Quality monitoring system and method for insulation side expansion sleeve production

Abstract

The invention discloses a quality monitoring system and method for insulation side expansion sleeve production, and relates to the field of pipe quality monitoring. The method comprises the steps that S1, ultrasonic wall thickness, infrared temperature, capacitance signals and process parameters are collected; S2, the signals are normalized to generate enhanced signals, and local gradient anomaly indexes are calculated; s3, a flaring stress index is calculated according to the thickness value deviation and the technological parameters; s4, calculating coupling unevenness based on a local gradient anomaly index; s5, calculating a comprehensive quality factor according to the local gradient anomaly index, the flaring stress index, the coupling unevenness and the process parameter deviation; s6, generating an anomaly identifier based on the comprehensive quality factor dynamic deviation rate and adaptive threshold detection anomaly; s7, mapping the time sequence characteristic corresponding to the abnormal identifier to a space coordinate to output defect distribution information; and S8, according to the defect distribution information, generating process parameter adjustment quantity and feeding back to a control system.

Description

Technical Field

[0001] The present invention relates to the field of pipe quality monitoring, and in particular to a quality monitoring system and method for producing insulating side-expanded casing. Background Art

[0002] Insulated side-expanded casing is widely used in power equipment, chemical pipelines, and high-voltage transmission systems. Its forming quality directly impacts the product's sealing performance and service life. Current production processes typically rely on single sensors or manual spot checks to monitor casing quality. This leads to issues such as insufficient monitoring dimensions, low defect location accuracy, and delayed process adjustments. Especially during the expansion forming process, factors such as wall thickness deviation, temperature fluctuations, and abnormal dielectric properties all interact, making it difficult for traditional methods to achieve real-time, comprehensive, and adaptive monitoring of the production process.

[0003] In recent years, the development of multimodal sensing and intelligent data processing technologies has provided new insights into quality monitoring in casing production. However, existing solutions still lack the ability to effectively address quality fluctuations caused by multi-factor coupling, such as multi-source signal fusion, defect spatial mapping, and closed-loop process optimization. Therefore, a quality monitoring method and system that can fuse multimodal signals, accurately locate defects, and provide closed-loop process optimization capabilities is urgently needed to improve the stability and quality of insulated side-expanded casing production. Summary of the Invention

[0004] Based on the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a quality monitoring system and method for the production of insulating side expansion casing to solve the above-mentioned technical problems.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solution: a quality monitoring method for insulating side expansion casing production, comprising: S1: Collect multimodal sensor signals and process parameters during the production process. The multimodal sensor signals include ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals. S2: normalizing the multimodal sensing signals to generate enhanced normalized signals, and calculating the local gradient anomaly index of each modality based on the enhanced normalized signals; S3: Calculate the expansion stress index based on the deviation between the ultrasonic wall thickness signal and the reference wall thickness value and the process parameters; S4: Based on the local gradient anomaly index, the coupling analysis of different modal sensing signals is performed to calculate the multimodal coupling unevenness; S5: Calculate the comprehensive quality factor based on the local gradient anomaly index, flaring stress index and multimodal coupling non-uniformity, combined with the process parameter deviation; S6: Based on the dynamic deviation rate of the comprehensive quality factor and the adaptive threshold, anomaly detection is performed on the production status and an anomaly flag is generated; S7: Mapping the multi-source time series features corresponding to the abnormal identification to the spatial coordinates of the casing, and outputting the spatial distribution information of the defects; S8: Generate process parameter adjustment values ​​based on the spatial distribution information of defects, feed the process parameter adjustment values ​​back to the production control system, and perform closed-loop optimization control on the production process.

[0006] The present invention is further configured such that S2 includes: Independent normalization processing of ultrasonic wall thickness signal, infrared temperature signal and capacitance signal; Perform fractional power weighting processing on the signal sequence within the preset historical time window of each sensing modality, and fuse the current signal normalization result of each sensing modality with the corresponding historical signal weighted processing result to generate an enhanced normalized signal; Based on the enhanced normalized signal of each sensing modality, the local gradient anomaly index of each sensing modality is generated by calculating the ratio of the signal energy change to the signal change intensity within a preset sliding time window.

[0007] The present invention is further configured such that S3 includes: According to the enhanced normalized ultrasonic wall thickness signal at each measurement position and the corresponding reference wall thickness value, the wall thickness deviation between the current ultrasonic wall thickness signal and the reference wall thickness value is calculated, and the wall thickness deviation is nonlinearly amplified; Obtain the process difference between the real-time process parameters and the local equivalent process parameters at each measurement position, and perform nonlinear adjustment processing on the process difference; Based on the nonlinearly amplified wall thickness deviation and the nonlinearly adjusted process difference, normalization processing is performed to obtain the local stress component at each measuring position; The local stress components at each measurement location are aggregated to generate the flaring stress index.

[0008] The present invention is further configured such that S4 includes: According to the local gradient anomaly index corresponding to each sensing mode, the anomaly difference between the local gradient anomaly indexes of any two different sensing modes is calculated, and nonlinear adjustment processing is performed on the anomaly difference; The local gradient anomaly indicators of two different sensing modes are nonlinearly weighted combined, and the weighted combination results are normalized using the nonlinearly adjusted anomaly difference to obtain the interactive coupling components corresponding to the two sensing modes. The interaction coupling components of all sensing mode pairs are aggregated to generate multimodal coupling inhomogeneity.

[0009] The present invention is further configured such that S5 includes: Performing a summation operation on the local gradient anomaly index of each sensing mode, and performing a first power transformation on the summation operation result; Performing a second power transformation on the expansion stress index, fusing the first power transformation result with the second power transformation result to generate a signal fusion factor; Perform third-power transformation and offset processing on the multi-modal coupling unevenness to generate the coupling impact factor; Calculate the absolute deviation between the real-time process parameters and the optimal process parameters, and perform exponential mapping on the absolute deviation to generate a process deviation penalty term; The first intermediate factor, coupling influence factor and process deviation penalty term are multiplied together to generate a comprehensive quality factor.

[0010] The present invention is further configured such that S6 includes: Calculate the dynamic deviation rate based on the continuous change of the comprehensive quality factor within the preset historical time window and the continuous change of the real-time process parameters within the preset historical time window; Calculate the adaptive threshold according to the current comprehensive quality factor, dynamic deviation rate and multi-modal coupling unevenness; The current comprehensive quality factor is compared with the adaptive threshold. If the current comprehensive quality factor is less than the adaptive dynamic threshold, an abnormal flag is generated.

[0011] The present invention is further configured such that S7 includes: Obtain the local gradient anomaly index and multimodal coupling unevenness of each sensing mode at the time point corresponding to the anomaly mark, as well as the enhanced normalized signal and corresponding reference signal of each sensing mode in the casing space coordinate; Calculate the signal deviation between the enhanced normalized signal of each sensing mode at each spatial coordinate and the corresponding reference signal, and perform nonlinear adjustment processing on the signal deviation; The local gradient anomaly index is nonlinearly amplified, and the nonlinearly adjusted signal deviation is used to normalize the nonlinearly amplified local gradient anomaly index to obtain the independent contribution of each sensing mode at each spatial coordinate; The independent contributions of all sensing modes are accumulated and summed to obtain the spatial contribution aggregation value; The spatial contribution aggregation value is fused with the multimodal coupling unevenness to generate a spatial mapping index; According to the numerical value and distribution of the spatial mapping index at each spatial coordinate, the spatial location and severity of the defect are determined, and the spatial distribution information of the defect is output.

[0012] The present invention is further configured such that S8 includes: Based on the spatial mapping index corresponding to the spatial distribution information of the defect, the spatial mapping index on all spatial coordinates is summed to generate the cumulative defect severity; Perform nonlinear transformation on current process parameters to generate process state adjustment factors; The process state adjustment factor is used to perform weighted modulation on the cumulative defect severity to generate the process parameter adjustment amount; Add the process parameter adjustment amount to the current process parameter to generate the optimized process parameter setting value; Feedback the optimized process parameter setting values ​​to the production control system to achieve closed-loop optimization control.

[0013] The present invention is further configured such that the multimodal sensing signals are collected by a distributed sensor array, and the sensor array is arranged along the axial direction and the circumferential direction of the casing.

[0014] The present invention also provides a quality monitoring system for insulating side expansion casing production, the system comprising: Signal acquisition module: used to collect multimodal sensor signals and process parameters during the production process. The multimodal sensor signals include ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals. Normalization anomaly module: used to normalize multimodal sensor signals to generate enhanced normalized signals, and calculate the local gradient anomaly index of each mode based on the enhanced normalized signals; Expanding stress evaluation module: used to calculate the expanding stress index based on the deviation between the ultrasonic wall thickness signal and the reference wall thickness value combined with the process parameters; Coupling analysis module: used to perform coupling analysis on different modal sensor signals based on local gradient anomaly indicators and calculate multi-modal coupling unevenness; Comprehensive quality assessment module: used to calculate the comprehensive quality factor based on the local gradient anomaly index, flaring stress index and multi-modal coupling non-uniformity, combined with process parameter deviation; Anomaly detection module: This module detects anomalies in production status and generates anomaly flags based on the dynamic deviation rate of the comprehensive quality factor and the adaptive threshold. Defect location module: used to map the multi-source time series features corresponding to the abnormal identification to the spatial coordinates of the casing and output the spatial distribution information of the defects; Closed-loop process control module: used to generate process parameter adjustments based on the spatial distribution information of defects, feed the process parameter adjustments back to the production control system, and perform closed-loop optimization control of the production process.

[0015] The present invention provides a quality monitoring system and method for the production of insulating side expansion casing. The method comprises the following steps: S1: collecting multimodal sensor signals and process parameters during the production process, wherein the multimodal sensor signals include ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals; S2: normalizing the multimodal sensor signals to generate enhanced normalized signals, and calculating the local gradient anomaly index of each mode based on the enhanced normalized signals; S3: calculating the expansion stress index based on the deviation between the ultrasonic wall thickness signal and the reference wall thickness value in combination with the process parameters; S4: performing coupling analysis on different modal sensor signals based on the local gradient anomaly index to calculate the expansion stress index. Multimodal coupling unevenness; S5: Calculate the comprehensive quality factor based on the local gradient anomaly index, flaring stress index and multimodal coupling unevenness, combined with the process parameter deviation; S6: Detect anomalies in the production status and generate anomaly identification based on the dynamic deviation rate and adaptive threshold of the comprehensive quality factor; S7: Map the multi-source time series features corresponding to the anomaly identification to the spatial coordinates of the casing and output the spatial distribution information of the defect; S8: Generate process parameter adjustments based on the spatial distribution information of the defect, and feed the process parameter adjustments back to the production control system for closed-loop optimization control of the production process. The beneficial effects produced include: 1. By synchronously collecting multimodal sensor data such as ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals, combined with real-time process parameters, and utilizing enhanced normalization and fractional-order weighting mechanisms to extract local anomaly indicators, the system constructs a comprehensive quality factor by calculating the flaring stress index and multimodal coupling unevenness. This achieves unified quantification and comprehensive evaluation of multi-source information in the production process, improving the integrity of data perception, the sensitivity of anomaly characteristics, and the accuracy of stress state representation. 2. By constructing a dynamic deviation rate and adaptive threshold, combined with a comprehensive quality factor, real-time quality anomaly detection is performed. A mapping relationship between anomaly time series characteristics and casing spatial coordinates is established to generate a spatial mapping index, thereby achieving precise spatial positioning and severity assessment of defects. This overcomes the limitation of traditional methods that can only provide overall anomaly signals but cannot represent spatial distribution, thereby improving the accuracy of anomaly detection and spatial diagnostic capabilities. 3. By feeding back the spatial distribution information of defects to the process control link, the process parameter adjustment amount is generated based on the cumulative amount of defect severity and the process state adjustment factor, thus achieving closed-loop adaptive optimization control of the production process. It can quickly intervene in significant defects while maintaining system stability, thereby improving the intelligence level of the production process and the overall quality stability.

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without inventive efforts. In the drawings: Figure 1 A flow chart of a quality monitoring method for insulating side expansion casing production is shown as an exemplary embodiment of the present invention; Figure 2 The figure is a schematic structural diagram of a quality monitoring system for insulating side expansion casing production according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following describes the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art will readily appreciate the other advantages and benefits of the present invention from the disclosure herein. The present invention may also be implemented or applied through various other specific embodiments, and the various details in this specification may be modified or altered based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are intended only to illustrate the present invention and are not intended to limit the scope of protection of the present invention.

[0019] It should be noted that the illustrations provided in the following embodiments are merely schematic illustrations of the basic concept of the present invention. Therefore, the illustrations only show components related to the present invention and are not drawn according to the number, shape, and size of components in actual implementation. In actual implementation, the type, quantity, and proportion of each component may be changed arbitrarily, and the component layout may also be more complex.

[0020] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the embodiments of the present invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring the embodiments of the present invention.

[0021] Example 1

[0022] Quality monitoring methods for insulating side expansion bushing production, such as Figure 1 Shown, including: S1: Collect multimodal sensor signals and process parameters during the production process. The multimodal sensor signals include ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals. S2: normalizing the multimodal sensing signals to generate enhanced normalized signals, and calculating the local gradient anomaly index of each modality based on the enhanced normalized signals; S3: Calculate the expansion stress index based on the deviation between the ultrasonic wall thickness signal and the reference wall thickness value and the process parameters; S4: Based on the local gradient anomaly index, the coupling analysis of different modal sensing signals is performed to calculate the multimodal coupling unevenness; S5: Calculate the comprehensive quality factor based on the local gradient anomaly index, flaring stress index and multimodal coupling non-uniformity, combined with the process parameter deviation; S6: Based on the dynamic deviation rate of the comprehensive quality factor and the adaptive threshold, anomaly detection is performed on the production status and an anomaly flag is generated; S7: Mapping the multi-source time series features corresponding to the abnormal identification to the spatial coordinates of the casing, and outputting the spatial distribution information of the defects; S8: Generate process parameter adjustment values ​​based on the spatial distribution information of defects, feed the process parameter adjustment values ​​back to the production control system, and perform closed-loop optimization control on the production process.

[0023] The present invention is further configured such that S2 includes: Independent normalization processing of ultrasonic wall thickness signal, infrared temperature signal and capacitance signal; Perform fractional power weighting processing on the signal sequence within the preset historical time window of each sensing modality, and fuse the current signal normalization result of each sensing modality with the corresponding historical signal weighted processing result to generate an enhanced normalized signal; Based on the enhanced normalized signal of each sensing mode, the local gradient anomaly index of each sensing mode is generated by calculating the ratio of the signal energy change to the signal change intensity within a preset sliding time window; specifically, during the casing production process, ultrasonic wall thickness signals, infrared temperature signals and capacitance signals are synchronously collected by a distributed sensor array. Each sensing signal corresponds to multiple measurement positions of the casing, achieving spatial coverage of the casing surface and wall thickness; ultrasonic wall thickness signals are detected by ultrasonic sensors arranged along the axial direction of the casing to detect the wall thickness of each measurement position, and the signal collected by each sensor corresponds to a specific spatial coordinate position of the casing; infrared temperature signals are collected by infrared sensors arranged along the circumference of the casing to collect the surface temperature of each measurement position, ensuring that the temperature changes at different positions during the production process are monitored and quantified in real time; capacitance signals are detected by infrared sensors arranged at key locations of the casing. Capacitive sensors in the forming area sense the local process status. Each collected signal corresponds to a specific spatial coordinate position of the sleeve to reflect the local dielectric properties and wall thickness changes. Each modal sensing signal is independently normalized to unify the numerical scale of each sensing mode and eliminate the dimensional differences between different physical quantities. The sensing modes include ultrasonic sensing mode, infrared temperature sensing mode, and capacitive sensing mode, which are used to respectively collect the sleeve's wall thickness signal, surface temperature signal, and capacitance signal of the sleeve's local dielectric properties and wall thickness changes. Within the historical time window of each sensing mode, the sensor signal sequence is subjected to fractional power weighting processing to enhance the characteristics of short-term abnormal responses. The current normalized signal of each sensing mode is fused with its corresponding historical weighted processing results to generate an enhanced normalized signal. The calculation logic of the enhanced normalized signal is as follows: ,in, For modal At the moment The enhanced normalized signal is used to unify the numerical scale of each sensing mode and amplify the short-term abnormal response. , Indicates ultrasonic wall thickness signal, Indicates infrared temperature signal, Represents capacitance signal; and Mode At the moment and The original signal; and For modal Minimum and maximum values ​​during the acquisition process; is the enhancement coefficient, which is used to control the influence strength of historical signals and its value range is [0.1, 0.5]; The preset historical time window length; It is the historical time index; is a fractional power exponent used to control the attenuation characteristics of historical signals, with a value range of [0.5, 0.8]; Normalization is used to map the signal to the range of [0,1] to eliminate the amplitude difference between modes; It is a historical weighted enhancement, which is used to perform fractional power accumulation on historical signals, amplify local anomalies and retain trend information; based on the enhanced normalized signal , at every moment The local gradient anomaly index is calculated within the preset sliding window of , and the local gradient anomaly index is used to describe the nonlinear change and energy offset of the signal within the local window; the calculation logic of the local gradient anomaly index is: ,in, For modal At the moment The local gradient anomaly index is used to quantify the fluctuation characteristics of the signal at the current moment and its adjacent time window, highlighting local anomalies or mutations; is the half length of the preset sliding time window; is the sliding time index; For modal At the moment The enhanced normalized signal of It is an adjustment parameter used to control the sensitivity of the calculation of the local gradient anomaly index, and its value range is [1.2, 1.8]; The signal energy change is used to reflect the change in signal energy between the current moment and the adjacent moment; It is the signal change intensity, which is used to quantify the absolute difference between the signal at the adjacent moment and the current moment, and characterize the local fluctuation intensity of the signal in a short time scale.

[0024] The present invention is further configured such that S3 includes: According to the enhanced normalized ultrasonic wall thickness signal at each measurement position and the corresponding reference wall thickness value, the wall thickness deviation between the current ultrasonic wall thickness signal and the reference wall thickness value is calculated, and the wall thickness deviation is nonlinearly amplified; Obtain the process difference between the real-time process parameters and the local equivalent process parameters at each measurement position, and perform nonlinear adjustment processing on the process difference; Based on the nonlinearly amplified wall thickness deviation and the nonlinearly adjusted process difference, normalization processing is performed to obtain the local stress component at each measuring position; The local stress components at each measurement position are aggregated to generate a flaring stress index. Specifically, during the casing production process, for each measurement position, an enhanced normalized ultrasonic wall thickness signal is obtained at the measurement position, compared with the reference wall thickness value at the corresponding position, the wall thickness deviation is calculated, and the wall thickness deviation is nonlinearly amplified to enhance the response of local stress to wall thickness changes. Local process parameters at the measurement position are collected and compared with real-time process parameters to calculate the process difference, and the process difference is nonlinearly adjusted to reflect the sensitivity of local stress to process fluctuations. The nonlinearly amplified wall thickness deviation and the nonlinearly adjusted process difference are normalized to obtain the local stress component at each measurement position. The local stress component is used to reflect the stress concentration at each measurement position during the flaring process. The local stress components at all measurement positions are aggregated to generate the flaring stress index of the casing. The flaring stress index is used to quantify the local stress distribution of the casing during the flaring process and reflect the severity of the local stress anomaly of the casing. The calculation logic of the flaring stress index is as follows: ,in, ; For the moment Space coordinates The enhanced normalized ultrasonic wall thickness signal at position The enhanced normalized ultrasonic wall thickness signal at the position is used to reflect the position The actual wall thickness; is the set of all measurement locations; is the spatial coordinate Reference wall thickness value at ; Indicates time Space coordinates The wall thickness deviation at is used to quantify the difference between the current wall thickness and the reference wall thickness, reflecting the thickness change caused by local stress; It is an adjustment parameter used to nonlinearly amplify or compress the wall thickness deviation and enhance the influence of the local stress concentration area. Its value range is [1.5,2]. Global real-time process parameters, such as flaring pressure, flaring motion speed, and flaring process temperature setting values, are used to provide a global reference for the current production process status; For the moment Space coordinates The estimated value of the local process parameter at can be derived by interpolation based on the sensor data; Indicates time Space coordinates The process difference at represents the amount by which the local process parameters deviate from the global process parameters; It is an adjustment parameter used to control the influence of process difference on the expansion stress index, and its value range is [0.8,1.2].

[0025] The present invention is further configured such that S4 includes: According to the local gradient anomaly index corresponding to each sensing mode, the anomaly difference between the local gradient anomaly indexes of any two different sensing modes is calculated, and nonlinear adjustment processing is performed on the anomaly difference; The local gradient anomaly indicators of two different sensing modes are nonlinearly weighted combined, and the weighted combination results are normalized using the nonlinearly adjusted anomaly difference to obtain the interactive coupling components corresponding to the two sensing modes. The interactive coupling components of all sensing mode pairs are aggregated to generate multimodal coupling unevenness. Specifically, the abnormal difference between the local gradient anomaly indicators of any two different sensing modes is calculated, and the difference sensitivity is enhanced through a nonlinear adjustment function to capture the collaborative anomaly characteristics between the modes, so that defects that are difficult to identify with a single mode are enhanced. The local gradient anomaly indicators of the two sensing modes are nonlinearly weighted combined, and the weighted combination result is normalized using the nonlinearly adjusted abnormal difference to generate the interactive coupling component between the two modes, which is used to reveal the collaborative response characteristics of the multimodal sensing signal on the local gradient. The interactive coupling components of all sensing mode pairs are aggregated to generate the multimodal coupling unevenness of the casing at that time point. The multimodal coupling unevenness is used to reflect the synergistic effect strength of the abnormal signals between different sensing modes. The calculation logic of the multimodal coupling unevenness is as follows: ,in, For the moment The multi-mode coupling unevenness is used to reflect the , the interactive coupling strength of local gradient anomaly indicators between different modal signals; Indicates that all modes are summed in pairs, and each pair of modes is calculated only once to avoid duplication. and ,and ; and Mode and At the moment The local gradient anomaly index; and are weight parameters, acting on and , used to control the influence of different modes in the interaction, with a value range of [1,2]; is a parameter used to adjust the sensitivity of the multimodal coupling inhomogeneity to the abnormal difference between the modes, and its value range is [1.3, 1.7]; It represents a nonlinear weighted combination of the local gradient anomaly indices of the two sensing modes. This nonlinear processing can enhance the influence of the mode with larger abnormal changes on the multimodal coupling inhomogeneity, while suppressing the contribution of the mode with smaller abnormal changes.

[0026] The present invention is further configured such that S5 includes: Performing a summation operation on the local gradient anomaly index of each sensing mode, and performing a first power transformation on the summation operation result; Performing a second power transformation on the expansion stress index, fusing the first power transformation result with the second power transformation result to generate a signal fusion factor; Perform third-power transformation and offset processing on the multi-modal coupling unevenness to generate the coupling impact factor; Calculate the absolute deviation between the real-time process parameters and the optimal process parameters, and perform exponential mapping on the absolute deviation to generate a process deviation penalty term; The first intermediate factor, the coupling influence factor and the process deviation penalty term are multiplied to generate a comprehensive quality factor; specifically, the local gradient anomaly indicators corresponding to the ultrasonic sensing mode, the infrared temperature sensing mode and the capacitive sensing mode are summed, and the summation result is subjected to the first power transformation to quantify the cumulative effect of the local anomalies of each mode; the flaring stress index is subjected to the second power transformation and fused with the first power transformation result to obtain a signal fusion factor, which is used to reflect the comprehensive local stress effect caused by wall thickness deviation and process parameter fluctuation; for multi-modal coupling unevenness, the coupling factor is generated through the third power transformation and offset processing. The combined influence factor is used to quantify the contribution of intermodal synergy to the overall quality. The absolute deviation between the real-time process parameters and the optimal process parameters is processed through exponential mapping to generate a process deviation penalty term, which is used to reflect the impact of process condition deviation on casing quality. The signal fusion factor, coupling influence factor and process deviation penalty term are multiplied to generate a comprehensive quality factor. This comprehensive quality factor is used to comprehensively evaluate the local anomaly accumulation effect, intermodal coupling effect and process deviation of the casing under current production conditions. The quality risk provided by the process deviation provides a unified indicator for subsequent dynamic deviation rate calculation and anomaly judgment. The calculation logic of the comprehensive quality factor is as follows: ,in, For the moment The comprehensive quality factor is used to measure the casing at the moment The overall quality status of the casing reflects the severity of local defects or process deviations; 、 and is the power parameter; It is used to adjust the contribution of the local gradient anomaly index of each mode to the comprehensive quality factor, with a value range of [2,3]; Adjust the influence of the expansion stress index on the comprehensive quality factor, with the value range being [1.5, 2.5]; It is used to adjust the contribution of multimodal coupling unevenness to the coupling impact factor, and the value range is [1.2, 1.8]; is a weight parameter used to control the ratio of amplification or compression of the multimodal coupling inhomogeneity to the comprehensive quality factor, and its value range is [-0.3, -0.1]; is a parameter adjustment used to adjust the attenuation effect of the deviation between the real-time process parameters and the optimal process parameters on the comprehensive quality factor, with a value range of [0.5, 2]; is the optimal process parameter value; It is a signal fusion factor that aggregates the local gradient anomaly index and the flaring stress index to reflect the contribution of single mode and process stress anomalies to the overall casing quality; The coupling influence factor is used to characterize the interactive coupling effect between different sensing modes and nonlinearly amplify or compress the impact of the synergistic change on the comprehensive quality factor. is the process deviation penalty term, which is used to quantify the negative impact of process parameters deviating from the optimal value on the casing quality.

[0027] The present invention is further configured such that S6 includes: Calculate the dynamic deviation rate based on the continuous change of the comprehensive quality factor within the preset historical time window and the continuous change of the real-time process parameters within the preset historical time window; Calculate the adaptive threshold according to the current comprehensive quality factor, dynamic deviation rate and multi-modal coupling unevenness; The current comprehensive quality factor is compared with the adaptive threshold. If the current comprehensive quality factor is less than the adaptive dynamic threshold, an abnormality flag is generated. Specifically, during the production process, the comprehensive quality factor at each time point is continuously recorded, and the continuous change amount is calculated within the preset historical time window to capture the fluctuation of the comprehensive quality factor over time. The real-time process parameters within the preset historical time window are collected and the continuous change amount is calculated to quantify the process fluctuation. The dynamic deviation rate of the comprehensive quality factor is calculated by combining the change of the comprehensive quality factor and the fluctuation of the process parameters to reflect the abnormality of the current state relative to the historical trend. The calculation logic of the dynamic deviation rate is as follows: ,in, For the moment The dynamic deviation rate is used to quantify the dynamic change degree of the comprehensive quality factor relative to the process parameter fluctuation within the preset historical time window; and Separate moments and The comprehensive quality factor of and is the adjustment parameter; Used to control the sensitivity of the comprehensive quality factor changes in the dynamic deviation rate calculation, the value range is [1.2,1.6]; Used to amplify or suppress the impact of process parameter fluctuations on the dynamic deviation rate, with a value range of [1,1.4]; and Separate moments and process parameters; Used to measure the intensity of changes in historical comprehensive quality factors; It is used to measure the overall fluctuation of process parameters. It comprehensively considers the current comprehensive quality factor, dynamic offset rate, and multimodal coupling unevenness to calculate the adaptive threshold. This adaptive threshold can dynamically adapt to changes in the production process and avoid false positives or negatives caused by fixed thresholds. The calculation logic of the adaptive threshold is: ,in, For the moment The adaptive threshold is used to determine whether the current comprehensive quality factor deviates from the normal range, thereby generating an abnormal flag; and is the adjustment index; To adjust the comprehensive part The nonlinear amplification or compression effect of the adaptive threshold is in the range of [1.1, 1.3]; For adjustment The overall amplification or compression effect of the adaptive threshold is in the range of [-1, -0.6]. The current comprehensive quality factor is compared with the adaptive threshold to detect anomalies. When the current comprehensive quality factor is less than the adaptive threshold, that is: , it is determined that an abnormality exists at that moment and an abnormality flag is generated.

[0028] The present invention is further configured such that S7 includes: Obtain the local gradient anomaly index and multimodal coupling unevenness of each sensing mode at the time point corresponding to the anomaly mark, as well as the enhanced normalized signal and corresponding reference signal of each sensing mode in the casing space coordinate; Calculate the signal deviation between the enhanced normalized signal of each sensing mode at each spatial coordinate and the corresponding reference signal, and perform nonlinear adjustment processing on the signal deviation; The local gradient anomaly index is nonlinearly amplified, and the nonlinearly adjusted signal deviation is used to normalize the nonlinearly amplified local gradient anomaly index to obtain the independent contribution of each sensing mode at each spatial coordinate; The independent contributions of all sensing modes are accumulated and summed to obtain the spatial contribution aggregation value; The spatial contribution aggregation value is fused with the multimodal coupling unevenness to generate a spatial mapping index; According to the numerical value and distribution of the spatial mapping index on each spatial coordinate, the spatial position and severity of the defect are determined, and the spatial distribution information of the defect is output. Specifically, the time point mark information obtained by anomaly detection is mapped to the physical spatial coordinates of the casing to realize defect positioning and spatial distribution evaluation. By combining the enhanced normalized signal, local gradient anomaly index and multimodal coupling unevenness of each sensing mode, the independent contribution of each spatial point to the anomaly is quantified, and the multimodal interaction effect is integrated to generate a spatial mapping index, providing a visualization basis for defect positioning. For the time point corresponding to the anomaly mark, the enhanced normalized signal and the corresponding reference signal of each sensing mode at each spatial coordinate are obtained, and the local gradient anomaly index and multimodal coupling unevenness at the same time point are obtained. For each spatial coordinate and sensing mode, the signal deviation between the enhanced normalized signal and the reference signal is calculated, and the signal deviation is nonlinearly adjusted to enhance the local anomaly response. The signal deviation after nonlinear adjustment is recorded as: ,in, For modal At the moment Space coordinates Enhanced normalized signal at ; For modal In spatial coordinates The reference signal at is an adjustment parameter used to amplify or compress the contribution of the signal deviation to the spatial mapping index, with a value range of [1.2, 1.6]. The signal deviation after nonlinear adjustment is used to normalize the amplified local gradient anomaly index to obtain the independent contribution of each sensing modality at each spatial coordinate. The independent contributions of all sensing modalities are accumulated to obtain the spatial contribution aggregation value, which is used to reflect the overall anomaly contribution of different sensing modalities at each spatial coordinate. The calculation logic of the spatial contribution aggregation value is: ,in, For modal At the moment Space coordinates The spatial contribution aggregation value at It is the independent contribution amount; It is a parameter used to adjust the influence of the local gradient anomaly index on the spatial mapping index, and its value range is [1.6, 2]. and multimodal coupling inhomogeneity The spatial mapping index is generated by fusion. The spatial mapping index is used to characterize the abnormal signal intensity and defect distribution of each spatial coordinate of the casing. The calculation logic of the spatial mapping index is: ,in, is the spatial mapping index, reflecting the casing at time Space coordinates The abnormal strength of the integrated signal at is a weight parameter used to control the influence of multimodal coupling unevenness on the spatial mapping index, with a value range of [0.8, 1.2]. By analyzing the numerical size and distribution of the defects, the location and severity of the defects can be determined, thus providing a reference for adjusting the production process parameters.

[0029] The present invention is further configured such that S8 includes: Based on the spatial mapping index corresponding to the spatial distribution information of the defect, the spatial mapping index on all spatial coordinates is summed to generate the cumulative defect severity; Perform nonlinear transformation on current process parameters to generate process state adjustment factors; The process state adjustment factor is used to perform weighted modulation on the cumulative defect severity to generate the process parameter adjustment amount; Add the process parameter adjustment amount to the current process parameter to generate the optimized process parameter setting value; The optimized process parameter setting values ​​are fed back to the production control system to achieve closed-loop optimization control. Specifically, during the casing production process, the production process parameters are dynamically adjusted by using the spatial mapping index corresponding to the spatial distribution information of the defects to achieve optimized control of the production process. The spatial mapping index of each spatial coordinate is After squaring, the sum is calculated to obtain the cumulative defect severity of the entire casing at the current time point. This cumulative defect severity is used to quantify the overall defect level of the entire casing at the current moment and highlight the contribution of high abnormality locations to the total defect severity. The calculation logic of the cumulative defect severity is: ,in, For the moment The cumulative defect severity of the current process parameters A nonlinear transformation is performed to generate a process state adjustment factor. This process state adjustment factor takes into account the impact of the current process parameter state on the adjustment amount. Using the process state adjustment factor for closed-loop control can intervene in defects while avoiding instability caused by excessive adjustment. The calculation logic of the process state adjustment factor is: ,in, For the moment Process state adjustment factor; and is the adjustment coefficient; Used to control the influence of process status on adjustment amount, the value range is [0.5, 0.9]; Used to adjust the direction of process parameter adjustment, the value range is [-1.2, -0.8]; according to the cumulative amount of defect severity and process state adjustment factors , calculate the process parameter adjustment amount, which is used to perform closed-loop optimization of the production process. The calculation logic of the process parameter adjustment amount is: ,in, For the moment The amount of process parameter adjustment; is the adjustment coefficient, which is used to control the overall amplitude of the process parameter adjustment, and its value range is [0.01, 0.1]. With current process parameters By superimposing, the optimized process parameter setting values ​​that can be directly applied to the production control system are generated. The calculation logic of the optimized process parameter setting values ​​is: ,in, For the moment The optimized process parameter setting value is obtained; the optimized process parameter setting value is obtained Feedback is sent to the production control system to achieve dynamic control of the casing production process. By adjusting process parameters in real time, the defect rate can be reduced and the overall quality of the casing can be improved.

[0030] The present invention is further configured such that the multimodal sensing signals are collected by a distributed sensor array, and the sensor array is arranged along the axial direction and circumferential direction of the casing; specifically, during the casing production process, the multimodal sensing signals are collected by a distributed sensor array, and the sensors are evenly arranged along the axial direction and circumferential direction of the casing, and the signal collected by each sensor corresponds to a specific spatial coordinate of the casing. , and each modal signal is synchronized through a high-precision timestamp; through this sensor arrangement, the dynamic changes of the casing in the axial and circumferential directions can be monitored simultaneously, realizing all-round, multi-modal monitoring of the flaring process and the overall quality status of the casing.

[0031] Example 2

[0032] See also Figure 2 The exemplary quality monitoring system for insulating side expansion casing production includes: Signal acquisition module: used to collect multimodal sensor signals and process parameters during the production process. The multimodal sensor signals include ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals. Normalization anomaly module: used to normalize multimodal sensor signals to generate enhanced normalized signals, and calculate the local gradient anomaly index of each mode based on the enhanced normalized signals; Expanding stress evaluation module: used to calculate the expanding stress index based on the deviation between the ultrasonic wall thickness signal and the reference wall thickness value combined with the process parameters; Coupling analysis module: used to perform coupling analysis on different modal sensor signals based on local gradient anomaly indicators and calculate multi-modal coupling unevenness; Comprehensive quality assessment module: used to calculate the comprehensive quality factor based on the local gradient anomaly index, flaring stress index and multi-modal coupling non-uniformity, combined with process parameter deviation; Anomaly detection module: This module detects anomalies in production status and generates anomaly flags based on the dynamic deviation rate of the comprehensive quality factor and the adaptive threshold. Defect location module: used to map the multi-source time series features corresponding to the abnormal identification to the spatial coordinates of the casing and output the spatial distribution information of the defects; Closed-loop process control module: used to generate process parameter adjustments based on the spatial distribution information of defects, feed the process parameter adjustments back to the production control system, and perform closed-loop optimization control of the production process.

[0033] It should be noted that the quality monitoring system for insulating side expansion casing production provided in the above-mentioned embodiment and the quality monitoring method for insulating side expansion casing production provided in the above-mentioned embodiment are based on the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the quality monitoring system for insulating side expansion casing production provided in the above-mentioned embodiment can allocate the above-mentioned functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0034] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A quality monitoring method for insulating side expansion casing production, characterized in that: include: S1: Collect multimodal sensor signals and process parameters during the production process. The multimodal sensor signals include ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals. S2: normalizing the multimodal sensing signals to generate enhanced normalized signals, and calculating the local gradient anomaly index of each modality based on the enhanced normalized signals; S3: Calculate the expansion stress index based on the deviation between the ultrasonic wall thickness signal and the reference wall thickness value and the process parameters; S4: Based on the local gradient anomaly index, the coupling analysis of different modal sensing signals is performed to calculate the multimodal coupling unevenness; S5: Calculate the comprehensive quality factor based on the local gradient anomaly index, flaring stress index and multimodal coupling non-uniformity, combined with the process parameter deviation; S6: Based on the dynamic deviation rate of the comprehensive quality factor and the adaptive threshold, anomaly detection is performed on the production status and an anomaly flag is generated; S7: Mapping the multi-source time series features corresponding to the abnormal identification to the spatial coordinates of the casing, and outputting the spatial distribution information of the defects; S8: Generate process parameter adjustment values ​​based on the spatial distribution information of defects, feed the process parameter adjustment values ​​back to the production control system, and perform closed-loop optimization control on the production process.

2. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The S2 includes: Independent normalization processing of ultrasonic wall thickness signal, infrared temperature signal and capacitance signal; Perform fractional power weighting processing on the signal sequence within the preset historical time window of each sensing modality, and fuse the current signal normalization result of each sensing modality with the corresponding historical signal weighted processing result to generate an enhanced normalized signal; Based on the enhanced normalized signal of each sensing modality, the local gradient anomaly index of each sensing modality is generated by calculating the ratio of the signal energy change to the signal change intensity within a preset sliding time window.

3. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The S3 includes: According to the enhanced normalized ultrasonic wall thickness signal at each measurement position and the corresponding reference wall thickness value, the wall thickness deviation between the current ultrasonic wall thickness signal and the reference wall thickness value is calculated, and the wall thickness deviation is nonlinearly amplified; Obtain the process difference between the real-time process parameters and the local equivalent process parameters at each measurement position, and perform nonlinear adjustment processing on the process difference; Based on the nonlinearly amplified wall thickness deviation and the nonlinearly adjusted process difference, normalization processing is performed to obtain the local stress component at each measuring position; The local stress components at each measurement location are aggregated to generate the flaring stress index.

4. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The S4 includes: According to the local gradient anomaly index corresponding to each sensing mode, the anomaly difference between the local gradient anomaly indexes of any two different sensing modes is calculated, and nonlinear adjustment processing is performed on the anomaly difference; The local gradient anomaly indicators of two different sensing modes are nonlinearly weighted combined, and the weighted combination results are normalized using the nonlinearly adjusted anomaly difference to obtain the interactive coupling components corresponding to the two sensing modes. The interaction coupling components of all sensing mode pairs are aggregated to generate multimodal coupling inhomogeneity.

5. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The S5 includes: Performing a summation operation on the local gradient anomaly index of each sensing mode, and performing a first power transformation on the summation operation result; Performing a second power transformation on the expansion stress index, fusing the first power transformation result with the second power transformation result to generate a signal fusion factor; Perform third-power transformation and offset processing on the multi-modal coupling unevenness to generate the coupling impact factor; Calculate the absolute deviation between the real-time process parameters and the optimal process parameters, and perform exponential mapping on the absolute deviation to generate a process deviation penalty term; The first intermediate factor, coupling influence factor and process deviation penalty term are multiplied together to generate a comprehensive quality factor.

6. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The S6 includes: Calculate the dynamic deviation rate based on the continuous change of the comprehensive quality factor within the preset historical time window and the continuous change of the real-time process parameters within the preset historical time window; Calculate the adaptive threshold according to the current comprehensive quality factor, dynamic deviation rate and multi-modal coupling unevenness; The current comprehensive quality factor is compared with the adaptive threshold. If the current comprehensive quality factor is less than the adaptive dynamic threshold, an abnormal flag is generated.

7. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The S7 includes: Obtain the local gradient anomaly index and multimodal coupling unevenness of each sensing mode at the time point corresponding to the anomaly mark, as well as the enhanced normalized signal and corresponding reference signal of each sensing mode in the casing space coordinate; Calculate the signal deviation between the enhanced normalized signal of each sensing mode at each spatial coordinate and the corresponding reference signal, and perform nonlinear adjustment processing on the signal deviation; The local gradient anomaly index is nonlinearly amplified, and the nonlinearly adjusted signal deviation is used to normalize the nonlinearly amplified local gradient anomaly index to obtain the independent contribution of each sensing mode at each spatial coordinate; The independent contributions of all sensing modes are accumulated and summed to obtain the spatial contribution aggregation value; The spatial contribution aggregation value is fused with the multimodal coupling unevenness to generate a spatial mapping index; According to the numerical value and distribution of the spatial mapping index at each spatial coordinate, the spatial location and severity of the defect are determined, and the spatial distribution information of the defect is output.

8. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The S8 includes: Based on the spatial mapping index corresponding to the spatial distribution information of the defect, the spatial mapping index on all spatial coordinates is summed to generate the cumulative defect severity; Perform nonlinear transformation on current process parameters to generate process state adjustment factors; The process state adjustment factor is used to perform weighted modulation on the cumulative defect severity to generate the process parameter adjustment amount; Add the process parameter adjustment amount to the current process parameter to generate the optimized process parameter setting value; Feedback the optimized process parameter setting values ​​to the production control system to achieve closed-loop optimization control.

9. The quality monitoring method for insulating side expansion casing production according to claim 1, characterized in that: The multimodal sensing signals are collected by a distributed sensor array, and the sensor array is arranged along the axial direction and the circumferential direction of the casing.

10. A quality monitoring system for insulating side expansion casing production, used to implement the quality monitoring method for insulating side expansion casing production according to any one of claims 1 to 9, characterized in that: include: Signal acquisition module: used to collect multimodal sensor signals and process parameters during the production process. The multimodal sensor signals include ultrasonic wall thickness signals, infrared temperature signals, and capacitance signals. Normalization anomaly module: used to normalize multimodal sensor signals to generate enhanced normalized signals, and calculate the local gradient anomaly index of each mode based on the enhanced normalized signals; Expanding stress evaluation module: used to calculate the expanding stress index based on the deviation between the ultrasonic wall thickness signal and the reference wall thickness value combined with the process parameters; Coupling analysis module: used to perform coupling analysis on different modal sensor signals based on local gradient anomaly indicators and calculate multi-modal coupling unevenness; Comprehensive quality assessment module: used to calculate the comprehensive quality factor based on the local gradient anomaly index, flaring stress index and multi-modal coupling non-uniformity, combined with process parameter deviation; Anomaly detection module: This module detects anomalies in production status and generates anomaly flags based on the dynamic deviation rate of the comprehensive quality factor and the adaptive threshold. Defect location module: used to map the multi-source time series features corresponding to the abnormal identification to the spatial coordinates of the casing and output the spatial distribution information of the defects; Closed-loop process control module: used to generate process parameter adjustments based on the spatial distribution information of defects, feed the process parameter adjustments back to the production control system, and perform closed-loop optimization control of the production process.

Images