Automated sludge treatment method, device, computer equipment and storage medium
By collecting sludge parameters and evaluating fluidity, using machine learning and deep learning algorithms to generate chemical agent delivery instructions, the problem of automated chemical agent delivery in sludge treatment is solved, the treatment efficiency is improved, the cost is reduced, and chemical agent is realized Optimal state used.
Patent Information
- Application Number
- CN202411089389.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-09
AI Technical Summary
The failure of existing sludge treatment technologies to achieve automated chemical agent dosing results in low treatment efficiency and high cost, especially in complex or highly variable sludge treatments.
By collecting sludge parameters, calculating the total sludge quality and evaluating fluidity, using machine learning and deep learning algorithms to generate chemical agent delivery instructions, realize automated chemical agent administration and optimize chemical agent usage and energy consumption.
It improves the efficiency and reliability of sludge treatment, reduces operating costs and environmental impact, reduces dependence on complex mechanical equipment, achieves the optimal state of chemical agent use, and adapts to different sludge treatment needs and environmental changes.
Smart Images

Figure CN118619505B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of environmental protection treatment technology, and in particular to an automated sludge treatment method, device, computer equipment and storage medium. Background Art
[0002] Sludge treatment technology is the technology for treating aqueous sludge generated in water treatment plants, sewage treatment plants and various industrial production processes. These technologies are mainly aimed at reducing the amount of sludge, reducing the water content, eliminating harmful components in sludge, and recovering useful substances through various physical, chemical and biological methods. With the increasing demand for resource recycling, sludge treatment technology is becoming an important research direction in the field of environmental engineering and waste management.
[0003] Some technologies, such as the announcement number CN112661367B, provide a control method for a pipeline sludge treatment system, which involves using sensors to monitor the operating status of the equipment and adjust the operating parameters to optimize the treatment effect. The system includes a garbage sorter, a vibrating sand sorter, and a sludge dewatering machine. The changes in the input sludge are responded to by adjusting the filter screen speed of the garbage sorter and the vibration frequency of the vibrating sand sorter in real time. In addition, it also includes adjusting the operating parameters of the sludge dewatering machine and adjusting the dosage of the flocculation tank according to the flocculation state. Some other technologies, such as the publication number CN107298516A, describe a sludge treatment control system that uses a central neural network to control the host for unmanned control. The system includes multiple subsystems, such as 3D virtual human-computer interaction, intelligent sensor networks, computer sensory processing, monitoring and early warning, and working robots. Although this system can realize automated operation and reduce human intervention, it is highly dependent on advanced AI technology and hardware facilities, and faces the problems of high cost and complex maintenance. Some other technologies, such as publication number CN114634287A, provide an adaptive control method and system for sludge treatment, which determines the target control conditions by analyzing the quality indicators in the sludge treatment report and adapts to the changes in sludge quality by adjusting the treatment parameters. It is highly dependent on the sludge quality indicators and still needs further optimization when treating complex or highly variable sludge.
[0004] Although the above-mentioned related technologies have provided some sludge treatment solutions, there are still some defects and limitations. For example, although the pipeline sludge treatment system can adjust the operating parameters in real time, it may lack sufficient intelligent technology to fully optimize the entire treatment process. Although the unmanned artificial intelligence control system has achieved unmanned control, the complexity and high cost of the system may limit its application in small or resource-limited facilities. Although the adaptive control method improves the flexibility of treatment, it may still need further optimization when treating complex or highly variable sludge.
[0005] In summary, the above technologies have failed to achieve the purpose of automated sludge treatment by automatically adding chemical reagents. Summary of the invention
[0006] In view of this, the present invention provides an automated sludge treatment method, device, computer equipment and storage medium to solve the problem of chemical agent addition in the sludge treatment process that cannot be automated.
[0007] In a first aspect, the present invention provides an automated sludge treatment method, the method comprising:
[0008] Collect sludge parameters during sludge treatment;
[0009] Calculate the total sludge mass and evaluate the sludge fluidity based on sludge parameters;
[0010] Predict the current sludge treatment status based on sludge parameters, total sludge mass and sludge fluidity, and generate chemical agent injection instructions;
[0011] During the sludge treatment process, corresponding chemicals are added based on the chemical addition instructions.
[0012] The automated sludge treatment method provided by the present invention collects sludge parameters in the sludge treatment process; calculates the total sludge mass and evaluates the sludge fluidity based on the sludge parameters; predicts the current sludge treatment state based on the sludge parameters, the total sludge mass and the sludge fluidity, and generates chemical agent dosing instructions; during the sludge treatment process, corresponding chemicals are respectively dosed based on the chemical agent dosing instructions, thereby realizing automated determination of the dosing of chemicals in the sludge treatment process, being able to accurately grasp the dosing time and dosing amount of chemicals according to the chemical agent dosing instructions, thereby ensuring that the use of chemicals is always in an optimal state and avoiding overdosage or underdosage, while improving the energy efficiency of the sewage treatment process and solving the problem of not being able to automatically dosing chemicals in the sludge treatment process.
[0013] In an optional embodiment, the sludge parameters include chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters;
[0014] Before calculating the sludge quality based on the sludge parameters and evaluating the sludge fluidity, the automated sludge treatment method also includes:
[0015] Data preprocessing including data cleaning and data formatting was performed on chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters.
[0016] The automated sludge treatment method provided by the present invention performs data cleaning and data formatting on chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters, removes abnormal values in sludge parameters, fills in missing data values, and ensures the accuracy of sludge parameters.
[0017] In an optional embodiment, the sludge parameter also includes the mass of a preset sludge sample;
[0018] Calculation of total sludge mass based on sludge parameters includes:
[0019] Calculate sludge volume using the volumetric method or an estimate based on wastewater flow and sludge concentration;
[0020] Calculate sludge density based on sludge volume and mass of a pre-set sludge sample;
[0021] The dry solids content of the pre-set sludge sample was calculated using the oven drying method;
[0022] The total sludge mass is calculated based on the sludge volume, sludge density and dry solids content of a pre-determined sludge sample.
[0023] The automated sludge treatment method provided by the present invention calculates the total sludge mass based on the sludge volume, sludge density and dry solid content in a preset sludge sample, thereby ensuring the accuracy and timeliness of the sludge mass calculation and providing a data basis for subsequent evaluation of the current sludge treatment process status.
[0024] In an optional embodiment, the sludge parameters further include sludge concentration, yield stress and activation energy parameters;
[0025] Assessment of sludge flowability based on sludge parameters includes:
[0026] Calculate the sludge plastic viscosity based on the sludge concentration;
[0027] Calculate the sludge shear stress at a preset shear rate based on the sludge plastic viscosity and yield stress;
[0028] Calculate the sludge viscosity at a preset temperature based on temperature parameters and activation energy parameters;
[0029] Sludge fluidity is evaluated based on sludge shear stress at a preset shear rate and sludge viscosity at a preset temperature.
[0030] The automated sludge treatment method provided by the present invention evaluates sludge fluidity based on the sludge shear stress at a preset shear rate and the sludge viscosity at a preset temperature, thereby grasping the flow properties of the sludge in real time and providing a data basis for subsequent evaluation of the current sludge treatment process status.
[0031] In an optional embodiment, the current sludge treatment state is predicted based on sludge parameters, sludge quality and sludge fluidity, and multiple chemical agent delivery instructions are generated, including:
[0032] Calculate the moving average, standard deviation and coefficient of variation of sludge parameters, and use the moving average, standard deviation and coefficient of variation as parameter characteristic values;
[0033] Use machine learning algorithms to analyze the data time series of parameter eigenvalues;
[0034] Evaluate the current sludge treatment status based on data time series, sludge quality and sludge fluidity;
[0035] Based on the current sludge treatment status, a deep learning network based on the improved AlphaGo algorithm is used to predict changes in sewage treatment and generate prediction results;
[0036] Based on the prediction results, chemical agent delivery instructions are generated.
[0037] The automated sludge treatment method provided by the present invention generates chemical agent dosing instructions that optimize the use of chemical agents and energy consumption, and reduces operating costs and environmental impacts by accurately controlling the dosage of agents and energy use. The intelligent capabilities of the system ensure that the use of chemical agents is always in the optimal state, avoiding overdosage or underdosage, while improving the energy efficiency of the treatment process, reducing dependence on complex mechanical equipment, and using software and algorithms to implement most functions, reducing initial equipment investment and long-term maintenance costs.
[0038] In an optional embodiment, before generating a chemical agent delivery instruction based on the prediction result, the automated sludge treatment method further includes:
[0039] The predicted results are compared with the actual sewage treatment to obtain the result difference. Based on the result difference, the deep learning network improved based on the AlphaGo algorithm is optimized to obtain the optimized deep learning network.
[0040] The automated sludge treatment method provided by the present invention compares the predicted result with the actual sewage treatment to obtain the result difference, and optimizes the deep learning network improved based on the AlphaGo algorithm based on the result difference to obtain the optimized deep learning network, thereby realizing adaptive optimization of the deep learning network improved based on the AlphaGo algorithm, improving the prediction accuracy of the deep learning network, and further improving the accuracy of generating chemical agent delivery instructions, which can ensure that the use of chemicals is always in the optimal state, and the self-learning ability enables the treatment effect to be continuously optimized over time, and can adapt to different sludge treatment needs and environmental changes.
[0041] In an optional embodiment, the optimized deep learning network includes an input layer, a first convolutional layer, a first batch normalization layer, a first activation layer, a first long short-term memory network layer, a first fully connected layer and an output layer connected in sequence;
[0042] Based on the prediction results, the chemical agent delivery instructions are generated including:
[0043] Input the prediction results to the input layer of the optimized deep learning network, perform deep learning in the first convolutional layer, the first batch normalization layer, the first activation layer, the first long short-term memory network layer, and the first fully connected layer in sequence, and transmit the deep learning results to the output layer;
[0044] Based on the deep learning results, a normalized function is used to obtain the probability distribution of various chemical dosage schemes;
[0045] Based on the probability distribution, AI decision function is used to select the chemical agent delivery plan with the highest probability;
[0046] Generate chemical agent delivery instructions based on the chemical agent delivery plan with the highest probability.
[0047] The automated sludge treatment method provided by the present invention ultimately automatically generates chemical agent dosing instructions by optimizing the neural network and the AI decision function, providing an instruction basis for the subsequent dosing of corresponding chemicals according to the chemical agent dosing instructions, which not only improves the efficiency and reliability of sludge treatment, but also reduces operating costs.
[0048] In a second aspect, the present invention provides an automated sludge treatment device, the device comprising:
[0049] Data acquisition module, used to collect sludge parameters during sludge treatment;
[0050] A data processing module for calculating the total mass of sludge based on sludge parameters and evaluating sludge fluidity;
[0051] AI decision-making module, used to predict the current sludge treatment status based on sludge parameters, total sludge mass and sludge fluidity, and generate chemical agent delivery instructions;
[0052] The execution module is used to add corresponding chemicals based on the chemical addition instructions during the sludge treatment process.
[0053] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the automated sludge treatment method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.
[0054] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the automated sludge treatment method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0056] Figure 1 is a schematic flow chart of an automated sludge treatment method according to an embodiment of the present invention;
[0057] Figure 2 is a schematic flow chart of another automated sludge treatment method according to an embodiment of the present invention;
[0058] Figure 3 is a schematic flow chart of another automated sludge treatment method according to an embodiment of the present invention;
[0059] Figure 4 is a structural block diagram of an automated sludge treatment device according to an embodiment of the present invention;
[0060] Figure 5 is a structural block diagram of another automated sludge treatment device according to an embodiment of the present invention;
[0061] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution 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 described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0063] According to an embodiment of the present invention, an embodiment of an automated sludge treatment method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0064] In this embodiment, an automated sludge treatment method is provided, which can be used in computers, servers, etc. Figure 1 is a flow chart of an automated sludge treatment method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:
[0065] Step S101, collecting sludge parameters during the sludge treatment process.
[0066] Specifically, a data acquisition module containing multiple sensors is used to monitor and collect sludge parameters such as chemical composition, temperature, pH value, biochemical oxygen demand and chemical oxygen demand in real time during the treatment process of the sewage treatment tank. Chemical composition includes total suspended solids, dissolved oxygen, ammonia nitrogen and phosphate. The various sensors and their uses are as follows:
[0067] COD (Chemical Oxygen Demand) sensor: uses ultraviolet spectrometer to monitor and collect chemical oxygen demand; BOD sensor: uses optical or electrochemical sensors to monitor and collect BOD; Turbidity sensor: uses turbidity meter to monitor and collect total suspended solids; pH sensor: uses glass electrode pH meter to monitor pH value; Temperature sensor: uses thermocouple or thermistor to monitor and collect temperature; DO (Dissolved Oxygen) sensor: uses optical or electrochemical dissolved oxygen sensor to monitor and collect dissolved oxygen; Ammonia nitrogen sensor: uses selective electrode or optical sensor to monitor and collect ammonia nitrogen; Phosphate sensor: uses ion selective electrode to monitor and collect phosphate.
[0068] Step S102, calculating the total mass of the sludge and evaluating the sludge fluidity based on the sludge parameters.
[0069] Specifically, the total mass of sludge and sludge fluidity have an important influence on the current sludge treatment status. Therefore, it is necessary to calculate the total mass of sludge in the sewage treatment tank and evaluate the sludge fluidity based on the sludge parameters.
[0070] Step S103, predicting the current sludge treatment state based on the sludge parameters, the total sludge mass and the sludge fluidity, and generating a chemical agent injection instruction.
[0071] Specifically, an AI (Artificial Intelligence) decision module is used to predict the current sludge treatment state based on sludge parameters, total sludge mass and sludge fluidity, and to generate chemical agent delivery instructions. This AI decision module includes a deep learning network model improved based on the AlphaGo algorithm, which analyzes and predicts the current sludge treatment state based on sludge parameters, total sludge mass and sludge fluidity, and decides which chemical agent to deliver and its dosage based on the prediction results, that is, generates chemical agent delivery instructions. Chemical agents include but are not limited to pH regulators, flocculants and disinfectants.
[0072] Step S104: during the sludge treatment process, corresponding chemicals are added based on the chemical addition instructions.
[0073] Specifically, the automatic delivery of chemicals is controlled based on the chemical delivery instruction, and the chemical delivery refers to the delivery time and delivery amount of the chemicals, which can accurately adjust the delivery time and amount of the drugs to ensure the processing efficiency and economy.
[0074] The automated sludge treatment method provided in the present embodiment collects sludge parameters during the sludge treatment process; calculates the total sludge mass and evaluates the sludge fluidity based on the sludge parameters; predicts the current sludge treatment status based on the sludge parameters, the total sludge mass and the sludge fluidity, and generates chemical agent dosing instructions; during the sludge treatment process, corresponding chemicals are respectively dosed based on the chemical agent dosing instructions, thereby realizing automated determination of the dosing of chemicals during the sludge treatment process, being able to accurately grasp the dosing time and amount of chemicals according to the chemical agent dosing instructions, thereby ensuring that the use of chemicals is always in the optimal state and avoiding overdosage or underdosage, while improving the energy efficiency of the sewage treatment process and solving the problem of not being able to automatically dosing chemicals during the sludge treatment process.
[0075] In this embodiment, an automated sludge treatment method is provided, which can be used in computers, servers, etc. Figure 2 is a flow chart of an automated sludge treatment method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:
[0076] Step S201, collect sludge parameters during sludge treatment. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.
[0077] Step S202 , the sludge parameters include chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters, and data preprocessing of the chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters is performed on the data cleaning and data formatting.
[0078] Specifically, a data acquisition module containing multiple sensors is used to monitor and collect sludge parameters such as chemical composition, temperature, pH value, biochemical oxygen demand and chemical oxygen demand in the sewage treatment pool in real time. Among them, chemical oxygen demand: in milligrams per liter; biochemical oxygen demand: in milligrams per liter; total suspended solids: in milligrams per liter; pH value: no unit, the value range is 0-14; temperature: in degrees Celsius; dissolved oxygen: in milligrams per liter; ammonia nitrogen: in milligrams per liter; phosphate: in milligrams per liter. The data processing module is used to perform data cleaning and data formatting on the chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters. Data preprocessing.
[0079] Data preprocessing includes the following data cleaning methods and corresponding processing formulas for each type of data:
[0080] Chemical oxygen demand and biochemical oxygen demand were used to eliminate outliers: outliers were eliminated by the IQR (Inter-Quartile Range) method, using the formula and ,in, and are the first and third quartiles, ; Smoothing: Use the moving average method, using the formula ,in, It's time The raw COD or BOD data, is a single moving window, is the size of the moving window.
[0081] Missing data values for total suspended solids are filled using linear interpolation, using the formula ,in, is the missing data point; data normalization of total suspended solids: To reduce the difference in measurement scale, use the formula ,in, is the set of all measurement data.
[0082] Noise filtering of pH, temperature, dissolved oxygen, ammonia nitrogen and phosphate: The data series are smoothed using local polynomial regression, and the formula is: ,in, It is based on the polynomial degree and window size Calculated coefficients; Outlier processing of pH, temperature, dissolved oxygen, ammonia nitrogen and phosphate: The standard deviation method is used to remove data points that exceed three standard deviations σ from the mean value μ, that is, If satisfied , then remove, It is pH value, temperature, dissolved oxygen, ammonia nitrogen or phosphate data.
[0083] Data formatting is achieved through normalization and standardization, specifically:
[0084] Normalization is a data preprocessing method that aims to scale the value range to a specific interval, usually 0 to 1, which helps the performance of the data processing model. It is achieved through the minimum-maximum scaling method. The normalization formula is as follows:
[0085]
[0086] Where x is the original data point, which includes chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameter data points; and They are the minimum and maximum values in the data set, respectively. The data set is a chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value or temperature parameter data set.
[0087] Standardization is another method of adjusting the data scale. It rescales the data by subtracting the moving mean and dividing by the standard deviation so that the processed data has zero mean and unit variance. The specific formula is as follows:
[0088]
[0089] Here, μ is the moving average of the data set and σ is the standard deviation of the data set.
[0090] Step S203, calculating the total mass of the sludge and evaluating the sludge fluidity based on the sludge parameters.
[0091] Specifically, the sludge parameters also include the mass of the preset sludge sample. The calculation of the total mass of the sludge in step S203 includes:
[0092] Step S2031, calculating the sludge volume by using a volumetric method or an estimation method based on sewage flow and sludge concentration.
[0093] Specifically, the sludge volume V is first calculated using a volumetric method or an estimation method based on sewage flow and sludge concentration, or the sludge volume can be obtained by physical measurement of the container or flow meter data.
[0094] Step S2032: Calculate the sludge density based on the sludge volume and the mass of the preset sludge sample.
[0095] Specifically, the density of sludge is calculated by sampling sludge and measuring its dry weight and wet weight in the laboratory using a standardized method. The specific calculation formula is:
[0096]
[0097] Wherein, m is the sludge mass of the preset sludge sample, and V is the sludge volume.
[0098] Step S2033, using a drying method to calculate the dry solid content in the preset sludge sample.
[0099] Specifically, the dry solid content of the sludge sample is determined by the drying method, and the specific calculation formula is as follows:
[0100]
[0101] in, is the solid weight of the preset sludge sample after drying, is the weight of the preset sludge sample, i.e. the wet sludge.
[0102] Step S2034, calculating the total mass of the sludge based on the sludge volume, the sludge density and the dry solid content in the preset sludge sample.
[0103] Specifically, the formula for calculating the total sludge mass based on the sludge volume, sludge density and dry solid content in the preset sludge sample is as follows:
[0104]
[0105] Where ρ is the sludge density, is the sludge volume, It is the dry solid content in the preset sludge sample.
[0106] It should be noted that when calculating the total mass of sludge, the amount of sewage entering the sludge treatment facility and the sludge output are monitored in real time, and the estimated values of the above parameters are adjusted according to the real-time data to ensure the accuracy and timeliness of the calculation of the total mass of sludge.
[0107] The sludge parameters also include sludge concentration, yield stress and activation energy parameters; the above step S203 of evaluating sludge fluidity based on sludge parameters includes:
[0108] Step S2035, calculating the sludge plastic viscosity based on the sludge concentration.
[0109] Specifically, the relationship between sludge concentration and its viscosity was analyzed, and the viscosity change at different concentrations was estimated. The specific calculation formula is as follows:
[0110]
[0111] in, is the sludge concentration, is the plastic viscosity, is the experimental constant.
[0112] Step S2036, calculating the sludge shear stress at a preset shear rate based on the sludge plastic viscosity and yield stress.
[0113] Specifically, the viscosity and shear stress characteristics of the sludge were measured using a rheometer. The rheological parameters of the sludge were specifically the plastic viscosity and yield stress. The specific calculation formula is as follows:
[0114]
[0115] in, is the shear stress, is the shear rate.
[0116] Step S2037, calculating the sludge viscosity at a preset temperature based on the temperature parameter and the activation energy parameter.
[0117] Specifically, the effect of temperature change on sludge fluidity can be evaluated. The effect of temperature on viscosity can be calculated by the Arrhenius equation. The specific calculation formula is as follows:
[0118]
[0119] in, For temperature The viscosity of is the base viscosity, is the activation energy parameter, is the gas constant, The temperature is in degrees Celsius.
[0120] Step S2038, evaluating sludge fluidity based on sludge shear stress at a preset shear rate and sludge viscosity at a preset temperature.
[0121] Specifically, computational fluid dynamics models are used to simulate the flow behavior of sludge in treatment facilities to further accurately evaluate the fluidity of sludge. Simulation analysis can help predict the flow performance of sludge under different operating conditions; real-time monitoring and adjustment: by real-time monitoring of sludge parameters, the parameters in the treatment process are automatically adjusted to optimize the fluidity of sludge.
[0122] Step S204: predict the current sludge treatment state based on the sludge parameters, total sludge mass and sludge fluidity, and generate a chemical agent injection instruction. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.
[0123] Step S205: during the sludge treatment process, corresponding chemicals are added based on the chemical agent addition instructions. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.
[0124] The automated sludge treatment method provided in this embodiment performs data cleaning and data formatting on chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters, removes abnormal values in sludge parameters, fills in missing data values, and ensures the accuracy of sludge parameters. The total sludge mass is calculated based on the sludge volume, sludge density and dry solid content in the preset sludge sample to ensure the accuracy and timeliness of the sludge mass calculation, providing a data basis for the subsequent evaluation of the current sludge treatment process status, and evaluating the sludge fluidity based on the sludge shear stress at a preset shear rate and the sludge viscosity at a preset temperature, so as to grasp the flow properties of the sludge in real time, and providing a data basis for the subsequent evaluation of the current sludge treatment process status.
[0125] In this embodiment, an automated sludge treatment method is provided, which can be used in computers, servers, etc. Figure 3 is a flow chart of an automated sludge treatment method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:
[0126] Step S301, collect sludge parameters during sludge treatment. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.
[0127] Step S302, calculate the total mass of sludge based on the sludge parameters and evaluate the sludge fluidity. Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.
[0128] Step S303, predicting the current sludge treatment state based on the sludge parameters, the total sludge mass and the sludge fluidity, and generating a chemical agent injection instruction.
[0129] Specifically, the above step S303 includes:
[0130] Step S3031, calculating the moving average, standard deviation and coefficient of variation of the sludge parameters, and taking the moving average, standard deviation and coefficient of variation as parameter characteristic values.
[0131] Moving Average (MA) is a technique used to analyze a time series of data points by creating a series of averages to smooth the data. The formula is:
[0132]
[0133] in, is the i-th data point, n is the size of the moving window (i.e., how many time points to consider for averaging), and t is the current time point.
[0134] Standard Deviation (SD) is a statistic that measures the degree of data dispersion, indicating the deviation of a data point from its mean value. The formula is:
[0135]
[0136] in, is the i-th data point, μ is the moving average of the data set, is the total number of data points.
[0137] The coefficient of variation (CV) is the ratio of the standard deviation to the moving average. It is used to compare the dispersion of different data sets, especially when the moving averages differ greatly. The formula is:
[0138]
[0139] Here, SD is the standard deviation and μ is the moving average of the data set.
[0140] Specifically, the AI decision module receives processed data from the data processing module, including the measured values of chemical oxygen demand, biochemical oxygen demand, total suspended solids, pH value, temperature, dissolved oxygen, ammonia nitrogen and phosphate of the sludge. The moving average, standard deviation and coefficient of variation of the sludge parameters are calculated, and the moving average, standard deviation and coefficient of variation are used as parameter characteristic values.
[0141] Step S3032, using a machine learning algorithm to analyze the data time series of parameter characteristic values.
[0142] Specifically, machine learning algorithms are used to analyze trends, periodicities, and mutation points in data time series.
[0143] During the data collection process, multiple sensors installed in the sewage treatment facility are used to monitor and automatically record various parameters in real time, such as dissolved oxygen, ammonia nitrogen, phosphate, etc. Whenever the sensor measures a new data point, the data will be recorded, including the measurement value and the corresponding timestamp. All collected data are stored in a database or data warehouse to ensure that the integrity and time sequence of the data are maintained, which is convenient for further analysis and processing.
[0144] Data time series construction: Extract continuous data within a specific time period from the database, sort these data according to timestamps to form a complete time series. The data time series reflects the changing trend of each parameter characteristic value over time.
[0145] Step S3033, evaluating the current sludge treatment status based on the data time series, sludge quality and sludge fluidity.
[0146] Specifically, based on the data time series, sludge quality and sludge fluidity, a deep learning network model improved based on the AlphaGo algorithm is used to evaluate the status of the current sludge treatment system to determine whether the current sludge treatment system is in the optimal working condition or whether the treatment dosage needs to be adjusted.
[0147] Step S3034, based on the current sludge treatment status, a deep learning network improved based on the AlphaGo algorithm is used to predict changes in sewage treatment and generate prediction results.
[0148] Specifically, the AlphaGo algorithm is a machine learning algorithm used for human-computer games, which combines natural language processing, deep learning and search algorithms. The deep learning network model improved based on the AlphaGo algorithm is used to predict the possible changes in the sludge treatment process based on the current sludge treatment status, and make decisions on drug administration based on this, that is, the prediction results. The deep learning network model improved based on the AlphaGo algorithm takes into account historical sludge parameters, current sludge treatment status evaluation and expected sludge treatment system response.
[0149] In some optional embodiments, in order to optimize the deep learning network improved based on the AlphaGo algorithm, the predicted results are compared with the actual sewage treatment to obtain the result difference, and the deep learning network improved based on the AlphaGo algorithm is optimized based on the result difference to obtain the optimized deep learning network.
[0150] Specifically, the predicted results are compared with the actual sewage treatment to obtain the result difference, and the deep learning network improved based on the AlphaGo algorithm is optimized based on the result difference, and the model parameters are adjusted and optimized to improve the accuracy of future decisions, thereby obtaining an optimized deep learning network.
[0151] The deep learning network improved based on the AlphaGo algorithm combines the structure of convolutional layer (CNN) and long short-term memory network layer (LSTM) to process time series data and spatial features to achieve dynamic prediction and optimal control of variables in the sludge treatment process.
[0152] 1. The following is an explanation of the deep learning network and its training process based on the improved AlphaGo algorithm:
[0153] The deep learning network improved based on the AlphaGo algorithm includes, from its input end to its output end, an input layer, a first convolutional layer, a first batch normalization layer, a first activation layer, a first long short-term memory network layer, a first fully connected layer and an output layer.
[0154] 1.1 The first convolutional layer (CNN layer) includes 64 3x3 filters with a stride of 1 and no padding; it is mainly used to extract spatial features from sludge treatment data. In this model, we designed four convolutional layers, each followed by a batch normalization layer and a ReLU activation function to enhance the nonlinear learning ability and stability of the model. The number of filters used in each convolutional layer increases layer by layer (such as 64, 128, 256, 512) to capture features from low-level to high-level.
[0155] The first batch normalization layer is configured as standard normalization.
[0156] The first activation layer uses the ReLU activation function.
[0157] 1.2 The first long short-term memory network layer includes 128 LSTM (Long Short-Term Memory) units with bidirectional connections. When the long short-term memory network layer (LSTM) is used to process time series data, the LSTM layer can learn and remember past information and make predictions for the future.
[0158] After the CNN layer processes the spatial features, the data is fed into two LSTM layers in series, each containing 256 units. These layers help the model understand the changing trends and cyclical behaviors of the processing parameters over time.
[0159] 1.3 The first fully connected layer includes 256 neurons and uses the ReLU activation function. After the CNN layer and LSTM layer extract and fuse the temporal and spatial features, the data is passed to the first fully connected layer, which further integrates the features and makes the final decision output. The output layer uses the softmax function to calculate the probability distribution of the dosage of each drug to ensure the accuracy of the output and the feasibility of the operation.
[0160] 2. Training process:
[0161] 2.1 Data preparation:
[0162] The training data set includes a variety of sensor data collected from actual sludge treatment facilities, such as chemical oxygen demand sensors, biochemical oxygen demand sensors, turbidity sensors, pH sensors, temperature sensors, dissolved oxygen sensors, etc., covering multiple months of operation records. Each record contains the corresponding operation results, such as the amount of chemical agent added and the changes in water quality after treatment.
[0163] 2.2 Data preprocessing:
[0164] Before being fed into the deep learning network improved based on the AlphaGo algorithm, all data were normalized to eliminate the impact of different dimensions. In addition, linear interpolation was used to fill in missing values. The data were randomly divided into a training set (80%) and a test set (20%).
[0165] 2.3 Deep learning network training based on improved AlphaGo algorithm:
[0166] The training of the deep learning network based on the improved AlphaGo algorithm was implemented using the TensorFlow framework (an open source machine learning framework). Adam (Adaptive Moment Estimation) was selected as the optimizer because its adaptive learning rate is suitable for processing data of different sizes. The loss function uses cross entropy loss to evaluate the error between the output of the deep learning network based on the improved AlphaGo algorithm and the actual operation.
[0167] During the training process, multiple callback functions are set, such as EarlyStopping to avoid overfitting, and ModelCheckpoint to save the best model. During the training process, the deep learning network improved by the AlphaGo algorithm is evaluated on the test set after each epoch to monitor its generalization ability.
[0168] 2.4 Performance evaluation and optimization:
[0169] The performance of the deep learning network based on the improved AlphaGo algorithm was evaluated by indicators such as accuracy, recall, and F1 score. In addition, the confusion matrix was used to analyze in detail the prediction performance of the deep learning network based on the improved AlphaGo algorithm in different categories. By continuously adjusting the network structure and parameter settings, we finally obtained a high-precision and stable deep learning network based on the improved AlphaGo algorithm, which is suitable for actual sludge treatment operations.
[0170] Through the deep learning network structure design based on the improved AlphaGo algorithm and a meticulous training process, the present invention can effectively support complex sludge treatment decisions, improve the automation and intelligence level of operations, optimize treatment effects, and reduce environmental impacts.
[0171] Step S3035, generating chemical agent delivery instructions based on the prediction results.
[0172] In some optional implementations, the above step S3035 includes:
[0173] Step a1: input the prediction results into the input layer of the optimized deep learning network, perform deep learning in the first convolutional layer, the first batch normalization layer, the first activation layer, the first long short-term memory network layer, and the first fully connected layer in sequence, and transmit the deep learning results to the output layer.
[0174] Step a2, based on the deep learning results, a normalized function is used to obtain the probability distribution of various chemical dosage schemes.
[0175] Step a3, using AI decision function based on probability distribution to select the chemical agent delivery plan with the highest probability.
[0176] Specifically, the AI decision module makes decisions based on the probability distribution obtained from the output layer and selects the chemical agent injection scheme with the highest probability to ensure the optimization of the treatment effect. During the decision-making process, the AI decision module evaluates the matching degree between the current sludge parameters and the historical data to dynamically adjust the drug dosage and achieve adaptive control.
[0177] Step a4, generating a chemical agent delivery instruction based on the chemical agent delivery plan with the highest probability.
[0178] The automated sludge treatment method provided in this embodiment ultimately automatically generates chemical agent dosing instructions by optimizing the neural network and AI decision function, providing an instruction basis for the subsequent dosing of corresponding chemicals according to the chemical agent dosing instructions, which not only improves the efficiency and reliability of sludge treatment, but also reduces operating costs.
[0179] Step S304: during the sludge treatment process, corresponding chemicals are added based on the chemical agent addition instructions. Figure 2 Step S205 of the illustrated embodiment will not be described in detail here.
[0180] The automated sludge treatment method provided in this embodiment generates chemical agent delivery instructions that optimize the use of chemicals and energy consumption, and reduces operating costs and environmental impacts by precisely controlling the dosage of agents and energy use. The intelligent capabilities of the system ensure that the use of chemicals is always in the optimal state, avoiding excess or deficiency, while improving the energy efficiency of the treatment process, reducing dependence on complex mechanical equipment, and using software and algorithms to implement most functions, reducing initial equipment investment and long-term maintenance costs. By integrating artificial intelligence technology, especially using a deep network learning model improved based on the AlphaGo algorithm, stronger data processing and decision-making capabilities are provided. This enables the method to not only handle conventional sludge quality fluctuations, but also effectively respond to sudden abnormal situations, automatically adjust treatment parameters to maximize treatment efficiency and quality, thereby achieving truly intelligent and adaptive sludge treatment.
[0181] As one or more specific application embodiments of the present invention, Figure 4 The automated sludge treatment provided in this embodiment is further described in detail as follows:
[0182] Data collection: Various sensors installed in the treatment facility collect different parameters about the sludge. The following Table 1 shows the data collected at a specific moment:
[0183] Table 1
[0184]
[0185] 2. Data processing:
[0186] In the data processing stage, the collected data was cleaned and features were extracted to provide accurate input for the AI decision-making module. The following are the results after data cleaning and the process of feature extraction:
[0187] The data cleaning results are shown in Table 2 below:
[0188] Table 2
[0189]
[0190] Feature extraction process:
[0191] Statistical analysis and machine learning algorithms are used to extract features from the cleaned data, mainly including calculating the sliding mean, standard deviation, coefficient of variation, etc. of each parameter to fully describe the state of the sludge. The feature extraction is shown in Table 3 below:
[0192] Table 3
[0193]
[0194] 3. Output of AI decision:
[0195] Based on the processed data, AI decision-making used a deep learning network based on the improved AlphaGo algorithm to perform decision calculations and determine the most suitable chemical agent delivery plan. The following Table 4 is the AI decision output:
[0196] Table 4
[0197]
[0198] This embodiment demonstrates the entire process from data collection, data processing to AI decision-making, and each step is processed with precise technology to ensure that the final treatment effect meets environmental protection standards and optimizes resource use. This intelligent processing flow not only improves the efficiency and reliability of sludge treatment, but also reduces operating costs, proving the practical value and technical advantages of the present invention in the field of modern sludge treatment. Because the present invention is highly adaptable and configurable, it is not only suitable for municipal sewage treatment, but also can be extended to industrial sludge treatment and sludge treatment in other special cases. The flexibility of this embodiment enables customized solutions to be provided to meet the needs of different customers and different industries. The hardware requirements and operating procedures are simplified, making it easier to install and maintain. By reducing the reliance on complex mechanical equipment and using software and algorithms to implement most functions, the initial equipment investment and long-term maintenance costs are reduced.
[0199] In this embodiment, an automated sludge treatment device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
[0200] This embodiment provides an automated sludge treatment device, such as Figure 4 and Figure 5 As shown, including:
[0201] The data collection module 401 is used to collect sludge parameters during the sludge treatment process.
[0202] The data processing module 402 is used to calculate the total mass of sludge and evaluate the fluidity of sludge based on the sludge parameters.
[0203] The AI decision module 403 is used to predict the current sludge treatment status based on sludge parameters, total sludge mass and sludge fluidity, and generate chemical agent injection instructions.
[0204] The execution module 404 is used to add corresponding chemical agents according to the chemical agent adding instruction during the sludge treatment process. Figure 5 In the embodiment, the execution module 404 is an automatic material feeding control module.
[0205] In some optional implementations, the data processing module 402 includes:
[0206] The sludge volume calculation unit is used to calculate the sludge volume using the volumetric method or the estimation method based on the sewage flow and the sludge concentration.
[0207] The sludge density calculation unit is used to calculate the sludge density based on the sludge volume and the mass of a preset sludge sample.
[0208] The dry solid content calculation unit is used to calculate the dry solid content in a preset sludge sample by oven drying method.
[0209] The sludge total mass calculation unit is used to calculate the sludge total mass based on the sludge volume, sludge density and dry solid content in a preset sludge sample.
[0210] The plastic viscosity calculation unit is used to calculate the sludge plastic viscosity based on the sludge concentration.
[0211] The sludge shear stress calculation unit is used to calculate the sludge shear stress at a preset shear rate based on the sludge plastic viscosity and yield stress.
[0212] The sludge viscosity calculation unit is used to calculate the sludge viscosity at a preset temperature based on a temperature parameter and an activation energy parameter.
[0213] The sludge fluidity evaluation unit is used to evaluate the sludge fluidity based on the sludge shear stress at a preset shear rate and the sludge viscosity at a preset temperature.
[0214] In some optional implementations, the AI decision module 403 includes:
[0215] The parameter characteristic value calculation unit is used to calculate the moving average value, standard deviation and coefficient of variation of the sludge parameters, and use the moving average value, standard deviation and coefficient of variation as the parameter characteristic value.
[0216] The analysis unit is used to analyze the data time series of parameter characteristic values by using a machine learning algorithm.
[0217] The sludge treatment status evaluation unit is used to evaluate the current sludge treatment status based on the data time series, sludge quality and sludge fluidity.
[0218] A prediction unit, used to predict changes in sewage treatment based on the current sludge treatment status using a deep learning network improved based on the AlphaGo algorithm, and generate prediction results;
[0219] The model optimization unit is used to compare the predicted results with the actual sewage treatment to obtain the result difference, and based on the result difference, optimize the deep learning network improved based on the AlphaGo algorithm to obtain the optimized deep learning network.
[0220] A delivery instruction generation unit is used to generate a chemical delivery instruction based on the prediction result. In some optional embodiments, the delivery instruction generation unit includes:
[0221] The deep learning subunit is used to input the prediction results into the input layer of the optimized deep learning network, perform deep learning in the first convolutional layer, the first batch normalization layer, the first activation layer, the first long short-term memory network layer, and the first fully connected layer in sequence, and transmit the deep learning results to the output layer.
[0222] The probability distribution calculation subunit is used to obtain the probability distribution of various chemical dosage schemes using a normalized function based on the deep learning results.
[0223] The AI decision-making subunit is used to select the chemical agent delivery plan with the highest probability based on the probability distribution using the AI decision function.
[0224] The delivery instruction generation subunit is used to generate a chemical delivery instruction based on the chemical delivery plan with the highest probability.
[0225] In some optional embodiments, the automated sludge treatment device further comprises:
[0226] The data preprocessing module is used for data cleaning and data formatting of chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters.
[0227] The user interface and monitoring module is used to provide an operation interface, allowing operators to monitor the operating status, historical data and real-time data of the entire device, and manually adjust parameters or intervene in the automatic process when necessary. Figure 5 As shown, the device provided in this embodiment includes a highly intuitive operating interface that enables operators to easily monitor and control the entire treatment process. Through integrated data analysis and reporting functions, the device can provide detailed operation logs, performance evaluations and optimization suggestions to help users better understand and optimize their sludge treatment operations.
[0228] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.
[0229] The automated sludge treatment device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.
[0230] The embodiment of the present invention also provides a computer device having the above Figure 4 and Figure 5 The automated sludge processing device shown.
[0231] See also Figure 6 , Figure 6is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.
[0232] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.
[0233] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.
[0234] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0235] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.
[0236] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.
[0237] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device may be a touch screen.
[0238] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.
[0239] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.
Claims
1. An automated sludge treatment method, characterized in that: The method comprises: Collect sludge parameters during sludge treatment; Calculating the total mass of sludge and evaluating sludge fluidity based on the sludge parameters; Predicting the current sludge treatment state based on the sludge parameters, the total sludge mass and the sludge fluidity, and generating a chemical agent delivery instruction; In the sludge treatment process, corresponding chemical agents are respectively added based on the chemical agent addition instruction; Based on the sludge parameters, sludge quality and sludge fluidity, the current sludge treatment state is predicted, and a variety of chemical agent delivery instructions are generated, including: Calculating the moving average, standard deviation and coefficient of variation of the sludge parameter, and using the moving average, standard deviation and coefficient of variation as parameter characteristic values; Use machine learning algorithms to analyze the data time series of parameter eigenvalues; Evaluate the current sludge treatment status based on the data time series, sludge quality and sludge fluidity; Based on the current sludge treatment state, a deep learning network improved based on the AlphaGo algorithm is used to predict changes in sludge treatment and generate a prediction result; Based on the prediction result, generating a chemical agent delivery instruction; The method adopts an automated sludge treatment device, which comprises: Data acquisition module, used to collect sludge parameters during sludge treatment; A data processing module, used for calculating the total mass of sludge and evaluating the fluidity of sludge based on the sludge parameters; An AI decision-making module is used to predict the current sludge treatment state based on the sludge parameters, the total sludge mass and the sludge fluidity, and generate a chemical agent delivery instruction; The execution module is used to put corresponding chemical agents based on the chemical agent putting instruction during the sludge treatment process.
2. The method according to claim 1, characterized in that The sludge parameters include chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters; Before calculating the sludge quality and evaluating the sludge fluidity based on the sludge parameters, the method further comprises: Data preprocessing including data cleaning and data formatting is performed on the chemical composition, chemical oxygen demand, biochemical oxygen demand, pH value and temperature parameters.
3. The method according to claim 2, characterized in that The sludge parameters also include the quality of the preset sludge sample; Calculating the total sludge mass based on the sludge parameters includes: Calculate sludge volume using the volumetric method or an estimate based on sludge flow and sludge concentration; Calculate sludge density based on sludge volume and mass of a pre-set sludge sample; The dry solids content of the pre-set sludge sample was calculated using the oven drying method; The total mass of the sludge is calculated based on the sludge volume, the sludge density and the dry solid content of the preset sludge sample.
4. The method according to claim 2, characterized in that: The sludge parameters also include sludge concentration, yield stress and activation energy parameters; The evaluation of sludge fluidity based on the sludge parameters includes: calculating the sludge plastic viscosity based on the sludge concentration; Calculating the sludge shear stress at a preset shear rate based on the sludge plastic viscosity and yield stress; Calculating the sludge viscosity at a preset temperature based on the temperature parameter and the activation energy parameter; The sludge fluidity is evaluated based on the sludge shear stress at the preset shear rate and the sludge viscosity at the preset temperature.
5. The method according to claim 1, characterized in that Before generating a chemical agent delivery instruction based on the prediction result, the method further includes: The predicted result is compared with the actual sludge treatment to obtain a result difference, and the deep learning network improved based on the AlphaGo algorithm is optimized based on the result difference to obtain an optimized deep learning network.
6. The method according to claim 5, characterized in that The optimized deep learning network includes an input layer, a first convolutional layer, a first batch normalization layer, a first activation layer, a first long short-term memory network layer, a first fully connected layer, and an output layer connected in sequence; Based on the prediction result, generating a chemical agent delivery instruction includes: Input the prediction results into the input layer of the optimized deep learning network, perform deep learning in the first convolutional layer, the first batch normalization layer, the first activation layer, the first long short-term memory network layer, and the first fully connected layer in sequence, and transmit the deep learning results to the output layer; Based on the deep learning results, a normalized function is used to obtain the probability distribution of various chemical dosage plans; Based on the probability distribution, an AI decision function is used to select the chemical agent delivery plan with the highest probability; A chemical agent delivery instruction is generated based on the chemical agent delivery plan with the highest probability.
7. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the automated sludge treatment method according to any one of claims 1 to 6 by executing the computer instructions.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the automated sludge treatment method according to any one of claims 1 to 6.
