Biomass gasification energy supply method and system based on intelligent control

Abstract

The invention relates to the technical field of automatic control, and discloses a biomass gasification energy supply method and system based on intelligent control, and the method comprises the steps: constructing a knowledge graph of a biomass gasification unit containing gasification technology, equipment relevance and historical fault mode information; taking temperature, pressure and output fuel gas component information of a reaction zone as input, taking a knowledge graph as priori knowledge, and utilizing a multi-algorithm fusion analysis engine to output an air distribution proportion and a biomass feeding rate of the biomass gasification unit; monitoring the downstream energy consumption load of the biomass gasification unit under the air distribution proportion and the biomass feeding rate; and when the downstream energy consumption load exceeds a preset downstream energy consumption load fluctuation threshold value, a grading emergency response unit of the biomass gasification unit is automatically triggered, and the grading emergency response unit executes progressive control actions of early warning notification, automatic parameter fine adjustment and control strategy switching to safe furnace shutdown according to the threshold value exceeding degree. According to the invention, the gasification efficiency of biomass gasification energy supply can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to a biomass gasification energy supply method and system based on intelligent control, belonging to the field of automatic control technology. BACKGROUND

[0002] Environmental and reliability test intelligent evaluation refers to a technology of quantitatively analyzing performance of a product under simulated environmental stress and predicting reliability through data analysis means. The technology is mainly applied to fields such as aerospace, automobile electronics and precision instruments which have extremely high requirements for product reliability.

[0003] The currently widely used evaluation method is mainly based on fixed test profile and standardized test process. During the test process, the product is placed under the preset environmental stress condition, and the technical personnel records the performance parameter change according to the established procedure. After the test, the reliability evaluation is completed by comparing the historical data threshold or performing conventional statistical analysis. However, due to the use of uniform test conditions, it is not suitable for individual characteristic differences of different products, resulting in insufficient accuracy of the evaluation results. SUMMARY

[0004] The present application provides a biomass gasification energy supply method and system based on intelligent control, which mainly aims to improve the gasification efficiency of biomass gasification energy supply.

[0005] To achieve the above purpose, the biomass gasification energy supply method based on intelligent control provided by the present application comprises: Collecting temperature, pressure and output gas component information of a reaction zone corresponding to a biomass gasification unit; Constructing a knowledge graph of the biomass gasification unit containing gasification process, equipment correlation and historical failure mode information; Using the temperature, pressure and output gas component information of the reaction zone as input, the knowledge graph as prior knowledge, and using a pre-set multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit; Monitoring downstream energy consumption load of the biomass gasification unit under the air distribution ratio and biomass feed rate; When the downstream energy consumption load exceeds a preset downstream energy consumption load fluctuation threshold, automatically triggering a hierarchical emergency response unit of the biomass gasification unit, wherein the hierarchical emergency response unit performs progressive control actions from early warning notification, parameter automatic fine-tuning, control strategy switching to safe shutdown according to the degree of exceeding the threshold.

[0006] Optionally, using the temperature, pressure and output gas component information of the reaction zone as input, the knowledge graph as prior knowledge, and using a pre-set multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit, comprising: extracting high-order features of temperature, pressure and output gas component information of the reaction zone, accessing the knowledge graph with the high-order features as query conditions to output a decision constraint space of the biomass gasification unit, and outputting, by the multi-algorithm fusion analysis engine, the air distribution ratio and the biomass feed rate of the biomass gasification unit based on the high-order features and the decision constraint space.

[0007] Optionally, outputting, by the multi-algorithm fusion analysis engine, the air distribution ratio and the biomass feed rate of the biomass gasification unit based on the high-order features and the decision constraint space includes: outputting, by a classifier layer in the multi-algorithm fusion analysis engine, a working condition classification label of the biomass gasification unit based on the high-order features; analyzing, by a time series analysis layer in the multi-algorithm fusion analysis engine, temperature analysis values and pressure analysis values of the biomass gasification unit according to the temperature and the pressure of the biomass gasification unit; outputting, by a DRL algorithm in the multi-algorithm fusion analysis engine, the air distribution ratio and the biomass feed rate of the biomass gasification unit in combination with the temperature analysis values, the pressure analysis values, the working condition classification label and the decision constraint space.

[0008] Optionally, outputting, by the DRL algorithm in the multi-algorithm fusion analysis engine, the air distribution ratio and the biomass feed rate of the biomass gasification unit in combination with the temperature analysis values, the pressure analysis values, the working condition classification label and the decision constraint space includes: analyzing a perception state vector of the biomass gasification unit in combination with the temperature analysis values, the pressure analysis values, the working condition classification label and the decision constraint space, and outputting, by the DRL algorithm, the air distribution ratio and the biomass feed rate of the biomass gasification unit according to the perception state vector.

[0009] Optionally, outputting, by the DRL algorithm, the air distribution ratio and the biomass feed rate of the biomass gasification unit according to the perception state vector includes: outputting a target action vector of the biomass gasification unit according to the perception state vector, and determining the air distribution ratio and the biomass feed rate of the biomass gasification unit based on the target action vector.

[0010] Optionally, collecting temperature, pressure and output gas component information of a reaction zone corresponding to the biomass gasification unit includes: Define the key temperature measuring points and key pressure measuring points of the corresponding reaction zone of the biomass gasification unit, wherein the key temperature measuring points include the oxidation layer, the reduction layer, the pyrolysis layer and the gasifier outlet, and the key pressure measuring points include the gasifier hearth, the air inlet and the fuel gas outlet pipeline; The temperature of the key temperature measuring points is collected by using an armored thermocouple, the pressure of the key pressure measuring points is collected by using a pressure transmitter, and the fuel gas sampled on the main pipeline before entering the energy utilization equipment is injected into a gas chromatograph to analyze the fuel gas component information of the corresponding fuel gas of the reaction zone.

[0011] Optionally, the knowledge graph of the biomass gasification unit containing the gasification process, equipment correlation and historical failure mode information is constructed, including: Based on the gasification process, equipment correlation and historical failure mode information, the data source of the biomass gasification unit is defined; The core entities of the data source are identified, and the core entity types, inter-entity relationships and entity attributes of the core entities are analyzed, and the core entity types, inter-entity relationships and entity attributes are stored in a graph database in the form of nodes-edges-attributes to obtain an initial knowledge graph of the biomass gasification unit; The initial knowledge graph is subjected to knowledge fusion to obtain the knowledge graph of the biomass gasification unit.

[0012] Optionally, the knowledge graph of the biomass gasification unit is obtained by subjecting the initial knowledge graph to knowledge fusion, including: Identify the same object entity pairs in the initial knowledge graph, and merge the same object entity pairs to obtain a merged entity knowledge graph; Identify the conflict relationships of the merged entity knowledge graph, and according to a preset fusion rule, the conflict relationships are subjected to knowledge fusion to obtain the knowledge graph of the biomass gasification unit.

[0013] Optionally, when the downstream energy utilization load exceeds a preset downstream energy utilization load fluctuation threshold, a hierarchical emergency response unit of the biomass gasification unit is automatically triggered, including: When the downstream energy utilization load exceeds a preset downstream energy utilization load fluctuation threshold, the emergency response level of the biomass gasification unit is determined to automatically trigger the hierarchical emergency response unit of the biomass gasification unit.

[0014] In order to solve the above problems, the application also provides a biomass gasification energy supply system based on intelligent control, which comprises: A reaction zone data acquisition module is configured to acquire the temperature, pressure and output fuel gas component information of the corresponding reaction zone of the biomass gasification unit; a knowledge graph construction module, configured to construct a knowledge graph of the biomass gasification unit, which contains information about gasification process, equipment correlation and historical failure mode; a gasification unit parameter determination module, configured to take the temperature, pressure and output gas component information of the reaction zone as input, and use the knowledge graph as prior knowledge to output the air distribution ratio and biomass feed rate of the biomass gasification unit by using a preset multi-algorithm fusion analysis engine; a downstream energy load analysis module, configured to monitor the downstream energy load of the biomass gasification unit under the air distribution ratio and biomass feed rate; a hierarchical emergency response module, configured to automatically trigger a hierarchical emergency response unit of the biomass gasification unit when the downstream energy load exceeds a preset downstream energy load fluctuation threshold, wherein the hierarchical emergency response unit performs progressive control actions from early warning notification, parameter automatic fine-tuning, control strategy switching to safe shutdown according to the degree of exceeding the threshold.

[0015] Firstly, by constructing a knowledge graph that integrates process, equipment and failure mode, and inputting real-time data and prior knowledge into a multi-algorithm fusion analysis engine, the system can accurately understand complex working conditions and output the optimal air distribution and feed strategy, significantly improving gasification efficiency and gas quality stability. More importantly, this scheme introduces a dynamic monitoring and hierarchical emergency response mechanism for downstream load, enabling the unit to actively adapt to demand fluctuations and realize a smart energy supply mode from production-to-use to use-to-production. The progressive emergency unit can automatically perform precise interventions from early warning, fine-tuning, strategy switching to safe shutdown when load changes dramatically, effectively avoiding operational risks and ensuring equipment and personnel safety. Therefore, the present application can improve the gasification efficiency of biomass gasification energy supply. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 a flowchart of the biomass gasification energy supply method based on intelligent control provided by an embodiment of the present application; Figure 2 a generation diagram of the decision constraint space based on intelligent control provided by an embodiment of the present application; Figure 3 a module diagram of the biomass gasification energy supply method based on intelligent control provided by an embodiment of the present application; Figure 4 a schematic diagram of a computer device for the biomass gasification energy supply method based on intelligent control provided by an embodiment of the present application; The objectives, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0017] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0018] This application provides a biomass gasification energy supply method based on intelligent control. The executing entity of the biomass gasification energy supply method based on intelligent control includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application embodiment: a server, a terminal, etc. In other words, the biomass gasification energy supply method based on intelligent control can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0019] Reference Figure 1 The diagram shown is a schematic flow chart of a biomass gasification energy supply method based on intelligent control according to an embodiment of the present invention. In this embodiment, the biomass gasification energy supply method based on intelligent control includes: S1. Collect information on the temperature, pressure, and composition of the produced gas in the corresponding reaction zone of the biomass gasification unit.

[0020] This invention collects information on temperature, pressure, and the composition of the produced gas in the corresponding reaction zone of the biomass gasification unit to provide high-quality, highly reliable raw data for the intelligent control system.

[0021] Specifically, the collection of temperature, pressure, and produced gas composition information in the corresponding reaction zone of the biomass gasification unit includes: Define the key temperature measurement points and key pressure measurement points in the corresponding reaction zone of the biomass gasification unit. The key temperature measurement points include the oxidation layer, reduction layer, pyrolysis layer and gasifier outlet. The key pressure measurement points include the gasifier furnace, air inlet and gas outlet pipeline. The temperature of the key temperature measurement points was collected using armored thermocouples. Use a pressure transmitter to collect pressure data at key pressure measurement points; The gas sampled from the main pipeline before entering the energy-consuming equipment is injected into a gas chromatograph to analyze the gas composition information of the gas corresponding to the reaction zone.

[0022] The biomass gasification unit refers to an industrial complete equipment for converting solid biomass raw materials into combustible gas, the reaction zone refers to the space region sum of a series of complex thermochemical reactions of biomass raw materials under high temperature and oxygen deficiency conditions inside the gasification furnace body, the oxidation layer refers to the region where air introduced through the air inlet reacts violently with hot carbon, the reduction layer refers to the region above the oxidation layer, which uses the heat and high-temperature gas generated by the oxidation layer to make carbon react with carbon dioxide, water vapor and the like, the pyrolysis layer refers to the region above the reduction layer, where biomass raw materials are cracked under the condition of air isolation or a small amount of air, the gasification furnace outlet refers to the flange interface connecting the gasification furnace body and the downstream fuel gas purification system, the gasification furnace hearth refers to the closed space surrounded by the inner wall of the gasification furnace and containing the entire reaction zone, the air inlet refers to the channel on the gasification furnace for introducing the gasification agent, the fuel gas outlet pipeline refers to the pipeline system connecting the gasification furnace outlet and the downstream purification system and finally leading to the energy utilization equipment, the temperature refers to the thermodynamic temperature measured at key points in the reaction zone by armored thermocouples, the armored thermocouple refers to a solid and bendable temperature measuring sensor made by combining a thermocouple wire, an insulating material and a metal protective sleeve, the pressure transmitter refers to an instrument for converting pressure physical quantities into standard electrical signals, the pressure refers to the static pressure of the fluid in the gasification system, the energy utilization equipment refers to terminal equipment for energy conversion using purified biomass fuel gas, such as fuel gas boilers, industrial furnaces, fuel gas internal combustion engines, gas turbines and the like, the fuel gas refers to combustible mixed gas generated by biomass raw materials through gasification reaction, the gas chromatograph refers to a precision analytical instrument for separating and analyzing components and their contents in complex mixtures, and the fuel gas component information refers to the volume or molar concentration data of various chemical components in the fuel gas measured by analytical instruments such as gas chromatographs.

[0023] S2, constructing a knowledge graph of the biomass gasification unit containing gasification process, equipment correlation and historical failure mode information.

[0024] The biomass gasification unit constructed by the present application contains gasification process, equipment correlation and historical failure mode information, which can construct a knowledge graph customized for biomass gasification unit and dynamically evolving.

[0025] In detail, the construction of the knowledge graph of the biomass gasification unit containing gasification process, equipment correlation and historical failure mode information comprises: Based on the gasification process, equipment correlation and historical failure mode information, the data source of the biomass gasification unit is defined; identifying core entities of the data source, and analyzing core entity types, inter-entity relationships and entity attributes of the core entities, and storing the core entity types, inter-entity relationships and entity attributes in a graph database in the form of node-edge-attribute to obtain an initial knowledge graph of the biomass gasification unit; performing knowledge fusion on the initial knowledge graph to obtain the knowledge graph of the biomass gasification unit.

[0026] The data source refers to a source set of original information required for constructing a knowledge graph, including structured data sources such as a historical operation database of a SCADA / DCS system, a device management database, and a maintenance work order system; semi-structured data sources such as a device operation manual, a process design document, a standard operation procedure, and a fault analysis report; and unstructured data sources such as experience notes of field experts, technical exchange recordings, and related academic papers and patent documents. The core entity refers to a key matter with independent meaning that is identified from the data source and constitutes a basic unit of the knowledge graph, for example, a gasifier, a temperature sensor, a slagging fault, and a feeding rate. The core entity type refers to classification of core entities with common characteristics. For example, gasifiers, fans, and valves are classified as equipment, temperatures and pressures are classified as parameters, and slagging and bridging are classified as faults. The inter-entity relationship refers to semantic connections between different core entities. The entity attribute refers to key-value pair information for describing the characteristics and state of a single core entity. The node-edge-attribute refers to a basic data model for storing and expressing knowledge in a graph database, where a node represents a core entity, an edge represents an inter-entity relationship connecting two nodes, and an attribute is an entity attribute stored in the form of a key-value pair on a node or an edge. The graph database refers to a native graph computing database for storing, managing, and querying node-edge-attribute structure data. The initial knowledge graph refers to a first version of the knowledge graph obtained by directly storing the extracted core entities, inter-entity relationships and entity attributes in the data source in the form of node-edge-attribute in the graph database without deep cleaning and integration. The knowledge graph refers to a high-quality, consistent, and structured semantic knowledge network formed by performing knowledge fusion on the initial knowledge graph.

[0027] Further, the knowledge fusion on the initial knowledge graph to obtain the knowledge graph of the biomass gasification unit comprises: identifying same-object entity pairs in the initial knowledge graph, and merging the same-object entity pairs to obtain a merged entity knowledge graph; identifying conflict relationships of the merged entity knowledge graph, performing knowledge fusion on the conflict relationships according to a preset fusion rule, and obtaining the knowledge graph of the biomass gasification unit.

[0028] The object entity pair refers to two or more different entity nodes of the same object in the real world, for example, one node is named reaction zone thermometer, and the other node is numbered T-101, if they describe the same physical sensor, the two nodes constitute an object entity pair, the merged entity knowledge graph refers to an intermediate product obtained by performing a merging operation on all identified object entity pairs in the initial knowledge graph, the conflict relationship refers to a plurality of relationship edges in the same pair of entities in the merged entity knowledge graph, which are contradictory to each other in type, attribute or confidence, for example, type conflict, attribute conflict, logic conflict and the like, the fusion rule refers to a set of predetermined judgment criteria, priority and processing logic for solving the conflict relationship, and the fusion rule can be based on data source priority, data timeliness, information confidence and the like.

[0029] S3, taking the temperature, pressure and output gas component information of the reaction zone as input, the knowledge graph as prior knowledge, and using a preset multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit.

[0030] The present application takes the temperature, pressure and output gas component information of the reaction zone as input, the knowledge graph as prior knowledge, and uses a preset multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit, which can accurately analyze and realize closed-loop intelligent control of the gasification process, so as to achieve the core functions of improving energy efficiency, ensuring safety and stable gas production.

[0031] In detail, the taking the temperature, pressure and output gas component information of the reaction zone as input, the knowledge graph as prior knowledge, and using a preset multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit includes: extracting high-order features of the temperature, pressure and output gas component information of the reaction zone; using the high-order features as a query condition, accessing the knowledge graph to output the decision constraint space of the biomass gasification unit; based on the high-order features and the decision constraint space, using the multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit.

[0032] The high-order feature refers to an index derived from the temperature, pressure of the reaction zone and the component information of the output gas, which can more deeply reflect the internal state and performance of the gasification process, such as gas component ratio, carbon conversion rate, gasification efficiency and the like, the query condition refers to the structured request information used when accessing the knowledge graph, the decision constraint space refers to the dynamic safety boundary set for a control decision cycle returned by the knowledge graph, the multi-algorithm fusion analysis engine refers to a software module integrated with multiple artificial intelligence algorithms, the air distribution ratio refers to the coupling control quantity between the gasification agent flow rate sent into the gasifier and the biomass feed rate, and the biomass feed rate refers to the mass flow rate of the biomass fuel delivered to the gasifier per unit time.

[0033] Referring to Figure 2 As shown in the figure, the generation schematic diagram of the decision constraint space based on intelligent control provided by an embodiment of the present application is shown: the safety operation boundary refers to the absolute red line set to ensure the safe and continuous operation of the system, such as the lower limit of the ignition critical value of the air-coal ratio, the upper limit of the furnace pressure fluctuation range, etc., the energy efficiency optimization interval refers to the best operation range determined within the safety boundary to achieve higher operation efficiency, such as the target heat value range of the synthesis gas, the equipment operation limit refers to the hard limit specified by the mechanical, electrical and material performance of the specific equipment in the system, such as the maximum rotation speed of the feeding screw, the maximum output torque of the fan, etc., and the environmental protection emission red line refers to the emission concentration control limit value that must be complied with.

[0034] Further, based on the high-order feature and the decision constraint space, the air distribution ratio and the biomass feed rate of the biomass gasification unit are output by the multi-algorithm fusion analysis engine, which includes: Based on the high-order feature, the working condition classification label of the biomass gasification unit is output by the classifier layer in the multi-algorithm fusion analysis engine; According to the temperature and pressure of the biomass gasification unit, the temperature analysis value and the pressure analysis value of the biomass gasification unit are analyzed by the time series analysis layer in the multi-algorithm fusion analysis engine; Combined with the temperature analysis value, the pressure analysis value, the working condition classification label and the decision constraint space, the air distribution ratio and the biomass feed rate of the biomass gasification unit are output by the DRL algorithm in the multi-algorithm fusion analysis engine.

[0035] The classifier layer refers to the algorithm component in the multi-algorithm fusion analysis engine responsible for identifying and classifying operating conditions. The operating condition classification label refers to the qualitative semantic description of the current operating status of the biomass gasification unit output by the classifier layer. For example, the operating condition classification label can be labels such as optimal, good, sub-healthy (requiring attention), risky (requiring intervention), or faulty (tar risk). The time series analysis layer refers to the algorithm component in the multi-algorithm fusion analysis engine specifically responsible for processing time series data and mining its dynamic patterns. It can be processed by LSTM, GRU, etc. The temperature analysis value refers to the in-depth interpretation information about temperature output by the time series analysis layer. The pressure analysis value refers to the in-depth interpretation information about pressure output by the time series analysis layer. The DRL algorithm refers to the deep reinforcement learning algorithm, which learns the optimal control strategy through continuous interaction with the gasification system.

[0036] Furthermore, the step of combining the temperature analysis value, the pressure analysis value, the operating condition classification label, and the decision constraint space, and using the DRL algorithm in the multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit includes: By combining the temperature analysis value, the pressure analysis value, the operating condition classification label, and the decision constraint space, the sensing state vector of the biomass gasification unit is analyzed. Based on the perceived state vector, the air distribution ratio and biomass feed rate of the biomass gasification unit are output using the DRL algorithm.

[0037] Furthermore, as another embodiment of the present invention, the sensing state vector is calculated using the following formula:

[0038] in, This represents the sensing state vector of the biomass gasification unit. This represents a time-series analysis vector containing temperature and pressure analysis values. The layer normalization function is represented. Represents time-series dynamic weights. Indicates the operating condition classification label, Indicates the embedding layer function. Indicates the weight of the operating mode. Represents the decision constraint space. This represents the constraint encoding function. This represents the safety boundary weight.

[0039] The perceived state vector refers to a highly integrated, digitized state representation vector, serving as the sole environmental observation input to the DRL algorithm. The temporal analysis vector refers to the deep feature vector resulting from the processing of raw sensor data through an upstream temporal analysis layer. The layer normalization function refers to a data standardization technique that transforms... All features within the vector are transformed to have a mean of 0 and a variance of 1. The temporal dynamic weights quantify the importance of temporal dynamic information in the current decision. The embedding layer function encodes sparse, high-dimensional one-hot data. The mapping is a low-dimensional, continuous, and dense feature vector. The operating mode weight refers to the quantification of the importance of working condition classification information in the current decision. The constraint encoding function refers to the function that encodes the symbolic constraints in the knowledge graph into numerical feature vectors. The safety boundary weight refers to the quantification of the importance of safety constraint information in the current decision.

[0040] Furthermore, the step of outputting the air distribution ratio and biomass feed rate of the biomass gasification unit using the DRL algorithm based on the perceived state vector includes: Based on the perceived state vector, the target action vector of the biomass gasification unit is output using the DRL algorithm; Based on the target motion vector, the air distribution ratio and biomass feed rate of the biomass gasification unit are determined.

[0041] Furthermore, as another embodiment of the present invention, the DRL algorithm is as follows:

[0042] in, This represents the sensing state vector of the biomass gasification unit. This represents a time-series analysis vector containing temperature and pressure analysis values. The layer normalization function is represented. Represents time-series dynamic weights. Indicates the operating condition classification label, Indicates the embedding layer function. Indicates the weight of the operating mode. Represents the decision constraint space. This represents the constraint encoding function. This represents the safety boundary weight.

[0043] Wherein, the target action vector refers to the vector at the current moment. The calculated action command to be executed. It is a specific numerical vector, such as [air distribution ratio = 1.2, feed rate = 0.8]. The action vector refers to an ordered set containing the values ​​of all key control variables of the biomass gasification unit at a given moment, and can refer to any set of feasible control commands. For example, [air distribution ratio = 1.1, feed rate = 0.9], the depth... A network refers to a deep neural network used to approximate the value function of an action.

[0044] S4. Monitor the downstream energy load of the biomass gasification unit under the specified air distribution ratio and biomass feed rate.

[0045] This invention monitors the downstream energy load of the biomass gasification unit under the specified air distribution ratio and biomass feed rate to achieve feedforward control, thereby improving the system's response speed. The downstream energy load refers to the immediate demand for the gas produced by the biomass gasification unit.

[0046] S5. When the downstream energy load exceeds the preset downstream energy load fluctuation threshold, the graded emergency response unit of the biomass gasification unit is automatically triggered. The graded emergency response unit performs progressive control actions from early warning notification, automatic parameter fine-tuning, control strategy switching to safe shutdown, depending on the degree of exceeding the threshold.

[0047] When the downstream energy load exceeds a preset downstream energy load fluctuation threshold, the present invention automatically triggers the graded emergency response unit of the biomass gasification unit, achieving a perfect combination of intelligence and robustness.

[0048] Specifically, the step of automatically triggering the graded emergency response unit of the biomass gasification unit when the downstream energy load exceeds a preset downstream energy load fluctuation threshold includes: When the downstream energy load exceeds the preset downstream energy load fluctuation threshold, the emergency response level of the biomass gasification unit is determined so as to automatically trigger the graded emergency response unit of the biomass gasification unit.

[0049] The downstream energy load fluctuation threshold element refers to the threshold used to determine whether the change in downstream energy load exceeds the normal controllable range, thus requiring the activation of emergency procedures. The emergency response level element refers to the different levels of response strategies classified according to the severity of the downstream energy load fluctuation exceeding the threshold. The graded emergency response unit refers to an automated control system module composed of both software and hardware.

[0050] The tiered emergency response unit includes a primary response unit and a secondary response unit. The primary response unit is configured to trigger when the downstream energy load exceeds a primary fluctuation threshold, and the secondary response unit is configured to trigger when the downstream energy load exceeds a secondary fluctuation threshold higher than the primary fluctuation threshold. The steps for triggering the primary response unit include: adjusting the reward function of the DRL algorithm to increase the weight of load tracking speed; and / or, within safe operating limits, relaxing the restrictions on the air distribution ratio and biomass feed rate adjustment rate. The steps for triggering the secondary response unit include: executing all emergency control strategies of the primary response unit; and automatically starting or adjusting the auxiliary energy supply system connected to the biomass gasification unit to share the load pressure of the main system.

[0051] First, by constructing a knowledge graph integrating processes, equipment, and failure modes, and inputting real-time data and prior knowledge into a multi-algorithm fusion analysis engine, the system can accurately understand complex operating conditions and output optimal air distribution and feed strategies, significantly improving gasification efficiency and gas quality stability. More importantly, this solution introduces a dynamic monitoring and tiered emergency response mechanism for downstream loads, enabling the unit to proactively adapt to demand fluctuations and achieve a smart energy supply mode that shifts from production-driven consumption to consumption-driven production. This progressive emergency unit can automatically execute precise interventions—from early warning and fine-tuning to strategy switching and even safe shutdown—when loads change drastically, effectively mitigating operational risks and ensuring equipment and personnel safety. Therefore, this invention can improve the gasification efficiency of biomass gasification for energy supply.

[0052] like Figure 3 The diagram shown is a functional block diagram of the biomass gasification energy supply system based on intelligent control according to the present invention.

[0053] The intelligent control-based biomass gasification energy supply system 300 described in this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent control-based biomass gasification energy supply system may include a reaction zone data acquisition module 301, a knowledge graph construction module 302, a gasification unit parameter determination module 303, a downstream energy load analysis module 304, and a tiered emergency response module 305. The module described in this invention can also be called a unit, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0054] In this embodiment of the invention, the functions of each module / unit are as follows: The reaction zone data acquisition module 301 is used to collect information on the temperature, pressure, and composition of the produced gas in the corresponding reaction zone of the biomass gasification unit. The knowledge graph construction module 302 is used to construct a knowledge graph of the biomass gasification unit that includes gasification process, equipment correlation and historical fault mode information; The gasification unit parameter determination module 303 is used to take the temperature, pressure and gas composition information of the reaction zone as input, the knowledge graph as prior knowledge, and use a pre-set multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit. The downstream energy load analysis module 304 is used to monitor the downstream energy load of the biomass gasification unit under the air distribution ratio and biomass feed rate. The graded emergency response module 305 is used to automatically trigger the graded emergency response unit of the biomass gasification unit when the downstream energy load exceeds a preset downstream energy load fluctuation threshold. The graded emergency response unit performs progressive control actions from early warning notification, automatic parameter fine-tuning, control strategy switching to safe shutdown, depending on the degree of exceeding the threshold.

[0055] In detail, the modules in the intelligent control-based biomass gasification energy supply system 300 described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method uses the same technology as the intelligent control-based biomass gasification energy supply method described in the article and can produce the same technical effect, so it will not be repeated here.

[0056] In one embodiment, a computer device is provided, which may be a server or a client, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used for communication with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a biomass gasification energy supply method based on intelligent control on the server or client side.

[0057] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the following steps: Collect information on temperature, pressure, and composition of the produced gas in the corresponding reaction zone of the biomass gasification unit; Construct a knowledge graph for the biomass gasification unit that includes information on gasification processes, equipment correlations, and historical failure modes; Using the temperature, pressure, and gas composition information of the reaction zone as input, and the knowledge graph as prior knowledge, the pre-set multi-algorithm fusion analysis engine outputs the air distribution ratio and biomass feed rate of the biomass gasification unit. Monitor the downstream energy load of the biomass gasification unit under the specified air distribution ratio and biomass feed rate; When the downstream energy load exceeds the preset downstream energy load fluctuation threshold, the graded emergency response unit of the biomass gasification unit is automatically triggered. The graded emergency response unit performs progressive control actions, from early warning notification, automatic parameter fine-tuning, control strategy switching to safe shutdown, according to the degree of exceeding the threshold.

[0058] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor: Collect information on temperature, pressure, and composition of the produced gas in the corresponding reaction zone of the biomass gasification unit; Construct a knowledge graph for the biomass gasification unit that includes information on gasification processes, equipment correlations, and historical failure modes; Using the temperature, pressure, and gas composition information of the reaction zone as input, and the knowledge graph as prior knowledge, the pre-set multi-algorithm fusion analysis engine outputs the air distribution ratio and biomass feed rate of the biomass gasification unit. Monitor the downstream energy load of the biomass gasification unit under the specified air distribution ratio and biomass feed rate; When the downstream energy load exceeds the preset downstream energy load fluctuation threshold, the graded emergency response unit of the biomass gasification unit is automatically triggered. The graded emergency response unit performs progressive control actions, from early warning notification, automatic parameter fine-tuning, control strategy switching to safe shutdown, according to the degree of exceeding the threshold.

[0059] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0060] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0061] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0062] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0063] Finally, it should be noted that in the above embodiments, each embodiment can be combined with each other or independent. Deleting any one of them will not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for biomass gasification energy supply based on intelligent control, characterized in that, The method comprises: Collecting temperature, pressure and output gas component information of the corresponding reaction zone of the biomass gasification unit; Constructing a knowledge graph of the biomass gasification unit containing gasification process, equipment correlation and historical failure mode information; Taking the temperature, pressure and output gas component information of the reaction zone as input and the knowledge graph as prior knowledge, using a pre-set multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit; Monitoring the downstream energy load of the biomass gasification unit under the air distribution ratio and biomass feed rate; When the downstream energy load exceeds the preset downstream energy load fluctuation threshold, automatically triggering the hierarchical emergency response unit of the biomass gasification unit, wherein the hierarchical emergency response unit performs progressive control actions from early warning notification, parameter automatic fine-tuning, control strategy switching to safe shutdown according to the degree of exceeding the threshold.

2. The method of claim 1, wherein the biomass gasification is controlled by the smart control system. Taking the temperature, pressure and output gas component information of the reaction zone as input and the knowledge graph as prior knowledge, using a pre-set multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit, comprising: Extracting high-order features of the temperature, pressure and output gas component information of the reaction zone, taking the high-order features as query conditions, accessing the knowledge graph to output the decision constraint space of the biomass gasification unit, and using the multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit based on the high-order features and the decision constraint space.

3. The method of claim 2, wherein the biomass gasification is controlled by the smart control system. Based on the high-order features and the decision constraint space, using the multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit, comprising: Based on the high-order features, using the classifier layer in the multi-algorithm fusion analysis engine to output the working condition classification label of the biomass gasification unit; According to the temperature and pressure of the biomass gasification unit, using the time series analysis layer in the multi-algorithm fusion analysis engine to analyze the temperature analysis value and pressure analysis value of the biomass gasification unit; Combining the temperature analysis value, the pressure analysis value, the working condition classification label and the decision constraint space, using the DRL algorithm in the multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit.

4. The method of claim 3, wherein the biomass gasification is controlled by the smart control system. Combining the temperature analysis value, the pressure analysis value, the working condition classification label and the decision constraint space, using the DRL algorithm in the multi-algorithm fusion analysis engine to output the air distribution ratio and biomass feed rate of the biomass gasification unit, comprising: Combining the temperature analysis value, the pressure analysis value, the working condition classification label and the decision constraint space, analyzing the perception state vector of the biomass gasification unit, and using the DRL algorithm to output the air distribution ratio and biomass feed rate of the biomass gasification unit according to the perception state vector.

5. The method of claim 3, wherein the biomass gasification is performed by a gasifier. According to the perception state vector, using the DRL algorithm to output the air distribution ratio and biomass feed rate of the biomass gasification unit, comprising: Output a target action vector of the biomass gasification unit according to the perception state vector, and determine a proportion of air distribution and a biomass feeding rate of the biomass gasification unit based on the target action vector.

6. The method of claim 5, wherein the biomass gasification is controlled by the smart control system. Collecting temperature, pressure and gas component information of the reaction zone of the biomass gasification unit, including: Defining key temperature measuring points and key pressure measuring points of the reaction zone of the biomass gasification unit, wherein the key temperature measuring points include an oxidation layer, a reduction layer, a pyrolysis layer and an outlet of the gasifier, and the key pressure measuring points include a hearth of the gasifier, an air inlet and a gas outlet pipeline; Collecting temperature of the key temperature measuring points by using armored thermocouples and collecting pressure of the key pressure measuring points by using pressure transmitters, and injecting sampled gas on the main pipeline before entering the energy utilization equipment into a gas chromatograph to analyze gas component information of the gas corresponding to the reaction zone.

7. The method of claim 1, wherein the biomass gasification is controlled by the smart control system. Constructing a knowledge graph of the biomass gasification unit including gasification process, equipment correlation and historical failure mode information, including: Defining data sources of the biomass gasification unit based on the gasification process, equipment correlation and historical failure mode information; Identifying core entities of the data sources, analyzing core entity types, inter-entity relationships and entity attributes of the core entities, and storing the core entity types, inter-entity relationships and entity attributes in the form of node-edge-attribute into a graph database to obtain an initial knowledge graph of the biomass gasification unit; Performing knowledge fusion on the initial knowledge graph to obtain the knowledge graph of the biomass gasification unit.

8. The method of claim 1, wherein the biomass gasification is controlled by the smart control system. Performing knowledge fusion on the initial knowledge graph to obtain the knowledge graph of the biomass gasification unit, including: Identifying same-object entity pairs in the initial knowledge graph, merging the same-object entity pairs to obtain a merged entity knowledge graph; Identifying conflict relationships of the merged entity knowledge graph, performing knowledge fusion on the conflict relationships according to a preset fusion rule to obtain the knowledge graph of the biomass gasification unit.

9. The smart control based biomass gasification power generation method as claimed in claim 1 wherein, When the downstream energy load exceeds a preset downstream energy load fluctuation threshold, automatically triggering a hierarchical emergency response unit of the biomass gasification unit, including: When the downstream energy load exceeds a preset downstream energy load fluctuation threshold, determining an emergency response level of the biomass gasification unit to automatically trigger the hierarchical emergency response unit of the biomass gasification unit.

10. A biomass gasification energy supply system based on intelligent control, characterized in that, The system includes: A reaction zone data collection module for collecting temperature, pressure and gas component information of a reaction zone of a biomass gasification unit; A knowledge graph construction module for constructing a knowledge graph of the biomass gasification unit including gasification process, equipment correlation and historical failure mode information; A gasification unit parameter determination module for taking the temperature, pressure and gas component information of the reaction zone as input, taking the knowledge graph as prior knowledge, and outputting a proportion of air distribution and a biomass feeding rate of the biomass gasification unit by using a preset multi-algorithm fusion analysis engine; A downstream energy load analysis module for monitoring a downstream energy load of the biomass gasification unit under the proportion of air distribution and the biomass feeding rate; The hierarchical emergency response module is configured to automatically trigger the hierarchical emergency response unit of the biomass gasification unit when the downstream energy load exceeds a preset downstream energy load fluctuation threshold, wherein the hierarchical emergency response unit performs progressive control actions from early warning notification, automatic fine-tuning of parameters, switching of control strategies to safe shutdown according to the degree of exceeding the threshold.

Images