Black light plant control method, device and equipment of waste incineration power plant

Abstract

This disclosure provides a method, apparatus, and equipment for controlling a "lights-out" waste-to-energy plant, relating to the field of industrial automation technology. The method includes: acquiring economic parameters and operational data of the waste-to-energy plant; determining the current operational state of the waste-to-energy plant; when the current operational state is a stable waste supply, controlling the operation of the waste-to-energy plant based on the economic parameters and operational data with the objective of maximizing power generation revenue; and when the current operational state is a waste surge, controlling the operation of the waste-to-energy plant based on the economic parameters and operational data with the objective of maximizing waste processing capacity. This method can improve intelligence and automation, and increase control efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of industrial automation technology, and in particular to a method, apparatus and equipment for controlling a lights-out factory in a waste incineration power plant. Background Technology

[0002] In related technologies, the control systems of waste-to-energy plants typically operate independently as single systems. For example, each process segment, such as incineration, flue gas purification, and power generation, operates independently, lacking a comprehensive collaborative optimization mechanism. This results in severe information silos, making it difficult to translate local optima into maximizing overall energy efficiency. This hinders the transformation and upgrading of waste-to-energy plants towards intelligent and unmanned operation, leading to low levels of intelligence and low operational efficiency. Summary of the Invention

[0003] This disclosure provides a method, apparatus, and equipment for controlling the "lights-out" process in a waste-to-energy incineration plant.

[0004] According to a first aspect of this disclosure, a method for controlling a lights-out process in a waste-to-energy incineration plant is provided, comprising:

[0005] Obtain economic parameters and operational data of waste-to-energy plants;

[0006] Determine the current operating status of the waste-to-energy plant;

[0007] When the current operating state of the waste incineration power plant is a stable waste supply, the operation of the waste incineration power plant is controlled based on the economic parameters and operating data with the goal of maximizing the power generation revenue of the waste incineration power plant.

[0008] When the current operating state of the waste incineration power plant is a state of surge in waste volume, the operation of the waste incineration power plant is controlled based on the economic parameters and operating data with the goal of maximizing the waste processing capacity of the waste incineration power plant.

[0009] According to a second aspect of this disclosure, a blackout plant control device for a waste incineration power plant is provided, comprising:

[0010] The data acquisition module is used to obtain economic parameters and operational data of waste-to-energy plants.

[0011] The status monitoring module also determines the current operating status of the waste incineration power plant;

[0012] The global optimization module is used to control the operation of the waste-to-energy plant with the goal of maximizing its power generation revenue when the current operating state of the waste-to-energy plant is a stable waste supply state, based on the economic parameters and operating data; and to control the operation of the waste-to-energy plant with the goal of maximizing its waste processing capacity when the current operating state of the waste-to-energy plant is a state of surging waste volume, based on the economic parameters and operating data.

[0013] The local optimization module is used to control the waste-to-energy plant to operate at its maximum power generation capacity based on the economic parameters and operating data when the current operating state of the waste-to-energy plant is a stable waste supply state, provided that the total waste processing volume remains stable; and to control the waste-to-energy plant to operate at its maximum waste processing capacity based on the economic parameters and operating data when the current operating state of the waste-to-energy plant is a waste surge state, provided that the incinerator and flue gas purification subsystem of the waste-to-energy plant are operating at full load and meet standards.

[0014] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and,

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0018] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0019] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0020] In the embodiments of this disclosure, by acquiring the economic parameters and operational data of the waste-to-energy plant, the current operational status of the waste-to-energy plant is determined. When the current operational status of the waste-to-energy plant is a stable waste supply state, the plant is controlled to maximize its power generation revenue based on the economic parameters and operational data. When the current operational status of the waste-to-energy plant is a state of surging waste volume, the plant is controlled to maximize its waste processing capacity based on the economic parameters and operational data. This allows for the construction of a global-local bidirectional interactive intelligent optimization system, overcoming the energy efficiency bottleneck caused by the independent operation of traditional single systems, thereby effectively improving the overall plant efficiency. Furthermore, through state perception and dynamic target switching, the need for manual intervention can be effectively reduced, increasing intelligence and automation, and improving control efficiency.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0022] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0023] Figure 1 A schematic flowchart illustrating a method for controlling a lights-out process in a waste-to-energy plant, as provided in this embodiment of the disclosure;

[0024] Figure 2 This is a schematic diagram of a system architecture for implementing a blackout factory control method for waste incineration power plants, provided by an embodiment of the present disclosure;

[0025] Figure 3 A schematic flowchart illustrating an implementation method for closed-loop control of health and environment provided in this disclosure embodiment;

[0026] Figure 4 A flowchart illustrating an implementation method for a cross-system collaboration mechanism provided in this embodiment of the disclosure;

[0027] Figure 5 This is a schematic diagram of a blackout plant control device for a waste incineration power plant, provided as an embodiment of the present disclosure. Detailed Implementation

[0028] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0029] The following describes, with reference to the accompanying drawings, a method, system, and equipment for controlling a "lights-out" plant in a waste-to-energy incineration plant according to embodiments of the present disclosure.

[0030] Figure 1 This is a schematic flowchart illustrating a method for controlling a "lights-out" process in a waste-to-energy incineration plant, as provided in an embodiment of this disclosure. Figure 1 As shown, the method includes the following steps:

[0031] Step 101: Obtain the economic parameters and operating data of the waste-to-energy plant.

[0032] In the embodiments disclosed herein, economic parameters and operational data of a waste-to-energy plant can be collected. Economic parameters may include real-time electricity prices, waste treatment subsidy unit prices, and procurement costs of environmental protection materials (such as deacidifying agents and activated carbon). Operational data may include the operating status of all plant equipment, such as furnace temperature, steam flow rate, grate speed of the incinerator, pollutant concentration and reagent dosing rate of the flue gas purification system, and steam turbine inlet parameters and power generation.

[0033] Step 102: Determine the current operating status of the waste-to-energy plant.

[0034] In the embodiments of this disclosure, the current operating status of the power plant (waste incineration power plant) can also be determined. For example, the "stable waste supply state" or "surge in waste supply state" can be identified based on the rate of change of waste silo level, the frequency of waste truck arrivals, and historical data trend analysis. For instance, when the waste supply is maintained at a set percentage of the design capacity (e.g., 60%-80%) and the daily waste arrival fluctuation is less than a preset percentage (e.g., 15%), it can be determined to be a stable state; conversely, when the level continues to rise to a surge percentage (e.g., above 90%) and the daily waste arrival increase exceeds a set increase percentage (e.g., 30%) and continues for a set duration (e.g., above 2 hours), it can be determined to be a surge state.

[0035] Step 103: Under the condition that the current operating status of the waste incineration power plant is a stable waste supply, control the operation of the waste incineration power plant based on economic parameters and operating data with the goal of maximizing the power generation revenue of the waste incineration power plant.

[0036] In the embodiments of this disclosure, if the current operating state of the waste-to-energy plant is a stable waste supply state, the operation of the waste-to-energy plant can be controlled based on economic parameters and operational data, with the goal of maximizing the power generation revenue of the waste-to-energy plant. For example, a pre-built digital twin model of the entire plant can be invoked, and economic parameters and operational data, such as real-time electricity prices, subsidy standards, environmental costs, and equipment status parameters, can be input. A mixed-integer programming algorithm can then be used to calculate the optimal load allocation strategy. For instance, taking advantage of the low nighttime temperatures and high power generation efficiency, the incinerator can be instructed to increase its processing load at night and appropriately reduce its load during the day, thereby maximizing the power generation of the turbine while keeping the total daily waste processing volume constant. As a specific example, during periods of higher nighttime electricity prices, the incinerator can be instructed to increase its processing load by 5%-10% (or other values), while simultaneously optimizing the turbine guide vane opening to the optimal efficiency point; during periods of lower daytime electricity prices, the load can be appropriately reduced, thereby increasing the turbine's power generation by 3%-5% while keeping the total daily waste processing volume constant, thus maximizing power generation revenue.

[0037] Step 104: When the current operating state of the waste incineration power plant is a surge in waste volume, control the operation of the waste incineration power plant based on economic parameters and operating data with the goal of maximizing the waste processing capacity of the waste incineration power plant.

[0038] In the embodiments of this disclosure, if the current operating state of the waste-to-energy plant is a state of surge in waste volume, the operation of the waste-to-energy plant is controlled based on economic parameters and operational data, with the goal of maximizing the waste processing capacity of the waste-to-energy plant. For example, the incinerator and flue gas purification system can operate at full load while ensuring environmental compliance, allowing the turbine power generation efficiency to temporarily deviate from its local optimum. As an example, when the amount of urban waste surges in the short term (such as during peak tourist season), the global objective switches to "maximizing the amount of waste treated harmlessly." At this time, the global optimization system will govern all local optimization systems, allowing the turbine power generation efficiency to temporarily deviate from its local optimum, prioritizing ensuring that the incinerator and flue gas purification system process all waste at full load and in compliance with emission standards.

[0039] In the embodiments of this disclosure, by acquiring the economic parameters and operational data of the waste-to-energy plant, the current operational status of the waste-to-energy plant is determined. When the current operational status of the waste-to-energy plant is a stable waste supply state, the plant is controlled to maximize its power generation revenue based on the economic parameters and operational data. When the current operational status of the waste-to-energy plant is a state of surging waste volume, the plant is controlled to maximize its waste processing capacity based on the economic parameters and operational data. This allows for the construction of a global-local bidirectional interactive intelligent optimization system, overcoming the energy efficiency bottleneck caused by the independent operation of traditional single systems, thereby effectively improving the overall plant efficiency. Furthermore, through state perception and dynamic target switching, the need for manual intervention can be effectively reduced, increasing intelligence and automation, and improving control efficiency.

[0040] In some possible implementations, assuming the current operating state of the waste-to-energy plant is one of stable waste supply, the plant's operation is controlled based on economic parameters and operational data with the objective of maximizing its power generation revenue. This includes:

[0041] When the current operating state of the waste incineration power plant is a stable waste supply, the turbine of the waste incineration power plant is controlled to operate at the maximum power generation state based on economic parameters and operating data, provided that the total amount of waste processed remains stable.

[0042] Given that the current operating state of the waste-to-energy plant is characterized by a surge in waste volume, the plant's operation is controlled based on economic parameters and operational data, with the goal of maximizing its waste processing capacity. This includes:

[0043] When the current operating state of the waste-to-energy plant is a surge in waste volume, the plant is controlled to operate at its maximum waste processing capacity based on economic parameters and operating data, while ensuring that the incinerator and flue gas purification subsystem are operating at full load and meet standards.

[0044] In the embodiments of this disclosure, when the current operating state of the waste-to-energy plant is a stable waste supply state, the turbine of the waste-to-energy plant can be controlled to operate at the highest power generation state based on economic parameters and operating data, provided that the total amount of waste processed remains stable. For example, a pre-built digital twin model of the entire plant can be invoked, and real-time electricity prices, subsidy standards, environmental protection material costs, and equipment status parameters can be input. A mixed-integer programming algorithm can then be used to calculate the optimal load allocation strategy. As a specific example, the low nighttime temperatures and high power generation efficiency can be utilized to instruct the incinerator to increase its processing load at night, while simultaneously optimizing the turbine guide vane opening to the optimal efficiency point. During the daytime low electricity price period, the load can be appropriately reduced, thereby maximizing power generation revenue while keeping the total daily waste processing volume constant. During this process, the local optimization system responds to global commands in real time: the incinerator local controller takes combustion stability as a sub-objective and adjusts the ratio of primary air and secondary air and the grate speed in real time through the built-in combustion optimization controller; the flue gas purification system takes the lowest reagent cost as a sub-objective and finely adjusts the injection amount of various reagents through the material addition optimization controller, forming a two-way closed-loop collaborative mechanism in which the global system governs the local system and the local system feeds back to the global system.

[0045] When a waste-to-energy plant is currently operating under conditions of a surge in waste volume, the plant is controlled to operate at its maximum waste processing capacity, while ensuring that the incinerator and flue gas purification subsystem operate at full load and meet standards. This is based on economic parameters and operational data. For example, priority can be given to ensuring that the incinerator and flue gas purification system operate at full load while meeting environmental standards, allowing the turbine power generation efficiency to temporarily deviate from its local optimum. As an example, by calculating the maximum processing capacity boundaries of each device using a digital twin model, the incinerator is instructed to increase its grate speed to the rated upper limit and increase the primary air volume to the design maximum. Simultaneously, the flue gas purification system increases the reserve of deacidifying agents and activated carbon in advance. Utilizing the approximately 10-second flue gas transmission delay between the incinerator and the purification system, the purification system adjusts its purification parameters in advance based on feedforward information to ensure pollutant emissions meet standards. When the flue gas purification system reaches its maximum agent dosing capacity or the negative pressure value touches the -30Pa safety threshold, a baseline feedback mechanism is immediately triggered. The local system feeds back capacity limitation information to the global system, which then proactively limits the increase in waste processing volume to no more than 10% and activates the emergency dispatch plan to ensure the overall safe and stable operation of the system. In this way, the plant's daily processing capacity can be effectively increased, effectively achieving the overall goal of maximizing the harmless treatment of waste.

[0046] In some possible implementations, it also includes:

[0047] If the operating parameter of at least one of the steam turbine, incinerator, and flue gas purification subsystems has reached a set threshold, adjust at least one of the maximum power generation and maximum waste processing capacity.

[0048] The threshold values ​​are not fixed values; they can be multi-dimensional parameter envelopes that are dynamically calculated based on equipment safety operation standards, environmental emission limits, and historical operating data. These include, but are not limited to, the upper limit of the deacidifying agent / activated carbon addition capacity of the flue gas purification system, the lower limit of the negative pressure value (-30Pa), the upper limit of the incinerator furnace temperature, the turbine vibration amplitude threshold, and the bearing temperature limit.

[0049] In the embodiments of this disclosure, when the operating parameters of any local system in the turbine, incinerator, or flue gas purification subsystem reach the corresponding set threshold, a degradation adjustment strategy can be automatically initiated. For example, under a stable waste supply condition, the maximum power generation target can be lowered, for example, by 3%-8%, instructing the incinerator to reduce grate speed and primary air volume, while optimizing turbine load distribution to avoid equipment overload. Alternatively, under a surge in waste volume, the maximum waste processing capacity target can be lowered, for example, by 10%-15%, prioritizing the compliance of the flue gas purification system with emission standards. In this way, a two-way closed loop can be achieved from local equipment constraints to dynamic correction of global targets, ensuring that when approaching physical limits or environmental bottom lines, the system can proactively yield rather than stubbornly continue operating, thereby effectively avoiding serious accidents such as equipment damage and environmental violations, and providing safety assurance for the long-term unmanned operation of the "lights-out" factory.

[0050] In some possible implementations, it also includes:

[0051] Monitor environmental parameters within a designated area of ​​the waste-to-energy plant; the environmental parameters include preset gas concentrations and negative pressure values, and the preset gas is at least one type.

[0052] When the preset gas concentration and negative pressure value meet the preset ventilation conditions, the target area corresponding to the preset gas concentration and negative pressure value that meet the preset ventilation conditions is determined, and the ventilation volume of the target area is increased; wherein, the preset ventilation conditions include: the existence of at least one preset gas concentration greater than a set concentration threshold, and the negative pressure value greater than a set negative pressure value threshold.

[0053] In the embodiments of this disclosure, an environmental monitoring sensor network covering key areas of the entire plant can be constructed to achieve real-time perception and dynamic acquisition of safety parameters of the production environment. For example, wide-area gas sensors based on electrochemical or infrared spectroscopy principles can be deployed in open workshop areas such as fly ash storage silos and waste unloading halls to continuously monitor the concentrations of toxic and harmful gases with persistent hazardous characteristics, such as CS2 and ammonia (NH3). In enclosed or semi-enclosed confined spaces such as waste pits and leachate channels, high-sensitivity point-type gas detectors and micro-differential pressure transmitters can be deployed to focus on monitoring the instantaneous concentrations of gases with acute poisoning risks, such as H2S and CO, and simultaneously collect negative pressure data for the area, maintaining a micro-negative pressure environment of -30 Pa to -50 Pa to prevent the leakage of harmful gases. Then, it can be determined whether the preset gas concentration and negative pressure value meet the preset ventilation conditions. For example, the concentration threshold and negative pressure threshold are dynamically set according to the area's risk level; for instance, the NH3 concentration threshold in the fly ash storage silo is set to 20 mg / m³, and the lower limit of the negative pressure value is set to -30 Pa. When the concentration of at least one preset gas exceeds a set threshold in any area, or the negative pressure deviates from the safe range (e.g., above -30 Pa), a high-priority safety event can be immediately triggered. The coordinates of the exceeding sensor can be quickly located using a Geographic Information System (GIS), accurately identifying the corresponding target area. Subsequently, control commands can be sent to the ventilation and negative pressure equipment in the target area (including but not limited to variable frequency fans, electric dampers, and negative pressure regulating valves) to increase the ventilation volume. For example, ventilation can be activated at maximum frequency or opening to ensure that the concentration of harmful gases is reduced to below the set percentage of the safe limit or safety threshold (e.g., below 50%) within a first set time period (e.g., 30 seconds), or that the negative pressure is restored to the ideal range of -40 Pa to -50 Pa within a second set time period (e.g., 60 seconds). Alternatively, the safety event and its handling can be recorded in a log database, and alarm information can be pushed to the upper-level monitoring system, forming a complete closed-loop evidence chain. In this way, a closed-loop control system for environmental safety can be constructed, transforming the traditional manual inspection and passive disposal mode into an intelligent prevention and control mode of proactive perception and automatic response. This can not only effectively reduce the average handling time of hazardous gas exceedance incidents and greatly reduce personnel health risks and the probability of environmental violations, but also provide safety guarantees for the unmanned operation of "lights-out" factories, facilitating the transformation and upgrading of waste incineration power plants towards intelligence and green development.

[0054] In some possible implementations, it also includes:

[0055] The system acquires first waste information of the received waste and operating data of the incinerator within a preset historical time period; wherein, the first waste information includes at least one of waste source, waste type, and waste weight;

[0056] Based on the first waste information and operational data, a waste characteristic prediction model is used to predict the second waste information that will soon enter the incinerator; the second waste information includes the calorific value and composition of the waste.

[0057] The operating parameters of the incinerator are pre-adjusted based on the calorific value and composition of the waste.

[0058] In the embodiments of this disclosure, a material-incineration collaborative chain can be constructed to achieve accurate prediction of waste calorific value and advance control of combustion. For example, when a garbage truck is weighed upon entering the plant, the origin (e.g., residential area, commercial area, industrial area), type (e.g., kitchen waste, plastic, paper), and weight information of each batch of waste can be identified or manually entered as the first waste information. Additionally, operational data from the incinerator within a preset historical period (e.g., the last 8 hours) can be obtained, including but not limited to furnace temperature curves, steam flow fluctuations, primary / secondary air ratio, grate speed, and historical waste calorific value estimates. Then, the first waste information and operational data are input into a waste characteristic prediction model, which is constructed using machine learning algorithms to achieve high-precision prediction of the calorific value and composition of the waste entering the incinerator. For example, a waste characteristic prediction model can use the first waste information as a static feature vector and the incinerator's 8-hour operating data as a dynamic feature sequence to predict and output the second waste information about to enter the incinerator. This includes the predicted calorific value (LHV) of the waste (accuracy up to ±5%) and the proportion of key waste components (such as moisture content, ash content, and chlorine content). The predicted information can then be converted into feedforward control commands to pre-adjust the incinerator's operating parameters, achieving proactive intervention in the combustion process rather than passive compensation. For instance, the grate speed (e.g., decelerating when the calorific value is high, increasing when it is low), the primary / secondary air ratio (e.g., increasing airflow to enhance combustion when the calorific value is high, reducing airflow to prevent flameout when the calorific value is low), and the feeding rate can be dynamically adjusted based on the predicted calorific value to ensure stable combustion of the waste entering the incinerator at the optimal air-fuel ratio. For example, when it is predicted that high-calorific-value waste (LHV>9000kJ / kg) from the commercial area will be fed into the furnace, the grate speed can be reduced by 8%-12% in advance, and the primary air volume can be increased by 15% to avoid furnace overheating and drastic fluctuations in steam parameters. When it is predicted that kitchen waste (moisture content>55%) will be fed during the rainy season, the feed rate can be reduced by 10% in advance, and the temperature of the grate drying section can be increased to ensure combustion stability. In this way, through the feedforward control mechanism of the material-incineration collaborative chain, furnace flameout or overheating accidents caused by sudden changes in waste composition can be avoided, ensuring continuous and stable operation of the production line, thereby effectively improving waste-to-energy efficiency, reducing auxiliary fuel input, and significantly reducing operating costs. Moreover, by using feedback information from the downstream incineration system to predict and regulate the characteristics of upstream materials, a data-driven cross-system closed-loop optimization can be formed, laying the technical foundation for the realization of full-chain autonomous collaboration in the "lights-out" plant.

[0059] In some possible implementations, it also includes:

[0060] Obtain operating data of the incinerator; wherein, the operating data includes at least one of flue gas composition, temperature, and flow rate;

[0061] Based on operating data, the purification parameters of the flue gas purification subsystem are calculated and adjusted.

[0062] In the embodiments of this disclosure, real-time data communication between the upstream incineration process and the downstream purification system can be achieved through an incineration-purification collaborative chain. For example, a high-temperature gas analyzer, thermocouples, and differential pressure flowmeters, capable of detecting flue gas composition, temperature, and flow rate, can be deployed at the outlet flue of the incinerator. These devices sample the flue gas composition (such as SO2, HCl, NOx, and particulate matter concentration), temperature, and flow rate, respectively. The sampling period can be customized, for example, set to no more than 1 second. Then, the operating parameters of the purification system (flue gas purification subsystem) can be optimized in advance using the acquired incinerator operating data. For example, the purification parameters of the flue gas purification subsystem can be calculated and adjusted based on the received flue gas composition, temperature, and flow rate data. For example, by combining preset pollutant removal efficiency targets (such as SO2 removal rate ≥95%, HCl removal rate ≥99%), the optimal injection amounts of desulfurizing agent (such as slaked lime) and activated carbon can be calculated in real time. This allows for the advance increase of the desulfurizing agent injection amount, avoiding emissions exceeding standards due to reaction lag. When the flue gas temperature exceeds 150℃, the spray cooling system is automatically activated in advance to prevent high-temperature damage to the bag filter. Thus, through the feedforward control mechanism of the incineration-purification synergistic chain, the response time of the flue gas purification subsystem can be effectively shortened, thereby significantly improving environmental stability.

[0063] In some possible implementations, it also includes:

[0064] Obtain monitoring data on rotating machinery and electrical equipment in waste-to-energy plants;

[0065] Based on monitoring data, predictive information on the equipment status of equipment in waste-to-energy plants is provided. The predicted equipment status information includes at least one of the following: equipment failure type, equipment failure probability, and remaining service life.

[0066] In the embodiments of this disclosure, a full lifecycle management system for equipment can also be constructed to monitor the health status of critical equipment. For example, for high-speed rotating equipment such as steam turbines, primary air fans, and boiler feed pumps, triaxial vibration sensors, PT100 temperature sensors, and noise spectrum analyzers can be deployed at key measuring points such as bearing housings and casings to acquire mechanical status parameters such as vibration amplitude, spectrum characteristics, bearing temperature rise, and operating noise in real time. For electrical equipment such as main transformers and high-voltage switchgear, wireless passive temperature sensors, high-frequency current transformers (for partial discharge detection), and voltage and current waveform acquisition units can be installed at windings, terminals, and insulating bushings to monitor electrical insulation status, contact temperature, and power quality parameters in real time. All sensor data undergoes signal conditioning and feature extraction (such as calculating vibration RMS values, kurtosis indices, and discharge pulse phase distribution) via an edge computing gateway, and is periodically uploaded to the equipment health data center of the black-light control platform via an industrial IoT protocol, forming a high-frequency monitoring data stream covering all mechanical and electrical dimensions, providing basic input for fault prediction.

[0067] Then, condition monitoring and fault prediction can be achieved through data fusion and deep learning algorithms. For example, spatiotemporal alignment and correlation analysis can be performed based on the time-series data of vibration, temperature, and noise of rotating machinery and the monitoring data of partial discharge, temperature, and electrical parameters of electrical equipment. For instance, a sudden increase in fan vibration can be coupled with motor current fluctuations to identify the feature vector of early signs of electromechanical coupling faults. The fused feature vector is then input into a fault prediction model library (fault prediction model). This library can, for example, employ a multi-layer LSTM (Long Short-Term Memory) network or a Transformer architecture, and the training data can cover historical fault cases and normal operation data throughout the equipment's entire lifecycle. The fault prediction model library can output equipment condition prediction information, including but not limited to: fault type (such as bearing wear, winding insulation aging, impeller scaling, etc.), fault occurrence probability (such as 0-100% confidence level), and remaining service life (such as in hours or days). Thus, through potential fault prediction, intelligent inspection robots or drones can be precisely scheduled for targeted verification, avoiding blind inspections and improving inspection efficiency.

[0068] In some possible implementations, it also includes:

[0069] When the probability of equipment failure exceeds a preset probability threshold, fault data of the equipment is collected; wherein, fault data includes at least one of image data and temperature data;

[0070] Based on fault data and equipment status prediction information, preventive maintenance strategies are generated.

[0071] In the embodiments of this disclosure, when the probability of a fault occurrence output by the fault prediction model exceeds a preset threshold, the black-light control platform can automatically generate a task instruction. This task instruction may include the equipment number, the predicted fault type, the confidence level, and the suggested inspection location, and can be sent to the intelligent inspection system to dispatch inspection robots or drones to autonomously plan the shortest path to the area where the target equipment is located. For example, the robot can be equipped with a high-definition visible light camera and an infrared thermal imager to take detailed pictures of the predicted fault points. If it is rotating machinery, the visible light camera can capture images of external defects such as the condition of the bearing housing oil seal, the misalignment of the coupling, and the scaling on the impeller surface; the infrared thermal imager can detect the temperature field distribution on the equipment surface and identify latent faults such as bearing overheating, localized overheating of the motor windings, and poor contact of electrical connectors. The collected image data (including visible light images and infrared thermal images) and temperature data (such as hot spot temperature and temperature rise rate) are used as fault data and transmitted back to the fault diagnosis center of the black-light control platform.

[0072] Then, the black-light control platform can analyze fault data and equipment status prediction information (such as fault type, probability, and remaining service life). For example, it can automatically identify physical damage such as cracks, wear, and corrosion in visible light images using image recognition algorithms, quantifying their size and severity. Simultaneously, it can extract features such as temperature gradients and hotspot areas using infrared thermal image analysis algorithms, cross-validating these features with temperature trends in the prediction model to obtain diagnostic results. Afterward, preventative maintenance strategies can be generated based on the diagnostic results. For example, preventative maintenance strategies can be generated based on a pre-set maintenance knowledge base, which can include an equipment structure tree, a fault mode library, standard operating procedures, and spare parts inventory data. Preventive maintenance strategies can include: maintenance work orders: clearly specifying the location of faulty equipment, component names, defect descriptions, and a list of required spare parts; maintenance time window recommendations: recommending the maintenance period with the shortest future downtime based on production plans and the remaining service life of the equipment; operation procedure guidelines: providing complete operational instructions from spare parts retrieval, tool preparation, and safety isolation to maintenance steps; risk assessment and safety plans: identifying risks such as electric shock, burns, and falls during the maintenance process, and developing corresponding measures such as energy isolation, gas detection, and emergency plans. Understandably, the generated preventive maintenance strategies can be automatically dispatched to maintenance personnel's mobile devices or the maintenance system. In this way, traditional troubleshooting relying on manual experience can be upgraded to data-driven, automated, and precise maintenance, effectively shortening equipment maintenance response time and improving the accuracy of maintenance work orders.

[0073] To make the methods provided in this disclosure clearer, specific examples are given below. The methods provided in this disclosure mainly include the following:

[0074] 1. Multi-level intelligent optimization system.

[0075] Local optimization: autonomous optimization and control of key process sections such as incinerator (technology 3), flue gas purification (technology 4), and steam turbine (technology 5);

[0076] Global optimization: Through technology 12 (production process simulation and evaluation), we achieve comprehensive optimization of the plant's energy efficiency, pollution emissions, and economic performance.

[0077] Overall implementation principles: 1. The global optimization system governs all local optimization systems; 2. Each local optimization follows its own optimal objective. Under the guidance of the global optimization, each local optimization can adjust its optimal value to achieve the overall optimal result; 3. When a local optimization reaches its limit, it can be fed back to the global optimization system to reduce the global optimization target value.

[0078] Taking waste-to-energy incineration plant production as an example: 1. When the amount of waste in a city increases in the short term due to factors such as increased tourism, the primary goal is to meet the full and timely harmless treatment of waste. Under the premise of meeting relevant requirements, the incinerator (technology 3) and flue gas purification (technology 4) do not pursue the highest power generation of the turbine (technology 5), and the waste is treated in compliance with standards throughout the day. 2. Under normal load conditions, under the premise of meeting environmental protection requirements, the overall goal is to maximize the power generation of the turbine (technology 5). At night, when the temperature is low, the power generation efficiency is high, and more waste can be processed. During the day, when the temperature is high, the load of the incinerator (technology 3) and flue gas purification (technology 4) can be appropriately reduced, so that the power generation reaches its maximum while the daily processing volume remains unchanged.

[0079] 2. Closed-loop control of health and environment.

[0080] Technology 11 (workshop environment monitoring) and Technology 7 (confined space hazardous gas control) are integrated into the control system to adjust ventilation and negative pressure equipment in real time to ensure personnel health and work safety.

[0081] General principle: Ensure the workshop environment meets relevant requirements around the clock, while ventilating as needed to save energy.

[0082] When Technology 11 (workshop environmental monitoring) detects an increase in the concentration of harmful gases, the ventilation intensity can be increased promptly through the blackout control platform to ensure that the workshop meets occupational health requirements. For example, in a waste incineration power plant, after fly ash undergoes stabilization treatment and is transported to the fly ash temporary storage warehouse, the concentrations of CS2 and ammonia in the workshop may exceed the standards within 1-5 hours. When these standards are exceeded, the ventilation volume should be increased promptly to ensure the health and safety of operating personnel.

[0083] Technology 7 (Control of Hazardous Gases in Confined Spaces) monitors hazardous gases such as H2S and CO in confined spaces, as well as the negative pressure value of the confined space (generally around -30Pa to -50Pa). It also combines production load data from the darkroom platform to dynamically adjust ventilation volume and negative pressure value, ensuring low-carbon operation while maintaining safety and occupational health.

[0084] 3. Cross-system collaboration mechanism.

[0085] See Figure 3 Data-driven chain control can include:

[0086] Technology 1 (material receiving) data → Technology 2 (material storage) predicting waste calorific value → Technology 3 (incinerator) pre-setting combustion parameters;

[0087] Data-driven control method: Technology 1 (material receiving) inputs the data it is responsible for (including waste source, waste quantity, and other waste quality and characteristic information) to Technology 2 (material storage). Technology 2 inputs the information into its own waste characteristic prediction model. Combined with historical data and the operating data of the previous 8 hours fed back by Technology 3 (incinerator), it can predict the waste quality data that will enter Technology 3 (incinerator) soon, providing valuable feedforward data for Technology 3 (incinerator) and ensuring efficient incineration.

[0088] Technology 3 operating data → Technology 4 (flue gas purification) feedforward control → Ensure pollutant emissions meet standards.

[0089] The flue gas generated by Technology 3 (incinerator) takes about 10 seconds to enter Technology 4 (flue gas purification) according to the process flow. Similarly, Technology 3 (incinerator) inputs real-time operating data to the black light control module of Technology 4 (flue gas purification) as feedforward information to provide optimization time for the black light control module of Technology 4 (flue gas purification) and avoid unnecessary material consumption.

[0090] 4. Equipment lifecycle management.

[0091] Technology 8 (rotating machinery) + Technology 9 (electrical equipment) condition monitoring → predicting faults and triggering Technology 10 (intelligent inspection) → generating preventive maintenance strategies.

[0092] Technology 8 (rotating machinery) mainly includes rotating machinery such as steam turbines, generators, fans, and water pumps, and their sensor networks (such as vibration sensors, temperature sensors, noise sensors, and displacement sensors) and data acquisition units, which are used to collect the physical operating parameters of the equipment in real time.

[0093] Technology 9 (Electrical Equipment) mainly includes electrical equipment such as transformers, switch cabinets, and cable joints, as well as sensor networks (such as temperature sensors, partial discharge sensors, current and voltage sensors) and data acquisition units on them, which are used to collect electrical parameters and insulation status parameters in real time.

[0094] The blackout control platform receives data from Technology 8 (rotating machinery) and Technology 9 (electrical equipment) and has the following built-in features:

[0095] Data fusion engine: It correlates and analyzes monitoring data from rotating machinery and electrical equipment to overcome information silos.

[0096] Fault prediction model library: Contains algorithm models based on machine learning (such as regression models, time series prediction) or deep learning (such as LSTM) to identify equipment performance degradation trends and predict potential fault types, locations and probabilities of occurrence.

[0097] Decision trigger: When the predicted failure probability or equipment health index exceeds the preset threshold, maintenance suggestions or inspection instructions are automatically generated and sent to Technology 10 (intelligent inspection).

[0098] Technology 10 (Intelligent Inspection) receives instructions from the black-light platform and dispatches automated equipment such as inspection robots or drones. These devices are equipped with high-definition cameras, infrared thermal imagers, acoustic sensors, etc., to perform targeted and refined verification and supplementary data collection on predicted potential fault points.

[0099] The black-light control platform performs a comprehensive analysis based on data from Technology 8 (rotating machinery), Technology 9 (electrical equipment), and Technology 10 (intelligent inspection) and the output of the fault prediction model. Based on a pre-set maintenance knowledge base and rule engine, it automatically generates the optimal preventative maintenance strategy. This strategy specifically includes: maintenance work orders (including maintenance equipment, maintenance content, required spare parts and tools); suggested maintenance time windows; maintenance operation procedure guidelines; risk assessment and safety contingency plans.

[0100] 5. Core capabilities of the Lights-Out Factory.

[0101] Technology 6 (intelligent leachate treatment) and Technology 10 (intelligent inspection) support "unmanned operation".

[0102] Technology 2 (material storage and feeding), Technology 3 (incinerator), Technology 4 (flue gas purification), Technology 5 (steam turbine), Technology 6 (intelligent leachate treatment), and Technology 10 (intelligent inspection) can all operate independently and intelligently in the main process production, supporting "unmanned intelligent operation".

[0103] Based on Table 1 below, the above five points comprehensively construct the autonomous, optimized, unattended operation mode of the light-out factory from the perspectives of light-out control architecture and global and local intelligent control modules, light-out factory environment safety, optimization and collaboration of various systems, and equipment monitoring and pre-maintenance.

[0104]

[0105] As an example, based on the above, the specific implementation of the method provided in this disclosure embodiment can be as follows:

[0106] 1. Build a unified data platform: such as Figure 2 As shown, data from 12 subsystems (such as technologies 1-12 above) can be integrated to establish a real-time database;

[0107] 2. Deploy the intelligent algorithm module:

[0108] Incineration optimization: Dynamic fuzzy control based on calorific value prediction (Technology 3);

[0109] Flue gas purification: Feedforward-feedback composite APC (Advanced Process Control) control (Technology 4);

[0110] Environmental control: temperature and humidity / harmful gas concentration → negative pressure system PID (Proportional-Integral-Derivative) adaptive (Technology 7+11).

[0111] End-to-end digital twin: Through technology 12, the energy efficiency of the entire plant under different operating conditions is simulated to generate the optimal scheduling instructions.

[0112] For example, the overall system architecture can be as follows: A central intelligent control platform (i.e., a lights-out control platform) integrating intelligent optimization, safety closed-loop control, cross-system collaboration, and equipment lifecycle management can be built for the lights-out factory. This platform, acting as the factory's "digital brain," interconnects with all the subsystems below via a data bus to achieve data exchange and command issuance, ultimately achieving a fully automated or minimally staffed lights-out operation mode.

[0113] Based on this, the implementation of a multi-level intelligent optimization system can include the following processes:

[0114] The multi-level intelligent optimization system consists of two levels: local optimization and global optimization, following the principle of "global overriding local and local feedback to the global." Specifically:

[0115] 1. Implementation of the local optimization layer:

[0116] Local optimization of the incinerator (technology 3): Through the built-in combustion optimization controller, the ratio of primary air and secondary air and the grate speed are adjusted in real time with the goal of "highest combustion stability" or "most stable steam parameters".

[0117] Flue gas purification (technology 4) Local optimization: Through the built-in material dosing optimization controller, the injection volume of various agents is adjusted with the local goal of "minimizing the consumption of deacidifying agent / activated carbon under the premise of pollutant emission compliance".

[0118] Steam turbine (Technology 5) (i.e., steam turbine) local optimization: Through the built-in efficiency optimization controller, the guide vane opening and other parameters are adjusted with the goal of "maximum power generation efficiency under the current steam parameters".

[0119] 2. Implementation of the global optimization layer (Technology 12):

[0120] Global optimization is achieved through Technology 12 (Production Process Simulation and Evaluation). This module constructs a digital twin model of the entire plant, with inputs including real-time electricity prices, waste disposal subsidies, environmental protection material costs, and the operating status of all plant equipment.

[0121] Global objective function: The global objective is to achieve the highest overall economic benefits for the entire plant or the largest daily waste processing volume.

[0122] Collaborative control mechanism:

[0123] Normal operation: When the waste supply is stable, the global optimization system is set with the overall goal of "maximizing power generation revenue". It will issue target instructions to the local optimization system. For example, taking advantage of the low temperature and high power generation efficiency at night, it will instruct the incinerator to increase the processing load at night and appropriately reduce the load during the day, so that the turbine (Technology 5) can generate the maximum amount of electricity while keeping the total amount of waste processed throughout the day constant.

[0124] Special operating conditions: When the amount of urban waste surges in a short period (such as during peak tourist season), the global objective switches to "maximum waste harmless treatment capacity". At this time, the global optimization system will take over the various local optimization systems, allowing the power generation efficiency of the steam turbine (technology 5) to temporarily deviate from its local optimum, and prioritizing the incinerator (technology 3) and flue gas purification (technology 4) to process all waste at full load and in compliance with emission standards.

[0125] Bottom-line feedback mechanism: When any local optimization system (such as a flue gas purification system) reaches its safety or environmental bottom line in its operating parameters (such as ammonia injection rate) due to equipment capacity limitations, and cannot meet the instructions issued by the global optimization system, this local system will report this information to the global optimization system. The global optimization system will then reduce the global target value (for example, reduce the overall plant processing load) to ensure the safe and stable operation of the entire system.

[0126] See Figure 3 The implementation of closed-loop control for health and the environment can be as follows:

[0127] This module integrates Technology 11 (workshop environment monitoring) and Technology 7 (confined space hazardous gas control) to achieve automatic, safe, and energy-saving control of the factory environment.

[0128] 1. Monitoring layer:

[0129] In workshop areas such as fly ash storage warehouse and waste unloading hall, a sensor network of Technology 11 is deployed to monitor the concentration of wide-area harmful gases such as CS2 and ammonia (NH3) in real time.

[0130] In confined spaces such as landfill pits and leachate channels, a sensor network based on technology 7 is deployed to monitor the concentration of acutely harmful gases such as H2S and CO in real time, and to monitor the negative pressure value of the area (maintained at -30Pa to -50Pa).

[0131] 2. Decision-making and execution level:

[0132] All environmental monitoring data is uploaded to the blackout control platform in real time.

[0133] Safety-first control: When any sensor detects that the gas concentration exceeds the national occupational health standard limit, or the negative pressure value exceeds the safe range, the platform immediately issues the highest priority command to the ventilation and negative pressure equipment (such as variable frequency fans and dampers) in that area, forcibly increasing the ventilation intensity to ensure the health and safety of personnel. For example, if the CS2 and ammonia concentrations exceed the standard within 1-5 hours after fly ash is put into storage, the system automatically increases the ventilation volume of the fly ash storage.

[0134] On-demand energy-saving control: Provided all environmental parameters meet the standards, the system will combine real-time production load data. During nighttime or low-load operation, it will automatically reduce ventilation volume and fan energy consumption, achieving low-carbon operation while ensuring safety and hygiene.

[0135] See Figure 4 The implementation of cross-system collaboration mechanisms can be as follows:

[0136] This mechanism is data-driven, enabling the upstream system to provide feedforward information to the downstream system, thus forming a chain control.

[0137] 1. Material-Incineration Collaborative Chain:

[0138] Technology 1 (Material Receiving): When receiving waste, record information such as the source, type, and weight of the waste, and upload it to the black light control platform in real time.

[0139] Technology 2 (Material Storage) retrieves the above information from the platform and inputs it into its built-in waste characteristic prediction model. This model, combined with historical waste data and the operational data from the most recent 8 hours fed back by Technology 3 (Incinerator), predicts the calorific value and composition of the waste that will soon enter the incinerator.

[0140] The prediction results are sent as feedforward data to Technology 3 (incinerator), and the incinerator control system adjusts combustion parameters such as grate speed and air volume in advance to ensure stable and efficient combustion of waste entering the furnace.

[0141] 2. Incineration-Purification Collaborative Chain:

[0142] The real-time operating data of flue gas composition, temperature, flow rate, etc. generated by Technology 3 (incinerator) are immediately sent to the black-light control module of Technology 4 (flue gas purification).

[0143] Utilizing the approximately 10-second transport time of flue gas from the incinerator to the purification system, the control module of Technology 4, based on feedforward information, calculates and adjusts in advance the injection volume of deacidifying agent and activated carbon, as well as the water volume of the spray cooling system, thereby avoiding the excessive or insufficient use of purification agents and optimizing material consumption while ensuring that pollutants are discharged in compliance with standards.

[0144] The implementation of equipment lifecycle management can be as follows:

[0145] This module enables predictive maintenance of critical equipment, and the process is as follows:

[0146] 1. Status monitoring:

[0147] Vibration, temperature, and noise sensors are deployed on technologies 8 (rotating machinery), such as steam turbines, fans, and water pumps.

[0148] Temperature, partial discharge, current and voltage sensors are deployed on transformers, switchgear and other technical (electrical equipment) devices.

[0149] All sensor data is uploaded to the blackout control platform in real time via the data acquisition unit.

[0150] 2. Intelligent Diagnosis and Prediction:

[0151] The platform's data fusion engine performs correlation analysis on monitoring data from rotating machinery and electrical equipment.

[0152] The fault prediction model library (using deep learning algorithms such as LSTM) analyzes the fused data to identify equipment performance degradation trends and predict potential fault types, probability of occurrence, and remaining service life.

[0153] 3. Decision-making and intelligent inspection:

[0154] When the predicted failure probability exceeds a preset threshold, the decision trigger is activated, automatically generating instructions and sending them to the Technology 10 (Intelligent Inspection) system.

[0155] The Technology 10 system dispatches inspection robots or drones equipped with high-definition cameras, infrared thermal imagers, etc., to conduct targeted and refined verification of predicted fault points, collect supplementary data such as images and temperature, and transmit them back.

[0156] 4. Maintenance strategy generation:

[0157] The platform integrates status monitoring, prediction results, and intelligent inspection verification data to conduct a final diagnosis.

[0158] Based on a pre-set maintenance knowledge base, the platform automatically generates optimal preventative maintenance strategies, including: maintenance work orders (equipment, content, spare parts), maintenance time window suggestions, operation process guidelines, and risk assessment and safety contingency plans.

[0159] The implementation of the core capabilities of a lights-out factory can include:

[0160] Through the synergistic effect of the above four mechanisms, the core process systems such as Technology 2 to Technology 6 can ultimately achieve independent and autonomous intelligent operation, and the traditional manual inspection and operation can be replaced by systems such as Technology 10 (intelligent inspection), jointly supporting the "unmanned intelligent operation" of the entire waste incineration power plant in a "lights-out" factory mode.

[0161] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0162] According to embodiments of this disclosure, this disclosure also provides a blackout plant control device for a waste incineration power plant. For example, Figure 5 This is a schematic diagram of a blackout plant control device for a waste incineration power plant, provided as an embodiment of this disclosure. The blackout plant control device 500 for the waste incineration power plant includes:

[0163] Data acquisition module 510 is used to acquire economic parameters and operating data of waste incineration power plants;

[0164] The status monitoring module 520 also determines the current operating status of the waste incineration power plant;

[0165] The global optimization module 530 is used to control the operation of the waste incineration power plant based on the economic parameters and operating data with the goal of maximizing the power generation revenue of the waste incineration power plant when the current operating state of the waste incineration power plant is a stable waste supply state; and to control the operation of the waste incineration power plant based on the economic parameters and operating data with the goal of maximizing the waste processing capacity of the waste incineration power plant when the current operating state of the waste incineration power plant is a surge in waste volume.

[0166] The local optimization module 540 is used to control the waste-to-energy plant to operate at its maximum power generation capacity based on the economic parameters and operating data when the current operating state of the waste-to-energy plant is a stable waste supply state, provided that the total waste processing volume remains stable; and to control the waste-to-energy plant to operate at its maximum waste processing capacity based on the economic parameters and operating data when the current operating state of the waste-to-energy plant is a waste surge state, provided that the incinerator and flue gas purification subsystem of the waste-to-energy plant are operating at full load and meet standards.

[0167] Furthermore, it also includes an adjustment module for:

[0168] If the operating parameters of at least one of the steam turbine, the incinerator, and the flue gas purification subsystem have reached a set threshold, at least one of the maximum power generation and the maximum waste processing capacity shall be adjusted.

[0169] Furthermore, it also includes a ventilation module for:

[0170] Monitor environmental parameters within a designated area of ​​the waste-to-energy plant; wherein the environmental parameters include a preset gas concentration and a negative pressure value, and the preset gas is at least one type;

[0171] When the preset gas concentration and negative pressure value meet the preset ventilation conditions, a target area corresponding to the preset gas concentration and negative pressure value that meet the preset ventilation conditions is determined, and the ventilation volume of the target area is increased; wherein, the preset ventilation conditions include: at least one of the following: the concentration of at least one preset gas is greater than a set concentration threshold, and the negative pressure value is greater than a set negative pressure value threshold.

[0172] Furthermore, it also includes an incinerator parameter adjustment module, used for:

[0173] The system acquires first waste information of the received waste and operating data of the incinerator within a preset historical time period; wherein, the first waste information includes at least one of waste source, waste type, and waste weight;

[0174] Based on the first waste information and the operational data, a waste characteristic prediction model predicts the second waste information that will soon enter the incinerator; wherein, the second waste information includes the calorific value and composition of the waste.

[0175] The operating parameters of the incinerator are pre-adjusted based on the calorific value and composition of the waste.

[0176] Furthermore, it also includes a purification parameter adjustment module, used for:

[0177] Obtain the operating condition data of the incinerator; wherein the operating condition data includes at least one of flue gas composition, temperature, and flow rate;

[0178] Based on the operating data, the purification parameters of the flue gas purification subsystem are calculated and adjusted.

[0179] Furthermore, it also includes a fault prediction module, used for:

[0180] Acquire monitoring data of the rotating machinery and electrical equipment of the waste incineration power plant;

[0181] Based on the monitoring data, predictive information on the equipment status of the equipment in the waste incineration power plant is generated; wherein, the predictive information on the equipment status includes at least one of the following: equipment failure type, equipment failure probability, and set remaining service life.

[0182] Furthermore, it also includes a maintenance module for:

[0183] When the probability of a device malfunctioning is greater than a preset probability threshold, fault data of the device is collected; wherein, the fault data includes at least one of image data and temperature data;

[0184] Based on the fault data and the equipment status prediction information, a preventive maintenance strategy is generated.

[0185] It should be noted that the description of the features of the control device for the blackout plant of a waste incineration power plant in the corresponding embodiment can be found in the relevant description of the control method for the blackout plant of a waste incineration power plant, and will not be repeated here.

[0186] Embodiments of this disclosure also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0187] Embodiments of this disclosure also provide a computer-readable storage medium storing a computer program configured to perform the steps in any of the above method embodiments when executed.

[0188] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0189] Embodiments of this disclosure also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0190] Embodiments of this disclosure also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0191] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0192] The above provides a detailed description of a method for controlling a "lights-out" waste-to-energy plant, as disclosed in this disclosure. Specific examples have been used to illustrate the principles and implementation methods of this disclosure. The descriptions of these embodiments are merely illustrative and are intended to aid in understanding the method and its core concepts. It should be noted that those skilled in the art can make various improvements and modifications to this disclosure without departing from its principles, and these improvements and modifications also fall within the scope of protection of the claims of this disclosure.

Claims

1. A method for controlling the "lights-out" operation of a waste-to-energy incineration plant, characterized in that, include: Obtain economic parameters and operational data of waste-to-energy plants; Determine the current operating status of the waste-to-energy plant; When the current operating state of the waste incineration power plant is a stable waste supply, the operation of the waste incineration power plant is controlled based on the economic parameters and operating data with the goal of maximizing the power generation revenue of the waste incineration power plant. When the current operating state of the waste incineration power plant is a state of surge in waste volume, the operation of the waste incineration power plant is controlled based on the economic parameters and operating data with the goal of maximizing the waste processing capacity of the waste incineration power plant; The method further includes: Acquire monitoring data of the rotating machinery and electrical equipment of the waste incineration power plant; Based on the monitoring data, predictive information on the equipment status of the equipment in the waste incineration power plant is generated; wherein, the predicted information on the equipment status includes at least one of the following: equipment failure type, equipment failure probability, and set remaining service life; The method further includes: When the probability of a device malfunctioning is greater than a preset probability threshold, fault data of the device is collected; wherein, the fault data includes at least one of image data and temperature data; Based on the fault data and the equipment status prediction information, a preventive maintenance strategy is generated.

2. The method for controlling the "lights-out" operation of a waste-to-energy plant according to claim 1, characterized in that, When the current operating state of the waste-to-energy plant is a stable waste supply, the operation of the waste-to-energy plant is controlled based on the economic parameters and operating data, with the objective of maximizing the power generation revenue of the waste-to-energy plant, including: When the current operating state of the waste incineration power plant is a stable waste supply state, the turbine of the waste incineration power plant controls the waste incineration power plant to operate at the maximum power generation state based on the economic parameters and operating data, provided that the total amount of waste processed remains stable. When the current operating state of the waste-to-energy plant is a state of surging waste volume, the operation of the waste-to-energy plant is controlled based on the economic parameters and operating data with the objective of maximizing the waste processing capacity of the waste-to-energy plant, including: When the current operating state of the waste incineration power plant is a state of surge in waste volume, the waste incineration power plant is controlled to operate at the maximum waste processing capacity based on the economic parameters and operating data, under the premise that the incinerator and flue gas purification subsystem of the waste incineration power plant are at full load and meet the standards.

3. The method for controlling the "lights-out" process in a waste-to-energy plant according to claim 2, characterized in that, Also includes: If the operating parameters of at least one of the steam turbine, the incinerator, and the flue gas purification subsystem have reached a set threshold, at least one of the maximum power generation and the maximum waste processing capacity shall be adjusted.

4. The method for controlling the "lights-out" process in a waste-to-energy plant according to claim 1, characterized in that, Also includes: Monitor environmental parameters within a designated area of ​​the waste-to-energy plant; wherein the environmental parameters include a preset gas concentration and a negative pressure value, and the preset gas is at least one type; When the preset gas concentration and negative pressure value meet the preset ventilation conditions, a target area corresponding to the preset gas concentration and negative pressure value that meet the preset ventilation conditions is determined, and the ventilation volume of the target area is increased; wherein, the preset ventilation conditions include: at least one of the following: the concentration of at least one preset gas is greater than a set concentration threshold, and the negative pressure value is greater than a set negative pressure value threshold.

5. The method for controlling the "lights-out" process in a waste-to-energy plant according to claim 2, characterized in that, Also includes: The system acquires first waste information of the received waste and operating data of the incinerator within a preset historical time period; wherein, the first waste information includes at least one of waste source, waste type, and waste weight; Based on the first waste information and the operational data, a waste characteristic prediction model predicts the second waste information that will soon enter the incinerator; wherein, the second waste information includes the calorific value and composition of the waste. The operating parameters of the incinerator are pre-adjusted based on the calorific value and composition of the waste.

6. The method for controlling a "lights-out" plant in a waste incineration power plant according to claim 5, characterized in that, Also includes: Obtain the operating condition data of the incinerator; wherein the operating condition data includes at least one of flue gas composition, temperature, and flow rate; Based on the operating data, the purification parameters of the flue gas purification subsystem are calculated and adjusted.

7. A blackout plant control device for a waste incineration power plant, characterized in that, include: The data acquisition module is used to obtain economic parameters and operational data of waste-to-energy plants. The status monitoring module also determines the current operating status of the waste incineration power plant; The global optimization module is used to control the operation of the waste-to-energy plant with the goal of maximizing its power generation revenue when the current operating state of the waste-to-energy plant is a stable waste supply state, based on the economic parameters and operating data; and to control the operation of the waste-to-energy plant with the goal of maximizing its waste processing capacity when the current operating state of the waste-to-energy plant is a state of surging waste volume, based on the economic parameters and operating data. The local optimization module is used to control the waste incineration power plant to operate at its maximum power generation state based on the economic parameters and operating data when the current operating state of the waste incineration power plant is a stable waste supply state. And, when the current operating state of the waste incineration power plant is a state of surge in waste volume, the waste incineration power plant is controlled to operate at the maximum waste processing capacity based on the economic parameters and operating data, provided that the incinerator and flue gas purification subsystem of the waste incineration power plant are operating at full load and meet the standards. The device also includes a fault prediction module for acquiring monitoring data of the rotating machinery and electrical equipment of the waste incineration power plant; Based on the monitoring data, predictive information on the equipment status of the equipment in the waste incineration power plant is generated; wherein, the predicted information on the equipment status includes at least one of the following: equipment failure type, equipment failure probability, and set remaining service life; The device further includes a maintenance module, used to collect fault data of the device when the probability of the device malfunctioning is greater than a preset probability threshold; wherein the fault data includes at least one of image data and temperature data; Based on the fault data and the equipment status prediction information, a preventive maintenance strategy is generated.

8. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-6.

Images