CN-122020449-A - Processing method, equipment and medium for plastic-lined pipe

CN122020449ACN 122020449 ACN122020449 ACN 122020449ACN-122020449-A

Abstract

The invention provides a processing method, equipment and medium of a plastic lining pipe, which comprises the steps of carrying out prediction processing on temperature data of an outer pipe and an inner pipe of the plastic lining pipe to be processed, wherein the temperature data of data acquisition points of the outer pipe and the inner pipe of the plastic lining pipe are located in a target time period, so as to obtain a plurality of first prediction data and a plurality of second prediction data corresponding to the current moment, determining first matching weights and second matching weights according to fluctuation characteristics of a plurality of temperature data of each data acquisition point of the inner pipe of the plastic lining pipe to be processed, so as to obtain a processing characteristic value corresponding to the current moment of the plastic lining pipe to be processed, and determining that the thermal processing state of the plastic lining pipe to be processed at the current moment is a normal state if the processing characteristic value is located in a preset normal processing characteristic value range, so that the thermal processing state of the plastic lining pipe to be processed at the current moment can be determined through data prediction respectively carried out on the outer pipe and the inner pipe of the plastic lining pipe to be processed, and workers can control quality in the processing process of the plastic lining pipe.

Inventors

ZHANG HONGSHUN
WANG ZHI
WANG YUANZHI
ZHAI YONGLI
YANG YAFEI
WANG ZHIJIE

Assignees

邯郸正大制管集团股份有限公司

Dates

Publication Date: 20260512
Application Date: 20251226

Claims (10)

1. The processing method of the plastic-lined pipe is characterized by comprising the following steps of: Step S100, predicting a plurality of temperature data corresponding to each data acquisition point position on an outer tube of a plastic lining tube to be processed in a target time period in the thermal processing process to obtain a plurality of first predicted data corresponding to the current time, wherein the duration of the target time period is a preset duration, and the ending time of the target time period is a data acquisition time which is positioned before the current time and has the shortest duration with the current time; Step 200, predicting a plurality of temperature data corresponding to each data acquisition point position corresponding to the inner pipe of the plastic-lined pipe to be processed in the target time period to obtain a plurality of second predicted data corresponding to the current moment; Step S300, determining a first matching weight and a second matching weight according to fluctuation characteristics of a plurality of temperature data corresponding to each data acquisition point position corresponding to the inner pipe of the plastic lining pipe to be processed at the current moment; Step S400, weighting the first matching weight, the second matching weight, the plurality of first prediction data and the plurality of second prediction data to obtain a processing characteristic value corresponding to the plastic lining pipe to be processed at the current moment; and S500, if the processing characteristic value is within a preset processing normal characteristic value range, determining that the thermal processing state of the plastic-lined pipe to be processed at the current moment is a normal state, and if not, determining that the thermal processing state of the plastic-lined pipe to be processed at the current moment is an abnormal state.
2. The method according to claim 1, wherein the step S100 comprises: step S110, acquiring a plurality of temperature data corresponding to each data acquisition point position on an outer tube of the plastic-lined tube to be processed in a target time period in a thermal processing process to obtain a plurality of first temperature data lists A 1 ,A 2 ,...,A i ,...,A j , wherein i=1, 2, j is the number of data acquisition moments included in the target time period, j is the previous data acquisition moment of the current moment, the time length between every two adjacent data acquisition moments in the target time period is equal, and A i is the first temperature data list corresponding to the i-th data acquisition moment in the target time period; A i =(A i1 ,A i2 ,...,A im ,...,A in ), m=1, 2, n being the number of data acquisition points on the outer tube of the plastic-lined tube to be processed, a plurality of data acquisition points on the outer tube being distributed on the outer tube in a matrix, a im being temperature data corresponding to the mth data acquisition point on the outer tube of the plastic-lined tube to be processed at the ith data acquisition time within the target time period; Step S120, inputting A 1 ,A 2 ,...,A i ,...,A j into a preset first prediction model to obtain a first prediction data list output by the first prediction model, wherein the first prediction data list comprises a plurality of first prediction data corresponding to the current moment, and the first prediction model is obtained by training a plurality of historical temperature data corresponding to a plastic lining pipe with a normal thermal processing state in a historical time period.
3. The method of claim 2, wherein the first predictive model is determined according to the steps of: Step S121, determining a plastic lining pipe which is in a normal thermal processing state in a historical time period and has the same specification as the plastic lining pipe to be processed as a target plastic lining pipe, wherein the ending time of the historical time period is positioned before the current time; Step S122, acquiring a plurality of historical temperature data of each data acquisition point position on an outer tube of each target plastic-lined tube in a plurality of corresponding historical sub-time periods to obtain a plurality of first historical temperature data list sets B 1 ,B 2 ,...,B t ,...,B s , wherein t=1, 2, S is the number of the target plastic-lined tubes, and B t is the first historical temperature data list set corresponding to the t-th target plastic-lined tube; B t =(B t1 ,B t2 ,...,B te ,...,B tf(t) ), e=1, 2,..f (t), f (t) being the number of historical sub-periods corresponding to the t-th said target plastic-lined pipe, B te being a first list of historical temperature data corresponding to the t-th said target plastic-lined pipe in its corresponding e-th historical sub-period; B te =(B te1 ,B te2 ,...,B tei ,...,B tej );B tei is a first historical temperature data sub-table corresponding to the ith data acquisition time of the t-th target plastic-lined pipe in the corresponding e-th historical subperiod; b tei =(B tei1 ,B tei2 ,...,B teim ,...,B tein );B teim is the corresponding historical temperature data at the ith data acquisition time in the corresponding ith historical subperiod of time of the mth data acquisition point position on the outer tube of the target plastic-lined tube; the arrangement mode of a plurality of data acquisition points on the outer tube of each target plastic-lined tube is the same as that of a plurality of data acquisition points on the outer tube of the plastic-lined tube to be processed; The historical subperiod is any subperiod in the process of carrying out heat treatment on the target plastic-lined pipe in the historical period, the duration of the historical subperiod is equal to the duration of the target period, the number of data acquisition moments in the historical subperiod is equal to the number of data acquisition moments in the target period, and the duration between two adjacent data acquisition moments in the historical subperiod is equal to the duration between two adjacent data acquisition moments in the target period; Step S123, acquiring a first historical temperature data sub-table C te1 =(C te11 ,C te12 ,...,C te1m ,...,C te1n corresponding to a first data acquisition time of the t-th target plastic-lined pipe after a corresponding e-th historical subperiod, wherein C te1m is historical temperature data corresponding to the first data acquisition time of the t-th data acquisition point on the outer pipe of the target plastic-lined pipe after the corresponding e-th historical subperiod; Step S124, taking the B te1 ,B te2 ,...,B tei ,...,B tej as an input sample, taking the C te1 as an output label, and performing supervised training on a preset neural network model to obtain a first prediction model.
4. A method according to claim 3, wherein said step S200 comprises: Step S210, acquiring a plurality of corresponding temperature data of each data acquisition point position on an inner pipe of the plastic-lined pipe to be processed in a target time period in the thermal processing process to obtain a plurality of second temperature data lists D 1 ,D 2 ,...,D i ,...,D j , wherein D i is a second temperature data list corresponding to the ith data acquisition moment in the target time period; D i =(D i1 ,D i2 ,...,D iy ,...,D iz ), y=1, 2, & gt, z, wherein z is the number of data acquisition points on the inner tube of the plastic-lined tube to be processed, a plurality of data acquisition points on the inner tube are distributed on the inner tube in a matrix form, and D iy is temperature data corresponding to the ith data acquisition time point of the y-th data acquisition point on the inner tube of the plastic-lined tube to be processed in the target time period; Step S220, inputting the D 1 ,D 2 ,...,D i ,...,D j into a preset second prediction model to obtain a second prediction data list output by the second prediction model, wherein the second prediction data list comprises a plurality of pieces of second prediction data corresponding to the current moment, and the second prediction model is obtained by training a plurality of pieces of historical temperature data corresponding to a plastic lining pipe with a normal thermal processing state in a historical time period.
5. The method of claim 4, wherein the second predictive model is determined according to the steps of: Step S221, acquiring a plurality of historical temperature data of each data acquisition point position on the inner tube of each target plastic-lined tube in a plurality of corresponding historical subperiods to obtain a plurality of second historical temperature data list sets E 1 ,E 2 ,...,E t ,...,E s , wherein E t is a second historical temperature data list set corresponding to the t-th target plastic-lined tube; e t =(E t1 ,E t2 ,...,E te ,...,E tf(t) );E te is a second historical temperature data list corresponding to the t-th target plastic-lined pipe in the corresponding E-th historical subperiod; E te =(E te1 ,E te2 ,...,E tei ,...,E tej );E tei is a second historical temperature data sub-table corresponding to the ith data acquisition time of the t-th target plastic-lined pipe in the corresponding E-th historical subperiod; E tei =(E tei1 ,E tei2 ,...,E teiy ,...,E teiz );E teiy is the corresponding historical temperature data at the ith data acquisition time in the corresponding ith historical subperiod of time of the nth data acquisition point on the inner tube of the target plastic-lined tube; the arrangement mode of a plurality of data acquisition points on the inner tube of each target plastic lining tube is the same as that of a plurality of data acquisition points on the inner tube of the plastic lining tube to be processed; Step S222, acquiring a second historical temperature data sub-table C te2 =(C te21 ,C te22 ,...,C te2y ,...,C te2z corresponding to a first data acquisition time of the t-th target plastic-lined pipe after a corresponding e-th historical subperiod, wherein C te2y is historical temperature data corresponding to a first data acquisition time of a y-th data acquisition point on an inner pipe of the t-th target plastic-lined pipe after the corresponding e-th historical subperiod; Step S223, taking E te1 ,E te2 ,...,E tei ,...,E tej as an input sample, taking C te2 as an output label, and performing supervised training on a preset neural network model to obtain a second prediction model.
6. The method according to claim 5, wherein the step S300 includes: Step S310, acquiring temperature data corresponding to each data acquisition point position on the inner pipe of the plastic-lined pipe to be processed at the current moment to obtain a second target data list F 2 =(F 21 ,F 22 ,...,F 2y ,...,F 2z ), wherein F 2y is temperature data corresponding to the y-th data acquisition point position on the inner pipe of the plastic-lined pipe to be processed at the current moment; Step S320, determining the variance of F 21 ,F 22 ,...,F 2y ,...,F 2z as H 2 ; Step S330, determining a variance interval in which H 2 is located from a preset variance interval list, and determining a matching weight corresponding to the variance interval as a second matching weight G 2 ; The variance interval list comprises a plurality of variance intervals and matching weights corresponding to each variance interval, and the average value of the variance intervals and the matching weights corresponding to the variance intervals are in a proportional relation; The smallest matching weight of the plurality of matching weights included in the variance interval list is greater than or equal to 0.5, and the largest matching weight of the plurality of matching weights included in the variance interval list is smaller than 1; Step S340, determining a first matching weight G 1 =1-G 2 .
7. The method according to claim 6, wherein the step S400 includes: Step S410, acquiring temperature data corresponding to each data acquisition point position on an outer tube of the plastic-lined tube to be processed at the current moment to obtain a first target data list F 1 =(F 11 ,F 12 ,...,F 1m ,...,F 1n ), wherein F 1m is temperature data corresponding to an mth data acquisition point position on the outer tube of the plastic-lined tube to be processed at the current moment; step S420, performing feature encoding on the first target data list and the first predicted data list, so as to obtain a first target data vector corresponding to the first target data list and a first predicted data vector corresponding to the first predicted data list; Step S430, determining that the matching degree of the first target data vector and the first predicted data vector is L 1 ; step S440, respectively performing feature encoding on the second target data list and the second predicted data list to obtain a second target data vector corresponding to the second target data list and a second predicted data vector corresponding to the second predicted data list; Step S450, determining that the matching degree between the second target data vector and the second predicted data vector is L 2 ; Step S460, determining a processing characteristic value t=g 1 ×L 1 +G 2 ×L 2 corresponding to the plastic-lined pipe to be processed at the current moment.
8. The method according to claim 7, wherein the step S500 includes: and step S510, if T is larger than T 0 , determining that the thermal processing state of the plastic lining pipe to be processed at the current moment is a normal state, otherwise, determining that the thermal processing state of the plastic lining pipe to be processed at the current moment is an abnormal state, wherein T 0 is a preset processing normal characteristic threshold value.
9. A non-transitory computer readable storage medium having stored therein at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the method of any one of claims 1-8.
10. An electronic device comprising a processor and the non-transitory computer readable storage medium of claim 9.

Description

Processing method, equipment and medium for plastic-lined pipe Technical Field The invention relates to the field of pipeline processing, in particular to a processing method, equipment and medium for a plastic-lined pipe. Background The plastic lining pipe is a composite pipe which takes a common carbon steel pipe as a base material and is formed by cold drawing composite or rotational molding of thermoplastic plastics, namely, an outer pipe of the plastic lining pipe is a steel pipe, an inner pipe of the plastic lining pipe is a plastic pipe, when the plastic lining pipe is manufactured by processing, the plastic pipe is required to be placed in the steel pipe, then the steel pipe is subjected to hot processing, and the plastic pipe is internally inflated, so that the temperature of the plastic pipe is increased, and the plastic pipe can be attached to the inner wall of the steel pipe, so that the plastic lining pipe is formed. In the process of processing the plastic-lined pipe, the processing effect of the plastic-lined pipe is possibly unsatisfactory due to the factors of unstable thermal processing temperature, uneven thermal processing position and the like, so that the quality detection of the plastic-lined pipe in the process of processing is needed, and the processing effect of the plastic-lined pipe is in accordance with the processing standard. Disclosure of Invention Aiming at the technical problems, the invention adopts the following technical scheme: according to one aspect of the application, there is provided a method of processing a plastic lined pipe, comprising: step S100, predicting a plurality of temperature data corresponding to each data acquisition point position on an outer tube of a plastic lining tube to be processed in a target time period in the process of performing thermal processing treatment to obtain a plurality of first predicted data corresponding to the current time, wherein the duration of the target time period is a preset duration, and the ending time of the target time period is a data acquisition time which is positioned before the current time and has the shortest duration with the current time; Step S200, predicting a plurality of temperature data corresponding to each data acquisition point position corresponding to the inner pipe of the plastic-lined pipe to be processed in a target time period to obtain a plurality of second prediction data corresponding to the current moment; Step S300, determining a first matching weight and a second matching weight according to fluctuation characteristics of a plurality of temperature data corresponding to each data acquisition point position corresponding to an inner pipe of a plastic lining pipe to be processed at the current moment; Step S400, carrying out weighting treatment on the first matching weight, the second matching weight, the plurality of first prediction data and the plurality of second prediction data to obtain a processing characteristic value corresponding to the plastic lining pipe to be processed at the current moment; and S500, if the processing characteristic value is within the preset processing normal characteristic value range, determining that the thermal processing state of the plastic lining pipe to be processed at the current moment is a normal state, and if not, determining that the thermal processing state of the plastic lining pipe to be processed at the current moment is an abnormal state. According to another aspect of the present application, there is provided a non-transitory computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement the aforementioned method of processing a plastic lined pipe. According to yet another aspect of the present application, there is provided an electronic device comprising a processor and the aforementioned non-transitory computer-readable storage medium. The invention has at least the following beneficial effects: According to the processing method of the lining plastic pipe, each data acquisition point on the outer pipe of the lining plastic pipe to be processed is firstly subjected to prediction processing on a plurality of temperature data corresponding to a target time period in the thermal processing process, so as to obtain a plurality of first prediction data corresponding to the current moment, and each data acquisition point corresponding to the inner pipe of the lining plastic pipe to be processed is subjected to prediction processing on a plurality of temperature data corresponding to the target time period, so as to obtain a plurality of second prediction data corresponding to the current moment, the first prediction data and the second prediction data are the temperature data of the current moment, which are obtained by predicting the temperature data of the outer pipe and the inner pipe of the lining plastic pipe to be processed in the target time perio