Method and system for detecting production of pe inner liner pipe based on distribution sensor and medium

Abstract

The present application relates to the technical field of pipe detection, and discloses a PE lining pipe production detection method and system based on a distributed sensor, and a medium, the method comprising: collecting original monitoring data of the lining pipe through a distributed sensor array network, evaluating signal quality and marking abnormal data segments; reconstructing complete monitoring data based on data evaluation results and space-time continuity characteristics; mapping data to a unified coordinate system to obtain a process state panorama by combining sensor and material track association; performing multi-physical field coupling analysis on the process state panorama, and identifying the internal action relationship between process parameters in the lining pipe to obtain a process state analysis report; adjusting process parameters of the lining pipe according to the process state analysis report, obtaining optimized parameters, and encoding the optimized parameters into production control instructions; issuing the production control instructions, and detecting the production quality of the lining pipe after regulation and control to obtain a quality detection report; and the present application can improve the efficiency of PE lining pipe production detection and parameter optimization.

Description

Technical Field

[0001] This invention relates to the field of pipe testing technology, and in particular to a method, system and medium for testing the production of PE lined pipes based on distributed sensors. Background Technology

[0002] In the field of PE liner pipe production and testing, existing technologies mostly use single or a small number of discrete sensors for data acquisition. This results in limited data coverage and a lack of coordination, leading to anomalies such as missing time sequences and spatial dispersion in the raw monitoring data, making it difficult to comprehensively capture dynamic changes during the production process. Furthermore, existing data processing methods do not fully consider the spatiotemporal continuity of data, resulting in insufficient accuracy in identifying and repairing abnormal data. This leads to a lack of reliable data support for subsequent process analysis, significantly reducing the accuracy and comprehensiveness of the test results.

[0003] Existing technologies have significant limitations in process state analysis and parameter optimization. They lack a multi-physics coupling analysis mechanism, making it difficult to effectively identify the intrinsic relationships between process parameters, resulting in a superficial understanding of the production process. Parameter adjustments rely heavily on experience-based judgment, lacking scientific collaborative optimization strategies, making precise control of process parameters difficult. This not only affects the stability of PE liner pipe production quality but also reduces the overall efficiency of the production process. Therefore, improving the efficiency of PE liner pipe production inspection and parameter optimization has become an urgent problem to be solved. Summary of the Invention

[0004] This disclosure provides a method, system, and medium for production testing of PE liner pipes based on distributed sensors.

[0005] In the first aspect, this disclosure provides a production inspection method for PE liner pipes based on distributed sensors, including:

[0006] S1. Collect raw monitoring data of the inner liner tube through a distributed sensor array network, evaluate the signal quality of the raw monitoring data, and mark abnormal data segments in the raw monitoring data to obtain the data evaluation result of the inner liner tube;

[0007] S2. Based on the data evaluation results and the spatiotemporal continuity characteristics of the original monitoring data, the data evaluation results are reconstructed to obtain complete monitoring data of the inner lining pipe;

[0008] S3. Based on the correlation between the distributed sensor array network and the material trajectory in the inner liner, the complete monitoring data is mapped to a preset unified coordinate system to obtain a panoramic view of the process status of the inner liner.

[0009] S4, multi-physical field coupling analysis is performed on the process state panorama, and internal action relationships between process parameters in the inner liner pipe are identified, and a process state analysis report of the inner liner pipe is obtained;

[0010] S5, according to the process state analysis report, adjusting the process parameters of the inner liner pipe, obtaining the optimization parameters of the inner liner pipe, and encoding the optimization parameters into the production control instructions of the inner liner pipe;

[0011] S6, issuing the production control instructions, and detecting the production quality of the inner liner pipe after regulation and control, and obtaining a quality detection report of the inner liner pipe.

[0012] In a preferred embodiment, the original monitoring data of the inner liner pipe is collected through a distributed sensor array network, the signal quality of the original monitoring data is evaluated, and abnormal data segments in the original monitoring data are marked, and a data evaluation result of the inner liner pipe is obtained, comprising:

[0013] The thickness distribution, temperature gradient and strain state data of the inner liner pipe during production are collected to obtain the original monitoring data of the inner liner pipe;

[0014] The time sequence integrity and spatial consistency of the original monitoring data are verified to identify missing segments and discrete points in the original monitoring data;

[0015] The time and space positions, abnormal types and abnormal levels of the missing segments and the discrete points are quantitatively aggregated to obtain the data evaluation result of the inner liner pipe.

[0016] In a preferred embodiment, the data evaluation result is reconstructed based on the data evaluation result and the spatiotemporal continuity feature of the original monitoring data, and the complete monitoring data of the inner liner pipe is obtained, comprising:

[0017] According to the spatiotemporal continuity feature of the original monitoring data, the normal data features adjacent to the abnormal data segments in the data evaluation result are used as the data repair reference of the inner liner pipe;

[0018] The adjacent normal data segments of the abnormal data segments and the historical data of the inner liner pipe are associated and analyzed to repair the abnormal data segments, and the reconstructed data of the inner liner pipe is obtained;

[0019] The continuity and consistency of the reconstructed data and the surrounding normal data in the reconstructed data are verified to obtain the complete monitoring data of the inner liner pipe.

[0020] In a preferred embodiment, the complete monitoring data is mapped into a preset unified coordinate system according to the association between the distribution sensor array network and the material track in the inner lining pipe, and a process state panoramic map of the inner lining pipe is obtained, including:

[0021] The spatial position information and the acquisition time sequence of the sensors in the distribution sensor array network are analyzed to obtain time-space coordinate description information of the sensors;

[0022] According to the continuous motion characteristics of the material track in the inner lining pipe during the production process, an average motion speed of the production material in the inner lining pipe along the material track is obtained;

[0023] A spatial axis is established with the production starting point of the inner lining pipe as a spatial origin and with the direction of the material track as a positive direction, and a unified coordinate system of the inner lining pipe is constructed with the total production time of the inner lining pipe as a time axis;

[0024] According to the time-space coordinate description information and the average motion speed, the distance and time of a real-time acquisition data point in the distribution sensor array network to the spatial origin are quantified, the specific coordinates of the real-time acquisition data point in the unified coordinate system are determined, and a coordinate mapping rule of the inner lining pipe is obtained;

[0025] According to the coordinate mapping rule, the data points in the complete monitoring data are mapped into the unified coordinate system one by one, and a process state panoramic map of the inner lining pipe is obtained.

[0026] In a preferred embodiment, the process state panoramic map is subjected to multi-physical field coupling analysis, and the inherent action relationship between the process parameters in the inner lining pipe is identified, and a process state analysis report of the inner lining pipe is obtained, including:

[0027] The detection data sequence of the physical field in the process state panoramic map is extracted to analyze the statistical characteristics of the detection data sequence;

[0028] Based on the data evaluation result, the reliability of the physical field is evaluated, and a quality weight coefficient of the physical field is obtained;

[0029] The coupling strength between the physical fields is calculated according to the statistical characteristics and the quality weight;

[0030] According to the coupling strength, the inherent action relationship between the process parameters in the inner lining pipe is analyzed, and a process state analysis report of the inner lining pipe is obtained.

[0031] In a preferred embodiment, the calculation formula of the coupling strength is:

[0032] ;

[0033] wherein, represents the coupling strength, represents the detection data sequence of the physical field, represents and the covariance of, represents the standard deviation of the detection data sequence, represents the mean of the detection data sequence, represents a preset coupling strength weight coefficient, represents a preset mean difference scaling factor, represents a preset standard deviation weight coefficient, represents the quality weight coefficient of the first physical field, represents the number of physical fields, represents an exponential function, represents an absolute value.

[0034] In a preferred embodiment, the process state analysis report is used to adjust the process parameters of the inner liner pipe, obtain the optimized parameters of the inner liner pipe, and encode the optimized parameters into production control instructions of the inner liner pipe, comprising:

[0035] Based on the process state analysis report, the process parameters of the inner liner pipe are prioritized to obtain the adjustment order and optimization weight of the process parameters;

[0036] Integrate the adjustment order, the optimization weight, and the intrinsic relationship to obtain a synergistic optimization strategy for the process parameters;

[0037] According to the synergistic optimization strategy, the process parameters are adjusted in stages to obtain the optimized parameters of the inner liner pipe;

[0038] According to the target production quality requirements of the inner liner pipe, the optimized parameters are encoded into production control instructions of the inner liner pipe.

[0039] In a preferred embodiment, the production control instructions are issued, and the production quality of the regulated inner liner pipe is detected to obtain a quality detection report of the inner liner pipe, comprising:

[0040] The production control instructions are input to the production terminal of the inner liner pipe, and the instruction execution state of the regulated inner liner pipe is monitored in real time;

[0041] The production data of the regulated inner liner pipe is collected through the distributed sensor array network, the fit degree of the production data and the target production quality requirements of the inner liner pipe is evaluated, and the quality compliance result of the regulated inner liner pipe is obtained.

[0042] According to the target production quality requirement, a cause of the substandard production data in the production data is diagnosed to generate an improvement suggestion for the liner pipe in the production process;

[0043] The improvement suggestion and the quality standard result are combined to obtain a quality detection report of the liner pipe.

[0044] Compared with the prior art, the present application has the following beneficial effects:

[0045] 1. The present application comprehensively collects multi-dimensional original monitoring data such as thickness distribution, temperature gradient and strain state in the production process of the liner pipe through a distributed sensor array network, combines data signal quality evaluation and abnormal marking, relies on spatiotemporal continuity characteristics and historical data correlation analysis to repair abnormal data segments, and generates complete and reliable monitoring data. Then, through the construction of a unified coordinate system, the complete monitoring data are associated and mapped with the material track to form a panoramic process state view, realizing all-around and fine perception of the production process, and significantly improving the completeness, consistency of the monitoring data and the visualization degree of the process state.

[0046] 2. The present application precisely identifies the internal action relationship among process parameters through multi-physical field coupling analysis, formulates a scientific parameter coordination optimization strategy based on the analysis result, completes process parameter adjustment in stages and encodes it into production control instructions, simultaneously verifies the regulation and control effect through closed-loop detection and generates improvement suggestions. This process realizes intelligent operation of the whole chain from data collection, analysis to parameter optimization and quality control, effectively improves the precision of PE liner pipe production parameter regulation and control and the stability of production quality, and further enhances the controllability and overall efficiency of the production process. BRIEF DESCRIPTION OF DRAWINGS

[0047] In the following, the present disclosure will be described in more detail based on embodiments and with reference to the accompanying drawings:

[0048] Figure 1 A work flow diagram of a PE liner pipe production detection method based on a distributed sensor according to an embodiment of the present application is shown;

[0049] Figure 2 A functional module diagram of a PE liner pipe production detection system based on a distributed sensor according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0050] In order for those skilled in the technical field to better understand the technical solutions of the present disclosure, and to fully understand and implement the implementation process of the present disclosure how to apply technical means to solve technical problems and achieve the corresponding technical effects, the technical solutions in the embodiments of the present disclosure will be described clearly and completely in the following with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, not all. The embodiments of the present disclosure and various features in the embodiments can be combined with each other without conflict, and the technical solutions formed thereby are all within the protection scope of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor should be within the protection scope of the present disclosure.

[0051] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described here can be executed in a different order.

[0052] Embodiment one

[0053] Figure 1 The flowchart of the PE inner liner pipe production detection method based on distributed sensors provided by the embodiments of the present disclosure is shown. As shown in the figure, the PE inner liner pipe production detection method based on distributed sensors comprises: Figure 1

[0054] S1, collecting original monitoring data of the inner liner pipe through a distributed sensor array network, evaluating the signal quality of the original monitoring data, and marking abnormal data segments in the original monitoring data to obtain a data evaluation result of the inner liner pipe;

[0055] In the embodiments of the present disclosure, the collecting original monitoring data of the inner liner pipe through a distributed sensor array network, evaluating the signal quality of the original monitoring data, and marking abnormal data segments in the original monitoring data to obtain a data evaluation result of the inner liner pipe comprises:

[0056] Collecting thickness distribution, temperature gradient and strain state data of the inner liner pipe during the production process to obtain the original monitoring data of the inner liner pipe;

[0057] Verifying the time sequence integrity and spatial consistency of the original monitoring data to identify missing segments and discrete points in the original monitoring data;

[0058] Quantitatively aggregating the time and space positions, abnormal types and abnormal levels of the missing segments and the discrete points to obtain the data evaluation result of the inner liner pipe.

[0059] ​The distributed sensor array network is evenly arranged along the key process line of the inner lining pipe production equipment, and the number of sensors is reasonably configured according to the length of the production pipeline and the detection accuracy requirement, to ensure the coverage of the full section and the whole production process of the inner lining pipe. Each sensor is started synchronously with the production of the inner lining pipe, and continuously monitors the pipe production process. The thickness distribution is directly contacted with the pipe surface through the sensor, and the thickness values at different positions in the circumferential direction and the axial direction of the pipe are recorded in real time. The temperature gradient is sensed by the sensor to capture the temperature difference between the inside and the surface of the pipe, the different circumferential positions and the different axial sections of the pipe, and continuously capture the temperature change. The strain state is monitored by the sensor to obtain the tensile or compression related data of the pipe in the production process. The collection actions of all sensors are kept synchronous, and the collected thickness distribution, temperature gradient and strain state related data are all integrated to form the original monitoring data of the inner lining pipe.

[0060] The original monitoring data is systematically sorted according to the collection time sequence, and it is checked whether there is corresponding monitoring data at each time node. If there is no monitoring data corresponding to the process in a certain time period, and the time period is in a normal production state, it is determined that the data set corresponding to the time period is a missing section. At the same time, the monitoring data collected by different spatial position sensors at the same collection time point is compared, and whether the detection results of adjacent position sensors present a continuous and reasonable change trend is analyzed. If the monitoring data of a certain position and the same period data of multiple adjacent positions exist significant differences, and the reasonable physical factors such as sensor hardware failure and sudden fluctuation of production process are excluded, it is determined that the data is a discrete point. The missing section and the discrete point in the original monitoring data are identified through the above method.

[0061] The starting collection time, ending collection time, corresponding pipe production section and sensor arrangement position of each missing section are recorded one by one, the specific collection time, corresponding sensor number and pipe position of each discrete point are determined, and the space-time position of all abnormal data is accurately locked. According to the specific performance of data anomaly, the missing section is defined as time sequence interruption type anomaly, and the discrete point is defined as spatial data deviation type anomaly, and the abnormal types are clearly divided. Taking the fluctuation range of the monitoring data in the normal production state as the benchmark, the missing section is divided into grades according to its duration, the duration within 1 minute is first grade anomaly, 1 to 5 minutes is second grade anomaly, and 5 minutes above is third grade anomaly. The discrete point is divided into grades according to the proportion of the average difference value of the discrete point to the normal data fluctuation range, the proportion within 20% is first grade anomaly, 20% to 50% is second grade anomaly, and 50% above is third grade anomaly. Then, the space-time position information of all abnormal data, the clear abnormal type and the divided abnormal grade are systematically sorted and centrally summarized to form the data evaluation result of the inner lining pipe.

[0062] The beneficial effect is that the integrity and authenticity of the original monitoring data are ensured through comprehensive and synchronous multidimensional data collection, the data abnormality is accurately identified through clear timing and spatial verification standards, and the abnormal information is integrated through clear classification and grading rules, so that the evaluation result of the finally obtained data set is comprehensive, accurate and detailed, which provides a clear targeted direction for subsequent data reconstruction work, effectively avoids the deviation of subsequent process analysis caused by data abnormality, and ensures the reliability of the entire production detection process.

[0063] S2, based on the data evaluation result and the spatio-temporal continuity feature of the original monitoring data, data reconstruction is performed on the data evaluation result to obtain complete monitoring data of the inner liner pipe;

[0064] In the embodiment of the application, the data reconstruction based on the data evaluation result and the spatio-temporal continuity feature of the original monitoring data includes:

[0065] According to the spatio-temporal continuity feature of the original monitoring data, the normal data features adjacent to the abnormal data segment in the data evaluation result are taken as the data repair reference of the inner liner pipe;

[0066] The adjacent normal data segment of the abnormal data segment and the historical data of the inner liner pipe are associated and analyzed to repair the abnormal data segment, and the reconstructed data of the inner liner pipe is obtained;

[0067] The continuity and consistency of the reconstructed data and the surrounding normal data in the reconstructed data are verified to obtain the complete monitoring data of the inner liner pipe.

[0068] According to the spatio-temporal continuity feature of the original monitoring data, the data change rule is determined, the data at each time node is continuously and gradually changed according to the order of the production process of the inner liner pipe, the monitoring data at each time node is logically associated with the adjacent node data, the data collected by the sensors at different positions at the same production time fluctuates around a reasonable interval, and the adjacent position data has no significant mutation. By locating the abnormal data segment marked in the data evaluation result, the directly adjacent previous normal data and subsequent normal data are found, the gradient amplitude of the thickness distribution, the fluctuation range of the temperature gradient, the change trend of the strain state and other core features of these normal data are extracted, and these features are determined as the data repair reference of the inner liner pipe.

[0069] Based on the data repair benchmark, first analyze the end value characteristics and rate of change of the normal data before the abnormal data segment, and the beginning value characteristics and rate of change of the normal data after the abnormal data segment to determine the transition law that the abnormal data segment should follow. Then, retrieve the complete historical monitoring data of the same production process, material specifications and production environment of the inner liner pipe, screen out the historical data segments that are consistent with the current production stage, extract the monitoring data change law of the production period corresponding to the abnormal data segment in the historical data, compare and match the transition law of adjacent normal data with the change law of historical data, fill in the corresponding values ​​for missing segments according to the transition law and historical data characteristics, and correct the values ​​of discrete points according to the surrounding normal data and historical similar data so that the repaired abnormal data segment is consistent with the overall data trend, forming the reconstructed data of the inner liner pipe.

[0070] The reconstructed data undergoes a continuity verification check to ensure that the starting value of the reconstructed data maintains a reasonable difference from the ending value of the previous normal data segment, that the rate of change is smoothly connected, and that the ending value of the reconstructed data transitions smoothly from the starting value of the next normal data segment without abrupt fluctuations. Simultaneously, a consistency verification is performed by comparing the reconstructed data with normal data from surrounding spatial locations at the same production time to confirm whether the numerical range and trend of the reconstructed data are consistent with the surrounding normal data and conform to the process characteristics and data patterns of this production stage. After both continuity and consistency verifications are successful, complete monitoring data for the inner lining pipe is obtained.

[0071] The beneficial effects are that by establishing clear repair benchmarks, adopting practical correlation analysis repair methods, and implementing a rigorous dual verification process, the rationality and accuracy of the reconstructed data are ensured. The resulting complete monitoring data can comprehensively and accurately reflect the actual state of the inner liner tube production process, providing reliable data support for the subsequent construction of a panoramic view of the process status and the analysis of process parameters, and ensuring the stability and effectiveness of the entire production and testing process.

[0072] S3. Based on the correlation between the distributed sensor array network and the material trajectory in the inner liner, the complete monitoring data is mapped to a preset unified coordinate system to obtain a panoramic view of the process status of the inner liner.

[0073] In this embodiment of the invention, the step of mapping the complete monitoring data to a preset unified coordinate system based on the correlation between the distributed sensor array network and the material trajectory in the inner liner tube to obtain a panoramic view of the process status of the inner liner tube includes:

[0074] By analyzing the spatial location information and acquisition time series of sensors in the distributed sensor array network, the spatiotemporal coordinate description information of the sensors is obtained;

[0075] According to the continuous motion characteristics of the material track in the production process of the inner liner pipe, an average motion speed of the production material in the inner liner pipe on the material track is obtained;

[0076] A uniform coordinate system of the inner liner pipe is constructed by taking a production starting point of the inner liner pipe as a spatial origin, establishing spatial axes with a direction of the material track as a positive direction, and taking a total production time of the inner liner pipe as a time axis.

[0077] According to the space-time coordinate description information and the average motion speed, distances and times of real-time collection data points in the distributed sensor array network to the spatial origin are quantified, specific coordinates of the real-time collection data points in the uniform coordinate system are determined, and a coordinate mapping rule of the inner liner pipe is obtained.

[0078] According to the coordinate mapping rule, data points in the complete monitoring data are mapped one by one into the uniform coordinate system, and a process state panorama of the inner liner pipe is obtained.

[0079] The installation positions of each sensor in the distributed sensor array network are analyzed, a fixed rack node of the PE inner liner pipe production equipment is taken as a key reference point, a laser range finder and a three-dimensional coordinate measuring instrument are used in cooperation to measure specific distances of each sensor in three directions of X-axis, Y-axis and Z-axis relative to the reference point, and three-dimensional space coordinates of each sensor are accurately determined. Meanwhile, collection clocks of all sensors are synchronized and calibrated with a master control clock of the production equipment, accurate starting collection moments of each sensor in response to a production starting signal are recorded, and each time node of subsequent data collection according to a preset collection interval is recorded to form a continuous and uninterrupted collection time sequence. The three-dimensional space coordinates of each sensor are one-to-one corresponding bound with the corresponding collection time sequence, the system is arranged in order of sensor numbers, and space-time coordinate description information of the sensors containing space positions, collection times and corresponding correlation relationships of the sensors is formed.

[0080] A complete moving path of the material from a production starting point to a forming terminal point in the production process of the inner liner pipe is observed, trigger sensors are arranged at the production starting point and the forming terminal point respectively, a trigger sensor at the production starting point records a starting moment when a front end of the material arrives at the production starting point, a trigger sensor at the forming terminal point records an arrival moment when a tail end of the material leaves the forming terminal point, and a difference between the two moments is a total motion time length of the material. Meanwhile, a pull rope type range finder is used to measure along a central axis of the production equipment to obtain a straight line distance from the production starting point to the forming terminal point as a total motion distance of the material. The total motion distance of the material obtained by measurement is divided by the total motion time length of the material to obtain an average motion speed of the production material in the inner liner pipe on the material track.

[0081] The center position of the extruder outlet of the inner liner pipe production equipment is set as the production starting point, which is taken as the spatial origin of the unified coordinate system. The axial direction of the material trajectory from the production starting point to the forming terminal is set as the positive direction of the spatial axis, and the scale unit of the spatial axis is millimeter, which is used to accurately represent the specific position of the material in the production process. According to the preset pipe length of single continuous production of the inner liner pipe and the rated production speed of the equipment, the total production time is preliminarily estimated, and then corrected combined with the start and stop signals of the equipment in the actual production process to determine the range of the time axis. The starting point of the time axis is the time when the production equipment is formally started, and the terminal point is the time when the production task is completed. The scale unit of the time axis is second, which is used to accurately represent the progress information of the production. Thus, the unified coordinate system of the inner liner pipe with spatial position representation and time process representation is constructed.

[0082] The acquired spatiotemporal coordinate description information of the sensors and the average movement speed of the material are retrieved. For each real-time data point in the distributed sensor array network, the projection distance of the data point on the spatial axis of the unified coordinate system, i.e., the straight-line distance to the spatial origin, is calculated according to the three-dimensional spatial coordinates of the corresponding sensor. According to the time sequence of the sensor data collection, the accurate collection time corresponding to the data point is determined. Combined with the average movement speed of the material, the theoretical spatial position of the material at the collection time point is calculated, and the matching of the actual spatial distance of the data point and the theoretical spatial position is verified. If the deviation is within the preset reasonable range, the data is confirmed to be valid. The spatial distance of each real-time data point is corresponded to the scale of the spatial axis of the unified coordinate system, and the collection time is corresponded to the scale of the time axis, so that the unique corresponding position of each data point in the unified coordinate system is determined, and a complete coordinate mapping rule of the inner liner pipe is formed.

[0083] According to the determined coordinate mapping rule, each data point is extracted from the complete monitoring data in the order of collection time. According to the spatiotemporal information of the sensor associated with the data point, the corresponding spatial axis coordinate and time axis coordinate in the unified coordinate system are found. The thickness distribution value, temperature gradient value, strain state value and other monitoring information carried by each data point are bound with the corresponding coordinates to generate a three-dimensional data group containing coordinate information and monitoring data. All data groups are positioned and labeled in the unified coordinate system according to the coordinate positions, and different types of monitoring data are presented by different color layers, and finally a process state panoramic map is formed, which can comprehensively and intuitively reflect the process state of each time node and each spatial position in the whole production process of the inner liner pipe.

[0084] The beneficial effects are as follows: by using precise measurement tools to determine the three-dimensional coordinates of sensors, synchronously calibrating clocks to ensure the continuity of time series, and combining trigger-type sensing and ranging devices to acquire material motion parameters, a unified coordinate system is constructed in a standardized manner and mapping rules are clarified. This achieves high-precision mapping of complete monitoring data to a unified coordinate system. The resulting panoramic view of the process status can not only intuitively present the spatiotemporal distribution characteristics of the production process, but also accurately correlate the monitoring data of each location and time period, which greatly improves the visualization of the process status and the data correlation. This provides more accurate and systematic data support for subsequent multi-physics coupling analysis and process parameter analysis, and further ensures the accuracy and efficiency of subsequent process analysis work.

[0085] S4. Perform multi-physics coupling analysis on the panoramic view of the process status and identify the intrinsic interaction between process parameters in the inner liner tube to obtain a process status analysis report of the inner liner tube.

[0086] In this embodiment of the invention, the step of performing multiphysics coupling analysis on the panoramic view of the process status and identifying the intrinsic interaction relationships between process parameters in the inner liner tube to obtain a process status analysis report of the inner liner tube includes:

[0087] Extract the detection data sequence of the physical field from the panoramic view of the process state to analyze the statistical characteristics of the detection data sequence;

[0088] Based on the data evaluation results, the credibility of the physical field is evaluated to obtain the mass weight coefficient of the physical field;

[0089] The coupling strength between the physical fields is calculated based on the statistical characteristics and the mass weights.

[0090] Based on the coupling strength, the intrinsic interaction between process parameters in the inner liner is analyzed to obtain a process status analysis report of the inner liner.

[0091] The formula for calculating the coupling strength is:

[0092] ;

[0093] in, Indicates the coupling strength, This represents the sequence of detection data for the physical field. express and covariance, This represents the standard deviation of the detected data sequence. This represents the mean of the detected data sequence. This represents the preset coupling strength weighting coefficient. This represents the preset mean difference scaling factor. represents a preset standard deviation weight coefficient, represents the quality weight coefficient of the represents the number of the physical field, represents an exponential function, represents an absolute value.

[0094] The monitoring data corresponding to each physical field such as the temperature field, the strain field and the thickness field is separated from the process state panoramic diagram, and all data points of each physical field are arranged in sequence according to the production time sequence and the spatial position distribution, so as to form a continuous detection data sequence. The system of each detection data sequence is combed, the sum of the values of all data points in the sequence is counted and divided by the total number of data points, so as to obtain the average level of the data; the maximum value and the minimum value in the sequence are found out, and the difference between the two is calculated to obtain the fluctuation range of the data; the values of adjacent data points are compared one by one, and the number and amplitude of the times of the value rising, falling or remaining stable are recorded, and the change trend of the data is summarized; the distribution characteristics of the data are determined by counting the repeated values and the occurrence frequency in the data sequence, and the statistical characteristics of the detection data sequence are comprehensively analyzed.

[0095] The data evaluation result obtained before is called, for the detection data sequence of each physical field, the total number of missing sections and discrete points is counted, and the proportion of the number in the total number of physical field detection data is calculated; according to the abnormal level marked in the data evaluation result, the abnormal data of each physical field is calculated by weighting, and the abnormal weighted value is obtained; the proportion of abnormal data and the abnormal weighted value are added to obtain the comprehensive confidence score, and the higher the confidence score is, the lower the physical field data confidence is. According to the comprehensive confidence score, the interval is divided, the lowest interval corresponds to the highest quality weight coefficient, and the highest interval corresponds to the lowest quality weight coefficient, and accordingly the corresponding quality weight coefficient is allocated to each physical field.

[0096] Any two physical fields are selected as a group of analysis objects, the change trend of the detection data sequence of the two is compared first, and whether the law of synchronous rising, synchronous falling or reverse change is judged; then the overlap proportion of the fluctuation ranges of the two groups of data is calculated, and the higher the overlap proportion is, the stronger the consistency of the data fluctuation is; at the same time, the difference between the average levels of the two is compared, and the difference value is recorded. The detection data sequence involved in these comparison processes is the physical field detection data sequence in the formula, the average level of the data corresponds to the mean, the fluctuation range related calculation corresponds to the standard deviation, the correlation degree of the two data corresponds to the covariance, and the quality weight coefficient obtained before is the first ​The mass weight coefficients of each physical field are used, and the total number of physical fields is the number of physical fields in the formula. The preset coupling strength weight coefficient, mean difference scaling factor, and standard deviation weight coefficient are fixed values ​​set during system initialization based on the theoretical importance of correlation and the need for influence adjustment. The formula first calculates for all pairwise physical fields, then uses the coupling strength weight coefficient to correct the ratio of the product of their covariance and standard deviation. Next, it uses an exponential function to adjust for the influence of mean difference. Finally, it sums all pairwise calculation results and divides them by the product of the number of physical fields and the number minus one for normalization. Simultaneously, it calculates the sum of the products of the mass weight coefficients of all physical fields and their respective standard deviations, corrects this with the standard deviation weight coefficient, and adds it to the previous results to comprehensively quantify the degree of correlation between physical fields. Combining the above comparison results with the mass weight coefficients of each physical field, the physical field with the higher mass weight coefficient has a greater influence on the coupling strength due to its data characteristics. After comprehensively considering these factors, the degree of correlation between the two sets of physical fields is quantitatively judged, obtaining the coupling strength between them. The coupling strength between all pairs of physical fields is calculated sequentially in the same way.

[0097] The coupling strength between all physical fields was graded, with the highest coupling strength indicating strong correlation, the middle range indicating moderate correlation, and the lowest range indicating weak correlation. Based on the grading results, strongly correlated process parameters showed significant mutual influence; for example, when temperature and strain parameters were strongly correlated, even a small change in temperature would cause a significant fluctuation in strain. Moderately correlated process parameters had moderate mutual influence, while weakly correlated process parameters had negligible mutual influence. The system systematically analyzed the correlation levels and influence directions among all process parameters, clarifying the correspondence between dominant and subordinate process parameters. These analytical results were compiled and summarized to form a process state analysis report for the inner liner tube, including parameter correlations, influence levels, and operational patterns.

[0098] The beneficial effects are that by systematically analyzing the statistical characteristics of physical field data and combining the data evaluation results, the mass weight coefficients are accurately allocated. Then, relying on formulas with clear parameter sources, the coupling strength is calculated by comprehensively considering multiple factors. Finally, the intrinsic relationship between process parameters is accurately identified, and the resulting process status analysis report is comprehensive and reliable, providing a scientific basis for subsequent process parameter adjustments and effectively ensuring the pertinence and rationality of parameter optimization.

[0099] S5. Based on the process status analysis report, adjust the process parameters of the inner liner tube to obtain the optimized parameters of the inner liner tube, and encode the optimized parameters into the production control instructions for the inner liner tube.

[0100] In the embodiment of the present application, the process parameters of the inner liner pipe are adjusted according to the process state analysis report, the optimized parameters of the inner liner pipe are obtained, and the optimized parameters are encoded into the production control instructions of the inner liner pipe, comprising:

[0101] Based on the process state analysis report, the priority of the process parameters of the inner liner pipe is analyzed, and the adjustment sequence and optimization weight of the process parameters are obtained;

[0102] The adjustment sequence, the optimization weight and the internal interaction are integrated to obtain the synergistic optimization strategy of the process parameters;

[0103] According to the synergistic optimization strategy, the process parameters are adjusted in stages and gradually to obtain the optimized parameters of the inner liner pipe;

[0104] According to the target production quality requirements of the inner liner pipe, the optimized parameters are encoded into the production control instructions of the inner liner pipe.

[0105] Based on the process state analysis report, all the process parameters of the inner liner pipe and the internal interaction between the parameters are extracted, and the influence degree of each process parameter on the key quality indicators such as pipe thickness distribution, temperature gradient and strain state is determined. The process parameters that affect the key quality indicators and have strong correlation with other parameters are listed as core parameters, and the process parameters that affect the secondary quality indicators or have weak correlation are listed as secondary parameters, so as to determine the adjustment sequence of the process parameters. The influence weight of the parameters on the production quality is quantitatively allocated, the core parameters correspond to higher optimization weight, and the secondary parameters correspond to lower optimization weight. By comparing the influence range and correlation strength of each parameter, the specific optimization weight value of each process parameter is determined, and finally the adjustment sequence and optimization weight of the process parameters are obtained.

[0106] The determined process parameter adjustment sequence is used as a basic framework, and the optimization weight of each parameter is sorted according to the sequence to ensure that the high weight parameters occupy the priority position in the adjustment process. Combined with the internal interaction between the parameters in the process state analysis report, the mutual influence of different parameter adjustments is analyzed. For the parameters with strong correlation, the adjacent adjustment period is arranged in the adjustment sequence to avoid process fluctuations caused by different parameter adjustments. For each adjustment stage, the optimization weight of the corresponding parameter and the synergistic requirements of the associated parameters are integrated to determine the adjustment direction and amplitude limit of each parameter, and a set of process parameter synergistic optimization strategies considering the adjustment sequence, optimization weight and interaction between parameters are formed.

[0107] The adjustment phases are divided according to a collaborative optimization strategy. In the first phase, only the highest-priority core process parameters are adjusted. The adjustment range is determined based on their optimization weights, and the parameter values ​​are gradually changed through the control components of the production equipment. Simultaneously, a distributed sensor array network collects production data in real time after the adjustments to verify whether the impact of parameter changes on the process status meets expectations. After the first phase stabilizes, the second phase begins, adjusting the next highest-priority parameters. Again, the adjustment range is controlled according to the optimization weights, and the values ​​of related core parameters are fine-tuned based on their intrinsic relationship with the already adjusted core parameters to ensure coordinated matching between parameters. This logic is followed to complete the parameter adjustments in all phases. After each phase, data collection verifies the adjustment effect, ultimately yielding optimized parameters for the inner liner pipe that meet the process requirements.

[0108] The target production quality requirements for the inner lining tubes are clearly defined, including specific standards such as the thickness distribution tolerance range, the reasonable temperature gradient range, and the safety threshold for strain states. The optimized parameters are then compared with these standards to confirm that all optimized parameters are within the target requirements. Based on the control protocol and signal reception format of the production equipment, the specific value of each optimized parameter is converted into a digital signal or instruction code that the equipment can recognize. For example, temperature optimization parameters are converted into voltage signal instructions corresponding to the temperature control module, and speed optimization parameters are converted into pulse signal instructions corresponding to the drive module. The encoded results of all parameters are integrated to ensure a unified instruction format and logical coherence, forming inner lining tube production control instructions that can be directly issued to the production terminal.

[0109] The beneficial effects are that scientific priority analysis clarifies the key points of parameter adjustment, and the formation of a collaborative optimization strategy based on the inherent interaction relationship. The phased adjustment ensures the accuracy and stability of parameter optimization. The coded production control instructions can be directly adapted to the production equipment, realizing a seamless connection between process parameters from optimization to execution, and effectively improving the controllability of the inner liner tube production process and the compliance rate of production quality.

[0110] S6. Issue the production control command and check the production quality of the inner lining tube after adjustment to obtain the quality inspection report of the inner lining tube.

[0111] In this embodiment of the invention, the step of issuing the production control command and detecting the production quality of the inner liner after adjustment to obtain a quality inspection report for the inner liner includes:

[0112] The production control command is input to the production terminal of the inner liner tube, and the command execution status of the inner liner tube after regulation is monitored in real time.

[0113] The production data of the regulated inner liner is collected through the distributed sensor array network, and the degree of conformity between the production data and the target production quality requirements of the inner liner is evaluated to obtain the quality compliance result of the regulated inner liner.

[0114] According to the target production quality requirement, the causes of the substandard production data in the production data are diagnosed to generate improvement suggestions for the liner pipe in the production process;

[0115] The improvement suggestions and the quality standard reaching results are combined to obtain a quality detection report of the liner pipe.

[0116] The encoded liner pipe production control instructions are transmitted to a liner pipe production terminal through a special wired communication interface. The production terminal includes core execution components such as an extruder control unit, a temperature control module, and a traction speed adjustment module. Each component returns signal reception confirmation information immediately after receiving the corresponding instructions, ensuring that there is no omission in the instruction transmission. At the same time, through the real-time feedback interface of the production terminal, the running parameters of each component are continuously collected, including the actual adjusted process parameter values, the equipment running power, the component working state identifier, etc. The actual running data collected is compared with the preset parameters in the production control instructions one by one to determine whether each component completes the parameter adjustment and stably operates according to the instruction requirements, and the instruction execution state of the liner pipe after regulation and control is monitored in real time.

[0117] The continuous working state of the distributed sensor array network is maintained, and the production data such as the thickness distribution, the temperature gradient, and the strain state in the liner pipe production process after regulation and control are synchronously collected at the collection frequency corresponding to the production control instructions, to ensure that the data collection covers the full section and the whole process of pipe production. The target production quality requirements of the liner pipe are determined, including the specific standards such as the allowed tolerance of the thickness distribution, the reasonable interval of the temperature gradient, and the safety threshold of the strain state. Each group of collected production data is compared with the corresponding standards one by one. If all the production data are within the target requirement range, it is determined that the quality is standard reaching; if any group of data exceeds the target requirement range, it is determined that the quality is substandard, and the specific type and the spatiotemporal position of the substandard data are recorded to obtain the quality standard reaching result of the liner pipe after regulation and control.

[0118] For the substandard production data marked in the quality standard reaching result, the production period corresponding to the substandard data, the involved process parameters, and the equipment running state are traced in combination with the target production quality requirements of the liner pipe and the process logic of the production process. The differences between the substandard data and the surrounding standard reaching data are analyzed, and information such as the process parameter adjustment record, the equipment running load change, and the material supply state in the period are associated to investigate the specific factors leading to the substandard data. If the thickness exceeds the standard and the temperature parameter in the corresponding period deviates from the optimized value, it is determined that the reason is that the temperature regulation does not completely adapt to the thickness requirement; if the strain data is abnormal and the traction speed fluctuates, it is determined that the reason is that the unstable traction speed affects the pipe deformation. According to the specific reasons, targeted improvement measures are developed, such as adjusting the regulation range of the corresponding process parameters and optimizing the equipment running load distribution, to generate improvement suggestions for the production process.

[0119] The quality up-to-standard results are systematically arranged according to production period, detection item, and up-to-standard condition, and all up-to-standard detection items and corresponding qualified data range are explicitly listed, and the unqualified detection item, specific value of unqualified data, and time and space position are recorded in detail. The generated improvement suggestions are sorted according to reason type, targeted measures, and implementation steps in sequence, and it is ensured that the suggestions are specific and operable. The arranged quality up-to-standard results and improvement suggestions are integrated together, and are typeset according to a unified report format. The report includes four core parts of detection overview, quality up-to-standard details, unqualified reason analysis, and improvement suggestions, and a complete quality detection report of the inner liner pipe is formed.

[0120] Beneficial effects are that the production control instructions are ensured to be effectively implemented through the explicit instruction transmission and execution monitoring mechanism, the real quality up-to-standard results are obtained relying on comprehensive data collection and accurate fitness evaluation, the unqualified reasons are traced according to the process logic and the feasible improvement suggestions are made, and finally the quality detection report is formed to be comprehensive, detailed and instructive, which provides a reliable basis for subsequent production process optimization and quality control, and effectively improves the stability and traceability of the inner liner pipe production quality.

[0121] Embodiment Two

[0122] As shown in Figure 2 , the embodiment also provides a functional module diagram of the PE inner liner pipe production detection system based on distributed sensors.

[0123] The PE inner liner pipe production detection system based on distributed sensors 100 described in the embodiment can be installed in an electronic device. According to the implemented functions, the PE inner liner pipe production detection system based on distributed sensors 100 can include a data evaluation module 101, a data reconstruction module 102, a process state panoramic map construction module 103, a process state analysis module 104, a production control instruction generation module 105, and a production quality detection module 106. The modules described in the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0124] In the embodiment, the functions of each module / unit are as follows:

[0125] The data evaluation module 101 is used for collecting the original monitoring data of the inner liner pipe through the distributed sensor array network, evaluating the signal quality of the original monitoring data, marking the abnormal data segment in the original monitoring data, and obtaining the data evaluation result of the inner liner pipe.

[0126] The data reconstruction module 102 is configured to reconstruct the data evaluation result based on the data evaluation result and the spatiotemporal continuity feature of the original monitoring data, to obtain complete monitoring data of the inner liner pipe.

[0127] The process state panoramic map construction module 103 is configured to map the complete monitoring data to a preset unified coordinate system according to the association between the distributed sensor array network and the material track in the inner liner pipe, to obtain a process state panoramic map of the inner liner pipe.

[0128] The process state analysis module 104 is configured to perform multi-physical field coupling analysis on the process state panoramic map, and identify the internal action relationship between process parameters in the inner liner pipe, to obtain a process state analysis report of the inner liner pipe.

[0129] The production control instruction generation module 105 is configured to adjust the process parameters of the inner liner pipe according to the process state analysis report, to obtain optimized parameters of the inner liner pipe, and encode the optimized parameters into a production control instruction of the inner liner pipe.

[0130] The production quality detection module 106 is configured to issue the production control instruction, and detect the production quality of the inner liner pipe after regulation and control, to obtain a quality detection report of the inner liner pipe.

[0131] In detail, the modules in the PE inner liner pipe production detection system 100 based on distributed sensors in the embodiment of the present application adopt the same technical means as the PE inner liner pipe production detection method based on distributed sensors in the embodiment one and the embodiment two when in use, and can produce the same technical effects, which will not be described here.

[0132] Embodiment three

[0133] The embodiment provides a medium storing a computer program, which is executed by a processor to realize the steps of the image editing method.

[0134] These program codes can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to generate a computer implemented process, so that the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in the flow Figure 1 In one flow or multiple flows.

[0135] Media can include, but is not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by a computing device.

[0136] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the term "includes" and / or "including" means incorporating with or having, whether fully or partially.

[0137] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the term "includes" and / or "including" means incorporating with or having, whether fully or partially.

[0138] In several embodiments provided by the present application, it should be understood that the disclosed medium, system and method can be implemented in other ways. For example, the above-described system embodiments are only illustrative, and the division of the modules is only a logical functional division. Actual implementation can have another division.

[0139] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, i.e. can be located in one place or distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0140] In addition, the functional modules in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0141] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0142] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. The artificial intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results.

[0143] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method for detecting the production of PE liner pipe based on distributed sensors, characterized in that, The method comprises: S1, acquiring original monitoring data of the inner lining pipe through a distributed sensor array network, evaluating signal quality of the original monitoring data, and marking abnormal data segments in the original monitoring data to obtain a data evaluation result of the inner lining pipe; S2, based on the data evaluation result and a spatiotemporal continuity feature of the original monitoring data, reconstructing the data evaluation result to obtain complete monitoring data of the inner lining pipe; S3, according to an association relationship between the distributed sensor array network and a material track in the inner lining pipe, mapping the complete monitoring data to a preset unified coordinate system to obtain a process state panorama of the inner lining pipe; S4, performing multi-physical field coupling analysis on the process state panorama and identifying an internal action relationship between process parameters in the inner lining pipe to obtain a process state analysis report of the inner lining pipe, comprising: extracting a detection data sequence of a physical field in the process state panorama to analyze statistical features of the detection data sequence; based on the data evaluation result, performing credibility evaluation on the physical field to obtain a quality weight coefficient of the physical field; according to the statistical features and the quality weight, calculating a coupling strength between the physical fields, wherein a calculation formula of the coupling strength is: ； wherein, denotes the coupling strength, denotes a detection data sequence of the physical field, denotes and a covariance of, denotes a standard deviation of the detection data sequence, denotes a mean value of the detection data sequence, denotes a preset coupling strength weight coefficient, denotes a preset mean value difference scaling factor, denotes a preset standard deviation weight coefficient, denotes a quality weight coefficient of a th physical field, denotes a number of the physical fields, denotes an exponential function, denotes an absolute value; according to the coupling strength, analyzing the internal action relationship between the process parameters in the inner lining pipe to obtain the process state analysis report of the inner lining pipe; S5, according to the process state analysis report, adjusting process parameters of the inner lining pipe to obtain optimized parameters of the inner lining pipe, and encoding the optimized parameters into production control instructions of the inner lining pipe; S6, issuing the production control instructions and detecting production quality of the inner lining pipe after regulation and control to obtain a quality detection report of the inner lining pipe.

2. The distributed sensor based PE liner pipe production inspection method according to claim 1, wherein, The method comprises: acquiring thickness distribution, temperature gradient and strain state data of the inner lining pipe in the production process to obtain original monitoring data of the inner lining pipe; verifying time sequence integrity and spatial consistency of the original monitoring data to identify missing segments and discrete points in the original monitoring data; quantitatively aggregating time and space positions, abnormal types and abnormal levels of the missing segments and the discrete points to obtain a data evaluation result of the inner lining pipe.

3. The distributed sensor based PE liner pipe production inspection method according to claim 1, wherein, The method comprises: according to a spatiotemporal continuity feature of the original monitoring data, taking normal data features adjacent to abnormal data segments in the data evaluation result as a data repair benchmark of the inner lining pipe; by associating adjacent normal data segments of the abnormal data segments and historical data of the inner lining pipe, repairing the abnormal data segments to obtain reconstructed data of the inner lining pipe; Verify the continuity and consistency of the reconstructed data and the surrounding normal data in the reconstructed data to obtain complete monitoring data of the inner liner pipe.

4. The distributed sensor-based PE liner pipe production inspection method of claim 1, wherein, According to the correlation between the distributed sensor array network and the material trajectory in the inner liner pipe, the complete monitoring data is mapped into a preset unified coordinate system to obtain a process state panoramic map of the inner liner pipe, including: Analyzing the spatial position information and acquisition time sequence of the sensors in the distributed sensor array network to obtain the spatiotemporal coordinate description information of the sensors; According to the continuous motion characteristics of the material trajectory in the production process of the inner liner pipe, the average motion speed of the production material in the inner liner pipe along the material trajectory is obtained; Taking the production starting point of the inner liner pipe as the spatial origin, establishing the spatial axis with the direction of the material trajectory as the positive direction, and taking the total production time of the inner liner pipe as the time axis, a unified coordinate system of the inner liner pipe is constructed; According to the spatiotemporal coordinate description information and the average motion speed, the distance and time of the real-time acquisition data points in the distributed sensor array network to the spatial origin are quantified to determine the specific coordinates of the real-time acquisition data points in the unified coordinate system, and the coordinate mapping rule of the inner liner pipe is obtained; According to the coordinate mapping rule, the data points in the complete monitoring data are mapped one by one into the unified coordinate system to obtain the process state panoramic map of the inner liner pipe.

5. The distributed sensor-based PE liner pipe production inspection method of claim 1, wherein, According to the process state analysis report, the process parameters of the inner liner pipe are adjusted to obtain the optimized parameters of the inner liner pipe, and the optimized parameters are encoded into the production control instructions of the inner liner pipe, including: Based on the process state analysis report, the priority of the process parameters of the inner liner pipe is analyzed to obtain the adjustment order and optimization weight of the process parameters; Integrating the adjustment order, the optimization weight, and the internal action relationship to obtain the collaborative optimization strategy of the process parameters; According to the collaborative optimization strategy, the process parameters are adjusted in stages to obtain the optimized parameters of the inner liner pipe; According to the target production quality requirements of the inner liner pipe, the optimized parameters are encoded into the production control instructions of the inner liner pipe.

6. The distributed sensor-based PE liner pipe production inspection method according to claim 1, wherein, The production control instructions are issued, and the production quality of the regulated inner liner pipe is detected to obtain a quality detection report of the inner liner pipe, including: The production control instructions are input into the production terminal of the inner liner pipe, and the instruction execution state of the regulated inner liner pipe is monitored in real time; The production data of the regulated inner liner pipe is collected through the distributed sensor array network, the fit degree of the production data and the target production quality requirements of the inner liner pipe is evaluated, and the quality standard result of the regulated inner liner pipe is obtained; According to the target production quality requirements, the causes of the unqualified production data in the production data are diagnosed to generate improvement suggestions for the production process of the inner liner pipe; The improvement suggestions and the quality standard result are combined to obtain the quality detection report of the inner liner pipe.

7. A PE liner pipe production inspection system based on distributed sensors, characterized in that, The system for implementing the distributed sensor-based PE inner liner pipe production detection method of claim 1, the system comprising: a data evaluation module, configured to collect original monitoring data of the inner lining pipe through the distributed sensor array network, evaluate signal quality of the original monitoring data, and mark abnormal data segments in the original monitoring data, to obtain a data evaluation result of the inner lining pipe; a data reconstruction module, configured to perform data reconstruction on the data evaluation result based on the data evaluation result and a spatiotemporal continuity feature of the original monitoring data, to obtain complete monitoring data of the inner lining pipe; a process state panoramic map construction module, configured to map the complete monitoring data to a preset unified coordinate system according to an association relationship between the distributed sensor array network and a material track in the inner lining pipe, to obtain a process state panoramic map of the inner lining pipe; a process state analysis module, configured to perform multi-physical field coupling analysis on the process state panoramic map, and identify an internal action relationship between process parameters in the inner lining pipe, to obtain a process state analysis report of the inner lining pipe, including: extracting a detection data sequence of a physical field in the process state panoramic map, to analyze statistical features of the detection data sequence; performing credibility evaluation on the physical field based on the data evaluation result, to obtain a quality weight coefficient of the physical field; calculating coupling strength between the physical fields according to the statistical features and the quality weight, wherein a calculation formula of the coupling strength is: ； wherein, denotes the coupling strength, denotes a detection data sequence of the physical field, denotes and a covariance of denotes a standard deviation of the detection data sequence, denotes a mean value of the detection data sequence, denotes a preset coupling strength weight coefficient, denotes a preset mean value difference scaling factor, denotes a preset standard deviation weight coefficient, denotes a quality weight coefficient of the physical field, denotes a number of the physical fields, denotes the number of the physical fields, denotes an exponential function, denotes an absolute value; analyzing the internal action relationship between process parameters in the inner lining pipe according to the coupling strength, to obtain the process state analysis report of the inner lining pipe; a production control instruction generation module, configured to adjust process parameters of the inner lining pipe according to the process state analysis report, to obtain optimized parameters of the inner lining pipe, and encode the optimized parameters into a production control instruction of the inner lining pipe; a production quality detection module, configured to issue the production control instruction, and detect production quality of the inner lining pipe after regulation and control, to obtain a quality detection report of the inner lining pipe.

8. A computer readable medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement steps of the method in any one of claims 1 to 6.

Images