Adaptive calibration method and system based on multi-sensor fusion

Abstract

This invention relates to the field of system management technology, and more specifically, to an adaptive calibration method and system based on multi-sensor fusion. The method acquires multi-sensor monitoring data from several functional compartments of a solid waste intelligent management system, interprets the multi-sensor monitoring data to obtain the status perception information of solid waste in each functional compartment, and, based on the processing flow between the functional compartments, connects and processes the status perception information to obtain the treatment effect information of solid waste in each functional compartment. Finally, the method combines the status perception information and treatment effect information of each functional compartment to perform an adaptive analysis of the monitoring and treatment modes of each functional compartment, generating a calibration strategy for each functional compartment.

Description

Technical Field

[0001] This invention relates to the field of system management technology, and more specifically, to an adaptive calibration method and system based on multi-sensor fusion. Background Technology

[0002] With the acceleration of urbanization and industrial development, the amount of solid waste generated is increasing day by day, and its composition and properties are becoming more and more complex. Solid waste from different sources, such as industrial waste residue, domestic waste, and medical waste, have different physical and chemical properties. The solid waste treatment industry has an urgent need to improve treatment efficiency and quality. Traditional solid waste treatment methods often require a lot of manpower, material resources and financial resources, resulting in high operating costs. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide an adaptive calibration method and system based on multi-sensor fusion to improve the efficiency and quality of solid waste treatment.

[0004] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: According to one aspect of the present invention, an adaptive calibration method based on multi-sensor fusion is provided, comprising: Acquire multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and interpret the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment. Based on the processing flow between each functional compartment, the aforementioned situational awareness information is combined and analyzed to obtain information on the treatment effect of solid waste in each functional compartment. By combining the status perception information and processing effect information of each functional module, an adaptive analysis of the monitoring mode and processing mode of each functional module is performed, and a calibration strategy for each functional module is generated.

[0005] According to another aspect of the present invention, an adaptive calibration system based on multi-sensor fusion is provided, comprising: The data monitoring module is used to acquire multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and to interpret the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment. The effect analysis module is used to combine and analyze the situation perception information based on the processing flow between each functional compartment to obtain the treatment effect information of solid waste in each functional compartment. The mode calibration mode is used to combine the status perception information and processing effect information of each functional module to perform adaptive analysis of the monitoring mode and processing mode of each functional module, and generate calibration strategies for each functional module.

[0006] As can be seen from the above technical solutions, the multi-sensor fusion adaptive calibration method provided by the present invention has the following beneficial effects: This invention acquires and interprets monitoring data from multiple sensor sources, enabling precise understanding of the solid waste status within each functional compartment. This lays the foundation for subsequent analysis. By connecting the processing status perception information with the processing effect information, it provides a clear understanding of the actual processing effectiveness of each functional compartment for solid waste. Combining these two aspects for adaptive analysis and generating calibration strategies, it can dynamically adjust the monitoring and processing modes, making the system adaptable to different solid waste conditions, improving processing efficiency and quality, reducing costs, and promptly identifying and resolving potential problems, ensuring the stable and efficient operation of the intelligent solid waste management system. Attached Figure Description

[0007] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort: Figure 1 A schematic diagram illustrating the steps of the adaptive calibration method for multi-sensor fusion provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of the multi-sensor fusion adaptive calibration system provided in an embodiment of the present invention. Detailed Implementation

[0008] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0009] With the acceleration of urbanization and industrial development, the amount of solid waste generated is increasing day by day, and its composition and properties are becoming more and more complex. Solid waste from different sources, such as industrial waste residue, domestic waste, and medical waste, have different physical and chemical properties. The solid waste treatment industry has an urgent need to improve treatment efficiency and quality. Traditional solid waste treatment methods often require a lot of manpower, material resources and financial resources, resulting in high operating costs.

[0010] In view of this, the present invention provides an adaptive calibration method based on multi-sensor fusion, the steps of which are as follows: Figure 1 As shown, it includes: The first step is to acquire multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and to interpret the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment.

[0011] Specifically, in the first step of the embodiment provided by the present invention, data is collected from each functional compartment by a sensor network pre-deployed in each functional compartment of the solid waste intelligent management system to obtain multi-sensor source monitoring data of each functional compartment. These sensor networks include various types of sensors, such as weight sensors for monitoring the weight of solid waste, temperature sensors for detecting the temperature inside the compartment, humidity sensors for measuring humidity, and gas sensors for detecting the concentration of specific gases. Different types of sensors work together to collect relevant data from multiple dimensions inside the functional compartment.

[0012] More specifically, the various functional compartments of the solid waste intelligent management system undertake different tasks in the solid waste treatment process, such as storage, classification, and treatment. A single sensor can only acquire information from a single dimension and cannot fully reflect the true status of solid waste in the functional compartment. Through multi-sensor data acquisition, richer and more comprehensive monitoring data from multiple sensor sources can be obtained, providing a foundation for accurate analysis of the status of solid waste in the future.

[0013] More specifically, based on the current active monitoring mode of the sensor network in each functional compartment, the key parameters of the pre-trained situation awareness model are adjusted accordingly to switch the situation awareness model to the corresponding perception mode. Different monitoring modes are for different processing stages or specific monitoring needs. For example, the key information to be focused on is different in the solid waste storage stage and the processing stage. Therefore, the parameters of the situation awareness model need to be adjusted to adapt to different monitoring modes.

[0014] More specifically, the condition of solid waste and the characteristics that need attention vary in different functional compartments at different processing stages. The pre-trained condition awareness model is a general model framework, but in order to more accurately interpret the monitoring data from multiple sensors, the key parameters of the model need to be adjusted according to the current monitoring mode. This will enable the model to better adapt to the actual monitoring scenario and improve the accuracy of data interpretation.

[0015] More specifically, the condition perception model in the specified perception mode interprets the multi-sensor source monitoring data to obtain the condition perception information of solid waste in each functional compartment. The condition perception model will analyze and process the collected multi-sensor source monitoring data according to the adjusted parameters to extract information related to the condition of solid waste, such as the type, quantity, and state of solid waste (whether it has deteriorated, whether there is an abnormal odor, etc.).

[0016] More specifically, the collected multi-sensor monitoring data is raw and messy, and needs to be interpreted by professional models to be transformed into valuable information. By using a condition perception model with adjusted parameters, information that reflects the true state of solid waste in each functional compartment can be extracted from the multi-sensor monitoring data, providing a basis for subsequent treatment effect analysis and calibration strategy formulation.

[0017] The second step involves combining and analyzing the situational awareness information based on the processing flow between the functional compartments to obtain information on the treatment effect of solid waste in each functional compartment.

[0018] Specifically, in the second step of the embodiment provided by the present invention, based on the processing flow between each functional compartment, the status perception information of each compartment is combined and analyzed to obtain the full-process perception information of each batch of solid waste. Specifically, according to the order in which solid waste flows from one functional compartment to the next, the status perception information obtained by different functional compartments at different time points is integrated. For example, the initial status information of a certain batch of solid waste from entering the storage compartment, to the classification information after passing through the classification compartment, and then to the relevant information after processing in the treatment compartment, etc., are recorded to form the full-process perception information chain of that batch of solid waste.

[0019] More specifically, the status awareness information of each functional compartment is isolated, and individual information cannot fully reflect the changes of solid waste in the entire treatment process. By connecting and processing this information according to the treatment process, we can obtain complete information on solid waste from entering the system to each treatment stage and finally to its final state, providing a comprehensive data foundation for subsequent analysis of the treatment effect of each functional compartment.

[0020] More specifically, based on the processing mode executed by each functional compartment at the current moment, the solid waste treatment performance of each functional compartment is analyzed to obtain the treatment performance characteristics of each functional compartment. This involves the evaluation of the processing capacity, processing efficiency, and processing quality of the functional compartment. For example, for a crushing and processing compartment, the amount of solid waste that can be crushed per unit time and the particle size distribution after crushing are analyzed under the current crushing mode to determine the treatment performance characteristics of the compartment.

[0021] More specifically, different functional compartments have different processing performance under different processing modes. Understanding the processing performance characteristics of each functional compartment helps to clarify the actual performance of each functional compartment in the solid waste treatment process, and provides a reference for subsequent evaluation of the actual treatment effect of each functional compartment on solid waste, so as to determine whether the treatment process has achieved the expected results.

[0022] More specifically, based on the processing flow between each functional compartment, the processing performance characteristics of each functional compartment are connected and processed to obtain the full-process processing information of the solid waste intelligent management system. This is similar to the acquisition of full-process sensing information. The processing performance characteristics of each functional compartment are integrated according to the processing flow to form the full-process processing information of the entire solid waste treatment system. For example, information such as the storage efficiency of the storage compartment, the classification accuracy of the classification compartment, and the treatment compliance rate of the treatment compartment are connected in series according to the solid waste flow sequence.

[0023] More specifically, the performance characteristics of individual functional compartments cannot reflect the synergistic effect of the entire solid waste treatment system. By connecting the performance characteristics of each functional compartment according to the treatment process, we can obtain comprehensive performance information of the entire system in the process of treating solid waste, thereby more comprehensively evaluating the role and effect of each functional compartment in the entire treatment process.

[0024] More specifically, based on the full-process sensing information, a difference analysis of sensing changes in each functional compartment is performed to obtain the sensing change characteristics of a designated batch of solid waste in each functional compartment. For example, by comparing the differences in weight, composition, state, etc. of a batch of solid waste when entering and leaving a certain functional compartment, the actual impact of that functional compartment on the solid waste can be determined.

[0025] More specifically, the full-process perception information and the full-process processing information are time-aligned so that the theoretical solid waste treatment effect of each functional compartment can be analyzed based on the full-process processing information corresponding to the full-process perception information, so as to obtain the expected effect characteristics of each functional compartment. That is, based on the treatment performance characteristics of each functional compartment and the initial state of the solid waste, the state that the solid waste should reach after treatment by each functional compartment is theoretically calculated.

[0026] More specifically, based on the expected effect characteristics and perceived change characteristics of each functional module, the processing effect of each functional module is predicted to obtain the processing effect information of each functional module. By comparing the expected effect and the actual perceived change, it is determined whether the processing effect of each functional module meets the standards, such as whether the expected processing volume and processing quality have been achieved.

[0027] More specifically, the analysis of perceived changes can provide a direct view of the actual changes in solid waste in each functional compartment; the analysis of expected effects sets a standard for treatment effect from a theoretical perspective; combining the two to predict the treatment effect can accurately assess the actual treatment effect of each functional compartment, identify potential problems in the treatment process, and provide a basis for subsequent adjustments to the treatment mode and optimization of the system.

[0028] The third step is to combine the status perception information and processing effect information of each functional module to conduct an adaptive analysis of the monitoring mode and processing mode of each functional module, and generate a calibration strategy for each functional module.

[0029] Specifically, in the third step of the embodiment provided by the present invention, an adaptive analysis is performed on the processing mode of each functional compartment at the current time based on the processing effect information to obtain the first adaptive parameter of the processing mode of each functional compartment. For example, if the processing effect information shows that the processing efficiency of a certain functional compartment is low under the current processing mode, or the solid waste after processing does not meet the expected standard, then the degree of adaptability of the processing mode under the current situation can be quantified as the first adaptive parameter.

[0030] More specifically, the situation awareness information is substituted into pre-set compartment treatment standards to analyze and obtain a second adaptability parameter for each functional compartment corresponding to the situation awareness information. The pre-set compartment treatment standards specify the appropriate treatment methods that functional compartments should adopt under different solid waste conditions. By comparing the situation awareness information and these standards, the degree of matching between the current treatment mode and the actual solid waste condition is determined, and the second adaptability parameter is obtained. Combining the first adaptability parameter and the second adaptability parameter, the treatment mode of each functional compartment is comprehensively analyzed to obtain the adaptability characteristics of the treatment mode of each functional compartment. The two parameters can be combined using methods such as weighted averaging to comprehensively evaluate the adaptability of the current treatment mode.

[0031] More specifically, single pieces of information cannot fully assess the adaptability of a treatment model. Treatment effect information reflects the results of the treatment model in actual operation, while status awareness information reflects the actual condition of solid waste. By analyzing the two aspects separately to obtain adaptability parameters, and then conducting a comprehensive analysis, it is possible to more accurately determine whether the current treatment model is suitable for the current solid waste condition and treatment needs, providing a basis for subsequent adjustments to the treatment model.

[0032] More specifically, based on the performance differences between various processing modes, adaptive predictions of multiple pre-processing modes are performed for each functional module to obtain the predicted adaptation characteristics of each functional module for each type of pre-processing mode. A prediction model can be established by inputting the status perception information, processing effect information, and performance parameters of each processing mode of the functional module, predicting the adaptation of each pre-processing mode in the functional module, and then assigning the optimal processing mode to each functional module according to the predicted adaptation characteristics, and selecting the processing mode with the best adaptation characteristics as the mode to be used subsequently.

[0033] More specifically, the current treatment mode may not be optimal. By adaptively predicting multiple pre-treatment modes, the mode that best suits the current solid waste situation and treatment needs can be found among many options. This helps to improve the treatment efficiency and quality of functional compartments and make the solid waste treatment process more optimized.

[0034] More specifically, the status perception information of functional modules in different time periods is arranged in chronological order to form the status perception sequence of functional modules. Then, based on the status perception sequence, the monitoring mode adaptability analysis of the sensor network is performed on the functional modules. For example, the accuracy, completeness and timeliness of the status perception information obtained under different monitoring modes are analyzed to determine which monitoring mode can better reflect the actual situation of the functional modules, so as to determine the optimal monitoring mode for each functional module.

[0035] More specifically, different monitoring modes have different effects on acquiring situation awareness information. By analyzing the situation awareness sequence, we can understand the performance of different monitoring modes in practical applications, and thus select the monitoring mode that can acquire the most accurate and timely information on the solid waste status of functional compartments. This helps to improve the monitoring accuracy of functional compartments and provides a more reliable basis for adjusting the treatment mode and making decisions.

[0036] More specifically, calibration strategies for each functional module are generated based on the processing and monitoring modes assigned to each module. These calibration strategies may include specific adjustments to processing mode parameters and monitoring mode settings to ensure that the functional modules can operate efficiently and accurately under the new processing and monitoring modes.

[0037] More specifically, the treatment mode and the monitoring mode are interrelated. A suitable treatment mode requires accurate monitoring information to support it, while an effective monitoring mode is designed to better serve the treatment process. Combining the two to generate a calibration strategy can comprehensively optimize the operating status of functional compartments and improve the overall performance of the solid waste intelligent management system.

[0038] More specifically, the error risk of each sensing unit in the sensor network is analyzed using a sensor-supervised model for the situation-aware sequence. Task weights are then assigned to each sensing unit based on its error risk. For example, if a sensing unit has a high error risk, its task weight in data acquisition and analysis can be reduced; conversely, if its error risk is low, its task weight can be appropriately increased. These task weights are then used to assist in analyzing the adaptive characteristics of each processing mode. When analyzing the adaptability of processing modes, information provided by sensing units with low error risk receives higher weight.

[0039] More specifically, each sensing unit in a sensor network may have errors, which can affect the accuracy of situational awareness information and consequently the results of adaptive processing mode analysis. By analyzing the error risks of sensing units and assigning task weights, the impact of errors on the analysis results can be reduced, improving the accuracy and reliability of the analysis and making the calibration strategy more scientific and reasonable.

[0040] As can be seen from the above technical solutions, the multi-sensor fusion adaptive calibration method provided by the present invention has the following beneficial effects: This invention acquires and interprets monitoring data from multiple sensor sources, enabling precise understanding of the solid waste status within each functional compartment. This lays the foundation for subsequent analysis. By connecting the processing status perception information with the processing effect information, it provides a clear understanding of the actual processing effectiveness of each functional compartment for solid waste. Combining these two aspects for adaptive analysis and generating calibration strategies, it can dynamically adjust the monitoring and processing modes, making the system adaptable to different solid waste conditions, improving processing efficiency and quality, reducing costs, and promptly identifying and resolving potential problems, ensuring the stable and efficient operation of the intelligent solid waste management system.

[0041] Furthermore, the steps of acquiring multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and interpreting the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment include: S11: By using the sensor network pre-deployed in each functional compartment of the solid waste intelligent management system, data is collected from multiple sensors in each functional compartment to obtain multi-sensor source monitoring data for each functional compartment. S12: Based on the current active monitoring mode of the sensor network in each functional compartment, adjust the key parameters of the pre-trained situation awareness model accordingly to switch the situation awareness model to the corresponding perception mode. S13: Instruct the condition perception model in the specified perception mode to interpret the monitoring data from the multi-sensor sources and obtain the condition perception information of solid waste in each functional compartment.

[0042] Specifically, various types of sensors are pre-installed in the functional compartments (such as storage compartments, sorting compartments, and treatment compartments) of the solid waste intelligent management system to form a sensor network. These sensors may include, but are not limited to, weight sensors, temperature sensors, humidity sensors, gas sensors, and image sensors. Each sensor measures relevant physical quantities in the functional compartment in real time or periodically according to a set sampling frequency. For example, weight sensors monitor the weight changes of solid waste in real time; temperature and humidity sensors record the temperature and humidity conditions in the compartment; gas sensors detect the concentration of specific harmful gases; and image sensors capture images of the appearance of solid waste. The data collected by all sensors are aggregated into the data acquisition unit to form multi-sensor source monitoring data for each functional compartment.

[0043] More specifically, a single type of sensor can only acquire information from one aspect, while the condition of solid waste is multi-dimensional, involving multiple factors such as weight, temperature, humidity, composition, and appearance. By working together with multiple sensors, information inside the functional compartment can be collected comprehensively from different angles, providing a rich data foundation for accurately judging the condition of solid waste. The sensors can collect data in real time or periodically, enabling the system to keep abreast of the dynamic changes of solid waste inside the functional compartment, facilitating the timely detection of abnormalities and the implementation of corresponding measures.

[0044] More specifically, each functional compartment's sensor network has multiple preset monitoring modes. Based on the current working status and monitoring needs of the functional compartment, the currently activated monitoring mode is determined. For example, during the storage phase, more attention is paid to temperature, humidity, and gas concentration; during the processing phase, more attention is paid to the operating parameters of the processing equipment and changes in the weight of solid waste. According to the determined monitoring mode, the key parameters of the pre-trained condition awareness model are adjusted. These key parameters include the model's weights, thresholds, and feature extraction methods. For example, if the current monitoring mode focuses on temperature and humidity monitoring, the parameters related to temperature and humidity in the model are adjusted to make the model more focused on processing information in these two aspects.

[0045] More specifically, different monitoring modes correspond to different monitoring priorities and data characteristics. The pre-trained situation awareness model is a general framework, but in order to process and analyze data under specific monitoring modes more accurately, the parameters of the model need to be adjusted so that it can better adapt to the actual monitoring scenario and improve the accuracy of data interpretation. By adjusting the model parameters, the model can be made more efficient in processing specific types of data, avoiding over-processing of irrelevant information, thereby optimizing the utilization of computing resources.

[0046] More specifically, the status perception model, after parameter adjustment and in a specified perception mode, is applied to the collected multi-sensor source monitoring data. The model will perform a series of data processing operations, including data preprocessing (such as filtering and normalization), feature extraction, and pattern recognition. Based on the processing results of the model, information related to the status of solid waste is extracted, such as the type, quantity, state (whether it has deteriorated, whether there is an abnormal odor, etc.), and processing progress of solid waste, forming status perception information of solid waste in each functional compartment.

[0047] More specifically, the collected multi-sensor monitoring data is raw and messy, requiring professional models to process and analyze it before it can be transformed into meaningful information. The situation awareness model, through data interpretation, can extract key information from large amounts of data, helping system and management personnel understand the true status of solid waste in each functional compartment. Accurate situation awareness information is an important basis for subsequent formulation of treatment strategies, adjustment of treatment modes and monitoring modes. By timely and accurately interpreting multi-sensor monitoring data, the system can make more reasonable decisions and improve the efficiency and quality of solid waste treatment.

[0048] Furthermore, based on the processing flow between each functional compartment, the steps of combining and analyzing the aforementioned situational awareness information to obtain information on the treatment effect of solid waste in each functional compartment include: S21: Based on the processing flow between each functional compartment, combine and analyze the aforementioned situation perception information to obtain the full-process perception information of each batch of solid waste. S22: Based on the processing mode executed by each functional compartment at the current moment, analyze the solid waste treatment performance of each functional compartment to obtain the treatment performance characteristics of each functional compartment. S23: Based on the processing flow between each functional compartment, the processing performance characteristics of each functional compartment are connected and processed to obtain the full-process processing information of the solid waste intelligent management system. S24: Combine the full-process perception information and the full-process processing information to analyze the solid waste treatment effect of each functional compartment and obtain the treatment effect information of each functional compartment.

[0049] Specifically, based on the pre-set processing flow between each functional compartment, a unique identifier is established for each batch of solid waste. When collecting status awareness information from each functional compartment, this information is associated with the identifier of the batch of solid waste. For example, by using timestamps, batch numbers, etc., the status awareness information generated by a certain batch of solid waste in different functional compartments such as storage compartment, sorting compartment, and processing compartment is matched one by one. According to the order of the processing flow, the status awareness information of each associated functional compartment is integrated. For example, the initial status of the solid waste when it enters the first functional compartment is recorded first, and then the status information after its changes in subsequent functional compartments is added in turn, forming a full-process awareness information chain for the batch of solid waste from entering the system to completing the processing.

[0050] More specifically, the status awareness information of each functional compartment is isolated and cannot reflect the full picture of solid waste in the entire treatment process when viewed in isolation. By connecting and processing the information from each functional compartment, the complete status change process of a batch of solid waste from start to finish can be obtained. This allows managers to have a comprehensive understanding of the treatment status of each batch of solid waste in the system. The full-process awareness information is the key foundational data for subsequent analysis of treatment effects and evaluation of treatment performance. Only with complete full-process information can the actual impact of each functional compartment on solid waste and the synergistic effect between each link be accurately determined.

[0051] More specifically, the specific processing mode being performed by each functional compartment at the current moment needs to be determined. For example, whether the storage compartment uses a normal temperature storage mode or a low temperature storage mode, and whether the sorting compartment uses a manual sorting mode or a mechanical automatic sorting mode. Based on different processing modes, corresponding performance evaluation indicators are selected to analyze the solid waste treatment performance of each functional compartment. For the storage compartment, its storage capacity utilization rate and loss rate during storage can be evaluated; for the sorting compartment, the sorting accuracy and sorting efficiency are examined; for the treatment compartment, the processing speed and the quality of the treated products are analyzed. Through the calculation and analysis of these indicators, the treatment performance characteristics of each functional compartment are obtained.

[0052] More specifically, under different processing modes, the processing capacity and effect of each functional module will vary. Analyzing the processing performance characteristics allows managers to clearly understand the actual performance of each functional module under the current mode, identify its strengths and weaknesses, and accurately grasp the processing performance of each functional module to determine whether it is necessary to adjust the processing mode or optimize the configuration of equipment and personnel in the functional modules in order to improve the processing efficiency and quality of the entire system.

[0053] More specifically, based on the processing flow between each functional compartment, the processing performance characteristics of each functional compartment are associated with the corresponding batch of solid waste. This ensures that the processing performance characteristics of each batch of solid waste can be accurately matched with those of each functional compartment. Following the order of the processing flow, the processing performance characteristics of each associated functional compartment are integrated. For example, the processing time and processing effect indicators of a certain batch of solid waste in each functional compartment are statistically analyzed to form the full-process processing information of that batch of solid waste in the entire processing system. By summarizing the full-process processing information of all batches, the full-process processing information of the entire solid waste intelligent management system is obtained.

[0054] More specifically, the performance characteristics of individual functional compartments can only reflect the situation of a single link and cannot reflect the synergistic effect of the entire solid waste treatment system. By connecting and processing the performance characteristics of each functional compartment, we can gain a comprehensive understanding of the overall performance of the system in the process of treating a batch of solid waste, including processing efficiency and resource utilization. The information on the entire process helps to identify bottlenecks in the entire process. For example, if the processing speed of a certain functional compartment is too slow, it will affect the processing time of the entire batch, or if the connection between several functional compartments is not smooth enough, it will lead to resource waste, thus providing direction for the optimization and improvement of the system.

[0055] More specifically, based on the full-process sensing information, a detailed analysis is conducted on the state changes of solid waste before and after entering each functional compartment. By comparing the weight, composition, appearance, and other conditions of solid waste when entering and leaving a certain functional compartment, the actual impact of that functional compartment on the solid waste is determined, and the perceived change characteristics of solid waste in that functional compartment are obtained. Combining the full-process sensing information and the full-process processing information, the theoretical treatment effect that each functional compartment should achieve for solid waste under the current treatment mode and process is calculated, i.e., the expected effect characteristics. For example, based on the treatment performance of the sorting compartment and the initial composition of the solid waste, the theoretical component ratio after sorting is calculated. Then, the actual perceived change characteristics are compared with the expected effect characteristics to analyze the differences between the two.

[0056] More specifically, based on the comparison results, the treatment effect of each functional compartment is evaluated. If the actual effect is close to the expected effect, it indicates that the treatment effect of the functional compartment is good. If there is a large difference, it is necessary to further analyze the reasons to determine whether it is due to an inappropriate treatment mode, equipment failure or other factors, and finally obtain the treatment effect information of each functional compartment.

[0057] More specifically, by comparing and analyzing the actual treatment results with the expected results, it is possible to accurately determine whether each functional compartment has reached the required treatment level, assess its work quality and efficiency, and the treatment effect information can provide a basis for subsequent adjustments to the treatment mode, optimization of equipment parameters, and improvement of operating procedures. If the treatment effect of a certain functional compartment is not good, targeted improvements can be made, thereby improving the treatment effect and resource utilization efficiency of the entire solid waste intelligent management system.

[0058] Furthermore, the steps of analyzing the solid waste treatment effect of each functional compartment by combining the full-process perception information and the full-process processing information to obtain the treatment effect information of each functional compartment include: S241: Based on the full-process perception information, perform a difference analysis on the perception changes of each functional compartment to obtain the perception change characteristics of a specified batch of solid waste in each functional compartment. S242: Time-align the full-process perception information and the full-process processing information to analyze the theoretical solid waste treatment effect of each functional compartment based on the full-process processing information corresponding to the full-process perception information, so as to obtain the expected effect characteristics of each functional compartment. S243: Based on the expected effect characteristics and perceived change characteristics of each functional module, the processing effect of each functional module is predicted to obtain the processing effect information of each functional module.

[0059] Specifically, key status information of a designated batch of solid waste in each functional compartment is extracted from the full-process sensing information, such as weight, composition, temperature, and appearance when entering and leaving the functional compartment. For each functional compartment, the difference or change ratio of various status information of the solid waste when entering and leaving the compartment is calculated. For example, the percentage of weight reduction or the increase or decrease of the content of a certain component is calculated. The calculated differences are integrated to summarize the sensing change characteristics of the batch of solid waste in each functional compartment. These characteristics can be presented intuitively in the form of data tables, charts, etc.

[0060] More specifically, the perceived change characteristics can intuitively show the actual changes that occur when solid waste passes through each functional compartment, allowing managers to clearly see the specific role and impact of each functional compartment on solid waste. By analyzing the perceived change characteristics, some abnormal changes can be detected in a timely manner, such as a certain functional compartment causing an abnormal reduction in the weight of solid waste or an unexpected change in its composition. This helps to quickly locate potential problems, such as equipment failure or operational errors.

[0061] More specifically, since the full-process sensing information and full-process processing information may differ in the time of collection, it is necessary to align the two according to the processing time of solid waste in each functional compartment. For example, find the moment when solid waste enters a certain functional compartment and match the sensing information before and after that moment with the corresponding processing information.

[0062] More specifically, based on the time-aligned full-process processing information, combined with the processing modes and performance parameters of each functional compartment, a theoretical processing effect model is established. For example, given the processing efficiency of a certain processing compartment and the initial state of solid waste, the ideal state that the solid waste should reach after being processed by that compartment under the processing mode is calculated, including expected values ​​for weight, composition, product quality, etc. Key features are extracted from the calculated theoretical processing effect to form the expected effect features of each functional compartment.

[0063] More specifically, the expected effect characteristics provide a reference standard for evaluating the actual treatment effect of each functional module. Only by clarifying the theoretically achievable treatment effect can we determine whether the actual treatment process meets the requirements and whether there are any deviations. By comparing the expected effect with the actual perceived changes, we can assess whether the current treatment mode adopted by each functional module is reasonable and effective. If the actual effect differs significantly from the expected effect, it is necessary to adjust the treatment mode or optimize the equipment parameters.

[0064] More specifically, a detailed comparison will be made between the expected effect characteristics and perceived change characteristics of each functional module, and the degree of difference between the two in various indicators will be analyzed, such as the difference between the actual weight reduction ratio and the expected weight reduction ratio, and the degree of deviation between the actual component change and the expected component change.

[0065] More specifically, based on the comparison results, the processing effect of each functional module is inferred. If the actual perceived change characteristics are close to the expected effect characteristics, it indicates that the processing effect of the functional module is good and the expected goal has been achieved. If there is a large difference, it is judged that the processing effect is poor, and the possible reasons are further analyzed, such as the inapplicability of the processing mode or the decline in equipment performance.

[0066] More specifically, the predicted treatment effects of each functional compartment will be summarized to form treatment effect information for each functional compartment, including the evaluation of the treatment effect (such as meeting the standard, partially meeting the standard, and not meeting the standard) as well as possible problems and improvement suggestions.

[0067] More specifically, by combining the expected effect characteristics and perceived change characteristics for analysis, the actual treatment effect of each functional compartment can be comprehensively and objectively evaluated, avoiding one-sided judgments based on a single piece of information. The treatment effect information can provide specific directions for the optimization of the solid waste intelligent management system. For functional compartments with poor treatment effects, corresponding improvement measures can be taken based on the analysis results, such as adjusting treatment parameters, replacing equipment, and strengthening personnel training, thereby improving the treatment efficiency and quality of the entire system.

[0068] Furthermore, the steps of combining the status awareness information and processing effect information of each functional module to conduct adaptive analysis of the monitoring and processing modes of each functional module and generate calibration strategies for each functional module include: S31: Combining the situation awareness information and the processing effect information, perform an adaptive analysis on the processing mode of each functional compartment to obtain the adaptive characteristics of the processing mode of each functional compartment. S32: Based on the performance differences between the processing modes, perform adaptive predictions for various pre-processing modes for each functional module to obtain the predicted adaptive characteristics of each functional module for various pre-processing modes, and assign the optimal processing mode to each functional module based on the predicted adaptive characteristics. S33: Arrange the status perception information of the functional modules in time sequence to form the status perception sequence of the functional modules, and perform a monitoring mode adaptability analysis of the sensor network for the functional modules based on the status perception sequence to determine the best monitoring mode for each functional module. S34: Generate calibration strategies for each functional module based on the processing and monitoring modes assigned to each functional module.

[0069] Specifically, based on the treatment effect information, the performance of each functional compartment's current treatment mode in achieving the expected treatment goals is evaluated. For example, if the treatment effect information shows that the solid waste treated by a certain functional compartment does not meet the quality standards or the treatment efficiency is lower than expected, the adaptability of the treatment mode under the current situation is quantified as the first adaptability parameter, which can be measured by indicators such as the treatment compliance rate and the ratio of treatment time to expected time.

[0070] More specifically, situational awareness information is substituted into pre-set compartment treatment standards. These standards specify appropriate treatment methods to be adopted under different solid waste conditions. By comparing the situational awareness information and the standards, the degree of matching between the current treatment mode and the actual solid waste condition is determined, and a second adaptability parameter is obtained. For example, based on the composition and humidity of the solid waste, it is judged whether the current treatment mode can effectively treat it. An appropriate method (such as weighted averaging) is used to combine the first and second adaptability parameters to comprehensively evaluate the adaptability of the treatment modes of each functional compartment and obtain the adaptability characteristics of the treatment mode.

[0071] More specifically, neither treatment effect information nor situation awareness information alone is sufficient to comprehensively assess the adaptability of a treatment model. Treatment effect reflects the actual results of the treatment model's execution, while situation awareness reflects the actual situation of solid waste. By combining the analysis of both, we can accurately determine whether the current treatment model is suitable for the current solid waste situation and treatment needs, providing a basis for subsequent adjustments to the treatment model.

[0072] More specifically, this study investigates the performance differences among various processing modes in terms of processing efficiency, processing quality, and resource consumption, and establishes corresponding models. Using these models, combined with the status awareness information of functional modules and existing processing effect information, the adaptability of various pre-processing modes in each functional module is predicted. Machine learning algorithms or simulation methods can be used to obtain the predicted adaptability characteristics of each functional module for various pre-processing modes, such as the predicted processing compliance rate and estimated processing time. Based on the predicted adaptability characteristics, the optimal processing mode is assigned to each functional module, and the processing mode with the best predicted adaptability characteristics (such as the highest processing compliance rate and the shortest processing time) is selected as the mode to be used subsequently.

[0073] More specifically, the current treatment mode may not be optimal. By adaptively predicting and comparing multiple alternative treatment modes, the mode that best suits the current solid waste situation and treatment needs can be found among many options, thereby improving the treatment efficiency and quality of the functional compartments and optimizing the solid waste treatment process.

[0074] More specifically, the status perception information acquired by the functional modules at different time periods is arranged in chronological order to form a status perception sequence. This sequence reflects the changes in the solid waste status over time. Based on the status perception sequence, the accuracy, completeness, and timeliness of the status perception information acquired under different monitoring modes are analyzed. For example, the error magnitude of monitoring key solid waste parameters (such as weight and composition) under different monitoring modes is compared, as well as the response time for detecting abnormalities. Based on the analysis results, the optimal monitoring mode is determined for each functional module, that is, the mode that can acquire solid waste status information of the functional module most accurately, timely, and comprehensively.

[0075] More specifically, different monitoring modes have different effects on acquiring situation awareness information. By analyzing the situation awareness sequence, we can understand the performance of different monitoring modes in actual applications, select the mode that best meets the monitoring needs of functional modules, and improve the monitoring accuracy of functional modules, providing a more reliable basis for adjusting the processing mode and making decisions.

[0076] More specifically, a detailed calibration strategy should be developed, taking into account the processing and monitoring modes assigned to each functional compartment. The calibration strategy should include specific parameter settings for the processing modes (such as the operating speed and temperature of the processing equipment), adjustments to the monitoring modes (such as the sampling frequency and monitoring indicators of the sensors), and the schedule and responsible persons for implementing these adjustments.

[0077] More specifically, the treatment mode and the monitoring mode are interconnected and influence each other. A suitable treatment mode requires accurate monitoring information, while an effective monitoring mode is designed to better serve the treatment process. Combining the two to generate a calibration strategy can comprehensively optimize the operating status of functional compartments, improve the overall performance of the solid waste intelligent management system, and ensure the stable and efficient operation of the system.

[0078] Furthermore, the step of combining the situational awareness information and the processing effect information to perform adaptive analysis on the processing modes of each functional compartment, and obtaining the adaptive characteristics of the processing modes of each functional compartment, includes: S311: Based on the processing effect information, perform an adaptive analysis on the processing mode of each functional module at the current time to obtain the first adaptive parameter of the processing mode of each functional module. S312: Substitute the situation awareness information into the pre-set cabin processing standards to analyze and obtain the second adaptive parameters of each functional cabin corresponding to the situation awareness information; S313: Combining the first adaptive parameter and the second adaptive parameter, a comprehensive analysis of the processing modes of each functional compartment is performed to obtain the adaptive characteristics of the processing modes of each functional compartment.

[0079] Specifically, based on the content covered by the treatment effect information, specific indicators are determined for evaluating the adaptability of the treatment mode. Common indicators include treatment efficiency (such as the amount of solid waste treated per unit time), treatment quality (such as the compliance rate of treated solid waste), and resource consumption (such as energy consumption and raw material usage). For each functional compartment, the current treatment mode is quantitatively evaluated according to the determined evaluation indicators. For example, if the treatment efficiency is evaluated, the ratio of the actual treatment volume to the expected treatment volume can be calculated; for treatment quality, the proportion of solid waste that meets the quality standards after treatment is statistically analyzed. These quantitative results are used as the first adaptability parameter of the treatment mode of each functional compartment.

[0080] More specifically, the processing effect information intuitively reflects the performance of the current processing mode in actual operation. By quantitatively evaluating the processing mode to obtain the first adaptability parameter, it is possible to measure whether the processing mode is suitable for the working needs of the functional compartment from the perspective of actual processing results. This helps to identify problems in the processing process, such as low processing efficiency and substandard processing quality, and provides direction for subsequent adjustments to the processing mode.

[0081] More specifically, pre-set treatment standards for each functional compartment under different solid waste conditions. These standards can be formulated based on industry norms, empirical data, or experimental results, covering the correspondence between factors such as the composition, properties, and state of solid waste and corresponding treatment methods. The condition perception information of each functional compartment (such as the composition, humidity, and temperature of solid waste) is compared with the pre-set compartment treatment standards to analyze whether the current treatment mode matches the actual condition of the solid waste. If the degree of matching is high, the adaptability is good; otherwise, the adaptability is poor. By quantifying this degree of matching, a second adaptability parameter for the condition perception information of each functional compartment is obtained. For example, different matching levels can be set, and each level can be assigned a corresponding value.

[0082] More specifically, situation awareness information reflects the actual characteristics and state of solid waste. Different solid waste conditions require different treatment methods to achieve the best treatment results. By incorporating situation awareness information into the cabin treatment standards for analysis, the adaptability of the current treatment mode can be assessed from the perspective of the actual situation of solid waste. This helps to ensure that the treatment mode is in line with the characteristics of solid waste and avoid poor treatment results or waste of resources due to inappropriate treatment mode.

[0083] More specifically, the weights are determined: based on actual needs and the importance of each parameter, weights are assigned to the first and second adaptability parameters respectively. For example, if more emphasis is placed on the actual performance of the treatment effect, a higher weight can be assigned to the first adaptability parameter; if the matching between the treatment mode and the solid waste condition is emphasized, a higher weight can be assigned to the second adaptability parameter. The first and second adaptability parameters are then weighted according to the determined weights. Based on the comprehensive adaptability parameter obtained from the weighted calculation, the adaptability characteristics of the treatment modes of each functional compartment are summarized. The adaptability characteristics can be divided into different levels, such as high adaptability, medium adaptability, and low adaptability, so as to intuitively understand the adaptability of the treatment modes of each functional compartment.

[0084] More specifically, a single first or second adaptability parameter can only assess the adaptability of a treatment mode from one aspect, which has limitations. By comprehensively considering these two parameters and weighting them according to their importance, the adaptability of the treatment mode can be comprehensively and objectively assessed. The resulting adaptability characteristics can provide an accurate basis for subsequent adjustments to the treatment mode and optimization of the solid waste treatment process, enabling the treatment mode to better adapt to the working needs of the functional compartments and the actual condition of the solid waste.

[0085] Furthermore, it also includes: analyzing the error risk of each sensing unit in the sensor network for the situation perception sequence through a sensor supervision model, and assigning task weights to each sensing unit according to the error risk of each sensing unit, so as to use the task weights to assist in analyzing the adaptive characteristics of each processing mode.

[0086] Specifically, historical data of each sensing unit in the sensor network is collected over a period of time, including data during normal operation and data when errors or malfunctions occur. This data can come from various sensors in different functional compartments, such as temperature sensors, weight sensors, and gas sensors. Appropriate machine learning or deep learning algorithms, such as neural networks and decision trees, are selected, and the collected historical data is used to train the sensor supervision model. The goal of the training is to enable the model to identify abnormal features in the sensor unit data, thereby predicting error risks.

[0087] More specifically, the status perception sequence of the functional compartments is input into the trained sensor supervision model. The status perception sequence contains data collected by each sensor unit at different time points, reflecting the real-time status of the functional compartments. Based on the input status perception sequence, the sensor supervision model evaluates the error risk of each sensor unit. The model analyzes factors such as the stability of the data, the degree of deviation from historical data, and the trend of data changes, and outputs an error risk value for each sensor unit. For example, if the data of a certain temperature sensor fluctuates abnormally and has poor correlation with the data of other related sensors, the model will judge that the error risk of that sensor is high.

[0088] More specifically, based on the magnitude of the error risk value, corresponding task weight allocation rules are set. Generally, sensing units with lower error risk provide more reliable data and should be assigned higher task weights; while sensing units with higher error risk provide less reliable data and should be assigned lower task weights. For example, the error risk value can be divided into several intervals, each interval corresponding to a task weight range. Task weights are then assigned to each sensing unit according to the set rules. Task weights can be represented numerically, typically ranging from 0 to 1. A higher weight indicates greater importance of the sensing unit in subsequent analysis.

[0089] More specifically, when analyzing the adaptive characteristics of each processing mode, the data provided by each sensing unit is weighted according to the assigned task weight. For example, when calculating a certain evaluation index, data from sensing units with large task weights are given higher weights, while data from sensing units with small task weights are given lower weights. By combining the weighted data with previously obtained first and second adaptive parameters, the adaptive characteristics of each processing mode are comprehensively analyzed. This can reduce the impact of sensing units with higher error risk on the analysis results and improve the accuracy of the analysis.

[0090] More specifically, the individual sensing units in a sensor network may be affected by various factors, such as environmental interference, equipment aging, and malfunctions, leading to errors in the collected data. By analyzing the error risks of sensing units through a sensor-supervised model and assigning task weights, the impact of erroneous data on the analysis results can be reduced, thereby improving the reliability and accuracy of the data.

[0091] More specifically, accurate data is crucial when analyzing the adaptability of processing modes. Data from sensors with a high risk of error can mislead the analysis results, leading to inaccurate assessments of the processing modes. By allocating task weights, the role of reliable data can be highlighted, enabling the analysis results to better reflect the true adaptability of the processing modes and providing a more reliable basis for subsequent decision-making.

[0092] More specifically, for sensing units with a high risk of error, their task weight in the analysis can be appropriately reduced, decreasing reliance on their data. This helps to allocate analytical resources rationally, focusing more attention and resources on highly reliable sensing units, thus improving analysis efficiency and quality. Simultaneously, it allows for the timely identification of sensing units with a high risk of error, facilitating maintenance or replacement and ensuring the normal operation of the sensor network.

[0093] Based on the technical content of the multi-sensor fusion adaptive calibration method described in the above-disclosed embodiments, the present invention provides a multi-sensor fusion adaptive calibration system, the structure of which is as follows: Figure 2An adaptive calibration method for implementing multi-sensor fusion as described in any one of the first aspects, comprising: The data monitoring module is used to acquire multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and to interpret the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment. The effect analysis module is used to combine and analyze the situation perception information based on the processing flow between each functional compartment to obtain the treatment effect information of solid waste in each functional compartment. The mode calibration mode is used to combine the status perception information and processing effect information of each functional module to perform adaptive analysis of the monitoring mode and processing mode of each functional module, and generate calibration strategies for each functional module.

[0094] In this embodiment, the specific implementation of each module in the above system embodiment is described in the above method embodiment, and will not be repeated here.

[0095] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0096] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0097] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-sensor fusion adaptive calibration method, characterized in that, include: Acquire multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and interpret the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment. Based on the processing flow between each functional compartment, the aforementioned situational awareness information is combined and analyzed to obtain information on the treatment effect of solid waste in each functional compartment. By combining the status perception information and processing effect information of each functional module, an adaptive analysis of the monitoring mode and processing mode of each functional module is performed, and a calibration strategy for each functional module is generated.

2. The adaptive calibration method for multi-sensor fusion as described in claim 1, characterized in that, The steps of acquiring multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and interpreting the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment include: By pre-deploying sensor networks in each functional compartment of the solid waste intelligent management system, data is collected from multiple sensors in each functional compartment to obtain multi-sensor source monitoring data for each functional compartment. Based on the current active monitoring mode of the sensor network in each functional compartment, the key parameters of the pre-trained situation awareness model are adjusted accordingly to switch the situation awareness model to the corresponding perception mode. The condition perception model, which is in a specified perception mode, interprets the monitoring data from the multiple sensor sources to obtain condition perception information of solid waste in each functional compartment.

3. The adaptive calibration method for multi-sensor fusion as described in claim 1, characterized in that, The steps for combining and analyzing the situational awareness information based on the processing flow between each functional compartment to obtain information on the treatment effect of solid waste in each functional compartment include: Based on the processing flow between each functional compartment, the aforementioned situational awareness information is combined and analyzed to obtain the full-process awareness information for each batch of solid waste being processed. Based on the processing mode performed by each functional compartment at the current moment, the solid waste treatment performance of each functional compartment is analyzed to obtain the treatment performance characteristics of each functional compartment. Based on the processing flow between each functional compartment, the processing performance characteristics of each functional compartment are connected and processed to obtain the full-process processing information of the solid waste intelligent management system. By combining the full-process perception information and the full-process processing information, the solid waste treatment effect of each functional compartment is analyzed to obtain the treatment effect information of each functional compartment.

4. The adaptive calibration method for multi-sensor fusion as described in claim 3, characterized in that, The steps for analyzing the solid waste treatment effect of each functional compartment by combining the full-process sensing information and the full-process processing information to obtain the treatment effect information of each functional compartment include: Based on the full-process sensing information, a differential analysis of sensing changes in each functional compartment is performed to obtain the sensing change characteristics of a specified batch of solid waste in each functional compartment. The full-process perception information and the full-process processing information are time-aligned so that the solid waste theoretical treatment effect of each functional compartment can be analyzed based on the full-process processing information corresponding to the full-process perception information, so as to obtain the expected effect characteristics of each functional compartment. Based on the expected effect characteristics and perceived change characteristics of each functional module, the processing effect of each functional module is predicted in order to obtain the processing effect information of each functional module.

5. The adaptive calibration method for multi-sensor fusion as described in claim 1, characterized in that, The steps involved in combining the status awareness information and processing effect information of each functional module to perform adaptive analysis of the monitoring and processing modes of each functional module, and generating calibration strategies for each functional module, include: By combining the situation awareness information and the processing effect information, an adaptive analysis is performed on the processing mode of each functional compartment to obtain the adaptive characteristics of the processing mode of each functional compartment. Based on the performance differences between the various processing modes, adaptive predictions of multiple pre-processing modes are performed for each functional module to obtain the predicted adaptation characteristics of each functional module for each type of pre-processing mode, and the optimal processing mode is assigned to each functional module based on the predicted adaptation characteristics. The status perception information of functional modules in each time period is arranged in time sequence to form the status perception sequence of functional modules. Based on the status perception sequence, the monitoring mode adaptability analysis of the sensor network of functional modules is performed to determine the optimal monitoring mode for each functional module. The calibration strategy for each functional module is generated based on the processing and monitoring modes assigned to each module.

6. The adaptive calibration method for multi-sensor fusion as described in claim 5, characterized in that, The steps of combining the situational awareness information and the processing effect information to perform adaptive analysis on the processing modes of each functional compartment and obtain the adaptive characteristics of the processing modes of each functional compartment include: Based on the processing effect information, an adaptive analysis is performed on the processing mode of each functional module at the current time to obtain the first adaptive parameter of the processing mode of each functional module. The situation awareness information is substituted into the pre-set cabin processing standards to analyze and obtain the second adaptive parameters of each functional cabin corresponding to the situation awareness information. By combining the first adaptive parameter and the second adaptive parameter, a comprehensive analysis of the processing modes of each functional compartment is conducted to obtain the adaptive characteristics of the processing modes of each functional compartment.

7. The adaptive calibration method for multi-sensor fusion as described in claim 6, characterized in that, Also includes: The error risk of each sensing unit in the sensor network is analyzed by a sensor-supervised model for the situation-aware sequence, and task weights are assigned to each sensing unit according to the error risk of each sensing unit. The first adaptive parameter and the second adaptive parameter are then weighted and fused by the task weights to obtain adaptive features.

8. A multi-sensor fusion adaptive calibration system, characterized in that, include: The data monitoring module is used to acquire multi-sensor source monitoring data from several functional compartments of the solid waste intelligent management system, and to interpret the multi-sensor source monitoring data to obtain the status perception information of solid waste in each functional compartment. The effect analysis module is used to combine and analyze the situation perception information based on the processing flow between each functional compartment to obtain the treatment effect information of solid waste in each functional compartment. The mode calibration mode is used to combine the status perception information and processing effect information of each functional module to perform adaptive analysis of the monitoring mode and processing mode of each functional module, and generate calibration strategies for each functional module.

Images