilities, dosing equipment, sludge storage tanks, concentration tanks or conditioning tanks and a big data analysis control platform in one embodiment of the present invention.

[0084] Figure 2 A schematic diagram of the structure of a big data analysis control platform in one embodiment of the present invention is shown.

[0085] Figure 3 A workflow diagram of a big data analysis control platform in one embodiment of the present invention is shown.

[0086] Among them, 1. Big data analysis control platform; 2. Wastewater treatment facilities; 2-1. Pretreatment part; 2-2. Biochemical reaction and sedimentation tank; 2-3. Deep treatment part; 3. Water quality and quantity monitoring facilities; 4. Sludge pump; 5. Sludge flow meter; 6. Microwave sludge concentration meter; 7. Sludge storage tank, concentration tank or conditioning tank; 8. Dehydration equipment; 9. Dosing pump; 10. Intelligent sludge discharge and dehydration dosing control module; 11. Dosing flow meter; 12. Sludge pipe ; 13. Dosing pipe; 14. Communication cable; 101. Server; 102. Storage device; 103. Communication equipment; 104. Computer; 105. Display device; 111. Basic database; 112. Effective database; 113. Mechanism model; 114. Low-carbon assessment model; 115. Big data decision-making optimization control model; 121. Calculation result display; 122. Energy-saving effect display; 123. Monitoring management; 124. Human-computer interaction. DETAILED DESCRIPTION

[0087] Example

[0088] like Figure 1 and Figure 3 As shown, the intelligent sludge discharge and dehydration and dosing control system of the sewage plant based on big data analysis includes sewage and wastewater treatment facilities 2, microwave sludge concentration online monitoring, sewage water quality and quantity online monitoring. The two features are in red fonts in the following text, as well as sludge flowmeter 5 and dosing flowmeter 11;

[0089] The sewage and wastewater treatment facility 2 is connected to the sludge storage tank, the concentration tank or the conditioning tank 7 through the sludge pipe 12, and then connected to the dehydration equipment 8;

[0090] The online monitoring of sewage water quality and quantity is a water quality and quantity monitoring facility 3 installed in the pre-treatment part 2-1 and the deep treatment part 2-3 of the sewage treatment facility 2;

[0091] Between the pretreatment part 2-1 and the deep treatment part 2-3 is a biochemical reaction and sedimentation tank 2-2;

[0092] The deep treatment part 2-3, the biochemical reaction and sedimentation tank 2-2, and the pretreatment part 2-1 are respectively connected to the sludge storage tank, the concentration tank or the conditioning tank 7 through the sludge pipe 12, and the sludge pipe 12 connected to the sludge storage tank, the concentration tank or the conditioning tank 7 is provided with a sludge pump 4, a sludge flow meter 5 and a microwave sludge concentration meter 6;

[0093] Three microwave sludge concentration meters 6 arranged between the deep treatment part 2-3, the biochemical reaction and sedimentation tank 2-2, the pretreatment part 2-1 and the sludge storage tank, the concentration tank or the conditioning tank 7 are used for online monitoring of microwave sludge concentration;

[0094] The sludge pipe 12 between the sludge storage tank, the concentration tank or the conditioning tank 7 and the dehydration equipment 8 is provided with a sludge pump 4, a sludge flow meter 5 and a microwave sludge concentration meter 6 in sequence;

[0095] The dehydration equipment 8 is connected to the dosing pump 9 through the dosing pipe 13, and a microwave sludge concentration meter 6 is provided at the sludge outlet;

[0096] The dosing pipe 13 is provided with a dosing flow meter 11;

[0097] It also includes a big data analysis control platform 1 connected to each water quality and quantity monitoring facility 3, each sludge pump 4, each sludge flow meter 5, each microwave sludge concentration meter 6, dehydration equipment 8, dosing pump 9 and dosing flow meter 11 through a communication cable 14;

[0098] The big data analysis control platform 1 analyzes and calculates the data obtained from the communication cable 14 and then performs control, specifically:

[0099] Step 1: The big data analysis control platform 1 obtains the previous data accumulation;

[0100] The previous data accumulation is historical data or data obtained through simulation of the mechanism model formula 2, including:

[0101] The amount of inlet / outlet water, SS, pH / ORP, BOD, COD, NH3-N, TP, TN of each part of the sewage and wastewater treatment facility 2,

[0102] The operating status, frequency and power of the dosing pump 9, the dewatering equipment 8 and each sludge pump 4,

[0103] The instantaneous value of each microwave sludge concentration meter 6 and each sludge flow meter 5;

[0104] Step 2: Establish a basic database and store the previous data accumulation into the basic database;

[0105] Step 3: Search the basic database to determine whether each set of data is complete; if any set of data has missing values, search for the next set of data; if any set of data is complete, perform subsequent steps on each complete set of data;

[0106] Step 4: Search the basic database and make distortion and compliance judgments for each complete set of data;

[0107] Step 5: Establish a valid database, and store all group data that are complete and have passed the distortion and compliance judgment into the valid database;

[0108] Step 6: Perform data preprocessing and data dimension reduction on all data in the valid database;

[0109] Step 7: Perform cluster analysis and association rule analysis;

[0110] Step 8: Establish a machine learning operation model through big data analysis and robot learning methods, and provide a variety of sludge discharge and dehydration dosing control strategies that meet the standards for effluent, sludge discharge and dehydration solid content;

[0111] Step 9: Conduct low-carbon evaluation on all sludge discharge and dehydration and dosing control strategies through the low-carbon evaluation model, give the carbon emission value of each sludge discharge and dehydration and dosing control strategy, and give the optimal control strategy;

[0112] Step 10: Run the completed big data decision optimization control model, i.e., the optimal control strategy, on the big data analysis control platform 1.

[0113] In the present invention, the water quality and quantity monitoring facilities 3, the sludge pump 4, the sludge flow meter 5, the microwave sludge concentration meter 6, the dehydration equipment 8 and the dosing pump 9 are connected to the big data analysis control platform 1 through the communication cable 14. The big data analysis control platform 1 analyzes and calculates the obtained data and then controls it to meet the needs of smart and low-carbon operation.

[0114] The big data analysis and control platform 1 realizes advanced control that integrates mechanism and mathematics through data preprocessing, data dimensionality reduction, cluster analysis, association rule analysis, machine learning operation model construction and expert decision-making optimization model, while integrating mechanism model and low-carbon assessment model.

[0115] In practical applications, the sludge discharge concentration is detected by a microwave sludge concentration meter 6 and then discharged into a sludge storage tank, a concentration tank or a conditioning tank 7 .

[0116] The dehydration device 8 and the dosing pump 9 are controlled according to the data collected by the microwave sludge concentration meter 6 and the sludge flow meter 5 between the dehydration device 8 and the sludge storage tank, concentration tank or conditioning tank 7, and the accurate dry basis amount of sludge treatment is calculated by the microwave sludge concentration meter 6 and the sludge flow meter 5, which serves as an important basis for dehydration and dosing;

[0117] The big data analysis control platform 1 discharges sludge on demand according to the sludge concentration collected by the microwave sludge concentration meter 6, which can reduce the load of the subsequent sludge pump 4, sludge storage tank, concentration tank or conditioning tank 7 and dehydration equipment 8, thereby extending the service life of these equipment and reducing energy consumption;

[0118] The microwave sludge concentration meter 6 installed at the sludge outlet of the dewatering equipment 8 monitors in real time whether the solid content of the dewatered sludge meets the requirements, and feeds back to the big data analysis control platform 1 to form a closed loop;

[0119] The sludge flow meter 5 arranged on the dosing pipe 13 is used to monitor the dosing flow rate, so as to realize the precise control of the dosing amount of the dosing pump 9 by the big data analysis control platform 1 .

[0120] The present invention continuously optimizes and realizes precise control of sludge discharge and dehydration dosing through basic mathematical models combined with historical operation and control data analysis. By accurately monitoring the sludge concentration online in real time, the sludge discharge and dehydration dosing are controlled by the absolute dry sludge volume (the product of concentration and flow rate). The moisture content of sludge discharge and dehydrated sludge can be stabilized, and the sludge discharge, reflux volume, processing volume, dosage, energy consumption and labor consumption for sampling and testing of the entire plant can be reduced, thereby saving energy, reducing consumption, reducing pollution and reducing carbon emissions.

[0121] In some embodiments, each water quality and quantity monitoring facility 3 is arranged in the corresponding pre-treatment part 2-1 or deep treatment part 2-3 through a sewage sampling pipe 11;

[0122] The sludge pump 4, the dewatering equipment 8, the dosing pump 9, the sludge flow meter 5 arranged on the sludge pipe 12 between the sludge pump 4 and the dewatering equipment 8, the microwave sludge concentration meter 6, the sludge flow meter 5 arranged on the dosing pipe 13 between the dosing pump 9 and the dewatering equipment 8, and the microwave sludge concentration meter 6 at the mud outlet of the dewatering equipment 8 constitute an intelligent sludge discharge and dewatering dosing control module 10.

[0123] In some embodiments, each of the sludge pump 4 and the dosing pump 9 is a variable frequency pump.

[0124] Each sludge pump 4 and dosing pump 9 is a variable frequency pump, which makes it easier to accurately control the amount of sludge discharged and the amount of dosing.

[0125] In practical applications, the starting sludge concentration D of each sludge pump 4 is Q , pump stop concentration D Z It can be set manually or calculated through the big data analysis control platform.

[0126] Pump start sludge concentration D Q , pump stop concentration D Z It varies according to the scale and process of the sewage treatment plant. It can also be formulated based on the total designed sludge volume of the plant and the sludge concentration at each location can be reversely calculated.

[0127] Pump start sludge concentration D Q For every 0.1% increase or decrease in TDS, the sludge pump control frequency increases or decreases m accordingly. m is generally 1 Hz to 3 Hz. The m value can be set manually or calculated by the big data analysis control platform 1.

[0128] like Figure 2 As shown, in some embodiments, the big data analysis control platform 1 includes a hardware support layer, a data support layer and an application service layer;

[0129] The hardware support layer provides the required supporting hardware for the big data analysis control platform 1, including a server 101, a storage device 102, a communication device 103, a computer 104, a display device 105, and instruments including water quality and quantity, sludge concentration and flow rate, and dosing flow rate;

[0130] The data support layer classifies and stores the collected data, and establishes corresponding models to process, analyze, calculate and evaluate the data, including basic database 111, effective database 112, mechanism model 113, low-carbon assessment model 114 and big data decision optimization control model 115;

[0131] The application service layer provides data display and interaction for sewage treatment plant supervisors, including calculation result display 121, energy-saving effect display 122, monitoring and management of each sludge dehydration and dosing equipment 123, and human-computer interaction 124.

[0132] In some embodiments, step 4 is as follows:

[0133] Step 4.1, whether each set of data is distorted refers to judging whether the dosage data Q0 satisfies the following formula; if not, the data is distorted data, if satisfied, continue with the subsequent steps;

[0134]

[0135] Among them, Q y is the dosage value;

[0136] x% and y% are both effective judgment standard coefficients, with values ​​ranging from 10% to 50%;

[0137] Step 4.2: The specific judgment of whether each set of data meets the standard is as follows:

[0138] If one or more of SS, pH / ORP, BOD, COD, NH3-N, TP, and TN in a set of data at any sampling time does not meet the standard, the control strategy of sludge pump 4 at the previous sampling time is not desirable;

[0139] If the microwave sludge concentration meter 6 at the mud outlet of the dehydration equipment 8 detects that the sludge moisture content does not meet the standard in a set of data at any sampling time, then the dosage control strategy at the previous sampling time is not advisable;

[0140] Step 4.3: Summarize all group data that have passed the distortion and compliance judgments.

[0141] In practical applications, the interval between every two adjacent sampling moments can be set according to requirements.

[0142] In some embodiments, the dosage value Q y The calculation is based on the mechanism model formula, as follows:

[0143]

[0144] Among them, Q y t n The instantaneous flow rate of the dosage in the time period, unit: m 3 / h;

[0145] F t is the instantaneous value of the mud flow rate of dewatering equipment 8 at time t, in m 3 / h;

[0146] D t is the sludge concentration value of the dewatering equipment 8 at time t, in %;

[0147] t n The dry sludge volume of the period;

[0148] D y is the concentration of the prepared drug, unit: %;

[0149] k is the dosing coefficient, which is the ratio of dry mud volume to dosing volume. The general empirical value is 3 to 5.0 and can be adjusted.

[0150] In some embodiments, in step 6, all data in the valid database are preprocessed using a discrete standardization processing method;

[0151] The random forest algorithm is used to perform data dimension reduction on all data in the valid database.

[0152] In practical applications, the use of discrete standardization processing to preprocess all data in the effective database can eliminate the impact of differences in the dimensions and value ranges of various production parameters;

[0153] The random forest algorithm is a commonly used big data modeling method for data dimensionality reduction.

[0154] In some embodiments, in step 7, each data object in the valid database that has completed data preprocessing and data dimension reduction is divided into m clusters, and the sum of squares of all data points in each cluster to the cluster center point of the corresponding cluster is minimized;

[0155] The Apriori algorithm is used to mine the correlation between the data after the cluster analysis is completed, and specific classification boundaries are defined for each data after the cluster analysis is completed. Then the minimum support and confidence are analyzed through the association rule analysis algorithm.

[0156] In some embodiments, in step 8, an LSTM model or a RNN-LSTM model is used, and the number of sample hidden layer units, learning rate, and number of iterations are optimized to track the equipment operation status, and based on the real-time collection of production data, intelligent analysis and calculation are performed to provide a variety of sludge discharge and dehydration dosing control strategies that meet the water output and dehydration rate standards, including control commands for the sludge pump 4, frequency control commands for the sludge pump 4, control commands for the dosing pump 9, and frequency control commands for the dosing pump 9.

[0157] In some embodiments, in step 9, the control strategy with the lowest comprehensive carbon emission value is selected as the optimal control strategy given by the expert decision optimization model.

[0158] In some embodiments, the low-carbon assessment model converts the power consumption, drug consumption and greenhouse gas emissions of all sludge pumps 4, dewatering equipment 8 and dosing pumps 9 into a comprehensive carbon emission value, and evaluates the carbon emission value of various sludge discharge and dewatering dosing control strategies. The specific formula is as follows:

[0159]

[0160] Among them, CE Z It is the comprehensive carbon emission value of the dry basis of sludge treated during the period t0, in kgCO2-eq / TDS;

[0161] p is the carbon emission coefficient of electricity consumption, which is generally set to 1 and is adjustable;

[0162] q is the carbon emission coefficient of drug consumption, which is generally set to 1 and is adjustable;

[0163] r is the greenhouse gas carbon emission coefficient, which is generally set to 1 and is adjustable;

[0164] It is the total power consumption of all sludge pumps 4, dehydration equipment 8 and dosing pumps 9 during the period t0, in Kwh;

[0165] EF n is the regional electricity emission factor, unit: kgCO2-eq / kWh;

[0166] The dry weight of sludge treated in time period t0, in TDS;

[0167] The usage of the j-th drug in time period t0, unit: m 3 ;

[0168] EF j is the emission factor of the jth agent, in kgCO2-eq / m 3 ;

[0169] CESqt It is the carbon value of greenhouse gas emissions. Greenhouse gases mainly include CO2, CH4, and N2O, kgCO2-eq. Since CO2, CH4, and N2O are difficult to measure, if the site does not have high requirements for carbon emissions, CES qt It can be ignored or the percentage of dry sludge volume can be taken according to empirical value.

[0170] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. Intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis, characterized in that: It comprises a big data analysis control platform (1) connected to each water quality and quantity monitoring facility (3), each sludge pump (4), each sludge flow meter (5), each microwave sludge concentration meter (6), a dehydration device (8), a dosing pump (9) and a dosing flow meter (11) via a communication cable (14); The big data analysis control platform (1) analyzes and calculates the data obtained from the communication cable (14) and then performs control, specifically: Step 1, the big data analysis control platform (1) obtains the previous data accumulation; The previous data accumulation is historical data or data obtained by simulation of the mechanism model formula 2, specifically including: (2) The amount of inlet / outlet water, SS, pH / ORP, BOD, COD, NH3-N, TP, TN of each part of sewage and wastewater treatment facilities. the operating status, frequency, and power of the dosing pump (9), the dehydration device (8), and each of the sludge pumps (4), The instantaneous value of each of the microwave sludge concentration meters (6) and each of the sludge flow meters (5); Step 2: Establish a basic database and store the accumulated early data into the basic database; Step 3, searching the basic database to determine whether each set of data is complete; if any set of data has missing values, searching for the next set of data; if any set of data is complete, executing subsequent steps for each complete set of data; Step 4: Search the basic database and make distortion and compliance judgments on each complete set of data; Step 5: Establish a valid database, and store all the data that are complete and have passed the distortion and compliance judgment into the valid database; Step 6: Perform data preprocessing and data dimension reduction on all the data in the valid database; Step 7: Perform cluster analysis and association rule analysis; Step 8: Establish a machine learning operation model through big data analysis and robot learning methods, and provide a variety of sludge discharge and dehydration dosing control strategies that meet the standards for effluent, sludge discharge and dehydration solid content; Step 9: low-carbon evaluation is performed on all the mud discharge and dehydration and dosing control strategies through a low-carbon evaluation model, the carbon emission value of each mud discharge and dehydration and dosing control strategy is given, and the optimal control strategy is given; Step 10: Run the optimal control strategy on the big data analysis control platform (1).

2. According to the intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 1, it is characterized in that: It also includes sewage and wastewater treatment facilities (2), microwave sludge concentration online monitoring, sewage water quality and quantity online monitoring, as well as a sludge flow meter (5) and a dosing flow meter (11); The sewage and wastewater treatment facility (2) is connected to a sludge storage tank, a concentration tank or a conditioning tank (7) through a sludge pipe (12), and then connected to a dehydration device (8); The sewage water quality and quantity online monitoring is a water quality and quantity monitoring facility (3) installed in the pre-treatment part (2-1) and the deep treatment part (2-3) of the sewage treatment facility (2); Between the pretreatment part (2-1) and the deep treatment part (2-3) is a biochemical reaction and sedimentation tank (2-2); The deep treatment part (2-3), the biochemical reaction and sedimentation tank (2-2), and the pretreatment part (2-1) are respectively connected to the sludge storage tank, the concentration tank or the conditioning tank (7) through the sludge pipe (12), and the sludge pipe (12) connected to the sludge storage tank, the concentration tank or the conditioning tank (7) is provided with a sludge pump (4), a sludge flow meter (5) and a microwave sludge concentration meter (6); The three microwave sludge concentration meters (6) arranged between the deep treatment part (2-3), the biochemical reaction and sedimentation tank (2-2), the pretreatment part (2-1) and the sludge storage tank, the concentration tank or the conditioning tank (7) are used for online monitoring of the microwave sludge concentration; The sludge pipe (12) between the sludge storage tank, the concentration tank or the conditioning tank (7) and the dehydration equipment (8) is provided with the sludge pump (4), the sludge flow meter (5) and the microwave sludge concentration meter (6) in sequence; The dehydration equipment (8) is connected to the dosing pump (9) via a dosing pipe (13), and the microwave sludge concentration meter (6) is provided at the sludge outlet; The drug adding pipe (13) is provided with the drug adding flow meter (11).

3. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 2 is characterized in that: Each of the water quality and quantity monitoring facilities (3) is arranged in the corresponding pre-treatment part (2-1) or the deep treatment part (2-3) through a sewage sampling pipe (11); The sludge pump (4), the dewatering device (8), the dosing pump (9), the sludge flow meter (5) arranged on the sludge pipe (12) between the sludge pump (4) and the dewatering device (8), the microwave sludge concentration meter (6), the sludge flow meter (5) arranged on the dosing pipe (13) between the dosing pump (9) and the dewatering device (8), and the microwave sludge concentration meter (6) at the mud outlet of the dewatering device (8) constitute an intelligent sludge discharge and dewatering dosing control module (10).

4. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 2 is characterized in that: Each of the sludge pump (4) and the dosing pump (9) is a variable frequency pump. Each of the sludge pump (4) and the dosing pump (9) is a variable frequency pump, which makes it easier to accurately control the amount of sludge discharged and the amount of dosing.

5. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 2 is characterized in that: The big data analysis control platform (1) comprises a hardware support layer, a data support layer and an application service layer; The hardware support layer provides the required supporting hardware for the big data analysis control platform (1), including a server (101), a storage device (102), a communication device (103), a computer (104), a display device (105), and instruments including water quality and quantity, sludge concentration and flow rate, and dosing flow rate; The data support layer classifies and stores the collected data, and establishes corresponding models to process, analyze, calculate and evaluate the data, including a basic database (111), an effective database (112), a mechanism model (113), a low-carbon assessment model (114) and a big data decision optimization control model (115); The application service layer provides data display and interaction for sewage treatment plant supervisors, including calculation result display (121), energy-saving effect display (122), monitoring and management of each sludge dehydration and dosing equipment (123), and human-computer interaction (124).

6. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 2 is characterized in that: Step 4 is as follows: Step 4.1, judging whether each group of data is distorted refers to judging whether the dosage data Q0 satisfies the following formula; if not, the data is distorted data, and if it is satisfied, continue with the subsequent steps; Among them, Q y is the dosage value; x% and y% are both effective judgment standard coefficients, with values ​​ranging from 10% to 50%; Step 4.2: The specific judgment of whether each set of data meets the standard is as follows: If at any sampling time, one or more of the SS, pH / ORP, BOD, COD, NH3-N, TP, and TN data do not meet the standards, then the control strategy of the sludge pump (4) at the previous sampling time is not desirable; If the microwave sludge concentration meter (6) at the sludge outlet of the dehydration equipment (8) in any of the data at the sampling time detects that the sludge moisture content does not meet the standard, then the dosage control strategy at the previous sampling time is not advisable; Step 4.3: Summarize the data of all groups that have passed the distortion and compliance judgments.

7. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 6 is characterized in that: The dosage value Q y The calculation is based on the mechanism model formula, as follows: Among them, Q y t n The instantaneous flow rate of the dosage in the time period, unit: m 3 / h; F t is the instantaneous value of the mud flow rate of the dewatering device (8) at time t, in units of m 3 / h; D t is the sludge concentration value of the dewatering device (8) at time t, in units of %; t n The dry sludge volume of the period; D y is the concentration of the prepared drug, unit: %; k is the dosing coefficient, which is the ratio of dry mud volume to dosing volume. The general empirical value is 3 to 5.0 and can be adjusted.

8. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 1 is characterized in that: In step 6, all the data in the valid database are preprocessed using a discrete standardization processing method; A random forest algorithm is used to perform data dimension reduction processing on all the data in the effective database.

9. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 1 is characterized in that: In step 7, each data object in the valid database that has completed data preprocessing and data dimension reduction is divided into m clusters, and the sum of squares of all data points in each cluster to the cluster center point of the corresponding cluster is minimized; The Apriori algorithm is used to mine the correlation between the data after the cluster analysis is completed, and a specific classification boundary is defined for each data after the cluster analysis is completed, and then the minimum support and confidence are analyzed by the association rule analysis algorithm.

10. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 1 is characterized in that: In step 8, an LSTM model or an RNN-LSTM model is used, and the number of hidden layer units, learning rate, and iteration times of the sample are optimized, the equipment operation status is tracked, and based on the intelligent analysis and calculation of the real-time collected production data, a plurality of sludge discharge and dehydration dosing control strategies that meet the water discharge and dehydration rate standards are given, including the control command of the sludge pump (4), the frequency control command of the sludge pump (4), the control command of the dosing pump (9), and the frequency control command of the dosing pump (9).

11. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 1 is characterized in that: In step 9, the control strategy with the lowest comprehensive carbon emission value is selected as the optimal control strategy given by the expert decision optimization model.

12. The intelligent sludge discharge and dehydration dosing control system for sewage treatment plants based on big data analysis according to claim 1 is characterized in that: The low-carbon assessment model converts the power consumption, drug consumption and greenhouse gas emissions of all the sludge pumps (4), the dewatering equipment (8) and the dosing pumps (9) into a comprehensive carbon emission value, and evaluates the carbon emission values ​​of various sludge discharge and dewatering dosing control strategies. The specific formula is as follows: Among them, CE Z It is the comprehensive carbon emission value of the dry basis of sludge treated during the period t0, in kgCO2-eq / TDS; p is the carbon emission coefficient of electricity consumption, which is generally set to 1 and is adjustable; q is the carbon emission coefficient of drug consumption, which is generally set to 1 and is adjustable; r is the greenhouse gas carbon emission coefficient, which is generally set to 1 and is adjustable; is the total power consumption of all the sludge pumps (4), the dehydration equipment (8) and the dosing pump (9) during the period t0, in Kwh; EF n is the regional electricity emission factor, unit: kgCO2-eq / kWh; The dry weight of sludge treated in time period t0, in TDS; The usage of the j-th drug in time period t0, unit: m 3 ; EF j is the emission factor of the jth agent, in kgCO2-eq / m 3 ; CES qt It is the carbon value of greenhouse gas emissions. Greenhouse gases mainly include CO2, CH4, and N2O, kgCO2-eq. Since CO2, CH4, and N2O are difficult to measure, if the site does not have high requirements for carbon emissions, CES qt Can be ignored, or Take the percentage of dry sludge volume according to experience.

Images