Intelligent early warning method and system for steel pipe flaw detection and corrosion prevention collaborative management

Abstract

The present application relates to a steel pipe flaw detection and anticorrosion collaborative control intelligent early warning method and system, belonging to the technical field of steel pipe production, comprising: real-time acquisition of steel pipe flaw detection defect data; inputting the steel pipe flaw detection defect data into a flaw detection-anticorrosion collaborative mapping model to generate a personalized anticorrosion process scheme; in the execution process of the personalized anticorrosion process scheme, real-time acquisition of anticorrosion process parameters and quality detection data, and inputting into a multidimensional quality early warning model for real-time analysis to determine whether the steel pipe after anticorrosion meets the quality requirements; when the steel pipe after anticorrosion does not meet the quality requirements, then the anticorrosion process parameters are readjusted. The present application establishes the correlation between defect data and anticorrosion process through a flaw detection-anticorrosion collaborative mapping model, realizes personalized anticorrosion process planning, solves the problem of insufficient protection or excessive anticorrosion caused by traditional unified process, and significantly improves the anticorrosion performance and service life of the steel pipe.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing and quality control technology for steel pipe production, specifically to an intelligent early warning method and system for the coordinated control of steel pipe flaw detection and corrosion prevention. Background Technology

[0002] In the steel pipe production process, flaw detection (identifying surface and internal cracks, inclusions, and other defects) and anti-corrosion treatment (forming a protective layer to resist corrosion) are key processes for ensuring product quality and extending service life. However, in current production, both processes generally adopt a "separate" management and control model, making it difficult for a matching MES system to achieve coordinated operation, leading to a series of technical defects, as follows:

[0003] 1. Disconnected process coordination: Flaw detection defect data cannot be synchronized to the corrosion protection module in real time. The corrosion protection process uses uniform parameters, resulting in insufficient protection of defective areas and waste of resources in defect-free areas. 2. Weak data integration: Flaw detection and corrosion protection equipment come from different manufacturers, with heterogeneous communication protocols. The MES lacks a unified integration interface, resulting in a broken quality traceability chain throughout the entire process and making it difficult to locate the root cause of the problem. 3. Delayed early warning mechanism: Early warning is only issued for parameters exceeding the standard in a single process, lacking a comprehensive early warning system that coordinates flaw detection and corrosion protection. Furthermore, it relies on fixed thresholds, which easily leads to false alarms and missed alarms. 4. Low scheduling efficiency: The MES cannot dynamically adjust the corrosion protection plan based on flaw detection results. Batch of non-conforming products can easily lead to ineffective processing, and equipment failures can easily cause work-in-process inventory buildup.

[0004] Currently, most domestic and international MES systems focus on front-end processes or single-process control, and a mature collaborative control solution for flaw detection and corrosion prevention has not yet been formed. As the application of steel pipes expands to high-risk corrosive environments such as deep seas, the requirements for product quality and corrosion resistance are increasing. There is an urgent need to develop MES systems and methods that can achieve collaborative process control and intelligent early warning to address the shortcomings of existing technologies. Summary of the Invention

[0005] To address the aforementioned problems, the purpose of this invention is to provide an intelligent early warning method and system for the coordinated management and control of steel pipe flaw detection and corrosion prevention.

[0006] Intelligent early warning methods for the coordinated management and control of steel pipe flaw detection and corrosion prevention include:

[0007] Step 1: Collect flaw detection data of steel pipes in real time;

[0008] Step 2: Input the flaw detection defect data of the steel pipe into the flaw detection-corrosion prevention collaborative mapping model to generate a personalized anti-corrosion process plan;

[0009] Step 3: During the implementation of the personalized anti-corrosion process plan, anti-corrosion process parameters and quality inspection data are collected in real time and input into a multi-dimensional quality early warning model for real-time analysis to determine whether the anti-corrosion steel pipe meets the quality requirements.

[0010] Step 4: If the anti-corrosion steel pipe does not meet the quality requirements, the anti-corrosion process parameters should be readjusted.

[0011] Preferably, in step 1, the flaw detection defect data includes: defect type, defect location, size, and defect detection time.

[0012] Preferably, in step 2, a flaw detection-corrosion prevention collaborative mapping model is constructed based on a knowledge graph library and machine learning algorithms; wherein, the flaw detection-corrosion prevention collaborative mapping model is trained with steel pipe specifications, defect type, defect size and defect location as input and appropriate anti-corrosion process parameters as output.

[0013] Preferably, in step 3, a multi-dimensional quality early warning model is constructed based on the LSTM time series prediction algorithm and the random forest classification algorithm; wherein, the multi-dimensional quality early warning model is trained with flaw detection defect data, anti-corrosion process parameters, environmental data, and material performance data as inputs and early warning results as outputs.

[0014] Preferably, in step 3, the anti-corrosion process parameters include: shot blasting intensity, spraying pressure, paint flow rate, curing temperature and time; environmental data include: workshop temperature, humidity, and dew point; and material performance data include: paint type, steel pipe material and specifications.

[0015] Preferably, step 4 further includes: if it is predicted that there is a risk of insufficient protection after corrosion prevention, an early warning is immediately triggered, adjustment suggestions are pushed, and the operation of the corrosion prevention equipment is suspended until the parameters are adjusted and production is resumed; if real-time process parameters are detected to exceed the standard, a real-time abnormality warning is triggered, an emergency response plan is pushed, and the warning information is recorded; the warning event, the handling process and the result data are added to the data layer to optimize the flaw detection-corrosion prevention collaborative mapping model and the multi-dimensional quality early warning model.

[0016] This invention also provides an intelligent early warning system for the coordinated management and control of steel pipe flaw detection and corrosion prevention, comprising:

[0017] The data acquisition module is used to collect flaw detection data of steel pipes in real time;

[0018] The anti-corrosion process generation module is used to input the flaw detection defect data of steel pipes into the flaw detection-anti-corrosion collaborative mapping model to generate personalized anti-corrosion process solutions.

[0019] The quality inspection module is used to collect anti-corrosion process parameters and quality inspection data in real time during the implementation of personalized anti-corrosion process solutions, and input them into a multi-dimensional quality early warning model for real-time analysis to determine whether the anti-corrosion steel pipe meets the quality requirements.

[0020] The anti-corrosion process parameter adjustment module is used to readjust the anti-corrosion process parameters when the anti-corrosion steel pipe does not meet the quality requirements.

[0021] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0022] This invention relates to an intelligent early warning method and system for the coordinated management and control of steel pipe flaw detection and corrosion prevention. Compared with the prior art, this invention constructs the correlation between defect data and corrosion prevention process through a flaw detection-corrosion prevention coordinated mapping model, realizes personalized corrosion prevention process planning, solves the problem of insufficient protection or excessive corrosion prevention caused by traditional uniform process, and significantly improves the corrosion resistance and service life of steel pipes.

[0023] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 The flowchart of the intelligent early warning method for the coordinated management and control of steel pipe flaw detection and corrosion prevention provided by the present invention is shown. Detailed Implementation

[0026] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0027] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0029] Please see Figure 1 Intelligent early warning methods for the coordinated management and control of steel pipe flaw detection and corrosion prevention include:

[0030] Step 1: Collect flaw detection data of steel pipe in real time; flaw detection data includes: defect type, defect location, size, and defect detection time.

[0031] Step 2: Input the flaw detection defect data of the steel pipe into the flaw detection-corrosion prevention collaborative mapping model to generate a personalized anti-corrosion process plan;

[0032] In step 2, a flaw detection-corrosion prevention collaborative mapping model is constructed based on a knowledge graph library and machine learning algorithms. The flaw detection-corrosion prevention collaborative mapping model is trained with steel pipe specifications, defect types, defect sizes and defect locations as inputs and appropriate corrosion prevention process parameters as outputs.

[0033] Step 3: During the implementation of the personalized anti-corrosion process plan, anti-corrosion process parameters and quality inspection data are collected in real time and input into a multi-dimensional quality early warning model for real-time analysis to determine whether the anti-corrosion steel pipe meets the quality requirements.

[0034] In step 3, a multi-dimensional quality early warning model is constructed based on the LSTM time series prediction algorithm and the random forest classification algorithm. The multi-dimensional quality early warning model is trained by taking flaw detection defect data, anti-corrosion process parameters, environmental data, and material performance data as inputs and taking the early warning results as outputs.

[0035] Step 4: If the anti-corrosion steel pipe does not meet the quality requirements, the anti-corrosion process parameters should be readjusted.

[0036] Step 4 also includes: if it is predicted that there is a risk of insufficient protection after corrosion prevention, an early warning will be triggered immediately, adjustment suggestions will be pushed, and the operation of the corrosion prevention equipment will be suspended until the parameters are adjusted and production is resumed; if real-time process parameters are detected to exceed the standard, a real-time abnormality warning will be triggered, an emergency response plan will be pushed, and the warning information will be recorded; the warning event, the handling process and the result data will be added to the data layer to optimize the flaw detection-corrosion prevention collaborative mapping model and the multi-dimensional quality early warning model.

[0037] It should be noted that this invention adopts a "layered architecture + collaborative model" design concept, which includes, from top to bottom, an interaction layer, an application layer, a model layer, a data layer, a connection layer, and a physical layer. The collaboration of each layer enables full-process collaborative control and intelligent early warning of flaw detection and corrosion prevention procedures. The specific structure is as follows:

[0038] 1. Physical Layer: This layer serves as the physical execution carrier of the system, including flaw detection units, corrosion protection units, and supporting testing instruments. The flaw detection units encompass various flaw detection equipment such as ultrasonic flaw detectors, eddy current flaw detectors, magnetic particle flaw detectors, and fluorescent flaw detectors, used to detect surface and internal defects in the steel pipes. The corrosion protection units include shot blasting pretreatment equipment, spraying equipment (electrostatic spraying, airless spraying), curing ovens, and cooling equipment, used to complete the corrosion protection treatment of the steel pipes. Supporting testing instruments include defect size measuring instruments, coating thickness gauges, coating adhesion testers, dew point meters, and temperature sensors, used to collect defect data during the flaw detection process and process parameters and quality data during the corrosion protection process.

[0039] 2. Connection Layer: This layer enables data transmission and command issuance between the physical and data layers. Its core components include a multi-protocol adapter gateway, edge computing nodes, and a data encryption module. A "general protocol + customized adaptation" strategy is adopted to address protocol incompatibility issues across multiple devices: for mainstream flaw detection and corrosion prevention equipment, data standardization is achieved through the OPC UA protocol; for older equipment, adaptation is achieved through a customized RS485 / Profibus to OPC UA module; and for instrument data, TCP / IP protocol is used for transmission. Edge computing nodes perform real-time preprocessing (cleaning, noise reduction, and format conversion) on the collected data to reduce data transmission latency; the data encryption module uses the AES encryption algorithm to encrypt transmitted data, ensuring data security.

[0040] 3. Data Layer: This layer stores and manages multi-source data across the entire process, employing a "hybrid database + knowledge graph" architecture. It includes a real-time database, a time-series database, a relational database, and a flaw detection-corrosion prevention knowledge graph library. The real-time database stores real-time data on flaw detection defects (defect type, location, size) and real-time parameters of the corrosion prevention process (spraying pressure, coating temperature, curing temperature), etc. The time-series database stores historical production data for model training and trend analysis. The relational database stores structured data such as production plans, order information, material information (coating type, steel pipe specifications), and quality standards. The flaw detection-corrosion prevention knowledge graph library constructs knowledge such as the mapping relationship between defect types and corrosion prevention process parameters, and the correlation between corrosion quality problems and flaw detection defects, providing knowledge support for collaborative management and early warning.

[0041] 4. Model Layer: This is the core collaborative and intelligent decision-making module of the system, comprising three core models:

[0042] Flaw Detection-Corrosion Prevention Collaborative Mapping Model: Based on a knowledge graph database and machine learning algorithms, this model constructs a mapping relationship between flaw detection defect data and corrosion prevention process parameters. Inputting data such as steel pipe specifications, defect types (e.g., cracks, slag inclusions), defect sizes, and defect locations, it outputs suitable corrosion prevention process parameters (e.g., differentiated spraying thickness, coating type, and curing time) to achieve "defect-oriented" personalized corrosion prevention process planning.

[0043] Multi-dimensional quality early warning model: This model integrates LSTM time-series prediction algorithm and random forest classification algorithm to construct a multi-input, multi-output early warning model. Input data includes flaw detection defect data, anti-corrosion process parameters, environmental data (workshop humidity, temperature), and material performance data. Outputs two types of early warning results: first, anti-corrosion effect prediction early warning (predicting whether there is insufficient protection risk after anti-corrosion based on flaw detection defects); second, real-time quality anomaly early warning (such as coating thickness exceeding the standard, or defects not being effectively covered).

[0044] Collaborative scheduling optimization model: Based on a genetic algorithm, this model aims to achieve optimal production efficiency and minimize resource waste. It dynamically adjusts the production plan for the anti-corrosion process by combining flaw detection results with the operating status of the anti-corrosion equipment. For example, when a batch of defective steel pipes is detected during flaw detection, they are prioritized for scheduling to differentiated anti-corrosion stations; when the anti-corrosion equipment malfunctions, feedback is given to the flaw detection process to adjust its production rhythm.

[0045] 5. Application Layer: This layer comprises the core functional modules of the system, focusing on the collaborative management of flaw detection and corrosion prevention, and includes five major functional modules:

[0046] Collaborative Data Management Module: Enables real-time fusion, querying, and display of flaw detection and corrosion prevention data, supports tracing the entire process data by the unique identifier of the steel pipe (such as QR code, RFID), and generates flaw detection-corrosion prevention collaborative data reports.

[0047] Personalized anti-corrosion process planning module: Based on the collaborative mapping model, it automatically generates personalized anti-corrosion process solutions according to flaw detection defect data, supports manual fine-tuning and solution approval, and automatically sends the solutions to the anti-corrosion equipment after approval.

[0048] Intelligent early warning and response module: The quality early warning model runs in real time. When an early warning is generated, it notifies relevant personnel through audible and visual alarms, system pop-ups, mobile push notifications, etc., and automatically pushes response suggestions (such as adjusting spraying parameters and re-inspection). It supports closed-loop tracking of the early warning and response process.

[0049] Collaborative production scheduling module: Based on the collaborative scheduling optimization model, it dynamically generates production plans for the anti-corrosion process to achieve capacity matching between flaw detection and anti-corrosion processes; it monitors the equipment operating status in real time and automatically adjusts the production scheduling plan when equipment malfunctions to reduce work-in-process inventory.

[0050] Quality Traceability and Analysis Module: Based on the end-to-end data chain, it enables reverse traceability from finished steel pipes to flaw detection and corrosion protection processes; through big data analysis, it uncovers the correlation between flaw detection defects and corrosion protection quality issues, providing data support for process optimization.

[0051] 6. Interaction Layer: Provides multi-terminal human-machine interaction interfaces, including a web-based management platform, a mobile app, and on-site operation terminals. The web platform supports functions such as production plan issuance, data statistical analysis, and report generation; the mobile app is used to receive real-time warning information, view production progress, and approve process plans; the on-site operation terminals are deployed at the flaw detection and corrosion prevention workstations, allowing operators to view process parameters and enter operation information in real time.

[0052] Based on the aforementioned intelligent MES system, this method achieves collaborative control and intelligent early warning for the entire process of flaw detection and corrosion prevention. The specific steps are as follows:

[0053] Full-process data acquisition and preprocessing: Through the multi-protocol adapter gateway and sensors in the connection layer, defect data (defect type, location, size, defect detection time) of the flaw detection process, process parameters (shot blasting intensity, spraying pressure, paint flow rate, curing temperature and time) of the anti-corrosion process, environmental data (workshop temperature, humidity, dew point) and material data (paint type, steel pipe material and specifications) are collected in real time; the collected data is cleaned (abnormal sensor data is removed), denoised (using the moving average method), and normalized through edge computing nodes to generate a standardized data stream, which is then transmitted to the data layer for storage.

[0054] Flaw detection and corrosion prevention data association and collaborative modeling: The data layer associates and binds the flaw detection data and corrosion prevention data of the same steel pipe through the unique identifier of the steel pipe (such as RFID tag) to build a full-process data chain for a single steel pipe; The model layer calls the basic data of the flaw detection and corrosion prevention knowledge graph library, and combines historical production data to train and optimize the collaborative mapping model and quality early warning model to generate model parameters adapted to the current production scenario.

[0055] Personalized anti-corrosion process planning: After the steel pipe completes flaw detection, the collaborative data management module pushes its defect data to the personalized anti-corrosion process planning module; this module calls the collaborative mapping model, inputs information such as steel pipe specifications and defect data, and generates a personalized anti-corrosion process plan (such as increasing the spraying thickness of crack defect areas by 20% compared to normal areas, and selecting a more corrosion-resistant coating); after the process plan is manually approved, it is sent to the control system of the anti-corrosion equipment through the connecting layer to guide the execution of the anti-corrosion process.

[0056] Collaborative control and real-time early warning: During the anti-corrosion process, the system collects process parameters and quality inspection data in real time and inputs them into a multi-dimensional quality early warning model; the model also combines related flaw detection defect data to perform real-time analysis and early warning judgment.

[0057] If it is anticipated that there is a risk of insufficient protection after anti-corrosion (such as the coating thickness in the defective area not meeting the standard), an early warning will be triggered immediately, adjustment suggestions will be pushed (such as increasing the spraying pressure in the corresponding area and extending the spraying time), and the operation of the anti-corrosion equipment will be suspended until the parameters are adjusted and production is resumed.

[0058] If real-time process parameters are detected to be out of control (such as excessively high curing temperature), a real-time anomaly warning is triggered, an emergency response plan is pushed (such as reducing heating power or adjusting conveyor belt speed), and the warning information is recorded to the data layer.

[0059] Early Warning Response and Closed-Loop Optimization: After receiving the early warning information, relevant personnel execute corresponding actions based on the suggested actions and enter the results into the system. The system verifies the effectiveness of the actions (e.g., re-inspecting the coating thickness). If the quality requirements are met after the actions, the closed loop is complete; otherwise, the process parameters are readjusted and verification is performed again. Simultaneously, the data on the early warning event, the response process, and the results are added to the data layer to optimize the parameters of the collaborative mapping model and the quality early warning model.

[0060] Full-process quality traceability and analysis: After production is completed, the quality traceability and analysis module generates a collaborative quality report on flaw detection and corrosion prevention based on the data link of a single steel pipe; through big data analysis, it explores the impact of different defect types on corrosion prevention effect, the optimization space of process parameters, etc., and provides decision support for subsequent production process improvement.

[0061] The present invention will be further described in detail below using a production scenario of a Φ219mm×10mm seamless steel pipe.

[0062] This embodiment focuses on the production of Φ219mm×10mm seamless carbon steel pipes. These pipes are used in oil and gas pipelines and have high requirements for corrosion resistance (coating thickness ≥300μm, adhesion ≥5MPa). In the production process, the flaw detection process uses a combination of ultrasonic and magnetic particle testing, while the corrosion protection process employs shot blasting pretreatment + electrostatic spraying + hot air curing. The challenge lies in addressing the issues of traditional production methods where flaw detection data cannot guide the corrosion protection process and where there is a high risk of localized corrosion after corrosion protection.

[0063] 1. System Deployment and Data Acquisition

[0064] Three multi-protocol adapter gateways are deployed in the connection layer to connect the ultrasonic flaw detector, magnetic particle flaw detector, and anti-corrosion equipment cluster, respectively. The ultrasonic flaw detector and magnetic particle flaw detector interact with each other via the OPC UA protocol to collect data such as defect type (crack, inclusion), defect location (distance from pipe end, circumferential angle), and defect size (crack length, inclusion area), with a collection frequency of 10Hz. The anti-corrosion equipment (shot blasting machine, electrostatic spraying equipment, curing oven) is adapted via Profinet to OPC UA to collect parameters such as shot blasting intensity (0.3-0.5MPa), spraying pressure (0.6-0.8MPa), coating temperature (25-30℃), and curing temperature (180-200℃), with a collection frequency of 5Hz. The supporting testing instruments collect data such as coating thickness (collection frequency 2Hz), adhesion (3 points are tested on each steel pipe), workshop temperature (20-30℃), and humidity (40%-60%). Edge computing nodes use the moving average method to denoise defect size data and the threshold method to remove abnormal coating thickness data. The processed data is then transmitted to the data layer for storage.

[0065] 2. Collaborative Modeling and Process Planning

[0066] The model layer calls upon the "Defects in Oil and Gas Pipelines - Corrosion Prevention Processes" related data from the flaw detection-corrosion prevention knowledge graph library, and combines it with 10,000 sets of historical production data to train a collaborative mapping model and a quality early warning model. The collaborative mapping model adopts the BP neural network algorithm, and the input parameters include the steel pipe specifications (Φ219mm×10mm), defect type (crack), crack length (5mm), and crack location (500mm from the pipe end). The output is a personalized anti-corrosion process plan: spray thickness 350μm (300μm in normal areas), use of epoxy coal tar coating, and extension of curing time by 10min. The quality early warning model integrates LSTM and random forest algorithms, and the early warning accuracy reaches 96.2% after training.

[0067] 3. Collaborative Management and Early Warning Execution

[0068] A steel pipe was found to have a 5mm axial crack 500mm from the pipe end during flaw detection. The collaborative data management module pushed this data to the personalized anti-corrosion process planning module, generating the aforementioned personalized process plan. After approval by the process engineer, it was issued to the electrostatic spraying equipment and curing oven. During the anti-corrosion process, the system collected real-time data on the spraying pressure (0.65MPa) and coating thickness (320μm in the crack area). After analysis by the quality early warning model, it predicted that "the coating thickness in the crack area is not up to standard, posing a risk of insufficient protection," immediately triggering an audible and visual warning and pushing an adjustment suggestion to "increase the spraying pressure in the crack area to 0.75MPa." After the operator adjusted the parameters, the coating was re-sprayed and inspected, and the coating thickness reached 352μm, meeting the requirements, completing the closed-loop handling of the early warning.

[0069] Compared with the prior art, the present invention has the following significant advantages:

[0070] 1. Achieve collaborative management of flaw detection and corrosion prevention, enhancing the targeted nature of corrosion prevention: By constructing a correlation between defect data and corrosion prevention processes through a collaborative mapping model, personalized corrosion prevention process planning is achieved. This solves the problems of insufficient or excessive corrosion prevention caused by traditional uniform processes, significantly improving the corrosion resistance and service life of steel pipes. Experimental verification shows that the risk of steel pipe corrosion failure is reduced by more than 30% after adopting this invention.

[0071] 2. Break down data silos and build a complete quality traceability chain: Through multi-protocol adaptation and data association technology, the comprehensive integration and binding of flaw detection and corrosion prevention data are realized, forming a full-process data traceability chain from defect detection to corrosion prevention treatment. When quality problems occur, the root cause can be located within 5 minutes, greatly improving the efficiency of quality problem handling.

[0072] 3. Improve the accuracy and foresight of early warning: Adopt a multi-algorithm fusion early warning model to achieve dual protection of "predictive early warning + real-time early warning", improve the early warning accuracy rate to over 95%, effectively reduce false and missed early warnings; it can predict the risk of corrosion prevention effect in advance and achieve proactive prevention and control of quality problems.

[0073] 4. Optimize production scheduling and reduce resource waste: A collaborative scheduling optimization model is used to match the capacity of the two processes and reduce the backlog of work-in-process.

[0074] This invention also provides an intelligent early warning system for the coordinated management and control of steel pipe flaw detection and corrosion prevention, comprising:

[0075] The data acquisition module is used to collect flaw detection data of steel pipes in real time;

[0076] The anti-corrosion process generation module is used to input the flaw detection defect data of steel pipes into the flaw detection-anti-corrosion collaborative mapping model to generate personalized anti-corrosion process solutions.

[0077] The quality inspection module is used to collect anti-corrosion process parameters and quality inspection data in real time during the implementation of personalized anti-corrosion process solutions, and input them into a multi-dimensional quality early warning model for real-time analysis to determine whether the anti-corrosion steel pipe meets the quality requirements.

[0078] The anti-corrosion process parameter adjustment module is used to readjust the anti-corrosion process parameters when the anti-corrosion steel pipe does not meet the quality requirements.

[0079] Compared with the prior art, the beneficial effects of the intelligent early warning system for the coordinated management and control of steel pipe flaw detection and corrosion prevention provided by the present invention are the same as those of the intelligent early warning method for the coordinated management and control of steel pipe flaw detection and corrosion prevention described in the above technical solution, and will not be repeated here.

[0080] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent early warning method for the coordinated management and control of steel pipe flaw detection and corrosion prevention, characterized in that, include: Step 1: Collect flaw detection data of steel pipes in real time; Step 2: Input the flaw detection defect data of the steel pipe into the flaw detection-corrosion prevention collaborative mapping model to generate a personalized anti-corrosion process plan; Step 3: During the implementation of the personalized anti-corrosion process plan, anti-corrosion process parameters and quality inspection data are collected in real time and input into a multi-dimensional quality early warning model for real-time analysis to determine whether the anti-corrosion steel pipe meets the quality requirements. Step 4: If the anti-corrosion steel pipe does not meet the quality requirements, the anti-corrosion process parameters should be readjusted.

2. The intelligent early warning method for coordinated control of steel pipe flaw detection and corrosion prevention according to claim 1, characterized in that, In step 1, the flaw detection data includes: defect type, defect location, size, and defect detection time.

3. The intelligent early warning method for coordinated control of steel pipe flaw detection and corrosion prevention according to claim 2, characterized in that, In step 2, a flaw detection-corrosion prevention collaborative mapping model is constructed based on a knowledge graph library and machine learning algorithms. The flaw detection-corrosion prevention collaborative mapping model is trained with steel pipe specifications, defect types, defect sizes and defect locations as inputs and appropriate corrosion prevention process parameters as outputs.

4. The intelligent early warning method for coordinated control of steel pipe flaw detection and corrosion prevention according to claim 3, characterized in that, In step 3, a multi-dimensional quality early warning model is constructed based on the LSTM time series prediction algorithm and the random forest classification algorithm. The multi-dimensional quality early warning model is trained by taking flaw detection defect data, anti-corrosion process parameters, environmental data, and material performance data as inputs and taking the early warning results as outputs.

5. The intelligent early warning method for coordinated control of steel pipe flaw detection and corrosion prevention according to claim 4, characterized in that, In step 3, the anti-corrosion process parameters include: shot blasting intensity, spraying pressure, paint flow rate, curing temperature and time; environmental data include: workshop temperature, humidity, and dew point; and material performance data include: paint type, steel pipe material and specifications.

6. The intelligent early warning method for coordinated control of steel pipe flaw detection and corrosion prevention according to claim 5, characterized in that, Step 4 also includes: if it is predicted that there is a risk of insufficient protection after corrosion prevention, an early warning will be triggered immediately, adjustment suggestions will be pushed, and the operation of the corrosion prevention equipment will be suspended until the parameters are adjusted and production is resumed; if real-time process parameters are detected to exceed the standard, a real-time abnormality warning will be triggered, an emergency response plan will be pushed, and the warning information will be recorded; the warning event, the handling process and the result data will be added to the data layer to optimize the flaw detection-corrosion prevention collaborative mapping model and the multi-dimensional quality early warning model.

7. An intelligent early warning system for the coordinated management and control of steel pipe flaw detection and corrosion prevention, characterized in that, include: The data acquisition module is used to collect flaw detection data of steel pipes in real time; The anti-corrosion process generation module is used to input the flaw detection defect data of steel pipes into the flaw detection-anti-corrosion collaborative mapping model to generate personalized anti-corrosion process solutions. The quality inspection module is used to collect anti-corrosion process parameters and quality inspection data in real time during the implementation of personalized anti-corrosion process solutions, and input them into a multi-dimensional quality early warning model for real-time analysis to determine whether the anti-corrosion steel pipe meets the quality requirements. The anti-corrosion process parameter adjustment module is used to readjust the anti-corrosion process parameters when the anti-corrosion steel pipe does not meet the quality requirements.

Images