Virtual simulation model based on thermal power plant pneumatic ash conveying

Abstract

The invention relates to the technical field of virtual simulation, and mainly relates to a virtual simulation model based on thermal power plant pneumatic ash conveying. A high-precision, high-performance and autonomous learning processing simulation model library is constructed, and the operation state and the optimization process of ash conveying of the thermal power plant are comprehensively simulated, so that powerful support is provided for operation of the intelligent power plant. According to the method, key technologies such as a simulation technology, a mathematical modeling technology, a three-dimensional modeling technology, a physical engine technology, a big data analysis technology and a neural network technology are mainly used. Firstly, according to relevant parameters and requirements, model construction is achieved through simulation software. And real-time data acquisition is realized through a plurality of communication protocols. The model is constructed through simulation software according to relevant parameters and requirements in combination with the actual situation of on-site physical equipment. And finally, powerful support is provided for operation of the intelligent power plant by comprehensively simulating the operation state and the optimization process of ash conveying of the thermal power plant.

Description

Technical Field

[0001] The invention relates to the technical field of virtual simulation, and mainly to a virtual simulation model based on pneumatic ash conveying in a thermal power plant. Background Art

[0002] As an important part of a thermal power plant, the operating efficiency and safety of the ash conveying system have a significant impact on the overall performance of the power system.

[0003] Traditional ash conveying control often relies on personnel estimating the ash volume and manually setting the execution time based on the volume of the ash, which leads to machine overload and waste of resources.

[0004] At present, some power plants have applied virtual simulation technology to specific links, but most of them have problems such as low simulation model accuracy or complex operation of the simulation system, which is not conducive to user operation and use. Summary of the invention

[0005] This paper mainly aims at the shortcomings existing in the ash conveying process of existing thermal power plants, and proposes a virtual simulation model based on pneumatic ash conveying of thermal power plants. The purpose is to provide strong support for the operation of smart power plants by building a high-precision, high-performance, self-learning simulation model library and comprehensively simulating the operating state and optimization process of ash conveying in thermal power plants.

[0006] To solve the above problems, the present invention adopts the following technical solutions.

[0007] 1. Build a high-precision virtual simulation model: According to the size and related parameters of the equipment, use professional drawing tools to build a digital simulation model. This model can clearly and accurately reflect the physical characteristics and operating rules of each equipment, and can accurately simulate the operating conditions of the ash conveying equipment in thermal power plants under different conditions.

[0008] 2. Build an artificial intelligence algorithm library: According to the characteristics of the ash conveying equipment in thermal power plants, build an intelligent ash conveying AI algorithm library. This algorithm library can continuously learn and calculate based on relevant data such as boiler combustion data, ash volume in ash storage, pipeline pressure value, etc., to provide the optimal frequency for the ash conveying system.

[0009] Compared with the prior art, the advantages of the present invention are:

[0010] 1. Reduce storage space: The present invention can greatly reduce the storage space requirements of the virtual simulation model through advanced model compression methods, thereby reducing data transmission and storage costs.

[0011] 2. Improving loading speed: The present invention can quickly improve the loading speed of the model and improve the data rendering process by compressing and optimizing the simulation model.

[0012] 3. Improve intelligent control: The present invention introduces interactive calculations of artificial intelligence and simulation models, which can calculate the status of equipment and operating parameters in real time, achieve learning while calculating, and intelligently adjust the optimal control. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a partial schematic diagram of the simulation model of pneumatic ash conveying in a thermal power plant.

[0014] Figure 2 Detailed schematic diagram of the simulation model for pneumatic ash conveying in a thermal power plant.

[0015] Figure 3 This is a schematic diagram of the artificial intelligence algorithm library for pneumatic ash conveying in thermal power plants. DETAILED DESCRIPTION

[0016] In order to clearly explain the examples of the present invention, a brief introduction will be given below in conjunction with the accompanying drawings. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] See also Figure 1 Figure 2 ,The simulation model of pneumatic ash conveying in thermal power plant ,includes the following steps:

[0018] 1. Simulation software technology:

[0019] 1. We build the model through simulation software based on the actual situation of the on-site physical equipment (see Table 1) and relevant parameters and requirements.

[0020] 2. According to the characteristics of the equipment type, we use OpenFOAM software to simulate and build equipment such as pipelines.

[0021] Table 1 On-site physical equipment data

[0022]

[0023]

[0024] 2. Mathematical modeling technology:

[0025] 1. Simulation models are usually based on mathematical equations or algorithms to describe the behavior of the system. Therefore, mathematical modeling technology is the core of the simulation model implementation. According to the relevant information of the device, analyze the method of converting the physical device into a digital model.

[0026] 2. In computer simulation, the mathematical model of the system must be rewritten into a simulation model before it can be processed by the computer. This involves converting mathematical equations into a form suitable for computer program operation. Converting the mathematical model into computer-processable code and algorithms generates a simulation environment in the computer based on the initial conditions and constraints set in the model.

[0027] 3. 3D modeling technology:

[0028] First, we need to clarify the application scenarios of virtual simulation based on relevant parameters and requirements, and then determine the required model type, detail level, interactive functions, etc. according to the needs. First, through geometric modeling, use basic geometric elements such as points, lines, and surfaces to build the basic shape and structure of the model. This can be done by manual modeling, scanning objects, or using tools in professional modeling software.

[0029] In texture mapping, texture images are added to the surface of the model to increase realism and details. This can be achieved through parametric texture mapping, cubemaps, normal maps, etc.

[0030] 4. Physics Engine Technology:

[0031] In order to realize the specific movement laws in the ash conveying process in the model, physical engine technology is used to simulate the physical laws in the real world, such as gravity, collision, friction, etc., so that the behavior of objects in the virtual world is more in line with reality, so that the corresponding data can be better calculated.

[0032] See also Figure 3 ,The artificial intelligence algorithm library of pneumatic ash conveying in thermal power plants,includes the following steps:

[0033] 1. Big Data Technology:

[0034] In order to access and process a large amount of data, we apply big data technology for processing. First, we collect data and access data from various sensor devices and control systems. For the accessed data, we use distributed storage technology to store massive amounts of data to improve the concurrency and reliability of data for subsequent analysis, processing and application. Import data from different data sources into a centralized large-scale distributed database or distributed storage cluster. After cleaning and preprocessing, the accessed data can remove a large amount of duplicate data to ensure data accuracy. Next, use statistical analysis, machine learning, data mining and other methods to mine and analyze big data to discover potential patterns, laws and trends. Finally, apply the results of the analysis to actual business.

[0035] 2. Neural Network Technology

[0036] In order to realize the model's analysis, computing and learning capabilities, the input layer is used to receive external information input, the hidden layer is used to process and process the input information, and the output layer is responsible for outputting the final result. Neural network technology is mainly divided into two processes: forward propagation and back propagation. In the forward propagation process, the input signal enters the neural network through the input layer and is passed to the output layer after a series of weighted and activation function processing. The back propagation process continuously optimizes the performance of the network by adjusting the connection weights between neurons based on the error between the output result and the actual value. Finally, the back propagation algorithm is used to adjust the network parameters to reduce the prediction error.

[0037] 3. Intelligent decision-making technology:

[0038] Intelligent decision-making is to analyze and predict the status of equipment by using advanced AI algorithms, such as deep learning, reinforcement learning, or hybrid intelligent algorithms. When implementing an integrated strategy, the AI ​​algorithm is integrated with the simulation model so that the AI ​​algorithm can learn based on the real-time data and information provided by the simulation model. Based on the analysis results of the AI ​​algorithm and the prediction of the simulation model, an intelligent control strategy is formulated to optimally control the equipment.

Claims

1. A virtual simulation model based on pneumatic ash conveying in thermal power plants; its features include Follow these steps: (1) Based on relevant parameters and requirements, the model is constructed through simulation software. (2) Realize real-time data collection through multiple communication protocols. (3) By combining the actual situation of on-site physical equipment and based on relevant parameters and requirements, the model is constructed through simulation software. (4) Use physics engine technology to simulate the physical laws in the real world, so that the behavior of objects in the virtual world is more in line with reality, so that the corresponding data can be better calculated.

2. The simulation model according to claim 1, characterized in that: The optimization strategy includes but is not limited to drawing a virtual model according to the parameters of the physical device.

3. The data information according to claim 1, characterized in that: The optimization strategy includes but is not limited to forward and reverse propagation of neural network technology, continuously optimizing performance, and adjusting network parameters to reduce prediction errors.

4. The data processing and analysis according to claim 1, characterized in that: The optimization strategy includes but is not limited to integrating the AI ​​algorithm with the simulation model, so that the AI ​​algorithm can learn based on the real-time data and information provided by the simulation model.

Images