Intelligent optimization control method for garbage treatment and power generation and electronic device

Abstract

The application discloses a kind of intelligent optimization control method and electronic equipment of garbage treatment power generation, it is related to garbage treatment related technical field, the method includes: in garbage treatment power generation equipment upper deployment garbage sensor network, acquisition obtains multi-source garbage perception data flow;Based on garbage treatment power generation equipment characteristic parameter flow and garbage historical power generation dataset carries out digital twin simulation;Build garbage power generation optimization objective function and embed garbage treatment power generation digital twin;Using garbage power generation control digital twin, the power generation control solution of multi-source garbage perception data flow is carried out, determines target power generation control parameter and executes power generation dynamic scheduling and feedback closed-loop control to garbage treatment power generation equipment based on target power generation control parameter.It solves the technical problems of garbage incineration power generation process dynamic optimization difficulty, multi-source data fusion capability deficiency, control strategy real-time poor in the prior art, achieves the technical effect of improving garbage power generation efficiency, optimizing equipment operation stability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of garbage disposal, and in particular to an intelligent optimization control method for garbage disposal and power generation and an electronic device. BACKGROUND

[0002] Garbage incineration power generation has both garbage reduction and energy recovery. However, the complexity of garbage composition, large fluctuation of calorific value, inaccurate operation parameters of equipment, and unstable combustion efficiency make the optimization control of garbage power generation process face great challenges. Traditional garbage incineration control mainly relies on artificial experience and static models, which is difficult to adapt to the dynamic changes of garbage characteristics, and thus cannot realize dynamic optimization, resulting in unstable energy conversion efficiency, low power generation efficiency, or excessive pollutant emissions. In addition, it is difficult to efficiently fuse heterogeneous data generated by a sensor network. The complexity of physical and chemical reactions involved in garbage incineration makes the precision of digital twin modeling insufficient, thereby affecting the garbage disposal power generation efficiency and operation stability.

[0003] Therefore, in the related art, there are technical problems of difficulty in dynamic optimization of garbage incineration power generation process, insufficient multi-source data fusion capability, and poor real-time performance of control strategy. SUMMARY

[0004] The present application provides an intelligent optimization control method for garbage disposal and power generation and an electronic device, which solves the technical problems of difficulty in dynamic optimization of garbage incineration power generation process, insufficient multi-source data fusion capability, and poor real-time performance of control strategy in the prior art, and achieves the technical effects of improving garbage power generation efficiency and optimizing equipment operation stability.

[0005] The present application provides an intelligent optimization control method for garbage disposal and power generation, which comprises: deploying a garbage sensor network on a garbage disposal and power generation equipment, acquiring a multi-source garbage perception data stream through the garbage sensor network; performing digital twin simulation based on characteristic parameter streams and garbage historical power generation data sets of the garbage disposal and power generation equipment, and building a garbage disposal and power generation digital twin; decomposing garbage disposal and power generation targets into power generation indicators and designing target functions, constructing a garbage power generation optimization target function, embedding the garbage power generation optimization target function into the garbage disposal and power generation digital twin, and generating a garbage power generation control digital twin; using the garbage power generation control digital twin to solve garbage power generation control, determining target power generation control parameters, and performing power generation dynamic scheduling and feedback closed-loop control on the garbage disposal and power generation equipment based on the target power generation control parameters.

[0006] In a possible implementation, the intelligent optimization control method for waste treatment and power generation further performs the following processing: performing functional system classification on the waste treatment and power generation equipment to obtain a waste power generation equipment system architecture, the waste power generation equipment system architecture including a waste receiving and feeding system, a furnace system, a flue gas treatment system, a steam turbine system, and a furnace slag sorting system; performing processing demand analysis on each waste power generation equipment system in the waste power generation equipment system architecture to determine equipment system waste treatment demand; performing sensor layout analysis based on the equipment system waste treatment demand to obtain an equipment system sensor layout parameter set; and deploying a sensor set on the waste treatment and power generation equipment according to the equipment system sensor layout parameter set and performing communication networking to obtain the waste sensor network.

[0007] In a possible implementation, the intelligent optimization control method for waste treatment and power generation further performs the following processing: performing three-dimensional geometric modeling based on characteristic parameter flow of the waste treatment and power generation equipment to generate a waste treatment and power generation three-dimensional model; determining a waste treatment and power generation equipment operation constraint parameter set according to the characteristic parameter flow of the waste treatment and power generation equipment; performing waste power generation simulation prediction based on the waste historical power generation data set to obtain a waste power generation simulation prediction network set; and performing constraint optimization on the waste treatment and power generation three-dimensional model based on the waste treatment and power generation equipment operation constraint parameter set and the waste power generation simulation prediction network set to obtain a waste treatment and power generation digital twin.

[0008] In a possible implementation, the intelligent optimization control method for waste treatment and power generation further performs the following processing: obtaining a waste power generation simulation target, performing task extraction on the waste power generation simulation target to obtain a waste power generation prediction task set; performing association and integration on the waste historical power generation data set by using the waste power generation prediction task set to obtain a waste power generation prediction task sample set; selecting a waste power generation prediction model set according to the waste power generation prediction task sample set; and performing prediction training optimization on the waste power generation prediction task sample set based on the waste power generation prediction model set to obtain the waste power generation simulation prediction network set.

[0009] In a possible implementation, the intelligent optimization control method for waste treatment and power generation further performs the following processing: mapping the waste treatment and power generation equipment operation constraint parameter set to the waste treatment and power generation three-dimensional model for constraint coupling to obtain a waste treatment and power generation constraint model; associating the waste power generation simulation prediction network set to the waste treatment and power generation constraint model for nested twin simulation to generate a waste treatment and power generation twin driving model; and performing dynamic simulation testing and iterative parameter optimization on the waste treatment and power generation twin driving model to obtain the waste treatment and power generation digital twin.

[0010] In a possible implementation, the method further includes: performing power generation index level decomposition on the garbage treatment power generation target to obtain a garbage treatment power generation optimization evaluation index system; designing a target function based on the garbage treatment power generation optimization evaluation index system to obtain a multi-level optimization target function; and performing level nesting and weighted fusion on the multi-level optimization target function to construct the garbage power generation optimization target function.

[0011] In a possible implementation, the method further includes: embedding the garbage power generation optimization target function into the garbage treatment power generation digital twin to obtain an initial power generation control digital twin; performing working condition simulation and strategy optimization update on the initial power generation control digital twin to generate the garbage power generation control digital twin.

[0012] In a possible implementation, the method further includes: initializing a multi-source data filter according to noise characteristics of the garbage sensor network; filtering the multi-source garbage sensing data stream by using the multi-source data filter to obtain available multi-source garbage sensing data stream; and performing power generation control solving on the available multi-source garbage sensing data stream based on the garbage power generation control digital twin to determine a target power generation control parameter.

[0013] In a possible implementation, the method further includes: performing power generation dynamic scheduling and running state monitoring on the garbage treatment power generation equipment based on the target power generation control parameter to obtain garbage power generation equipment state parameters; and when the garbage power generation equipment state parameters exceed preset running limits, triggering a feedback control loop to dynamically close-loop correct the target power generation control parameter and perform garbage power generation control.

[0014] The application further provides an electronic device, including: a memory configured to store executable instructions; and a processor configured to execute the executable instructions stored in the memory to implement the method.

[0015] The application provides an intelligent optimization control method and an electronic device for garbage treatment and power generation. A garbage sensor network is arranged on a garbage treatment and power generation device to collect multi-source garbage sensing data streams. Digital twin simulation is performed based on garbage treatment and power generation device characteristic parameter streams and garbage historical power generation data sets. A garbage power generation optimization objective function is constructed and embedded into a garbage treatment and power generation digital twin. The garbage power generation control digital twin is used to solve the garbage power generation control of the multi-source garbage sensing data streams, determine target power generation control parameters, and perform power generation dynamic scheduling and feedback closed-loop control on the garbage treatment and power generation device based on the target power generation control parameters. The technical problems of difficulty in dynamic optimization of the garbage incineration and power generation process, insufficient multi-source data fusion capability, and poor real-time control strategy in the prior art are solved, and the technical effects of improving garbage power generation efficiency and optimizing equipment operation stability are achieved. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application will be briefly introduced below. In the present application, a flowchart is used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the foregoing or the following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously as needed. Meanwhile, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0017] Figure 1 A garbage treatment and power generation intelligent optimization control method flowchart is provided for the embodiments of the present application.

[0018] Figure 2 A structure diagram of an electronic device is provided for the embodiments of the present application.

[0019] Explanation of reference numerals: input device 401, processor 402, memory 403, output device 404. DETAILED DESCRIPTION

[0020] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the embodiments can be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described.

[0021] In order to make the purposes, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by those skilled in the art without making creative efforts fall within the scope of protection of the present application.

[0022] In the following description, "some embodiments" are referred to, which describe a subset of all possible embodiments, but it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict, and the term "first\second" referred to only distinguishes similar objects, and does not represent a specific order of the objects. The terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0023] The embodiments of the present application provide an intelligent optimization control method for waste treatment and power generation, as shown in the method, the method comprises: Figure 1

[0024] Step S100, deploying a waste sensor network on a waste treatment and power generation device, and collecting multi-source waste perception data streams through the waste sensor network.

[0025] Preferably, the intelligent sensing devices distributed in the key links of waste treatment are used to monitor and collect multi-dimensional data related to the characteristics of waste, the treatment process and the running state of the device in real time, and then the data is transmitted through the Internet of Things to form continuous multi-source waste perception data streams. A plurality of sensors constitute a waste sensor network and are deployed in various links of waste treatment, such as a feed inlet, an incinerator, a flue gas treatment system, etc. The waste sensor network includes a waste composition sensor for detecting the physical and chemical properties of waste, such as organic matter content, moisture content, and calorific value; a weighbridge, a laser volume scanner, etc. for monitoring the waste feeding amount in real time; a thermocouple, an infrared thermal imager, etc. for monitoring the temperature distribution in different areas of the incinerator; a gas sensor for detecting the composition of flue gas generated by combustion; a humidity sensor for measuring the moisture content of waste; a pressure and flow sensor for monitoring the airflow dynamics in the incinerator to optimize oxygen supply and combustion efficiency; a vibration and acoustic sensor for monitoring; and a waste treatment and power generation device mechanical state. The multi-source waste perception data streams collected through the waste sensor network refer to different sensors, different links, real-time continuous, heterogeneous numerical, image, spectrum, etc., mainly including waste characteristic data streams such as calorific value, composition, humidity, combustion process data streams such as furnace temperature, flue gas composition, combustion efficiency, power generation equipment state data streams such as motor speed, pressure, vibration, and environmental data streams such as emission pollutant concentration. Further, precise waste characteristic perception and monitoring of the equipment state are realized.

[0026] ​Further, the step S100 further comprises a step S110 of classifying the garbage treatment power generation equipment into functional systems to obtain a garbage power generation equipment system architecture, the garbage power generation equipment system architecture comprising a garbage receiving and feeding system, a furnace system, a flue gas treatment system, a steam turbine system, and a furnace slag sorting system; a step S120 of analyzing a processing requirement of each garbage power generation equipment system in the garbage power generation equipment system architecture to determine an equipment system garbage treatment requirement; a step S130 of performing sensor layout analysis based on the equipment system garbage treatment requirement to obtain an equipment system sensor layout parameter set; and a step S140 of deploying a sensor set on the garbage treatment power generation equipment according to the equipment system sensor layout parameter set and performing communication networking to obtain the garbage sensor network.

[0027] Preferably, the garbage treatment power generation equipment is classified into functional systems to establish a complete garbage power generation equipment system architecture, including a garbage receiving and feeding system, a furnace system, a flue gas treatment system, a steam turbine system, and a furnace slag sorting system. The garbage receiving and feeding system is responsible for receiving, temporarily storing, and conveying garbage to the furnace, and the key equipment includes a garbage unloading platform, a crusher, a grab crane, a belt conveyor, etc. The furnace system is the core combustion unit, which burns garbage at high temperature and releases heat energy, and the key equipment includes a grate furnace / fluidized bed incinerator, a fan, and combustion-supporting equipment such as a burner. The flue gas treatment system is used to purify harmful gases generated by combustion to ensure that the emissions meet the standards, and the key equipment includes an acid removal tower, a bag-type dust collector, an SCR denitration device, etc. The steam turbine system is used to convert the heat energy generated by combustion into electrical energy, and the key equipment includes a waste heat boiler, a steam turbine, a generator, etc. The furnace slag sorting system is used to process the residue after incineration and recover recyclable materials such as metals, and the key equipment includes a magnetic separator, a vibrating screen, a conveyor belt, etc.

[0028] Preferably, for each waste-to-energy system in the waste-to-energy system architecture, analyze its waste treatment requirements, i.e. key operating parameters that affect operating efficiency, safety and environmental protection, such as waste receiving and feeding system needs to monitor waste composition, feeding amount, metal, large waste, etc.; incinerator system needs to monitor combustion temperature, oxygen concentration, residence time, etc. to ensure sufficient combustion; flue gas treatment system needs to detect SO2, NOx, dust and other pollutant concentrations in real time; steam turbine system needs to monitor steam pressure, temperature, flow to ensure power generation efficiency; slag sorting system needs to identify metal content, residual ash loss on ignition rate to determine whether the combustion is sufficient. Then according to the analysis results of the treatment requirements, determine the type, number and installation position of the sensors to form the sensor layout parameter set of the equipment system, wherein the sensor types include infrared thermal imager, gas analyzer, weight sensor, etc. and multiple sensors are needed, and the installation positions include incinerator furnace, flue, feeding port, etc. For example, weight sensors and moisture meters are deployed in the feeding system to control the waste feeding ratio; thermocouples and gas analyzers are arranged in the incinerator to optimize the combustion efficiency. Finally, deploy sensors on the waste treatment power generation equipment according to the sensor layout parameter set of the equipment system, and realize communication networking through industrial Ethernet or LoRa, 5G, etc. to finally build a waste sensor network covering the whole process to realize data acquisition closed loop of the whole process of waste-to-energy.

[0029] Step S200, based on the characteristic parameter flow of the waste treatment power generation equipment and the waste historical power generation data set, digital twin simulation is carried out, and a waste treatment power generation digital twin is built.

[0030] Step S200 further comprises step S210, based on the characteristic parameter flow of the waste treatment power generation equipment, three-dimensional geometric modeling is carried out, and a waste treatment power generation three-dimensional model is generated; step S220, according to the characteristic parameter flow of the waste treatment power generation equipment, the waste treatment power generation equipment operating constraint parameter set is determined; step S230, based on the waste historical power generation data set, waste power generation simulation prediction is carried out, and a waste power generation simulation prediction network set is obtained; step S240, based on the waste treatment power generation equipment operating constraint parameter set and the waste power generation simulation prediction network set, the waste treatment power generation three-dimensional model is constrained and optimized, and a waste treatment power generation digital twin is obtained.

[0031] Preferably, according to the geometry, mechanical properties and real-time collected characteristic parameters of the waste-to-energy power plant, such as incinerator size, heat transfer coefficient, fan speed, etc., a three-dimensional model of the waste-to-energy power plant is constructed using CAD or BIM tools to realize the visual digital mapping of the physical equipment. Then, according to the equipment design specifications and real-time operation data such as the maximum temperature threshold of the incinerator, the maximum heat load, the flue gas emission limit, the steam pressure threshold, etc., the operating constraint parameter set of the waste-to-energy power plant is analyzed and determined to limit the simulation boundary conditions of the digital twin, ensuring that the virtual model is consistent with the actual working conditions of the physical equipment. Then, based on the historical waste-to-energy data set, such as the waste heat value, power generation, and pollutant emission records of the past year, a machine learning model (such as LSTM, neural network) or physical simulation model is trained to obtain a waste-to-energy simulation prediction network set for simulating the output results such as power generation efficiency and pollutant generation under different waste characteristics and operating parameters. Finally, the waste-to-energy plant operating constraint parameter set and the waste-to-energy simulation prediction network set are input into the waste-to-energy three-dimensional model for optimization, i.e., by using genetic algorithms, model predictive control, and other optimization algorithms to dynamically adjust the waste-to-energy three-dimensional model, so that it can accurately reproduce the real-time state and future waste-to-energy behavior of the physical equipment under the constraints of safety, environmental protection, and other conditions. Finally, the waste-to-energy digital twin is generated, and the virtual and real synchronization of the waste-to-energy plant is realized, thereby improving the efficiency and stability of waste-to-energy.

[0032] Further, step S230 further comprises step S231 of obtaining a waste-to-energy simulation target, step S232 of performing task extraction on the waste-to-energy simulation target to obtain a waste-to-energy prediction task set, step S233 of associating and integrating the waste-to-energy historical power generation data set using the waste-to-energy prediction task set to obtain a waste-to-energy prediction task sample set, step S234 of selecting a waste-to-energy prediction model set according to the waste-to-energy prediction task sample set, and step S235 of performing prediction training optimization on the waste-to-energy prediction task sample set based on the waste-to-energy prediction model set to obtain the waste-to-energy simulation prediction network set.

[0033] Preferably, the garbage power generation simulation target is obtained, which can include predicting power generation, optimizing combustion efficiency, and reducing pollutant emissions. The garbage power generation simulation target is extracted to be disassembled into a plurality of specific garbage power generation prediction tasks, such as predicting calorific value based on garbage composition and predicting steam output based on working condition parameters, and then a garbage power generation prediction task set is formed. For example, if the garbage power generation simulation target is to improve power generation efficiency, the extracted garbage power generation prediction tasks can include incinerator temperature prediction and garbage calorific value-power generation mapping relationship modeling. Then, the garbage power generation prediction task set is used to associate and integrate the garbage historical power generation data set, that is, according to the prediction task set, the associated data fields such as garbage composition, incineration temperature, power generation power, and emission indicators are screened from the historical power generation data set, and preprocessing such as time sequence alignment and missing value filling is performed to form a structured prediction task sample set. For example, for the calorific value-power generation prediction task, the historical garbage detection data and the contemporaneous power generation records are integrated to build a sample pair of input (garbage calorific value, combustion humidity) -output (power generation, gas pollutant emission).

[0034] Preferably, a garbage power generation prediction model set is selected according to the garbage power generation prediction task sample set, wherein the garbage power generation prediction model can include an LSTM time series prediction model, a random forest classification regression model, and a combustion dynamics-thermal balance model. Then, the garbage power generation prediction task sample set is predicted, trained, and optimized according to the garbage power generation prediction model set to improve the prediction accuracy of the garbage power generation prediction model through hyperparameter tuning, cross-validation, etc. Finally, a group of high-performance prediction models, i.e., a garbage power generation simulation prediction network set, is obtained, which can predict power generation efficiency in real time, simulate equipment behavior under different working conditions, and provide data support for dynamic optimization of digital twins.

[0035] Further, step S240 further includes step S241 of mapping the garbage disposal power generation equipment operation constraint parameter set to the garbage disposal power generation three-dimensional model for constraint coupling to obtain a garbage disposal power generation constraint model; step S242 of associating the garbage power generation simulation prediction network set to the garbage disposal power generation constraint model for nested twin simulation to generate a garbage disposal power generation twin driving model; and step S243 of performing dynamic simulation testing and iterative parameter optimization on the garbage disposal power generation twin driving model to obtain the garbage disposal power generation digital twin.

[0036] Preferably, a set of operation constraint parameters of the waste-to-energy power plant, such as the temperature limit of the incinerator, the maximum load of the steam turbine, the environmental emission threshold, etc., are mapped to the waste-to-energy three-dimensional model for constraint coupling, i.e. the constraint conditions such as furnace temperature and flue gas emission concentration are embedded in the waste-to-energy three-dimensional model in the form of mathematical rules or logical judgments, for example, in the simulation, the temperature parameter is forced to be limited to a safe value, the emission compliance verification unit is added to the flue gas treatment system, etc., so as to obtain a virtual model that not only retains the three-dimensional visualization capability but also meets the actual operation restrictions, i.e. a waste-to-energy constraint model. Then, the waste-to-energy simulation prediction network set is associated with the waste-to-energy constraint model for nested twin simulation, i.e. the prediction model and the constraint model are dynamically associated to form a bidirectional interaction, including forward driving, inputting real-time waste data, the prediction model calculating the power generation, pollutant, etc. and feeding back to the three-dimensional model for dynamic display; reverse constraint, the equipment state in the three-dimensional model as a boundary condition, constraining the output range of the prediction model; and then outputting a waste-to-energy twin driving model that can simulate real working conditions and respond to parameter changes. Finally, the waste-to-energy twin driving model is subjected to dynamic simulation test and iterative parameter optimization, wherein the dynamic simulation test refers to simulating extreme working conditions such as high-humidity waste into the furnace and equipment sudden failure in the virtual environment to verify the robustness of the twin driving model; the iterative parameter optimization is through closed-loop feedback, such as comparing the actual power generation data with the simulation results and adjusting the model parameters using reinforcement learning, for example, optimizing the air supply coefficient of the combustion control model and correcting the weight deviation of the heat value prediction model, so as to finally output a waste-to-energy digital twin that can predict and optimize the operation strategy in real time.

[0037] In step S300, the waste-to-energy target is subjected to power generation index disassembly and objective function design, an optimization objective function of waste-to-energy is constructed, and the optimization objective function of waste-to-energy is embedded into the waste-to-energy digital twin to generate a waste-to-energy control digital twin.

[0038] Preferably, the garbage treatment and power generation target is decomposed into power generation index, and quantifiable sub-indices are obtained, such as unit garbage power generation, steam turbine efficiency, pollution gas emission concentration, residue heat loss reduction rate, fuel consumption cost, equipment maintenance frequency, etc. Then, a multi-objective optimization function, i.e. garbage power generation optimization target function, is constructed based on the decomposed indices in a weighted constraint form. If there are conflicting targets, such as increasing power generation leading to increased emissions, a Pareto optimization or constraint optimization method is used to balance the indices. Then, the garbage power generation optimization target function is embedded into the garbage treatment and power generation digital twin, so that it can dynamically calculate the optimal control parameters according to the sensor data and simulate the influence of different control strategies on the garbage power generation optimization target function in the virtual environment. Finally, a garbage power generation control digital twin is formed, which receives real-time sensor data, predicts the power generation and emission results of different control schemes based on the garbage power generation control digital twin, calls the target function to solve the optimal parameters and then issues them to the physical equipment for execution, forming a closed-loop feedback and realizing real intelligent control to improve the stability and efficiency of garbage treatment and power generation.

[0039] Further, step S300 further includes step S310 of performing hierarchical decomposition on the garbage treatment and power generation target to obtain a garbage treatment and power generation optimization evaluation index system; step S320 of designing a target function based on the garbage treatment and power generation optimization evaluation index system to obtain a multi-level optimization target function; and step S330 of hierarchically nesting and weightedly fusing the multi-level optimization target function to construct the garbage power generation optimization target function.

[0040] Preferably, the garbage treatment and power generation target is hierarchically decomposed into power generation indices. Specifically, the maximum energy recovery rate and the minimum comprehensive operation cost are decomposed into first-level indices, including energy efficiency index power generation efficiency, steam production, environmental protection index pollutant emission concentration, residue harmless rate, economic index tons of garbage treatment cost, equipment maintenance cost. Then, the first-level indices are decomposed to obtain second-level indices, including garbage heat value utilization rate, boiler thermal efficiency, pollution gas emission, fuel consumption cost, manual intervention frequency, etc., to form a tree-structured garbage treatment and power generation optimization evaluation index system covering all key influencing factors. Then, a target function is designed according to the garbage treatment and power generation optimization evaluation index system, i.e. a sub-target function is designed for each level of index and embedded with equipment operation restrictions and emission standards to obtain a multi-level optimization target function. Finally, the multi-level optimization target function is hierarchically nested according to the garbage treatment and power generation optimization evaluation index system, and weightedly fused according to historical data to output the garbage power generation optimization target function, which can be embedded into the garbage treatment and power generation digital twin for control decision.

[0041] Further, step S300 further comprises step S340 of embedding the garbage power optimization objective function into the garbage treatment power digital twin to obtain an initial power generation control digital twin; and step S350 of performing working condition simulation and strategy optimization update on the initial power generation control digital twin to generate the garbage power generation control digital twin.

[0042] Preferably, embedding the designed garbage power optimization objective function into the garbage treatment power digital twin comprises embedding a linear programming solver in the garbage treatment power digital twin for real-time calculation of optimal control parameters, establishing a variable mapping relationship between the objective function and the three-dimensional simulation model, and obtaining an initial power generation control digital twin, which can perform decision optimization on the basis of perception simulation functions; and then performing working condition simulation and strategy optimization update on the initial power generation control digital twin, specifically, simulating typical working conditions in the initial power generation control digital twin, including testing control strategies under different garbage components (high calorific value / high moisture), simulating emergency plans when equipment fails or environmental protection indicators exceed standards; and then comparing simulation results with actual operation data to correct model parameters, and when the prediction deviation exceeds a threshold, triggering reinforcement learning update strategy network of the machine learning model, while real-time updating the set of operation constraint parameters; through continuous simulation-optimization cycles, the prediction accuracy and control reliability of the initial power generation control digital twin are improved, and finally the garbage power generation control digital twin is generated, thereby improving garbage power generation efficiency and optimizing equipment operation stability.

[0043] Step S400 adopts the garbage power generation control digital twin to perform garbage power generation control solving on the multi-source garbage perception data stream, determines target garbage power generation control parameters, and performs garbage power dynamic scheduling and feedback closed-loop control on the garbage treatment power equipment based on the target garbage power generation control parameters.

[0044] Preferably, the garbage power generation control digital twin is used to perform garbage power generation control solving on the multi-source garbage perception data stream, that is, the multi-source garbage perception data stream is injected into the garbage power generation control digital twin to predict the overall state of future garbage treatment power generation in a virtual environment, a multi-objective optimization algorithm is used to solve the optimal solution of garbage power generation control, and then target garbage power generation control parameters such as air volume ratio and grate movement speed are determined; then the target garbage power generation control parameters are converted into control instructions, transmitted to the garbage treatment power equipment through an industrial bus, and garbage power dynamic scheduling is performed, which may include adjusting the garbage input amount and feeding speed of the garbage receiving and feeding system, and optimizing the damper opening degree and grate movement mode of the incinerator system; then the deviation between the actual power generation and the predicted value is compared in real time, and whether the key environmental protection indicators meet the standards is monitored, when the deviation continuously exceeds the threshold, the digital twin model is retrained and optimized, and then the feedback update of the target garbage power generation control parameters is realized to complete the feedback closed-loop control, thereby improving the garbage treatment power efficiency, the environmental protection standard reaching rate, and the operation stability of the garbage treatment power equipment.

[0045] Further, step S400 further comprises step S410, initializing a multi-source data filter according to noise characteristics of the garbage sensor network; step S420, filtering the multi-source garbage perception data stream using the multi-source data filter to obtain a usable multi-source garbage perception data stream; step S430, solving garbage power generation control based on the garbage power generation control digital twin to determine the target garbage power generation control parameter.

[0046] Preferably, the garbage sensor network is analyzed and identified to determine the noise characteristics, which can include periodic interference caused by mechanical vibration, signal jump caused by electromagnetic interference, and baseline drift caused by environmental factors. A hybrid filtering scheme is constructed according to the noise characteristics to initialize the multi-source data filter. Specifically, for fast fluctuation signals such as furnace temperature, moving average and wavelet transform are used to eliminate high-frequency noise; for slowly varying signals such as garbage bin level, Kalman filter is used to predict the real trend; for composition analysis data such as heat value detection, spectral denoising algorithm is configured to improve the signal-to-noise ratio.

[0047] Preferably, the multi-source data filter is used to filter the multi-source garbage perception data stream, that is, the data streams of different sampling frequencies are processed in parallel, and the filtering parameters are dynamically adjusted, such as switching the vibration filtering intensity according to the crusher start-stop state, then identifying and removing sensor readings that obviously exceed the physical possibility, and then performing data quality verification, including physical reasonableness verification such as incinerator temperature cannot be lower than ambient temperature, cross-sensor consistency verification of the coupling relationship between steam flow and power generation power, and timing continuity check, to obtain the usable multi-source garbage perception data stream. The usable multi-source garbage perception data stream is then input into the garbage power generation control digital twin for power generation control solving, including predicting the future garbage treatment power generation equipment running state evolution and selecting the comprehensive optimal solution from multiple feasible solutions, and finally outputting directly executable control instructions as the target garbage power generation control parameter, such as air volume, grate speed, activated carbon injection rate, and maximum allowed load variation gradient, to ensure the control accuracy, running stability and reliability of garbage treatment power generation.

[0048] Further, step S400 further comprises step S440, performing garbage power generation dynamic scheduling and running state monitoring based on the target garbage power generation control parameter to obtain garbage power generation equipment state parameters; step S450, when the garbage power generation equipment state parameters exceed the preset running limit value, triggering a feedback control loop to dynamically close-loop correct the target garbage power generation control parameter and garbage power generation control.

[0049] Preferably, the target power generation control parameter is converted into a device executable control instruction, transmitted to the waste treatment power generation device to perform power generation dynamic scheduling, including adjusting the damper opening, controlling the waste input rate and optimizing the activated carbon injection amount, and then establishing device linkage logic, for example, when the heat value increases, the air volume is increased synchronously and the frequency of the grate movement is adjusted, and when the steam pressure fluctuates, the feed water pump and the turbine control valve are coordinated to act; then the device response data, i.e. the waste power generation device state parameters, including the combustion state, the steam pressure and temperature, and the flue gas particulate matter concentration, are obtained by real-time monitoring of the operating state through the sensor network. If the waste power generation device state parameters exceed the preset operating limit, a feedback control loop is triggered to dynamically correct the target power generation control parameter and control the waste power generation, specifically, the digital twin distinguishes between real abnormalities and sensor failures and identifies the abnormal propagation path, and then corrects the target power generation control parameter based on the real-time working condition, and then uses the adjusted control parameter to accurately control the waste treatment power generation device, thereby improving the waste treatment power generation efficiency and operation stability.

[0050] The intelligent optimization control system for waste treatment power generation provided by the embodiments of the present application can execute the intelligent optimization control method for waste treatment power generation provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0051] Figure 2 FIG. 1 is a structural schematic diagram of an electronic device provided by the embodiments of the present application, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present application. Figure 2 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application. The electronic device is in the form of a general computing device, and its components can include but are not limited to an input device 401, a processor 402, a memory 403 and an output device 404. The processor 402 can be one or more; the memory 403 can include a computer readable medium and at least one program product, which has a set of (at least one) program modules configured to perform the functions of the embodiments of the present application.

[0052] The memory 403 shown in the embodiments of the present application can adopt any combination of one or more computer readable media; the computer readable storage medium can be but is not limited to an infrared ray, a semiconductor system, a device or a component, or any combination of the above, for storing software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the intelligent optimization control method for waste treatment power generation in the embodiments of the present application. The processor 402 performs various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 403, i.e. implements the above-mentioned intelligent optimization control method for waste treatment power generation.

[0053] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server, the various units and modules included are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific name of each functional unit is only for the convenience of mutual differentiation, and is not used to limit the protection scope of the present application.

[0054] 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 and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions 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. An intelligent optimization control method for waste disposal power generation, characterized by, The method comprises: deploying a garbage sensor network on a garbage disposal power generation device, acquiring a multi-source garbage perception data stream through the garbage sensor network; carrying out digital twin simulation based on a characteristic parameter stream of the garbage disposal power generation device and a garbage historical power generation data set, and building a garbage disposal power generation digital twin; carrying out power generation index disassembly and target function design on a garbage disposal power generation target, constructing a garbage power generation optimization target function, embedding the garbage power generation optimization target function into the garbage disposal power generation digital twin, and generating a garbage power generation control digital twin; using the garbage power generation control digital twin to solve garbage power generation control, determining a target power generation control parameter, and performing power generation dynamic scheduling and feedback closed-loop control on the garbage disposal power generation device based on the target power generation control parameter; the building of the garbage disposal power generation digital twin comprises: carrying out three-dimensional geometric modeling based on the characteristic parameter stream of the garbage disposal power generation device, and generating a garbage disposal power generation three-dimensional model; determining a garbage disposal power generation device operation constraint parameter set according to the characteristic parameter stream of the garbage disposal power generation device; carrying out garbage power generation simulation prediction based on the garbage historical power generation data set, and obtaining a garbage power generation simulation prediction network set; carrying out constraint optimization on the garbage disposal power generation three-dimensional model based on the garbage disposal power generation device operation constraint parameter set and the garbage power generation simulation prediction network set, and obtaining a garbage disposal power generation digital twin; the obtaining of the garbage disposal power generation digital twin comprises: mapping the garbage disposal power generation device operation constraint parameter set to the garbage disposal power generation three-dimensional model for constraint coupling, and obtaining a garbage disposal power generation constraint model; associating the garbage power generation simulation prediction network set to the garbage disposal power generation constraint model for nested twin simulation, and generating a garbage disposal power generation twin driving model; carrying out dynamic simulation test and iterative parameter optimization on the garbage disposal power generation twin driving model, and obtaining the garbage disposal power generation digital twin.

2. The intelligent optimization control method for waste disposal power generation according to claim 1, wherein, the deployment of the garbage sensor network on the garbage disposal power generation device comprises: carrying out functional system classification on the garbage disposal power generation device, obtaining a garbage power generation device system architecture, and the garbage power generation device system architecture comprising a garbage receiving and feeding system, a incinerator system, a flue gas treatment system, a steam turbine system and a slag sorting system; carrying out processing demand analysis on each garbage power generation device system in the garbage power generation device system architecture, and determining device system garbage disposal demand; carrying out sensor layout analysis based on the device system garbage disposal demand, and obtaining a device system sensor layout parameter set; deploying a sensor set on the garbage disposal power generation device according to the device system sensor layout parameter set and communication networking, and obtaining the garbage sensor network.

3. The intelligent optimization control method for waste treatment power generation according to claim 1, characterized in that: the obtaining of the garbage power generation simulation prediction network set comprises: obtaining a garbage power generation simulation target, carrying out task extraction on the garbage power generation simulation target, and obtaining a garbage power generation prediction task set; The garbage power prediction task set is used for associated integration of the garbage historical power generation data set, and a garbage power prediction task sample set is obtained; According to the garbage power prediction task sample set, a garbage power prediction model set is selected; Based on the garbage power prediction model set, the garbage power prediction task sample set is predicted and trained and optimized, and the garbage power simulation prediction network set is obtained.

4. The intelligent optimization control method for waste disposal power generation according to claim 1, characterized in that, The construction of the garbage power optimization objective function includes: The garbage treatment power generation target is decomposed in a power generation index level to obtain a garbage treatment power generation optimization evaluation index system; Based on the garbage treatment power generation optimization evaluation index system, a target function is designed to obtain a multi-level optimization target function; The multi-level optimization target function is hierarchically nested and weightedly fused to construct the garbage power optimization objective function.

5. The intelligent optimization control method for waste disposal power generation according to claim 1, characterized in that, The generation of the garbage power control digital twin includes: The garbage power optimization objective function is embedded into the garbage treatment power generation digital twin to obtain an initial power generation control digital twin; The initial power generation control digital twin is simulated and updated in a working condition to generate the garbage power control digital twin.

6. The intelligent optimization control method for waste disposal power generation according to claim 1, wherein, The determination of the target power generation control parameter includes: According to the noise characteristics of the garbage sensor network, a multi-source data filter is initialized; The multi-source garbage perception data stream is filtered using the multi-source data filter to obtain an available multi-source garbage perception data stream; Based on the garbage power control digital twin, the available multi-source garbage perception data stream is solved to determine the target power generation control parameter.

7. The intelligent optimization control method for waste disposal power generation according to claim 1, characterized in that, The garbage treatment power generation equipment is executed based on the target power generation control parameter to perform power generation dynamic scheduling and feedback closed-loop control, including: Based on the target power generation control parameter, the garbage treatment power generation equipment is executed to perform power generation dynamic scheduling and operation state monitoring to obtain garbage power generation equipment state parameters; When the garbage power generation equipment state parameters exceed the preset operating limit value, a feedback control loop is triggered to dynamically correct the target power generation control parameter and control garbage power generation.

8. An electronic device, comprising: The electronic device includes: A memory for storing executable instructions; A processor for executing the executable instructions stored in the memory to implement the intelligent optimization control method of the garbage treatment power generation of any one of claims 1-7.

Images