Intelligent optimization method for solid waste treatment of thermal power plant

Abstract

The invention provides an intelligent optimization method for solid waste treatment of a thermal power plant, and the method comprises the steps: collecting data in real time through a multi-parameter sensor, predicting the solid waste flow and the temperature and humidity trend in combination with historical data, and triggering automatic adjustment and alarm for abnormal parameters; the solid waste components are judged based on the combination of convolutional neural network image recognition and spectral analysis, so that the sorting accuracy is ensured; dynamically starting the multi-mode drying device according to the content of the solid wastewater, and repeating drying circulation until the water content reaches the standard if the water content still exceeds the standard after drying is completed; performing multi-threshold judgment on parameters such as processing efficiency, energy consumption and dust concentration by using an Internet of Things platform, generating an optimization strategy, dynamically adjusting drying temperature, wind speed, conveying speed and equipment load, and triggering an emission reduction mode and giving an alarm when the dust concentration exceeds the standard; and performing long-term regression analysis on the processing data acquired in real time through a machine learning algorithm, predicting future processing efficiency, energy consumption and resource rate trends, and realizing adaptive optimization according to prediction results.

Description

Technical Field

[0001] This invention relates to the field of intelligent treatment and resource utilization of industrial solid waste, and in particular to an intelligent optimization method for solid waste treatment in thermal power plants. Background Technology

[0002] Solid waste treatment in thermal power plants is a core component of the power industry's green transformation, widely applied to the resource management of wastes such as fly ash, slag, and desulfurization gypsum generated during coal-fired power generation. With the integrated development of intelligent environmental protection technologies, the existing technological system has gradually built a complete process framework from solid waste collection and classification to treatment, specifically covering key aspects such as automated conveying, multi-parameter sensing and monitoring, AI-assisted sorting, and IoT platform integration. Traditional systems often rely on single-parameter detection such as weight and temperature, combined with human experience for sorting decisions. While basic automation was achieved in the early stages, their technical architecture remains at the discrete control stage, lacking the ability to collaboratively analyze multi-dimensional characteristics such as particle size, density, and hazardous components.

[0003] However, existing solid waste treatment methods directly employ fixed threshold judgments and static control logic, without establishing dynamic adjustment mechanisms or data-driven closed-loop optimization systems. This may lead to problems such as classification accuracy below 95%, drying energy consumption exceeding 6 kWh / ton, or resource utilization rates below the industry average. Specifically, traditional sorting technologies rely solely on particle size screening or density sorting, failing to effectively identify harmful components such as heavy metals, resulting in misjudgments of usable solid waste; drying processes often employ constant-temperature hot air modes, which, when the moisture reduction rate... The lack of adaptive adjustment capabilities can easily lead to the dual risks of over-drying or under-drying; at the same time, existing systems lack the ability to predict changes in solid waste flow and composition, especially when storage occupancy rates are high. Or fluctuations in downstream demand In some cases, it is difficult to dynamically adjust the transportation plan, ultimately resulting in a resource utilization rate of less than 90%. These technical deficiencies not only limit the improvement of solid waste treatment efficiency in thermal power plants, but may also lead to problems due to dust concentration. Abnormal operating conditions and other factors can lead to secondary pollution risks, which hinders the in-depth implementation of the circular economy in the power industry. Summary of the Invention

[0004] The present invention aims to at least partially solve one of the technical problems in the related art.

[0005] Therefore, the first objective of this invention is to propose an intelligent optimization method for solid waste treatment in thermal power plants.

[0006] The second objective of this invention is to provide an intelligent optimization device for solid waste treatment in thermal power plants.

[0007] The third objective of this invention is to provide an electronic device.

[0008] The fourth objective of this invention is to provide a computer-readable storage medium.

[0009] The fifth objective of this invention is to provide a computer program product.

[0010] To achieve the above objectives, a first aspect of the present invention proposes an intelligent optimization method for solid waste treatment in thermal power plants, comprising: S1 collects real-time data on the weight, temperature, moisture, and vibration of solid waste through multi-parameter sensors, and combines historical data to predict the flow rate and temperature and humidity trends of solid waste, triggering automatic adjustment and alarms for abnormal parameters. S2, based on convolutional neural network image recognition and spectral analysis, determines the composition of solid waste, performs intelligent sorting according to particle size, density and hazardous component thresholds, and triggers secondary detection and manual intervention for abnormal batches; S3: The multi-mode drying device is dynamically activated based on the moisture content of solid waste. The drying mode is automatically switched and the temperature, wind speed and drying time are adjusted by monitoring the rate of moisture descent. If the moisture content still exceeds the standard after drying, the drying cycle is repeated until the standard is met. S4 utilizes an IoT platform to perform multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generates optimization strategies, and dynamically adjusts drying temperature, wind speed, conveying speed, and equipment load. Simultaneously, it triggers emission reduction mode and alarms when dust concentration exceeds the standard. S5 uses machine learning algorithms to perform long-term regression analysis on the real-time collected processing data to predict future trends in processing efficiency, energy consumption, and resource utilization rate, and automatically adjusts control parameters and performs equipment maintenance operations based on the prediction results.

[0011] In one embodiment of the present invention, the step of collecting real-time data on the weight, temperature, moisture, and vibration of solid waste using multi-parameter sensors, and combining this data with historical data to predict solid waste flow rate and temperature and humidity trends, and triggering automatic adjustments and alarms for abnormal parameters, includes: S11 has a weight detection accuracy of ±1%, a temperature detection range of 0~500℃ with an accuracy of ±2℃, a moisture detection accuracy of ±0.5%, and a monitoring frequency of 1Hz. S12: When the weight change exceeds ±10%, the temperature change exceeds ±20℃, or the moisture change exceeds ±2% in five consecutive measurements, the conveying speed is automatically adjusted to the range of 0.5~5 m³ / min and an alarm is triggered.

[0012] In one embodiment of the present invention, the method of jointly determining solid waste composition based on convolutional neural network image recognition and spectral analysis, performing intelligent sorting according to particle size, density, and hazardous component thresholds, and triggering secondary detection and manual intervention for abnormal batches includes: S21, the classification rule is that solid waste with a particle size of 0.1 to 50 mm, a density of 1.5 to 3.0 g / cm³, and a hazardous component content of more than 0.1% is marked as unusable solid waste; S22, the system automatically marks abnormal batches based on particle size, density and harmful component thresholds, and records them in the database to optimize subsequent sorting strategies.

[0013] In one embodiment of the present invention, the step of dynamically activating a multi-mode drying device based on the moisture content of solid waste, automatically switching drying modes and adjusting temperature, wind speed, and drying time by monitoring the rate of moisture descent, and repeating the drying cycle until the standard is met if the moisture content still exceeds the limit after drying, includes: S31, the drying methods include hot air, microwave and high frequency induction, the parameter adjustment range is temperature 80~300℃, wind speed 2~8 m / s, drying time 30~120 minutes; S32: When the rate of change in moisture content is ≤1% / 10 min, or when the temperature or wind speed deviation exceeds the set threshold, the system automatically switches the drying mode and increases the heating power, and the drying energy consumption is controlled within 2 to 5 kWh per ton of solid waste.

[0014] In one embodiment of the present invention, the method of using an IoT platform to perform multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generating optimization strategies, and dynamically adjusting drying temperature, wind speed, conveying speed, and equipment load, while triggering an emission reduction mode and alarm when dust concentration exceeds the standard, includes: S41 When the processing efficiency is below 95% or the energy consumption exceeds 6 kWh / ton of solid waste, the system automatically generates and executes optimization strategies, including adjusting the drying temperature, wind speed, conveying speed and equipment load. S42: When the dust concentration exceeds 50 mg / m³, the emission reduction mode is triggered and an alarm is sounded. At the same time, the dust concentration data is recorded to the database to optimize subsequent emission reduction strategies.

[0015] In one embodiment of the present invention, it further includes: S6 When downstream demand changes by ≥20%, the system automatically optimizes the delivery plan and adjusts the storage capacity to the range of 50-200 m³ based on flow and weighing data combined with historical prediction models to ensure downstream utilization rate ≥90%.

[0016] To achieve the above objectives, a second aspect of the present invention provides an intelligent optimization device for solid waste treatment in thermal power plants, comprising: The multi-parameter acquisition and prediction module is used to collect solid waste weight, temperature, moisture and vibration data in real time through multi-parameter sensors, and combine historical data to predict solid waste flow and temperature and humidity trends, and trigger automatic adjustment and alarm for abnormal parameters. The component determination and sorting module is used to determine the solid waste components based on convolutional neural network image recognition and spectral analysis, and to perform intelligent sorting based on particle size, density and hazardous component thresholds, triggering secondary detection and manual intervention for abnormal batches. The multi-mode drying control module is used to dynamically start the multi-mode drying device according to the moisture content of solid waste. It automatically switches the drying mode and adjusts the temperature, wind speed and drying time by monitoring the rate of moisture drop. If the moisture content still exceeds the standard after drying, the drying cycle is repeated until the standard is met. The IoT optimization and emission reduction module is used to use the IoT platform to make multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generate optimization strategies, and dynamically adjust drying temperature, wind speed, conveying speed and equipment load. At the same time, it triggers emission reduction mode and alarms when dust concentration exceeds the standard. The machine learning prediction and adaptation module is used to perform long-term regression analysis on real-time collected processing data through machine learning algorithms to predict future trends in processing efficiency, energy consumption, and resource utilization rate, and automatically adjust control parameters and perform equipment maintenance operations based on the prediction results.

[0017] To achieve the above objectives, a third aspect of the present invention provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of the first aspects.

[0018] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method as described in any one of the first aspects.

[0019] To achieve the above objectives, a fifth aspect of the present invention provides a computer program product that, when executed by a processor, implements the method described in any one of the first aspects.

[0020] The technical solutions provided by the embodiments of the present invention bring at least the following beneficial effects: The embodiments of the present invention significantly improve the level of intelligence in solid waste treatment in thermal power plants, achieving a sorting accuracy rate of ≥95%, a reduction in energy consumption of ≥10%, and an increase in resource utilization rate of ≥8%, effectively improving treatment efficiency and resource utilization, and reducing environmental risks.

[0021] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0022] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic flowchart of an intelligent optimization method for solid waste treatment in thermal power plants, provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of an intelligent optimization device for solid waste treatment in thermal power plants, provided in an embodiment of the present invention. Detailed Implementation

[0023] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0024] Figure 1 This is a schematic flowchart illustrating an intelligent optimization method for solid waste treatment in thermal power plants, provided by an embodiment of the present invention. Figure 1 As shown, the method includes the following steps: S1 collects real-time data on the weight, temperature, moisture, and vibration of solid waste using multi-parameter sensors, and combines this data with historical data to predict solid waste flow rate and temperature and humidity trends. It also triggers automatic adjustments and alarms for abnormal parameters.

[0025] Specifically, in the solid waste collection and preliminary monitoring step, the system integrates multi-parameter sensors to collect and process real-time data on solid waste (such as fly ash and slag) generated by thermal power plants. This step is technically implemented based on the coordinated control of automated conveying devices and sensor networks, aiming to provide accurate input parameters and anomaly warning mechanisms for subsequent processing.

[0026] At the technical implementation level, the system employs an adjustable-speed automated conveying device with a conveying rate ranging from 0.5 to 5 m³ / min, ensuring stable transport of solid waste under various operating conditions. Simultaneously, the system is equipped with high-precision weight sensors, temperature sensors, moisture sensors, and vibration sensors to monitor the weight, temperature, moisture content, and physical state of the solid waste. Specifically, the weight detection accuracy is ±1%, with a processing capacity of 1–5 tons / hour; the temperature detection range is 0–500℃ with an accuracy of ±2℃; and the moisture detection accuracy is ±0.5% with a sampling frequency of 1 Hz, meeting real-time monitoring requirements. Sensor data is uploaded to the central control system via industrial communication protocols (such as Modbus and OPC UA) for centralized data processing and analysis.

[0027] Regarding parameter indicators, the system is configured with the following anomaly detection logic: if the weight change exceeds ±10%, the temperature change exceeds ±20℃, or the moisture change exceeds ±2% in five consecutive measurements, the system will trigger an automatic adjustment mechanism and an alarm signal. This logic is based on a time series prediction model, combined with historical data to predict the current solid waste flow rate and temperature and humidity trends, thereby providing a dynamic reference for subsequent classification, drying, and storage steps.

[0028] In application scenarios, this step is widely applicable to the front-end processes of solid waste treatment in thermal power plants, especially in the treatment of high-temperature and high-humidity solid wastes such as fly ash and slag. Through real-time monitoring and anomaly warning, the system can effectively avoid problems such as equipment overload, decreased processing efficiency, or resource waste caused by parameter fluctuations.

[0029] The technical advantage of this step lies in its ability to achieve early intervention and adaptive control of the solid waste treatment process through real-time acquisition of multiple parameters and intelligent prediction, significantly improving system stability and processing efficiency. Combined with an IoT platform and historical data analysis, this step provides a data-driven decision-making basis for the entire solid waste treatment system and is a key link in achieving intelligent and efficient solid waste treatment.

[0030] Furthermore, S1 includes: S11 has a weight detection accuracy of ±1%, a temperature detection range of 0~500℃ with an accuracy of ±2℃, a moisture detection accuracy of ±0.5%, and a monitoring frequency of 1Hz.

[0031] Specifically, in the solid waste collection and preliminary monitoring step, the system integrates multiple sensors to collect real-time parameters and identify anomalies in the solid waste entering the treatment process, providing data support for subsequent treatment. This step is technically implemented based on the coordinated control of an automated conveying device and a multi-parameter sensing system, with weight, temperature, and moisture being the core monitoring indicators.

[0032] At the technical implementation level, weight detection employs a high-precision electronic weighing module with an accuracy of ±1%, suitable for solid waste streams with a processing capacity of 1–5 tons / hour. Temperature detection is achieved through infrared or thermocouple sensors, with a detection range of 0–500℃ and an accuracy of ±2℃, covering the characteristic changes of solid waste from thermal power plants under high-temperature environments. Moisture detection uses the dielectric constant method or near-infrared spectroscopy with an accuracy of ±0.5%, ensuring reliable identification of solid waste with high moisture content. The monitoring frequency of all sensors is uniformly set to 1Hz, i.e., data is collected once per second to ensure the system's real-time response capability to the solid waste status.

[0033] Regarding parameters, the system is set to a conveying speed of 0.5–5 m³ / min, which can be dynamically adjusted according to the solid waste flow rate. The anomaly detection mechanism is based on statistical analysis of five consecutive measurements. When the weight change exceeds ±10%, the temperature change exceeds ±20℃, or the moisture change exceeds ±2%, the system will automatically adjust the conveying speed and trigger an alarm signal to prevent abnormal solid waste from entering subsequent processing stages. Furthermore, the system incorporates a time-series prediction model to model and analyze the trends of solid waste flow rate, temperature, and humidity, providing a predictive basis for the classification and drying steps.

[0034] In application scenarios, this step is deployed at the front end of solid waste treatment in thermal power plants, and is suitable for the preliminary treatment of high-temperature and high-humidity solid wastes such as fly ash and slag. Through real-time monitoring and dynamic control, the system can effectively cope with operating conditions such as fluctuations in solid waste composition, conveyor blockages, or equipment malfunctions, ensuring the continuity and stability of the treatment process.

[0035] The technical value of this step lies in providing reliable data input for the entire system. Its high-precision and high-frequency monitoring capabilities significantly improve the response speed and accuracy of subsequent intelligent sorting and drying control, making it a key preliminary step for realizing system intelligence and adaptive optimization.

[0036] S12: When the weight change exceeds ±10%, the temperature change exceeds ±20℃, or the moisture change exceeds ±2% in five consecutive measurements, the conveying speed is automatically adjusted to the range of 0.5~5 m³ / min and an alarm is triggered.

[0037] Specifically, in the solid waste collection and preliminary monitoring step, if the weight change exceeds ±10%, the temperature change exceeds ±20℃, or the moisture change exceeds ±2% in five consecutive measurements, the system will automatically adjust the conveying speed to the range of 0.5–5 m³ / min and trigger an alarm mechanism. This step, based on multi-parameter real-time monitoring and dynamic response control technology, is a key link in realizing intelligent and automated control of solid waste treatment in thermal power plants.

[0038] From a technical implementation perspective, the system continuously monitors solid waste entering the collection bin by deploying a high-precision sensor network, including weight sensors (accuracy ±1%), temperature sensors (measurement range 0–500℃, accuracy ±2℃), and moisture sensors (accuracy ±0.5%, sampling frequency 1Hz). Sensor data is acquired and processed by an embedded control system, which uses a sliding window algorithm to compare and analyze five consecutive measurements. If the change in any parameter exceeds a set threshold (weight change > ±10%, temperature change > ±20℃, moisture change > ±2%), the system will determine it as an abnormal operating condition.

[0039] Regarding parameter indicators, the weight change threshold is ±10%, the temperature change threshold is ±20℃, and the moisture change threshold is ±2%. These thresholds are set based on the typical physical characteristics of solid waste from thermal power plants, ensuring that the system can respond promptly to sudden fluctuations in material levels. The conveying speed adjustment range is 0.5–5 m³ / min, which conforms to the standard operating range of industrial conveying systems, while ensuring that the system can maintain basic operation even under abnormal conditions.

[0040] In application scenarios, this step is mainly used to address instability at the solid waste input end, such as sudden changes in boiler load, conveying equipment failure, or abnormal material mixing. By automatically adjusting the conveying speed and triggering alarms, the system can effectively prevent subsequent processing equipment from malfunctioning due to overload or parameter imbalance, ensuring the continuity and safety of the entire processing flow.

[0041] In terms of technical effectiveness, this step enables real-time perception and rapid response to the input status of solid waste, improving the system's robustness and adaptability. Combined with a time series prediction model, the system can not only handle current anomalies but also predict future trends, providing data support for subsequent steps such as sorting and drying, thereby improving overall processing efficiency and resource utilization rate.

[0042] S2 uses convolutional neural network image recognition and spectral analysis to jointly determine the composition of solid waste. It performs intelligent sorting based on particle size, density and hazardous component thresholds, and triggers secondary detection and manual intervention for abnormal batches to ensure sorting accuracy.

[0043] Specifically, in the classification and intelligent sorting steps, the system uses a combination of convolutional neural network (CNN) image recognition and spectral analysis to accurately determine the composition of solid waste generated by thermal power plants and intelligently sort it based on particle size, density, and hazardous component thresholds. This step is the core of the entire solid waste treatment process, directly affecting the efficiency and safety of subsequent drying, storage, and resource utilization.

[0044] At the technical implementation level, the system first acquires image data of solid waste using a high-resolution industrial camera. The image resolution is 1024×768 pixels or higher, and the frame rate is no less than 15 fps to ensure image continuity and clarity during dynamic transportation. The image data is input into a pre-trained convolutional neural network model, which is customized based on mainstream architectures such as ResNet or YOLO. The input channels are RGB three channels, and the output is the category label of solid waste components (such as fly ash, slag, desulfurization gypsum, etc.). At the same time, the system integrates a near-infrared (NIR) or Raman spectroscopy analysis module to acquire and analyze the surface reflectance spectrum of solid waste. The spectral resolution is 1 nm, and the wavelength range is 400–2500 nm, which is used to identify harmful components such as heavy metals and organic matter.

[0045] Regarding parameters, the system is set with a particle size range of 0.1–50 mm, a density range of 1.5–3.0 g / cm³, and automatically marks particles with a hazardous component threshold >0.1% as unusable solid waste. If the component identification accuracy is below 95%, the system will automatically trigger a secondary detection mechanism or switch to manual verification mode to ensure the reliability of the sorting results. All abnormal batch information will be recorded in the database for subsequent optimization of sorting strategies and model retraining.

[0046] In application scenarios, this step is widely applicable to the front-end sorting stage of solid waste treatment lines in thermal power plants, especially showing significant advantages in the treatment of fly ash and slag mixtures. Through multimodal fusion of images and spectra, the system can effectively identify fine particles and high-density mixtures that are difficult to distinguish using traditional methods, thereby improving the recovery rate of recyclable solid waste.

[0047] The technical advantage of this step lies in achieving high-precision identification and classification of solid waste components, with a sorting accuracy rate of ≥95%, significantly superior to traditional manual or single-sensor sorting methods. Simultaneously, through automatic labeling and anomaly handling mechanisms, the system possesses adaptive optimization capabilities, providing a reliable data foundation for subsequent drying and resource utilization, thereby improving overall processing efficiency and resource utilization.

[0048] Furthermore, S2 includes: S21, the classification rule is that solid waste with a particle size of 0.1 to 50 mm, a density of 1.5 to 3.0 g / cm³, and a hazardous component content of more than 0.1% is marked as unusable solid waste.

[0049] Specifically, in the classification and intelligent sorting steps, the system performs high-precision identification and sorting of solid waste generated by thermal power plants according to preset classification rules. This step is technically achieved through the synergistic effect of multi-dimensional physical parameter detection and intelligent recognition algorithms. Specifically, the system first uses traditional physical sorting methods such as vibrating screens and air separation to perform preliminary particle size and density separation of the solid waste. The particle size detection range is 0.1–50 mm, measured in real time using a high-precision laser particle size analyzer or image processing algorithms; density detection is performed through vibration frequency response or mass-to-volume ratio calculation, with a detection range of 1.5–3.0 g / cm³ and an accuracy of ±0.1 g / cm³. After physical sorting, the system further uses a combination of convolutional neural network (CNN) image recognition technology and near-infrared spectral analysis to determine the hazardous components in the solid waste. When the content of hazardous components exceeds 0.1%, the system marks the batch of solid waste as unusable solid waste and records its characteristics in a database for continuous optimization of the subsequent sorting model.

[0050] In terms of parameter settings, the system sets clear threshold ranges for particle size, density, and hazardous component content to ensure the standardization and repeatability of the sorting process. For example, solid waste with a particle size exceeding 50 mm or less than 0.1 mm will be processed or rejected separately to avoid interfering with subsequent drying and resource utilization stages. Solid waste with a density below 1.5 g / cm³ or above 3.0 g / cm³ may be classified as unusable due to its loose structure or high heavy metal content. The detection accuracy of hazardous components needs to reach ±0.05% to ensure the reliability of the judgment results. The design target for the sorting accuracy of this step is ≥95%, and quality control is achieved through a secondary detection mechanism for abnormal batches and a manual intervention interface.

[0051] In practical applications, this classification rule is widely applicable to solid waste types such as fly ash, slag, and desulfurization gypsum generated by thermal power plants. The system can be deployed as a front-end sorting module in solid waste treatment lines, integrated with conveying devices, sensor networks, and image acquisition systems to achieve a continuous and automated solid waste sorting process. This step plays a crucial "front-end filtering" role in the overall system, effectively reducing ineffective energy consumption in subsequent processing stages and improving resource utilization by accurately identifying unusable solid waste. Simultaneously, its data recording function provides a basis for historical data analysis and step optimization, helping the system adaptively adjust sorting strategies and further improve processing efficiency and intelligence.

[0052] S22, the system automatically marks abnormal batches based on particle size, density and harmful component thresholds, and records them in the database to optimize subsequent sorting strategies.

[0053] Specifically, in the classification and intelligent sorting steps, the system performs multi-dimensional judgments on solid waste materials generated by thermal power plants based on preset classification rules, and continuously optimizes the sorting strategy by automatically marking abnormal batches. The technical implementation of this step is based on the integration of physical property detection and intelligent identification technologies, specifically including comprehensive analysis of particle size, density, and hazardous components.

[0054] At the technical implementation level, the system first uses a vibrating screen to perform preliminary particle size classification of solid waste. The screen aperture is adjustable from 0.1 to 50 mm to accommodate solid waste materials of different particle sizes. Subsequently, pneumatic conveying and wind-driven separation technologies, combined with a density detection module (accuracy range 1.5–3.0 g / cm³), are used to perform density separation of the materials. For component identification, the system deploys an image recognition algorithm based on a convolutional neural network (CNN) combined with near-infrared spectroscopy (NIR) technology to accurately determine hazardous components in the solid waste. When the content of hazardous components detected exceeds 0.1%, the system marks the batch as unusable solid waste and records it in the central database.

[0055] Regarding parameter indicators, the system sets clear engineering standards for particle size, density, and hazardous component thresholds. For example, materials with a particle size exceeding 50 mm may affect the operational stability of subsequent processing equipment and require separate treatment; materials with a density below 1.5 g / cm³ may be light contaminants and require further screening. The logic for judging abnormal batches is as follows: if a batch exceeds the set threshold in any dimension of particle size, density, or hazardous components, the system automatically triggers a secondary detection process to ensure that the sorting accuracy is not less than 95%.

[0056] In application scenarios, this step is widely applicable to the classification and treatment of solid wastes such as fly ash and slag from thermal power plants. By automatically marking abnormal batches and recording them in a database, the system can accumulate a large amount of sorting data, providing data support for subsequent machine learning model training, thereby enabling dynamic optimization of sorting strategies. For example, during continuous operation, the system can adjust the screening frequency or the distribution of sampling points for spectral analysis based on historical data, improving overall processing efficiency.

[0057] The technical benefits of this step lie in significantly improving the intelligence level and resource utilization rate of solid waste classification. Through multi-parameter joint judgment and automatic labeling mechanisms, the system can effectively identify and isolate unusable components, reduce ineffective energy consumption in subsequent processing stages, and provide more accurate input data for drying and resource utilization steps, thereby achieving closed-loop optimization of the entire processing flow.

[0058] S3 dynamically starts the multi-mode drying device according to the moisture content of solid waste. It automatically switches the drying mode and adjusts the temperature, wind speed and drying time by monitoring the rate of moisture descent. If the moisture content still exceeds the standard after drying, the drying cycle is repeated until the standard is met.

[0059] Specifically, in the intelligent drying and treatment step, the system achieves dynamic control and optimized treatment of solid waste moisture through a multi-mode drying device. The core technology of this step is based on a real-time moisture monitoring and feedback control mechanism, combined with adaptive switching of multiple drying methods (such as hot air drying, microwave drying, and high-frequency induction drying) to ensure that the final moisture content of the solid waste meets the resource utilization standard of ≤5%. The system first uses a high-precision moisture sensor (accuracy ±0.5%, monitoring frequency 1 Hz) to perform initial moisture detection on the solid waste entering the drying device. If the detected value exceeds 10%, the drying process is automatically triggered.

[0060] In terms of implementation, the system employs a closed-loop control strategy, continuously monitoring the rate of moisture reduction during the drying process. If the rate of moisture reduction is ≤1% / 10 min, or if the temperature or wind speed deviation exceeds the set thresholds (temperature 80–300℃, wind speed 2–8 m / s), the system will automatically switch drying modes or adjust the heating power to improve drying efficiency. The drying time is set to 30–120 minutes and can be dynamically adjusted according to the type of solid waste and the initial moisture content. After drying is completed, the system re-detects the moisture content; if it is still >5%, it automatically enters a repeat drying cycle until the moisture content is ≤5%.

[0061] The energy efficiency control target for this step is to ensure that the drying energy consumption per ton of solid waste does not exceed 2–5 kWh. Through multi-sensor fusion and intelligent algorithm optimization, refined management of the drying process is achieved. In practical applications at thermal power plants, this technology can effectively address the issue of moisture fluctuations in different batches of solid waste, improving the feasibility and stability of subsequent resource utilization (such as building material preparation and soil improvement). Simultaneously, this step works in conjunction with online monitoring and historical data analysis modules to provide key input parameters for the overall adaptive optimization of the system, significantly improving processing efficiency and resource recovery rate.

[0062] Furthermore, S3 includes: S31, the drying methods include hot air, microwave and high frequency induction, the parameter adjustment range is temperature 80~300℃, wind speed 2~8 m / s, drying time 30~120 minutes.

[0063] Specifically, in the intelligent drying and treatment process, the system employs three drying methods: hot air, microwave, and high-frequency induction, to achieve efficient control of the moisture content in solid waste from thermal power plants. The core of this step lies in automatically activating the drying device based on the initial moisture content of the solid waste (>10%), and using a multi-parameter dynamic adjustment mechanism to reduce the final moisture content to ≤5%, meeting the resource utilization standard. At the technical implementation level, the system integrates multiple drying technologies and combines them with real-time feedback control to ensure the energy efficiency and stability of the drying process.

[0064] In some implementations, hot air drying heats the surface of solid waste through high-temperature air convection, with a temperature range of 80–300℃, wind speed controlled at 2–8 m / s, and drying time set at 30–120 minutes. Microwave drying utilizes electromagnetic waves to penetrate the interior of solid waste, causing water molecules to vibrate rapidly and evaporate, making it suitable for solid waste materials with high moisture content and dense structure. High-frequency induction drying generates heat through electromagnetic induction, offering advantages such as uniform heating and fast response, making it suitable for solid waste with high metal content. The system automatically switches drying modes based on the solid waste composition, moisture content, and downstream treatment requirements through preset control logic.

[0065] Regarding parameter adjustment, the system monitors the rate of moisture decrease during the drying process in real time using a moisture sensor. If the rate of change is ≤1% / 10 min, or if the temperature or wind speed deviation exceeds the set threshold (e.g., ±5%), the system triggers a switch in the drying mode or an adjustment in the heating power. After drying is completed, the system checks the moisture content again. If it is still >5%, the system automatically enters a repeat drying cycle until the set parameters are met. The drying energy consumption is controlled within the range of 2–5 kWh per ton of solid waste, which meets industrial energy-saving standards.

[0066] This step is widely used in the pretreatment of high-moisture-content solid wastes such as fly ash and slag, and is especially suitable for dehydration treatment before the resource utilization of solid waste in thermal power plants. By dynamically controlling the drying parameters, the system not only improves drying efficiency but also significantly reduces energy consumption, providing stable and controllable material input conditions for subsequent resource utilization. It is a key step in achieving efficient treatment and recycling of solid waste.

[0067] S32: When the rate of change in moisture content is ≤1% / 10 min, or when the temperature or wind speed deviation exceeds the set threshold, the system automatically switches the drying mode or increases the heating power, and the drying energy consumption is controlled within 2 to 5 kWh per ton of solid waste.

[0068] Specifically, in the intelligent drying and treatment process, when the system detects that the rate of change in the moisture content of the solid waste is ≤1% / 10min, or that the temperature or wind speed deviation exceeds the set threshold, it will automatically switch the drying mode or increase the heating power to ensure that the drying efficiency and energy consumption are controlled within a reasonable range. This step is based on a multi-sensor fusion and dynamic feedback control mechanism to achieve adaptive adjustment of the drying process.

[0069] From a technical implementation perspective, the system monitors the rate of change in the moisture content of solid waste in real time using a high-precision moisture sensor (accuracy ±0.5%, sampling frequency 1Hz). If the rate of moisture decrease during continuous monitoring is lower than a set threshold, i.e., the moisture decrease is less than 1% every 10 minutes, the system will determine that the current drying method is inefficient, possibly caused by changes in solid waste characteristics, fluctuations in ambient temperature and humidity, or a decline in equipment performance. At this time, the system will automatically switch to other drying modes according to a preset drying strategy library, such as switching from hot air drying to microwave or high-frequency induction drying, to improve the drying rate. Simultaneously, if the temperature sensor (accuracy ±2℃) or the wind speed sensor detects that the actual temperature or wind speed deviates from the set value by more than ±5% (e.g., the set temperature is 200℃, but the actual temperature is below 190℃ or above 210℃), the system will trigger a heating power adjustment or wind speed recalibration mechanism to ensure that the drying environment is in optimal condition.

[0070] In terms of parameters, the drying temperature range is 80–300℃, the wind speed range is 2–8 m / s, and the drying time is controlled between 30 and 120 minutes. By dynamically adjusting these parameters, the system keeps the drying energy consumption within 2–5 kWh per ton of solid waste, meeting industrial energy-saving standards. Furthermore, after drying, the system will re-detect the moisture content; if it remains above 5%, it will automatically enter a repeat drying cycle until the set drying endpoint conditions are met.

[0071] In application scenarios, this step is widely applicable to the treatment of high-moisture solid waste (such as wet desulfurization gypsum and high-moisture fly ash) generated by thermal power plants. Through real-time feedback and multi-mode switching, the system can cope with the differences in physicochemical properties of different batches of solid waste, ensuring the stability and repeatability of the drying process.

[0072] The technical benefits of this step are a significant improvement in drying efficiency and energy efficiency ratio, avoiding limited resource utilization due to insufficient drying or energy waste caused by excessive drying. Through a dynamic control strategy, the system controls unit energy consumption to 2-5 kWh / ton while ensuring solid waste moisture content is ≤5%, which is more than 10% lower than traditional constant temperature drying methods. This provides high-quality raw materials for subsequent resource utilization and achieves the goal of green and low-carbon operation.

[0073] S4 utilizes an IoT platform to perform multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generate optimization strategies, and dynamically adjust drying temperature, wind speed, conveying speed, and equipment load. At the same time, it triggers emission reduction mode and alarms when dust concentration exceeds the standard.

[0074] Specifically, in the online monitoring and intelligent decision-making process, the system uses an IoT platform to collect key operating parameters and perform multi-threshold judgments in real time during the solid waste treatment process of thermal power plants, thereby achieving dynamic adjustment of drying temperature, wind speed, conveying speed, and equipment load. This step is based on a distributed sensor network and edge computing architecture, integrating sensors for weight, temperature, moisture, and dust concentration, and collecting data at a frequency of 1Hz to ensure the system's highly timely perception of the solid waste status.

[0075] At the technical implementation level, the IoT platform interacts with sensors deployed at each processing node via lightweight communication protocols such as MQTT or CoAP. The system first preprocesses the collected parameters, including filtering, normalization, and outlier removal, and then inputs the processed data into a multi-parameter threshold judgment module. This module judges based on preset operating standards; for example, when the processing efficiency is below 95% or the energy consumption per ton of solid waste exceeds 6 kWh / ton, the system will automatically trigger optimization strategies, adjusting parameters such as drying temperature, wind speed, and conveyor speed. Furthermore, when the dust concentration exceeds 50 mg / m³, the system will immediately activate emission reduction mode and issue an alarm to operators via audible and visual alarms to prevent dust pollution from exceeding standards.

[0076] Regarding the parameters, the system is set with a treatment efficiency threshold of 95%, an energy consumption threshold of 6 kWh / ton, and a dust concentration threshold of 50 mg / m³. The drying temperature adjustment range is 80–300℃, the wind speed adjustment range is 2–8 m / s, and the conveying speed adjustment range is 0.5–5 m³ / min. These parameters are all set based on industry standards for solid waste treatment in thermal power plants (such as GB / T 18599-2020 "Standard for Pollution Control of General Industrial Solid Waste Storage and Landfill") to ensure the safety and compliance of the system operation.

[0077] This step is widely deployed in the drying and conveying stages of solid waste treatment in thermal power plants, and is particularly suitable for treating high-moisture solid wastes such as fly ash and slag. By dynamically adjusting the drying temperature and air velocity, the system can effectively improve drying efficiency and reduce energy consumption. At the same time, it can promptly activate emission reduction mechanisms when dust concentration exceeds the standard, ensuring environmental safety and stable equipment operation.

[0078] From a technical perspective, this step achieves closed-loop control of the solid waste treatment process, improving system response speed and operational stability. Through multi-parameter threshold judgment and adaptive optimization strategies, the system can reduce energy consumption by more than 10% while ensuring that dust emissions meet environmental standards, significantly improving the intelligence level and resource utilization efficiency of solid waste treatment in thermal power plants.

[0079] Furthermore, S4 includes: S41 When the processing efficiency is below 95% or the energy consumption exceeds 6 kWh / ton of solid waste, the system automatically generates and executes optimization strategies, including adjusting the drying temperature, wind speed, conveying speed and equipment load.

[0080] Specifically, when the system's online monitoring module detects that the processing efficiency is below 95% or energy consumption exceeds 6 kWh / ton of solid waste, it will automatically trigger the optimization strategy generation and execution mechanism. This step is based on multi-dimensional data collected in real time by the IoT platform, including solid waste weight, temperature, moisture content, drying efficiency, and equipment operating status, and anomaly identification is performed through preset multi-parameter threshold judgment logic. Specifically, the system uses a distributed sensor network to continuously monitor key parameters at a sampling frequency of 1 Hz and uploads the data to the central control unit for real-time analysis.

[0081] At the technical implementation level, the system's built-in intelligent decision-making engine dynamically adjusts key control variables such as drying temperature, wind speed, conveyor speed, and equipment load based on a preset optimization model. For example, when a decrease in drying efficiency is detected, the system can automatically switch drying modes based on the current rate of moisture reduction (e.g., moisture reduction change rate ≤ 1% / 10 min), switching from hot air drying to microwave or high-frequency induction drying to improve the drying rate and reduce energy consumption. Simultaneously, the wind speed adjustment range is 2–8 m / s, and the system can optimize the wind speed gradient based on the airflow distribution model within the drying chamber, ensuring uniform heat distribution and reducing energy waste.

[0082] Regarding parameter settings, the system sets a processing efficiency threshold of 95% and an energy consumption threshold of 6 kWh / ton of solid waste. Exceeding these ranges triggers an optimization strategy. The generation of the optimization strategy relies on the fusion analysis of historical and real-time data, employing a time series prediction model to predict processing trends and adaptively adjusting parameters based on equipment operating status. For example, when excessively high conveying speed leads to a decrease in drying efficiency, the system can reduce the conveying speed from 5 m³ / min to 0.5–2 m³ / min to match the drying capacity.

[0083] This step is widely applicable in practical scenarios for continuous operation of solid waste treatment in thermal power plants, especially when treating solid waste with high moisture content (such as desulfurization gypsum) or when energy consumption increases due to equipment aging. It can effectively maintain the system operating within the optimal range. By dynamically adjusting the drying temperature (80-300℃) and wind speed, the system can control drying energy consumption within the range of 2-5 kWh / ton of solid waste, thereby improving overall energy efficiency and reducing operating costs.

[0084] In summary, this step, through the linkage mechanism of multi-parameter real-time monitoring and intelligent optimization strategies, realizes closed-loop control of the solid waste treatment process in thermal power plants, and is a key link in improving the system's intelligence level and resource utilization efficiency.

[0085] S42: When the dust concentration exceeds 50 mg / m³, the emission reduction mode is triggered and an alarm is sounded. At the same time, the dust concentration data is recorded to the database to optimize subsequent emission reduction strategies.

[0086] Specifically, in the online monitoring and intelligent decision-making process, when the dust concentration exceeds 50 mg / m³, the system will automatically trigger the emission reduction mode and issue an alarm signal. Simultaneously, the dust concentration data will be recorded in real-time to the database for subsequent optimization of emission reduction strategies. This step is based on a multi-sensor fusion monitoring mechanism, combined with an IoT platform to achieve dynamic response and closed-loop control of dust emissions.

[0087] From a technical implementation perspective, the system deploys high-precision dust concentration sensors at key processing nodes (such as drying outlets, conveyor channels, and storage bin entrances). These sensors utilize laser scattering or beta-ray absorption principles for real-time detection, with a sampling frequency of at least 1 Hz and a detection accuracy within ±5%. Dust concentration data is uploaded to the central control unit via industrial Ethernet or wireless communication modules (such as LoRa, 5G, or Wi-Fi 6), where it is analyzed in real-time by edge computing nodes or a cloud server. If three consecutive detection values ​​exceed a set threshold... When this occurs, the system determines it to be an abnormal emission event and automatically activates the emission reduction control logic.

[0088] In terms of parameters, the dust concentration monitoring range is 0–100 mg / m³, the response time is less than 2 seconds, and the alarm delay is controlled within 1 second. The triggering condition for emission reduction mode is... ,in This represents the measured dust concentration at the current moment. Emission reduction strategies include adjusting the conveyor speed, starting dust collection equipment (such as bag filters or electrostatic precipitators), and optimizing drying parameters to reduce the dust emission rate. The system simultaneously records dust concentration data to the database in the format of timestamp + concentration value, with a sampling frequency of 1 Hz and a storage period of one record per second in real time, ensuring data continuity and traceability.

[0089] In terms of application scenarios, this step is widely used at key emission points in the solid waste treatment process of thermal power plants, such as drying outlets, conveyor belt ends, and storage silo inlets. When the system detects that the dust concentration exceeds the standard, emission reduction control can be activated immediately to prevent dust from spreading into the environment. At the same time, data accumulation provides training samples for subsequent machine learning models, enabling adaptive optimization of parameters such as drying efficiency and conveying rate, thereby improving the overall environmental performance and operating efficiency of the system.

[0090] The technical benefits of this step lie in its ability to effectively control dust emissions through real-time monitoring and intelligent response mechanisms, ensuring that emission concentrations remain below environmental standards. Simultaneously, the data recording function provides a basis for long-term system optimization, enhancing the scientific rigor and adaptability of emission reduction strategies and achieving a green and intelligent upgrade of the solid waste treatment process in thermal power plants.

[0091] S5 uses machine learning algorithms to perform long-term regression analysis on the real-time collected processing data to predict future trends in processing efficiency, energy consumption, and resource utilization. Based on the prediction results, it automatically adjusts control parameters and performs equipment maintenance operations to achieve adaptive optimization.

[0092] Specifically, in the historical data analysis and optimization step, the system uses machine learning algorithms to perform long-term regression analysis and predictive modeling on the real-time collected solid waste treatment data. This enables the prediction of future trends in key performance indicators such as treatment efficiency, energy consumption, and resource utilization rate. Based on the prediction results, the system automatically adjusts control parameters or performs equipment maintenance operations to achieve adaptive optimization. This step is the core link in achieving closed-loop control and continuous improvement in the entire intelligent thermal power plant solid waste treatment system.

[0093] At the technical implementation level, the system first collects data at a frequency of 1 Hz per second using sensors deployed in each processing module (such as weight, temperature, moisture, and dust concentration), and uploads the data to the central data processing unit in real time. This unit uses time-series-based regression models (such as ARIMA and LSTM) to model and analyze historical data, identifying periodic changes, trend characteristics, and abnormal patterns in the solid waste treatment process. Simultaneously, the system introduces predictive models (such as linear regression, support vector regression (SVR), or ensemble learning models) to predict future treatment efficiency, energy consumption, and resource recovery rates. The input variables of the predictive models include multi-dimensional features such as the current particle size, density, moisture content, treatment time, and equipment operating status of the solid waste, and the output is an estimate of performance indicators within a future time window.

[0094] Regarding parameters, the system sets an optimization target of ≥95% for processing efficiency, ≤6 kWh per ton of solid waste for energy consumption, and ≥8% for resource utilization rate. When the processing efficiency output by the predictive model is lower than 95% or the energy consumption exceeds 6 kWh / ton, the system will automatically trigger optimization strategies, such as adjusting drying temperature, wind speed, conveyor speed, or equipment load. Furthermore, if the dust concentration exceeds 50 mg / m³, the system will enter emission reduction mode and issue an alarm signal to prevent environmental pollution.

[0095] In application scenarios, this step is widely used in the closed-loop control of the entire solid waste treatment process in thermal power plants, especially in key stages such as drying, sorting, conveying, and storage. Through long-term trend prediction, the system can identify equipment aging, abnormal energy consumption, or processing bottlenecks in advance, thereby performing preventive maintenance or parameter adjustments before failures occur, ensuring stable system operation and improving resource utilization.

[0096] The technical value of this step lies in the fact that it enables data-driven dynamic optimization through machine learning, which not only improves the system's response speed and control precision, but also significantly reduces the need for manual intervention, improves overall processing efficiency and resource recovery rate, and provides solid technical support for the intelligent and green treatment of solid waste in thermal power plants.

[0097] S6 When downstream demand changes by ≥20%, the system automatically optimizes the delivery plan and adjusts the storage capacity to the range of 50-200m³ based on flow and weighing data combined with historical prediction models to ensure downstream utilization rate ≥90%.

[0098] Specifically, in the resource utilization and storage steps, when the downstream demand changes by 20% or more, the system will automatically optimize the transportation plan and adjust the storage capacity based on real-time collected flow and weighing data, combined with historical prediction models, to ensure that the downstream utilization rate is not less than 90%. This step is a key link in achieving dynamic response and efficient resource allocation in the entire solid waste treatment system.

[0099] From a technical implementation perspective, the system uses high-precision weighing sensors and flow meters deployed on the conveying line to acquire real-time data on the weight and conveying rate of solid waste. The weighing accuracy is ±1%, and the flow rate adjustment range is 0.5–5 m³ / min. Simultaneously, the system's built-in historical prediction model, based on time series analysis (such as ARIMA and LSTM), predicts trends in downstream demand fluctuations. When a demand change of ≥20% is detected, the system triggers an optimization algorithm to recalculate the optimal conveying rate and batch allocation strategy to match the dynamic adjustment of downstream processing capacity. The storage bin capacity is designed to be 50–200 m³. Based on the downstream processing capacity output by the prediction model, the system dynamically adjusts the storage bin filling strategy to ensure its occupancy rate is not less than 80%, thereby avoiding resource waste or processing interruptions due to overfilling or empty bins.

[0100] Regarding parameters, the system sets a response threshold of 20% for changes in downstream demand and requires that downstream utilization must be ≥90% after adjustment. The flow rate adjustment range is 0.5–5 m³ / min, the weighing accuracy is ±1%, and the prediction model updates at a rate of one data point per second to ensure real-time responsiveness. Furthermore, the system ensures sufficient buffering capacity under different operating conditions by setting a maximum storage capacity of 200 m³ and a minimum of 50 m³.

[0101] In application scenarios, this step is suitable for the classified transportation and storage management of materials such as fly ash and slag in the solid waste treatment system of thermal power plants. When downstream users such as cement plants and building material plants experience sudden changes in demand due to production fluctuations, the system can respond quickly to avoid resource waste or processing interruptions caused by supply and demand mismatches. For example, if the demand for slag surges by 20%, the system will automatically increase the conveying rate to 5 m³ / min and adjust the discharge plan of the storage silo according to the predictive model to ensure that the downstream utilization rate remains above 90%.

[0102] The technical benefits of this step lie in its significant improvement in the response speed and resource utilization efficiency of the solid waste treatment system through dynamic optimization of transport plans and storage strategies. Combined with high-precision sensors and predictive models, the system can adaptively adjust to sudden changes in demand, reducing manual intervention and enhancing the overall intelligence level of the treatment process. Simultaneously, by maintaining a downstream utilization rate of ≥90%, it effectively increases the resource recovery rate of solid waste, reduces the proportion of stockpiling and landfilling, thereby achieving the goals of energy conservation, emission reduction, and sustainable development.

[0103] The intelligent optimization method for solid waste treatment in thermal power plants according to this invention can dynamically optimize the transportation plan and intelligently adjust the storage capacity (50-200 m³) by integrating flow rate, weighing data and historical prediction models when the system detects a downstream demand fluctuation of ≥20%, thereby further improving the downstream solid waste utilization rate to ≥90% and enhancing the system's responsiveness to demand changes and resource scheduling efficiency.

[0104] The intelligent optimization method for solid waste treatment in thermal power plants according to the present invention significantly improves the level of intelligence and resource utilization rate of solid waste treatment in thermal power plants. Through real-time monitoring of multiple parameters and adaptive control strategies, it achieves a sorting accuracy rate of ≥95%, a reduction in energy consumption of ≥10%, and an increase in resource utilization rate of ≥8%.

[0105] To achieve the above embodiments, the present invention also proposes an intelligent optimization device for solid waste treatment in thermal power plants. Figure 2 This is a schematic diagram of the structure of an intelligent optimization device for solid waste treatment in a thermal power plant, provided as an embodiment of the present invention. Figure 2 As shown, the device includes: The multi-parameter acquisition and prediction module is used to collect data on the weight, temperature, moisture and vibration of solid waste in real time through multi-parameter sensors, and combine historical data to predict the flow rate and temperature and humidity trends of solid waste, and trigger automatic adjustment or alarm for abnormal parameters. The component determination and sorting module is used to determine the solid waste components based on convolutional neural network image recognition and spectral analysis, and to perform intelligent sorting based on particle size, density and hazardous component thresholds, triggering secondary detection or manual intervention for abnormal batches. The multi-mode drying control module is used to dynamically start the multi-mode drying device according to the moisture content of solid waste. It automatically switches the drying mode and adjusts the temperature, wind speed and drying time by monitoring the rate of moisture drop. If the moisture content still exceeds the standard after drying, the drying cycle is repeated until the standard is met. The IoT optimization and emission reduction module is used to use the IoT platform to make multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generate optimization strategies, and dynamically adjust drying temperature, wind speed, conveying speed and equipment load. At the same time, it triggers emission reduction mode and alarms when dust concentration exceeds the standard. The machine learning prediction and adaptation module is used to perform long-term regression analysis on real-time collected processing data through machine learning algorithms to predict future trends in processing efficiency, energy consumption, and resource utilization rate, and automatically adjust control parameters or perform equipment maintenance operations based on the prediction results.

[0106] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0107] To implement the above embodiments, the present invention also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0108] To implement the above embodiments, the present invention also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0109] To implement the above embodiments, the present invention also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0110] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0111] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0112] This invention is intended to provide implementation schemes for users to selectively prevent the use or access to personal information data. That is, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0113] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0114] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0115] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of the invention pertain.

[0116] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0117] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0118] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0119] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0120] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0121] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0122] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An intelligent optimization method for solid waste treatment in thermal power plants, characterized in that, Includes the following steps: S1 collects real-time data on the weight, temperature, moisture, and vibration of solid waste through multi-parameter sensors, and combines historical data to predict the flow rate and temperature and humidity trends of solid waste, triggering automatic adjustment and alarms for abnormal parameters. S2, based on convolutional neural network image recognition and spectral analysis, determines the composition of solid waste, performs intelligent sorting according to particle size, density and hazardous component thresholds, and triggers secondary detection and manual intervention for abnormal batches; S3: The multi-mode drying device is dynamically activated based on the moisture content of solid waste. The drying mode is automatically switched and the temperature, wind speed and drying time are adjusted by monitoring the rate of moisture descent. If the moisture content still exceeds the standard after drying, the drying cycle is repeated until the standard is met. S4 utilizes an IoT platform to perform multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generates optimization strategies, and dynamically adjusts drying temperature, wind speed, conveying speed, and equipment load. Simultaneously, it triggers emission reduction mode and alarms when dust concentration exceeds the standard. S5 uses machine learning algorithms to perform long-term regression analysis on the real-time collected processing data to predict future trends in processing efficiency, energy consumption, and resource utilization rate, and automatically adjusts control parameters and performs equipment maintenance operations based on the prediction results.

2. The method according to claim 1, characterized in that, The system uses multi-parameter sensors to collect real-time data on the weight, temperature, moisture, and vibration of solid waste, and combines this data with historical data to predict solid waste flow rate and temperature / humidity trends. It also triggers automatic adjustments and alarms for abnormal parameters, including: S11 has a weight detection accuracy of ±1%, a temperature detection range of 0~500℃ with an accuracy of ±2℃, a moisture detection accuracy of ±0.5%, and a monitoring frequency of 1Hz. S12: When the weight change exceeds ±10%, the temperature change exceeds ±20℃, or the moisture change exceeds ±2% in five consecutive measurements, the conveying speed is automatically adjusted to the range of 0.5~5 m³ / min and an alarm is triggered.

3. The method according to claim 1, characterized in that, The method of jointly determining solid waste composition based on convolutional neural network image recognition and spectral analysis, and intelligently sorting according to particle size, density, and hazardous component thresholds, triggering secondary detection and manual intervention for abnormal batches, includes: S21, the classification rule is that solid waste with a particle size of 0.1 to 50 mm, a density of 1.5 to 3.0 g / cm³, and a hazardous component content of more than 0.1% is marked as unusable solid waste; S22, the system automatically marks abnormal batches based on particle size, density and harmful component thresholds, and records them in the database to optimize subsequent sorting strategies.

4. The method according to claim 1, characterized in that, The process involves dynamically activating a multi-mode drying device based on the solid waste moisture content. This involves automatically switching drying modes and adjusting temperature, airflow, and drying time by monitoring the rate of moisture descent. If the moisture content still exceeds the standard after drying, the drying cycle is repeated until the standard is met. This includes: S31, the drying methods include hot air, microwave and high frequency induction, the parameter adjustment range is temperature 80~300℃, wind speed 2~8m / s, drying time 30~120 minutes; S32: When the rate of change in moisture content is ≤1% / 10 min, or when the temperature or wind speed deviation exceeds the set threshold, the system automatically switches the drying mode and increases the heating power, and the drying energy consumption is controlled within 2 to 5 kWh per ton of solid waste.

5. The method according to claim 1, characterized in that, The method utilizes an IoT platform to perform multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generates optimization strategies, and dynamically adjusts drying temperature, wind speed, conveying speed, and equipment load. Simultaneously, it triggers an emission reduction mode and alarm when dust concentration exceeds the standard, including: S41 When the processing efficiency is below 95% or the energy consumption exceeds 6kWh / ton of solid waste, the system automatically generates and executes optimization strategies, including adjusting the drying temperature, wind speed, conveying speed and equipment load. S42: When the dust concentration exceeds 50 mg / m³, the emission reduction mode is triggered and an alarm is sounded. At the same time, the dust concentration data is recorded to the database to optimize subsequent emission reduction strategies.

6. The method according to claim 1, characterized in that, Also includes: S6 When downstream demand changes by ≥20%, the system automatically optimizes the delivery plan and adjusts the storage capacity to the range of 50-200m³ based on flow and weighing data combined with historical prediction models to ensure downstream utilization rate ≥90%.

7. An intelligent optimization device for solid waste treatment in thermal power plants, characterized in that, include: The multi-parameter acquisition and prediction module is used to collect solid waste weight, temperature, moisture and vibration data in real time through multi-parameter sensors, and combine historical data to predict solid waste flow and temperature and humidity trends, and trigger automatic adjustment and alarm for abnormal parameters. The component determination and sorting module is used to determine the solid waste components based on convolutional neural network image recognition and spectral analysis, and to perform intelligent sorting based on particle size, density and hazardous component thresholds. It also triggers secondary detection and manual intervention for abnormal batches. The multi-mode drying control module is used to dynamically start the multi-mode drying device according to the moisture content of solid waste. It automatically switches the drying mode and adjusts the temperature, wind speed and drying time by monitoring the rate of moisture drop. If the moisture content still exceeds the standard after drying, the drying cycle is repeated until the standard is met. The IoT optimization and emission reduction module is used to use the IoT platform to make multi-threshold judgments on parameters such as processing efficiency, energy consumption, and dust concentration, generate optimization strategies, and dynamically adjust drying temperature, wind speed, conveying speed and equipment load. At the same time, it triggers emission reduction mode and alarms when dust concentration exceeds the standard. The machine learning prediction and adaptation module is used to perform long-term regression analysis on real-time collected processing data through machine learning algorithms to predict future trends in processing efficiency, energy consumption, and resource utilization rate, and automatically adjust control parameters and perform equipment maintenance operations based on the prediction results.

8. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-6.

Images