Production management method and system for plastic-sleeve-steel thermal insulation pipe

Abstract

The present application relates to the technical field of intelligent manufacturing, in particular to a plastic sleeve steel heat preservation pipe production management method and system, comprising the following steps: extracting heat preservation pipe multi-parameter evaluation sensitivity, dynamically adjusting injection parameters, monitoring forming data, identifying forming abnormalities, outputting control instructions, recording execution deviations, optimizing configuration tables, and generating management records. In the present application, by extracting heat preservation pipe wall thickness fluctuation, bubble structure size and center offset data, the response degree of each specification to injection parameter change is determined, a sensitivity level configuration is established, the parameter adjustment accuracy is improved, real-time data is collected and combined with target value to calculate the change trend, the forming state is dynamically mastered, the abnormal paragraphs are identified based on time series and trend clustering, accurate identification under multi-source interference is realized, adjustment instructions are generated combined with deviation direction and frequency information, injection rhythm matching is improved, and a dynamic regulation and control mechanism based on trend calculation and pattern recognition is formed as a whole, effectively enhancing the forming consistency and abnormal response efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent manufacturing, in particular to a plastic-steel composite pipe production management method and system. BACKGROUND

[0002] The technical field of intelligent manufacturing includes integrated technologies of manufacturing automation, digitization and informatization, and the core content is to realize intelligent perception, intelligent decision and intelligent execution of the manufacturing process through software and hardware system collaboration, optimize production efficiency and resource allocation, involve manufacturing execution system, industrial control system, automation equipment and information management platform, and complete perception, analysis and control of the whole manufacturing process under data driving, form a highly collaborative production network, and the technical field of intelligent manufacturing relies on the integration of information technology, industrial software and automatic control technology, and is widely applied to various discrete manufacturing and process manufacturing industries, and is a key direction for the development of modern manufacturing from automation to intelligence.

[0003] Among them, the plastic-steel composite pipe production management method focuses on the process coordination and production information processing in the composite manufacturing process of pipe insulation materials, covers multiple production links such as raw material processing, plastic outer protective layer sleeving, steel pipe prefabrication assembly, and insulation layer injection of insulation pipes, adopts material coding and real-time tracking means to collect and analyze production data of each process, schedules task instructions, process parameters and station information based on a manufacturing execution system, controls material warehouse in and out and process tracing in combination with a bar code scanning device, introduces a database management means to centrally manage order information, production line status and finished product flow records, compares data results of key process nodes by setting fixed logic rules, and realizes information interconnection and sequence coordination of operation processes between production stages.

[0004] In the actual operation of the prior art, each link is coordinated by relying on rule setting and result comparison, and there is a lack of real-time deep analysis of process variables, which leads to a lag in response to the gradual trend and implicit fluctuations in the forming process. In the injection process, the matching degree of the collected value and the process setting is used to judge the quality state, and the trend deviation existing in the parameter fluctuation cannot be identified, so that part of the small abnormalities evolves into substantial defects after accumulation, causing the rejection rate of finished products to rise. Depending on the fixed value threshold to judge the process nodes, when multiple specifications are parallel or frequently switched, due to insufficient parameter adaptability, the debugging time is prolonged and the forming precision is reduced, thereby restricting the flexible operation ability of the overall production line, and it is difficult to cover the active response ability of the process under the multi-element disturbance scene, and the realization degree of lean production is limited. SUMMARY

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present application provide a plastic-steel composite pipe production management method and system. The technical solution is as follows:

[0006] In order to achieve the above object, the present application adopts the following technical scheme, a plastic sleeve steel thermal insulation pipe production management method, comprising the following steps:

[0007] S1: By extracting the wall thickness fluctuation, bubble structure size and center offset data of a plurality of specifications of plastic sleeve steel thermal insulation pipes, the sensitivity of each specification configuration to the control parameter is evaluated, and the injection step length and adjustment frequency value are dynamically adjusted according to the sensitivity, and a pipe diameter sensitivity level configuration table is constructed;

[0008] S2: Based on the pipe diameter sensitivity level configuration table, the injection port back pressure signal, pipe wall thickness, inner diameter and injection rate value in the production process of the thermal insulation pipe are collected, the injection speed target center value is called, the injection port back pressure change slope, wall thickness deviation value, inner diameter fluctuation trend direction, injection speed variation amplitude and target value deviation are calculated, and a forming monitoring data set is output;

[0009] S3: Based on the forming monitoring data set, the time period when the injection port back pressure signal is lower than the lower limit pressure is screened, the continuous deviation interval in the pipe wall thickness deviation sequence is identified, the K-Means algorithm is used to classify the inner diameter fluctuation trend, the forming state of the thermal insulation pipe is identified, and forming abnormality identification information is output;

[0010] S4: Based on the forming abnormality identification information, the abnormal type and time characteristics are obtained, the difference between the injection speed value and the target center value is calculated and the directional parameter is extracted, the corresponding injection step length and adjustment frequency value are combined, and the injection rhythm control instruction is output.

[0011] As a further scheme of the present application, the pipe diameter sensitivity level configuration table includes specification grading standards, control parameter adaptation range, sensitivity grading index, the forming monitoring data set includes wall thickness stability index, back pressure dynamic change curve, inner diameter fluctuation model, the forming abnormality identification information includes abnormal type mark, abnormal occurrence time period, pattern recognition label, and the injection rhythm control instruction includes rhythm adjustment direction, injection rate correction value, response timing parameter;

[0012] The pattern recognition label is a classification result generated by using the K-Means algorithm on the inner diameter fluctuation trend in the forming process data, and is used to represent different types of forming fluctuation patterns;

[0013] The response timing parameter refers to the time response characteristic parameter that needs to be referred to when the control system adjusts the injection rhythm after identifying the forming abnormality, including instruction validity delay, response duration, adjustment slope.

[0014] As a further scheme of the present application, the steps for constructing the pipe diameter sensitivity level configuration table by extracting the wall thickness fluctuation, bubble structure size and center offset data of multiple specifications of plastic jacketed steel thermal insulation pipes, evaluating the sensitivity of each specification configuration to the control parameters, and dynamically adjusting the injection step length and adjustment frequency values according to the sensitivity are as follows:

[0015] S101: Obtain a thermal insulation pipe specification parameter set by extracting the wall thickness fluctuation value, bubble structure size value and center offset data value of multiple specifications of plastic jacketed steel thermal insulation pipes;

[0016] S102: Call the thermal insulation pipe specification parameter set, quantitatively assign weights to the parameters according to the wall thickness fluctuation value, bubble structure size value and center offset data value corresponding to each specification using the analytic hierarchy process, analyze the sensitivity requirement of multiple specification configurations to production control parameters, and obtain a sensitivity level value;

[0017] The analytic hierarchy process calculates the relative influence coefficients of the wall thickness fluctuation, bubble structure size and center offset value by constructing a parameter judgment matrix, multiplies each specification parameter value by the corresponding influence coefficient after standardization, and sums up to obtain a sensitivity score value for each specification;

[0018] S103: Based on the sensitivity level value, dynamically adjust the injection step length and adjustment frequency value parameters corresponding to each thermal insulation pipe specification, establish a mapping relationship between the control parameters and the sensitivity level, and obtain a pipe diameter sensitivity level configuration table;

[0019] As a further scheme of the present application, based on the pipe diameter sensitivity level configuration table, collect the injection port back pressure signal, pipe wall thickness, inner diameter and injection rate value in the production process of the thermal insulation pipe, call the injection speed target center value, calculate the injection port back pressure change slope, wall thickness deviation value, inner diameter fluctuation trend direction, injection speed variation amplitude and target value deviation, and output a forming monitoring data set, the steps are as follows:

[0020] S201: Based on the pipe diameter sensitivity level configuration table, collect the injection port back pressure signal value, pipe wall thickness value, inner diameter value and injection rate value in the production process of the thermal insulation pipe, extract the injection speed target center value, and number and classify each data point in chronological order to generate a forming process basic data set;

[0021] S202: Call the forming process basic data set, calculate the injection speed variation amplitude, and obtain the target value deviation according to the difference between the injection speed target center value and the actual injection rate value to obtain an injection speed characteristic parameter group;

[0022] S203: According to the injection speed characteristic parameter group, extract the injection port back pressure change slope, calculate the wall thickness deviation value and the inner diameter fluctuation trend direction, and obtain a forming monitoring data set.

[0023] As a further scheme of the present application, based on the forming monitoring data set, the time period when the back pressure signal of the injection port is lower than the lower limit pressure is screened, the continuous deviation interval in the pipe wall thickness deviation sequence is identified, the K-Means algorithm is used to classify the inner diameter fluctuation trend, the forming state of the heat preservation pipe is identified, and the step of outputting the forming abnormality identification information is specifically:

[0024] S301: Based on the forming monitoring data set, the injection port back pressure signal value sequence is extracted, and compared with the set injection lower limit pressure threshold value, the continuous time period interval lower than the limited value is screened, and the low pressure interval data segment is obtained;

[0025] The lower limit pressure threshold value is the lowest allowed back pressure value set according to the rated minimum working pressure of the equipment, the material filling continuity requirement and the stability boundary of the forming process during the injection process;

[0026] S302: The low pressure interval data segment is called, the pipe wall thickness deviation value sequence is extracted, and compared with the set fluctuation deviation limit, the deviation value is detected and the continuous deviation interval is identified, and the wall thickness deviation extension interval is obtained;

[0027] The fluctuation deviation limit is set as a limit value by analyzing the fluctuation range of the pipe wall thickness in multiple forming processes, calculating the mean value and standard deviation, and setting a maximum fluctuation range as a limit value;

[0028] S303: According to the wall thickness deviation extension interval, according to the low pressure interval data segment, the continuous deviation interval and the inner diameter fluctuation trend data, the slope feature of the inner diameter change trend is extracted, the data is multi-dimensional feature construction, the K-Means algorithm is used for clustering analysis, the forming state of the heat preservation pipe is identified and the corresponding state label is recorded, and the forming abnormality identification information is obtained;

[0029] The specific formula for identifying the forming state of the heat preservation pipe and recording the corresponding state label is:

[0030]

[0031] Calculate the deviation feature value D Δ ′;

[0032] Wherein, D Δ ′ is the corrected comprehensive deviation feature value, n is the total number of sampling points in the continuous deviation interval, j is the index number of the sampling point in the continuous deviation interval, is the actual inner diameter data of the heat preservation pipe of the jth sampling point, is the target reference inner diameter value of the jth sampling point, is the measurement time of the jth sampling point at the outlet of the heat preservation pipe, is the measurement time of the jth sampling point at the forming inlet of the vacuum tube, j is the linear speed of the jth sampling point in the vacuum tube forming process, is the standard deviation of the inner diameter data of all sampling points in the sustained deviation interval;

[0033] The K-Means algorithm refers to clustering and classifying time series data according to the slope characteristics of the inner diameter fluctuation trend, and outputting the forming mode label corresponding to each time period.

[0034] As a further scheme of the present application, based on the forming abnormality identification information, the abnormal type and time characteristics are obtained, the difference between the injection speed value and the target center value is calculated, and the directional parameter is extracted, combined with the corresponding injection step length and adjustment frequency value, and the injection rhythm control instruction is outputted. The steps are specifically:

[0035] S401: Based on the forming abnormality identification information, the abnormal type state label and time index range value corresponding to each abnormal record are extracted, and the abnormal period characteristic parameter group is obtained;

[0036] S402: The actual injection speed value and injection speed target center value of the corresponding time period are extracted and the difference value is calculated by calling the abnormal period characteristic parameter group, the deviation trend direction is identified, including upward, downward and flat, and the injection speed direction index is obtained.

[0037] S403: According to the injection speed direction index, the injection step length value and the adjustment frequency value corresponding to the target vacuum tube specification are matched, the injection rhythm adjustment instruction is constructed, including the adjustment direction type, the rhythm intensity parameter, the frequency amplitude correction value, and the injection rhythm control instruction is generated.

[0038] As a further scheme of the present application, the specific formula for constructing the injection rhythm adjustment instruction is:

[0039]

[0040] The rhythm intensity correction value is calculated;

[0041] Where, P adj represents the rhythm intensity correction value, v act represents the normalized value of the actual injection speed, v tar represents the normalized reference of the target injection speed value, Δt i represents the relative time ratio of the abnormality duration in the ith time period, f iThe normalized value of the injection adjustment frequency in the i-th time period, ΔS represents the normalized value of the difference between the injection step value and the previous cycle step value, ΔF represents the normalized value of the difference between the injection adjustment frequency value and the previous cycle frequency value, n represents the number of time periods of abnormal state records, and i is the index letter of the abnormal time period in the time sequence.

[0042] As a further scheme of the present application, the method further comprises a step S5 of:

[0043] S5: based on the injection beat control instruction, collecting and analyzing the offset degree of the actual execution value and the target parameter, outputting an adjustment instruction, establishing an execution deviation record combined with timestamp information, and optimizing the pipe diameter sensitivity level configuration table dynamically, and outputting a heat preservation pipe production management record;

[0044] The heat preservation pipe production management record includes an execution deviation log, a parameter correction history, and sensitivity configuration update information.

[0045] As a further scheme of the present application, based on the injection beat control instruction, collecting and analyzing the offset degree of the actual execution value and the target parameter, outputting an adjustment instruction, establishing an execution deviation record combined with timestamp information, and optimizing the pipe diameter sensitivity level configuration table dynamically, and outputting a heat preservation pipe production management record, the step specifically comprises:

[0046] S501: based on the injection beat control instruction, collecting actual execution value data of the injection equipment and target parameter data in the corresponding time period and comparing them, calculating the numerical deviation amount between the injection speed value, the adjustment frequency value and the step value, and obtaining an execution parameter offset coefficient;

[0047] S502: calling the execution parameter offset coefficient, combining the deviation direction and amplitude characteristics corresponding to each group of offset coefficients, constructing a correction instruction parameter, and outputting an injection correction adjustment instruction;

[0048] S503: according to the injection correction adjustment instruction, extracting the effective timestamp of each instruction, establishing an execution deviation record combined with the actual execution value offset range in the corresponding time period, optimizing the pipe diameter sensitivity level configuration table according to the control parameter type corresponding to the deviation data, and generating a heat preservation pipe production management record.

[0049] On the other hand, a plastic jacketed steel heat preservation pipe production management system is provided, which is applied to the plastic jacketed steel heat preservation pipe production management method, and the system comprises:

[0050] The pipe diameter sensitivity evaluation module uses the wall thickness fluctuation, bubble structure size and center offset data to calculate the corresponding relationship between the wall thickness variation range, structure size average and center offset range of each specification, evaluates the sensitivity of each specification configuration to the control parameter, dynamically adjusts the injection step length and adjustment frequency value, constructs a pipe diameter sensitivity level configuration table and transmits it to the molding monitoring data acquisition module;

[0051] The molding monitoring data acquisition module acquires the injection port back pressure signal, pipe wall thickness, inner diameter and injection rate data in the production process of the heat preservation pipe based on the pipe diameter sensitivity level configuration table, calls the injection speed target center value, calculates the injection port back pressure change slope, wall thickness deviation value, inner diameter fluctuation trend direction, injection speed variation range and target value deviation, generates a molding monitoring data set and transmits it to the molding anomaly recognition module;

[0052] The molding anomaly recognition module filters the time period when the injection port back pressure signal is lower than the lower limit pressure, identifies the continuous deviation interval in the pipe wall thickness deviation sequence, classifies the inner diameter fluctuation trend by using the K-Means algorithm, identifies the molding state of the heat preservation pipe, generates molding anomaly recognition information and transmits it to the injection rhythm control module;

[0053] The injection rhythm control module obtains the abnormal type and time characteristics based on the molding anomaly recognition information, calculates the difference between the injection speed and the target center value and extracts the directional parameter, combines the injection step length and the adjustment frequency value, generates an injection rhythm control instruction and transmits it to the production management optimization module;

[0054] The production management optimization module acquires and analyzes the deviation degree of the actual execution value and the target parameter based on the injection rhythm control instruction, outputs an adjustment instruction, establishes an execution deviation record combined with the time stamp information, dynamically optimizes the pipe diameter sensitivity level configuration table and generates a heat preservation pipe production management record.

[0055] The technical scheme provided by the embodiment of the application has at least the following beneficial effects:

[0056] In the process of manufacturing the vacuum tube, by extracting the wall thickness fluctuation, bubble structure size and center offset data, based on the influence degree of various parameters on the forming effect, the sensitive level is divided, which can effectively avoid the inconsistency of different specification parameters on the injection behavior interference, optimize the accuracy of parameter setting response; in real-time production, the key indicators such as injection port back pressure, wall thickness, inner diameter and injection rate are collected, combined with the target center value, the trend slope and deviation range are calculated, not only the more accurate forming dynamic is obtained, but also the manufacturing quality can be fed back in real time; further filtering the low pressure period and wall thickness deviation sequence, combining the clustering algorithm to analyze the inner diameter change trend, the forming state can be patterned and classified, so as to accurately identify the abnormal stage and feature form in the multivariate disturbance; finally, combining the difference direction and frequency control, the beat control instruction is output, realizing the closed loop optimization of abnormal response. The series of actions in the manufacturing process constructs an intelligent adjustment chain driven by data, feedback response, abnormal discrimination and control adjustment, so that the injection behavior is no longer dependent on static setting, but can dynamically adapt to the forming trend, improve the control of product consistency, and significantly strengthen the process stability, production efficiency and precision of abnormal treatment. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0058] Figure 1 The workflow diagram of the present application;

[0059] Figure 2 The system flowchart of the present application. DETAILED DESCRIPTION

[0060] The technical solutions in the present application will be described below in combination with the drawings.

[0061] In the embodiments of the present application, the words such as "example", "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0062] In the embodiments of the present application, "image" and "picture" can be used interchangeably, and it should be pointed out that their meanings are consistent when their differences are not emphasized.

[0063] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1, and their meanings are consistent when their differences are not emphasized.

[0064] In order to make the technical problems, technical solutions and advantages to be solved by the present application more clear, the following will be described in detail with reference to the drawings and specific embodiments.

[0065] Please refer to Figure 1 The present application provides a technical solution, a plastic sleeve steel heat preservation pipe production management method, comprising the following steps:

[0066] S1: By extracting the wall thickness fluctuation, bubble structure size and center offset data of a plurality of specifications of plastic sleeve steel heat preservation pipes, the sensitivity of each specification configuration to control parameters is evaluated, and the injection step length and adjustment frequency value are dynamically adjusted according to the sensitivity, and a pipe diameter sensitivity level configuration table is constructed;

[0067] S2: Based on the pipe diameter sensitivity level configuration table, the injection port back pressure signal, pipe wall thickness, inner diameter and injection rate value in the production process of the heat preservation pipe are collected, the injection speed target center value is called, the injection port back pressure change slope, wall thickness deviation value, inner diameter fluctuation trend direction, injection speed variation amplitude and target value deviation are calculated, and a forming monitoring data set is output;

[0068] S3: Based on the forming monitoring data set, the time period when the injection port back pressure signal is lower than the lower limit pressure is screened, the continuous deviation interval in the pipe wall thickness deviation sequence is identified, the K-Means algorithm is used to classify the inner diameter fluctuation trend, the heat preservation pipe forming state is identified, and forming abnormality identification information is output;

[0069] S4: Based on the forming abnormality identification information, the abnormal type and time characteristics are obtained, the difference between the injection speed value and the target center value is calculated and the directional parameter is extracted, the corresponding injection step length and adjustment frequency value are combined, and the injection beat control instruction is output;

[0070] S5: Based on the injection beat control instruction, the offset degree of the actual execution value and the target parameter is collected and analyzed, the adjustment instruction is output, the execution deviation record is established combined with the time stamp information, and the dynamic optimization pipe diameter sensitivity level configuration table is optimized, and the heat preservation pipe production management record is output.

[0071] The pipe diameter sensitivity level configuration table includes specification grading standards, control parameter adaptation range, and sensitivity grading index. The forming monitoring data set includes wall thickness stability index, back pressure dynamic change curve, and inner diameter fluctuation model. The forming abnormality identification information includes abnormal type label, abnormal occurrence time period, and pattern recognition label. The injection beat control instruction includes beat adjustment direction, injection rate correction value, and response time sequence parameter. The heat preservation pipe production management record includes execution deviation log, parameter correction history, and sensitivity configuration update information.

[0072] The pattern recognition label is a classification result generated by using the K-Means algorithm on the inner diameter fluctuation trend in the forming process data, and is used to represent different types of forming fluctuation patterns.

[0073] The response time sequence parameter refers to the time response characteristic parameter that needs to be referred to when the control system adjusts the injection beat after identifying the forming abnormality, including instruction validity delay, response duration, and adjustment slope.

[0074] Please refer to Figure 1 , by extracting the wall thickness fluctuation, bubble structure size and center offset data of various specifications of plastic jacketed steel heat preservation pipes, the sensitivity of each specification configuration to the control parameter is evaluated, and the injection step and adjustment frequency value are dynamically adjusted according to the sensitivity, and the steps of constructing the pipe diameter sensitivity level configuration table are as follows:

[0075] S101: Obtain the heat preservation pipe specification parameter set by extracting the wall thickness fluctuation value, bubble structure size value and center offset data value of various specifications of plastic jacketed steel heat preservation pipes.

[0076] For the wall thickness fluctuation value, bubble structure size value and center offset data value of various specifications of plastic jacketed steel heat preservation pipes, the collection object needs to be determined first, and the representative specification range of the heat preservation pipe is set, such as DN65, DN80, DN100, etc. Three different specifications, 100 samples are selected from the production line for measurement of the three parameters. In the execution process, the wall thickness fluctuation value is obtained by measuring the wall thickness value at three fixed positions in each sample, which are denoted as t1, t2, t3, and the wall thickness fluctuation value Δt is calculated as follows: Δt = max(t1, t2, t3) - min(t1, t2, t3). If the thickness of a sample is t1 = 4.2 mm, t2 = 4.0 mm, and t3 = 3.8 mm, then the wall thickness fluctuation value is Δt = 4.2 - 3.8 = 0.4 mm. The bubble structure size value is obtained by statistically analyzing the average pore diameter of the bubble, such as 100 pore diameters in each of the 5 regions and the average value is obtained. The sampling points are denoted as D 1i ,D 2i ,…D 5i , and the average value is: The average pore size of the 5 regions is 1.1 mm, 1.2 mm, 1.0 mm, 1.3 mm, and 1.2 mm, respectively, and the value of the bubble structure size is recorded as the average value The center offset value is obtained by diameter measurement, and the distances from the tube core to the outer diameter in four directions are R1, R2, R3, and R4. The center offset is represented by the maximum difference, i.e. ΔR = max(R i )-min(R i ), for example, R1 = 25.2 mm, R2 = 24.8 mm, R3 = 24.9 mm, and R4 = 25.0 mm, then the center offset value is ΔR = 25.2-24.8 = 0.4 mm. The final three types of parameter result data need to be unified to form the heat preservation tube specification parameter set, as shown below:

[0077] Table 1 Heat Preservation Tube Specification Parameter Set

[0078] Gauge (OD) Wall thickness fluctuation value (mm) Cell structure size (mm) Center offset value (mm) DN65 0.3 1.10 0.2 DN80 0.4 1.16 0.4 DN100 0.5 1.25 0.6

[0079] Table 1 lists the three key parameters of different specifications of heat preservation tubes in the sample.

[0080] S102: Call the heat preservation tube specification parameter set, and according to the wall thickness fluctuation value, the bubble structure size value, and the center offset data value corresponding to each specification, use the analytic hierarchy process to quantitatively assign weights to the parameters, analyze the sensitivity requirement of multiple specification configurations to production control parameters, and obtain the sensitivity grade value;

[0081] After calling the above insulation pipe specification parameter set, the influence of wall thickness fluctuation value, bubble structure size value and center offset value on production control parameters (such as temperature regulation, injection rate, mold pressure) needs to be analyzed for each specification. In the specific implementation process, the corresponding relationship between each parameter and the production control variable needs to be tested to evaluate its sensitivity level. In the analysis process, first fix other conditions, only change the input of wall thickness fluctuation value, observe the change of molding stability and error amplitude, if the wall thickness fluctuation changes from 0.2mm to 0.5mm, and the error expands more than 5%, then the sensitivity is high. If the average pore size of the bubble structure is changed from 1.0mm to 1.4mm, and the corresponding foaming density deviation is observed to be more than 10%, then the parameter is more sensitive to foaming control. If the injection flow rate needs to be adjusted at a frequency of 1 time / 10min for every increase of 0.1mm in the center offset, then the sensitivity level is medium. For the above analysis, the sensitivity level division standard needs to be defined for each index: for example, less than 0.2mm is low sensitivity (L), 0.2-0.4mm is medium sensitivity (M), and more than 0.4mm is high sensitivity (H). The same method is used to divide the bubble size and offset level. The following judgment intervals are set: wall thickness fluctuation value sensitivity level: L (<0.2mm), M (0.2-0.4mm), H (>0.4mm), bubble structure size value sensitivity level: L (<1.1mm), M (1.1-1.3mm), H (>1.3mm), center offset value sensitivity level: L (<0.2mm), M (0.2-0.4mm), H (>0.4mm). By matching the three parameters of each specification with the sensitivity level, the following combinations can be obtained, for example, the DN80 pipe has three parameter values of 0.4mm, 1.16mm and 0.4mm, corresponding to the sensitivity levels of M, M and M. After statistical summary, the comprehensive sensitivity level score is obtained using the scoring method: L=1, M=2, H=3. The comprehensive sensitivity of DN80 is 2+2+2=6, which is medium sensitivity level (5-7 points). In this way, the corresponding sensitivity level value of each specification is generated to form the parameter sensitivity level evaluation table.

[0082] The analytic hierarchy process constructs a parameter judgment matrix, calculates the relative influence coefficients of wall thickness fluctuation, bubble structure size and center offset value, and multiplies the standardized parameter values of each specification with the corresponding influence coefficients and sums them up to obtain the sensitivity score value of each specification.

[0083] S103: Based on the sensitivity level value, dynamically adjust the injection step and adjustment frequency value parameters corresponding to each insulation pipe specification, establish the mapping relationship between the control parameters and the sensitivity level, and obtain the pipe diameter sensitivity level configuration table.

[0084] Based on the sensitivity level value score, set the dynamic response rule in the feeding control system, configure the matching of the feeding step and the adjustment frequency parameters for the insulation pipe specifications with different sensitivity levels, and during the execution, for the high sensitivity level (score > 7), for example, the DN100 specification score is 8, the feeding step is set to 70% of the standard value, for example, if the standard value is 5g / s, it is adjusted to 3.5g / s, and the adjustment frequency is increased from every 20 seconds to every 10 seconds; for the medium sensitivity level (score 5-7), the feeding step is set to 85% of the standard value, and the adjustment frequency is maintained every 15 seconds; for the low sensitivity level (score < 5), the default parameters are maintained, and the specific setting results are as follows:

[0085] Step adjustment parameter setting: high sensitivity (x0.7), medium sensitivity (x0.85), low sensitivity (x1.0);

[0086] Frequency adjustment parameter setting: high sensitivity (10 seconds), medium sensitivity (15 seconds), low sensitivity (20 seconds);

[0087] After establishing this matching relationship, a pipe diameter sensitivity level configuration table is constructed, the specification, three parameter values, sensitivity score and feeding control parameters are one-to-one corresponding, forming a standard configuration template, so as to facilitate the control system to call, for example, the feeding step of DN100 specification is 3.5g / s, the adjustment frequency is 10 seconds, forming a standardized control strategy configuration record. The results show that different insulation pipe specifications can configure corresponding control parameters according to their sensitivity levels, and realize the production process setting corresponding to the structural difference.

[0088] Please refer to Figure 1 , based on the pipe diameter sensitivity level configuration table, collect the feeding port back pressure signal, pipe wall thickness, inner diameter and feeding rate value in the insulation pipe production process, call the feeding speed target center value, calculate the feeding port back pressure change slope, wall thickness deviation value, inner diameter fluctuation trend direction, feeding speed variation amplitude and target value deviation, and output the steps of forming the monitoring data set as follows:

[0089] S201: Based on the pipe diameter sensitivity level configuration table, collect the feeding port back pressure signal value, pipe wall thickness value, inner diameter value and feeding rate value in the insulation pipe production process, extract the feeding speed target center value, and number and classify each data point in time stamp order to generate the forming process basic data set;

[0090] Based on the pipe diameter sensitivity level configuration table, in order to accurately perform the data acquisition task in the injection stage, first, four types of sensors are deployed in the molding system in turn: injection port back pressure sensor, laser thickness gauge, optical internal diameter scanner and mass flow meter, which collect corresponding physical variables respectively. The sampling period is uniformly set to 1 second / time, and four values are recorded at each sampling point and matched with the time stamp identifier. For example, at the injection starting point 10:00:01, the injection port pressure sensor detects a value of 2.5 MPa, the laser thickness gauge obtains a real-time pipe wall thickness of 4.0 mm, the optical system synchronously measures an internal diameter of 65.1 mm, and the mass flow meter feeds back that the injection mass in 1 second is 5.0 g, and the conversion injection rate is 5.0 g / s. Similarly, the sampling is continued to the 5th second, forming 5 continuous data points, each data point is numbered in time sequence from P001 to P005, and each variable is recorded into the database through the real-time control system to form the original basic data set. In actual production, taking a DN80 specification pipe sample as an example, this sampling strategy covers the complete time window from the injection head injection, bubble expansion to the mold cavity wall thickness stable stage, ensures that the linkage characteristics between wall thickness, internal diameter, rate and pressure are fully reflected in the basic data set, and the sampling results are shown in the following table.

[0091] Table 2 Injection process sampling data table

[0092]

[0093] As shown in Table 2, the data set summarizes five groups of real-time parameters of the injection process at different time points, which provides support for subsequent injection behavior modeling and monitoring of basic features.

[0094] S202: Call the molding process basic data set, calculate the injection speed variation amplitude, and obtain the target value deviation according to the difference between the injection speed target center value and the actual injection rate value, to obtain the injection speed characteristic parameter group;

[0095] After obtaining the basic data set, the variation amplitude of the injection rate sequence is analyzed. First, the injection rate is extracted as an array V=[5.0, 5.2, 5.5, 5.1, 5.3] according to the time sequence, and the absolute value of the difference between adjacent points is calculated. i+1 -v i| The difference sequence [0.2, 0.3, 0.4, 0.2] is obtained, the maximum variation amplitude is 0.4 g / s, which corresponds to the occurrence between the 3rd and 4th points, indicating that the rate change is most violent at this stage; then the target rate center value 5.2 g / s is extracted, and compared with the actual value of each point respectively, the target deviation vector is [-0.2, 0.0, 0.3, -0.1, 0.1], which can be regarded as the feedback item of the control error of the injection system, and the size of each deviation value directly affects the uniformity of foaming and the consistency of wall thickness; further classify the deviation values, the interval is as follows: deviation absolute value <0.1 is "low", 0.1-0.2 is "medium", >0.2 is "high", the low deviation points in this data are 2 (2nd, 5th points), the medium deviation is 2 (1st, 4th points), and the high deviation is 1 (3rd point), according to the actual injection control strategy, the deviation distribution will be used for subsequent step adjustment and frequency matching strategy adjustment, this analysis constructs the injection speed characteristic parameter group, which contains five deviation values, maximum amplitude, deviation level label and time index field, which provides the necessary basis for the slope trend extraction in the next paragraph.

[0096] S203: According to the injection speed characteristic parameter group, the injection port back pressure change slope is extracted, and the wall thickness deviation value and the inner diameter fluctuation trend direction are calculated to obtain the molding monitoring data set;

[0097] Based on the injection speed characteristic parameter group, the change characteristics of the forming behavior are further extracted. First, the pressure change rate in the adjacent time difference unit, i.e. the slope vector [0.1, 0.2, 0.2, 0.1] MPa / s, is calculated from the back pressure value sequence P = [2.5, 2.6, 2.8, 3.0, 3.1]. The calculation rule is: slope = current point pressure - previous time point pressure, and the time interval is uniform, i.e. 1 second. For example, the slope of the 3rd point is (2.8-2.6) / 1 = 0.2 MPa / s. This vector reflects the response rate change of the pressure system to the injection rhythm. Then, the wall thickness deviation is calculated, taking the nominal thickness 4.0 mm as the reference, and the deviation vector [0.0, 0.1, 0.2, 0.0, -0.1] mm is obtained. The maximum deviation 0.2 mm appears at the 3rd point, which can be regarded as the unstable peak time of the wall thickness. Finally, the inner diameter change trend is extracted. The change direction of each adjacent point is: the 1st to 2nd point is decreasing (-0.1), the 2nd to 3rd point is increasing (+0.3), the 3rd to 4th point is decreasing (-0.1), and the 4th to 5th point is flat (0). The trend sequence is extracted and converted into "down, up, down, right". After the trend symbolization processing, it is converted into [-1, +1, -1, 0], which can be used as the change characteristic input in the fluctuation analysis and prediction model. The above three processing results are merged into a structured data set according to the time stamp. Each data point corresponds to three types of sub-parameter group item values, i.e. the slope value, the wall thickness deviation value and the trend direction label. The combination forms the forming monitoring data set, which is used as the direct input source for control optimization and abnormality identification, and provides real-time feedback basis in the injection behavior precision monitoring.

[0098] Please refer to Figure 1 Based on the forming monitoring data set, the time period when the injection port back pressure signal is lower than the lower limit pressure is screened, the sustained deviation interval in the pipe wall thickness deviation sequence is identified, the K-Means algorithm is used to classify the inner diameter fluctuation trend, the forming state of the heat preservation pipe is identified, and the steps of outputting the forming abnormality identification information are as follows:

[0099] S301: Based on the forming monitoring data set, the injection port back pressure signal value sequence is extracted and compared with the set injection lower limit pressure threshold. The continuous time interval lower than the limited value is screened, and the low pressure interval data segment is obtained.

[0100] Based on the back pressure signal value sequence in the molding monitoring data set, the change data of the variable in the time domain is extracted, and then point-to-point numerical comparison operation is performed. The lower limit threshold of back pressure in the injection process is set to 2.5 MPa. Then the back pressure value of each time point is read from the recorded sequence in turn. The first time point is 10:00:01, and the corresponding back pressure is 2.4 MPa, which is less than 2.5 MPa, and is recorded as "low pressure". The second point time 10:00:02 is 2.3 MPa, which continues to be less than the threshold value, and is also recorded as "low pressure". The third point is 2.2 MPa, which continues to be "low pressure". When the fourth point time 10:00:04 is read, the back pressure rises to 2.6 MPa, which is judged as "normal". The fifth point is 2.7 MPa, which is also "normal". The sixth point 10:00:06 is 2.1 MPa, which is recorded as "low pressure" again. The seventh point is 2.0 MPa, which is also "low pressure". The continuous three "low pressure" values 10:00:01 to 10:00:03 are combined into the first low pressure interval, and 10:00:06 and 10:00:07 are combined into the second low pressure interval. Then the minimum pressure value and the average value of the data in each interval are calculated. The minimum value of the first interval is 2.2 MPa, and the average value is (2.4+2.3+2.2) / 3=2.3 MPa. The minimum value of the second interval is 2.0 MPa, and the average is (2.1+2.0) / 2=2.05 MPa. The start and end time and length are marked and counted, and the data is saved as a low pressure interval data segment, which is used for subsequent wall thickness fluctuation analysis.

[0101] Table 3 Low pressure detection data table

[0102]

[0103]

[0104] As shown in Table 3, the selected time points are all lower than the threshold value 2.5 MPa, forming two low pressure continuous sections.

[0105] The lower limit pressure threshold is the lowest allowed back pressure value set according to the rated minimum working pressure of the equipment, the continuity requirement of material filling and the stability boundary of the molding process during the injection process.

[0106] S302: Call the low pressure interval data segment, extract the pipe wall thickness deviation value sequence, and compare it with the set fluctuation deviation limit. Detect the deviation value and identify the continuous deviation interval to obtain the wall thickness deviation extension interval.

[0107] The low pressure interval data segment is called, respectively corresponding to time points 10:00:01 to 10:00:03 and 10:00:06 to 10:00:07, the wall thickness value sequence of the insulation pipe in the time segment is retrieved, and is compared with the set deviation limit point by point, the wall thickness nominal value is defined as 4.0mm, the allowable fluctuation deviation is set as ±0.2mm, the reasonable fluctuation interval is [3.8mm, 4.2mm], then the deviation value of each time point and whether it exceeds the limit are calculated: 10:00:01 thickness 4.0mm, deviation 0.0, marked as 'no'; 10:00:02 thickness 3.8mm, deviation-0.2, at the critical value, not marked as exceeding the limit; 10:00:03 thickness 3.7mm, deviation-0.3, marked as 'yes'; 10:00:06 thickness 3.6mm, deviation-0.4, as an exceeding limit point; 10:00:07 thickness 3.5mm, deviation-0.5, also exceeding the limit, marked as 'yes', in the analysis result, two wall thickness deviation extension intervals are identified, the first one is 10:00:03 single point, and the second one is 10:00:06 to 10:00:07 continuous segment, the maximum deviation and the average value of the two intervals are counted respectively, the maximum deviation in the 10:00:06 to 10:00:07 segment is-0.5mm, and the average deviation is (3.6+3.5) / 2-4.0=-0.45mm, which exceeds the limit amplitude most in the whole segment fluctuation, so this segment is identified as the wall thickness deviation extension interval and recorded;

[0108] Table 4 wall thickness deviation extension detection table

[0109]

[0110] As shown in Table 4, there are three recorded points where the wall thickness deviation exceeds the set allowed range, and two extension segments are formed, which constitute the basis for the wall thickness abnormal fluctuation judgment result;

[0111] The fluctuation deviation limit is calculated by analyzing the fluctuation range of the pipe wall thickness in the multiple forming process, calculating the mean value and standard deviation, and setting a maximum fluctuation range as the limit value.

[0112] S303: According to the wall thickness deviation extension interval, according to the low pressure interval data segment, the continuous deviation interval and the inner diameter fluctuation trend data, the slope feature of the inner diameter change trend is extracted, the multi-dimensional feature construction is carried out on the data, the K-Means algorithm is used for cluster analysis, the insulation pipe forming state is identified and the corresponding state label is recorded, and the forming abnormality recognition information is obtained;

[0113] The specific formula for calculating the identified insulation pipe forming state and recording the corresponding state label is:

[0114]

[0115] The deviation feature value D is calculatedΔ ′;

[0116] wherein, D Δ ′ is the corrected comprehensive deviation characteristic value, n is the total number of sampling points in the continuous deviation interval, j is the index number of the sampling point in the continuous deviation interval, is the actual inner diameter data of the vacuum tube of the jth sampling point, is the target reference inner diameter value of the jth sampling point, is the measurement time of the jth sampling point at the outlet of the vacuum tube forming, is the measurement time of the jth sampling point at the inlet of the vacuum tube forming, v j is the linear speed of the jth sampling point in the vacuum tube forming process, is the standard deviation of the vacuum tube inner diameter data of all sampling points in the continuous deviation interval;

[0117] Formula:

[0118]

[0119] Formula details and formula calculation derivation process:

[0120] The formula is used to calculate the comprehensive deviation characteristic value D Δ ′ of the vacuum tube in the continuous deviation interval, which is used to identify the vacuum tube forming state in the clustering analysis;

[0121] Parameter meaning and setting value:

[0122] The following parameter values are set:

[0123] The number of sampling points n = 5;

[0124] The actual inner diameter of the sampling point [120.5, 121.0, 119.8, 120.2, 120.7];

[0125] The reference inner diameter of the sampling point [120.0, 120.0, 120.0, 120.0, 120.0];

[0126] The forming inlet time of the sampling point [0, 10, 20, 30, 40];

[0127] The forming outlet time of the sampling point [10, 20, 30, 40, 50];

[0128] The linear speed v of the sampling point j : [5, 5, 5, 5, 5];

[0129] The standard deviation of the inner diameter of the heat preservation tube is obtained by calculating the deviation square sum of the actual inner diameter data of the sampling points from the average value and then taking the square root of the deviation square sum:

[0130] The parameters are substituted into the formula for calculation:

[0131]

[0132]

[0133] The result 0.2167 indicates that the comprehensive deviation eigenvalue of the heat preservation tube in the continuous deviation interval is 0.2167, and this value is used to identify the forming state of the heat preservation tube in the clustering analysis;

[0134] The K-Means algorithm refers to clustering and classifying time series data according to the slope characteristics of the inner diameter fluctuation trend, and outputting the corresponding forming mode label of each time period.

[0135] Please refer to Figure 1 , based on the abnormal type and time characteristics obtained from the forming abnormality identification information, the difference between the injection speed value and the target center value is calculated and the directionality parameter is extracted, combined with the corresponding injection step length and adjustment frequency value, and the steps of outputting the injection rhythm control instruction are as follows:

[0136] S401: Based on the forming abnormality identification information, the abnormal type state label and time index range value corresponding to each abnormal record are extracted, and the abnormal period characteristic parameter group is obtained;

[0137] Based on the molding anomaly identification information, the record entry content identified as an anomaly needs to be extracted from the historical collection records. The anomaly record needs to have two key fields: anomaly type status label and time index range value. During execution, first define the anomaly types as "low pressure" and "wall thickness anomaly", then retrieve the anomaly record list in the previous monitoring data set in turn, determine the specific label content of the anomaly type, for example, the number E001 anomaly is "low pressure", its corresponding time index start time is 10:00:01, end time is 10:00:03, and duration is 3 seconds. The number E002 anomaly is "wall thickness anomaly", the start time is 10:00:06, the end time is 10:00:07, and the duration is 2 seconds. Then extract the corresponding anomaly duration period according to the time index, and store the time interval as the core field in the anomaly period data table. At the same time, all original measurement data associated with this interval, such as injection speed, back pressure, thickness, inner diameter, etc. are bound to generate anomaly period data units with structure identification. Each anomaly data is identified as a separate record number E001, E002, and is associated with corresponding anomaly type, start time, end time and other fields to form a complete anomaly period feature parameter group. The specific field combination includes anomaly type, time period range, anomaly data item number, whether continuous, whether out of bounds, etc. dimensions, and is recorded by anomaly category group. Finally, an anomaly section index data set with behavior attribution ability is constructed.

[0138] Table 5: Abnormal injection speed period comparison table

[0139]

[0140] As shown in Table 5, the two anomaly records correspond to different time indexes and anomaly types, and have bound injection rate data, forming a complete anomaly period feature parameter group.

[0141] S402: Call the anomaly period feature parameter group, extract the actual injection speed value and injection speed target center value of the corresponding time period and calculate the difference, identify the deviation trend direction, including up, down and flat, to get the injection speed direction index;

[0142] After calling the preceding set of abnormal period feature parameters, the target injection speed value and the actual sampling speed value in each abnormal interval are extracted, and difference operation and trend judgment are performed. In the first step of the execution process, the target rate values of the two abnormal records are both 5.2 g / s. Then the actual injection speed sequence is read, for example, the sampling rate of the low pressure abnormal section is 5.0, 5.2, 5.5 g / s. The deviation of each point is calculated as follows: the deviation of point 1 is -0.2 g / s, the deviation of point 2 is 0.0 g / s, and the deviation of point 3 is +0.3 g / s. Then the trend of the sequence deviation is judged. According to the judgment rule: if the latter value is greater than the former and continuously increases in the positive direction, it is judged as "upward", if the latter value is less than the former and continuously decreases in the negative direction, it is judged as "downward", and if the value is basically stable between ±0.1 g / s, it is marked as "flat". The deviation trend of this section is -0.2→0.0→+0.3, the trend continuously increases, and it is judged as "upward". The actual rate of the wall thickness abnormal section is 5.1, 5.0, 4.8 g / s, and the deviation is -0.1, -0.2, -0.4, respectively. The trend is negative, and it is judged as "downward". Finally, the injection speed direction index of the two abnormal sections is "upward" and "downward" respectively. This index is used to depict the fluctuation trend of the injection behavior when the abnormality occurs, and is an auxiliary feature field for abnormal mechanism judgment. The result is finally recorded in the abnormal trend index table for subsequent state modeling.

[0143] S403: According to the injection speed direction index, match the injection step value and the adjustment frequency value corresponding to the target holding tube specification, construct the injection beat adjustment instruction, including the adjustment direction type, the rhythm intensity parameter, and the frequency amplitude correction value, and generate the injection beat control instruction;

[0144] The specific formula for constructing the injection beat adjustment instruction is as follows:

[0145]

[0146] Calculate the rhythm intensity correction value;

[0147] Wherein, P adj represents the rhythm intensity correction value, v act represents the normalized value of the actual injection speed, v tar represents the normalized reference value of the target injection speed, Δt i represents the relative time ratio of the abnormality in the i-th time period, f i represents the normalized value of the injection adjustment frequency in the i-th time period, ΔS represents the normalized value of the difference between the injection step value and the step value of the previous period, ΔF represents the normalized value of the difference between the injection adjustment frequency value and the frequency value of the previous period, n represents the number of time periods of the abnormal state record, and i is the index letter of the abnormal time period in the time sequence;

[0148] Formula:

[0149]

[0150] Formula details and formula calculation derivation process:

[0151] The formula is used to calculate the injection rhythm strength correction value, which is used as the rhythm strength parameter in the subsequent generated injection rhythm adjustment instruction; its basis is the deviation of the current injection speed and the target value, the frequency-time load accumulation of the historical abnormal period, and the strength of the adjustment response change, so as to complete the feedback quantification of the current control state of the injection system;

[0152] Parameter meaning and setting value:

[0153] v act is the normalized value of the actual injection speed, which is obtained by the minimum-maximum normalization method, the sampling value is set to 2.85 m / s, the maximum speed of the system is set to 4.00 m / s, and the normalized value is:

[0154] v tar is the normalized value of the target injection speed, which is obtained by the minimum-maximum normalization method, the control target is set to 3.20 m / s, the maximum value is set to 4.00 m / s, and the normalization is:

[0155] Δt i is the time proportion of the abnormal period, which is obtained by the minimum-maximum normalization method, the durations of the three abnormal periods are set to 5s, 4s and 6s respectively, and the total injection period is 60s, and the normalized value is:

[0156] f i is the normalized value of the injection adjustment frequency of each period, which is obtained by the minimum-maximum normalization method, the frequencies are set to 1.0Hz, 0.8Hz and 1.2Hz respectively, and the maximum frequency of the system is 2.0Hz, and the normalization is:

[0157] ΔS is the normalized difference value of the injection step length and the last period, which is obtained by the minimum-maximum normalization method, the step length of the last period is set to 12mm, the current period is 14mm, and the maximum step length of the system is 20mm, the difference is 2mm, and the normalization is:

[0158] ΔF is the normalized value of the injection frequency difference, which is obtained by the minimum-maximum normalization method, the frequency of the last period is set to 1.0Hz, the current is 1.2Hz, and the maximum difference is set to 2.0Hz, and the normalization is:

[0159] Substitute the parameters into the formula to calculate:

[0160] v act -v tar = 0.7125 - 0.8000 = -0.0875;

[0161]

[0162] (v act -v tar )·∑Δt i ·f i = -0.0875·0.12833 = -0.011229;

[0163]

[0164] The result 0.01138 indicates the normalized output intensity of the current correction intensity value of the material injection rhythm.

[0165] Please refer to Figure 1 , based on the material injection rhythm control instruction, collect and analyze the deviation degree of the actual execution value and the target parameter, output the adjustment instruction, establish the execution deviation record combined with the timestamp information and optimize the dynamic optimization pipe diameter sensitivity level configuration table, and the steps of outputting the heat preservation pipe production management record are as follows:

[0166] S501: Based on the material injection rhythm control instruction, collect the actual execution value data of the material injection equipment and the target parameter data in the corresponding time period and compare them, calculate the numerical deviation between the material injection speed value, the adjustment frequency value and the step value, and obtain the execution parameter deviation coefficient;

[0167] Based on the history record of the injection beat control instruction, the execution value data of the injection equipment in the actual running process needs to be collected and compared with the preset target control parameters in this section to calculate the offset. In the execution process, first extract the target values of the three key control variables from the production record: injection rate (unit g / s), adjustment frequency (unit times / min) and step length (unit g). In the time period of May 10, 2025, 10:01, the target value of the injection rate is 5.2 g / s, the adjustment frequency is 6 times / min, and the step length is 3.5 g. The actual execution values collected in the same time period are as follows: at 10:01:00, the rate is 5.0 g / s, the frequency is 5 times / min, and the step length is 3.8 g; at 10:01:10, the rate is 5.4 g / s, the frequency is 7 times / min, and the step length is 3.4 g; at 10:01:20, the rate is 5.1 g / s, the frequency is 6 times / min, and the step length is 3.5 g. Calculate the offset value of the three parameters respectively, for example, the injection rate offset at 10:01:00 is 5.0-5.2=-0.2 g / s, the adjustment frequency offset is 5-6=-1 times / min, and the step length offset is 3.8-3.5=+0.3 g. Uniformly summarize the above difference values into an offset vector and further convert it into an offset coefficient group. The coefficient is defined as: For example, the injection rate offset coefficient is -0.2 / 5.2=-0.0385, the step length offset coefficient is 0.3 / 3.5=0.0857, and the adjustment frequency offset coefficient is -1 / 6=-0.1667. Record the three coefficients to form a parameter offset group of an execution point, and record the offset vector of all points in time sequence to finally form an execution parameter offset coefficient table.

[0168] Table 6 Injection control execution parameter offset table

[0169]

[0170]

[0171] As shown in Table 6, the target values and actual values of the control parameters in the three time periods are recorded. The offset values are calculated by comparison to form a complete set of execution parameter offset coefficients.

[0172] S502: Call the execution parameter offset coefficient, combine the deviation direction and amplitude characteristics corresponding to each group of offset coefficients, construct the correction instruction parameter, and output the injection correction adjustment instruction.

[0173] After calling the offset coefficient data corresponding to each set of time points, the offset direction (positive or negative) and the absolute value of the offset amplitude need to be combined to construct the correction parameter for the injection system instruction adjustment. First, the direction of the offset coefficient value is determined. The coefficient value greater than zero is defined as "up", less than zero is defined as "down", and equal to zero is "flat". Then the absolute value is classified. The amplitude division standard is set as follows: offset absolute value less than 2% is "slight", 2%-5% is "moderate", and greater than 5% is "serious". Taking the injection rate offset coefficient -0.0385 as an example, the offset direction is "down" and the offset amplitude is 3.85%, which corresponds to moderate decline. According to the set rules, the correction parameter is set as follows: increase the injection rate target value by 3%, increase the frequency by 1 / min, and keep the step size unchanged. For example, the adjustment frequency offset coefficient -0.1667, the direction is "down", the amplitude is 16.67%, which belongs to serious offset, then the correction instruction should be that the frequency is directly increased to the target value +2 / min, and the injection step size is reduced by 0.1g for buffering. The above results are converted into a structured correction instruction record table, including target parameters, offset coefficients, judgment direction, judgment level, and recommended adjustment amount, which constitutes the injection correction adjustment instruction output by the system.

[0174] S503: According to the injection correction adjustment instruction, the effective time stamp of each instruction is extracted, the actual execution value offset range in the corresponding time period is established, the control parameter type corresponding to the deviation data is optimized, and the pipe diameter sensitive level configuration table is optimized to generate the insulation pipe production management record;

[0175] According to the content of each correction adjustment instruction formed, the corresponding execution time stamp information needs to be extracted and recorded in the control log. Then, the offset range between the actual execution value and the original target value in the time period is found, and the execution deviation record is established. Each deviation record needs to mark the corresponding control parameter type, i.e. rate, frequency or step size, and associate the corresponding offset value and direction. For example, the adjustment frequency offset is -1 / min at 10:01:00, the parameter type is frequency, the offset value is -1, and the direction is down. This information needs to be bound with the control system feedback structure and identified as the trigger mechanism for this offset correction, which is "frequency severe decline". Then, the control parameter category, offset direction and sensitive level configuration table are linked. According to the severe level of frequency parameter offset, the sensitive weight of this control category is increased by one level. For example, the original frequency parameter is sensitive to DN80 pipe diameter at intermediate level. Due to the severe frequency execution deviation, the adjustment is optimized to high level. Finally, the optimized control parameter level is rewritten into the sensitive level configuration table of the insulation pipe specification, and the time, adjustment basis, correction amplitude and other fields are updated synchronously to form a complete and behavior-closed insulation pipe production management record.

[0176] Please refer to Figure 2The plastic sleeve steel thermal insulation pipe production management system is used for executing the above-mentioned plastic sleeve steel thermal insulation pipe production management method, and the system comprises:

[0177] A pipe diameter sensitivity evaluation module uses the wall thickness fluctuation, bubble structure size and center offset data to calculate the corresponding relationship between the wall thickness variation range, structure size mean value and center offset range of each specification, evaluate the sensitivity of each specification configuration to the control parameter, dynamically adjust the injection step length and adjustment frequency value, construct a pipe diameter sensitivity level configuration table and deliver it to the molding monitoring data acquisition module;

[0178] A molding monitoring data acquisition module acquires the injection port back pressure signal, pipe wall thickness, inner diameter and injection rate data during the production of the thermal insulation pipe based on the pipe diameter sensitivity level configuration table, calls the injection speed target center value, calculates the injection port back pressure change slope, wall thickness deviation value, inner diameter fluctuation trend direction, injection speed variation range and target value deviation, generates a molding monitoring data set and delivers it to the molding anomaly recognition module;

[0179] A molding anomaly recognition module filters the time period when the injection port back pressure signal is lower than the lower limit pressure based on the molding monitoring data set, identifies the continuous deviation interval in the pipe wall thickness deviation sequence, uses the K-Means algorithm to classify the inner diameter fluctuation trend, identifies the molding state of the thermal insulation pipe, generates molding anomaly recognition information and delivers it to the injection rhythm control module;

[0180] An injection rhythm control module obtains the abnormal type and time characteristics based on the molding anomaly recognition information, calculates the difference between the injection speed and the target center value and extracts the directional parameter, combines the injection step length and adjustment frequency value, generates injection rhythm control instructions and delivers them to the production management optimization module;

[0181] A production management optimization module acquires and analyzes the deviation degree of the actual execution value and the target parameter based on the injection rhythm control instructions, outputs adjustment instructions, establishes execution deviation records combined with the time stamp information, dynamically optimizes the pipe diameter sensitivity level configuration table, and generates thermal insulation pipe production management records.

[0182] The above-described embodiments can be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0183] It should be understood that the term "and / or" herein merely describes the association relationship of the associated objects, and indicates that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after it, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0184] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0185] It should be understood that in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0186] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0187] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0188] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is merely logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0189] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0190] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0191] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0192] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A production management method for plastic-coated steel insulated pipes, characterized in that, The method includes: S1: By extracting data on wall thickness fluctuation, foam structure size and center offset of various specifications of plastic-coated steel insulation pipes, the sensitivity of each specification configuration to control parameters is evaluated, and the injection step length and adjustment frequency value are dynamically adjusted according to the sensitivity to construct a pipe diameter sensitivity level configuration table. S2: Based on the pipe diameter sensitivity level configuration table, collect the back pressure signal of the injection port, pipe wall thickness, inner diameter and injection rate value during the production process of the insulation pipe, call the target center value of the injection speed, calculate the slope of the back pressure change of the injection port, the wall thickness deviation value, the direction of the inner diameter fluctuation trend, the amplitude of the injection speed change and the target value deviation, and output the molding monitoring dataset. S3: Based on the molding monitoring dataset, filter the time period when the back pressure signal of the injection port is lower than the lower limit pressure, identify the continuous deviation interval in the pipe wall thickness deviation sequence, use the K-Means algorithm to classify the inner diameter fluctuation trend, identify the molding status of the insulation pipe, and output molding anomaly identification information. S4: Based on the molding anomaly identification information, obtain the anomaly type and time characteristics, calculate the difference between the injection speed value and the target center value and extract the directional parameters, and combine the corresponding injection step length and adjustment frequency value to output the injection cycle control command.

2. The production management method for plastic-coated steel insulated pipes according to claim 1, characterized in that, The pipe diameter sensitivity level configuration table includes specification grading standards, control parameter adaptation range, and sensitivity grading index. The molding monitoring dataset includes wall thickness stability index, back pressure dynamic change curve, and inner diameter fluctuation model. The molding anomaly identification information includes anomaly type marker, anomaly occurrence time period, and pattern recognition label. The injection cycle control command includes cycle adjustment direction, injection rate correction value, and response timing parameters. The pattern recognition label is a classification result generated by using the K-Means algorithm to analyze the inner diameter fluctuation trend in the molding process data, and is used to characterize different types of molding fluctuation patterns. The response timing parameters refer to the time response characteristic parameters that the control system needs to refer to when adjusting the injection cycle after identifying molding abnormalities, including command activation delay, response duration, and adjustment slope.

3. The production management method for plastic-coated steel insulated pipes according to claim 1, characterized in that, By extracting wall thickness fluctuation, foam structure dimensions, and center offset data of various specifications of plastic-coated steel insulation pipes, the sensitivity of each specification configuration to control parameters is evaluated, and the injection step length and adjustment frequency are dynamically adjusted based on the sensitivity to construct a pipe diameter sensitivity level configuration table. The specific steps are as follows: S101: By extracting the wall thickness fluctuation value, bubble structure size value and center offset data value of various specifications of plastic-coated steel insulation pipes, the specification parameter set of insulation pipes is obtained; S102: Call the set of insulation pipe specifications and parameters, and use the analytic hierarchy process to quantify and weight the parameters according to the wall thickness fluctuation value, bubble structure size value and center offset data value corresponding to each specification, analyze the sensitivity requirements of various specification configurations to production control parameters, and obtain the sensitivity level value. The analytic hierarchy process constructs a parameter judgment matrix, calculates the relative influence coefficients of wall thickness fluctuation, bubble structure size and center offset value, and then standardizes the parameter values ​​of each specification, multiplies them by the corresponding influence coefficients and sums them to obtain the sensitivity score value of each specification. S103: Based on the sensitivity level value, dynamically adjust the injection step length and adjustment frequency value parameters corresponding to each insulation pipe specification, establish the mapping relationship between control parameters and sensitivity level, and obtain the pipe diameter sensitivity level configuration table.

4. The production management method for plastic-coated steel insulated pipes according to claim 3, characterized in that, Based on the aforementioned pipe diameter sensitivity level configuration table, the specific steps for collecting the back pressure signal at the injection port, pipe wall thickness, inner diameter, and injection rate during the production process of the insulation pipe, calling the target center value of the injection rate, calculating the slope of the back pressure change at the injection port, the wall thickness deviation, the direction of the inner diameter fluctuation trend, the amplitude of the injection rate change, and the target value deviation, and outputting the molding monitoring dataset are as follows: S201: Based on the pipe diameter sensitivity level configuration table, collect the back pressure signal value of the injection port, the pipe wall thickness value, the inner diameter value and the injection rate value during the production process of the insulation pipe, extract the target center value of the injection speed, and number and classify each data point according to the timestamp order to generate the basic dataset of the molding process. S202: Call the basic dataset of the molding process, calculate the variation range of the injection speed, and obtain the target value deviation based on the difference between the target center value of the injection speed and the actual injection rate value, and obtain the injection speed characteristic parameter group; S203: Based on the injection speed characteristic parameter group, extract the slope of the back pressure change at the injection port, calculate the wall thickness deviation value and the direction of the inner diameter fluctuation trend, and obtain the molding monitoring dataset.

5. The production management method for plastic-coated steel insulated pipes according to claim 4, characterized in that, Based on the molding monitoring dataset, the specific steps for filtering time periods when the back pressure signal at the injection port is lower than the lower limit pressure, identifying continuous deviation intervals in the pipe wall thickness deviation sequence, using the K-Means algorithm to classify the inner diameter fluctuation trend, identifying the molding status of the insulation pipe, and outputting molding anomaly identification information are as follows: S301: Based on the molding monitoring dataset, extract the back pressure signal value sequence of the injection port, compare it with the set injection lower limit pressure threshold, filter the continuous time interval below the limit value, and obtain the low pressure interval data segment; The lower limit pressure threshold is the minimum allowable back pressure value set during the injection process based on the equipment's rated minimum working pressure, the requirements for continuous material filling, and the stability boundary of the molding process. S302: Call the low-pressure range data segment, extract the pipe wall thickness deviation value sequence, compare it with the set fluctuation deviation limit, detect the deviation value and identify the continuous deviation range, and obtain the wall thickness deviation extension range. The fluctuation deviation limit is determined by analyzing the fluctuation range of the pipe wall thickness during multiple forming processes, calculating its mean and standard deviation, and setting a maximum fluctuation range as the limit value. S303: Based on the wall thickness deviation extension range, and based on the low-pressure range data segment, the continuous deviation range, and the inner diameter fluctuation trend data, extract the slope feature of the inner diameter change trend, construct multi-dimensional features for the data, use the K-Means algorithm for cluster analysis, identify the forming state of the insulation pipe and record the corresponding state label, and obtain forming anomaly identification information. The specific formula for identifying the forming state of the insulation pipe and recording the corresponding state label is as follows: Calculate the deviation eigenvalue D Δ ′; Among them, D Δ ′ represents the corrected comprehensive deviation characteristic value, n represents the total number of sampling points within the continuous deviation interval, and j represents the index number of the sampling point within the continuous deviation interval. The actual inner diameter data of the insulation pipe at the j-th sampling point. Let j be the target reference inner diameter value for the j-th sampling point. Let j be the measurement time at the outlet of the insulation pipe forming process at the j-th sampling point. Let v be the measurement time at the j-th sampling point at the inlet of the insulation pipe forming process. j Let be the linear velocity during the forming process of the insulation pipe corresponding to the j-th sampling point. This represents the standard deviation of the inner diameter data of the insulation pipe at all sampling points within the continuous deviation interval; The K-Means algorithm refers to clustering and classifying time series data based on the slope characteristics of the inner diameter fluctuation trend, and outputting the forming pattern label corresponding to each time period.

6. The production management method for plastic-coated steel insulated pipes according to claim 5, characterized in that, The specific steps for obtaining the abnormality type and time characteristics based on the molding abnormality identification information, calculating the difference between the injection speed value and the target center value and extracting the directional parameters, and combining the corresponding injection step size and adjustment frequency value to output the injection cycle control command are as follows: S401: Based on the molding anomaly identification information, extract the anomaly type status label and time index range value corresponding to each anomaly record, and obtain the anomaly time period feature parameter group; S402: Call the abnormal time period feature parameter group, extract the actual injection speed value and the injection speed target center value of the corresponding time period and calculate the difference, identify the offset trend direction, including floating, falling and leveling, and obtain the injection speed direction index; S403: Based on the injection speed direction index, match the injection step length value and adjustment frequency value corresponding to the target insulation pipe specification, construct the injection cycle adjustment instruction, including adjustment direction type, rhythm intensity parameter, frequency amplitude correction value, and generate the injection cycle control instruction.

7. The production management method for plastic-coated steel insulated pipes according to claim 6, characterized in that, The specific formula for constructing the injection cycle adjustment command is as follows: Calculate the rhythm intensity correction value; Among them, P adj v represents the rhythm intensity correction value. act v represents the normalized value of the actual injection rate. tar The normalized reference for the target injection rate value, Δt i f represents the ratio of the relative duration of the anomaly within the i-th time period. i ΔS represents the normalized value of the injection adjustment frequency in the i-th time period, ΔS represents the normalized value of the difference between the injection step size and the step size of the previous cycle, ΔF represents the normalized value of the difference between the injection adjustment frequency and the frequency of the previous cycle, n represents the number of time periods recorded in the abnormal state, and i is the index letter of the abnormal time period in the time series.

8. The production management method for plastic-coated steel insulated pipes according to claim 1, characterized in that, The method further includes: S5: Based on the injection cycle control command, collect and analyze the deviation of the actual execution value and the target parameter, output adjustment command, combine timestamp information to establish execution deviation record and optimize the dynamic optimization of the pipe diameter sensitivity level configuration table, and output insulation pipe production management record; The production management records for the insulation pipe include execution deviation logs, parameter correction history, and sensitivity configuration update information.

9. The production management method for plastic-coated steel insulated pipes according to claim 8, characterized in that, Based on the injection cycle control command, the steps of collecting and analyzing the deviation between the actual execution value and the target parameter, outputting adjustment commands, establishing an execution deviation record by combining timestamp information, optimizing the dynamically optimized pipe diameter sensitivity level configuration table, and outputting the insulation pipe production management record are as follows: S501: Based on the injection cycle control command, collect the actual execution value data of the injection equipment and the target parameter data within the corresponding time period and compare them, calculate the numerical deviation between the injection speed value, the adjustment frequency value and the step size value, and obtain the execution parameter offset coefficient. S502: Call the execution parameter offset coefficient, combine the deviation direction and amplitude characteristics corresponding to each set of offset coefficients to construct correction instruction parameters, and output the injection correction adjustment instruction; S503: Based on the injection correction and adjustment instructions, extract the effective timestamp of each instruction, establish an execution deviation record by combining the actual execution value offset range within the corresponding time period, optimize the pipe diameter sensitivity level configuration table according to the control parameter type corresponding to the deviation data, and generate the insulation pipe production management record.

10. A production management system for plastic-coated steel insulated pipes, characterized in that, The system is used to implement the production management method for plastic-coated steel insulated pipes according to any one of claims 1-9, and the system includes: The pipe diameter sensitivity assessment module uses wall thickness fluctuation, bubble structure size and center offset data to calculate the correspondence between the wall thickness variation range, the average structural size and the center offset range for each specification, assess the sensitivity of each specification configuration to control parameters, dynamically adjust the injection step length and adjustment frequency value, construct a pipe diameter sensitivity level configuration table and transmit it to the molding monitoring data acquisition module. The molding monitoring data acquisition module, based on the pipe diameter sensitivity level configuration table, collects the back pressure signal of the injection port, pipe wall thickness, inner diameter and injection rate data during the production of the insulation pipe, calls the target center value of the injection speed, calculates the slope of the back pressure change of the injection port, the wall thickness deviation value, the direction of the inner diameter fluctuation trend, the amplitude of the injection speed change and the target value deviation, generates the molding monitoring dataset and transmits it to the molding anomaly identification module. The molding anomaly identification module, based on the molding monitoring dataset, filters the time period when the back pressure signal of the injection port is lower than the lower limit pressure, identifies the continuous deviation interval in the pipe wall thickness deviation sequence, uses the K-Means algorithm to classify the inner diameter fluctuation trend, identifies the molding status of the insulation pipe, generates molding anomaly identification information and transmits it to the injection cycle control module. The injection cycle control module, based on the molding anomaly identification information, obtains the anomaly type and time characteristics, calculates the difference between the injection speed and the target center value and extracts the directional parameters, and combines the injection step length and adjustment frequency value to generate an injection cycle control command and transmit it to the production management optimization module. The production management optimization module, based on the injection cycle control command, collects and analyzes the deviation between the actual execution value and the target parameter, outputs adjustment commands, establishes an execution deviation record by combining timestamp information, dynamically optimizes the pipe diameter sensitivity level configuration table, and generates insulation pipe production management records.

Images