CN116638770A - PE pipe continuous transmission welding system and welding method thereof - Google Patents
PE pipe continuous transmission welding system and welding method thereof Download PDFInfo
- Publication number
- CN116638770A CN116638770A CN202310835721.3A CN202310835721A CN116638770A CN 116638770 A CN116638770 A CN 116638770A CN 202310835721 A CN202310835721 A CN 202310835721A CN 116638770 A CN116638770 A CN 116638770A
- Authority
- CN
- China
- Prior art keywords
- heating
- cambered surface
- temperature
- training
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003466 welding Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000005540 biological transmission Effects 0.000 title claims description 10
- 238000010438 heat treatment Methods 0.000 claims abstract description 292
- 239000012943 hotmelt Substances 0.000 claims abstract description 99
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 239000013598 vector Substances 0.000 claims description 87
- 238000012549 training Methods 0.000 claims description 74
- 239000011159 matrix material Substances 0.000 claims description 72
- 238000013527 convolutional neural network Methods 0.000 claims description 24
- 238000000354 decomposition reaction Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 19
- 230000003247 decreasing effect Effects 0.000 claims description 14
- 230000004043 responsiveness Effects 0.000 claims description 14
- 238000007405 data analysis Methods 0.000 claims description 13
- 230000004044 response Effects 0.000 claims description 12
- 230000009471 action Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 abstract description 16
- 230000002457 bidirectional effect Effects 0.000 abstract description 5
- 239000004698 Polyethylene Substances 0.000 description 61
- 238000009826 distribution Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 12
- 238000010276 construction Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 230000009977 dual effect Effects 0.000 description 7
- 230000014509 gene expression Effects 0.000 description 5
- 230000002829 reductive effect Effects 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000001125 extrusion Methods 0.000 description 4
- 238000002844 melting Methods 0.000 description 4
- 230000008018 melting Effects 0.000 description 4
- -1 polyethylene Polymers 0.000 description 4
- 229920000573 polyethylene Polymers 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 239000012530 fluid Substances 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000004033 plastic Substances 0.000 description 3
- 229920003023 plastic Polymers 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000002195 synergetic effect Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 239000003513 alkali Substances 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000002079 cooperative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009474 hot melt extrusion Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C65/00—Joining or sealing of preformed parts, e.g. welding of plastics materials; Apparatus therefor
- B29C65/02—Joining or sealing of preformed parts, e.g. welding of plastics materials; Apparatus therefor by heating, with or without pressure
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C66/00—General aspects of processes or apparatus for joining preformed parts
- B29C66/90—Measuring or controlling the joining process
- B29C66/91—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux
- B29C66/912—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux by measuring the temperature, the heat or the thermal flux
- B29C66/9121—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux by measuring the temperature, the heat or the thermal flux by measuring the temperature
- B29C66/91231—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux by measuring the temperature, the heat or the thermal flux by measuring the temperature of the joining tool
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C66/00—General aspects of processes or apparatus for joining preformed parts
- B29C66/90—Measuring or controlling the joining process
- B29C66/91—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux
- B29C66/914—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux by controlling or regulating the temperature, the heat or the thermal flux
- B29C66/9141—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux by controlling or regulating the temperature, the heat or the thermal flux by controlling or regulating the temperature
- B29C66/91421—Measuring or controlling the joining process by measuring or controlling the temperature, the heat or the thermal flux by controlling or regulating the temperature, the heat or the thermal flux by controlling or regulating the temperature of the joining tools
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C66/00—General aspects of processes or apparatus for joining preformed parts
- B29C66/90—Measuring or controlling the joining process
- B29C66/96—Measuring or controlling the joining process characterised by the method for implementing the controlling of the joining process
- B29C66/965—Measuring or controlling the joining process characterised by the method for implementing the controlling of the joining process using artificial neural networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29L—INDEXING SCHEME ASSOCIATED WITH SUBCLASS B29C, RELATING TO PARTICULAR ARTICLES
- B29L2023/00—Tubular articles
- B29L2023/22—Tubes or pipes, i.e. rigid
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Radiation Pyrometers (AREA)
Abstract
The application discloses a PE pipe non-stop welding system and a welding method thereof, wherein in the heating process of a double-arc heater, a camera is used for collecting a state monitoring video of a hot melt at the joint of a connecting pipe fitting and the double-arc heater so as to adaptively regulate and control the heating temperature of the double-arc heater based on the state change condition of the hot melt, thereby intelligently realizing the bidirectional heating welding of the contact surface of the pipe fitting and a pipeline in the PE pipe non-stop state so as to improve the welding quality.
Description
Technical Field
The application relates to the technical field of intelligent welding, in particular to a PE pipe continuous transmission welding system and a welding method thereof.
Background
In the normal use process of the polyethylene plastic pipeline (PE pipeline), branch lines with the same pipe diameter are often added on the pipeline according to production and living needs, besides the branch lines are added, the original pipeline in use can be maintained, changed or replaced due to the service life, urban construction and other reasons, and plugging is also carried out. How to safely and leak-free connect PE pipeline with pipe diameter branch line under the condition of no stop transportation and to carry out plugging construction due to maintenance, diversion or pipeline replacement is a problem to be improved in the technical field of PE pipeline construction at present.
At present, in the traditional PE pipeline hot-melt welding method, only the pipeline is usually heated, and the pipe fitting is heated by means of heat conduction, so that temperature non-uniformity is easily caused, and welding quality is easily affected. In the prior art, there are two-way heating of the contact surface of the pipe fitting and the pipe in the continuous conveying state by the double-arc heater, so as to ensure the uniform distribution of the temperature in the welding process, thereby improving the welding quality. However, the temperature control of the double-arc heater in the prior art is performed by means of manual experience, and the extrusion height of the hot melt at the joint of the connecting pipe fitting and the double-arc heater in the pressing and heating process is not concerned, so that the temperature of the hot melt is easily too high or too low, and the welding quality is easily affected. Specifically, during the pressing and heating process, uneven extrusion heights of the hot melt may cause uneven or weak welding seams, affect welding strength and tightness, and increase the risk of leakage. And, the uneven hot melt extrusion height at the joint of the connecting pipe fitting and the double-arc heater can also cause uneven pressure application, so that the welding contact surface is uneven, and the welding quality is affected.
Accordingly, an optimized PE tube non-stop welding system is desired.
Disclosure of Invention
The embodiment of the application provides a PE pipe continuous welding system and a welding method thereof, wherein in the heating process of a double-arc heater, a camera is used for collecting a state monitoring video of a hot melt at the joint of a connecting pipe fitting and the double-arc heater so as to adaptively regulate and control the heating temperature of the double-arc heater based on the state change condition of the hot melt, thereby intelligently realizing the bidirectional heating welding of the contact surface of the pipe fitting and a pipeline in the PE pipe continuous state so as to improve the welding quality.
The embodiment of the application also provides a PE pipe continuous welding system, which comprises:
the data acquisition module is used for acquiring heating temperature values of the first heating cambered surface and heating temperature values of the second heating cambered surface at a plurality of preset time points in a preset time period and acquiring a state monitoring video of a hot melt object in the preset time period through the camera;
the data analysis module is used for carrying out cooperative analysis on the heating temperature values of the first heating cambered surface and the second heating cambered surface at the plurality of preset time points and the state monitoring video of the hot melt to obtain a state-temperature correlation characteristic matrix; and
and the heating temperature control module of the first heating cambered surface is used for determining whether the heating temperature value of the first heating cambered surface should be increased or decreased based on the state-temperature correlation characteristic matrix.
The embodiment of the application also provides a PE pipe continuous welding method, which comprises the following steps:
acquiring heating temperature values of a first heating cambered surface and heating temperature values of a second heating cambered surface at a plurality of preset time points in a preset time period, and acquiring a state monitoring video of a hot melt in the preset time period through a camera;
carrying out cooperative analysis on the heating temperature values of the first heating cambered surface and the second heating cambered surface at a plurality of preset time points and the state monitoring video of the hot melt to obtain a state-temperature correlation characteristic matrix; and
based on the state-temperature correlation feature matrix, it is determined that the heating temperature value of the first heating profile should be increased or decreased.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a block diagram of a PE pipe continuous welding system according to an embodiment of the present application.
Fig. 2 is a block diagram of the data analysis module in the PE pipe continuous welding system according to the embodiment of the present application.
Fig. 3 is a block diagram of the training module in the PE pipe continuous welding system according to the embodiment of the present application.
Fig. 4 is a flowchart of a method for welding a PE pipe without stopping transmission according to an embodiment of the present application.
Fig. 5 is a schematic diagram of a system architecture of a method for continuous welding of PE pipes according to an embodiment of the present application.
Fig. 6 is an application scenario diagram of a PE pipe continuous welding system provided in an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present application and their descriptions herein are for the purpose of explaining the present application, but are not to be construed as limiting the application.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In describing embodiments of the present application, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
Polyethylene plastic tubing (Polyethylene Pipe, PE tubing for short) is a common plastic tubing made of polyethylene material. The PE pipeline has excellent chemical corrosion resistance, can resist corrosion of various chemical substances such as acid, alkali, salt and the like, and is suitable for conveying various media. The PE pipeline has higher strength and impact resistance, can bear certain external pressure and impact load, and is suitable for various engineering environments. The PE pipeline has certain flexibility and plasticity, can adapt to the influence of external forces such as ground deformation, earthquake and the like, and reduces the risk of pipeline rupture. The PE pipeline has good wear resistance, can resist the abrasion of particulate matters, and prolongs the service life. PE pipeline is lighter relatively, and the transport and the installation of being convenient for reduce the construction degree of difficulty and cost. The PE pipeline has longer service life, which can reach decades, and reduces the frequency and cost of maintenance and replacement. The PE pipeline is an environment-friendly material, can be recycled and meets the requirement of sustainable development.
PE pipeline wide application in urban water supply, drainage, natural gas transportation, petrochemical industry, irrigation in farmland etc.. In the construction engineering, the PE pipe is commonly used for a cold and hot water supply system, a floor heating system, etc., and meanwhile, the PE pipe is also widely used in industrial fields such as chemical plants, power stations, etc.
It should be appreciated that conventional pipe welding requires stopping fluid delivery, and performs welding operations, which can lead to downtime and downtime in the production line or process, while PE pipe continuous welding can be performed while fluid delivery is being performed, without downtime and downtime, thereby greatly improving the efficiency of construction. The PE pipe is not required to be stopped and produced without stopping transportation and welding, so that the interruption time of a production line or a process flow is reduced, the manpower resource and the energy cost are saved, and meanwhile, the construction cost is also reduced because no additional process equipment and materials are required.
The PE pipe can realize the bidirectional heating welding of the contact surface of the pipe fitting and the pipe without stopping the transmission welding, the uniformity and the sealing performance of the welding are ensured, and the heating parameters can be timely adjusted by monitoring the state of the hot melt at the joint, so that the stability and the reliability of the welding quality are ensured. Moreover, the PE pipe is welded without stopping transmission, so that the risks of pipeline pressure fluctuation and fluid leakage caused by shutdown can be avoided, the possibility of pipeline water leakage and leakage can be reduced due to the improvement of welding quality, and the safety and reliability of the pipeline are enhanced.
Namely, PE pipe continuous transmission welding has the necessity of improving construction efficiency, reducing construction cost, improving welding quality and enhancing pipeline safety, is an intelligent technical conception, and can be widely applied to the existing pipeline system.
In one embodiment of the present application, fig. 1 is a block diagram of a PE pipe continuous welding system provided in an embodiment of the present application. As shown in fig. 1, a PE pipe continuous welding system 100 according to an embodiment of the present application includes: the data acquisition module 110 is configured to acquire heating temperature values of a first heating arc surface and heating temperature values of a second heating arc surface at a plurality of predetermined time points in a predetermined time period, and acquire a state monitoring video of a hot melt object in the predetermined time period through a camera; the data analysis module 120 is configured to cooperatively analyze the heating temperature values of the first heating cambered surface and the second heating cambered surface at the plurality of predetermined time points, and the state monitoring video of the hot melt object to obtain a state-temperature correlation feature matrix; and a heating temperature control module 130 of the first heating arc surface, configured to determine, based on the state-temperature correlation feature matrix, whether the heating temperature value of the first heating arc surface should be increased or decreased.
The data acquisition module 110 ensures that the heating temperature values of the first heating cambered surface and the second heating cambered surface at a plurality of preset time points in a preset time period are accurately acquired, and the state monitoring video of the hot melt is acquired through the camera, and meanwhile, the accuracy and the reliability of the sensor, and the definition and the stability of the camera are ensured. The data acquisition module 110 can acquire the heating temperature value and the state monitoring video of the hot melt in real time, and provide accurate data support for subsequent data analysis and temperature control.
The data analysis module 120 performs collaborative analysis on the heating temperature values at a plurality of predetermined time points and the state monitoring video of the hot melt to obtain a state-temperature correlation feature matrix, which performs data processing and design of an analysis algorithm to extract effective feature information. The data analysis module 120 can perform collaborative analysis on the heating temperature value and the information of the state of the hot melt to obtain a state-temperature correlation characteristic matrix, so as to provide accurate basis for temperature control.
The heating temperature control module 130 of the first heating cambered surface determines that the heating temperature value of the first heating cambered surface should be increased or decreased based on the state-temperature correlation feature matrix, and adopts a corresponding temperature adjustment strategy according to the analysis result of the feature matrix. Through the heating temperature control module 130 of the first heating cambered surface, intelligent control of the heating temperature of the first heating cambered surface can be realized according to the state-temperature correlation characteristic matrix, so that the welding quality and stability are improved.
The PE pipe continuous transmission welding system 100 realizes intelligent control of heating temperature through the synergistic effect of the data acquisition, analysis and temperature control modules, and improves welding quality and efficiency. Meanwhile, the state of the hot melt is monitored through the camera, abnormal conditions can be found in time and processed, and the reliability and safety of welding are further guaranteed.
Specifically, the data acquisition module 110 is configured to acquire a heating temperature value of the first heating cambered surface and a heating temperature value of the second heating cambered surface at a plurality of predetermined time points within a predetermined time period, and acquire a state monitoring video of the hot melt in the predetermined time period through a camera.
Aiming at the technical problems, the technical conception of the application is that in the heating process of the double-arc heater, the state monitoring video of the hot melt at the joint of the connecting pipe fitting and the double-arc heater is collected through the camera so as to adaptively regulate and control the heating temperature of the double-arc heater based on the state change condition of the hot melt, thereby intelligently realizing the bidirectional heating welding of the contact surface of the pipe fitting and the pipeline under the PE pipe continuous conveying state so as to improve the welding quality.
Specifically, in the technical scheme of the application, firstly, the heating temperature values of the first heating cambered surface and the second heating cambered surface at a plurality of preset time points in a preset time period and the state monitoring video of the hot melt in the preset time period are obtained.
The state monitoring video of the hot melt object collected by the camera can provide real-time visual information in the welding process, and the heating temperature value provides temperature data corresponding to the video image. In the monitoring video, the melting condition, the melting degree, the contact surface state of the hot melt and the pipeline and the like of the hot melt can be observed, and the information can judge whether the hot melt in the welding process reaches the expected state or not and whether any abnormal condition exists, such as uneven heating, incomplete melting or overheating of the hot melt and the like.
Meanwhile, the heating temperature value provides quantitative data of temperature change of the heating cambered surface in the welding process, and the heating process can be analyzed and evaluated in real time by monitoring and recording the heating temperature values of the first heating cambered surface and the second heating cambered surface. By comparing the temperature value with the observation result in the hot melt state monitoring video, the relation between the heating temperature and the hot melt state can be determined, and the welding parameters and the control strategy are further optimized so as to improve the welding quality and efficiency.
Therefore, by combining the heating temperature values of the first heating cambered surface and the second heating cambered surface with the state monitoring video of the hot melt, the temperature change and the state of the hot melt in the welding process can be comprehensively known, and the welding quality can be monitored and controlled.
Specifically, the data analysis module 120 is configured to cooperatively analyze the heating temperature values of the first heating cambered surface and the second heating cambered surface at the plurality of predetermined time points, and the state monitoring video of the hot melt to obtain a state-temperature correlation feature matrix. Fig. 2 is a block diagram of the data analysis module in the PE pipe continuous welding system according to the embodiment of the present application, as shown in fig. 2, the data analysis module 120 includes: a heating temperature time sequence correlation feature extraction unit 121, configured to perform time sequence correlation feature extraction on a heating temperature value of a first heating arc surface and a heating temperature value of a second heating arc surface at the plurality of predetermined time points to obtain a double heating arc surface cooperative temperature time sequence feature vector; a hot melt state feature extraction unit 122, configured to extract a hot melt state time sequence feature vector from a state monitoring video of the hot melt; and a feature responsiveness correlation unit 123, configured to perform responsiveness correlation encoding on the dual-heating cambered surface collaborative temperature time sequence feature vector and the hot melt state time sequence feature vector to obtain the state-temperature correlation feature matrix.
The heating temperature time sequence correlation feature extraction unit is used for extracting time sequence correlation features of the heating temperatures of the double heating cambered surfaces, so that a double heating cambered surface collaborative temperature time sequence feature vector is obtained, the change condition of the heating temperatures is monitored and controlled, and the welding quality and stability are improved. Through hot melt state characteristic extraction element, can follow the state monitoring video of hot melt and draw hot melt state time sequence feature vector, can monitor the state of hot melt like this in real time, including information such as melting degree, form, help in time finding and solving the problem that probably appears in the welding process. Through the feature responsiveness association unit, responsiveness association coding can be carried out on the double-heating cambered surface collaborative temperature time sequence feature vector and the hot melt state time sequence feature vector, so that a state-temperature association feature matrix is obtained, association analysis on heating temperature and hot melt state is facilitated, more comprehensive information is provided, and support is provided for further data analysis and decision.
Through the steps, the intelligent level of the heating process of the double-arc heater can be improved, the welding quality is improved, the real-time monitoring of the state of the hot melt and the relevant feature coding of the responsiveness are realized, and the method has higher practicability and application value.
Wherein, for the heating temperature timing-related feature extraction unit 121, it includes: a heating temperature time sequence arrangement subunit, configured to arrange the heating temperature values of the first heating cambered surface and the heating temperature values of the second heating cambered surface at the plurality of predetermined time points into a first heating cambered surface temperature time sequence input vector and a second heating cambered surface temperature time sequence input vector according to a time dimension respectively; the double-heating cambered surface heating temperature association subunit is used for carrying out association coding on the first heating cambered surface temperature time sequence input vector and the second heating cambered surface temperature time sequence input vector to obtain a double-heating cambered surface cooperative temperature action matrix; and the double-heating cambered surface temperature cooperative characteristic extraction subunit is used for enabling the double-heating cambered surface cooperative temperature action matrix to pass through a cooperative time sequence characteristic extractor based on a convolutional neural network model so as to obtain the double-heating cambered surface cooperative temperature time sequence characteristic vector.
Then, considering that the heating temperature values of the first heating cambered surface and the heating temperature values of the second heating cambered surface have dynamic change rules in the time dimension, in order to perform time sequence collaborative analysis on the double cambered surface heating temperature values of the double-arc heater so as to establish a mapping association relation with the hot melt state, firstly, the heating temperature values of the first heating cambered surface and the heating temperature values of the second heating cambered surface at a plurality of preset time points are respectively arranged into a first heating cambered surface temperature time sequence input vector and a second heating cambered surface temperature time sequence input vector according to the time dimension so as to integrate time sequence distribution information of the heating temperature values of the first heating cambered surface and the heating temperature values of the second heating cambered surface respectively.
And then, carrying out association coding on the first heating cambered surface temperature time sequence input vector and the second heating cambered surface temperature time sequence input vector so as to establish a time sequence cooperative association relationship between the heating temperature value of the first heating cambered surface and the heating temperature value of the second heating cambered surface, so that the time sequence cooperative action characteristic capture of the double cambered surface temperatures of the double-arc heater can be fully and effectively carried out subsequently, and a double heating cambered surface cooperative temperature action matrix is obtained.
Then, a cooperative time sequence feature extractor based on a convolutional neural network model with excellent performance in implicit association feature extraction is used for carrying out feature mining on the dual-heating cambered surface cooperative temperature action matrix, so that time sequence cooperative association feature distribution information between heating temperature values of two heating cambered surfaces of the dual-arc heater is extracted, and a dual-heating cambered surface cooperative temperature time sequence feature vector is obtained.
Collaborative timing feature extractor based on convolutional neural network (Convolutional Neural Network, CNN) model is an effective method for extracting implicit correlation features in timing data, CNN model has achieved remarkable results in the field of image processing, but it can also be applied to other types of data, such as timing data.
In the application of a dual arc heater, a CNN-based collaborative timing feature extractor may be used to extract timing collaborative correlation feature distribution information between heating temperature values of dual heating arcs, typically consisting of multiple convolution layers and pooling layers, and capture spatial and temporal features in the input data by learning the weights of the convolution kernels.
The CNN-based collaborative timing feature extractor may encode timing collaborative correlation feature distribution information between heating temperature values of the dual heating arcs into dual heating arc collaborative temperature timing feature vectors, which may be used for subsequent data analysis and decision, such as monitoring a change trend of the heating temperature, detecting an abnormal situation, and the like.
Further, for the hot melt state feature extraction unit 122, it is configured to: and performing sparse sampling on the state monitoring video of the hot melt, and then obtaining the state time sequence feature vector of the hot melt through a state time sequence feature extractor based on a three-dimensional convolutional neural network model.
Further, in order to monitor the extrusion height of the hot melt at the joint of the connecting pipe fitting and the double-arc heater in real time during the heating process of the double-arc heater, so as to ensure the uniformity of the extrusion height of the hot melt and the quality of welding, the state time sequence change characteristic information related to the hot melt in the state monitoring video is required to be described. Therefore, in the technical scheme of the application, after sparse sampling is carried out on the state monitoring video of the hot melt, feature mining is carried out in a state time sequence feature extractor based on a three-dimensional convolutional neural network model so as to extract state time sequence related feature information about the hot melt in the state monitoring video, thereby obtaining a state time sequence feature vector of the hot melt. In particular, here, by sparse sampling, redundancy and storage requirements of the state monitoring video data can be reduced while key information is retained, thereby reducing the amount of computation and improving the processing efficiency.
Still further, for the feature responsiveness associating unit 123, it is configured to: and calculating the response estimation of the hot melt state time sequence feature vector relative to the double-heating cambered surface collaborative temperature time sequence feature vector to obtain the state-temperature correlation feature matrix.
Next, it is also considered that since the hot-melt state timing characteristic vector and the double heating cambered surface cooperative temperature timing characteristic vector each correspond to one characteristic distribution manifold in a high-dimensional characteristic space, which is extremely irregular and complex in boundary of the newly obtained characteristic distribution manifold due to its own irregular shape and scattering position, if fusion-associated characteristic representation of the hot-melt state timing variation characteristic information and the heating temperature timing cooperative associated characteristic information of the double heating cambered surface is performed by cascading only the hot-melt state timing characteristic vector and the double heating cambered surface cooperative temperature timing characteristic vector, it is equivalent to simply superimposing these characteristic distribution manifolds in original position and shape, so that it is extremely easy to sink into a local extremum point when finding an optimum point by gradient descent, and it is impossible to obtain a global optimum point. Therefore, in the technical scheme of the application, a Gaussian density chart is used for calculating the response estimation of the state time sequence feature vector of the hot melt relative to the double-heating cambered surface cooperative temperature time sequence feature vector to obtain the state-temperature correlation feature matrix, so that the correlation feature information between the state time sequence change feature of the hot melt and the heating temperature time sequence cooperative correlation feature of the double-heating cambered surface is represented.
The responsiveness estimation refers to the sensitivity degree of the hot melt state time sequence feature vector to the change of the double-heating cambered surface cooperative temperature time sequence feature vector. By estimating the responsiveness, the degree of correlation between the hot melt state time sequence feature vector and the double-heating cambered surface temperature time sequence feature vector can be known.
In one embodiment of the application, various statistical methods or machine learning algorithms may be used for responsiveness estimation, for example, using correlation coefficients to measure the degree of correlation between two variables. The correlation coefficient has a value ranging from-1 to 1, wherein 1 represents a complete positive correlation, -1 represents a complete negative correlation, and 0 represents no correlation.
For the hot melt state timing characteristic vector and the double heating arc temperature timing characteristic vector, a correlation coefficient therebetween may be calculated to estimate responsiveness. If the correlation coefficient is close to 1 or-1, the time sequence feature vector representing the state of the hot melt is very sensitive to the change of the time sequence feature vector of the temperature of the double heating cambered surfaces, and has strong correlation.
Through the response estimation, a state-temperature correlation characteristic matrix can be obtained, so that the relation between the state and the temperature of the hot melt in the heating process of the double-arc heater can be better understood and controlled, and the welding quality is improved.
Specifically, the heating temperature control module 130 of the first heating cambered surface is configured to determine, based on the state-temperature correlation feature matrix, whether the heating temperature value of the first heating cambered surface should be increased or decreased. Further used for: and passing the state-temperature correlation characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature value of the first heating cambered surface should be increased or decreased.
And then, the state-temperature correlation characteristic matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature value of the first heating cambered surface should be increased or decreased. That is, classification processing is performed by using correlation characteristic information between the state time sequence change characteristic of the hot melt and the heating temperature time sequence cooperative correlation characteristic of the double-arc heating surface, so that the heating temperature of the double-arc heater is adaptively regulated and controlled based on the state change condition of the hot melt. Through the mode, the welding process can be monitored and regulated in real time, so that the welding quality and the construction efficiency are improved, and the leakage risk is reduced.
Further, in the application, the PE pipe continuous welding system further comprises a training module for training the collaborative time sequence feature extractor based on the convolutional neural network model, the state time sequence feature extractor based on the three-dimensional convolutional neural network model and the classifier. Fig. 3 is a block diagram of the training module in the PE pipe continuous welding system according to the embodiment of the present application, as shown in fig. 3, the training module 140 includes: the training data acquisition unit 141 is configured to acquire training data, where the training data includes training heating temperature values of a first heating arc surface and training heating temperature values of a second heating arc surface at a plurality of predetermined time points in a predetermined period, a state monitoring video of a training hot melt in the predetermined period, and a real value that the heating temperature value of the first heating arc surface should be increased or decreased; a training heating temperature time sequence arrangement unit 142, configured to arrange training heating temperature values of the first heating cambered surface and training heating temperature values of the second heating cambered surface at the plurality of predetermined time points into a first training heating cambered surface temperature time sequence input vector and a second training heating cambered surface temperature time sequence input vector according to a time dimension, respectively; the training double-heating cambered surface temperature cooperative association unit 143 is used for carrying out association coding on the first training heating cambered surface temperature time sequence input vector and the second training heating cambered surface temperature time sequence input vector to obtain a training double-heating cambered surface cooperative temperature action matrix; a training double-heating cambered surface temperature correlation feature extraction unit 144, configured to pass the training double-heating cambered surface cooperative temperature action matrix through the cooperative time sequence feature extractor based on the convolutional neural network model to obtain a training double-heating cambered surface cooperative temperature time sequence feature vector; the training hot melt state time sequence feature extraction unit 145 is configured to obtain a training hot melt state time sequence feature vector through the state time sequence feature extractor based on the three-dimensional convolutional neural network model after performing sparse sampling on the training hot melt state monitoring video; the training feature responsiveness correlation unit 146 is configured to calculate responsiveness estimation of the training hot melt state time sequence feature vector relative to the training double-heating cambered surface collaborative temperature time sequence feature vector to obtain a training state-temperature correlation feature matrix; a classification loss unit 147, configured to pass the training state-temperature correlation feature matrix through a classifier to obtain a classification loss function value; a manifold convex decomposition consistency loss unit 148 for calculating a manifold convex decomposition consistency factor of the training state-temperature correlation feature matrix to obtain a manifold convex decomposition consistency loss function value; and a model training unit 149 for training the collaborative timing feature extractor based on the convolutional neural network model, the state timing feature extractor based on the three-dimensional convolutional neural network model, and the classifier by back propagation of gradient descent with a weighted sum of the classification loss function value and the manifold convex decomposition consistency loss function value as a loss function value.
In particular, in the technical solution of the present application, when the state-temperature correlation feature matrix is obtained by calculating the responsiveness estimation of the hot-melt state time-series feature vector with respect to the dual heating cambered surface cooperative temperature time-series feature vector using a gaussian density chart, the response feature vector of the hot-melt state time-series feature vector with respect to the dual heating cambered surface cooperative temperature time-series feature vector is probability-sampled based on each row variance distribution of the response variance matrix of the self variance matrix of the hot-melt state time-series feature vector with respect to the self variance matrix of the dual heating cambered surface cooperative temperature time-series feature vector, so as to obtain each row feature vector of the state-temperature correlation feature matrix, and here, in consideration of randomness in probability sampling, each row feature vector of the state-temperature correlation feature matrix is preferably constrained so as to avoid the under-fitting of the overall feature expression of the state-temperature correlation feature matrix through a classifier.
Here, since the overall feature distribution of the response feature vector conforms to the timing feature distribution of the hot-melt state image semantics and the synergistic temperature action of the double heating cambered surfaces, while the feature distribution of the state-temperature correlation feature matrix in the column direction follows the overall feature distribution of the response feature vector, if the manifold expression of the state-temperature correlation feature matrix in the high-dimensional feature space is kept uniform in different distribution dimensions corresponding to the row direction and the column direction, the individual row feature vectors of the state-temperature correlation feature matrix can be constrained.
Therefore, the applicant of the present application further introduces, in addition to the classification loss function, a manifold convex decomposition consistency loss function of the state-temperature correlation feature matrix M, specifically expressed as: calculating a manifold convex decomposition consistency factor of the training state-temperature correlation feature matrix by using a loss formula to obtain a manifold convex decomposition consistency loss function value; wherein, the loss formula is:
v c ＝∑ i m i，j
v c ＝∑ j m i，j
wherein m is i,j Characteristic values representing the (i, j) th position of the training state-temperature correlation characteristic matrix, V r And V c The training state-temperature correlation characteristic matrix is respectively the mean value vector of the ith row vector and the mean value vector of the column vector, and II is II 1 Representing a norm of the vector, II F The Frobenius norms of the matrix are represented, W and H are the width and height of the training state-temperature correlation feature matrix, and W 1 、w 2 And w 3 Is a weight superparameter, sigmoid (·) represents a Sigmoid function,representing the manifold convex decomposition consistency loss function value.
That is, considering the dimensional expressions of the row and column dimensions of the state-temperature correlation feature matrix M as described above, the manifold convex decomposition consistency factor flattens the set of finite convex polynomials of manifolds in different dimensions by the geometric convex decomposition of the feature manifold represented by the state-temperature correlation feature matrix M with respect to the distribution differences in the sub-dimensions represented by the row and column of the classification feature matrix M, and constrains the geometric convex decomposition in the form of shape weights associated by the sub-dimensions, thereby promoting consistency of the convex geometric representations of the feature manifold of the state-temperature correlation feature matrix M in the decomposable dimensions represented by the row and column, so that the manifold expressions of the state-temperature correlation feature matrix in the high-dimensional feature space remain consistent in the different distribution dimensions corresponding to the row and column directions, thereby avoiding under-fitting of the overall feature expression of the state-temperature correlation feature matrix by the classifier. Like this, can carry out the self-adaptation regulation and control to the heating temperature of double arc heater based on the state change condition of hot melt thing to the two-way heating welding of pipe fitting and pipeline contact surface under the intelligent realization PE pipe does not stop the transportation state reduces the leakage risk, improves welding quality.
In summary, the PE pipe continuous welding system 100 according to the embodiment of the application is illustrated, which adaptively adjusts and controls the heating temperature of the double-arc heater based on the state change condition of the hot melt, so as to intelligently realize bidirectional heating welding of the contact surface of the pipe fitting and the pipe in the PE pipe continuous state, and improve the welding quality.
As described above, the PE pipe non-stop welding system 100 according to the embodiment of the present application may be implemented in various terminal devices, such as a server for PE pipe non-stop welding, and the like. In one example, the PE tube continuous welding system 100 in accordance with an embodiment of the application may be integrated into the terminal device as a software module and/or hardware module. For example, the PE tube continuous welding system 100 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the PE tube continuous welding system 100 can also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the PE tube continuous welding system 100 and the terminal device may be separate devices, and the PE tube continuous welding system 100 may be connected to the terminal device via a wired and/or wireless network and communicate interactive information in accordance with a agreed data format.
In one embodiment of the present application, fig. 4 is a flowchart of a method for welding a PE pipe without stopping the transmission provided in the embodiment of the present application. Fig. 5 is a schematic diagram of a system architecture of a method for continuous welding of PE pipes according to an embodiment of the present application. As shown in fig. 4 and 5, a method for welding a PE pipe without stopping according to an embodiment of the present application includes: 210, acquiring heating temperature values of a first heating cambered surface and heating temperature values of a second heating cambered surface at a plurality of preset time points in a preset time period, and acquiring a state monitoring video of a hot melt in the preset time period through a camera; 220, performing collaborative analysis on the heating temperature values of the first heating cambered surface and the second heating cambered surface at the plurality of preset time points and the state monitoring video of the hot melt object to obtain a state-temperature correlation characteristic matrix; and, 230, determining that the heating temperature value of the first heating profile should be increased or decreased based on the state-temperature correlation feature matrix.
It will be appreciated by those skilled in the art that the specific operation of each step in the above-described PE tube continuous welding method has been described in detail in the above description of the PE tube continuous welding system with reference to FIGS. 1 to 3, and thus, repetitive descriptions thereof will be omitted.
Fig. 6 is an application scenario diagram of a PE pipe continuous welding system provided in an embodiment of the present application. As shown in fig. 6, in the application scenario, first, a heating temperature value (e.g., C1 as illustrated in fig. 6) of a first heating arc surface and a heating temperature value (e.g., C2 as illustrated in fig. 6) of a second heating arc surface at a plurality of predetermined time points within a predetermined period of time are acquired, and a state monitoring video (e.g., C3 as illustrated in fig. 6) of a hot melt for the predetermined period of time is acquired by a camera; then, the obtained heating temperature value of the first heating arc surface, the heating temperature value of the second heating arc surface and the state monitoring video are input into a server (for example, S as illustrated in fig. 6) provided with a PE pipe continuous welding algorithm, wherein the server can process the heating temperature value of the first heating arc surface, the heating temperature value of the second heating arc surface and the state monitoring video based on the PE pipe continuous welding algorithm to determine whether the heating temperature value of the first heating arc surface should be increased or decreased.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. A PE pipe continuous welding system, comprising:
the data acquisition module is used for acquiring heating temperature values of the first heating cambered surface and heating temperature values of the second heating cambered surface at a plurality of preset time points in a preset time period and acquiring a state monitoring video of a hot melt object in the preset time period through the camera;
the data analysis module is used for carrying out cooperative analysis on the heating temperature values of the first heating cambered surface and the second heating cambered surface at the plurality of preset time points and the state monitoring video of the hot melt to obtain a state-temperature correlation characteristic matrix; and
and the heating temperature control module of the first heating cambered surface is used for determining whether the heating temperature value of the first heating cambered surface should be increased or decreased based on the state-temperature correlation characteristic matrix.
2. The PE tube continuous welding system according to claim 1, wherein the data analysis module comprises:
a heating temperature time sequence correlation feature extraction unit, configured to perform time sequence correlation feature extraction on heating temperature values of the first heating cambered surface and heating temperature values of the second heating cambered surface at the plurality of predetermined time points to obtain a double-heating cambered surface cooperative temperature time sequence feature vector;
the hot melt state characteristic extraction unit is used for extracting a hot melt state time sequence characteristic vector from a state monitoring video of the hot melt; and
and the characteristic response association unit is used for carrying out response association coding on the double-heating cambered surface collaborative temperature time sequence characteristic vector and the hot melt state time sequence characteristic vector so as to obtain the state-temperature association characteristic matrix.
3. The PE pipe non-stop welding system according to claim 2, wherein the heating temperature timing-related feature extraction unit includes:
a heating temperature time sequence arrangement subunit, configured to arrange the heating temperature values of the first heating cambered surface and the heating temperature values of the second heating cambered surface at the plurality of predetermined time points into a first heating cambered surface temperature time sequence input vector and a second heating cambered surface temperature time sequence input vector according to a time dimension respectively;
the double-heating cambered surface heating temperature association subunit is used for carrying out association coding on the first heating cambered surface temperature time sequence input vector and the second heating cambered surface temperature time sequence input vector to obtain a double-heating cambered surface cooperative temperature action matrix; and
and the double-heating cambered surface temperature cooperative characteristic extraction subunit is used for enabling the double-heating cambered surface cooperative temperature action matrix to pass through a cooperative time sequence characteristic extractor based on a convolutional neural network model so as to obtain the double-heating cambered surface cooperative temperature time sequence characteristic vector.
4. A PE pipe non-stop welding system according to claim 3, characterized in that the hot melt state feature extraction unit is adapted to: and performing sparse sampling on the state monitoring video of the hot melt, and then obtaining the state time sequence feature vector of the hot melt through a state time sequence feature extractor based on a three-dimensional convolutional neural network model.
5. The PE pipe non-stop welding system of claim 4, wherein the characteristic responsiveness correlation unit is configured to: and calculating the response estimation of the hot melt state time sequence feature vector relative to the double-heating cambered surface collaborative temperature time sequence feature vector to obtain the state-temperature correlation feature matrix.
6. The PE tube continuous welding system according to claim 5, wherein the heating temperature control module of the first heating arc surface is configured to: and passing the state-temperature correlation characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the heating temperature value of the first heating cambered surface should be increased or decreased.
7. The PE tube continuous welding system of claim 6, further comprising a training module for training the collaborative timing feature extractor based on the convolutional neural network model, the state timing feature extractor based on the three-dimensional convolutional neural network model, and the classifier.
8. The PE tube continuous welding system of claim 7, wherein the training module comprises:
the training data acquisition unit is used for acquiring training data, wherein the training data comprise training heating temperature values of a first heating cambered surface and training heating temperature values of a second heating cambered surface at a plurality of preset time points in a preset time period, a state monitoring video of a training hot melt object in the preset time period, and a real value that the heating temperature value of the first heating cambered surface should be increased or decreased;
the training heating temperature time sequence arrangement unit is used for arranging the training heating temperature values of the first heating cambered surface and the training heating temperature values of the second heating cambered surface at the plurality of preset time points into a first training heating cambered surface temperature time sequence input vector and a second training heating cambered surface temperature time sequence input vector according to the time dimension;
the training double-heating cambered surface temperature cooperative association unit is used for carrying out association coding on the first training heating cambered surface temperature time sequence input vector and the second training heating cambered surface temperature time sequence input vector so as to obtain a training double-heating cambered surface cooperative temperature action matrix;
the training double-heating cambered surface temperature correlation feature extraction unit is used for enabling the training double-heating cambered surface cooperative temperature action matrix to pass through the cooperative time sequence feature extractor based on the convolutional neural network model to obtain a training double-heating cambered surface cooperative temperature time sequence feature vector;
the training hot melt state time sequence feature extraction unit is used for obtaining training hot melt state time sequence feature vectors through the state time sequence feature extractor based on the three-dimensional convolutional neural network model after sparse sampling is carried out on the training hot melt state monitoring video;
the training feature response correlation unit is used for calculating response estimation of the training hot melt state time sequence feature vector relative to the training double-heating cambered surface cooperative temperature time sequence feature vector so as to obtain a training state-temperature correlation feature matrix;
the classification loss unit is used for passing the training state-temperature association characteristic matrix through a classifier to obtain a classification loss function value;
the manifold convex decomposition consistency loss unit is used for calculating the manifold convex decomposition consistency factor of the training state-temperature correlation characteristic matrix to obtain a manifold convex decomposition consistency loss function value; and
and the model training unit is used for training the collaborative time sequence feature extractor based on the convolutional neural network model, the state time sequence feature extractor based on the three-dimensional convolutional neural network model and the classifier by taking the weighted sum of the classification loss function value and the manifold convex decomposition consistency loss function value as the loss function value and through the back propagation of gradient descent.
9. The PE pipe non-stop welding system of claim 8, wherein the manifold male decomposition consistency loss unit is configured to: calculating a manifold convex decomposition consistency factor of the training state-temperature correlation feature matrix by using a loss formula to obtain a manifold convex decomposition consistency loss function value;
wherein, the loss formula is:
wherein m is i,j Characteristic values representing the (i, j) th position of the training state-temperature correlation characteristic matrix, V r And V c The training state-temperature correlation characteristic matrix is respectively the mean value vector of the ith row vector and the mean value vector of the column vector, and II is II 1 Representing a norm of the vector, II F The Frobenius norms of the matrix are represented, W and H are the width and height of the training state-temperature correlation feature matrix, and W 1 、w 2 And w 3 Is a weight superparameter, sigmoid (·) represents a Sigmoid function,representing the manifold convex decomposition consistency loss function value.
10. The PE pipe continuous transmission welding method is characterized by comprising the following steps of:
acquiring heating temperature values of a first heating cambered surface and heating temperature values of a second heating cambered surface at a plurality of preset time points in a preset time period, and acquiring a state monitoring video of a hot melt in the preset time period through a camera;
carrying out cooperative analysis on the heating temperature values of the first heating cambered surface and the second heating cambered surface at a plurality of preset time points and the state monitoring video of the hot melt to obtain a state-temperature correlation characteristic matrix; and determining that the heating temperature value of the first heating cambered surface should be increased or decreased based on the state-temperature correlation characteristic matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310835721.3A CN116638770A (en) | 2023-07-10 | 2023-07-10 | PE pipe continuous transmission welding system and welding method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310835721.3A CN116638770A (en) | 2023-07-10 | 2023-07-10 | PE pipe continuous transmission welding system and welding method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116638770A true CN116638770A (en) | 2023-08-25 |
Family
ID=87619163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310835721.3A Pending CN116638770A (en) | 2023-07-10 | 2023-07-10 | PE pipe continuous transmission welding system and welding method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116638770A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117189071A (en) * | 2023-11-07 | 2023-12-08 | 克拉玛依市远山石油科技有限公司 | Automatic control method for core drilling rig operation |
| CN117211758A (en) * | 2023-11-07 | 2023-12-12 | 克拉玛依市远山石油科技有限公司 | Intelligent drilling control system and method for shallow hole coring |
-
2023
- 2023-07-10 CN CN202310835721.3A patent/CN116638770A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117189071A (en) * | 2023-11-07 | 2023-12-08 | 克拉玛依市远山石油科技有限公司 | Automatic control method for core drilling rig operation |
| CN117211758A (en) * | 2023-11-07 | 2023-12-12 | 克拉玛依市远山石油科技有限公司 | Intelligent drilling control system and method for shallow hole coring |
| CN117211758B (en) * | 2023-11-07 | 2024-04-02 | 克拉玛依市远山石油科技有限公司 | Intelligent drilling control system and method for shallow hole coring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116638770A (en) | PE pipe continuous transmission welding system and welding method thereof | |
| CN106706215B (en) | A kind of therrmodynamic system valves leakage quantity monitoring method | |
| US11204590B2 (en) | State estimation method for heating network in steady state based on bilateral equivalent model | |
| WO2019200662A1 (en) | Stability evaluation and static control method for electricity-heat-gas integrated energy system | |
| Dann et al. | Automated matching of pipeline corrosion features from in-line inspection data | |
| CN103302777B (en) | Neural-network-based energy consumption anomaly detection method of tire vulcanizing machine | |
| WO2023029117A1 (en) | Method and apparatus for analyzing alum floc feature by using image recognition technology | |
| CN112052564A (en) | Heat exchanger predictive maintenance method and system based on machine learning | |
| CN116557950A (en) | Central heating power network operation fault monitoring and early warning system based on artificial intelligence | |
| CN106322412A (en) | Coal-fired unit convection heating surface intelligent soot blowing method based on two-dimensional optimization | |
| WO2019071438A1 (en) | Method and apparatus for monitoring state of device in process industry and medium | |
| Na et al. | Residual stress prediction of dissimilar metals welding at NPPs using support vector regression | |
| CN113486950B (en) | Intelligent pipe network water leakage detection method and system | |
| CN112307650A (en) | Multi-step prediction method for ultra-supercritical boiler heating surface pipe wall overtemperature early warning | |
| CN117647143B (en) | Large-scale waste heat recovery control system | |
| KR20130089111A (en) | Estimating method for heat loss of secondary pipeline for district heating of apartment complex | |
| CN116045357A (en) | Urban heat supply three-dimensional visual monitoring system and method based on geothermal energy | |
| CN113591406B (en) | Heat pipe cooling reactor measuring point optimal arrangement and fault diagnosis method and system | |
| Zhou et al. | Leakage diagnosis of heating pipe-network based on BP neural network | |
| CN117066496B (en) | Casting cooling control method and system | |
| Xiong et al. | Optimization of process parameters for induction welding of composite materials based on NSGA-II and BP neural network | |
| CN117232317A (en) | Remote control method and remote control system for heat exchange unit | |
| CN105741184B (en) | Transformer state evaluation method and device | |
| Lin et al. | Thermal conductivity prediction of WO3-CuO-Ag (35: 40: 25)/water hybrid ternary nanofluid with Artificial Neural Network and back-propagation algorithm | |
| Biyanto | Fouling resistance prediction using artificial neural network nonlinear auto-regressive with exogenous input model based on operating conditions and fluid properties correlations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |