Method and device for determining coal quality based on coal quality parameters

Abstract

The application provides a method and device for determining coal quality based on coal quality parameters, wherein the method comprises: establishing a mapping relationship between the coal quality parameters and a plurality of characteristic factors affecting the operation of a coal furnace, to form an initial coal quality model; collecting the coal quality parameters of the coal entering the coal furnace and the operation data of the coal furnace of the coal yard in real time through an online coal quality monitor; based on the real-time collected coal quality parameters of the coal entering the coal furnace and the operation data of the coal furnace of the target coal yard, the initial coal quality model is adaptively optimized and updated, the grid demand peak shaving, frequency modulation and reactive power compensation function correlation technical mechanism influences the key steps of combustion and optimization strategy, the corresponding algorithm is called to apply an integrated strategy, efficient and accurate determination of the coal quality is realized, and the stable operation of the power grid plant is ensured, which realizes the collaborative linkage of the unified power market and the new power system on the supply side.

Description

Technical Field

[0001] This application belongs to the field of intelligent coal-fired power technology, and in particular relates to a method and apparatus for determining coal quality based on coal quality parameters. Background Technology

[0002] Coal is the primary fuel for thermal power generation, and its quality parameters directly affect boiler thermal efficiency, pollutant emissions, equipment lifespan, and operating costs. With the increasing demand for new power systems, the role of the power grid in power plants is changing, requiring them to provide peak shaving, frequency regulation, and reactive power support. Coal quality directly determines system stability and the ability to meet these functions. Currently, most thermal power dispatching relies on manual experience and static models, without digitizing and quantifying coal quality, making it difficult to adapt to fluctuations in coal quality and the peak shaving needs of the power grid, thus reducing power generation efficiency and system stability.

[0003] There is currently no effective solution for accurately identifying coal quality in order to achieve more efficient thermal power dispatch. Summary of the Invention

[0004] The purpose of this application is to provide a method and apparatus for determining coal quality based on coal quality parameters, which can achieve efficient and accurate determination of coal quality.

[0005] This application provides a method and apparatus for determining coal quality based on coal quality parameters, which is implemented as follows:

[0006] A method for determining coal quality based on coal quality parameters, the method comprising:

[0007] Multiple coal quality parameters for different coal types are obtained, wherein the coal quality parameters include at least one of the following: total moisture, ash content, volatile matter, fixed carbon on a dry basis, sulfur content, carbon content, hydrogen content, nitrogen content, and ash fusion point;

[0008] A mapping relationship is established between the coal quality parameters and multiple characteristic factors affecting coal furnace operation to form an initial coal quality model. The characteristic factors include at least one of the following: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index.

[0009] The coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace are collected in real time by an online coal quality monitoring instrument.

[0010] Based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time from the target coal yard, the initial coal quality model is adaptively optimized and updated to obtain the optimized coal quality model.

[0011] The coal quality parameters of the target coal are obtained, and the coal quality parameters of the target coal are input into the optimized coal quality model to obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors based on the knowledge graph summarized from the coal furnace operation data to find the characteristic factors, key combustion steps and optimization strategies related to the power grid demand.

[0012] The quality of target coal is determined by assigning weights to the characteristic factors of the target coal.

[0013] An apparatus for determining coal quality based on coal quality parameters, comprising:

[0014] The acquisition module is used to acquire multiple coal quality parameters for different coal types, wherein the coal quality parameters include at least one of the following: total moisture, ash content, volatile matter, fixed carbon on a dry basis, sulfur content, carbon content, hydrogen content, and nitrogen content;

[0015] The mapping establishment module is used to establish the mapping relationship between the coal quality parameters and multiple characteristic factors affecting the operation of the coal furnace, forming an initial coal quality model. The characteristic factors include at least one of the following: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index.

[0016] The monitoring module is used to collect coal quality parameters of coal fed into the furnace and furnace operation data in real time through an online coal quality monitor.

[0017] The optimization module is used to adaptively optimize and update the initial coal quality model based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time, so as to obtain the optimized coal quality model.

[0018] The generation module is used to obtain the coal quality parameters of the target coal, input the coal quality parameters of the target coal into the optimized coal quality model, and obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors based on the knowledge graph summarized from the coal furnace operation data to find the characteristic factors, key combustion steps and optimization strategies related to the power grid demand.

[0019] The determination module is used to determine the quality of target coal by weighting the characteristic factors of the target coal.

[0020] An electronic device includes a processor and a memory for storing processor-executable instructions, wherein the processor, when executing the instructions, implements the steps of the method described above.

[0021] A computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0022] The method and apparatus for determining coal quality based on coal quality parameters provided in this application establish a mapping relationship between coal quality parameters and multiple characteristic factors affecting coal furnace operation, forming an initial coal quality model. The method involves real-time acquisition of coal quality parameters of coal fed into the furnace and coal furnace operation data from an online coal quality monitor. Based on the real-time acquisition of coal quality parameters of coal fed into the furnace from a target coal yard and coal furnace operation data, the initial coal quality model is adaptively optimized and updated to obtain an optimized coal quality model. The coal quality parameters of the target coal are then input into the optimized coal quality model to obtain the characteristic factors of the target coal. The quality of the target coal is determined by the weighting of these characteristic factors. In the example above, by mapping and associating coal quality parameters with characteristic factors affecting coal furnace operation, and then influencing key combustion steps and optimization strategies through the linkage mechanism of power grid demand peak shaving, frequency regulation, and reactive power compensation functions, an integrated strategy is applied using corresponding algorithms. This achieves efficient and accurate determination of coal quality and ensures the stable operation of the power grid plant. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of one embodiment of the method for determining coal quality based on coal quality parameters provided in this application;

[0025] Figure 2 This is a flowchart of a method for incorporating coal quality parameters into the modeling of characteristic factors of a digital power system, as provided in this application.

[0026] Figure 3 This is a hardware structure block diagram of an electronic device for determining coal quality based on coal quality parameters, as provided in this application.

[0027] Figure 4 This is a schematic diagram of the module structure of one embodiment of the device for determining coal quality based on coal quality parameters provided in this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0029] It should be noted that the information and data related to users involved in the embodiments of this specification are all information and data authorized by the user or fully authorized by the relevant parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with relevant laws, regulations, and standards, and necessary confidentiality measures have been taken. They do not violate public order and good morals, and corresponding operation entry points are provided for users or relevant parties to choose to authorize or refuse.

[0030] It should also be noted that in the embodiments of this specification, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0031] Given that current methods for calculating sulfur and hydrogen content in coal production and sales do not quantify their impact on coal quality, resulting in insufficient expression of coal quality parameters and a failure to reasonably reflect the proper relationship between production and cost, and considering that the auxiliary functions of coal-fired power plants are increasingly becoming their main contribution under a unified power environment, this case necessitates a multi-headed attention mechanism based on grid peak shaving, frequency regulation, and reactive power compensation needs to measure key factors of coal quality. Market-based fuel costs cannot solely consider carbon content and high / low calorific value. Under new production conditions, it is necessary to introduce parameters related to coal type through grid demand, and then logically link them to key combustion steps, optimization strategies, and technical steps based on physical mechanisms. This involves applying appropriate algorithms to ultimately determine the weighting of changing characteristic factors to reflect coal quality, thereby further defining its value and utility. The development of artificial intelligence provides a possibility for the quantitative measurement of coal quality on the supply side through coal-power linkage, which is conducive to establishing a unified power market and constructing a new power system, creating a more disruptive and innovative method for new quality productivity.

[0032] Figure 1This is a flowchart illustrating one embodiment of the method for determining coal quality based on coal quality parameters provided in this application. While this application provides method operation steps or apparatus structures as shown in the following embodiments or accompanying drawings, more or fewer operation steps or module units may be included in the method or apparatus based on conventional methods or without inventive effort. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the apparatus is not limited to the execution order or module structure described in the embodiments and accompanying drawings of this application. When the method or module structure is applied in actual devices or end products, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiments or accompanying drawings (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment).

[0033] Specifically, such as Figure 1 As shown, the method for determining coal quality based on coal quality parameters may include the following steps:

[0034] Step 101: Obtain multiple coal quality parameters for different coal types, wherein the coal quality parameters include at least one of the following: total moisture, ash content, volatile matter, fixed carbon on a dry basis, sulfur content, carbon content, hydrogen content, nitrogen content, and ash fusion point;

[0035] Step 102: Establish the mapping relationship between the coal quality parameters and multiple characteristic factors affecting the operation of the coal furnace to form an initial coal quality model. The characteristic factors include at least one of the following: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index.

[0036] Step 103: Collect coal quality parameters of coal fed into the furnace and furnace operation data in real time using an online coal quality monitoring instrument;

[0037] Step 104: Based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time from the target coal yard, the initial coal quality model is adaptively optimized and updated to obtain the optimized coal quality model.

[0038] Step 105: Obtain the coal quality parameters of the target coal, input the coal quality parameters of the target coal into the optimized coal quality model, and obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors based on the knowledge graph summarized from the coal furnace operation data to find the characteristic factors related to the power grid demand, key combustion steps and optimization strategies.

[0039] Step 106: Determine the quality of the target coal by assigning weights to the characteristic factors of the target coal.

[0040] Specifically, this example demonstrates several ways to obtain multiple coal quality parameters for different coal types, such as:

[0041] Method 1) Obtain well logging curves for different coal types, including: measured density logging values ​​and sonic transit time; calculate ash and volatile matter based on the well logging curves using the following formula:

[0042] ;

[0043] in, It is ash. These are measured density logging values. For coal matrix density, The density of shale;

[0044] ;

[0045] in, As volatile components, This refers to the time difference of sound waves.

[0046] Method 2) Perform laser-induced breakdown on the coal; obtain the characteristic peak intensity of the laser-induced breakdown spectrum; calculate the sulfur and carbon content based on the characteristic peak intensity of the laser-induced breakdown spectrum:

[0047] ;

[0048] in, Sulfur content, The intensity of the characteristic peak of sulfur at 180.7 nm;

[0049] ;

[0050] in, Carbon content, The characteristic peak intensity is 247.8 nm.

[0051] When establishing the mapping relationship between the coal quality parameters and multiple characteristic factors affecting coal furnace operation, it can be done by establishing a mapping relationship between the characteristic factors and multiple coal quality parameters. Specifically, this example provides several specific mapping relationships for establishing a mapping relationship between a characteristic factor and multiple coal quality parameters, which can be expressed as follows:

[0052] 1) Establish the mapping relationship between total moisture, ash, volatile matter, and lower heating value as follows:

[0053] ;

[0054] in, Based on low heating value, This is an empirical coefficient. It is total water. It is ash. For volatile matter; different coal types correspond to different K values. For example, K is 80-86 for bituminous coal and 85-90 for anthracite.

[0055] 2) Establish the mapping relationship between ash content and volatile matter, and the gross calorific value:

[0056] ;

[0057] in, Based on high calorific value, , , This is an empirical coefficient, for example, when the coal type is bituminous coal. For 335, For 1034, It is 10050.

[0058] 3) Establish the mapping relationship between total moisture, dry-basis fixed carbon, volatile matter, calorific value, and ash content, and combustion characteristic factors as follows:

[0059] ;

[0060] in, Combustion characteristic factor, As volatile components, Calorific value, It is ash. For the fixation of carbon on the drying basis, It is total water content.

[0061] In other words, the combustion characteristic factor characterizes the overall performance of ignition and burnout. The larger the value, the better the performance. Considering that volatile matter determines the ease of ignition, calorific value determines the heat release capacity, ash content is a combustion hindrance, and moisture consumes heat, the fixed carbon / volatile matter ratio can correct the burnout rate. Therefore, the above formula is used for correlation. Furthermore, by introducing a square root term, the synergistic effect of fixed carbon and volatile matter can be corrected, avoiding deviations caused by a single parameter.

[0062] 4) Establish the mapping relationship between volatile matter, ash content, sulfur content, and coal slagging characteristic factors as follows:

[0063] ;

[0064] in, For coal slagging characteristic factors, As volatile components, It is ash. This refers to the sulfur content.

[0065] That is, the coal slagging characteristic factor characterizes the slagging risk during combustion. The larger the value, the more serious the slagging. Considering that ash is the material basis for slagging, low volatile matter (anthracite) is prone to ash accumulation, alkali metal / iron oxides (numerator) lower the ash melting point, silicon and aluminum (denominator) raise the ash melting point, and sulfur promotes caking and slagging, in this example, coupling coal quality indicators (volatile matter, sulfur content) with ash composition indicators can overcome the limitations of existing methods that only consider ash.

[0066] 5) Establish the mapping relationship between volatile matter, ash, and dry-basis fixed carbon, and the coal gasification reaction activity factor as follows:

[0067] ;

[0068] in, It is an active factor in coal gasification reaction. The volatile matter content is the highest; the higher the volatile matter content, the stronger the activity. The 0.6 power is used to mitigate the excessive influence of high volatile matter content. It is ash content, ( The hydrogen-to-oxygen ratio (H / O) is used to characterize the active hydrogen content in coal. Carbon is fixed on a dry basis;

[0069] That is, the higher the value of the coal gasification reaction activity factor, the better the activity and the easier the gasification is. The higher the volatile matter content, the stronger the activity. Ash content hinders the reaction. The hydrogen-oxygen ratio characterizes the active hydrogen content in coal. The total amount of combustible matter can correct the activity. In this example, by introducing a hydrogen-oxygen difference correction term, the active functional group content is accurately characterized, which is more consistent with the gasification mechanism than the single hydrogen content.

[0070] 6) Establish the mapping relationship between volatile matter, ash content, carbon content, hydrogen content, and characteristic factors of coal gasification efficiency:

[0071] ;

[0072] in, As a characteristic factor of coal gasification efficiency, Carbon content, Hydrogen content, Sulfur content, This refers to the calorific value.

[0073] That is, the gasification efficiency characteristic factor characterizes the gasification gas production efficiency. The larger the value, the higher the efficiency. Considering that hydrocarbons are the core elements of gas production, the calorific value determines the gas production calorific value, ash and sulfur are ineffective components, and high volatile matter is easy to escape with the gas. Therefore, in this example, the above method can take into account both the gas production calorific value and the gas production rate to correct the loss of high volatile matter.

[0074] 7) Establish the mapping relationship between hydrogen content, sulfur content, nitrogen content, total moisture content, and characteristic factors of clean coal combustion as follows:

[0075]

[0076] in, Characteristic factors of clean coal combustion Hydrogen content, Sulfur content, Nitrogen content, Calorific value, It is total water. This represents the percentage of silicon dioxide content. This represents the percentage of aluminum oxide content. This represents the mass percentage of ferric oxide. This represents the mass percentage of calcium oxide.

[0077] That is, the clean combustion characteristic factor of coal represents the degree of cleanliness. The higher the value, the cleaner it is. Considering that ash, sulfur and nitrogen are the sources of pollution, moisture will increase the loss of flue gas, the higher the calorific value, the lower the pollution emission per unit calorific value, and the higher the silicon-aluminum ratio, the easier the ash is to be disposed of, based on this, in this example, atmospheric pollution factors (S, N) are coupled to comprehensively characterize the cleanliness.

[0078] 8) Establish the mapping relationship between hydrogen content, sulfur content, nitrogen content, total moisture, and characteristic factors of coal desulfurization potential as follows:

[0079] ;

[0080] in, Characteristic factors for coal desulfurization potential As volatile components, This represents the mass percentage of magnesium oxide.

[0081] That is, the characteristic factor of coal desulfurization potential characterizes the sulfur fixation capacity of coal itself. The larger the value, the stronger the sulfur fixation. Considering that calcium and magnesium are the core elements of sulfur fixation, silicon and aluminum will inhibit calcium and magnesium sulfur fixation. The more combustible matter there is in the combustion atmosphere, the more conducive it is to sulfur fixation. Volatile matter will promote the contact between calcium and magnesium and sulfur. Based on this, in the above example, a combustible matter correction term is introduced to fit the dynamic environment of sulfur fixation during the combustion process, rather than the static ash component ratio.

[0082] 9) Using support vector machines, the mapping relationship between multiple coal quality parameters and grindability index is established as follows:

[0083] ;

[0084] in, The grindability index, For kernel function, For support vector machine coefficients, For bias terms, As a characteristic factor, The number of characteristic factors affecting the grindability index is represented by i, where i is the identifier for the number of characteristic factors.

[0085] In one implementation, determining the quality of target coal through characteristic factors may include: establishing a multi-head attention mechanism based on the power grid demand peak shaving, frequency regulation, and reactive power compensation functions, and obtaining the weight values ​​of each characteristic factor among multiple characteristic factors; weighting and summing multiple characteristic factors to obtain a quality value; and determining the quality of the target coal based on the quality value, wherein the weight values ​​of each characteristic factor are set according to the current power grid demand determination function, so that the coal quality parameters and characteristic factors reflect the changes in coal quality under the guidance of the multi-head attention of the demand function.

[0086] Specifically, in this case, focusing on the three core functional requirements of power grid peak shaving, frequency regulation, and reactive power compensation, a full-process technical system of demand modeling, knowledge association, and feature extraction is constructed. Through a multi-head attention mechanism, the priority of power grid demand is accurately anchored. Combined with the knowledge graph summarized from coal furnace operation data, the deep correlation between demand and coal furnace operation is explored. Finally, key feature factors are efficiently extracted to provide scientific support for coal furnace operation optimization and power grid coordinated scheduling, thereby achieving a dual improvement in energy utilization efficiency and power grid operation stability.

[0087] That is, firstly, the abstract demands for peak shaving, frequency regulation, and reactive power compensation are transformed into a quantifiable and modelable indicator system, clarifying the demand priorities and constraint boundaries under different scenarios; secondly, a bridge is built between the coal furnace and the power grid: a structured association between coal furnace operation data and power grid demand is achieved based on a knowledge graph, establishing a mapping link between power grid demand, coal furnace operation, and optimization strategies; furthermore, key feature factors are efficiently extracted: redundant information is eliminated, and core feature factors that play a decisive role in adapting to power grid demand and optimizing coal furnace operation are selected; finally, standardized feature results are output to provide data support for adjusting coal furnace operation parameters and coordinating power grid and coal furnace scheduling, thereby improving the system's collaborative adaptability. For example, this can be implemented in stages as follows:

[0088] Phase 1: Grid Demand Analysis and Construction of Multi-Owner Attention Mechanism

[0089] In this example, the abstract demand of the power grid is transformed into quantitative features that the model can identify. The core demand is focused through a multi-head attention mechanism, providing a clear anchor point for subsequent associated coal furnace operation data, thus realizing the transformation of demand from abstract to concrete.

[0090] 1. Decomposition and Quantitative Characterization of Core Power Grid Demands:

[0091] First, a systematic breakdown of power grid demand is conducted. Combining power grid operation standards and historical data, a multi-dimensional quantitative indicator system is established to clarify the core parameters, priority rules, and constraints of each demand, ensuring that demand is modelable and assessable.

[0092] Peak shaving demand is quantified into several core indicators, including load fluctuation range (unit: MW), peak-to-valley difference threshold (unit: MW), response delay requirement (unit: s), and regulation accuracy (unit: %). Priority is assigned using a dynamic value mechanism, which is automatically adjusted based on the real-time load pressure of the power grid (load rate ≥85% is high priority, 60%-85% is medium priority, and <60% is low priority).

[0093] Frequency regulation requirements: The core indicators are the allowable frequency deviation range (national standard ±0.2Hz), frequency regulation response speed (unit: s / Hz), frequency regulation accuracy (unit: %), and frequency regulation capacity reserve (unit: MW); the priority is directly linked to the stability of the power grid frequency, and the priority is automatically increased when the frequency deviation exceeds ±0.1Hz.

[0094] Reactive power compensation requirements: Focus on power factor compliance (≥0.95), voltage fluctuation range (±5% of rated voltage), reactive power adjustment range (unit: Mvar), and adjustment response time (unit: s); priority is set in conjunction with grid voltage stability, and high priority is triggered when voltage fluctuation exceeds ±3% of rated voltage.

[0095] Through the above quantification process, the abstract power grid functional requirements are transformed into structured, input-model-compatible data vectors, providing a clear focus and training basis for the construction of a multi-head attention mechanism.

[0096] 2. Construction, training, and optimization of multi-head attention mechanisms:

[0097] Based on quantified power grid demand indicators, a targeted multi-head attention mechanism is constructed. Through parallel focusing and global coordination among multiple heads, it achieves precise adaptation and priority balance for different demands, ensuring that the mechanism's output accurately reflects the current demands of the power grid.

[0098] Mechanism Structure Design: In this example, three dedicated heads are used to correspond to the single demand of peak shaving, frequency regulation, and reactive power compensation, respectively, and are responsible for focusing on the core indicators and weights of the corresponding demand; one global coordination head is based on the attention weight normalization algorithm to balance the priority conflicts between multiple demands (such as when peak shaving and frequency regulation demands are superimposed, the weights are dynamically allocated according to the real-time state of the power grid), so as to achieve precise focus on single demand and collaborative adaptation of multiple demands. The underlying mechanism adopts the Transformer architecture, with the hidden layer dimension set to 512 and the attention head dimension set to 64 to ensure the model's fitting ability.

[0099] Input and training data preparation: The input is a quantified power grid demand index vector. For example, it can be historical power grid operation data for the past 3 years (which may include load data, frequency data, voltage data, reactive power data, etc., with a sampling frequency of 15 minutes / time) or extreme operating condition data (such as load change scenarios caused by typhoons and cold waves) as training samples. Before training, the data is standardized and preprocessed and outliers are removed to ensure data quality.

[0100] Training and optimization strategies: The Adam optimizer is used with an initial learning rate of 0.001. Overfitting is avoided through a learning rate decay mechanism (e.g., 10% decay every 100 rounds). The loss function is mean squared error, aiming to minimize the deviation between the model output and the actual priority of the power grid demand. An early stopping mechanism is introduced during training (training stops if the validation set loss does not decrease for 20 consecutive rounds) to ensure the model's generalization ability.

[0101] Output: The mechanism ultimately outputs a weighted power grid demand feature vector with dimension 128. The vector contains the priority weight of each demand and the target value of the core quantitative indicators, which clarifies the demand direction and quantitative standards that coal furnace operation needs to adapt to under the current power grid scenario, and provides accurate demand retrieval conditions for subsequent association with the coal furnace operation knowledge graph.

[0102] Phase Two: Construction and Association Mining of Knowledge Graph for Coal Furnace Operation

[0103] In this example, a structured knowledge graph is constructed based on the full-process operation data of the coal furnace. Then, the demand feature vector output by the multi-head attention mechanism is used as the core of retrieval to explore the deep correlation between power grid demand and coal furnace operation, and to open up the mapping link between demand and operation, providing a basis for feature extraction.

[0104] 1. Coal furnace operation data collection and knowledge graph construction:

[0105] First, complete the collection, sorting, and preprocessing of data from the entire coal furnace operation process. Then, based on data summarization and domain knowledge, construct a coal furnace operation knowledge graph to transform scattered operation data into a structured knowledge system, achieving the conversion from data to knowledge.

[0106] Data Acquisition and Preprocessing: The acquisition scope covers the core systems of the coal furnace, including the combustion system (coal feed rate, forced / induced draft rate, furnace temperature, furnace pressure, combustion efficiency, ash carbon content), the steam-water system (steam pressure, steam temperature, steam flow rate, feedwater flow rate, water quality indicators), and the control system (regulating valve opening, frequency converter parameters, PLC control commands, operating status indicators). It also integrates historical fault data, optimized adjustment case data, and maintenance record data. For example, the acquisition frequency can be 5 minutes per acquisition. Data preprocessing may include: missing value imputation (using linear interpolation), outlier removal (based on industry standard thresholds), and data standardization (Min-Max normalization), ultimately forming a standardized dataset.

[0107] Knowledge Graph Construction: A knowledge graph is constructed using the core link of operating parameters, key combustion steps, optimization strategies, and operational effects, combined with knowledge from the power industry. Graph nodes can be categorized into four main types: feature factor nodes (e.g., coal feed rate, steam flow rate, furnace temperature), key combustion step nodes (e.g., coal feed adjustment, air supply ratio, furnace temperature control, steam pressure regulation), optimization strategy nodes (e.g., coal feed rate gradient adjustment, air supply / induced draft ratio optimization, valve opening adjustment), and operational effect nodes (e.g., peak shaving response speed, combustion efficiency, energy consumption indicators). The relationships between nodes are constructed based on data association patterns and domain experience. For example: coal feed rate adjustment leads to improved furnace combustion uniformity and faster peak shaving response; air supply ratio optimization leads to improved combustion efficiency and reduced energy consumption. Each edge relationship is assigned a weight based on its association strength, thus forming a complete and reasonable knowledge system for coal furnace operation.

[0108] 2. Exploring the correlation between power grid demand and coal furnace operation:

[0109] The power grid demand feature vector output by the multi-head attention mechanism is used as the core retrieval condition and input into the coal furnace operation knowledge graph. Through graph reasoning algorithms, coal furnace operation elements that are strongly correlated with power grid demand are mined to form a precise mapping relationship between power grid demand and coal furnace operation, thus narrowing down the scope for subsequent feature extraction.

[0110] The dimensions for mining related elements are as follows: First, feature factor correlation: based on the quantitative indicators in the demand feature vector, we screen out the coal furnace operation feature factors directly related to peak shaving, frequency regulation, and reactive power compensation needs (e.g., coal feed rate, steam flow rate, furnace pressure, forced draft / induced draft rate, etc.); Second, key combustion step correlation: we locate the core combustion steps that affect the above feature factors and clarify the transmission path of step adjustment - feature factor change - demand adaptation (e.g., the coal feed adjustment step directly affects the coal feed rate, which in turn affects the steam flow rate, ultimately adapting to the grid peak shaving needs); Third, optimization strategy correlation: we sort out effective strategies in historical data that can achieve grid demand adaptation by adjusting the above feature factors and optimizing combustion steps, forming a strategy library for future reference.

[0111] Association strengthening and redundancy removal: Combining the demand weights output by the multi-head attention mechanism, the mined association elements are quantitatively sorted. Using the association strength threshold method (threshold set to 0.6), elements with an association strength ≥ 0.6 with high-priority grid demand are retained first, while weakly associated redundant information with an association strength < 0.6 (such as coal furnace appearance temperature, ambient humidity, etc., which have minimal impact on demand adaptation) is removed. Finally, a set of association elements focusing on the core needs of the power grid is formed, clarifying the complete association link of demand-feature factors-combustion steps-optimization strategy.

[0112] Phase 3: Key Feature Factor Extraction and Validation

[0113] In this example, based on the set of related elements, key feature factors are extracted through a process of filtering, eliminating, sorting, and verifying to ensure the relevance, effectiveness, and reliability of the feature factors, providing core data support for subsequent engineering applications.

[0114] 1. Precise extraction of key feature factors:

[0115] A hierarchical extraction strategy is adopted to progressively screen core feature factors from the set of related elements, eliminate redundant information, clarify the importance weight of each factor, and ensure that the extraction results can accurately reflect the adaptation relationship between coal furnace operation and power grid demand.

[0116] Preliminary screening: Extract all coal furnace operation characteristic factors from the set of related elements, and combine the experience of domain experts to remove factors that have no substantial impact (such as maintenance record identifiers, data collection timestamps, etc.) to form a set of candidate characteristic factors, ensuring that all factors in the set are directly related to the power grid demand.

[0117] Redundancy Removal: A dual mechanism of correlation analysis and domain validation is employed to remove redundant factors. The correlation between candidate factors can be analyzed using the Pearson correlation coefficient (with a threshold of 0.7) and mutual information method to remove redundant factors with high information overlap (e.g., when the correlation between steam pressure and steam temperature is too high, steam pressure, which has a greater impact on demand adaptation, is retained). Simultaneously, evaluation by power industry experts is combined to ensure the independence and representativeness of the remaining factors after removal.

[0118] Importance ranking and key extraction: Combining the demand weight of the multi-head attention mechanism with the association strength of the knowledge graph, the random forest algorithm is used to evaluate the importance of the screened factors and output the importance score of each factor (range 0-10); an importance threshold is set (score ≥ 6), and the top-N feature factors with scores higher than the threshold are extracted as key feature factors. At the same time, the influence weight of each factor on the different needs of the power grid is defined (e.g., the influence weight of coal feed on peak demand is 0.8, and the influence weight of steam flow on frequency regulation demand is 0.75), forming a set of key feature factors.

[0119] 2. Feature factor validity verification and output:

[0120] Multiple verifications ensure the reliability of key feature factors, preventing subsequent optimization strategies from failing due to factor bias. Standardized results are output to provide clear guidance for engineering applications: After successful verification, a standardized key feature factor report is output, including: key feature factor name, importance weight, adjustment range to adapt to different power grid needs, adjustment response time, and correlation with combustion steps. A feature factor database and a visualized correlation graph are also output, providing data interfaces and core support for the coal furnace operation optimization control system and the power grid-coal furnace collaborative scheduling platform.

[0121] In other words, the power grid demand is quantitatively focused through a multi-head attention mechanism, providing direction for correlation mining; the coal furnace knowledge graph provides a carrier for the correlation between demand and operation, locking in the related elements; key feature factors, after multiple verifications, guide the optimization of coal furnace operation to adapt to power grid demand; at the same time, the optimized coal furnace operation data can be fed back to update the knowledge graph and optimize the parameters of the multi-head attention mechanism, realizing continuous optimization of demand-model-knowledge-feature-application-iteration, ensuring the adaptability and long-term effectiveness of the solution.

[0122] In the example above, while some existing studies have attempted to incorporate coal quality parameters into scheduling models, they are mostly limited to single aspects (e.g., coal blending or combustion control), lacking multi-node optimization from coal quality acquisition to scheduling decisions. Therefore, this example presents a method for using coal quality parameters to model eigenvalue factors in digital power. The model utilizes coal quality parameter eigenvalue factors for model construction: It analyzes the physical correlation effects, essentially labeling different eigenvalues ​​with certain logic, overcoming the limitations of machine recognition relying solely on semantics. A eigenvalue extraction method based on coal quality parameters (such as hydrogen content and ash fusion point) is used for graph neural network training. Then, the coal quality parameters are transformed into digital eigenvalue factors, which are correlated with boiler efficiency, heat consumption, environmental indicators, etc., achieving multi-variable fusion modeling.

[0123] Specifically, we can identify factors that may affect the operation and economy of coal-fired power generating units, such as total moisture, reference moisture, ash content, sulfur content, ash fusion point, volatile matter, fixed carbon, hydrogen content, and nitrogen content. We can then construct a list of influencing factors, such as the coal quality parameters, on the operational performance. Furthermore, we can classify these characteristic factors, such as those affecting thermal efficiency, effective calorific value, corrosion, difficulty in combustion control, calorific value coal consumption, latent heat of vaporization, and hydrogen and nitrogen emissions.

[0124] In implementation, online coal quality monitoring instruments (e.g., laser scattering, X-ray carbon measurement, etc.) are used to collect real-time data on ash, moisture, sulfur content, etc., of coal from the coal yard and coal fed into the furnace, establishing multi-parameter data models for different coal types. Key feature factors (e.g., the mapping relationship between coal calorific value, volatile matter, and ignition delay) are extracted using machine learning algorithms, and the model is continuously trained online for adaptive updates. Guided by the TRIZ "adaptive" principle, the model automatically adapts to changes in different coal types, embedding coal quality information into the scheduling process: during unit load scheduling, fuel heat consumption is estimated based on the coal quality model, automatically optimizing output allocation or proposing coal blending adjustments, thereby ensuring long-term operational stability and economy. Furthermore, coal quality early warning signals can be output for advance warning, such as increasing the blast temperature or adjusting the primary air volume in advance when high-moisture coal is fed into the furnace, avoiding sudden operational risks.

[0125] The impact of various coal quality parameters on operational performance is explained below:

[0126] 1) Moisture (total moisture / baseline moisture)

[0127] The presence of moisture reduces the proportion of combustibles in coal. Before combustion, coal must consume a large amount of heat to evaporate the moisture, leading to a decrease in furnace temperature, delayed ignition of pulverized coal, and an increased risk of incomplete combustion. Simultaneously, increased flue gas volume raises the load on induced draft and forced draft air, directly reducing boiler thermal efficiency and increasing plant power consumption. High-moisture coal also easily causes pulverizer blockage and accelerated wear, increasing maintenance costs.

[0128] 2) Ash content:

[0129] Ash, as a non-combustible mineral, does not directly release heat, and high-ash coal has a relatively low effective calorific value. During combustion, the slag formed by a large amount of ash carries away heat and deposits on the heating surface, leading to decreased heat transfer efficiency, localized overheating, and even the risk of tube rupture. When the ash content is high, the surface area of ​​the pulverized coal particles is large, the ignition point is raised, and the combustion kinetics deteriorate, easily causing incomplete carbon oxidation and resulting in unburned carbon loss. Furthermore, the combustion of high-ash coal increases fly ash and solid waste emissions, raising environmental remediation costs.

[0130] 3) Sulfur content:

[0131] Sulfur in coal can be categorized into combustible and non-combustible types. During combustion, high-sulfur coal produces gases such as SO2 and SO3, causing high-temperature corrosion on heated surfaces like superheaters and reheaters. Sulfates formed in cold-end air preheaters and water-cooled walls can then trigger low-temperature corrosion. SOx emissions require desulfurization systems (limestone-gypsum method, seawater desulfurization, etc.) and increase waste transport volume, leading to higher flue gas resistance and additional energy consumption. Overall, high sulfur content in coal reduces equipment reliability and lifespan, and increases environmental costs such as dust removal and desulfurization.

[0132] 4) Ash melting point:

[0133] The melting temperature of coal ash is a key indicator of its slagging tendency. Low-melting-point ash easily melts and adheres to heated surfaces in high-temperature zones, accumulating over time to form a slagging layer. This hinders heat transfer and causes localized temperature increases, sometimes requiring furnace shutdown for cleaning, thus affecting unit safety and reliability. Therefore, the ash melting characteristics of different coal types necessitate measures such as adjusting furnace temperature or stratified combustion to prevent slagging.

[0134] 5) Volatile matter:

[0135] Volatile matter, comprising volatile hydrocarbons, carbon monoxide, hydrogen, and other components of coal, is a major factor determining coal's ignition performance and combustion stability. High-volatile-content coal has a lower ignition point, allowing for stable flame formation at lower temperatures, faster start-up, improved thermal energy utilization, and reduced unburned carbon. However, excessively high volatile matter content generates a large amount of combustion flue gas, carrying away heat and reducing boiler thermal efficiency; the combustion process is also more intense and rapid, increasing control difficulty and even affecting safety. Therefore, the optimal use of volatile matter content must be optimized by comprehensively considering unit load and burner configuration.

[0136] 6) Fixed carbon:

[0137] Fixed carbon is the main calorific component of coal. Coal with high fixed carbon content undergoes a predominantly late-burning stage during combustion, with a slower flame speed, making it suitable for long-term, stable, high-load combustion. Coal with low fixed carbon (high volatile matter) burns rapidly initially but is difficult to maintain at high temperatures, requiring appropriate furnace temperature management. Combining these two types of coal can balance ignition performance and combustion integrity.

[0138] 7) Hydrogen content / Nitrogen content / Oxygen content:

[0139] Hydrogen in coal increases the specific calorific value of the fuel, but the water vapor produced during combustion carries away additional heat, reducing the actual output. Nitrogen content is directly related to the formation of nitrogen oxides (NOx) in the fuel. High oxygen content indicates more organic oxygen in the coal, typically corresponding to a lower calorific value and more moisture, requiring more coal to achieve the same power generation.

[0140] Based on this, the classification of feature factors reveals the following:

[0141] Moisture-rich coal absorbs a large amount of evaporative heat before combustion, which lowers the furnace temperature and delays the ignition of pulverized coal.

[0142] Ash content reduces the effective calorific value and also carries away heat by forming slag after combustion;

[0143] Sulfur combustion produces SOx, which can cause metal corrosion in high-temperature areas and acid corrosion in low-temperature areas of flue gas.

[0144] The volatile components are flammable and easily ignited, and the furnace temperature is uniform, which can shorten the start-up time and improve the instantaneous thermal efficiency;

[0145] The amount of heat directly determines the amount of coal consumed per unit of electricity; low-calorific-value coal requires more fuel input and increased pulverizing and conveying power.

[0146] A higher hydrogen content results in more water vapor being produced during combustion;

[0147] Nitrogen will be converted into nitrogen oxides, increasing nitrogen and oxygen emissions.

[0148] Therefore, characteristic factors can include: ① high moisture content; ② high ash content; ③ high sulfur content; ④ high volatile matter content; ⑤ calorific value; ⑥ high hydrogen content; and ⑦ nitrogen content. Abstracting characteristic factors into physical properties ensures that these modeling features are key factors in functionality and subsequent generation processes. Characteristic factors are not limited to the above inputs but also include outputs, such as key factors across scenarios and industries, like carbon footprint and reactive power (the power plant's impact on the grid's frequency and voltage). Good characteristic factors contain information including the main characteristics of coal. Only by establishing a database of coal characteristic factor influences can the connection and transmission of implementation information and logic be achieved.

[0149] Furthermore, a subsequent impact database can be established for each characteristic factor to generate corresponding technical solutions and strategies for quantifying the degree of economic impact: a decrease in boiler thermal efficiency and combustible burnout rate can increase the load on mills and fans; it leads to a decrease in heat transfer efficiency and an increased risk of slagging; it requires the operation of desulfurization facilities, thus affecting equipment lifespan and operating costs; excessively high volatile matter will generate a large amount of flue gas that carries away heat and increases the difficulty of combustion control; low calorific value leads to an increase in plant power consumption and fuel consumption rate; additional evaporation heat, i.e., latent heat of vaporization, is required; nitrogen content will be converted into nitrogen oxides, increasing nitrogen and oxygen emissions, and pollution needs to be quantified.

[0150] Specifically, the selection of coal parameters may include the following process:

[0151] S1: Establish a database of the impact of coal quality parameters on operational performance.

[0152] Table 1 below shows the impact of key coal quality parameters on boiler combustion, equipment safety, environmental compliance, and economic efficiency:

[0153] Table 1

[0154]

[0155]

[0156] Based on the aforementioned coal quality parameters, a knowledge graph can be established to demonstrate how these parameters influence the combustion process, equipment status, and economic benefits, ultimately impacting digital scheduling. Furthermore, by utilizing the operational library of coal quality parameters, corresponding models and formula libraries can be invoked to quantify the state of coal combustion. This allows for quantified adjustments to technical solutions in areas such as coal selection and blending strategies, combustion optimization and in-furnace control, boiler thermal efficiency and heat consumption management, peak shaving and frequency regulation response strategies, ancillary service pricing mechanisms, and the linkage between power plant cost accounting and digital scheduling.

[0157] In the example above, based on the thought chain tool in artificial intelligence, factors that may affect the operation and economy of coal-fired power generating units are identified. The influence of coal quality parameters on operational performance is constructed, and then characteristic factors are classified, modeled as factors of these characteristic factors. A subsequent influence library is established for each characteristic factor, leading to corresponding technical solutions and strategies for quantifying the degree of economic impact. An application example integrates coal quality parameters into the data model and algorithm flow, achieving closed-loop optimization in the coal-fired power dispatching process. Guided by the TRIZ innovation principle, this includes strategies such as coal-fired power decoupling and stratified combustion proposed through "functional separation," premixing and preheating measures based on "preparation," intelligent coal blending and thermal storage dispatching based on "parameter changes," and iterative and automatic control features based on "adaptive" and "self-service" algorithms. Unlike existing methods that fail to quantify the characteristic factors and characteristics of coal quality and establish their correlation with technical solutions in the influence database to form strategies, this proposed solution addresses the issue of assigning mechanistic logic to all factors, extracting characteristic factors, and quantifying them into an integrated strategy for decision-making. This allows the composition and content of coal quality to establish a key quantitative analysis and role in subsequent fuel strategies, preheating, intelligent coal blending, and thermal storage scheduling. It enables adaptive algorithm iteration and automatic control features, providing the basic functions of a coal-power intelligent agent. Fuel analysis and AI enable the new productivity model to truly transform productivity into a function of coal quality, driving the correlation between coal quality, technical solutions, and economic effects. This represents a new innovative breakthrough in the research of intelligent quantification of fuel for power system transformation.

[0158] In other words, considering that thermal power generation will shift from being a primary energy source to an auxiliary regulator and support for the power grid in a future power system dominated by new energy sources, its role and function are changing. If we consider the entire power system as a neural network, various energy types are correlated with this network, and this correlation supports the safety and stability of the power grid and users. However, in actual design, construction, commissioning, and operation, no specific technical solution can link this characteristic of coal-fired power generation with the power grid and various energy sources. This correlation will inevitably solve some of the current technical deficiencies of the power grid and power plants, including, but not limited to, ensuring that power grid regulation fully considers coal quality and power plant efficiency, and bringing specific technical effects. By linking the characteristics of the power grid with the characteristics of coal quality parameters, the accuracy and stability of power grid dispatching are improved.

[0159] Specifically, a method is provided for incorporating coal quality parameters into the modeling of characteristic factors of digital power systems, which can be used as follows: Figure 2 As shown, it includes the following steps:

[0160] S201: Collect coal quality parameters, including total moisture, ash, sulfur, volatile matter, fixed carbon, hydrogen content, nitrogen content, and ash fusion point.

[0161] S202: Map the coal quality parameters to characteristic factors that affect boiler operation, wherein the characteristic factors include: combustion rate, burnout rate, slagging risk, and SOx / NOx emission tendency.

[0162] S203: Constructing models based on feature factors to convert physical quantities into computable digital quantities;

[0163] S204: Use reinforcement learning to label and reward feature factors to quantify environmental and quality parameters.

[0164] The established knowledge graph can be represented as follows:

[0165] 1. Core node classification:

[0166] Coal quality parameter nodes: total moisture, reference moisture, ash, volatile matter, fixed carbon, sulfur, nitrogen content, hydrogen content, oxygen content, ash fusion point, coal particle size, and coal powder abrasion characteristics.

[0167] 2. Influencing Mechanisms (Coal Quality Parameters and Influencing Mechanisms):

[0168] Heat absorption and evaporation are related to moisture content; the proportion of combustibles / lower heating value decreases, which are related to ash content and high moisture content; ignition delay / combustion rate changes are related to volatile matter and fixed carbon; slagging risk / heat transfer loss of furnace heating surfaces are related to ash content and low ash melting point; emissions are related to sulfur and nitrogen content; pulverized coal wear and increased mill load are related to high ash and high-hardness minerals.

[0169] 3. Technical module nodes:

[0170] Online coal quality monitoring system, adapted to intelligent coal blending algorithm module;

[0171] In-furnace combustion adaptive control system;

[0172] Thermal storage coupling system;

[0173] Scheduling auxiliary service pricing module.

[0174] 4. Recommended node connection method:

[0175] Starting from the coal quality parameter node, connect to one or more influencing mechanism nodes, representing: parameter → mechanism. Then, from each mechanism node, connect to the relevant technical module node, indicating that the mechanism is the key issue that the technical module needs to address or optimize. The technical module node then connects to one or more economic / operational indicator nodes, indicating that the module influences the final indicator by improving the mechanism.

[0176] For example, a path in a knowledge graph can be represented as follows:

[0177] Ash content → Reduced proportion of combustibles / Ash and slag remove heat → Intelligent coal blending algorithm module (prioritizes low-ash coal or blending) → Improved boiler thermal efficiency → Reduced unit heat consumption.

[0178] Moisture → Evaporative heat loss / Increased mill load → Online coal quality monitoring system and in-furnace adaptive control system → Reduced plant power consumption rate → Decreased marginal cost of power generation.

[0179] Sulfur content → SO2 / SO3 generation / low-temperature metal corrosion → increased desulfurization load / slagging risk → thermal storage coupling system (using inferior coal + thermal storage during low-load periods) → extended equipment life / improved peak-shaving flexibility.

[0180] The methods and embodiments provided in the above-described embodiments of this application can be executed in a mobile terminal, computer terminal, or similar computing device. Taking operation on an electronic device as an example... Figure 3 This is a hardware structure block diagram of an electronic device for a method of determining coal quality based on coal quality parameters, as provided in this application. Figure 3 As shown, the electronic device 10 may include one or more (only one is shown in the figure) processors 02 (processors 02 may include, but are not limited to, processing devices such as microprocessors (MCUs) or programmable logic devices (FPGAs), a memory 04 for storing data, and a transmission module 06 for communication functions. Those skilled in the art will understand that... Figure 3 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, electronic device 10 may also include... Figure 3 The more or fewer components shown, or having the same Figure 3 The different configurations shown.

[0181] The memory 04 can be used to store software programs and modules of application software, such as the program instructions / modules corresponding to the method for determining coal quality based on coal quality parameters in this embodiment. The processor 02 executes various functional applications and data processing by running the software programs and modules stored in the memory 04, thereby realizing the above-mentioned application method for determining coal quality based on coal quality parameters. The memory 04 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 04 may further include memory remotely located relative to the processor 02, and these remote memories can be connected to the electronic device 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0182] The transmission module 06 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 10. In one example, the transmission module 06 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 06 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0183] At the software level, the aforementioned device for determining coal quality based on coal quality parameters can be implemented as follows: Figure 4 As shown, it includes:

[0184] The acquisition module 401 is used to acquire multiple coal quality parameters for different coal types, wherein the coal quality parameters include at least one of the following: total moisture, ash, volatile matter, dry basis fixed carbon, sulfur content, carbon content, hydrogen content, and nitrogen content;

[0185] The mapping establishment module 402 is used to establish the mapping relationship between the coal quality parameters and multiple characteristic factors affecting the operation of the coal furnace, forming an initial coal quality model. The characteristic factors include at least one of the following: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index.

[0186] The monitoring module 403 is used to collect coal quality parameters of coal fed into the furnace and operating data of the coal furnace in real time through an online coal quality monitor.

[0187] The optimization module 404 is used to adaptively optimize and update the initial coal quality model based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time, so as to obtain the optimized coal quality model.

[0188] The generation module 405 is used to obtain the coal quality parameters of the target coal, input the coal quality parameters of the target coal into the optimized coal quality model, and obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors after finding the characteristic factors, key combustion steps and optimization strategies associated with the power grid demand based on the knowledge graph summarized from the coal furnace operation data.

[0189] The determination module 406 is used to determine the quality of the target coal by weighting the characteristic factors of the target coal.

[0190] In one embodiment, the acquisition module 401 can specifically acquire well logging curves for different coal types, wherein the well logging curves include: measured density logging values ​​and sonic transit time; based on the well logging curves, ash content and volatile matter are calculated according to the following formula:

[0191] ;

[0192] in, It is ash. These are measured density logging values. For coal matrix density, The density of shale;

[0193] ;

[0194] in, As volatile components, This refers to the time difference of sound waves.

[0195] In one embodiment, the acquisition module 401 can specifically perform laser-induced breakdown on the coal type; acquire the characteristic peak intensity of the laser-induced breakdown spectrum; and calculate the sulfur content and carbon content based on the characteristic peak intensity of the laser-induced breakdown spectrum.

[0196] ;

[0197] in, Sulfur content, The intensity of the characteristic peak of sulfur at 180.7 nm;

[0198] ;

[0199] in, Carbon content, The characteristic peak intensity is 247.8 nm.

[0200] In one implementation, the mapping establishment module 402 can specifically establish a mapping relationship between a characteristic factor and multiple coal quality parameters.

[0201] In one implementation, the mapping module 402 can specifically establish the mapping relationship between total moisture, ash, and volatile matter, and the lower heating value, as follows:

[0202] ;

[0203] in, Based on low heating value, This is an empirical coefficient. It is total water. It is ash. It refers to volatile matter; different coal types correspond to different K values.

[0204] In one implementation, the mapping module 402 can specifically establish the mapping relationship between total moisture, dry basis fixed carbon, volatile matter, calorific value, and ash content, and combustion characteristic factors as follows:

[0205] ;

[0206] in, Combustion characteristic factor, As volatile components, Calorific value, It is ash. For the fixation of carbon on the drying basis, It is total water content.

[0207] In one implementation, the mapping module 402 can specifically establish the mapping relationship between volatile matter, ash content, and sulfur content, and coal slag characteristic factors as follows:

[0208] ;

[0209] in, For coal slagging characteristic factors, As volatile components, It is ash. This refers to the sulfur content.

[0210] In one embodiment, the mapping module 402 can specifically establish the mapping relationship between volatile matter, ash, and dry-based fixed carbon, and the coal gasification reaction activity factor as follows:

[0211] ;

[0212] in, It is an active factor in coal gasification reaction. The volatile matter content is the highest; the higher the volatile matter content, the stronger the activity. The 0.6 power is used to mitigate the excessive influence of high volatile matter content. It is ash content, ( The hydrogen-to-oxygen ratio (H / O) is used to characterize the active hydrogen content in coal. Carbon is fixed on a dry basis.

[0213] In one implementation, the mapping establishment module 402 can specifically establish the mapping relationship between hydrogen content, sulfur content, nitrogen content, total moisture content, and coal clean combustion characteristic factors as follows:

[0214]

[0215] in, Characteristic factors of clean coal combustion Hydrogen content, Sulfur content, Nitrogen content, Calorific value, It is total water. This represents the percentage of silicon dioxide content. This represents the percentage of aluminum oxide content. This represents the mass percentage of ferric oxide. This represents the mass percentage of calcium oxide.

[0216] In one implementation, the mapping establishment module 402 can specifically establish a mapping relationship between multiple coal quality parameters and grindability index using a support vector machine:

[0217] ;

[0218] in, The grindability index, For kernel function, For support vector machine coefficients, For bias terms, As a characteristic factor, The number of characteristic factors affecting the grindability index is represented by i, where i is the identifier for the number of characteristic factors.

[0219] In one implementation, the determining module 406 can specifically establish a multi-head attention mechanism based on the grid demand peak shaving, frequency regulation, and reactive power compensation functions, and obtain the weight values ​​of each characteristic factor among multiple characteristic factors; perform weighted summation on multiple characteristic factors to obtain a quality value; and determine the quality of the target coal based on the quality value, wherein the weight values ​​of each characteristic factor are set according to the current grid demand determination function, so that the coal quality parameters and characteristic factors reflect the changes in coal quality under the guidance of the demand function multi-head attention.

[0220] This application also provides a specific implementation of an electronic device capable of implementing all steps of the method for determining coal quality based on coal quality parameters in the above embodiments. The electronic device specifically includes: a processor, a memory, a communication interface, and a bus; wherein the processor, memory, and communication interface communicate with each other via the bus; the processor is used to call a computer program in the memory, and when the processor executes the computer program, it implements all steps of the method for determining coal quality based on coal quality parameters in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0221] Step 1: Obtain multiple coal quality parameters for different coal types, wherein the coal quality parameters include at least one of the following: total moisture, ash content, volatile matter, fixed carbon on a dry basis, sulfur content, carbon content, hydrogen content, nitrogen content, and ash fusion point;

[0222] Step 2: Establish the mapping relationship between the coal quality parameters and multiple characteristic factors affecting coal furnace operation to form an initial coal quality model. The characteristic factors include at least one of the following: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index.

[0223] Step 3: Collect coal quality parameters of coal fed into the furnace and furnace operation data in real time using an online coal quality monitoring instrument;

[0224] Step 4: Based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time from the target coal yard, the initial coal quality model is adaptively optimized and updated to obtain the optimized coal quality model.

[0225] Step 5: Obtain the coal quality parameters of the target coal, input the coal quality parameters of the target coal into the optimized coal quality model, and obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors based on the knowledge graph summarized from the coal furnace operation data to find the characteristic factors related to the power grid demand, key combustion steps and optimization strategies.

[0226] Step 6: Determine the quality of the target coal by assigning weights to the characteristic factors of the target coal.

[0227] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the method for determining coal quality based on coal quality parameters in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the method for determining coal quality based on coal quality parameters in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0228] Step 1: Obtain multiple coal quality parameters for different coal types, wherein the coal quality parameters include at least one of the following: total moisture, ash content, volatile matter, fixed carbon on a dry basis, sulfur content, carbon content, hydrogen content, nitrogen content, and ash fusion point;

[0229] Step 2: Establish the mapping relationship between the coal quality parameters and multiple characteristic factors affecting coal furnace operation to form an initial coal quality model. The characteristic factors include at least one of the following: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index.

[0230] Step 3: Collect coal quality parameters of coal fed into the furnace and furnace operation data in real time using an online coal quality monitoring instrument;

[0231] Step 4: Based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time from the target coal yard, the initial coal quality model is adaptively optimized and updated to obtain the optimized coal quality model.

[0232] Step 5: Obtain the coal quality parameters of the target coal, input the coal quality parameters of the target coal into the optimized coal quality model, and obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors based on the knowledge graph summarized from the coal furnace operation data to find the characteristic factors related to the power grid demand, key combustion steps and optimization strategies.

[0233] Step 6: Determine the quality of the target coal by assigning weights to the characteristic factors of the target coal.

[0234] As described above, this application establishes a mapping relationship between coal quality parameters and multiple characteristic factors affecting coal furnace operation, forming an initial coal quality model. The coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace are collected in real time using an online coal quality monitor. Based on the real-time collected coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace, the initial coal quality model is adaptively optimized and updated to obtain an optimized coal quality model. The coal quality parameters of the target coal are input into the optimized coal quality model to obtain the characteristic factors of the target coal. The quality of the target coal is determined by the weighting of the characteristic factors of the target coal. In the example above, by mapping and associating coal quality parameters with characteristic factors affecting coal furnace operation, and then influencing key combustion steps and optimization strategies through the linkage mechanism of power grid demand peak shaving, frequency regulation, and reactive power compensation functions, and calling the corresponding algorithm application integrated strategy, efficient and accurate determination of coal quality is achieved, ensuring the stable operation of the power grid plant.

[0235] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0236] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0237] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0238] While this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or end product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded.

[0239] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0240] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0241] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0242] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0243] The embodiments described in this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0244] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, 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 embodiments in this specification. 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 can 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 and the features of different embodiments or examples.

[0245] The above description is merely an embodiment of the embodiments in this specification and is not intended to limit the embodiments of this specification. For those skilled in the art, various modifications and variations can be made to the embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of this specification should be included within the scope of the claims of the embodiments of this specification.

Claims

1. A method for determining coal quality based on coal quality parameters, characterized in that, The method includes: Obtain multiple coal quality parameters for different coal types, including: total moisture, ash content, volatile matter, fixed carbon on a dry basis, sulfur content, carbon content, hydrogen content, nitrogen content, and ash fusion point; A mapping relationship is established between the various coal quality parameters and a class of characteristic factors affecting coal furnace operation to form an initial coal quality model. The characteristic factors include: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index. The coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace are collected in real time by an online coal quality monitoring instrument. Based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time from the target coal yard, the initial coal quality model is adaptively optimized and updated to obtain the optimized coal quality model. The coal quality parameters of the target coal are obtained, and the coal quality parameters of the target coal are input into the optimized coal quality model to obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors based on the knowledge graph summarized from the coal furnace operation data to find the characteristic factors, key combustion steps and optimization strategies related to the power grid demand. The quality of target coal is determined by assigning weights to the characteristic factors of the target coal.

2. The method according to claim 1, characterized in that, Obtain multiple coal quality parameters for different coal types, including: Obtain logging curves for different coal types, including: measured density logging values ​​and sonic transit time; Based on the well logging curves, calculate the ash and volatile matter using the following formula: ； in, It is ash. These are measured density logging values. For coal matrix density, The density of shale; ； in, As volatile components, This refers to the time difference of sound waves.

3. The method according to claim 1, characterized in that, Obtain multiple coal quality parameters for different coal types, including: Laser-induced breakdown of coal types; Obtain the characteristic peak intensities of the laser-induced breakdown spectrum; The sulfur and carbon content were calculated based on the characteristic peak intensities of the laser-induced breakdown spectrum. ； in, Sulfur content, The intensity of the characteristic peak of sulfur at 180.7 nm; ； in, Carbon content, The characteristic peak intensity is 247.8 nm.

4. The method according to claim 1, characterized in that, Establish a mapping relationship between multiple coal quality parameters and a class of characteristic factors, including: The mapping relationship between total moisture, ash, volatile matter, and basic lower calorific value is established as follows: ； in, Based on low heating value, This is an empirical coefficient. It is total water. It is ash. It refers to volatile matter; different coal types correspond to different K values.

5. The method according to claim 1, characterized in that, Establish a mapping relationship between multiple coal quality parameters and a class of characteristic factors, including: The mapping relationship between total moisture, dry-basis fixed carbon, volatile matter, calorific value, and ash content, and combustion characteristic factors is established as follows: ； in, Combustion characteristic factor, As volatile components, Calorific value, It is ash. For the drying basis, fixed carbon, It is total water content.

6. The method according to claim 1, characterized in that, Establish a mapping relationship between multiple coal quality parameters and a class of characteristic factors, including: The mapping relationship between volatile matter, ash content, sulfur content, and coal slagging characteristic factors is established as follows: ； in, For coal slagging characteristic factors, As volatile components, It is ash. This refers to the sulfur content.

7. The method according to claim 1, characterized in that, Establish a mapping relationship between multiple coal quality parameters and a class of characteristic factors, including: The mapping relationship between volatile matter, ash, and dry-basis fixed carbon and coal gasification reaction activity factors is established as follows: ； in, It is an active factor in coal gasification reaction. The volatile matter content is the highest; the higher the volatile matter content, the stronger the activity. The 0.6 power is used to mitigate the excessive influence of high volatile matter content. It is ash content, ( The hydrogen-to-oxygen ratio (H / O) is used to characterize the active hydrogen content in coal. For the drying basis, fixed carbon, This refers to the carbon content.

8. The method according to claim 1, characterized in that, Establish a mapping relationship between multiple coal quality parameters and a class of characteristic factors, including: The mapping relationship between hydrogen content, sulfur content, nitrogen content, total moisture content, and characteristic factors of clean coal combustion is established as follows: in, Characteristic factors of clean coal combustion Hydrogen content, Sulfur content, Nitrogen content, Calorific value, It is total water. This represents the percentage of silicon dioxide content. This represents the percentage of aluminum oxide content. This represents the mass percentage of ferric oxide. This represents the mass percentage of calcium oxide.

9. The method according to claim 1, characterized in that, Establish a mapping relationship between multiple coal quality parameters and a class of characteristic factors, including: Using support vector machines, a mapping relationship between various coal quality parameters and grindability indices is established: ； in, The grindability index, For kernel function, For support vector machine coefficients, For bias terms, As a characteristic factor, The number of characteristic factors affecting the grindability index is represented by i, where i is the identifier for the number of characteristic factors.

10. The method according to claim 1, characterized in that, The quality of target coal is determined by its characteristic factors, including: A multi-head attention mechanism is established based on the grid demand peak shaving, frequency regulation, and reactive power compensation functions, and the weight values ​​of various characteristic factors among multiple characteristic factors are obtained. The quality value is obtained by weighted summation of multiple feature factors. Based on the quality value, the quality of the target coal is determined, wherein the weight values ​​of various characteristic factors are set according to the current power grid demand function settings, so that the coal quality parameters and characteristic factors reflect the changes in coal quality under the guidance of the multi-head attention of the demand function.

11. A device for determining coal quality based on coal quality parameters, characterized in that, include: The acquisition module is used to acquire multiple coal quality parameters for different coal types, including: total moisture, ash content, volatile matter, fixed carbon on a dry basis, sulfur content, carbon content, hydrogen content, and nitrogen content. The mapping establishment module is used to establish the mapping relationship between the various coal quality parameters and a class of characteristic factors affecting coal furnace operation, forming an initial coal quality model. The characteristic factors include: basic lower heating value, basic higher heating value, combustion characteristic factor, coal slagging characteristic factor, coal burnout characteristic factor, coal gasification reaction activity factor, coal gasification efficiency characteristic factor, clean coal combustion characteristic factor, coal desulfurization potential characteristic factor, and grindability index. The monitoring module is used to collect coal quality parameters of coal fed into the furnace and furnace operation data in real time through an online coal quality monitor. The optimization module is used to adaptively optimize and update the initial coal quality model based on the coal quality parameters of the coal fed into the furnace and the operating data of the coal furnace collected in real time, so as to obtain the optimized coal quality model. The generation module is used to obtain the coal quality parameters of the target coal, input the coal quality parameters of the target coal into the optimized coal quality model, and obtain the characteristic factors of the target coal. The optimized coal quality model is established by first establishing a multi-head attention mechanism based on the peak shaving, frequency regulation and reactive power compensation functions of the power grid, and then extracting key characteristic factors based on the knowledge graph summarized from the coal furnace operation data to find the characteristic factors, key combustion steps and optimization strategies related to the power grid demand. The determination module is used to determine the quality of target coal by weighting the characteristic factors of the target coal.

12. An electronic device comprising a processor and a memory for storing processor-executable instructions, characterized in that, When the processor executes the instructions, it implements the steps of the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 10.

Images