A garbage incineration intelligent charging matching method based on multi-source data fusion

Abstract

The application discloses a garbage incineration intelligent feeding method based on multi-source data fusion, and relates to the technical field of intelligent control of garbage incineration power generation, which comprises the following steps: S1, source data acquisition; S2, garbage pool state modeling; S3, calculation of incinerator load demand; S4, intelligent matching calculation; S5, garbage crane task assignment and execution; and S6, closed-loop feedback optimization. Through integration of vehicle scheduling, garbage fermentation, material level monitoring and incinerator working condition data, the application constructs an intelligent matching method, automatically generates optimal operation instructions of a garbage crane, realizes precise, stable and efficient intelligent feeding, and solves many defects of a traditional manual feeding mode.

Description

Technical Field

[0001] This application relates to the technical field of intelligent control of waste incineration power generation, and in particular to a smart furnace feeding and matching method for waste incineration based on multi-source data fusion. Background Technology

[0002] Currently, the complex composition and large fluctuations in calorific value of municipal solid waste pose a core challenge to the stable and efficient operation of waste incineration plants. Traditional waste-to-incineration methods rely on operator experience, involving manual judgment of waste type, visual estimation of waste level and fermentation level in the waste pit, and manual operation of the waste grab bucket for mixing and feeding. This method has the following drawbacks: (1) Data silos: The garbage source, type, weight, and unloading gate information of the vehicle dispatching system are isolated from the garbage pool material level, fermentation time, and incinerator load data, which makes it impossible to form a collaborative decision-making process, resulting in a lack of comprehensive data support for the feeding scheme; (2) Coarse mixing: The mixing ratio has no quantitative basis, which can easily lead to the calorific value of the waste entering the furnace fluctuating, causing problems such as furnace temperature fluctuation, unstable steam parameters, and excessive pollutant emissions, which affect the long-term stable operation of the incinerator. (3) Control lag: slow manual response and low operation accuracy make it difficult to match the real-time changes in the incinerator's operating conditions, resulting in low combustion efficiency, high plant energy consumption, and increased equipment wear and tear, thus increasing operating costs; (4) Standardization gap: Over-reliance on personal experience, large differences in operation during shift handover, difficulty in achieving stable and replicable optimal operating conditions, which is not conducive to the standardized management of incineration plants.

[0003] While some existing intelligent control systems for waste incineration involve feeding control, they generally lack multi-source fusion and dynamic matching modeling of vehicle source data, waste fermentation time, and three-dimensional material level in the waste pool. This fails to achieve intelligent closed-loop control of the entire chain from waste entering the plant to incineration, and cannot fundamentally solve the aforementioned technical problems. Summary of the Invention

[0004] The purpose of this application is to provide a smart incineration matching method for waste incineration based on multi-source data fusion, in order to solve the problem that the existing technology lacks multi-source fusion and dynamic matching modeling of vehicle source data, waste fermentation time, and three-dimensional material level in the waste pool, and fails to achieve full-link smart closed-loop control from waste entering the plant to incineration, thus failing to fundamentally solve the above-mentioned technical problems.

[0005] The intelligent incineration furnace matching method based on multi-source data fusion provided in this application adopts the following technical solution: A smart incineration furnace matching method based on multi-source data fusion includes the following steps: S1. Source data collection: After the garbage transport vehicle enters the unloading platform, the vehicle dispatch terminal automatically identifies the vehicle information and uploads various types of garbage data to the data transmission and storage layer in real time. After the data is uploaded, it is stored in the real-time database and the storage area of ​​the batch of garbage is marked. S2. Garbage pool status modeling: 1) The garbage pool is divided into zones according to the storage area. Each zone independently records the garbage fermentation start time Ts. The system calculates the fermentation time Δt = current time - Ts in real time for each zone. 2) The waste pool is then scanned from all angles using LiDAR to generate a three-dimensional material level map, marking the waste level height H and available waste quantity M in each zone; at the same time, a high-definition industrial camera is deployed at the inlet of the incinerator to monitor the material level in real time through camera imaging technology, capture the accumulation height and distribution of the waste entering the furnace, and synchronously feed the material level data into the intelligent decision core layer to correct the feeding parameters. 3) Finally, combining the fermentation temperature (Tg) collected by the infrared thermometer and the CH4 concentration (C) collected by the gas sensor, a fermentation quality scoring function was established to quantify the degree of fermentation of waste in each zone. ; S3. Incinerator load demand calculation: Receives main steam flow, furnace temperature, and flue gas oxygen content data uploaded by the incinerator operating condition module through the task planning unit in the intelligent decision core layer. S4. Intelligent Mixing Calculation: Using an intelligent mixing model, the optimal mixing ratio of waste in each zone is determined under the constraints of stable calorific value, complete combustion, and compliance with emission standards. S5. Garbage crane task issuance and execution: 1) The mixing scheme output by the intelligent matching model is converted into control instructions that the garbage crane can execute through the task planning unit, including material grabbing coordinates, material grabbing sequence, mixing times, and material feeding points; 2) After receiving control commands, the garbage crane execution module automatically executes the operation process without any manual intervention. 3) After feeding is completed, the system updates the material level height H, available waste Mi, and cumulative feeding amount of each zone of the waste pool in real time. Then, it collects the furnace feeding level data in real time through a high-definition industrial camera, verifies the feeding effect in a synchronous manner, and stores the feeding data, waste pool material level data, and furnace feeding level data together into the real-time database and the historical database. S6. Closed-loop feedback optimization: 1) The furnace temperature, steam parameters, and pollutant emission data uploaded by the incinerator operating condition module are collected in real time through the closed-loop optimization unit, and the waste pool material level data collected by the lidar and the furnace feed material level data collected by the high-definition industrial camera are compared with the target value set by the system. 2) System self-learning: The system automatically stores the compatibility cases that meet the requirements of stable calorific value, complete combustion and emission standards into the knowledge base. The intelligent compatibility model is iterated and optimized once a day at midnight to continuously improve the compatibility accuracy and system adaptability.

[0006] Furthermore, in step S1, the various types of garbage data are as follows: 1) Waste type K = {k1, k2, ..., kn}, where k1 is kitchen waste, k2 is combustible waste, k3 is ash and soil waste, etc.; 2) The weight of each type of waste is W = {w1, w2, ..., wn}; 3) Corresponding unloading gate number D, where D1-D8 are set according to the number of unloading gates in the waste pool; 4) Unloading time T0.

[0007] Further, in step S2, the usable waste quantity M is calculated based on the material level height H and the partition area, i.e., M = H × partition area × waste bulk density; wherein, the waste bulk density is 1.2 t / m³. 3 It can be adjusted according to the actual type of waste.

[0008] Further, in step S2, the formula for calculating the degree of fermentation is: , Where: a, b, and c are weighting coefficients: a=0.4, b=0.3, c=0.3, and F ranges from 0 to 1.

[0009] Further, in step S3, the required total calorific value of the waste to be fed into the incinerator, Qreq, and the feeding rate, Vreq, are calculated using the following formulas: Where P is the main steam power and η is the incinerator thermal efficiency; Qavg is the average estimated calorific value of the waste fed into the furnace.

[0010] Furthermore, in step S4, the specific process of solving for the optimal mixing ratio of waste in each zone is as follows: 1) Input parameters: waste type Ki, estimated calorific value Qi, fermentation score Fi, and usable waste quantity Mi for each zone; 2) Objective function: Xi is the proportion of waste fed into the i-th zone; the basic calorific value is preset according to the type of waste and corrected by the fermentation score F, Qi = basic calorific value × F; the goal is to minimize the deviation between the total calorific value of the mixed waste and the total calorific value Qreq required by the incinerator; 3) Constraints: ① ; ②Xi≥0; ③Xi·Mi≤maximum catchable amount in the region; ④Furnace temperature maintained at 850-1050℃; 4) Output results: Optimal mixing scheme X={x1,x2,...,xn}, single feeding amount G, feeding interval ΔT.

[0011] Furthermore, in step S5, the operation process of the garbage crane execution module is as follows: the garbage crane travels to the designated grabbing position, then the grab bucket descends to grab the designated weight of garbage, the weighing sensor confirms the weight of the grabbed material, then the garbage crane moves to the mixing area to mix the material, then moves to the designated feeding point, the grab bucket unloads the material to complete the feeding, and finally returns to the initial position to wait.

[0012] Furthermore, in step S6, if the deviation between the actual parameters and the set target value exceeds the threshold, the closed-loop optimization unit immediately triggers the intelligent matching model to recalculate the matching scheme, correct the mixing ratio, single feeding amount and feeding interval, and ensure that the incineration conditions return to the optimal range.

[0013] Compared with the prior art, the beneficial effects of this application are as follows: This application integrates data from vehicle scheduling, waste fermentation, material level monitoring, and incinerator operating conditions to construct an intelligent matching method, automatically generating optimal operation instructions for the waste crane, thereby achieving precise, stable, and efficient intelligent incineration and solving many shortcomings of the traditional manual incineration mode.

[0014] Specifically, it has the function of deep integration of multi-source data: breaking down the data barriers between the vehicle dispatching system, the waste pool monitoring system, and the incinerator control system, realizing information sharing of the entire chain from waste entering the plant to being put into the furnace, solving the problem of data silos in the traditional model, and providing comprehensive data support for precise matching.

[0015] Meanwhile, the mixing accuracy is high: the mixing ratio is quantified through the AI ​​intelligent mixing model, the fluctuation of the calorific value of the waste entering the furnace is controlled within ±5%, and the furnace temperature is stabilized within the optimal combustion range of 850-1050℃, effectively avoiding the roughness and subjectivity of manual mixing.

[0016] In addition, it operates efficiently and stably: the automatic operation rate of the garbage crane is ≥98%, eliminating the need for manual operation and significantly reducing the labor intensity of operators; and the stability of the main steam is improved by more than 35%, and the combustion efficiency of the incinerator is improved by 8-15%, ensuring the long-term stable operation of the incineration plant.

[0017] In addition, the energy conservation and emission reduction effects are significant: through precise matching and closed-loop optimization, the power consumption rate of the incinerator plant has decreased by 5-9%, the consumption of environmental protection consumables (desulfurizing agent and denitrification agent) has decreased by 14-20%, and the pollutant emissions have been stably up to standard, meeting the requirements of national environmental protection policies.

[0018] Secondly, it has an intelligent closed-loop self-optimization function: realizing full-link closed-loop control of "collection-decision-execution-feedback-optimization". The system can optimize the matching model through self-learning and iteration, get rid of the dependence on human experience, adapt to different types and batches of garbage, and has strong versatility and adaptability. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the intelligent incineration furnace matching method for waste incineration based on multi-source data fusion, as described in this application embodiment. Detailed Implementation

[0020] The following is in conjunction with the appendix Figure 1 This application will be described in further detail.

[0021] This application discloses a smart incineration furnace matching method based on multi-source data fusion, referring to... Figure 1 In this embodiment, the intelligent incineration furnace matching method for waste incineration includes the following steps: S1. Source Data Collection: After the garbage trucks enter the unloading platform, the vehicle dispatch terminal automatically identifies the vehicle information and uploads various types of garbage data to the data transmission and storage layer in real time. After the data is uploaded, it is stored in the real-time database, and the storage area of ​​the batch of garbage is marked.

[0022] Specifically, in step S1, the various types of garbage data are as follows: 1) Waste type K = {k1, k2, ..., kn}, where k1 is kitchen waste, k2 is combustible waste, k3 is ash and soil waste, etc.; 2) The weight of each type of waste is W = {w1, w2, ..., wn}; 3) The corresponding unloading gate number D, where D1-D8 are set according to the number of unloading gates in the waste pool; and the storage area corresponds to the unloading gate number.

[0023] 4) Unloading time T0.

[0024] S2. Garbage pool status modeling: 1) The garbage pool is divided into 8 storage zones according to the unloading gate number, namely D1-D8; each zone independently records the garbage fermentation start time Ts, that is, the first unloading time of the zone. The system calculates the fermentation time of garbage in each zone in real time Δt = current time - Ts.

[0025] The waste pit is then scanned from all angles using a lidar sensor to generate a three-dimensional material level map, marking the waste level height H and the available waste quantity M for each zone. Specifically, in step S2, the available waste quantity M is calculated based on the material level height H and the zone area, i.e., M = H × zone area × waste bulk density; where the waste bulk density is 1.2 t / m³.3 It can be adjusted according to the actual type of waste.

[0026] Meanwhile, a high-definition industrial camera is deployed at the inlet of the incinerator. The camera imaging technology monitors the material level in the furnace in real time, captures the accumulation height and distribution of the waste entering the furnace, and synchronously feeds the material level data back to the core layer of intelligent decision-making to correct the feeding parameters.

[0027] 3) Finally, combining the fermentation temperature (Tg) collected by the infrared thermometer and the CH4 concentration (C) collected by the gas sensor, a fermentation quality scoring function was established to quantify the degree of fermentation of waste in each zone. Specifically, in step S2, the formula for calculating the degree of fermentation is: , Where: a, b, and c are weighting coefficients: a=0.4, b=0.3, c=0.3; and F ranges from 0 to 1. The closer the F value is to 1, the better the waste fermentation effect and the higher the combustion efficiency.

[0028] S3. Incinerator load demand calculation: The task planning unit within the intelligent decision-making core layer receives data on main steam flow, furnace temperature, and flue gas oxygen content uploaded by the incinerator operating condition module. Specifically, in step S3, the required total calorific value of the waste entering the incinerator, Qreq, and the feeding rate, Vreq, are calculated using the following formulas: Where P is the main steam power (MW) and η is the incinerator thermal efficiency, which is 85% by default and can be corrected according to actual operating conditions. Qavg is the average estimated calorific value of the waste entering the furnace, which can be estimated based on the type of waste and fermentation score of each zone.

[0029] S4, Intelligent Matching Calculation: Using an intelligent mixing model with constraints of stable calorific value, complete combustion, and compliance with emission standards, the optimal mixing ratio for waste in each zone is determined. Specifically, the process of determining the optimal mixing ratio for waste in each zone in step S4 is as follows: 1) Input parameters: waste type Ki, estimated calorific value Qi, fermentation score Fi, and usable waste amount Mi for each zone; among which, the basic calorific value is preset according to the waste type and corrected by the fermentation score F, Qi = basic calorific value × F.

[0030] 2) Objective function: Xi is the proportion of waste fed into the i-th zone; the basic calorific value is preset according to the type of waste and corrected by the fermentation score F, Qi = basic calorific value × F; the goal is to minimize the deviation between the total calorific value of the mixed waste and the total calorific value Qreq required by the incinerator.

[0031] 3) Constraints: ① ① The sum of the feeding ratios of all zones is 1; ② Xi ≥ 0, meaning the feeding ratio is non-negative; ③ Xi·Mi ≤ the maximum grabbable amount of the zone, meaning the single grabbable amount does not exceed 10% of the usable amount of waste in that zone, thus avoiding excessive grabbable amount leading to material level fluctuations; ④ The furnace temperature is maintained at 850-1050℃, which is the optimal combustion temperature range for the incinerator.

[0032] 4) Output results: Optimal mixing scheme X={x1,x2,...,xn}, single feeding amount G, which is calculated based on the feeding rate Vreq and feeding interval, and feeding interval ΔT, which is set based on the incinerator grate speed and furnace capacity, usually 15-20min.

[0033] S5. Garbage crane task assignment and execution: 1) The mixing scheme output by the intelligent compatibility model is converted into control instructions that the garbage crane can execute through the task planning unit, including the material grabbing coordinates (corresponding to the X / Y / Z three-axis coordinates of each zone), the material grabbing sequence (grabbing materials in order from large to small according to the mixing ratio), the number of mixing times (determined according to the mixing ratio, usually 2-3 times to ensure uniform mixing), and the feeding point (corresponding to zones 1-3 of the incinerator grate, adjusted according to the grate load distribution).

[0034] 2) After receiving the control command, the garbage crane execution module automatically executes the operation process without human intervention. Specifically, in step S5, the operation process of the garbage crane execution module is as follows: the garbage crane moves to the designated grabbing position, then the grab bucket descends to grab the designated weight of garbage, the weighing sensor confirms the weight of the grabbed material, and the deviation is ≤ ±0.1t. Then the garbage crane moves to the mixing area to mix the material, and then moves to the designated feeding point. The grab bucket unloads the material to complete the feeding, and finally returns to the initial position to wait.

[0035] 3) After feeding is completed, the system updates the material level height H, available waste Mi, and cumulative feeding amount of each zone of the waste pool in real time. Then, it collects the furnace feeding level data in real time through a high-definition industrial camera, verifies the feeding effect in a synchronous manner, and stores the feeding data, waste pool material level data, and furnace feeding level data together into the real-time database and the historical database.

[0036] S6, Closed-loop feedback optimization: 1) The closed-loop optimization unit collects real-time data on furnace temperature, steam parameters, and pollutant emissions from the incinerator operating condition module, as well as data on waste pool level collected by lidar and data on inlet level collected by high-definition industrial cameras, and compares them with the target values ​​set by the system.

[0037] Specifically, in step S6, if the deviation between the actual parameters and the set target values ​​exceeds the threshold, more specifically, the threshold is preset as follows: calorific value deviation > 8%, furnace temperature fluctuation > 100℃, NOx / SOx emission concentration exceeds the standard value; then the closed-loop optimization unit immediately triggers the intelligent matching model to recalculate the matching scheme, correct the mixing ratio, single feeding amount and feeding interval, and ensure that the incineration conditions return to the optimal range.

[0038] 2) System self-learning: The system automatically stores the matching cases that meet the requirements of stable calorific value (deviation ≤ ±5%), complete combustion (thermal efficiency ≥ 85%), and emission compliance into the knowledge base. The system performs parameter iteration optimization on the intelligent matching model once every morning to continuously improve the matching accuracy and system adaptability.

[0039] Therefore, by executing the steps described above in sequence, this application can form a closed-loop control. Specifically, by integrating vehicle scheduling, waste fermentation, material level monitoring and incinerator operating data, an intelligent matching method is constructed to automatically generate the optimal operation instructions for the waste crane, thereby achieving precise, stable and efficient intelligent incineration and solving many defects of the traditional manual incineration mode.

[0040] Specifically, it has the function of deep integration of multi-source data: breaking down the data barriers between the vehicle dispatching system, the waste pool monitoring system, and the incinerator control system, realizing information sharing of the entire chain from waste entering the plant to being put into the furnace, solving the problem of data silos in the traditional model, and providing comprehensive data support for precise matching.

[0041] Meanwhile, the mixing accuracy is high: the mixing ratio is quantified through the AI ​​intelligent mixing model, the fluctuation of the calorific value of the waste entering the furnace is controlled within ±5%, and the furnace temperature is stabilized within the optimal combustion range of 850-1050℃, effectively avoiding the roughness and subjectivity of manual mixing.

[0042] In addition, it operates efficiently and stably: the automatic operation rate of the garbage crane is ≥98%, eliminating the need for manual operation and significantly reducing the labor intensity of operators; and the stability of the main steam is improved by more than 35%, and the combustion efficiency of the incinerator is improved by 8-15%, ensuring the long-term stable operation of the incineration plant.

[0043] In addition, the energy conservation and emission reduction effects are significant: through precise matching and closed-loop optimization, the power consumption rate of the incinerator plant has decreased by 5-9%, the consumption of environmental protection consumables (desulfurizing agent and denitrification agent) has decreased by 14-20%, and the pollutant emissions have been stably up to standard, meeting the requirements of national environmental protection policies.

[0044] Secondly, it has an intelligent closed-loop self-optimization function: realizing full-link closed-loop control of "collection-decision-execution-feedback-optimization". The system can optimize the matching model through self-learning and iteration, get rid of the dependence on human experience, adapt to different types and batches of garbage, and has strong versatility and adaptability.

[0045] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A smart incineration furnace matching method based on multi-source data fusion, characterized in that, Includes the following steps: S1. Source data collection: After the garbage transport vehicle enters the unloading platform, the vehicle dispatch terminal automatically identifies the vehicle information and uploads various types of garbage data to the data transmission and storage layer in real time. After the data is uploaded, it is stored in the real-time database and the storage area of ​​the batch of garbage is marked. S2. Garbage pool status modeling: 1) The garbage pool is divided into zones according to the storage area. Each zone independently records the garbage fermentation start time Ts. The system calculates the fermentation time Δt = current time - Ts in real time for each zone. 2) The waste pool is then scanned from all angles using LiDAR to generate a three-dimensional material level map, marking the waste level height H and available waste quantity M in each zone; at the same time, a high-definition industrial camera is deployed at the inlet of the incinerator to monitor the material level in real time through camera imaging technology, capture the accumulation height and distribution of the waste entering the furnace, and synchronously feed the material level data into the intelligent decision core layer to correct the feeding parameters. 3) Finally, combining the fermentation temperature (Tg) collected by the infrared thermometer and the CH4 concentration (C) collected by the gas sensor, a fermentation quality scoring function was established to quantify the degree of fermentation of waste in each zone. ; S3. Incinerator load demand calculation: Receives main steam flow, furnace temperature, and flue gas oxygen content data uploaded by the incinerator operating condition module through the task planning unit in the intelligent decision core layer. S4. Intelligent Mixing Calculation: Using an intelligent mixing model, the optimal mixing ratio of waste in each zone is determined under the constraints of stable calorific value, complete combustion, and compliance with emission standards. S5. Garbage crane task issuance and execution: 1) The mixing scheme output by the intelligent matching model is converted into control instructions that the garbage crane can execute through the task planning unit, including material grabbing coordinates, material grabbing sequence, mixing times, and material feeding points; 2) After receiving control commands, the garbage crane execution module automatically executes the operation process without any manual intervention. 3) After feeding is completed, the system updates the material level height H, available waste Mi, and cumulative feeding amount of each zone of the waste pool in real time. Then, it collects the furnace feeding level data in real time through a high-definition industrial camera, verifies the feeding effect in a synchronous manner, and stores the feeding data, waste pool material level data, and furnace feeding level data together into the real-time database and the historical database. S6. Closed-loop feedback optimization: 1) The furnace temperature, steam parameters, and pollutant emission data uploaded by the incinerator operating condition module are collected in real time through the closed-loop optimization unit, and the waste pool material level data collected by the lidar and the furnace feed material level data collected by the high-definition industrial camera are compared with the target value set by the system. 2) System self-learning: The system automatically stores the compatibility cases that meet the requirements of stable calorific value, complete combustion and emission standards into the knowledge base. The system performs parameter iteration and optimization on the intelligent compatibility model once every morning to continuously improve the compatibility accuracy and system adaptability.

2. The intelligent incineration furnace matching method based on multi-source data fusion for waste incineration according to claim 1, characterized in that, In step S1, the garbage data for each type is as follows: 1) Waste type K = {k1, k2, ..., kn}, where k1 is kitchen waste, k2 is combustible waste, k3 is ash and soil waste, etc.; 2) The weight of each type of waste is W = {w1, w2, ..., wn}; 3) Corresponding unloading gate number D, where D1-D8 are set according to the number of unloading gates in the waste pool; 4) Unloading time T0.

3. The intelligent incineration furnace matching method based on multi-source data fusion for waste incineration according to claim 1, characterized in that, In step S2, the usable waste quantity M is calculated based on the material level height H and the partition area, i.e., M = H × partition area × waste bulk density; wherein, the waste bulk density is 1.2 t / m³. 3 It can be adjusted according to the actual type of waste.

4. The intelligent incineration furnace matching method based on multi-source data fusion for waste incineration according to claim 3, characterized in that, In step S2, the formula for calculating the degree of fermentation is: , Where: a, b, and c are weighting coefficients: a=0.4, b=0.3, c=0.3, and F ranges from 0 to 1.

5. The intelligent incineration furnace matching method based on multi-source data fusion for waste incineration according to claim 1, characterized in that, In step S3, the total calorific value of the waste required for the current incinerator, Qreq, and the feeding rate, Vreq, are calculated using the following formulas: Where P is the main steam power and η is the incinerator thermal efficiency; Qavg is the average estimated calorific value of the waste fed into the furnace.

6. The intelligent incineration furnace matching method based on multi-source data fusion for waste incineration according to claim 1, characterized in that, In step S4, the specific process of solving for the optimal mixing ratio of waste in each zone is as follows: 1) Input parameters: waste type Ki, estimated calorific value Qi, fermentation score Fi, and usable waste quantity Mi for each zone; 2) Objective function: Xi is the proportion of waste fed into the i-th zone; the basic calorific value is preset according to the type of waste and corrected by the fermentation score F, Qi = basic calorific value × F; The goal is to minimize the deviation between the total calorific value of the mixed waste and the total calorific value Qreq required by the incinerator; 3) Constraints: ① ; ②Xi≥0; ③Xi·Mi≤maximum catchable amount in the region; ④Furnace temperature maintained at 850-1050℃; 4) Output results: Optimal mixing scheme X={x1,x2,...,xn}, single feeding amount G, feeding interval ΔT.

7. The intelligent incineration furnace matching method based on multi-source data fusion for waste incineration according to claim 1, characterized in that, In step S5, the operation process of the garbage crane execution module is as follows: the garbage crane moves to the designated grabbing position, then the grab bucket descends to grab the designated weight of garbage, the weighing sensor confirms the weight of the grabbed material, then the garbage crane moves to the mixing area to mix the material, then moves to the designated feeding point, the grab bucket unloads the material to complete the feeding, and finally returns to the initial position to wait.

8. The intelligent incineration furnace matching method based on multi-source data fusion for waste incineration according to claim 1, characterized in that, In step S6, if the deviation between the actual parameters and the set target value exceeds the threshold, the closed-loop optimization unit immediately triggers the intelligent matching model to recalculate the matching scheme, correct the mixing ratio, single feeding amount and feeding interval, and ensure that the incineration conditions return to the optimal range.

Images