Sludge solidification treatment method and device, electronic equipment and medium

Abstract

The invention provides a sludge solidification treatment method and device, electronic equipment and a medium. The method comprises the following steps: acquiring first monitoring data of sludge solidification treatment equipment; inputting the first monitoring data into a trained monitoring data prediction model to predict second monitoring data in a period of time in the future, inputting the second monitoring data into a multi-target optimization model, and outputting control parameters of the sludge solidification processing equipment; and controlling the operation of the sludge solidification treatment equipment based on the control parameters. The method can solve the problem that the existing scheme depends on historical data to match the curing scheme, and the sludge curing efficiency is low due to small target optimization amount.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sludge solidification treatment, and in particular to a sludge solidification treatment method and device, an electronic device and a medium. BACKGROUND

[0002] Sludge solidification technology, as a core method for realizing sludge reduction and stabilization treatment, has been widely used in river and lake dredging, port dredging, industrial sludge treatment and other fields. For example, in the municipal sewage treatment industry, sludge generated by treating domestic sewage and industrial wastewater through sludge solidification equipment can effectively reduce the harmfulness of sludge and facilitate subsequent treatment and disposal. In the industrial sewage treatment industry, according to the characteristics of chemical sludge, appropriate solidifying agents are selected to fix harmful substances in the sludge in the solidified body, preventing them from being released into the environment again during subsequent disposal. By adding sludge solidification reagents, adjusting the treatment process, and other means, the water content of sludge is reduced, the mechanical strength is improved, and harmful substances such as heavy metals are fixed, which is a key link for sludge resource utilization (such as roadbed filling and land improvement). Traditional sludge solidification technology mainly relies on experience to set the solidifying agent ratio (such as the dosage of cement, fly ash and other cementitious materials) and treatment parameters (such as mixing time and curing period), forming a treatment process of “component detection-experience ratio-solidification construction”. Some technologies begin to explore the use of machine learning to optimize solidification parameters, or use intelligent sensing systems to control the dosage of reagents, thereby improving the solidification efficiency to a certain extent.

[0003] However, the existing sludge solidification technology still faces the following common problems: Lack of dynamic adaptability: Different sources of sludge (such as river and lake sludge, industrial sludge, and marine sludge) have significant differences in composition. Existing methods rely on historical data to match solidification schemes, lack intelligent response capabilities to real-time composition fluctuations, and are prone to cause substandard mechanical properties after solidification or waste of reagents.

[0004] Lack of multi-objective optimization: In the solidification process, in addition to improving strength, it is also necessary to ensure that the leaching concentration of heavy metals such as lead is below 5 mg / L to meet environmental standards, while controlling costs. Traditional technology often only focuses on the improvement of a single performance, such as strength, while modern solidification technology such as HT sludge solidification technology can not only improve the chemical and physical properties of sludge in a short time, but also effectively reduce the leaching toxicity of heavy metals and improve the bearing capacity and air permeability.

[0005] Treatment process presents a fragmented state: Each link of solidifying agent preparation, mixing, curing and forming is mostly controlled independently, lacking a data linkage mechanism for the whole process (for example, changes in water content are not fed back to the reagent dosing system in real time), and manual intervention still dominates (for example, curing time is adjusted based on experience), resulting in relatively low automation and intelligence. SUMMARY

[0006] The application provides a sludge solidification treatment method and device, electronic equipment and medium, which are used for solving the problems of low sludge solidification efficiency caused by the dependence of the existing scheme on historical data for matching a solidification scheme and a small target optimization quantity.

[0007] According to an aspect of the application, a sludge solidification treatment method is provided, which comprises: obtaining first monitoring data of a sludge solidification treatment device; inputting the first monitoring data into a trained monitoring data prediction model to predict second monitoring data in a future period of time, inputting the second monitoring data into a multi-objective optimization model, and outputting control parameters of the sludge solidification treatment device; controlling the operation of the sludge solidification treatment device based on the control parameters.

[0008] Optionally, after the first monitoring data of the sludge solidification treatment device is obtained, the method further comprises pre-processing the first monitoring data. The pre-processing at least comprises data cleaning, filtering processing and normalization processing of the first monitoring data.

[0009] Optionally, the first monitoring data and the second monitoring data at least comprise the moisture content of sludge at the inlet of a mixer, the concentration of heavy metal ions and the viscosity of sludge at the outlet of a mixing reaction tank in the mixer, the temperature and the pH value of a solidification agent dosing point, the torque of a mixer main shaft, and the pressure of a press. The control parameters at least comprise the solidification agent ratio, the mixer stirring speed and the press pressure.

[0010] Optionally, before the first monitoring data is input into the trained monitoring data prediction model to predict the second monitoring data in the future period of time, the second monitoring data is input into the multi-objective optimization model, and the control parameters of the sludge solidification treatment device are output, the method further comprises: obtaining historical monitoring data of multiple kinds of sludge; pre-processing the historical monitoring data, and constructing a data set based on the pre-processed historical monitoring data; training the monitoring data prediction model and the multi-objective optimization model based on the constructed data set to obtain the trained monitoring data prediction model and the multi-objective optimization model.

[0011] Optionally, the training of the monitoring data prediction model and the multi-objective optimization model based on the constructed data set comprises: The input of the monitoring data prediction model is historical monitoring data in a first time period, and the output is predicted monitoring data in a second time period later than the first time period; The multi-objective optimization model calculates control parameters based on a target function, a constraint condition, a preset parameter screening strategy, and the predicted monitoring data, and outputs the control parameters; the multi-objective optimization model has multiple objectives including at least minimization of water content deviation, minimization of heavy metal overrun penalty, and minimization of cost, and the constraint condition includes at least press pressure constraint, mixer torque constraint, and reaction environment constraint; A reward function is set for the multi-objective optimization model to continuously optimize parameters of the multi-objective optimization model.

[0012] Optionally, the minimization of water content deviation is:

[0013] wherein H 实测 is the actual measured water content after the sludge is solidified, H 目标 is a preset target water content; The minimization of heavy metal overrun penalty is: (unit: mg / L) wherein C Pb is the concentration of lead in the solidified sludge, and a is a lead concentration threshold value; C Cd is the concentration of cadmium in the solidified sludge, and b is a cadmium concentration threshold value; The minimization of cost is:

[0014] wherein x1, x2, and x3 are the dosages of cement, fly ash, and chelating agent, p1, p2, and p3 are the unit prices of cement, fly ash, and chelating agent, the equipment energy consumption cost is calculated based on press pressure p and time t, and c is an equipment energy consumption cost coefficient; The reward function is:

[0015] In the formula, d is a compliance rate weight coefficient, e is a compliance rate threshold value, f is a cost saving rate weight coefficient, g is a cost saving rate threshold value, and h is an equipment load rate coefficient; wherein the equipment load rate is:

[0016] , , are respectively a torque load coefficient, a pressure load coefficient, and an energy consumption load coefficient.

[0017] Optionally, the preset parameter screening strategy includes a priority strategy and a cumulative solution screening strategy. The priority strategy respectively assigns different weight coefficients to different objective functions according to different priorities of different modes, that is, when the environmental protection mode is prioritized, the function of minimizing the heavy metal over-limit penalty is assigned the largest weight coefficient, and when the cost mode is prioritized, the function of minimizing the cost is assigned the largest weight coefficient.

[0018] According to another aspect of the present application, a sludge solidification treatment device is provided, comprising: a data acquisition unit configured to acquire the first monitoring data of the sludge solidification treatment device; a parameter calculation unit configured to input the first monitoring data into a trained monitoring data prediction model to predict second monitoring data of a future period of time, input the second monitoring data into a multi-objective optimization model, and output control parameters of the sludge solidification treatment device; a control unit configured to control the operation of the sludge solidification treatment device based on the control parameters. According to another aspect of the present application, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the sludge solidification treatment method according to any one of the embodiments of the present application.

[0019] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the sludge solidification treatment method according to any one of the embodiments of the present application when executed.

[0020] The technical scheme of the embodiments of the present application acquires real-time first monitoring data of a sludge solidification treatment device as input data, and outputs control parameters of the sludge solidification treatment device, wherein the control parameters include a solidification agent ratio, thereby enabling intelligent response to real-time component fluctuations, avoiding waste of solidification agents and poor solidification effects; the first monitoring data is input into a trained monitoring data prediction model to predict second monitoring data of a future period of time, the second monitoring data is input into a multi-objective optimization model, and control parameters of the sludge solidification treatment device are output, thereby enabling the control parameters of the sludge solidification device to be generated by focusing on multiple sludge solidification performance indicators, and achieving global optimization.

[0021] It is to be understood that the embodiments described herein are merely exemplary of the application and that a person skilled in the art can devise other embodiments without departing from the scope of the present application. It is also to be understood that not all of the benefits described herein need necessarily be realized in any particular embodiment of the application. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort.

[0023] Figure 1 is a flow chart of a sludge solidification treatment method according to an embodiment of the present application; Figure 2 is a flow chart of a sludge solidification treatment method according to an embodiment of the present application; Figure 3 is a structural diagram of a sludge solidification treatment device according to an embodiment of the present application; Figure 4 is a structural diagram of an electronic device for implementing a sludge solidification treatment method according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the technical personnel in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should be within the scope of the present application.

[0025] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] Embodiment one Figure 1A flowchart of a sludge solidification treatment method is provided for Embodiment One of the present application. As shown in Figure 1 The method comprises the following steps: S101, acquiring the first monitoring data of the sludge solidification treatment equipment.

[0027] It should be noted that the sludge solidification treatment equipment generally comprises a mixer, a conveyor belt and a press. During the solidification treatment of the sludge, the raw sludge is first conveyed to the mixer by the conveyor belt, then the sludge is mixed with the solidifying agent in the mixing bin, and then conveyed to the press by the conveyor belt, so that the sludge is dehydrated and solidified in the press, and finally the solidified solid sludge is obtained. In this embodiment, a moisture content sensor can be installed at the entrance of the conveyor belt to measure the moisture content entering the mixer; a heavy metal ion electrode can be arranged at the outlet of the mixing reaction tank in the mixer to measure the concentration of heavy metal ions in the sludge; a pressure sensor can be installed in the hydraulic cylinder of the press to collect pressure signals; temperature and pH sensors can be arranged at the dosing point of the solidifying agent to monitor the temperature data and pH value data of the dosing point; and a torque sensor can be installed on the main shaft of the mixer to monitor the stirring torque of the mixer.

[0028] The first monitoring data acquired from the sludge solidification treatment equipment can include sensor data at various places in the sludge solidification treatment equipment, real-time monitoring data of the sludge input into the sludge solidification treatment equipment, and environmental data at various places in the equipment, etc. In addition, the first monitoring data is time series data within a period of time, i.e. it can be discrete point data such as sensor data varying with time or environmental data varying with time.

[0029] S102, inputting the first monitoring data into the trained monitoring data prediction model to predict the second monitoring data in the future period of time, inputting the second monitoring data into the multi-objective optimization model, and outputting the control parameters of the sludge solidification treatment equipment.

[0030] In this embodiment, the monitoring data prediction model can predict the time series data in the future period of time based on the input time series data, i.e. when the first monitoring data is input, the second monitoring data predicted by the monitoring data prediction model is the monitoring data in the period of time after the time period of the first monitoring data. For example, the first monitoring data is the monitoring data of the sludge solidification treatment equipment from 0 to 6, and the second monitoring data is the monitoring data from 6 to 7 predicted based on the first monitoring data.

[0031] In this embodiment, the multi-objective optimization model can include multiple objective functions for finding a set of optimal solutions that can balance multiple conflicting objectives when there are multiple objectives. Unlike single-objective optimization, multi-objective optimization cannot find an "absolute optimal solution" that can simultaneously optimize all objectives, but instead obtains a set of non-dominated solutions called "Pareto Optimal Solutions", any improvement in one objective requires sacrificing other objectives as a price.

[0032] Specifically, the objective functions of the multi-objective optimization model are functions related to the monitoring data of the sludge in the sludge solidification equipment and the solidification agent ratio, and the constraint conditions of the multi-objective optimization model are the physical related limit conditions of the sludge solidification equipment itself or the sludge related limit conditions, such as the maximum pressure that the sludge solidification equipment press can provide, the minimum pressure required for solidification forming, the torque of the mixer, etc. The multi-objective optimization model can obtain the corresponding Pareto optimal solution based on the objective functions and the constraint conditions, that is, the ratio of the solidification agent and the operating parameters of the equipment (pressing machine pressure and mixer torque, etc.) can be obtained.

[0033] Specifically, in this embodiment, the first monitoring data and the second monitoring data each at least include the water content of the sludge at the inlet of the mixer, the heavy metal ion concentration and viscosity of the sludge at the outlet of the mixing reaction tank in the mixer, the temperature and pH value of the solidification agent dosing point, the torque of the mixer main shaft, and the pressure of the press.

[0034] S103, controlling the operation of the sludge solidification treatment equipment based on the control parameters.

[0035] In this embodiment, the control parameters can include the solidification agent ratio (cement / fly ash / chelating agent content) and the equipment control parameters (mixer torque, press pressure, curing time (referring to the time for the sludge cake formed after the sludge is mixed and pressed to dewater to be placed in a specific environment (temperature, humidity) to complete the solidification reaction), etc.). After obtaining the control parameters, the system will convert the control parameters into corresponding control instructions to adjust the solidification agent ratio, or adjust the mixer torque, press pressure and curing time in the sludge solidification treatment equipment.

[0036] The technical scheme of the embodiment of the present application obtains real-time first monitoring data of the sludge solidification treatment equipment as data input, and takes the control parameters of the sludge solidification treatment equipment as output, wherein the control parameters include the solidification agent ratio, so that the intelligent response capability to real-time component fluctuation can be achieved, and the problems of waste of solidification agent and poor solidification effect can be avoided; the first monitoring data is input into the trained monitoring data prediction model, the second monitoring data in a future period of time is predicted, the second monitoring data is input into the multi-objective optimization model, and the control parameters of the sludge solidification treatment equipment are output, so that the control parameters of the sludge solidification equipment can be generated by focusing on multiple sludge solidification performance indicators, and global optimization is achieved.

[0037] Embodiment two Figure 2 A flowchart of a sludge solidification treatment method provided by the embodiment two of the present application is shown in FIG. 2. Figure 2 As shown in the figure, the method further includes: S201, obtaining historical monitoring data of multiple types of sludge.

[0038] In this embodiment, the historical monitoring data of multiple types of sludge, such as historical detection data of river sludge and industrial sludge, can be obtained, so as to ensure the diversity of sample data in the constructed data set. The historical monitoring data of sludge includes parameters such as water content (generally 20%-80%), heavy metal concentration (generally 0-10 mg / L), and viscosity (1-5000 cP).

[0039] S202, preprocessing the historical monitoring data, and constructing a data set based on the preprocessed historical monitoring data.

[0040] In order to make the trained monitoring data prediction model as accurate as possible, the historical monitoring data can be preprocessed.

[0041] In this embodiment, the preprocessing at least includes data cleaning, filtering processing, and normalization processing of the monitoring data. For example, when the historical monitoring data is subjected to data cleaning, if the water content data appears negative or exceeds the historical normal range ±10%, it is directly excluded; in the filtering processing, the pressure data is subjected to Kalman filtering algorithm for noise reduction, and the heavy metal data is subjected to moving average filtering; finally, all the monitoring data is subjected to Z-Score method for normalization processing, wherein the mean μ and the standard deviation σ are dynamically updated according to the actual situation.

[0042] S203, training the monitoring data prediction model and the multi-objective optimization model based on the constructed data set, to obtain the trained monitoring data prediction model and the multi-objective optimization model.

[0043] The input of the monitoring data prediction model is historical monitoring data in a first time period, and the output is predicted monitoring data in a second time period later than the first time period. The multi-objective optimization model calculates the control parameters based on the objective function, the constraint condition, the preset parameter screening strategy, and the predicted monitoring data, and outputs the control parameters. The multi-objective optimization model has at least three objectives, including minimizing water content deviation, minimizing heavy metal over-limit penalty, and minimizing cost. The constraint condition includes at least presser constraint, mixer torque constraint, and reaction environment constraint. A reward function is set for the multi-objective optimization model to continuously optimize the parameters of the multi-objective optimization model.

[0044] In this embodiment, the monitoring data prediction model can use an LSTM time series prediction model. The input of the model can be 24-hour monitoring time series data with a sampling interval of 10 minutes, and the feature dimension includes three items: water content, Pb 2+ concentration, and viscosity. The output can be the future 1-hour trend, i.e., the prediction step length is 6, and the model structure uses 2-layer LSTM (64 units) + Dropout (0.2).

[0045] The multi-objective optimization model can use an NSGA-II multi-objective optimization model. The input data of the NSGA-II multi-objective optimization model includes at least real-time components of sludge (water content, heavy metal concentration, and viscosity), real-time states of treatment equipment (mixing torque and pressing pressure), and treatment targets (water content threshold, heavy metal emission standard, and cost budget). The output is the optimal dosage ratio (cement / fly ash / chelating agent content) and equipment parameters (mixing speed, pressing pressure, and curing time). The objective function of the NSGA-II multi-objective optimization model includes: The water content deviation minimization is:

[0046] wherein H 实测 is the actual measured water content of the sludge after solidification, and H 目标 is the preset target water content. This objective function measures the deviation between the actual water content and the target water content. The smaller the deviation value, the closer the water content is to the target value.

[0047] The heavy metal over-limit penalty minimization is: (unit: mg / L) wherein C Pb is the concentration of lead in the solidified sludge, and a is the threshold value of lead concentration, which can be set to 5 mg / L; and C CdFor the concentration of cadmium in the solidified sludge, b is the threshold value of cadmium concentration, which can be generally set to 0.3 mg / L. If the concentration of lead exceeds 5 mg / L or the concentration of cadmium exceeds 0.3 mg / L, the objective function f2 will produce a value greater than 0, and the size of the value directly reflects the severity of the heavy metal over-limit. If the concentration does not exceed the standard value, the item is 0. This objective function is used to punish the over-limit of heavy metals and promote the treatment process to reduce the risk of heavy metal leaching as much as possible.

[0048] Cost minimization:

[0049] where x1, x2, x3 are the dosages of cement, fly ash, and chelating agent, p1, p2, p3 are the unit prices of cement, fly ash, and chelating agent, the equipment energy consumption cost is calculated based on the pressing pressure p and time t, and c is the equipment energy consumption cost coefficient, which can be set to 0.1. This objective function f3 considers the reagent cost and equipment energy consumption cost comprehensively, and strives to minimize the total cost of the entire treatment process.

[0050] The constraint conditions of the NSGA-II multi-objective optimization model include at least: molding pressure ≥ 2 MPa (real-time feedback from pressure sensor to ensure that the compressive strength of the solidified body meets the standard); stirring torque ≤ 150 N·m (to prevent motor overload); presser pressure ≤ 5 MPa (equipment rated threshold); reaction environment constraints: pH ∈ [7, 10] (to ensure reagent activity, monitored in real time by pH sensor).

[0051] In this embodiment, the reinforcement learning parameter tuning module is used to gradually optimize the parameters of the NSGA-II multi-objective optimization model, i.e., to automatically optimize the NSGA-II parameters: mutation probability (0.05-0.15) and sludge treatment optimal solution population size (50-200), with the treatment effect (standard compliance rate ≥ 95% (probability of solidified body meeting compressive strength standard), cost saving rate ≥ 10%) as the reward function.

[0052] Specifically, the reward function is:

[0053] In the formula, d is the standard compliance rate weight coefficient; e is the standard compliance rate threshold, which can be set to 0.95 in this embodiment; f is the cost saving rate weight coefficient, g is the cost saving rate threshold, which can be set to 10% in this embodiment; h is the device load rate coefficient.

[0054] The device load rate can be:

[0055] , , Torque load coefficient, pressure load coefficient and energy consumption load coefficient, respectively.

[0056] In addition, the preset parameter screening strategy in the embodiment can include a priority strategy and a cumulative solution screening strategy. The priority strategy assigns different weight coefficients to different objective functions according to different priorities of different modes, that is, when the environmental protection mode is prioritized, the function of minimizing the heavy metal over-limit penalty is assigned the largest weight coefficient, and when the cost mode is prioritized, the function of minimizing the cost is assigned the largest weight coefficient.

[0057] For example, for the environmental protection priority mode under the priority strategy, the weight of the three objective functions can be allocated as f2=0.7, f1=0.2, and f3=0.1, and when the Pb concentration reaches or exceeds 4 mg / L, the mode will automatically trigger.

[0058] Under the cost priority mode, the weight of the three objective functions can be allocated as f3=0.6, f1=0.2, and f2=0.2.

[0059] Under the balanced mode, the weight of the three objective functions can be allocated as f1=0.4, f2=0.3, and f3=0.3, and the operator can define the weight combination.

[0060] In the cumulative solution screening strategy, the following is included: Environmental protection priority mode: calculate the comprehensive score:

[0061] Directly select the solution with the minimum score.

[0062] Cost priority mode: directly select the solution with the lowest total cost (while meeting the heavy metal standard).

[0063] Weight dynamic adjustment mechanism: when the equipment load rate exceeds the preset threshold (for example, 0.8), the intelligent decision-making module reduces the weight of the squeezing pressure, and preferentially selects a processing strategy with low torque and low energy consumption to ensure safe operation of the equipment.

[0064] In the embodiment, after the optimal strategy is obtained, control instructions (such as: the dosing device controls the opening degree of the corresponding solidifying agent valve, the squeezing machine pressure parameter, and the stirring machine torque) can be generated according to the output optimal strategy and sent to the actuator of the processing equipment to realize automatic control of the processing process.

[0065] The control instruction generation method includes: solidifying agent dosing amount calculation: calculate the valve opening degree according to the solidifying agent ratio (for example: 15% cement content corresponds to 45% valve opening degree).

[0066] Squeezing pressure control curve: the pressure is smoothly increased at a rate of 0.2 MPa per minute to prevent filter plate rupture caused by sudden pressure changes.

[0067] In an embodiment further comprising: Simulation test of the system: inject historical monitoring data sets, verify that the LSTM prediction error is ≤5%, and the NSGA-II solution time is ≤30 seconds; pressure overrun test: forcibly set the squeezing pressure to 5.5 MPa, and check the emergency stop function of the equipment.

[0068] On-site trial operation of the system: compliance rate verification: continuously process 100 batches of sludge, and count the moisture content compliance rate (±2%) and heavy metal qualification rate; cost analysis: compare the reagent consumption and energy consumption data before and after optimization using the multi-objective optimization model, and calculate the saving rate.

[0069] Model self-updating mechanism: the system automatically triggers model retraining every month, and introduces a sliding window mechanism to only retain the last 200 batches of data, avoiding historical data interference and ensuring long-term operation accuracy.

[0070] The technical scheme of the embodiment of the application obtains real-time first monitoring data of a sludge solidification treatment device as data input, takes the control parameters of the sludge solidification treatment device as output, and the control parameters include the curing agent ratio, so that the intelligent response capability to real-time component fluctuations can be achieved, and the problems of waste of curing agent and poor curing effect can be avoided; the first monitoring data is input into a trained monitoring data prediction model, the second monitoring data predicted for a future period of time is obtained, the second monitoring data is input into a multi-objective optimization model, and the control parameters of the sludge solidification treatment device are output, so that the control parameters of the sludge solidification device can be generated by focusing on multiple sludge solidification performance indicators, and global optimization can be achieved; the application dynamically generates the reagent ratio and device parameter instructions through the LSTM time series prediction model and the NSGA-II multi-objective optimization model, and realizes real-time closed-loop optimization, which greatly improves the automation level and overall efficiency of the treatment process.

[0071] Embodiment three Figure 3 A structure diagram of a sludge solidification treatment device provided for the third embodiment of the application. As shown in the figure, Figure 3 The device comprises: The data acquisition unit 301 is configured to acquire the first monitoring data of the sludge solidification treatment device; The parameter calculation unit 302 is configured to input the first monitoring data into a trained monitoring data prediction model to predict the second monitoring data for a future period of time, input the second monitoring data into a multi-objective optimization model, and output the control parameters of the sludge solidification treatment device; The control unit 303 is configured to control the operation of the sludge solidification treatment device based on the control parameter.

[0072] The message data processing resource scheduling apparatus provided by the embodiments of the present application can perform the sludge solidification treatment method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0073] Embodiment four Figure 4 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0074] As shown in Figure 4 The electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0075] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunications networks.

[0076] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, and the like. The processor 11 performs various methods and processes described above, such as a sludge solidification treatment method.

[0077] In some embodiments, a sludge solidification treatment method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the sludge solidification treatment method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform a sludge solidification treatment method by any other suitable means, such as by means of firmware.

[0078] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0079] Computer programs used to implement the methods of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a machine or a remote machine or a server.

[0080] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0081] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0082] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0083] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0084] It should be understood that the various forms of flow shown above can be reordered, added to, or have steps deleted. For example, the steps described in the present application can be performed in parallel, in series, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which are not limited herein.

[0085] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for solidifying sludge, characterized in that, include: Obtain the first monitoring data from the sludge solidification treatment equipment; The first monitoring data is input into the trained monitoring data prediction model to predict the second monitoring data for a future period of time. The second monitoring data is then input into the multi-objective optimization model to output the control parameters of the sludge solidification treatment equipment. The operation of the sludge solidification treatment equipment is controlled based on the aforementioned control parameters.

2. The sludge solidification treatment method according to claim 1, characterized in that, After acquiring the first monitoring data from the sludge solidification treatment equipment, the method further includes preprocessing the first monitoring data. The preprocessing includes at least data cleaning, filtering, and normalization of the first monitoring data.

3. The sludge solidification treatment method according to claim 1, characterized in that, Both the first monitoring data and the second monitoring data include at least the moisture content of the sludge at the mixer inlet, the heavy metal ion concentration and viscosity of the sludge at the outlet of the mixing reaction tank in the mixer, the temperature and pH value at the solidifier addition point, the torque of the mixer main shaft, and the pressure of the press. The control parameters include at least the curing agent ratio, the mixer speed, and the press pressure.

4. The sludge solidification treatment method according to claim 1, characterized in that, Before inputting the first monitoring data into the trained monitoring data prediction model to predict the second monitoring data for a future period, and inputting the second monitoring data into the multi-objective optimization model to output the control parameters of the sludge solidification treatment equipment, the process further includes: Obtain historical monitoring data for various types of silt; The historical monitoring data is preprocessed, and a dataset is constructed based on the preprocessed historical monitoring data; The monitoring data prediction model and the multi-objective optimization model are trained based on the constructed dataset to obtain the trained monitoring data prediction model and the multi-objective optimization model.

5. The sludge solidification treatment method according to claim 4, characterized in that, The training of the monitoring data prediction model and the multi-objective optimization model based on the constructed dataset includes: The input to the monitoring data prediction model is historical monitoring data within a first time period, and the output is predicted monitoring data within a second time period, which is later than the first time period. The multi-objective optimization model calculates control parameters based on the objective function, constraints, a preset parameter selection strategy, and the predicted monitoring data, and outputs the control parameters. The multi-objectives of the multi-objective optimization model include at least minimizing moisture content deviation, minimizing heavy metal exceedance penalties, and minimizing costs. The constraints include at least pressing machine pressure constraints, mixer torque constraints, and reaction environment constraints. A reward function is set for the multi-objective optimization model to continuously optimize the parameters of the multi-objective optimization model.

6. The sludge solidification treatment method according to claim 5, characterized in that, The moisture content deviation is minimized as follows: Among them, H 实测 H represents the actual moisture content measured after the sludge has solidified. 目标 The preset target moisture content; The penalty for exceeding the heavy metal limit is minimized as follows: (Unit: mg / L) Among them, C Pb C represents the lead concentration in the solidified sludge, where a is the lead concentration threshold. Cd denoted as , and b as the cadmium concentration threshold in the solidified sludge. The cost minimization: Where x1, x2, and x3 are the dosages of cement, fly ash, and chelating agent, p1, p2, and p3 are the unit prices of cement, fly ash, and chelating agent, the equipment energy consumption cost is calculated based on the pressing pressure p and time t, and c is the equipment energy consumption cost coefficient. The reward function is: In the formula, d is the compliance rate weighting coefficient, e is the compliance rate threshold; f is the cost saving rate weighting coefficient, g is the cost saving rate threshold; and h is the equipment load rate coefficient. Among them, the equipment load rate is: , , These are the torque load factor, pressure load factor, and energy load factor, respectively.

7. The sludge solidification treatment method according to claim 6, characterized in that, The preset parameter filtering strategy includes a priority strategy and a calculus filtering strategy; The priority strategy assigns different weight coefficients to different objective functions based on the different priorities of different modes; that is, when the environmental protection mode is prioritized, the function that minimizes the penalty for exceeding the heavy metal limit is assigned the largest weight coefficient; when the cost mode is prioritized, the function that minimizes the cost is assigned the largest weight coefficient.

8. A sludge solidification treatment device, characterized in that, include: The data acquisition unit is used to acquire the first monitoring data from the sludge solidification treatment equipment; The parameter calculation unit is used to input the first monitoring data into the trained monitoring data prediction model to predict the second monitoring data for a future period of time, input the second monitoring data into the multi-objective optimization model, and output the control parameters of the sludge solidification treatment equipment. The control unit is used to control the operation of the sludge solidification treatment equipment based on the control parameters.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the sludge solidification treatment method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the sludge solidification treatment method according to any one of claims 1-7.

Images