A method for predicting and controlling strip breakage suitable for eighteen-roller mill control

Abstract

The present application relates to the technical field of data management, and more particularly to a strip break prediction and control method suitable for eighteen-roller mill control. The method comprises the following steps: performing equipment state detection and repair optimization processing on the eighteen-roller mill equipment to obtain the optimized eighteen-roller mill equipment; performing strip production operation based on the optimized eighteen-roller mill equipment; performing identification strip break data analysis according to the strip production operation to generate identification strip break data; performing strip break control critical parameter analysis based on the identification strip break data to generate strip break control critical parameters; performing real-time strip production operation based on the optimized eighteen-roller mill equipment; performing abnormal fluctuation control processing on the real-time strip production operation based on the strip break control critical parameters to obtain real-time strip production data; and performing strip break control critical parameter iterative updating operation according to the real-time strip production data. The present application realizes more accurate strip break control of the eighteen-roller mill.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data management, and in particular to a strip break prediction and control method suitable for eighteen-roller rolling mill control. BACKGROUND

[0002] As a transition model between the four-six roller conventional model and the twenty-roller multi-roller model, the eighteen-roller rolling mill has the easy roller replacement, easy maintenance and inspection characteristics of the former and the small roller diameter and strong rolling thin capability of the latter, which is beneficial to the calendering of stainless steel, electrical steel, high-strength steel and other strip products, and has become the main model for stable production of the above steel. Although the above technical advantages reduce the production cost of this model and improve the production quality of the corresponding products, it is still difficult to deal with the strip break problem under high-speed production, that is, the related technical means cannot provide a solution from the perspective of strip break risk prevention. The strip break diagnosis and analysis during the production process of the eighteen-roller rolling mill still needs to follow the conventional strip break investigation method and treatment scheme, and a specific strip break treatment method suitable for the eighteen-roller rolling mill has not yet been formed. However, the strip break prediction and control method of the traditional roller rolling mill control has the following problems: the detection variables are single, which is difficult to cover all products during the production of this type of model; the detection variables are difficult to cover the control characteristics of the equipment, resulting in low detection accuracy of the strip break detection; and the detection logic only targets real-time monitoring data, ignores the influence law of historical data, and does not consider the periodic changes of the equipment, resulting in poor strip break detection results. SUMMARY

[0003] Therefore, the present application provides a strip break prediction and control method suitable for eighteen-roller rolling mill control to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a strip break prediction and control method suitable for eighteen-roller rolling mill control includes the following steps:

[0005] Step S1: performing equipment state detection and repair optimization processing on the eighteen-roller rolling mill equipment to obtain the optimized eighteen-roller rolling mill equipment;

[0006] Step S2: performing strip steel production operation based on the optimized eighteen-roller rolling mill equipment; performing identification strip break data analysis according to the strip steel production operation to generate identification strip break data;

[0007] Step S3: performing strip break control critical parameter analysis based on the identification strip break data to generate strip break control critical parameters; performing real-time strip steel production operation based on the optimized eighteen-roller rolling mill equipment; performing abnormal fluctuation control processing on the real-time strip steel production operation based on the strip break control critical parameters to obtain real-time strip steel production data;

[0008] Step S4: performing strip break control critical parameter iterative updating operation according to the real-time strip steel production data.

[0009] The application detects and repairs the eighteen-roller rolling mill equipment to ensure that each component of the rolling mill is in the best working condition, improve the overall performance of the equipment, including the centering accuracy of the roller shaft, the flatness and smoothness of the roller surface, and the response speed of the key performance indicators. The optimized equipment is more reliable, the production interruption caused by equipment failure is reduced, the stable operation of the production line is ensured, and the production efficiency is improved. The use of the optimized eighteen-roller rolling mill equipment for strip steel production can greatly improve the production efficiency and the quality of the strip steel product. Since the state of the rolling mill equipment has been optimized, the thickness and flatness of the strip steel during production are more accurately controlled, which directly affects the quality of the final product. In addition, by analyzing the identification of the strip steel production operation and generating identification of the strip steel data, the risk factors that cause the strip to break during production can be effectively identified, providing data support for subsequent strip breakage prevention and control. Not only does it reduce the risk of production interruption, but it also reduces maintenance costs and improves the overall efficiency of the production line. Based on the identification of the strip breakage data, the critical parameters for strip breakage control are analyzed in depth and the corresponding parameters are generated to support real-time monitoring and control of abnormal fluctuation data in the production process. It can accurately identify the conditions that may cause the strip to break during production, and then prevent the occurrence of strip breakage events by adjusting the production parameters in real time. In addition, the optimized eighteen-roller rolling mill equipment is used to perform strip steel production in real time, and based on the strip breakage control critical parameters, abnormal fluctuation control processing is performed to significantly improve the stability of the production process and ensure the consistency of product quality. Through iterative updating of the strip breakage control critical parameters based on real-time data of strip steel production, the dynamic adaptability of the eighteen-roller rolling mill equipment for producing strip steel is enhanced, enabling the production control system to more flexibly adapt to changes in the production process. This iterative updating mechanism ensures that production parameters are always optimized based on the latest data, thereby continuously improving production efficiency and product quality.

[0010] Preferably, the equipment state detection and repair optimization process includes spatial accuracy detection and repair processing, actuator detection and repair processing, and sensor detection optimization processing at each level, and step S1 includes the following steps:

[0011] Step S11: Perform spatial accuracy detection and repair processing on the eighteen-roller rolling mill equipment to obtain spatial accuracy repaired eighteen-roller rolling mill equipment;

[0012] Step S12: Perform actuator detection and repair processing on the spatial accuracy repaired eighteen-roller rolling mill equipment to obtain effective actuator eighteen-roller rolling mill equipment;

[0013] Step S13: Perform sensor detection optimization processing at each level on the effective actuator eighteen-roller rolling mill equipment to obtain the optimized eighteen-roller rolling mill equipment.

[0014] The application ensures the correct alignment and cooperative work of each component of the equipment by accurately detecting and necessary repairing the spatial precision of the eighteen-roller rolling mill equipment, thereby significantly improving the machining precision of the rolling mill and the quality of finished products. The improvement of spatial precision is particularly crucial for high-precision strip steel production, which can ensure the dimensional stability and surface flatness of the products and reduce material waste during production. After repairing the spatial precision, detecting and repairing the actuator of the eighteen-roller rolling mill equipment further ensures the operation efficiency and reliability of the rolling mill. The good state of the actuator is the key to ensure continuous production and reduce downtime maintenance time. By ensuring the effectiveness of the actuator, the stability and response speed of the production line are improved, which has a direct impact on improving production efficiency and reducing operating costs. Sensors are an indispensable part of modern rolling mill equipment, which are responsible for real-time monitoring of equipment status and key parameters in the production process. By detecting and optimizing these sensors, the accuracy and reliability of data acquisition are greatly improved, and the optimized sensor system ensures fine control of the production process, which is crucial for improving product quality, reducing production abnormalities, and improving automation level.

[0015] Preferably, step S11 comprises the following steps:

[0016] Based on the preset wear state detection sequence data, the equipment wear state data of the eighteen-roller rolling mill equipment is collected to generate equipment wear state data;

[0017] The gyroscopic equipment is used to detect the roll system axis rotation angle offset state of the eighteen-roller rolling mill equipment to generate roll system axis state data;

[0018] The laser tracker is used to detect the transmission roll axis position offset state of the eighteen-roller rolling mill equipment to generate transmission roll axis position offset data;

[0019] Based on the equipment wear state data, roll system axis state data and transmission roll axis position offset data, the equipment spatial precision repair analysis processing is performed to generate equipment spatial precision repair data;

[0020] Based on the equipment spatial precision repair data, the spatial precision repair processing of the eighteen-roller rolling mill equipment is performed to obtain the spatial precision repaired eighteen-roller rolling mill equipment.

[0021] The application collects wear state data of the equipment based on preset wear state detection sequence data, accurately identifies the wear degree and wear position of the equipment, helps to find and repair wear problems in time, and thus improves the overall precision of the equipment and prolongs the service life. The rotation angle offset and position offset state of the key components of the rolling mill, such as the roll axis and the transmission roll axis, are detected by using the gyroscope equipment and the laser tracker, and the accuracy correction of these components is ensured, which directly affects the stability of the rolling process and the quality of the final product, and is crucial for optimizing the operation performance of the equipment. Through the spatial precision repair analysis and processing of the equipment based on various state data, the equipment structure is accurately adjusted and optimized, the optimal position and state of each component in the production process are ensured, the material waste caused by equipment precision problems is reduced, and the operation efficiency of the production line and the product output speed are improved. Through systematic detection and repair of the spatial precision problems of the equipment, the uniform thickness and surface flatness of the material in the production process are ensured, and the high-standard product quality requirements are met.

[0022] Preferably, step S12 comprises the following steps:

[0023] The main roll system driving test data of the spatial precision repaired eighteen-roll mill equipment is obtained by performing main roll system driving test processing on the spatial precision repaired eighteen-roll mill equipment.

[0024] The main roll system driving test data is analyzed by using the preset main roll system driving threshold value, including: when the main roll system driving test data is not less than the main roll system driving threshold value, the spatial precision repaired eighteen-roll mill equipment corresponding to the main roll system driving test data is marked as main roll system effective driving, to obtain the main roll system effective driving eighteen-roll mill equipment; when the main roll system driving test data is less than the main roll system driving threshold value, the spatial precision repaired eighteen-roll mill equipment corresponding to the main roll system driving test data is marked as main roll system invalid driving, to obtain the main roll system invalid driving eighteen-roll mill equipment.

[0025] The main roll system invalid driving eighteen-roll mill equipment is fed back to the terminal to perform the screwdown device model repair work.

[0026] The support roll system driving test data of the main roll system effective driving eighteen-roll mill equipment is obtained by performing support roll system driving test processing on the main roll system effective driving eighteen-roll mill equipment.

[0027] The preset support roller system driving threshold is used to analyze the support roller system driving test data, including: when the support roller system driving test data is not less than the support roller system driving threshold, the main roller system effective driving eighteen-roller mill equipment corresponding to the support roller system driving test data is marked as support roller system effective driving, to obtain the effective eighteen-roller mill equipment; when the support roller system driving test data is less than the support roller system driving threshold, the main roller system effective driving eighteen-roller mill equipment corresponding to the support roller system driving test data is marked as support roller system invalid driving, to obtain the support roller system invalid driving eighteen-roller mill equipment;

[0028] The main roller system invalid driving eighteen-roller mill equipment is fed back to the terminal to perform support roller system maintenance work.

[0029] The present application tests and analyzes the driving ability of the main roller system and the support roller system, ensures that the driving performance of these key components reaches the preset threshold, thereby ensuring the reliability and stability of the rolling mill in the production process, timely discovering potential problems of the driving system, preventing faults in the production process, and reducing unplanned downtime. The main roller system and the support roller system of the rolling mill are the key to ensuring the flatness and thickness accuracy of the strip, ensuring the effective driving of these roller systems can maintain the uniformity and consistency of the material in the production process, directly affecting the quality of the final product. Comparing the driving test data with the preset threshold and marking and feeding back the non-compliant actuators can help quickly and accurately identify the components that need to be repaired or adjusted, guide maintenance personnel to carry out targeted maintenance work, and improve maintenance efficiency and effectiveness. Regular driving tests and timely repairs and maintenance effectively reduce equipment wear and damage, prolong the service life of the rolling mill and related actuators, and such preventive maintenance reduces long-term maintenance costs and improves the overall return on investment of the equipment. The effective eighteen-roller mill equipment ensures the continuity and efficiency of the production process, reduces production interruptions caused by actuator problems, and achieves higher production efficiency and lower operating costs.

[0030] Preferably, step S13 comprises the following steps:

[0031] The effective eighteen-roller mill equipment is subjected to sensor accuracy data collection at each level to generate sensor accuracy data at each level;

[0032] According to the sensor accuracy data at each level, sensor accuracy repair data analysis is performed to generate sensor accuracy repair data at each level;

[0033] According to the sensor accuracy repair data at each level, sensor accuracy repair optimization processing is performed on the effective eighteen-roller mill equipment to obtain the optimized eighteen-roller mill equipment.

[0034] The present application collects and repairs precision data of sensors at all levels, ensures that the measurement data of the sensors are more accurate, improves the reliability of data monitoring, and is crucial for precise control and operation of the rolling mill, because sensor data directly affects the control system of the rolling mill. The sensors after precision repair can provide more accurate real-time data, so that the control system of the rolling mill can operate based on more reliable information, reducing production problems caused by sensor failure or precision decline.

[0035] Preferably, step S2 comprises the following steps:

[0036] Step S21: performing a strip production operation based on the optimized eighteen-roller rolling mill equipment, and collecting strip production data according to the strip production operation to generate strip production data;

[0037] Step S22: extracting and processing strip breakage data according to the strip production data to generate strip breakage data;

[0038] Step S23: monitoring equipment state change parameters according to the strip production operation to generate equipment change parameters;

[0039] Step S24: using the equipment change parameters to identify the change information of the strip breakage data to generate identified strip breakage data.

[0040] The present application collects strip production data during production to ensure the comprehensiveness and accuracy of the data, not only including basic information of strip production, but also covering various indicators that are crucial for quality control, which is the basis for subsequent analysis and optimization. Extracting strip breakage data from production data can accurately identify the causes and patterns of strip breakage, which is crucial for developing corresponding preventive measures. Monitoring equipment state change parameters provides real-time information about the running state of the equipment, which helps to discover potential equipment failure problems in time, optimizes maintenance plans and arranges repair work in advance to effectively avoid production interruption. Combining equipment change parameters with strip breakage data for change information identification further deepens the identification of strip breakage causes, not only helping to identify the correlation between strip breakage and specific equipment state changes, but also promoting the development of targeted improvement measures.

[0041] Preferably, the step S3 of analyzing the strip breakage control critical parameters based on the identified strip breakage data comprises the following steps:

[0042] Step S301: collecting strip breakage index data from the identified strip breakage data according to a preset strip breakage index type to generate strip breakage index data;

[0043] Step S302: performing data normalization processing on the strip breakage index data to generate normalized strip breakage index data;

[0044] Step S303: According to the preset isolated forest algorithm, the normalized strip break index data is processed for strip break event correlation scoring to generate strip break event correlation scoring data;

[0045] Step S304: Based on the strip break event correlation scoring data, the normalized strip break index data is processed for dimension reduction screening to generate screened strip break index data;

[0046] Step S305: According to the screened strip break index data, strip break control critical parameter analysis is performed to generate strip break control critical parameter.

[0047] The present application collects detailed strip break index data from the identified strip break data, accurately identifies various potential factors that cause strip break. Data normalization ensures that data of different sources and different magnitudes are compared and analyzed under the same standard, improving the efficiency and accuracy of data processing. The isolated forest algorithm is applied for strip break event correlation scoring processing, which effectively identifies the data nodes highly related to the strip break event. The application of this machine learning method makes the prediction of strip break risk more accurate and efficient. Through dimension reduction screening, only the index data with high influence is retained, simplifying the monitoring and management of strip break risk, not only improving the processing speed, but also improving the prediction accuracy of strip break risk monitoring and management. In-depth analysis is performed according to the screened strip break index data, and the generated strip break control critical parameter provides accurate basis for real-time monitoring and early warning in the production process. These parameters help production managers to develop more effective preventive measures to reduce the occurrence of strip break events.

[0048] Preferably, step S305 comprises the following steps:

[0049] According to the preset random forest algorithm, the screened strip break index data is processed for index sensitivity evaluation to generate index sensitivity evaluation data;

[0050] According to the index sensitivity evaluation data, the screened strip break index data is processed for hypersensitive index selection to generate hypersensitive strip break index data;

[0051] The hypersensitive strip break index data is subjected to numerical distribution analysis to generate hypersensitive strip break index numerical distribution data;

[0052] Based on the normal distribution algorithm, the hypersensitive strip break index numerical distribution data is subjected to strip break control critical parameter analysis of hypersensitive strip break index to generate strip break control critical parameter.

[0053] The application can more accurately identify which indicators have a significant impact on strip breakage events by evaluating the sensitivity of the screened strip breakage indicators through a random forest algorithm, and focus resources and attention on those strip breakage indicators that are most likely to cause production problems. Selecting oversensitive indicators and performing numerical distribution analysis on them can help understand how the data subsets of oversensitive indicators affect the production process of the strip steel, so as to develop more effective preventive measures and improve the pertinence and efficiency of the measures to prevent strip breakage in the production process of the strip steel. The strip breakage control critical parameter analysis on the numerical distribution of the oversensitive indicators based on the normal distribution algorithm reflects how the operation should be adjusted in the production process to avoid strip breakage, which helps to adjust the production strategy in real time, reduce the risk of production strip breakage, better predict and manage potential risks in the production process, and thus avoid unexpected downtime and production loss.

[0054] Preferably, the abnormal fluctuation control processing of the strip steel production real-time operation based on the strip breakage control critical parameter in step S3 comprises the following steps:

[0055] The abnormal fluctuation control processing of the strip steel production real-time operation according to the strip breakage control critical parameter comprises: when the oversensitive strip breakage indicator data of the strip steel production real-time operation is not within the range of the strip breakage control critical parameter, stopping the execution of the strip steel production real-time operation; when the oversensitive strip breakage indicator data of the strip steel production real-time operation is within the range of the strip breakage control critical parameter, continuing to execute the strip steel production real-time operation to obtain strip steel production real-time data.

[0056] The application can timely identify conditions that may cause production accidents by monitoring the oversensitive strip breakage indicator data in real time and comparing it with the strip breakage control critical parameter, and once it is found that these indicators exceed the safe range, the production operation is immediately stopped, thereby preventing potential production accidents, reducing resource waste, ensuring that the oversensitive strip breakage indicator data is always within the safe range of the strip breakage control critical parameter, and helping to maintain the stability and continuity of the production process. By preventing production interruptions caused by abnormal fluctuations, unnecessary losses caused by downtime repair and scrap production are reduced, material utilization and production efficiency are improved, and production costs are reduced. Continuous monitoring and timely adjustment of the production process ensure that production activities are carried out under optimal conditions, and the strip breakage control critical parameter is continuously optimized based on the iterative update of subsequent steps, forming a positive feedback loop to continuously improve the intelligence and automation level of the production process, and the obtained strip steel production real-time data ensures the consistency and high standards of product quality.

[0057] Preferably, the strip breakage control critical parameter iterative update operation in step S4 comprises the following steps:

[0058] The real-time strip breaking data monitoring and processing of the strip steel production real-time data includes: when the strip steel production real-time data does not monitor the real-time strip breaking data, the strip breaking control critical parameter is fed back to the terminal to execute the strip breaking prediction mechanism establishment operation; when the strip steel production real-time data monitors the real-time strip breaking data, the strip breaking data is iteratively updated by using the real-time strip breaking data, the updated strip breaking data is generated, and the updated strip breaking data is transmitted to step S22 to execute the strip breaking control critical parameter iterative update.

[0059] When the real-time data does not monitor the strip breaking condition, the current strip breaking control critical parameter is maintained to ensure the stability of the production process; when the real-time strip breaking data is monitored, the strip breaking data and the control critical parameter are updated in time, and the adjusted control critical parameter considers the influence law of the historical data, and this dynamic adjustment mechanism enables the strip breaking prediction mechanism to adapt to the changes in the production process. For the long-period production unit, the spatial accuracy, equipment wear state, incoming size and performance and other factors will change periodically with the rolling process, which will also affect the cold rolling strip breaking parameter abnormal fluctuation law in different production periods. Through continuous collection and analysis of real-time data in the production process and continuous iterative update, the deficiencies and potential improvement points in the production process are identified, data support is provided for continuous improvement of the production process, the changes in the production conditions are adapted to, and the high quality and high stability of the production process are ensured.

[0060] The application has the beneficial effects that the actual production data of the cold rolling production line (specifically, an eighteen-roller rolling mill cold rolling production line) is used to strip the historical strip breaking data under different steel types, different size specifications and different rolling conditions from a large amount of data, which is used as a strip breaking sensitive data set; then, the sensitivity relationship between the cold rolling process data and the strip breaking phenomenon under different conditions is analyzed by means of the isolated forest algorithm and the random forest algorithm; then, the changes of the strip breaking sensitive data are observed in different steel types, different size specifications and different rolling conditions; once the sensitivity data abnormal fluctuation in the actual production is found, the main drive motor is mobilized to implement the shutdown operation, thereby avoiding the strip breaking. Through the multi-dimensional detection variable, all products of this type of machine can be covered, and whether each type of product has a strip breaking risk can be accurately judged; and the detection variables of the main roller system and the side support roller system completely cover the control characteristics of the eighteen-roller rolling mill equipment, so that the detection accuracy of the strip breaking detection is higher; and the detection logic not only targets the real-time monitoring data, but also targets the influence law of the historical data, including considering that the spatial accuracy, equipment wear state, incoming size and performance and other factors will change periodically with the rolling process, so that the strip breaking detection result in different production periods is excellent. BRIEF DESCRIPTION OF DRAWINGS

[0061] Figure 1A step flow diagram of the strip break prediction and control method suitable for eighteen-roller mill control of the application is shown in the figure.

[0062] Figure 2 For Figure 1 A detailed implementation step flow diagram of the strip break control critical parameter analysis in step S3 is shown in the figure.

[0063] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0064] The technical method of the application will be described below in detail with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the application.

[0065] In addition, the accompanying drawings are only schematic illustrations of the application, and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some block diagrams shown in the drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0066] It should be understood that although the terms "first", "second" and the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the exemplary embodiments, a first element can be called a second element, and similarly a second element can be called a first element. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0067] To achieve the above-mentioned purpose, please refer to Figures 1 to 2 The application provides a strip break prediction and control method suitable for eighteen-roller mill control, comprising the following steps:

[0068] Step S1: detecting the equipment state of the eighteen-roller mill equipment and performing repair optimization processing, to obtain optimized eighteen-roller mill equipment;

[0069] Step S2: performing strip production work based on the optimized eighteen-roller mill equipment; performing identification strip break data analysis according to the strip production work, to generate identification strip break data;

[0070] Step S3: Based on the identification of the strip break data, the strip break control critical parameter analysis is performed to generate the strip break control critical parameter; based on the optimized eighteen-roller mill equipment, the strip steel production real-time operation is performed; based on the strip break control critical parameter, the abnormal fluctuation control processing is performed on the strip steel production real-time operation to obtain the strip steel production real-time data;

[0071] Step S4: According to the strip steel production real-time data, the strip break control critical parameter iterative updating operation is performed.

[0072] The present application detects and optimizes the state of the eighteen-roller mill equipment, ensures that each component of the mill is in the best working condition through regular state detection and repair, improves the overall performance of the equipment, including the centering accuracy of the roller shaft, the flatness and smoothness of the roller surface, and the response speed and other key performance indicators, and the optimized equipment is more reliable, the production interruption caused by equipment failure is reduced, and the stable operation of the production line is ensured, and the production efficiency is improved. The use of the optimized eighteen-roller mill equipment to perform strip steel production operation can greatly improve the production efficiency and the quality of the strip steel product. Since the state of the mill equipment has been optimized, the thickness and flatness control of the strip steel during production is more accurate, which directly affects the quality of the final product. In addition, by analyzing the identification of the strip break data and generating the identification of the strip break data, the risk factors that cause the strip break during production can be effectively identified, which provides data support for subsequent strip break prevention and control, reduces the risk of production interruption, reduces maintenance cost and improves the overall operation efficiency of the production line. Based on the identification of the strip break data, the strip break control critical parameter is analyzed in depth and the corresponding parameter is generated, which supports real-time monitoring and control of abnormal fluctuation data in the production process, can accurately identify the conditions that may cause the strip break during production, and then prevent the occurrence of strip break events by adjusting the production parameters in real time. In addition, the optimized eighteen-roller mill equipment is used to perform strip steel production real-time operation, and based on the strip break control critical parameter, the abnormal fluctuation control processing is performed, which significantly improves the stability of the production process and ensures the consistency of the product quality. Through the iterative updating operation of the strip break control critical parameter on the strip steel production real-time data, the dynamic adaptability of the eighteen-roller mill equipment for producing strip steel is enhanced, so that the production control system can more flexibly adapt to the changes in the production process. This iterative updating mechanism ensures that the production parameters are always optimized based on the latest data, so as to continuously improve the production efficiency and product quality.

[0073] In the embodiment of the present application, reference Figure 1 The present application is a kind of eighteen-roller mill control strip break prediction and control method, and the step flow chart of the present application is shown in the embodiment, and the strip break prediction and control method suitable for eighteen-roller mill control includes the following steps:

[0074] Step S1: perform equipment state detection and repair optimization processing on the eighteen-roller rolling mill equipment to obtain the optimized eighteen-roller rolling mill equipment;

[0075] In the embodiment of the application, first, spatial precision detection is performed on the eighteen-roller rolling mill equipment, including: using a laser tracker, a total station and other devices to detect the wear state of the assembly position in the eighteen-roller rolling mill rack, and recording the wear amount of each roller bushing on the transmission side and the operation side in order according to the sequence of "upper support roller - upper intermediate roller - lower intermediate roller - lower support roller"; using a gyroscope to detect the state of the roller axis (operation side offset, transmission side offset), including the main roller and the side support roller system; using a laser tracker to detect the axis state (operation side offset, transmission side offset) of each transmission roller of the left and right process platforms to obtain spatial precision monitoring data. According to the spatial precision monitoring data, the eighteen-roller rolling mill equipment with spatial precision detection abnormalities is repaired for spatial precision abnormalities to obtain the eighteen-roller rolling mill equipment after spatial precision repair. After confirming that the eighteen-roller rolling mill equipment spatial precision detection is correct, the main roller system actuator is detected, including checking whether the main roller system is driven from the negative stroke position to the positive stroke position by the driving press-down device, and whether the design capacity of the main roller system of the rolling mill is consistent with the actual measurement. If not, the press-down device is overhauled; the side support roller system is also subjected to similar stroke amount detection to ensure that its stroke amount meets the design standard, and the side support roller system is overhauled if it does not meet the design standard. The precision of each sensor of the rolling mill, including the rolling force sensor, the tension meter of the left and right process platforms, the channels of the shape roller and the thickness gauge, is detected to ensure the precision of the data collected during rolling. If the sensor equipment does not meet the data precision, the sensor is overhauled to maintain the high quality and high stability of the production process, and finally the optimized eighteen-roller rolling mill equipment is obtained.

[0076] Step S2: perform strip production operation based on the optimized eighteen-roller rolling mill equipment; perform identification of strip breakage data analysis based on the strip production operation to generate identification of strip breakage data;

[0077] In the embodiment of the present application, the optimized eighteen-roller rolling mill equipment is used to perform strip steel production operation of 500 coils, including preparing production materials, setting rolling mill parameters and starting production process. In the production operation, relevant production data such as rolling force, tension, rolling speed, temperature and other parameters are collected in real time. The production data of each coil are collected from the performed strip steel production operation, including but not limited to rolling parameters, material properties, production speed and time, etc. According to the collected strip steel production data, the extraction processing of strip breakage data is performed. This process involves analyzing the signs that may imply the risk of strip breakage in the production data, such as abnormal rolling force fluctuation, tension anomaly, etc., identifying and recording any actual strip breakage event occurred in the production process, including the specific time, position, related production parameters and reasons of strip breakage. In the strip steel production process, the change parameters related to the equipment state are continuously monitored, such as the degree of rolling mill wear, the position offset of each roller, etc. The correlation between these equipment state change parameters and strip breakage events is analyzed to identify the equipment factors that may affect the risk of strip breakage. The extracted strip breakage data is further processed by identifying the change information using the monitored equipment change parameters, identifying those strip breakage data closely related to the equipment state change, and generating the identified strip breakage data, which should clearly indicate which production parameter changes have significant correlation with the strip breakage event under the specific equipment state change.

[0078] Step S3: performing strip breakage control critical parameter analysis based on the identified strip breakage data to generate strip breakage control critical parameters; performing real-time strip steel production operation based on the optimized eighteen-roller rolling mill equipment; performing abnormal fluctuation control processing on the real-time strip steel production operation based on the strip breakage control critical parameters to obtain real-time strip steel production data;

[0079] In the embodiments of the present application, according to the preset strip break index type (such as rolling force, tension, abnormal fluctuation of plate shape, etc.), the relevant index data is extracted from the strip break data to establish the strip break index data set. The collected strip break index data is normalized to eliminate the influence of different dimensions and orders of magnitude, and to ensure the accuracy and effectiveness of subsequent analysis. The preset isolation forest algorithm is applied to the normalized strip break index data for correlation scoring to identify and evaluate the correlation strength between each index and the strip break event. Based on the strip break event correlation scoring data, the normalized strip break index data is dimensionally reduced and screened to eliminate weakly correlated indicators and retain the most critical indicators for strip break risk prediction. According to the screened strip break index data, strip break control critical parameter analysis is performed, which involves further statistical analysis of the screened indicators, such as using random forest to further screen sensitive strip break index data, which reflects more relevant device parameter indicators for strip break, and through normal distribution analysis to determine the normal operating range and control critical value of each key indicator. The defined strip break control critical parameters are used to monitor the strip steel production real-time operation performed by the eighteen-roller rolling mill equipment, real-time monitor the sensitive strip break index data, and compare with the preset strip break control critical parameters. When the monitored sensitive strip break index data is not within the safety range of the strip break control critical parameters, the strip steel production real-time operation is immediately stopped to avoid potential strip break risk. When the sensitive strip break index data is within the safety range, the strip steel production real-time operation continues, and production data is collected in real time for continuous monitoring and subsequent data analysis.

[0080] Step S4: Perform strip break control critical parameter iterative update operation according to strip steel production real-time data.

[0081] In the embodiment of the present application, the strip steel production real-time operation is continuously monitored, the strip steel production data is collected and analyzed in real time, and the sensitive strip breaking index data is collected in real time. The sensitive strip breaking index data is compared with the current strip breaking control critical parameter to determine whether there is a strip breaking risk. If no real-time strip breaking data is detected in real-time monitoring, that is, the sensitive strip breaking index data is within the safety range of the strip breaking control critical parameter, it is considered that the current strip breaking prediction mechanism is effective, and the existing strip breaking control critical parameter is maintained. If real-time strip breaking data is monitored, that is, the sensitive strip breaking index data exceeds the range of the control critical parameter, it indicates that the current strip breaking prediction mechanism may need to be adjusted, and the next step is entered. The detected real-time strip breaking data is used to iteratively update the strip breaking data, including analyzing the specific conditions of strip breaking, identifying possible new risk factors, and updating related strip breaking index data. Based on the updated strip breaking data, the strip breaking control critical parameter is reevaluated and set, which involves returning to step S3 to reanalyze and integrate, to ensure that the new critical parameter can more accurately reflect the actual risk in the production process. The updated strip breaking control critical parameter is fed back to the monitoring system of the production line to guide the subsequent abnormal fluctuation control processing of the strip steel production real-time operation, continuously monitors the real-time production data to verify the effectiveness of the new strip breaking control critical parameter, and further iteratively updates as needed.

[0082] Preferably, the device state detection and repair optimization process includes spatial precision detection and repair process, actuator detection and repair process, and sensor detection optimization process at each level, and step S1 includes the following steps:

[0083] Step S11: performing spatial precision detection and repair process on the eighteen-roller mill device to obtain the spatial precision repaired eighteen-roller mill device;

[0084] Step S12: performing actuator detection and repair process on the spatial precision repaired eighteen-roller mill device to obtain the effective actuator eighteen-roller mill device;

[0085] Step S13: performing sensor detection optimization process at each level on the effective actuator eighteen-roller mill device to obtain the optimized eighteen-roller mill device.

[0086] The application ensures the correct alignment and cooperative work of each part of the equipment by accurately detecting and necessary repairing the space precision of the eighteen-roller rolling mill equipment, thereby significantly improving the machining precision of the rolling mill and the quality of finished products. The improvement of space precision is particularly crucial for high-precision strip steel production, which can ensure the dimensional stability and surface flatness of the products and reduce material waste during production. After the space precision is repaired, the actuators of the eighteen-roller rolling mill equipment are detected and repaired to further ensure the operation efficiency and reliability of the rolling mill. The good state of the actuators is the key to ensuring continuous production and reducing downtime maintenance time. By ensuring the effectiveness of the actuators, the stability and response speed of the production line are improved, which has a direct impact on improving production efficiency and reducing operating costs. Sensors are an indispensable part of modern rolling mill equipment, which are responsible for real-time monitoring of equipment status and key parameters in the production process. By detecting and optimizing these sensors, the accuracy and reliability of data acquisition are greatly improved, and the optimized sensor system ensures fine control of the production process, which is crucial for improving product quality, reducing production abnormalities, and improving automation level.

[0087] In the embodiment of the present application, a laser tracker, a total station and other devices are used to detect the wear state of the assembly position in the eighteen-roller rolling mill equipment, and the "upper support roller-upper intermediate roller-lower intermediate roller-lower support roller" sequence is recorded in turn, and the "upper support roller left upper lining wear-upper support roller right upper lining wear-upper intermediate roller left upper lining wear-upper intermediate roller right upper lining wear-lower intermediate roller left lower lining wear-lower intermediate roller right lower lining wear" of the transmission side and the operation side is recorded in turn. A gyroscope is used to detect the axis state of the assembled roller system (operation side offset, transmission side offset), and the rolling mill involves the rollers including the upper support roller, the upper intermediate roller, the lower intermediate roller, the lower support roller, the left upper side support roller system, the right upper side support roller system, the left lower side support roller system, and the right lower side support roller system. A laser tracker is used to detect the axis state of each transmission roller of the left and right process platforms (operation side offset, transmission side offset), and the transmission rollers include the left side winding drum, the left side guide roller, the left side plate-shaped roller, the right side plate-shaped roller, the right side guide roller, the right side winding drum, etc. The spatial precision detection abnormal nodes of the eighteen-roller rolling mill equipment are repaired to obtain the spatial precision repaired eighteen-roller rolling mill equipment. On the basis of the spatial precision repaired eighteen-roller rolling mill equipment, the main roller system is driven from the negative stroke position to the positive stroke position, and whether the design capacity of the main roller system is consistent with the actual measurement is checked. When the negative stroke position of the main roller system is driven to the positive stroke position and does not reach the pre-set 80% stroke distance, the drive screwdown device needs to be repaired; when the negative stroke position of the main roller system is driven to the positive stroke position and reaches the pre-set 80% stroke distance, the drive screwdown device does not need to be repaired. After the stroke amount of the side support roller system is tested, the stroke amounts of the left upper, left lower, right upper and right lower side support roller systems reach 94%, 91%, 90% and 86% of the design stroke respectively, and the side support roller system does not need to be repaired. If the stroke amounts of the side support roller system reach below 80% of the design stroke, the corresponding side support roller system needs to be repaired

[0088] Preferably, step S11 comprises the following steps:

[0089] Based on the preset wear state detection sequence data, the equipment wear state data of the eighteen-roller rolling mill equipment is collected, and the equipment wear state data is generated;

[0090] The roller system axis rotation angle offset state of the eighteen-roller rolling mill equipment is detected by using a gyroscope device, and the roller system axis state data is generated;

[0091] The transmission roller axis position offset state of the eighteen-roller rolling mill equipment is detected by using a laser tracker, and the transmission roller axis position offset data is generated;

[0092] Based on the equipment wear state data, the roller system axis state data and the transmission roller axis position offset data, the equipment spatial precision repair analysis processing is performed, and the equipment spatial precision repair data is generated;

[0093] The device space precision repair data is used to repair the space precision of the eighteen-roller rolling mill device.

[0094] The application accurately identifies the wear degree and wear position of the device by collecting wear state data of the device based on the preset wear state detection sequence data, which helps to discover and repair wear problems in time, thereby improving the overall precision of the device and prolonging the service life. The rotation angle deviation and position deviation of the key components of the rolling mill, such as the roll axis and the transmission roll axis, are detected by using the gyroscope device and the laser tracker, and the accuracy of these components is ensured. These accuracy correction measures directly affect the smoothness of the rolling process and the quality of the final product, and are crucial for optimizing the operating performance of the device. Through the device space precision repair analysis and processing based on various state data, the device structure is accurately adjusted and optimized to ensure the optimal position and state of each component in the production process, reduce material waste caused by device precision problems, and improve the operation efficiency of the production line and the product output speed. By systematically detecting and repairing the space precision problems of the device, the uniform thickness and surface flatness of the material in the production process are ensured, and the high-standard product quality requirements are met.

[0095] In the embodiment of the present application, a laser tracker, a total station and other devices are used to detect the wear state of the assembly position in the eighteen-roller rolling mill equipment, and the pre-designed wear state detection sequence data is in the order of "upper support roller - upper intermediate roller - lower intermediate roller - lower support roller". The transmission side and the operation side are recorded in the order of "upper support roller left upper liner wear amount - upper support roller right upper liner wear amount - upper intermediate roller left upper liner wear amount - upper intermediate roller right upper liner wear amount - lower intermediate roller left lower liner wear amount - lower intermediate roller right lower liner wear amount". Suitable detection tools and equipment (such as micrometer, depth gauge, etc.) are used to measure and record the wear degree, and the wear degree is transmitted to the system. The gyro is used to detect the axis state of the assembled roller system (operation side offset, transmission side offset), which involves rollers including upper support roller, upper intermediate roller, lower intermediate roller, lower support roller, left upper side support roller system, right upper side support roller system, left lower side support roller system, right lower side support roller system. The focus is on detecting the rotation angle and offset state of the roller system axis, analyzing the centering and parallelism of the roller system axis, ensuring that the offset of each axis relative to the ideal position is minimized, and recording the roller system axis rotation angle offset data in the system. The laser tracker is used to detect the axis state of each transmission roller on the left and right process platforms (operation side offset, transmission side offset), which involves transmission rollers including left side winding drum, left side guide roller, left side plate-shaped roller, right side plate-shaped roller, right side guide roller, right side winding drum, etc. The focus is on detecting the horizontal and vertical position offset of the transmission roller, as well as the angle offset relative to the rolling direction, and recording these offset parameters in the system. The collected equipment wear state data, roller system axis state data and transmission roller axis position offset data are comprehensively analyzed to identify the key factors affecting the spatial accuracy of the equipment, and the parameter data of the spatial accuracy of the equipment is repaired through the key factors affecting the spatial accuracy of the equipment. According to the analysis and processing results, the spatial accuracy repair of the eighteen-roller rolling mill equipment is performed. This may include re-adjusting the roller system position, replacing severely worn parts, adjusting the transmission roller position, etc. After completing the spatial accuracy repair, necessary verification and testing work is carried out to confirm that the repair effect meets the expectations, ensuring that the spatial accuracy of the equipment is restored to the optimal state. The verification process can include repeating the detection work of steps S11 to S13, comparing the data differences before and after repair, and ensuring that all key indicators meet or exceed the design standard.

[0096] Preferably, step S12 includes the following steps:

[0097] The main roller system driving test data of the eighteen-roller rolling mill equipment after spatial accuracy repair is obtained.

[0098] The main roller system drive test data is analyzed by using a preset main roller system drive threshold, including: when the main roller system drive test data is not less than the main roller system drive threshold, the main roller system effective drive of the eighteen-roller mill equipment corresponding to the spatial precision repair of the main roller system drive test data is marked, so as to obtain the eighteen-roller mill equipment with main roller system effective drive; when the main roller system drive test data is less than the main roller system drive threshold, the main roller system invalid drive of the eighteen-roller mill equipment corresponding to the spatial precision repair of the main roller system drive test data is marked, so as to obtain the eighteen-roller mill equipment with main roller system invalid drive;

[0099] The eighteen-roller mill equipment with main roller system invalid drive is fed back to the terminal to perform the screwdown device model maintenance work.

[0100] The support roller system drive test data is obtained by performing support roller system drive test processing on the eighteen-roller mill equipment with main roller system effective drive.

[0101] The support roller system drive test data is analyzed by using a preset support roller system drive threshold, including: when the support roller system drive test data is not less than the support roller system drive threshold, the support roller system effective drive of the eighteen-roller mill equipment corresponding to the main roller system effective drive of the support roller system drive test data is marked, so as to obtain the eighteen-roller mill equipment with effective actuator; when the support roller system drive test data is less than the support roller system drive threshold, the support roller system invalid drive of the eighteen-roller mill equipment corresponding to the main roller system effective drive of the support roller system drive test data is marked, so as to obtain the eighteen-roller mill equipment with support roller system invalid drive.

[0102] The eighteen-roller mill equipment with main roller system invalid drive is fed back to the terminal to perform the screwdown device model maintenance work.

[0103] The application ensures that the driving performance of these key components reaches the preset threshold value by testing and analyzing the driving capacity of the main roller system and the supporting roller system, thereby guaranteeing the reliability and stability of the rolling mill in the production process, discovering potential problems of the driving system in time, preventing faults in the production process, and reducing unplanned downtime. The main roller system and the supporting roller system of the rolling mill are the key to ensuring the flatness and thickness accuracy of the strip steel, and ensuring the effective driving of these roller systems can maintain the uniformity and consistency of the material in the production process, directly affecting the quality of the final product. Comparing the driving test data with the preset threshold value and marking and feeding back the actuators that do not meet the standard can help quickly and accurately identify the components that need to be repaired or adjusted, guide maintenance personnel to carry out targeted maintenance work, and improve maintenance efficiency and effect. Regular driving tests and timely repair and maintenance can effectively reduce equipment wear and damage and prolong the service life of the rolling mill and related actuators. This preventive maintenance reduces long-term maintenance costs and improves the overall return on investment of the equipment. The eighteen-roller rolling mill equipment with effective actuators ensures the continuity and efficiency of the production process, reduces production interruptions caused by actuator problems, and achieves higher production efficiency and lower operating costs.

[0104] In the embodiment of the present application, the main roll system of the repaired 18-roller rolling mill equipment is driven for testing to evaluate whether the driving performance meets the design requirements. The testing includes, but is not limited to, measuring the speed, torque and power output of the main roll system to ensure that it meets the production requirements. The main roll system is driven from the negative stroke position to the positive stroke position by the driving screwdown device, and the design capacity of the main roll system is measured to see if it is consistent with the actual measurement. The collected main roll system driving test data is analyzed using a preset main roll system driving threshold (e.g. 80% of the pre-designed main roll system driving target stroke). If the test data is not less than the main roll system driving threshold, it is marked as effective driving, and the 18-roller rolling mill equipment with effective main roll system driving is confirmed. If the test data is less than the main roll system driving threshold, it is marked as invalid driving, and the main roll system invalid driving equipment that needs to be repaired is identified. For example, if the actual stroke amount of the screwdown driving device or the main driving component is 83% of the designed stroke amount, no repair work of the screwdown device or the main driving component is needed. All the equipment marked as main roll system invalid driving is fed back to the terminal for performing repair work of the screwdown device or the main driving component. The 18-roller rolling mill equipment with effective main roll system driving is subjected to driving test of the support roll system to ensure that the support roll system can also meet the performance requirements. Similar to the main roll system, the speed, torque and other key driving parameters of the support roll system are tested. The test data is analyzed using a preset support roll system driving threshold (e.g. 80% of the pre-designed support roll system driving target stroke). When the test data is not less than the threshold, it is marked as effective driving of the support roll system. When the test data is less than the threshold, it is marked as invalid driving of the support roll system, and subsequent repair is performed. For example, after testing the stroke amount of the side support roll system, the stroke amounts of the upper left, lower left, upper right and lower right side support roll systems are 94%, 91%, 90% and 86% of the designed stroke amounts, respectively, and no repair of the support roll system is needed. The equipment marked as invalid driving of the support roll system is also fed back to the repair team for targeted repair. The repaired equipment should be subjected to driving test again to verify the repair effect and ensure that all driving components meet or exceed the preset performance standards.

[0105] Preferably, step S13 comprises the following steps:

[0106] The 18-roller rolling mill equipment with effective actuators is subjected to data collection of the accuracy of sensors at all levels to generate accuracy data of sensors at all levels.

[0107] The accuracy repair data of sensors at all levels is analyzed based on the accuracy data of sensors at all levels to generate accuracy repair data of sensors at all levels.

[0108] The 18-roller rolling mill equipment with effective actuators is subjected to accuracy repair optimization processing of sensors at all levels based on the accuracy repair data of sensors at all levels to obtain the optimized 18-roller rolling mill equipment.

[0109] The present application collects and repairs precision data of sensors at all levels, ensures that the measurement data of the sensors is more accurate, improves the reliability of data monitoring, and is crucial for precise control and operation of the rolling mill, because sensor data directly affects the control system of the rolling mill. The sensors after precision repair can provide more accurate real-time data, so that the control system of the rolling mill can operate based on more reliable information, reducing production problems caused by sensor failure or precision decline.

[0110] In the embodiment of the present application, the eighteen-roller rolling mill equipment with confirmed effective actuators is comprehensively detected for sensor precision, including but not limited to rolling force sensors, tension sensors, displacement sensors, speed sensors and temperature sensors, etc. When collecting data, the model, installation position, current reading, theoretical reading (if available) and any known calibration data of each sensor are recorded. The collected sensor precision data are analyzed, the actual reading of the sensor is compared with its theoretical reading or calibration data to determine the degree of deviation and precision state, the sensor whose precision does not meet the preset standard is identified, and the sensor that needs to be calibrated or replaced is determined. For the sensor whose precision does not meet the standard, according to the type and nature of the problem, corresponding repair or optimization processing is performed. Including but not limited to: calibration: recalibration of the sensor to ensure accurate reading; adjustment: fine-tuning of the installation position or angle of the sensor to improve its performance; replacement: for the sensor that cannot restore precision through calibration or adjustment, replacement is performed. After repairing or replacing the sensor, precision test is performed again to verify the effect of the repair measures, to ensure that all sensors meet the required precision standard, and to update the equipment maintenance record including the repair, calibration and replacement information of the sensor for future tracking and management. After the above steps, the optimized eighteen-roller rolling mill equipment is confirmed, the sensor system of which can accurately reflect the equipment running state and production parameters, and comprehensive equipment function test is performed to ensure that the overall performance of the equipment and the sensor system meets the production requirements.

[0111] Preferably, step S2 comprises the following steps:

[0112] Step S21: performing strip production operation based on the optimized eighteen-roller rolling mill equipment, and collecting strip production data according to the strip production operation to generate strip production data;

[0113] Step S22: performing strip breakage data extraction processing according to the strip production data to generate strip breakage data;

[0114] Step S23: performing equipment state change parameter monitoring according to the strip production operation to generate equipment change parameters;

[0115] Step S24: performing change information identification processing on the strip breakage data using the equipment change parameters to generate identified strip breakage data.

[0116] The present application guarantees the comprehensiveness and accuracy of the data by collecting strip production data during the production process, not only including the basic information of strip production, but also covering various indicators that are crucial to quality control, which is the basis for subsequent analysis and optimization. Extracting strip break data from production data can accurately identify the causes and patterns of strip break, which is crucial for developing corresponding preventive measures. The monitoring of equipment state change parameters provides real-time information about the running state of the equipment, which helps to discover potential equipment failure problems in time, optimizes maintenance plans and arranges repair work in advance to avoid production interruption, which is very effective. Combining equipment change parameters with strip break data and performing change information identification processing further deepens the identification of strip break causes, not only helping to identify the correlation between strip break and specific equipment state changes, but also promoting the development of targeted improvement measures.

[0117] In the embodiment of the present application, 500 rolls of strip production data are continuously detected by the optimized eighteen-roller rolling mill equipment from the completion of the eighteen-roller rolling mill equipment state detection; the strip break roll production information in the 500 rolls of strip is extracted, including rolling force, tension, strip break pass, outlet shape value of strip break pass, and front slip value of strip break pass, etc. According to statistics, there are 137 rolls of strip break in the 500 rolls of strip, and the parameters are shown in the strip break roll production information of the 137 rolls of strip in Table 1. Analyze the collected strip production data, extract the key data points and abnormal indicators related to the strip break event, generate specific strip break data for further analysis and preventive measures. In the strip production process, the changes of equipment state are monitored in real time, including equipment wear, sensor deviation, precision change of actuator, etc. Record all monitored equipment state change parameters, especially those key parameter changes that may affect production stability and product quality. Use the equipment state change parameters monitored in step S23 to further analyze the strip break data generated in step S22, identify the correlation and influence between these change parameters and strip break data, mark the strip break data with clear correlation and note the relationship between them and specific equipment state change parameters, so as to develop targeted prevention and adjustment measures.

[0118] Table 1 Strip break roll production information of 137 rolls of strip

[0119]

[0120] Preferably, the step S3 of analyzing the critical parameters for strip break control based on the identified strip break data comprises the following steps:

[0121] Step S301: Collecting strip break index data from the identified strip break data according to the pre-set strip break index type, and generating strip break index data;

[0122] Step S302: Perform data normalization on the band breakage index data to generate normalized band breakage index data;

[0123] Step S303: Perform band breakage event correlation scoring on the normalized band breakage index data according to the preset isolated forest algorithm to generate band breakage event correlation score data;

[0124] Step S304: Perform dimensionality reduction and filtering on the normalized band breakage index data based on the band breakage event correlation score data to generate filtered band breakage index data;

[0125] Step S305: Analyze the critical parameters for belt breakage control based on the screened belt breakage index data, and generate the critical parameters for belt breakage control.

[0126] This invention involves detailed collection of tape breakage index data to accurately identify various potential factors leading to tape breakage. Data normalization ensures that data from different sources and at different scales can be compared and analyzed under the same standard, improving data processing efficiency and analytical accuracy. The application of the isolated forest algorithm for tape breakage event correlation scoring effectively identifies data nodes highly correlated with tape breakage events. This machine learning approach makes tape breakage risk prediction more accurate and efficient. Dimensionality reduction filtering retains only the most influential index data, simplifying tape breakage risk monitoring and management, improving both processing speed and predictive accuracy. In-depth analysis of the selected tape breakage index data generates critical parameters for tape breakage control, providing precise data for real-time monitoring and early warning in the production process. These parameters help production managers develop preventative measures more effectively, reducing the occurrence of tape breakage events.

[0127] As an example of the present invention, reference is made to Figure 2 As shown, Figure 1 A detailed flowchart illustrating the implementation steps of step S3, the critical parameter analysis for interrupt band control, is shown in this example. Step S3 includes:

[0128] Step S301: Collect band breakage index data from the identified band breakage data according to the preset band breakage index type, and generate band breakage index data;

[0129] In this embodiment of the invention, according to the pre-designed strip breakage index type, including rolling force, tension, and forward slip value of the strip breakage pass, strip breakage index data is collected from the identified strip breakage data. The corresponding index data is extracted from the identified strip breakage data. This data will be used for subsequent analysis and modeling to generate strip breakage index data.

[0130] Step S302: Perform data normalization on the band breakage index data to generate normalized band breakage index data;

[0131] In the embodiment of the present application, the collected strip break index data is normalized to eliminate the influence of dimension and unify the scale of data, limit the influence of each index on strip break to the same range, and generate normalized strip break index data.

[0132] Step S303: According to the preset isolated forest algorithm, the normalized strip break index data is processed for strip break event correlation scoring to generate strip break event correlation scoring data.

[0133] In the embodiment of the present application, the key parameters of the isolated forest algorithm are determined, including the number of trees in the forest, the sample size of each tree, and any other parameters specific to the algorithm implementation. The selection of parameters can be based on the size and dimension of the data set, and previous experience. Using the pre-selected algorithm parameters, the isolated forest algorithm is applied to the normalized strip break index data, and the features and feature values are randomly selected to randomly build decision trees. In this process, each data point is isolated on the leaf node of the tree, and the path length to the leaf node can be used as an estimate of the anomaly score. The higher the degree of isolation of the data point (i.e. the shorter the path), the greater the likelihood of being an anomaly point. This feature makes the isolated forest algorithm particularly suitable for identifying abnormal indexes highly related to strip break events. The anomaly score calculated for each data point (i.e. each data instance of the strip break index) is the strip break event correlation score of the data point, and a high score indicates that the data point is highly correlated with the strip break event, and vice versa. The scores of all data points are integrated into a strip break event correlation scoring data set for subsequent analysis and decision-making.

[0134] Step S304: Based on the strip break event correlation scoring data, the normalized strip break index data is processed for dimensionality reduction and screening to generate screened strip break index data.

[0135] In the embodiment of the present application, based on the strip break event correlation scoring, the normalized strip break index data is processed for dimensionality reduction and screening, and only those indexes with high contribution to predicting strip break risk are retained. For example, the isolated forest will gradually isolate the indexes with poor correlation with strip break time in the normalized strip break index data, and then retain the normalized strip break index data with high correlation with strip break events to generate screened strip break index data. For example, the screened strip break index data obtained after dimensionality reduction and screening includes strip break pass rolling force, strip break pass tension, strip break outlet plate shape value (extreme difference), and strip break pass front slip value.

[0136] Step S305: According to the screened strip break index data, strip break control critical parameter analysis is performed to generate strip break control critical parameters.

[0137] In the embodiment of the present application, the evaluation indexes of the screened strip breaking index data are analyzed by using the random forest algorithm to obtain the hypersensitive indexes, and the hypersensitive index values are combined with the normal distribution law to obtain the strip breaking frequent value parameters as the strip breaking control critical parameters of the indexes, and then the construction of the strip breaking prediction system is completed and put into production. Once the detection value of the hypersensitive index exceeds the control critical parameter in the production monitoring, the production line stops, and the corresponding strip breaking control critical parameters of the 1, 2, 3, 4, and 5 gears of the calculated and optimized eighteen-roller rolling mill equipment include: the strip breaking pass rolling force / Ton is 872, 932, 955, 1107, and 1300; the strip breaking pass tension / Ton is 21, 23, 25, 31, and 33; the strip breaking outlet plate shape value (extreme difference) is 54I, 40I, 27I, 19I, and 14I; and the strip breaking pass front slip value is 1.78, 1.65, 1.32, 1.29, and 1.16.

[0138] Preferably, step S305 comprises the following steps:

[0139] According to the preset random forest algorithm, the index sensitivity evaluation processing is performed on the screened strip breaking index data to generate index sensitivity evaluation data;

[0140] According to the index sensitivity evaluation data, the hypersensitive index selection processing is performed on the screened strip breaking index data to generate hypersensitive strip breaking index data;

[0141] The value distribution analysis is performed on the hypersensitive strip breaking index data to generate hypersensitive strip breaking index value distribution data;

[0142] Based on the normal distribution algorithm, the hypersensitive strip breaking index value distribution data is analyzed to generate the strip breaking control critical parameters of the hypersensitive strip breaking index.

[0143] The present application can more accurately identify which indexes have a significant impact on the strip breaking event by using the random forest algorithm to evaluate the screened strip breaking indexes, and focus resources and attention on those strip breaking indexes that are most likely to cause production problems. The hypersensitive indexes are selected and the value distribution analysis is performed on them to deeply understand how the data subsets of the hypersensitive indexes affect the production process of the strip steel, so as to develop more effective preventive measures, improve the pertinence and efficiency of the preventive measures for the strip breaking in the production of the strip steel. Based on the normal distribution algorithm, the value distribution of the hypersensitive indexes is analyzed to generate the strip breaking control critical parameters, which reflects how the operation should be adjusted in the production process to avoid strip breaking, helps to adjust the production strategy in real time, reduces the risk of production strip breaking, better predicts and manages the potential risks in the production process, and thus avoids unexpected shutdown and production loss.

[0144] In the embodiment of the present application, the random forest algorithm is applied to the screened strip breaking index data. The random forest can process high-dimensional data and give the sensitivity score of each index to the strip breaking event, which is suitable for evaluating the sensitivity of the index. The random forest model is initialized by pre-designing the number of trees and other model parameters, such as maximum depth, minimum sample splitting number, etc., to optimize the performance of the model. The normalized strip breaking index data is used to train the random forest model, and the importance score of each index is calculated as a quantitative indicator of its sensitivity. According to the importance score of the index, select the data with higher score in the index as the hypersensitive strip breaking index. These indexes are considered to have high sensitivity and predictive value for predicting strip breaking events. Determine the selection criteria for hypersensitive indexes, for example, select the indexes with importance scores in the top percentage. Perform numerical distribution analysis on the selected hypersensitive strip breaking index data to understand its distribution characteristics. Use descriptive statistical analysis, including calculating mean, standard deviation, skewness, and kurtosis, etc. to analyze whether the distribution of the index data is close to normal distribution, or whether there are other significant distribution characteristics, such as bimodal distribution, long-tailed distribution, etc. Use normal distribution algorithm to analyze the critical threshold of the numerical distribution data of the hypersensitive strip breaking index, and use these critical thresholds as the control critical parameters of the corresponding index in each gear. For example, the calculated and optimized critical parameters for the 1, 2, 3, 4, and 5 gears of the eighteen-roller rolling mill equipment include: strip breaking pass rolling force / Ton: 872, 932, 955, 1107, 1300; strip breaking pass tension / Ton: 21, 23, 25, 31, 33; strip breaking exit plate shape value (extreme difference): 54I, 40I, 27I, 19I, 14I; strip breaking pass front slip value: 1.78, 1.65, 1.32, 1.29, 1.16.

[0145] Preferably, the step S3 of performing abnormal fluctuation control processing on the strip steel production real-time operation based on the strip breaking control critical parameters comprises the following steps:

[0146] According to the strip breaking control critical parameters, the abnormal fluctuation control processing on the strip steel production real-time operation is performed, including: when the hypersensitive strip breaking index data of the strip steel production real-time operation is not within the range of the strip breaking control critical parameters, stop executing the strip steel production real-time operation; when the hypersensitive strip breaking index data of the strip steel production real-time operation is within the range of the strip breaking control critical parameters, continue to execute the strip steel production real-time operation to obtain the strip steel production real-time data.

[0147] The application can identify the conditions that may cause production accidents in time by monitoring the sensitive strip breakage index data in real time and comparing it with the strip breakage control critical parameters, and stop production operation as soon as the indicators are found to be out of the safe range, thereby preventing potential production accidents, reducing resource waste, ensuring that the sensitive strip breakage index data is always within the safe range of the strip breakage control critical parameters, and helping to maintain the stability and continuity of the production process. By preventing production interruption caused by abnormal fluctuations, unnecessary losses caused by downtime repair and waste products are reduced, material utilization and production efficiency are improved, and production costs are reduced. Continuous monitoring and timely adjustment of the production process ensure that production activities are carried out under optimal conditions, and the strip breakage control critical parameters are continuously optimized based on the iterative update of subsequent steps, forming a positive feedback loop to continuously improve the intelligence and automation level of the production process, and the obtained strip steel production real-time data ensures the consistency and high standards of product quality.

[0148] In the embodiment of the application, the strip breakage control critical parameters are used to control and process the abnormal fluctuations of the strip steel production real-time operation by reading the key operation parameters in the strip steel production process in real time, especially those identified as sensitive strip breakage index data. The strip breakage control critical parameters of the strip steel production real-time operation are compared with the sensitive strip breakage index data, and it is judged whether the current value of the sensitive strip breakage index data of the strip steel production real-time operation is within the range of the corresponding critical parameter. If any sensitive strip breakage index data of the strip steel production real-time operation is not within the range of the strip breakage control critical parameter, a signal is immediately sent to the production control system to stop executing the strip steel production real-time operation to prevent potential strip breakage risks. The signal should trigger the safety shutdown program of the production line and notify the maintenance team to check and intervene if necessary. When all sensitive strip breakage index data of the strip steel production real-time operation is within the safe range of the strip breakage control critical parameter, the monitoring system allows the strip steel production real-time operation to continue, ensuring the continuity and efficiency of the production process, and finally the data of the strip steel production record is collected in real time to obtain the strip steel production real-time data.

[0149] Preferably, the strip breakage control critical parameter iterative update operation of step S4 includes the following steps:

[0150] The real-time strip breakage data monitoring process of the strip steel production real-time data includes: when the strip steel production real-time data does not monitor real-time strip breakage data, the strip breakage control critical parameter is fed back to the terminal to perform the strip breakage prediction mechanism establishment operation; when the strip steel production real-time data monitors real-time strip breakage data, the real-time strip breakage data is used to iteratively update the strip breakage data, generate updated strip breakage data, and transmit the updated strip breakage data to step S22 to perform the strip breakage control critical parameter iterative update.

[0151] When the real-time data does not monitor the strip breakage, the current strip breakage control critical parameter is maintained to ensure the stability of the production process; when the real-time strip breakage data is monitored, the strip breakage data and the control critical parameter are updated in time, and the adjusted control critical parameter considers the influence law of historical data. This dynamic adjustment mechanism enables the strip breakage prediction mechanism to adapt to changes in the production process. For a long-period production unit, spatial accuracy, equipment wear state, incoming material size and performance, and other factors will change periodically during the rolling process, which will also affect the abnormal fluctuation of the cold rolling strip breakage parameter in different production periods. Through continuous collection and analysis of real-time data in the production process, and continuous iteration and updating, the deficiencies and potential improvement points in the production process are identified to provide data support for continuous improvement of the production process, to adapt to changes in production conditions, and to ensure high quality and high stability of the production process.

[0152] In the embodiment of the present application, real-time strip production data is continuously collected and analyzed, and real-time monitoring is performed to detect whether real-time strip breakage data occurs, that is, whether there is data indicating a possible strip breakage event in the production process. If no strip breakage event occurs in the monitored real-time data (that is, all monitored sensitive strip breakage index data is within the safe range of the strip breakage control critical parameter), the existing strip breakage control critical parameter is used for monitoring. If the real-time data shows a potential strip breakage event (and the monitored sensitive strip breakage index data does not exceed the range of the strip breakage control critical parameter), the sensitive strip breakage index data needs to be iteratively updated. The existing strip breakage data set is updated using the monitored real-time strip breakage data, including recording new strip breakage events, actual values of related indicators, and specific production conditions when the strip breakage occurs. The updated strip breakage data is fed back to step S22 to update the strip breakage index of step S22, and the sensitive strip breakage index data in the sub-step of step S3 is analyzed according to the updated strip breakage data to obtain the updated sensitive strip breakage index data and the corresponding updated strip breakage control critical parameter. The real-time strip breakage data monitoring process of the real-time strip production data is performed again using the updated sensitive strip breakage index data and the corresponding updated strip breakage control critical parameter, and the iteration is continuously updated until no strip breakage data occurs in the latest strip production operation. Then the iteration is stopped, and a strip breakage prediction mechanism establishment operation is performed. The strip breakage prediction mechanism establishment operation sets the equipment parameters of the eighteen-roller rolling mill equipment according to the latest strip breakage control critical parameter to prevent strip breakage.

[0153] The application has the beneficial effects that the application utilizes the actual production data of a cold rolling production line (specifically, an eighteen-roller rolling mill cold rolling production line), strips the historical broken strip data under different steel grades, different size specifications and different rolling conditions from a large amount of data to serve as a broken strip sensitive data set; then, the isolated forest algorithm and the random forest algorithm are used to analyze the sensitivity relationship between the cold rolling process data and the broken strip phenomenon under different conditions; then, the changes of the broken strip sensitive data are observed in different steel grades, different size specifications and different rolling conditions; once the sensitivity data abnormal fluctuation in actual production is found, the main drive motor is adjusted to implement the shutdown operation, thereby avoiding the broken strip. Through the multi-dimensional detection variable, all products of the machine type can be covered, and it can be judged whether all kinds of products have the broken strip risk; the detection variable of the main roller system and the side support roller system completely covers the control characteristics of the eighteen-roller rolling mill equipment, so that the detection accuracy of the broken strip detection is higher; and the detection logic is not only for the instant monitoring data, but also for the influence law of the historical data, including considering that the spatial accuracy of the equipment, the equipment wear state, the incoming material size and performance and other factors will appear periodic changes with the rolling process, so that the broken strip detection result in different production periods is excellent.

[0154] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, the scope of the application being defined by the attached claims and not by the above description, therefore all variations falling within the meaning and scope of the equivalent elements of the application file are intended to be included in the application.

[0155] The above description is only a specific implementation of the application, enabling those skilled in the art to understand or implement the application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the application. Therefore, the application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting and controlling strip breakage suitable for eighteen-roller mill control, characterized by, The method comprises the following steps: Step S1: performing equipment state detection and repair optimization processing on the eighteen-roller rolling mill equipment to obtain the optimized eighteen-roller rolling mill equipment; Step S2: performing strip steel production operation based on the optimized eighteen-roller rolling mill equipment; According to the strip steel production operation, the identification strip break data analysis is performed to generate identification strip break data; Step S3: performing strip break control critical parameter analysis based on the identification strip break data to generate strip break control critical parameters; Based on the optimized eighteen-roller rolling mill equipment, the strip steel production real-time operation is performed; based on the strip break control critical parameters, the abnormal fluctuation control processing is performed on the strip steel production real-time operation to obtain strip steel production real-time data; Step S4: performing strip break control critical parameter iterative updating operation according to the strip steel production real-time data; Wherein, step S2 comprises the following steps: Step S21: performing strip steel production operation based on the optimized eighteen-roller rolling mill equipment, and performing strip steel production data acquisition according to the strip steel production operation to generate strip steel production data; Step S22: performing strip break data extraction processing according to the strip steel production data to generate strip break data; Step S23: performing equipment state variation parameter monitoring according to the strip steel production operation to generate equipment variation parameters; Step S24: using the equipment variation parameters to perform variation information identification processing on the strip break data to generate identification strip break data; Wherein, the strip break control critical parameter analysis based on the identification strip break data in step S3 comprises the following steps: Step S301: performing strip break index data acquisition on the identification strip break data according to the preset strip break index type to generate strip break index data; Step S302: performing data normalization processing on the strip break index data to generate normalized strip break index data; Step S303: performing strip break event correlation scoring processing on the normalized strip break index data according to the preset isolated forest algorithm to generate strip break event correlation scoring data; Step S304: performing dimensionality reduction screening processing on the normalized strip break index data based on the strip break event correlation scoring data to generate screened strip break index data; Step S305: performing strip break control critical parameter analysis according to the screened strip break index data to generate strip break control critical parameters; Wherein, step S305 comprises the following steps: Performing index sensitivity evaluation processing on the screened strip break index data according to the preset random forest algorithm to generate index sensitivity evaluation data; Performing hypersensitive index selection processing on the screened strip break index data according to the index sensitivity evaluation data to generate hypersensitive strip break index data; Performing numerical distribution analysis on the hypersensitive strip break index data to generate hypersensitive strip break index numerical distribution data; Performing strip break control critical parameter analysis on the hypersensitive strip break index data based on the normal distribution algorithm to generate strip break control critical parameters.

2. The strip break prediction and management method adapted to the control of an eighteen-roller rolling mill according to claim 1, characterized in that, The equipment state detection and repair optimization processing comprises spatial accuracy detection and repair processing, actuator detection and repair processing, and sensor detection and optimization processing, and step S1 comprises the following steps: Step S11: performing spatial accuracy detection and repair processing on the eighteen-roller rolling mill equipment to obtain the spatial accuracy repaired eighteen-roller rolling mill equipment; Step S12: execute mechanism detection repair processing on the spatial precision repaired eighteen-roller rolling mill equipment to obtain the effective execution mechanism eighteen-roller rolling mill equipment; Step S13: perform sensor detection optimization processing on the effective execution mechanism eighteen-roller rolling mill equipment to obtain the optimized eighteen-roller rolling mill equipment.

3. The strip break prediction and management method adapted to the control of an eighteen-roller rolling mill according to claim 2, characterized in that, Step S11 includes the following steps: Collecting equipment wear state data of the eighteen-roller rolling mill equipment based on the preset wear state detection sequence data, and generating equipment wear state data; Detecting the roll system axis rotation angle offset state of the eighteen-roller rolling mill equipment using a gyroscope device, and generating roll system axis state data; Detecting the transmission roll axis position offset state of the eighteen-roller rolling mill equipment using a laser tracker, and generating transmission roll axis position offset data; Performing equipment spatial precision repair analysis processing based on the equipment wear state data, the roll system axis state data, and the transmission roll axis position offset data, and generating equipment spatial precision repair data; Performing spatial precision repair processing on the eighteen-roller rolling mill equipment based on the equipment spatial precision repair data, and obtaining the spatial precision repaired eighteen-roller rolling mill equipment.

4. The strip break prediction and management method adapted for eighteen-roller mill control of claim 2, wherein, Step S12 includes the following steps: Performing main roll system drive test processing on the spatial precision repaired eighteen-roller rolling mill equipment to obtain main roll system drive test data; Performing main roll system drive test compliance data analysis on the main roll system drive test data using a preset main roll system drive threshold, including: when the main roll system drive test data is not less than the main roll system drive threshold, marking the spatial precision repaired eighteen-roller rolling mill equipment corresponding to the main roll system drive test data as main roll system effective drive to obtain the main roll system effective drive eighteen-roller rolling mill equipment; when the main roll system drive test data is less than the main roll system drive threshold, marking the spatial precision repaired eighteen-roller rolling mill equipment corresponding to the main roll system drive test data as main roll system invalid drive to obtain the main roll system invalid drive eighteen-roller rolling mill equipment; Feedback the main roll system invalid drive eighteen-roller rolling mill equipment to the terminal to perform press-down device model maintenance work; Performing support roll system drive test processing on the main roll system effective drive eighteen-roller rolling mill equipment to obtain support roll system drive test data; Performing support roll system drive test compliance data analysis on the support roll system drive test data using a preset support roll system drive threshold, including: when the support roll system drive test data is not less than the support roll system drive threshold, marking the main roll system effective drive eighteen-roller rolling mill equipment corresponding to the support roll system drive test data as support roll system effective drive to obtain the effective execution mechanism eighteen-roller rolling mill equipment; when the support roll system drive test data is less than the support roll system drive threshold, marking the main roll system effective drive eighteen-roller rolling mill equipment corresponding to the support roll system drive test data as support roll system invalid drive to obtain the support roll system invalid drive eighteen-roller rolling mill equipment; Feedback the main roll system invalid drive eighteen-roller rolling mill equipment to the terminal to perform support roll system maintenance work.

5. The strip break prediction and management method adapted for eighteen-roller mill control of claim 2, wherein, Step S13 includes the following steps: Collecting sensor precision data of the effective execution mechanism eighteen-roller rolling mill equipment, and generating sensor precision data; According to the accuracy data of each level sensor, accuracy repair data analysis of each level sensor is performed to generate accuracy repair data of each level sensor; According to the accuracy repair data of each level sensor, accuracy repair optimization processing of the eighteen-roller rolling mill equipment of the effective actuator is performed to obtain the optimized eighteen-roller rolling mill equipment.

6. The strip break prediction and management method adapted for eighteen-roller mill control of claim 1, wherein, The abnormal fluctuation control processing of the strip steel production real-time operation based on the strip break control critical parameter in step S3 includes the following steps: The abnormal fluctuation control processing of the strip steel production real-time operation based on the strip break control critical parameter includes: when the hypersensitive strip break index data of the strip steel production real-time operation is not within the range of the strip break control critical parameter, the strip steel production real-time operation is stopped; when the hypersensitive strip break index data of the strip steel production real-time operation is within the range of the strip break control critical parameter, the strip steel production real-time operation is continued to obtain strip steel production real-time data.

7. The strip break prediction and management method adapted for eighteen-roller mill control of claim 6, wherein, The iteration update operation of the strip break control critical parameter in step S4 includes the following steps: The real-time strip break data monitoring processing of the strip steel production real-time data includes: when the strip steel production real-time data does not monitor real-time strip break data, the strip break control critical parameter is fed back to the terminal to perform the strip break prediction mechanism establishment operation; when the strip steel production real-time data monitors real-time strip break data, the real-time strip break data is used to iteratively update the strip break data to generate updated strip break data, and the updated strip break data is transmitted to step S22 to perform the iteration update of the strip break control critical parameter.

Images