Intelligent compensation method for deformation of double-lug tank

Abstract

The invention relates to the technical field of binaural tank deformation compensation, and discloses an intelligent binaural tank deformation compensation method, which comprises the following steps of: firstly, acquiring structural parameters and working environment data of a binaural tank, analyzing the structural parameters and the working environment data, constructing a deformation feature set, and determining an initial compensation feature library; determining a compensation model update information set according to dynamic optimization operation fed back by the initial compensation feature library, and obtaining target compensation parameters through hierarchical disassembly and classification statistics; and acquiring a compensation resource configuration information set, and determining and outputting an adaptability compensation scheme based on the compensation resource configuration information set and according to the target compensation parameter. According to the method, through multi-dimensional data acquisition and analysis, dynamic updating of a compensation model and comprehensive consideration of historical data to optimize compensation resource configuration, intelligent and accurate compensation of the deformation of the binaural tank is realized, the compensation precision and efficiency are improved, the cost is reduced, and the system stability and adaptability are enhanced; the method is suitable for deformation compensation scenes of double-lug tanks in multiple industries such as chemical engineering and metallurgy.

Description

Technical Field

[0001] The present invention relates to the technical field of deformation compensation of amphorae, and in particular to an intelligent deformation compensation method of amphorae. Background Art

[0002] In industrial production and manufacturing, amphorae, as common containers or structural components, are widely used in a variety of industries, including chemical, metallurgy, and energy. However, during actual use, amphorae are subject to deformation due to various factors, which not only affects their normal function but also poses safety risks.

[0003] From a structural perspective, differences in amphora's geometry, size, material properties, and other structural parameters can lead to variations in deformation when exposed to the same external conditions. For example, different groups of structural geometric features can result in different positional association weights and structural influence scores for each feature point, thus affecting the overall deformation pattern.

[0004] The complexity of the operating environment also significantly influences the deformation of the amphora. Variations in the load cycle cause the amphora to experience varying loads at different stages, leading to differences in the critical observation phases. The rate of change in the thermal environment also influences the mechanical properties of the material, further complicating the deformation of the amphora.

[0005] Existing methods for compensating for amphora deformation suffer from numerous shortcomings when faced with these complex situations. Traditional methods often struggle to comprehensively and accurately collect and analyze the amphora's structural parameters and operating environment data, making it impossible to construct a complete set of deformation features. This results in an incomplete initial compensation feature library, making it difficult to accurately predict and compensate for deformation. Furthermore, traditional methods lack the ability to dynamically adjust and optimize the compensation model based on real-time monitoring data, leading to a decrease in compensation effectiveness over time.

[0006] In the configuration of compensation resources and the determination of plans, traditional methods usually do not fully consider historical data and actual conditions, making it difficult to achieve optimal resource configuration and adaptability of compensation plans, resulting in high compensation costs and poor results.

[0007] With the development of industrial automation and intelligentization, higher requirements are being placed on the accuracy and efficiency of amphora deformation compensation. Therefore, a method that can intelligently and efficiently compensate for amphora deformation is urgently needed to address the problems existing in the existing technology and improve the safety and reliability of amphora. Summary of the Invention

[0008] The purpose of the present invention is to provide an intelligent deformation compensation method for a two-ear jar to solve the problems raised in the above background technology.

[0009] To achieve the above-mentioned object, the present invention provides the following technical solution: a method for intelligently compensating deformation of a two-ear jar, the method comprising: collecting amphora structural parameters and operating environment data, analyzing the amphora structural parameters and operating environment data, constructing a deformation feature set, and determining and outputting an initial compensation feature library; Determine the compensation model update information set based on the dynamic optimization operation fed back by the initial compensation feature library; Parsing the compensation model update information set, performing hierarchical decomposition and classification statistics on the compensation model update information set, and determining target compensation parameters; A compensation resource configuration information set is obtained, and based on the compensation resource configuration information set and in accordance with the target compensation parameters, an adaptive compensation scheme is determined and output.

[0010] Preferably, the analyzing the amphora structural parameters and the operating environment data, constructing a deformation feature set, and determining and outputting an initial compensation feature library includes: Analyzing the structural parameters of the amphorae and the operating environment data to extract the structural geometric feature groups, mechanical distribution features, and temperature change environment features; Analyzing the structural geometric feature group to determine the position association weight and structural impact score corresponding to each feature point; determining a key observation phase of the amphora according to the load cycle period in the operating environment data, and determining a deformation attenuation coefficient according to the load cycle period and the key observation phase of the amphora; constructing a multidimensional feature vector according to the position association weight, the structural influence score, the deformation attenuation coefficient, and the mechanical distribution characteristics; According to the multi-dimensional feature vector, a matching search is performed on a preset historical deformation case database to determine and output the initial compensation feature library.

[0011] Preferably, constructing a multidimensional feature vector according to the position association weight, the structural influence score, the deformation attenuation coefficient and the mechanical distribution characteristics specifically includes: The structural weight parameters are determined according to the dimensional deviation degree of the structural geometric characteristics, the mechanical weight parameters are determined according to the stress concentration degree of the mechanical distribution characteristics, and the environmental weight parameters are determined according to the change rate of the temperature change environmental characteristics; The structural weight parameter, mechanical weight parameter, environmental weight parameter and deformation attenuation coefficient are weighted and fused to form a composite feature vector including structural dimension, mechanical dimension and environmental dimension.

[0012] Preferably, the dynamic optimization operation based on the feedback of the initial compensation feature library to determine the compensation model update information set includes: Based on the initial compensation feature library, a real-time deformation visualization interface is provided for the deformation monitoring system, and the feature space mapping effect is synchronously updated according to the monitoring data trajectory fed back by the system; Based on the monitoring data trajectory, potential deformation features of the amphora are identified through pattern clustering analysis, the sorting priority of the initial features is dynamically adjusted, and a feature update plan is generated; Analyze the feature update scheme, evaluate the stability of the compensation model, determine model stability feedback information, and feed back corresponding feature optimization suggestions to the control end, and receive adjustment confirmation instructions; According to the adjustment confirmation instruction, a compensation model update information set is determined.

[0013] Preferably, analyzing the feature update scheme, evaluating the stability of the compensation model, and determining model stability feedback information include: According to the feature update scheme, the number of feature dimensions, compensation confidence interval, historical compensation result distribution and feature importance ranking of the model are extracted; According to the structural properties of each feature, the compensation error tolerance threshold, historical compensation accuracy ratio and continuous compensation consistency rate of the model are determined; Based on the number of feature dimensions, the compensation confidence interval, and the historical compensation result distribution, and according to the feature importance ranking and the compensation error tolerance threshold, a statistical stability determination condition is established; determining an effective time range of model compensation according to the load cycle and the key observation phase of the amphora; Based on the historical compensation accuracy ratio and the effective time range, and according to the continuous compensation consistency rate and the feature importance ranking, a time series stability judgment condition is established; According to the statistical stability judgment condition and the temporal stability judgment condition, it is judged whether the statistical stability or temporal stability corresponding to the current feature update scheme meets the requirements, and a judgment conclusion is determined, which is used as the model stability feedback information.

[0014] Preferably, the statistical stability judgment condition is constructed based on the number of feature dimensions, the compensation confidence interval and the historical compensation result distribution, according to the feature importance ranking and the compensation error tolerance threshold, and specifically includes: Calculate the correlation between the number of feature dimensions and the compensation confidence interval, analyze the matching degree between the distribution of historical compensation results and the feature importance ranking, and set the critical range of statistical stability in combination with the compensation error tolerance threshold; The time series stability determination condition is constructed based on the historical compensation accuracy ratio and the effective time range, according to the continuous compensation consistency rate and the feature importance ranking, and specifically includes: Calculate the fluctuation range of the historical compensation accuracy ratio within the effective time range, analyze the temporal correlation between the continuous compensation consistency rate and the feature importance ranking, and set the critical range of temporal stability.

[0015] Preferably, the parsing of the compensation model update information set, performing hierarchical decomposition and classification statistics on the compensation model update information set, and determining target compensation parameters includes: Update the information set according to the compensation model, and calculate the key feature optimization set and the auxiliary parameter adjustment set; According to the model update period set by the mechanism, the load cycle periods corresponding to different amphorae in the compensation model update information set are divided into a number of update batches to determine an update batch information set; Based on the update batch information set, the key feature optimization set is parsed, and according to the parameter drift ratio corresponding to each feature in the key feature optimization set in the historical update records, the parameter redundancy corresponding to each feature in each update batch is determined; The target compensation parameter is constructed according to the auxiliary parameter adjustment set, the update batch information set and the parameter redundancy.

[0016] Preferably, the determining and outputting an adaptive compensation scheme based on the compensation resource configuration information set and in accordance with the target compensation parameter includes: parsing the target compensation parameters based on the compensation resource configuration information set, and determining a number of target compensation resources corresponding to each characteristic optimization item in the target compensation parameters; Extract the historical collaboration records corresponding to each target compensation resource based on the compensation resource configuration information set, thereby determining the historical application times, historical optimization costs, historical compensation accuracy ratios, and historical execution risks of each feature optimization item under the corresponding target compensation resource by the current organization; Based on the historical application times, historical optimization costs, historical compensation accuracy ratio and historical execution risks of each feature optimization item under the corresponding target compensation resources, comprehensive cost optimization processing is performed on each feature optimization item to determine the optimal compensation resources corresponding to each feature optimization item, thereby constructing and outputting the adaptive compensation plan.

[0017] Preferably, the comprehensive cost optimization process is performed on each feature optimization item based on the historical application times, the historical optimization cost, the historical compensation accuracy ratio and the historical execution risk of each feature optimization item under the corresponding target compensation resource, specifically including: Calculate the weighted sum of the number of historical applications and the historical optimization cost as the resource usage cost indicator, and calculate the weighted sum of the historical compensation accuracy ratio and the historical execution risk as the effect risk cost indicator; The resource use cost index is comprehensively compared with the effect risk cost index, and the compensation resource with the lowest comprehensive cost is selected as the optimal resource.

[0018] Preferably, identifying the potential deformation characteristics of the amphora through pattern cluster analysis includes: Dividing the monitoring data trajectory into time windows and extracting the deformation fluctuation amplitude and frequency within each time window; The initial classification standard of the clustering algorithm is set as the feature library of historical high compensation demand cases, and clustering iteration is performed based on the matching degree between the deformation fluctuation amplitude and frequency and the initial classification standard; The reliability of the clustering results was evaluated by classification purity, and cluster groups whose matching degree with historical high compensation features exceeded the preset critical value were screened out, and their corresponding feature combinations were identified as potential deformation features of the amphorae.

[0019] Compared with the prior art, the present invention has the following beneficial effects: This method collects data on the amphora's structural parameters and operating environment, analyzes them, constructs a set of deformation features, and determines an initial compensation feature library, laying a solid foundation for subsequent compensation work. This comprehensive data collection and analysis fully considers the amphora's structural characteristics and operating environment, making the initial compensation feature library more accurate and complete, thereby improving the accuracy of deformation prediction and compensation.

[0020] Regarding compensation model updates, dynamic optimization operations based on feedback from the initial compensation feature library determine the compensation model update information set, which is then broken down and classified into hierarchical categories to determine target compensation parameters. This process enables dynamic updating and optimization of the compensation model, enabling timely adjustments based on real-time monitoring data to adapt to changes in the amphora's deformation, ensuring the stability and reliability of the compensation effect. Pattern clustering analysis identifies potential deformation features and dynamically adjusts feature prioritization, further improving the model's adaptability to complex deformation situations.

[0021] To determine the compensation plan, we obtain the compensation resource configuration information set and determine and output an adaptive compensation plan based on the target compensation parameters. By analyzing historical collaboration records, including factors such as the number of historical applications, optimization costs, compensation accuracy ratio, and execution risk, we perform comprehensive cost optimization on each feature optimization item and select the optimal compensation resource. This achieves optimal resource allocation, reduces compensation costs, and improves the effectiveness and reliability of the compensation plan.

[0022] This method considers a weighted fusion of structural, mechanical, and environmental weight parameters, along with the deformation attenuation coefficient, when constructing a multidimensional feature vector. This method comprehensively describes the deformation characteristics of the amphora from multiple dimensions, further improving the accuracy and reliability of the model. When evaluating the stability of the compensation model, statistical and temporal stability criteria were established. These criteria assess the model's stability from both statistical and temporal perspectives, ensuring that the model maintains a stable compensation effect under different circumstances.

[0023] By dividing update batches and determining parameter redundancy, the compensation model updates are more organized and efficient, adapting to the load cycles and model update intervals of different amphora, thereby improving the system's adaptability and flexibility. In summary, the method of the present invention can comprehensively and accurately compensate for amphora deformation, improving compensation accuracy and efficiency, reducing compensation costs, and enhancing the system's stability and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a working principle diagram of the intelligent compensation method for deformation of amphora jars according to the present invention; Figure 2 Design diagrams constructed for the initial compensation feature library; Figure 3 Design drawings for dynamic updates of compensation models; Figure 4 Design diagram for model stability assessment; Figure 5 Design diagram generated for the adaptive compensation scheme. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1-Figure 5 The intelligent deformation compensation method of the double-eared jar involved in the present invention is specifically implemented in the following steps: The system collects and analyzes the structural parameters and operating environment data of the amphora, constructs a set of deformation features, and determines and outputs an initial compensation feature library. The structural parameters include the amphora's geometric dimensions and material properties, while the operating environment data covers temperature variations and load conditions. By analyzing this data, relevant features are extracted.

[0027] Based on the dynamic optimization operation of the initial compensation feature library feedback, the compensation model update information set is determined. In actual application, the initial compensation feature library will be optimized and adjusted based on the feedback to generate the information set required for model update.

[0028] The compensation model update information set is parsed, and the compensation model update information set is broken down and classified into different levels for statistical analysis to determine target compensation parameters. Through in-depth analysis and classification of the update information set, the target compensation parameters that need to be adjusted are clearly identified.

[0029] Obtain a compensation resource configuration information set, determine and output an adaptive compensation scheme based on the compensation resource configuration information set and the target compensation parameters, and formulate an appropriate compensation scheme based on the configuration of the compensation resources and the target compensation parameters.

[0030] Example 1: In the implementation method of constructing a deformation feature set and determining an initial compensation feature library, it is necessary to comprehensively collect and analyze the structural parameters of the amphorae and the operating environment data. Among them, the structural parameters of the amphorae include geometric dimensional parameters, such as the height and diameter of the amphorae, the position coordinates of the amphorae, the connection angle between the amphorae and the amphorae, and other specific structural dimensional information, as well as material property parameters, such as the elastic modulus, yield strength, Poisson's ratio and other physical property data of the material. The operating environment data includes temperature change data, such as the real-time monitoring value of the ambient temperature, the rate and period of temperature change, etc.; load condition data, such as the size of the load applied to the amphorae, the type of load (static load or dynamic load), the load cycle period, etc.

[0031] After analyzing this data, we begin extracting structural geometric feature groups, mechanical distribution features, and temperature-dependent environmental features. Extracting structural geometric feature groups requires detailed analysis of each structural component of the amphorae jar. Taking the main body of the amphorae jar as an example, we extract features such as the radius of curvature of the cylindrical surface and the uniformity of the wall thickness. For the amphorae jar, we extract features such as the cross-sectional shape of the ears and the dimensions of the transition fillet at the connection between the ears and the jar body. When extracting mechanical distribution features, we use methods such as finite element analysis to obtain stress distribution cloud maps of the amphorae jar under different load conditions. This allows us to extract features such as the location of stress concentration areas and the magnitude of stress values, as well as strain distribution features such as the magnitude and gradient of strain at various locations. Extracting temperature-dependent environmental features involves processing temperature monitoring data to obtain a temperature curve over time, thereby extracting features such as the peaks, valleys, and rate of change of temperature.

[0032] An in-depth analysis of the structural geometric feature groups is conducted to determine the position-related weight and structural impact score corresponding to each feature point. When determining the position-related weight, the importance of the position of the feature point in the overall structure of the amphorae is taken into account. For example, the connection between the amphorae and the tank body is a key stress-bearing part, and the position-related weight of the feature points in this part is relatively high; while the center area of ​​the bottom of the tank body is less stressed under normal load conditions, and its position-related weight of the feature points is relatively low. When determining the structural impact score, the degree of influence of the geometric dimension changes of each feature point on the overall deformation of the amphorae is analyzed. For example, changes in the cross-sectional dimensions of the amphorae will directly affect their bearing capacity, and thus have a greater impact on the deformation of the tank body, and the structural impact score of this feature point will be higher; while a small dimensional deviation in a non-critical part of the tank surface will have little impact on the overall deformation, and its structural impact score will be lower.

[0033] The critical observation stages of the amphora are determined based on the load cycle period in the operating environment data. The load cycle period is the time it takes for the load to change from one state to its initial state after a series of changes. During the load cycle period, the stress state of the amphora undergoes periodic changes, and the deformation varies at different stages. By analyzing the load cycle period, we can identify the stages where the amphora's deformation is likely to be most significant. These stages are designated as critical observation stages. For example, the stage when the load reaches its maximum value and the stage when the load begins to unload from its maximum value may be critical observation stages. Next, based on the load cycle period and the amphora's critical observation stages, we determine the deformation attenuation coefficient. The deformation attenuation coefficient describes the time-dependent attenuation of the amphora's deformation after a load cycle. By analyzing historical monitoring data, we establish a relationship model between the load cycle period, critical observation stages, and the deformation attenuation coefficient, thereby determining the corresponding deformation attenuation coefficient.

[0034] After obtaining the position-related weights, structural influence scores, deformation attenuation coefficients, and mechanical distribution characteristics, we begin constructing a multidimensional feature vector. This multidimensional feature vector contains feature information from multiple dimensions and can comprehensively describe the deformation characteristics of the amphora. The position-related weights, structural influence scores, deformation attenuation coefficients, and mechanical distribution characteristics, such as stress and strain, are used as components of a vector to form a multidimensional vector space. The position and weight of each feature in the vector are determined based on its influence on the amphora's deformation, allowing the multidimensional feature vector to accurately reflect the actual deformation characteristics of the amphora.

[0035] Based on the constructed multidimensional feature vector, a matching search is performed against a pre-set database of historical deformation cases. This database contains a large number of previously processed amphora deformation cases, each of which includes a corresponding multidimensional feature vector and compensation solution. By calculating the similarity between the currently constructed multidimensional feature vector and the case feature vectors in the database, historical cases with high similarity are identified. Based on the compensation solutions corresponding to these similar cases, an initial compensation feature library is determined and output. This initial compensation feature library contains preliminary compensation strategies and related parameters for the current amphora deformation situation.

[0036] Example 2: In the implementation method of constructing a multi-dimensional feature vector, it is necessary to determine the structural weight parameter based on the degree of dimensional deviation of the structural geometric feature. The dimensional deviation of the structural geometric feature refers to the difference between the actual structural dimensions and the designed dimensions of the amphorae. For different structural parts, the degree of influence of the dimensional deviation on the overall deformation is different. For example, the wall thickness deviation of the tank body will directly affect its bearing capacity. If the wall thickness is less than the design value, it may cause the tank body to be more easily deformed under the action of load. Therefore, the greater the degree of dimensional deviation of the structural feature, the higher the corresponding structural weight parameter; and the dimensional deviation of a non-critical part of the bottom of the amphorae has a relatively small effect on the overall deformation, and the increase in its structural weight parameter is also relatively low. When determining the structural weight parameter, it is necessary to establish a quantitative relationship between the degree of dimensional deviation and the weight parameter. By analyzing and summarizing a large amount of historical data, a corresponding mapping rule is formed so that the structural weight parameter can accurately reflect the degree of influence of dimensional deviation on deformation.

[0037] The mechanical weighting parameters are determined based on the degree of stress concentration in the mechanical distribution characteristics. Stress concentration refers to the phenomenon where stress values ​​in certain parts of an amphora structure are significantly higher than the average stress due to factors such as its geometry and load. Regions with higher stress concentration are more susceptible to plastic deformation or even fracture, and their impact on the amphora's deformation is greater. To determine the mechanical weighting parameters, it is necessary to first analyze the stress distribution of the amphora under different operating conditions using methods such as finite element analysis, identify areas of stress concentration, and calculate the stress concentration factor for each area. The stress concentration factor is an important indicator of stress concentration; a higher value indicates a higher degree of stress concentration. The corresponding mechanical weighting parameters are then determined based on the stress concentration factor. For example, the junction between the amphora and the tank body is often an area of ​​significant stress concentration. If the stress concentration factor in this area is high, the mechanical weighting parameter is also high. On the other hand, the stress distribution in the main body of the tank is relatively uniform, with a lower stress concentration factor and a lower mechanical weighting parameter. In this way, the mechanical weighting parameters can accurately reflect the impact of the mechanical distribution characteristics on the deformation of the amphora.

[0038] The environmental weighting parameter is determined based on the rate of change of the temperature-dependent environmental characteristic. The rate of change of the temperature-dependent environmental characteristic refers to the speed at which the ambient temperature changes over time. Rapid temperature changes cause the material of the amphora to expand and contract. When the temperature change rate is too rapid, significant thermal stress is generated within the material, causing deformation of the amphora. Different rates of temperature change have varying degrees of impact on the deformation of the amphora. The faster the rate of change, the greater the impact and the higher the corresponding environmental weighting parameter. To determine the environmental weighting parameter, temperature monitoring data must be processed to calculate the temperature change per unit time, i.e., the temperature change rate. Based on the temperature change rate, the corresponding environmental weighting parameter is determined using pre-set rules or models. For example, when the temperature change rate exceeds a certain threshold, the environmental weighting parameter will increase significantly; whereas, when the temperature change rate is lower, the increase in the environmental weighting parameter will be smaller.

[0039] After obtaining the structural, mechanical, and environmental weight parameters, along with the previously determined deformation attenuation coefficient, these parameters need to be weighted and fused to form a composite feature vector encompassing the structural, mechanical, and environmental dimensions. This weighted fusion process considers the influence of each parameter on the deformation of the amphora, assigning appropriate weight coefficients to each parameter based on the application scenario and actual requirements. The structural dimension primarily reflects the influence of structural geometry on deformation, the mechanical dimension reflects the role of mechanical distribution characteristics, the environmental dimension considers the influence of temperature variations, and the deformation attenuation coefficient describes the decay of deformation over time. During the fusion process, the structural, mechanical, and environmental weight parameters are first multiplied by their respective weight coefficients and then combined with the deformation attenuation coefficient to form a multidimensional vector. For example, the weight coefficient for the structural weight parameter can be set to 0.3, the weight coefficient for the mechanical weight parameter to 0.4, the weight coefficient for the environmental weight parameter to 0.2, and the weight coefficient for the deformation attenuation coefficient to 0.1. This weight distribution allows the composite feature vector to comprehensively account for factors from all dimensions and fully describe the deformation characteristics of the amphora.

[0040] During the weighted fusion process, it's important to ensure that the weighting coefficients are both reasonable and scientifically sound. These can be determined through expert experience, statistical analysis of historical data, and other methods. For example, by analyzing a large number of amphora deformation cases, the influence of structural, mechanical, and environmental factors on deformation under different operating conditions can be determined, providing a basis for setting the weighting coefficients. Furthermore, the correlation between various parameters must be considered to avoid duplicate calculations or omission of important information.

[0041] After the composite feature vector is formed, it needs to be verified and optimized. This can be done by applying the composite feature vector to a known amphora deformation case to observe how well it describes the deformation characteristics. If the composite feature vector accurately reflects the deformation characteristics of the case, then the weight coefficient setting and fusion process are reasonable. If there are deviations, the weight coefficients need to be adjusted and optimized until the composite feature vector meets the requirements.

[0042] Example 3: In an implementation method of determining the compensation model update information set based on the dynamic optimization operation fed back by the initial compensation feature library, it is necessary to build a real-time deformation visualization interface for the deformation monitoring system based on the initial compensation feature library. The interface needs to integrate the structural parameters of the amphorae and the real-time monitoring data, and present the deformation state of the amphorae in the form of a three-dimensional model or a dynamic curve graph. For example, the deformation levels of different areas are marked by color coding, the red area represents the part with a larger deformation variable, and the green area represents the part with a smaller deformation variable. At the same time, the displacement data, stress change trend and other information of the key feature points are displayed in real time on the interface. When the system obtains a new monitoring data trajectory, it is necessary to synchronously update the feature space mapping effect, that is, adjust the distribution of the feature vector in the multidimensional space according to the new data, so that the visualization interface can reflect the latest deformation characteristics of the amphorae in real time, and provide intuitive data support for subsequent dynamic optimization.

[0043] Pattern clustering analysis is performed on the monitoring data trajectory to identify potential deformation characteristics. In specific implementation, the monitoring data trajectory is first divided into time windows. The length of the time window needs to be determined based on the load cycle period and the key observation stage. For example, if the load cycle period is 10 minutes, the time window can be set to 1 minute to capture the deformation characteristics of different stages within each cycle. Within each time window, the deformation fluctuation amplitude and frequency characteristics are extracted. The deformation fluctuation amplitude refers to the difference between the maximum and minimum values ​​of the deformation variable within the time period, and the frequency is the number of times the deformation variable changes significantly.

[0044] The initial classification criteria for the clustering algorithm are set to a historical high compensation demand case feature library, which stores feature vectors of cases that previously required high compensation efforts. Clustering iterations are performed by calculating the degree of match between the deformation fluctuation amplitude and frequency extracted within the current time window and the initial classification criteria. This match can be calculated using methods such as Euclidean distance and cosine similarity. For example, for two feature vectors, the square root of the sum of the squares of the differences in their corresponding dimensions is calculated; smaller values ​​indicate a higher degree of match. During the iteration process, the cluster centers are continuously adjusted until the clustering results stabilize or the preset number of iterations is reached.

[0045] The reliability of the clustering results is assessed by classification purity, which refers to the proportion of samples belonging to the same category in each cluster. For example, if more than 80% of the samples in a cluster belong to cases with historically high compensation demands, the purity of the cluster is considered high. Cluster groups whose matching degree with historically high compensation features exceeds a preset critical value (such as 0.7), which can be set according to actual application requirements, are selected, and the corresponding feature combinations are identified as potential deformation features of the amphorae. These potential features may be caused by new load conditions, environmental changes, and other factors, and are not yet covered by the initial compensation feature library.

[0046] After identifying potential deformation features, the sorting priority of the initial features needs to be dynamically adjusted and a feature update plan needs to be generated. The sorting priority of the initial features is originally determined based on factors such as structural geometry and mechanical distribution characteristics. When potential deformation features are discovered, the degree of impact of these new features on the deformation of the amphora needs to be evaluated. For example, if the deformation variable corresponding to a potential feature is large and occurs frequently, its priority should be raised to a higher position in the initial features. By adjusting the sorting priority of features, the compensation model can pay more attention to features that have a greater impact on deformation, thereby improving the accuracy of compensation. The feature update plan must clearly list the potential features to be added, the feature priorities to be adjusted, and the corresponding parameter settings.

[0047] The feature update scheme is analyzed and the stability of the compensation model is evaluated. First, parameters such as the number of feature dimensions, compensation confidence interval, historical compensation result distribution, and feature importance ranking are extracted. The number of feature dimensions refers to the number of features considered by the model, the compensation confidence interval indicates the reliable range of the compensation results, the historical compensation result distribution reflects the effectiveness of previous compensation, and the feature importance ranking reflects the impact of each feature on compensation.

[0048] Based on the structural properties of each feature, the model's compensation error tolerance threshold, historical compensation accuracy ratio, and continuous compensation consistency rate are determined. The compensation error tolerance threshold refers to the maximum allowable compensation error range. For example, for the deformation of key parts, the error tolerance threshold can be set to ±0.1mm. The historical compensation accuracy ratio refers to the proportion of historical compensation cases where the error is within the tolerance threshold. The continuous compensation consistency rate refers to the proportion of consistent results in multiple consecutive compensations.

[0049] Based on the number of feature dimensions, compensation confidence intervals, and the distribution of historical compensation results, combined with feature importance ranking and compensation error tolerance thresholds, statistical stability judgment criteria are constructed. For example, the correlation between the number of feature dimensions and the compensation confidence interval is calculated. If the compensation confidence interval decreases as the number of feature dimensions increases, it indicates that the stability of the model may be improved. The matching degree between the distribution of historical compensation results and the feature importance ranking is analyzed. If the compensation results of important features deviate significantly, the stability of the model may be affected. The statistical stability of the model is judged by setting critical ranges for statistical stability, such as the number of feature dimensions being between 5 and 10 and the compensation confidence interval not exceeding ±5%.

[0050] Determine the effective time range of model compensation based on the load cycle and the key observation phase of the amphorae. For example, during the key observation phase within the load cycle, the effective time range of model compensation is from the start time to the end time of that phase. Based on the historical compensation accuracy ratio and the effective time range, combined with the continuous compensation consistency rate and feature importance ranking, construct the time series stability judgment condition. Calculate the fluctuation range of the historical compensation accuracy ratio within the effective time range. If the fluctuation range is small, it means that the model has good stability in the time series; analyze the time series correlation between the continuous compensation consistency rate and the feature importance ranking. If the continuous compensation consistency rate of important features is high, the model has high time series stability. Set the critical range of time series stability, such as the fluctuation range of the historical compensation accuracy ratio does not exceed 10%, the continuous compensation consistency rate is not less than 80%, etc., to judge the time series stability of the model.

[0051] Based on the statistical stability and temporal stability criteria, the system determines whether the statistical stability or temporal stability of the current feature update scheme meets the requirements. If so, the updated model is considered to have good stability; if not, the feature update scheme needs to be adjusted. The judgment conclusion is used as model stability feedback, and corresponding feature optimization suggestions are fed back to the control end, such as increasing the weight of a certain feature or adjusting the setting of a certain parameter.

[0052] After receiving the adjustment confirmation instruction, the control end determines the compensation model update information set based on the instruction. The compensation model update information set must include the feature update plan, model stability feedback information, and adjusted parameter settings.

[0053] Example 4: In the implementation method of evaluating the stability of the compensation model, it is necessary to extract the number of feature dimensions of the model, the compensation confidence interval, the distribution of historical compensation results and the feature importance ranking based on the feature update scheme. The number of feature dimensions refers to the total number of feature parameters included in the current compensation model, such as the number of specific features of different dimensions such as structural geometric features, mechanical distribution features, and temperature change environment features. The compensation confidence interval is a range indicator used to measure the reliability of the compensation result. For example, the confidence interval of a certain deformation variable compensation value is ±0.5mm, indicating that the actual deformation variable has a high probability of falling within this interval. The distribution of historical compensation results is a statistical analysis of the results of all past compensation cases, showing distribution states such as the proportion of the number of cases under different compensation accuracies. The feature importance ranking is a priority ranking based on the degree of influence of each feature on the compensation result. For example, the stress concentration feature at the double-ear connection may be ranked higher, while the size features of non-critical parts of the tank body are ranked relatively low.

[0054] The compensation error tolerance threshold, historical compensation accuracy ratio and continuous compensation consistency rate of the model are determined based on the structural properties of each feature. The compensation error tolerance threshold needs to be set in combination with the functional importance and structural safety of the part where the feature is located. For example, for the binaural part that directly bears the main load, the compensation error tolerance threshold of its deformation may be set to ±0.1mm, while the threshold of the non-stress critical area of ​​the tank side wall can be relaxed to ±0.5mm. The historical compensation accuracy ratio is obtained by counting the number of cases in which the compensation result error is within the corresponding tolerance threshold in historical compensation cases and the ratio of the total number of cases. For example, in 100 historical cases, the compensation error of 85 cases is within the threshold range, and the accuracy ratio is 85%. The continuous compensation consistency rate is the ratio of the results of the same feature in multiple consecutive compensations that are consistent with expectations and each other. For example, if a feature has consistent results in 9 out of 10 consecutive compensations, the consistency rate is 90%.

[0055] Based on the number of feature dimensions, compensation confidence interval, and historical compensation result distribution, combined with feature importance ranking and compensation error tolerance threshold, statistical stability judgment conditions are constructed. In specific implementation, the correlation between the number of feature dimensions and the compensation confidence interval is first calculated. For example, by analyzing historical data, it is found that when the number of feature dimensions is between 8 and 12, the fluctuation range of the compensation confidence interval is the smallest, thus determining this number range as the optimal range. At the same time, the matching degree between the historical compensation result distribution and the feature importance ranking is analyzed. If the proportion of features with high importance ranking showing large deviations in the compensation result distribution is high, it indicates that there may be problems with the statistical stability of the model. Combined with the compensation error tolerance threshold, a critical range of statistical stability is set. For example, the number of feature dimensions needs to be maintained at 6-15, the upper limit of the compensation confidence interval must not exceed ±8%, and the deviation rate of important features in the historical compensation results must be less than 15%. When these conditions are met at the same time, it can be determined that the statistical stability of the model meets the requirements.

[0056] At the same time, the effective time range of model compensation is determined based on the load cycle and the amphora's critical observation period. The load cycle refers to the time span from the start to the end of a complete load cycle. For example, if the load cycle of an amphora is 24 hours, the peak load period (e.g., 8:00-10:00 AM daily) is the critical observation period. In this case, the effective time range of model compensation is the specific time period of this peak period.

[0057] Based on the historical compensation accuracy ratio and the effective time range, combined with the continuous compensation consistency rate and the feature importance ranking, the time series stability judgment condition is constructed. First, the fluctuation range of the historical compensation accuracy ratio within the effective time range is calculated. For example, in the key observation phase of the past 10 load cycles, the historical compensation accuracy ratio fluctuated between 75% and 85%, and the fluctuation range was 10%. Then, the time series correlation between the continuous compensation consistency rate and the feature importance ranking was analyzed. If the consistency rate of the highly important features in the continuous compensation shows a significant downward trend, it may indicate that the stability of the model in the time series has deteriorated. By setting the critical range of time series stability, such as the fluctuation range of the historical compensation accuracy ratio within the effective time range does not exceed 15%, the continuous compensation consistency rate is not less than 70% for important features, and the overall consistency rate is not less than 80%, etc., this is used as the basis for judging time series stability.

[0058] After establishing the criteria for determining statistical stability and temporal stability, a comprehensive assessment of the stability of the current feature update scheme is required. Each critical indicator for statistical stability is verified, for example, to determine whether the number of feature dimensions is within the preset range, whether the compensation confidence interval exceeds the upper limit, and whether the deviation rate of important features in historical compensation results meets the requirements. Furthermore, various conditions for temporal stability are checked, such as whether the fluctuation in the accuracy ratio within the effective time range is within the allowable range and whether the continuous compensation consistency rate reaches the critical value.

[0059] If both the statistical stability and temporal stability criteria are met, the current feature update scheme will not significantly negatively impact model stability. If one or more of these criteria are not met, the model stability risk is determined and further adjustments to the feature update scheme are necessary. This judgment is ultimately used as model stability feedback, which should clearly indicate the model's stability at both the statistical and temporal levels, as well as specific factors that may affect stability, such as an excessive number of feature dimensions or a low consistency rate for continuous compensation of a key feature.

[0060] Throughout the evaluation process, the accuracy of data extraction must be ensured. For example, the distribution of historical compensation results must be based on a sufficient number of valid cases, and the feature importance ranking must be scientifically evaluated in combination with actual force analysis and structural functions. At the same time, the setting of the critical range must refer to industry standards, historical experience, and the specific usage scenarios of the amphorae to ensure the scientificity and rationality of the stability assessment. In addition, when it is found that the stability does not meet the requirements, it is necessary to promptly trace back to the specific problem points in the feature update plan, such as whether too many non-critical features have been added, causing the number of feature dimensions to exceed a reasonable range, or whether the parameter settings of an important feature have been adjusted, resulting in a decrease in the continuous compensation consistency rate, etc., to provide an accurate basis for subsequent feature optimization suggestions, thereby ensuring that the compensation model can maintain good stability after the update, and continue to provide reliable support for the deformation compensation of amphorae.

[0061] In the implementation of determining the adaptive compensation scheme based on the compensation resource configuration information set and the target compensation parameter, the target compensation parameter needs to be parsed based on the compensation resource configuration information set to determine the target compensation resource corresponding to each feature optimization item. The compensation resource configuration information set includes information such as the type, specification, quantity, and technical parameters of the compensation resources available in the organization, such as different types of compensation pads, various stress release devices, temperature control equipment, etc. The target compensation parameter is obtained by hierarchical disassembly and classification statistics of the compensation model update information set, involving structural geometric feature optimization parameters, mechanical distribution adjustment parameters, temperature change environment adaptation parameters, etc. Taking a feature optimization item "stress concentration compensation at the double-ear connection" as an example, the corresponding target compensation resources after parsing may include wedge-shaped compensation pads A, flexible stress release sheets B, and local heating control devices C, etc. These resources all have potential compensation ability for the feature optimization item.

[0062] From the compensation resource configuration information set, the historical cooperation records corresponding to each target compensation resource are extracted to determine the historical application times, historical optimization cost, historical compensation accuracy ratio, and historical execution risk of the current organization for each feature optimization item under the corresponding target compensation resource. The historical cooperation record is a summary of past cases using the resource for compensation, for example, the target compensation resource "wedge-shaped compensation pad A" in the feature optimization item "stress concentration compensation at the double-ear connection", the historical application times is 50 times, the material cost, labor cost, etc. of each application constitutes the historical optimization cost, of which 40 times of compensation results meet the error tolerance threshold, the historical compensation accuracy ratio is 80%, and there are 3 times of historical execution risk events of installation position deviation in the past application. These data need to be systematically sorted and counted through the historical project archives, resource use account book, etc. of the organization to ensure the integrity and accuracy of the data.

[0063] After obtaining the historical application times, historical optimization cost, historical compensation accuracy ratio, and historical execution risk, a comprehensive cost optimization process is performed for each feature optimization item. In specific implementation, the weighted sum of the historical application times and the historical optimization cost is calculated as the resource use cost indicator. The historical application times reflects the popularity and maturity of the resource in actual application, and resources with more application times may have advantages in procurement cost, operation proficiency, etc.; the historical optimization cost directly reflects the economic input of using the resource. For example, if the weight of the historical application times is set to 0.3 and the weight of the historical optimization cost is set to 0.7, the historical application times of a certain target compensation resource is 50 times (converted to a standardized value of 0.8), and the historical optimization cost is 1000 yuan (standardized value of 0.6), then the resource use cost indicator is 0.3x0.8+0.7x0.6=0.66.

[0064] The weighted sum of the historical compensation accuracy ratio and the historical execution risk is calculated as the performance risk cost indicator. The historical compensation accuracy ratio reflects the reliability of the compensation effect of the resource; a higher ratio indicates a more stable effect. The historical execution risk reflects the operational and security risks that may be faced by using the resource. The more risk events occur, the higher the risk level. For example, if the weight of the historical compensation accuracy ratio is set to 0.6 and the weight of the historical execution risk is set to 0.4, and the historical compensation accuracy ratio of a resource is 80% (normalized to 0.8) and there have been three historical execution risk events (normalized to 0.3, with lower values ​​indicating higher risk), the performance risk cost indicator is 0.6 × 0.8 + 0.4 × 0.3 = 0.6.

[0065] A comprehensive comparison is performed between the resource usage cost indicator and the effect risk cost indicator, and the compensation resource with the lowest comprehensive cost is selected as the optimal resource. The comprehensive cost is calculated by weighting the two indicators. For example, if the weight of the resource usage cost indicator is 0.5 and the weight of the effect risk cost indicator is 0.5, the comprehensive cost of a resource is 0.5 × 0.66 + 0.5 × 0.6 = 0.63. This calculation is performed for all target compensation resources corresponding to each feature optimization item, and the resource with the lowest comprehensive cost is selected as the optimal compensation resource for that feature optimization item.

[0066] When converting standardized values, a unified quantitative standard must be established. For example, historical application times can be standardized by the ratio of actual applications to the maximum application times within the organization; historical optimization costs can be standardized by the ratio of actual costs to minimum costs (or by cost range grading); historical compensation accuracy ratios can be directly converted to a standardized value between 0 and 1 as a percentage; historical execution risk can be converted to a standardized value by the ratio of risk events to total applications (or by risk level grading). The more risk events, the higher the standardized value (or the lower, depending on the indicator definition).

[0067] The weighting process should consider factors such as the application scenario of the amphorae and the priority of compensation needs. For example, in industrial scenarios with extremely high safety requirements, the weighting of historical compensation accuracy and historical execution risk can be appropriately increased to ensure the reliability of compensation and operational safety. For cost-sensitive scenarios, the weighting of historical optimization costs can be increased to achieve optimal economic performance. Weighting can be determined through methods such as expert evaluation and the Delphi method to ensure the scientific and reasonable weight distribution.

[0068] After determining the optimal compensation resource for each feature optimization item, these optimal resources are combined to construct an adaptive compensation plan. The plan must clearly define the optimal compensation resource for each feature optimization item, how the resource is used, installation parameters, operating procedures, and other content. For example, for the feature optimization item "stress concentration compensation at the double-ear connection," the optimal resource is "flexible stress relief sheet B." The plan must specify the specific parameters of the relief sheet, such as its installation location, fixing method, and preload requirements, as well as precautions and quality inspection standards during installation.

[0069] The completed adaptive compensation scheme requires feasibility verification. Simulations and small-scale tests can be used to verify whether the various compensation resource combinations in the scheme can achieve the desired compensation effect and whether there are any resource conflicts or compatibility issues. For example, finite element simulation analysis can be used to verify the effectiveness of using "Flexible Stress Relief Sheet B" to alleviate stress concentration at the lug joint, ensuring that its deformation and stress distribution meet design requirements.

[0070] Throughout the implementation process, the accuracy and completeness of historical data must be ensured to avoid miscalculations of comprehensive costs due to data bias. Furthermore, consistent and interpretable weighting and normalization conversion methods must be implemented to ensure fair comparisons between different feature optimization items and compensation resources. Furthermore, the adaptive compensation scheme must be operational and adjustable, capable of dynamic optimization based on unexpected situations or new monitoring data in actual applications, ensuring optimal compensation for amphora deformation.

[0071] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0072] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent deformation compensation method for a two-ear jar, characterized in that: include: collecting amphora structural parameters and operating environment data, analyzing the amphora structural parameters and operating environment data, constructing a deformation feature set, and determining and outputting an initial compensation feature library; Determine the compensation model update information set based on the dynamic optimization operation fed back by the initial compensation feature library; Parsing the compensation model update information set, performing hierarchical decomposition and classification statistics on the compensation model update information set, and determining target compensation parameters; A compensation resource configuration information set is obtained, and based on the compensation resource configuration information set and in accordance with the target compensation parameters, an adaptive compensation scheme is determined and output.

2. The intelligent deformation compensation method for amphorae according to claim 1 is characterized in that: The analyzing the amphora structural parameters and the operating environment data, constructing a deformation feature set, and determining and outputting an initial compensation feature library includes: Analyzing the structural parameters of the amphorae and the operating environment data to extract the structural geometric feature groups, mechanical distribution features, and temperature change environment features; Analyzing the structural geometric feature group to determine the position association weight and structural impact score corresponding to each feature point; determining a key observation phase of the amphora according to the load cycle period in the operating environment data, and determining a deformation attenuation coefficient according to the load cycle period and the key observation phase of the amphora; constructing a multidimensional feature vector according to the position association weight, the structural influence score, the deformation attenuation coefficient, and the mechanical distribution characteristics; According to the multi-dimensional feature vector, a matching search is performed on a preset historical deformation case database to determine and output the initial compensation feature library.

3. The intelligent deformation compensation method for amphorae according to claim 2 is characterized in that: The method of constructing a dynamic load-bearing structure according to the position association weight, the structural influence score, the deformation attenuation coefficient and the mechanical distribution characteristics is described. Multidimensional feature vectors, specifically including: The structural weight parameters are determined according to the dimensional deviation degree of the structural geometric characteristics, the mechanical weight parameters are determined according to the stress concentration degree of the mechanical distribution characteristics, and the environmental weight parameters are determined according to the change rate of the temperature change environmental characteristics; The structural weight parameter, mechanical weight parameter, environmental weight parameter and deformation attenuation coefficient are weighted and fused to form a composite feature vector including structural dimension, mechanical dimension and environmental dimension.

4. The intelligent deformation compensation method for amphorae according to claim 2, characterized in that: The dynamic optimization operation based on the feedback of the initial compensation feature library determines the compensation model update information set, including: Based on the initial compensation feature library, a real-time deformation visualization interface is provided for the deformation monitoring system, and the feature space mapping effect is synchronously updated according to the monitoring data trajectory fed back by the system; Based on the monitoring data trajectory, potential deformation features of the amphora are identified through pattern clustering analysis, the sorting priority of the initial features is dynamically adjusted, and a feature update plan is generated; Analyze the feature update scheme, evaluate the stability of the compensation model, determine model stability feedback information, and feed back corresponding feature optimization suggestions to the control end, and receive adjustment confirmation instructions; According to the adjustment confirmation instruction, a compensation model update information set is determined.

5. The intelligent deformation compensation method for amphora according to claim 4 is characterized in that: The analyzing the feature update scheme, evaluating the stability of the compensation model, and determining model stability feedback information include: According to the feature update scheme, the number of feature dimensions, compensation confidence interval, historical compensation result distribution and feature importance ranking of the model are extracted; According to the structural properties of each feature, the compensation error tolerance threshold, historical compensation accuracy ratio and continuous compensation consistency rate of the model are determined; Based on the number of feature dimensions, the compensation confidence interval, and the historical compensation result distribution, and according to the feature importance ranking and the compensation error tolerance threshold, a statistical stability determination condition is established; determining an effective time range of model compensation according to the load cycle and the key observation phase of the amphora; Based on the historical compensation accuracy ratio and the effective time range, and according to the continuous compensation consistency rate and the feature importance ranking, a time series stability judgment condition is established; According to the statistical stability judgment condition and the temporal stability judgment condition, it is judged whether the statistical stability or temporal stability corresponding to the current feature update scheme meets the requirements, and a judgment conclusion is determined, which is used as the model stability feedback information.

6. The intelligent deformation compensation method for amphora according to claim 5 is characterized in that: The statistical stability judgment condition is constructed based on the number of feature dimensions, the compensation confidence interval, and the historical compensation result distribution, according to the feature importance ranking and the compensation error tolerance threshold, and specifically includes: Calculate the correlation between the number of feature dimensions and the compensation confidence interval, analyze the matching degree between the distribution of historical compensation results and the feature importance ranking, and set the critical range of statistical stability in combination with the compensation error tolerance threshold; The time series stability determination condition is constructed based on the historical compensation accuracy ratio and the effective time range, according to the continuous compensation consistency rate and the feature importance ranking, and specifically includes: Calculate the fluctuation range of the historical compensation accuracy ratio within the effective time range, analyze the temporal correlation between the continuous compensation consistency rate and the feature importance ranking, and set the critical range of temporal stability.

7. The intelligent deformation compensation method for amphora according to claim 6, characterized in that: The parsing of the compensation model update information set, performing hierarchical decomposition and classification statistics on the compensation model update information set, and determining target compensation parameters includes: Update the information set according to the compensation model, and calculate the key feature optimization set and the auxiliary parameter adjustment set; According to the model update period set by the mechanism, the load cycle periods corresponding to different amphorae in the compensation model update information set are divided into a number of update batches to determine an update batch information set; Based on the update batch information set, the key feature optimization set is parsed, and according to the parameter drift ratio corresponding to each feature in the key feature optimization set in the historical update records, the parameter redundancy corresponding to each feature in each update batch is determined; The target compensation parameter is constructed according to the auxiliary parameter adjustment set, the update batch information set and the parameter redundancy.

8. The intelligent deformation compensation method for amphora according to claim 7, characterized in that: The determining and outputting an adaptive compensation scheme based on the compensation resource configuration information set and in accordance with the target compensation parameter includes: parsing the target compensation parameters based on the compensation resource configuration information set, and determining a number of target compensation resources corresponding to each characteristic optimization item in the target compensation parameters; Extract the historical collaboration records corresponding to each target compensation resource based on the compensation resource configuration information set, thereby determining the historical application times, historical optimization costs, historical compensation accuracy ratios, and historical execution risks of each feature optimization item under the corresponding target compensation resource by the current organization; Based on the historical application times, historical optimization costs, historical compensation accuracy ratio and historical execution risks of each feature optimization item under the corresponding target compensation resources, comprehensive cost optimization processing is performed on each feature optimization item to determine the optimal compensation resources corresponding to each feature optimization item, thereby constructing and outputting the adaptive compensation plan.

9. The intelligent deformation compensation method for amphora according to claim 8, characterized in that: The comprehensive cost optimization process is performed on each feature optimization item based on the historical application times, the historical optimization cost, the historical compensation accuracy ratio, and the historical execution risk of each feature optimization item under the corresponding target compensation resource, specifically including: Calculate the weighted sum of the number of historical applications and the historical optimization cost as the resource usage cost indicator, and calculate the weighted sum of the historical compensation accuracy ratio and the historical execution risk as the effect risk cost indicator; The resource use cost index is comprehensively compared with the effect risk cost index, and the compensation resource with the lowest comprehensive cost is selected as the optimal resource.

10. The intelligent deformation compensation method for amphora according to claim 4, characterized in that: The method of identifying potential deformation characteristics of amphora through pattern cluster analysis includes: Dividing the monitoring data trajectory into time windows and extracting the deformation fluctuation amplitude and frequency within each time window; The initial classification standard of the clustering algorithm is set as the feature library of historical high compensation demand cases, and clustering iteration is performed based on the matching degree between the deformation fluctuation amplitude and frequency and the initial classification standard; The reliability of the clustering results was evaluated by classification purity, and cluster groups whose matching degree with historical high compensation features exceeded the preset critical value were screened out, and their corresponding feature combinations were identified as potential deformation features of the amphorae.

Images