Method, system and equipment for adjusting tip thickness of lower leg of steel rail and medium

Abstract

The invention relates to the field of steel rolling, and provides a method, a system, equipment and a medium for adjusting the tip thickness of a lower leg of a steel rail, and the method comprises the following steps: obtaining historical data of steel rail production, carrying out multi-modal data fusion, and constructing an expert empirical model based on the fused data; detecting the tip thickness of the lower leg in real time; when the deviation of the specification size of the tip thickness of the lower leg exceeds a first preset value, a lower horizontal roller of the semi-universal rolling mill is adjusted; when the deviation of the specification size of the tip thickness of the lower leg exceeds a second preset value, lower horizontal rollers of a second universal rolling mill and a semi-universal rolling mill are adjusted; and adjusting lower horizontal rollers of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill in response to the situation that the deviation of the specification size of the lower leg tip thickness exceeds a third preset value. According to the method, through multi-modal data fusion, actual operation experience is adjusted in combination with the steel rail lower leg tip thickness, and the online steel rail lower leg tip thickness specification abnormal state is adjusted and rectified in real time in an expert experience extraction mode.

Description

Technical Field

[0001] The invention relates to the field of steel rolling, and in particular to a method, system, equipment and medium for adjusting the thickness of a rail lower leg tip. Background Art

[0002] The production of heavy rails is a very important part of railway construction, which is related to the safety and operation efficiency of the railway. From the information you provided, modern heavy rail production mainly adopts two rolling modes: the traditional two-roller mode and the advanced four-roller universal mode.

[0003] Two-roller mode: This is an older production method. Since the heavy rails produced by it cannot meet the high standards of modern high-speed heavy rails in terms of surface quality, cross-sectional dimensional accuracy and fullness of the rail crown, it is gradually being replaced by more advanced technologies.

[0004] Four-roll universal mode: This mode is the mainstream choice for modern heavy rail production lines. It achieves accurate rolling of heavy rails through the combination of multiple stands. Specifically, the rolling process of the universal rolling mill includes the following steps: Billet opening machine: First, the steel billet is preliminarily rolled through two billet opening machines to form a rolled piece with a preliminary rail shape and establish the proportional relationship between the head, waist and bottom.

[0005] Universal unit: Universal unit usually consists of three or five racks, of which the five-rack configuration has higher control accuracy. Universal unit includes: Universal Roughing Mill (UR1), Edge Mill (E1), Universal Intermediate Mill (UR2), Edge Mill (E2) and Universal Finishing Mill (UF).

[0006] Multi-pass rolling: Through continuous rolling of these stands, a finished heavy rail that meets the standards is finally formed.

[0007] Flexibility of adjustment: Compared with the traditional hole-type rolling method, the universal rolling method has greater flexibility in adjusting the head width and lower leg tip thickness, which can be adjusted separately and in a variety of ways.

[0008] Advantages: The main advantage of the universal rolling method is that during the rolling process, the rolling of the rail head and the rail bottom is completed by directly pressing down the vertical rollers, which makes the rolling direction the same as the rotation direction of the rollers, thereby improving the efficiency and quality of rolling.

[0009] In general, the four-roll universal mode has become the preferred method for modern heavy rail production due to its high precision and flexibility. The rail leg tip thickness plays a vital role in railway track design. It is not only directly related to the bearing capacity of the track, but also essential to ensure the smooth operation and safety of the train. Rails with thicker lower leg tips can withstand heavier train loads and adapt to more frequent trains because they provide a wider contact area and stronger support, thus significantly improving the bearing capacity of the track.

[0010] In addition, the increase in the thickness of the lower leg of the rail can effectively improve the stability of the track. The wider bottom design helps to reduce the bending and deformation of the track caused by train loads and reduce the risk of train derailment, which is crucial to ensuring the safety of railway transportation.

[0011] However, in the production process of rails, the precise adjustment of the lower leg tip thickness is a technical challenge. There are cross-influences between different adjustment methods and parameters, and the accuracy of the parameters is crucial to the analysis results of equipment and specification parameters. These factors may cause deviations between the analysis results and the actual deformation law and adjustment method. Summary of the invention

[0012] Based on the above purpose, the present invention proposes a method for adjusting the thickness of a rail lower leg tip, comprising: Obtain historical data on rail production, perform multimodal data fusion, and build an expert experience model based on the fused data; Real-time detection of lower leg tip thickness; In response to the deviation of the specification dimension of the lower leg tip thickness exceeding a first preset value, adjusting the lower horizontal roll of the semi-universal rolling mill; In response to the deviation of the specification size of the lower leg tip thickness exceeding a second preset value, adjusting the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill; In response to the deviation of the specification size of the lower leg tip thickness exceeding the third preset value, the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill are adjusted.

[0013] In some embodiments, in response to the deviation of the specification size of the lower leg tip thickness exceeding a first preset value, the step of adjusting the lower horizontal roll of the semi-universal rolling mill includes: In response to the deviation of the specification dimension of the lower leg tip thickness being less than a first preset value, adjusting the lower horizontal roll of the semi-universal mill based on a first scheme; In response to the deviation of the specification dimension of the lower leg tip thickness being greater than the first preset value, the lower horizontal roll of the semi-universal rolling mill is adjusted based on the second scheme.

[0014] In some embodiments, in response to the deviation of the specification size of the lower leg tip thickness exceeding the second preset value, the step of adjusting the lower horizontal rolls of the universal rolling mill and the semi-universal rolling mill includes: In response to the deviation of the specification size of the lower leg tip thickness being less than a second preset value, adjusting the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill based on the third scheme; In response to the deviation of the specification size of the lower leg tip thickness being greater than the second preset value, the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill are adjusted based on the fourth scheme.

[0015] In some embodiments, in response to the deviation of the specification size of the lower leg tip thickness exceeding a third preset value, the step of adjusting the lower horizontal rolls of the universal rolling mill and the semi-universal rolling mill includes: In response to the deviation of the specification size of the lower leg tip thickness being less than the third preset value, adjusting the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill based on the fifth scheme; In response to the deviation of the specification size of the lower leg tip thickness being greater than the third preset value, the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill are adjusted based on the sixth scheme.

[0016] In some embodiments, the step of constructing the expert experience model comprises: The fused lower leg tip thickness specifications of each team are extracted from the fused data; Analyze the distribution of the fusion lower leg tip thickness specification size values, rank them according to the control effect of the fusion lower leg tip thickness specification, and take the teams whose ranking exceeds the threshold as expert knowledge; Generate an expert experience model based on specification size value distribution and expert knowledge.

[0017] In some embodiments, historical data of rail production is obtained and multimodal data fusion is performed; Align historical data of different modalities based on timestamps; Extract features from the data of each modality, and fuse the extracted features to form a multimodal feature vector; The principal component analysis method is used to reduce the dimensionality of multimodal feature vectors.

[0018] In some embodiments, the historical data includes sensor data, visual data, textual data, and numerical data.

[0019] The present invention provides a system for adjusting the thickness of a rail lower leg tip, comprising: A construction unit configured to obtain historical data of rail production, perform multimodal data fusion, and construct an expert experience model based on the fused data; A detection unit configured to detect the thickness of the lower leg tip in real time; a first adjustment unit configured to adjust a lower horizontal roll of the semi-universal rolling mill in response to a deviation of a specification dimension of the lower leg tip thickness exceeding a first preset value; a second adjustment unit configured to adjust the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill in response to a deviation of the specification size of the lower leg tip thickness exceeding a second preset value; The third adjustment unit is configured to adjust the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill in response to the deviation of the specification size of the lower leg tip thickness exceeding a third preset value.

[0020] The present invention provides a computer device, comprising: At least one processor; and a memory, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the steps of the method for adjusting the thickness of the lower leg tip of the rail are performed.

[0021] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for adjusting the thickness of a lower leg tip of a rail are executed.

[0022] The present invention has at least the following beneficial technical effects: The present invention proposes a method, system, equipment and medium for adjusting the thickness of a lower leg tip of a rail. The method comprises: acquiring historical data of rail production, performing multimodal data fusion, and constructing an expert experience model based on the fused data; detecting the thickness of the lower leg tip in real time; in response to a deviation in the specification size of the lower leg tip thickness exceeding a first preset value, adjusting the lower horizontal roller of a semi-universal rolling mill; in response to a deviation in the specification size of the lower leg tip thickness exceeding a second preset value, adjusting the lower horizontal rollers of a second universal rolling mill and a semi-universal rolling mill; in response to a deviation in the specification size of the lower leg tip thickness exceeding a third preset value, adjusting the lower horizontal rollers of a first universal rolling mill, a second universal rolling mill and a semi-universal rolling mill.

[0023] The invention is a method for constructing a rail leg tip thickness adjustment model. Its innovation lies in that it combines the actual operation experience of rail leg tip thickness adjustment through multi-modal data fusion, applies the expert experience extraction method, and finally can recommend the rail leg tip thickness specification control plan in real time through the unique expert knowledge data value method and solution optimization algorithm. It forms an independent rail leg tip thickness specification adjustment calculation, and makes real-time adjustment and correction to the abnormal state of the online rail leg tip thickness specification, so that the rail leg tip thickness specification is always stable within the internal control standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A flow chart of a method for adjusting the thickness of a rail lower leg tip provided by the present invention; Figure 2 A system module diagram for adjusting the thickness of a rail lower leg tip provided by the present invention; Figure 3 A flow chart of an embodiment of a method for adjusting rail bottom width provided by the present invention; Figure 4 A process diagram of a universal rolling rail pass profile of an embodiment of a method for adjusting rail bottom width provided by the present invention; Figure 5 A schematic diagram of a rail cross section and bottom width of an embodiment of a method for adjusting the bottom width of a rail provided by the present invention; Figure 6 A schematic diagram of a rail cross section and rail crown height of an embodiment of a rail bottom width adjustment method provided by the present invention; Figure 7 A schematic diagram of a rail cross section and belly cavity of an embodiment of a method for adjusting rail bottom width provided by the present invention; Figure 8 A schematic diagram of a rail cross section and an upper leg tip of an embodiment of a method for adjusting the bottom width of a rail provided by the present invention; Fig. 9 A schematic diagram of a rail cross section and a lower leg tip of an embodiment of a method for adjusting the bottom width of a rail provided by the present invention; Fig.10 A schematic diagram of a hole pattern of an adjustment scheme for a rail bottom width adjustment method provided by the present invention, in which the 60kg / m lower leg tip exceeds the specification by 0.1mm-0.2mm; Fig.11 A schematic diagram of a hole pattern of an adjustment scheme for increasing the specification of 0.2mm-0.4mm at the lower leg tip of 60kg / m in one embodiment of a method for adjusting the bottom width of a rail provided by the present invention; Fig.12 A schematic diagram of a hole pattern of an adjustment scheme for increasing the size of the 60kg / m lower leg tip by 0.5mm-0.6mm in one embodiment of a method for adjusting the bottom width of a rail provided by the present invention; Fig.13 A schematic diagram of the structure of an embodiment of a computer device provided by the present invention; Fig.14 A schematic diagram of the structure of an embodiment of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0027] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.

[0028] The present invention proposes a method for adjusting the thickness of the lower leg of a rail. Figure 1 , Figure 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 8 and Fig. 9 ,include: S1: Obtain historical data of rail production, perform multimodal data fusion, and build an expert experience model based on the fused data; S2: Real-time detection of lower leg tip thickness; S3: in response to the deviation of the specification size of the lower leg tip thickness exceeding the first preset value, adjusting the lower horizontal roll of the semi-universal rolling mill; S4: in response to the deviation of the specification size of the lower leg tip thickness exceeding the second preset value, adjusting the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill; S5: In response to the deviation of the specification size of the lower leg tip thickness exceeding the third preset value, the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill are adjusted.

[0029] Universal rolling rail pass technology Figure 4 As shown: Production line: semi-universal production line, equipment UR1 (universal rolling mill), E1, UR2 (universal rolling mill), E2, UF (semi-universal rolling mill); adjusted production situation: normal steel output, normal rolling force, normal temperature, reasonable rolling speed, normal temperature.

[0030] Figure 5 , Figure 6 , Figure 7 , Figure 8 and Fig. 9 The different parameters of the rail section are shown. Among them, Figure 5 The bottom width, Figure 6 For the rail crown, Figure 7 For the abdominal cavity, Figure 8 For the upper leg tip, Fig. 9 It is the tip of the lower leg.

[0031] Rail section Fig. 9 As shown, the lower leg tip thickness is an important specification of the rail. There are two ideas for adjusting the lower leg tip thickness of the rail in actual production. The first idea is: when the metal distribution of the rail is normal, the horizontal roll of the two-roller mill is adjusted to achieve the purpose of controlling the lower leg tip thickness. The second idea is: adjust the metal change at the bottom of the rail through the bottom vertical roll of the universal mill / semi-universal mill to achieve the purpose of controlling the lower leg tip thickness of the rail.

[0032] The design process of the present invention is as follows: Data collection and analysis: By statistically analyzing the production control data and expert experience data of each team, multi-modal data fusion is performed to compile a historical lower leg tip thickness specification control ranking table. The team with the best control effect is selected as the object of expert knowledge extraction.

[0033] Empirical model construction: Based on specification deviation values ​​and expert experience, the optimal adjustment plan is formed, and an empirical data model for lower leg tip thickness specification control is established.

[0034] Establishment of adjustment scheme library: For different specification deviation values, corresponding adjustment schemes are established in the experience model library to ensure the diversity and adaptability of the schemes.

[0035] Practical application: In actual production, the actual specifications of the rails are automatically measured by online profile scanners. The deviation between the actual specifications and the standard values ​​is compared, and appropriate adjustment plans are retrieved from the empirical model library.

[0036] Parameter adjustment and control: The adjustment plan contains necessary adjustment parameters, which are sent to the PLC (Programmable Logic Controller) through data communication to achieve automatic adjustment of the rack parameters and ensure that the thickness of the finished lower leg tip meets the control requirements.

[0037] The adjustment method of the present invention: specification parameter setting: setting the actual rail lower leg tip thickness to H, the head height to X, and the leg height to Z; the standard rail lower leg tip thickness to H0, the head height to X0, and the leg height to Z0.

[0038] Automatic measurement and judgment: Use online profile scanner to automatically measure the finished product specifications. The system automatically judges the dimensional deviation between the lower leg tip thickness H and the standard value H0 Whether it exceeds the control deviation ΔH0. If so, adjustment is required.

[0039] Determination of adjustment position: When the lower leg tip thickness H exceeds the deviation ΔH0, the system automatically determines the main factors affecting the lower leg tip thickness based on the head and leg heights. According to the deviation values ​​ΔX and ΔZ of the head and leg heights, the rolling mill position that needs to be adjusted is determined.

[0040] Adjustment ideas and priorities: If the head and leg height deviations exceed the control deviation at the same time, the system will adjust the height according to the percentage of excess. , compare the percentage of head and leg height excess, and give priority to adjusting the specification items with larger excess ratios.

[0041] Determination of roll gap adjustment amount: In the empirical model library, according to the different levels of the lower leg tip thickness deviation range, the corresponding rack parameters are selected for adjustment to achieve precise control.

[0042] By acquiring historical data of rail production and performing multimodal data fusion, data from different sources and formats can be integrated to improve the comprehensiveness and accuracy of the data. Multimodal data fusion can make full use of the complementarity of various data sources, reduce information redundancy and errors, and improve the reliability and consistency of data. The expert experience model built based on the fused data can more accurately reflect the actual status and change trend of the rails. By introducing expert experience and historical data, the model can learn more laws and characteristics and improve the accuracy of prediction and judgment. The expert experience model can provide scientific decision-making support to help maintenance personnel identify and deal with potential problems of rails in a timely manner. Through real-time monitoring and early warning, the model can detect abnormal situations in advance and provide sufficient time to prepare for maintenance and replacement work.

[0043] In some embodiments, see Figure 1 , Figure 3 and Fig.10 In response to the deviation of the specification size of the lower leg tip thickness exceeding the first preset value, the step of adjusting the lower horizontal roll of the semi-universal rolling mill includes: In response to the deviation of the specification dimension of the lower leg tip thickness being less than a first preset value, adjusting the lower horizontal roll of the semi-universal mill based on a first scheme; In response to the deviation of the specification dimension of the lower leg tip thickness being greater than the first preset value, the lower horizontal roll of the semi-universal rolling mill is adjusted based on the second scheme.

[0044] The adjustment range is the first preset value: 0.1mm~0.2mm (exceeding / under the standard): Adjusting roller: UF lower horizontal roller axial direction; Adjustment logic description: UF universal rolling mill is equipped with 60KG final product pass type, which has the most obvious influence on the adjustment of rail specifications. The principle of adjusting the lower leg tip thickness specification is to change the amount of metal at the bottom of the rail by adjusting the axial roll gap value of the UF lower horizontal roller, such as Fig.10 It can be seen that the specifications of the rolled product change when the UF axial head vertical roll is adjusted in the positive direction.

[0045] The impact of the adjustment scheme: During the rail production process, a positive adjustment of the UF axis can reduce the amount of bottom metal processed on the inner side of the lower leg. This results in more metal on the lower leg at the bottom of the rail, which increases the thickness of the lower leg tip. However, since the rollers reduce the processing of the inner side of the lower leg of the rolled piece, the widening of the leg tip is also reduced, which shortens the length of the lower leg and reduces the symmetry of the lower leg. Conversely, a negative adjustment of the UF axis will produce the opposite effect of a positive adjustment.

[0046] Adjustment plan: If the specification is less than the standard lower limit, use the first option; When the lower leg tip thickness specification is less than the standard lower limit of 0.1mm~0.2mm, by adjusting the axial positive adjustment of the lower horizontal roller of UF in the first pass by 0.1mm~0.2mmmm roller gap, the lower leg tip thickness can be increased by 0.1mm~0.2mm, the lower profile can be increased by 0.1mm~0.2mm, the lower symmetry can be reduced by 0.1mm~0.2mm, and the bottom width can be reduced by 0.1mm~0.2mm.

[0047] If the specification exceeds the upper limit of the standard, use the second option; When the lower leg tip thickness specification is less than the standard lower limit of 0.1mm~0.2mm, by adjusting the axial positive adjustment of the lower horizontal roller of UF in the first pass by 0.1mm~0.2mmmm roller gap, the lower leg tip thickness can be reduced by 0.1mm~0.2mm, the lower profile can be reduced by 0.1mm~0.2mm, the lower symmetry can be increased by 0.1mm~0.2mm, and the bottom width can be increased by 0.1mm~0.2mm.

[0048] In some embodiments, see Figure 1 , Figure 3 and Fig.11 In response to the deviation of the specification size of the lower leg tip thickness exceeding the second preset value, the step of adjusting the lower horizontal rolls of the universal rolling mill and the semi-universal rolling mill includes: In response to the deviation of the specification size of the lower leg tip thickness being less than a second preset value, adjusting the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill based on the third scheme; In response to the deviation of the specification size of the lower leg tip thickness being greater than the second preset value, the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill are adjusted based on the fourth scheme.

[0049] The adjustment range is the second preset value: 0.3mm~0.4mm (exceeding / falling short of the standard); Adjusting roller: UF lower roller axial direction, UR2 lower roller axial direction; Adjustment logic description: For the case where the bottom leg tip thickness is lower than the standard, it is feasible to adjust the axial direction of the UF lower roller alone, but this is not reasonable, which will cause the UF rolling force to be unbalanced and the steel to be twisted. Therefore, a more reasonable adjustment idea is to adjust the axial direction of the UR2 lower roller to balance the bottom metal changes, such as Fig.11The specification changes and impacts after the adjustment of the scheme shown. If the lower leg tip thickness specification is lower than the standard, the adjustment idea is opposite to the adjustment that exceeds the standard.

[0050] The impact of the adjustment plan: The axial roll gap value of the UR2 lower roller is adjusted to change the amount of metal in the lower leg at the bottom of the rail, affecting the thickness specifications of the lower leg tip; and because UF is a semi-universal rolling mill and is equipped with finished holes, the axial adjustment of the lower roller causes the bottom metal to expand horizontally and extend vertically in the direction of the upper and lower leg tips, affecting the thickness specifications of the lower leg tip.

[0051] Adjustment plan: If the specification is less than the standard lower limit, use the third option; When the lower leg tip thickness specification is less than the standard lower limit of 0.3mm, the UR2 lower roller axially adjusts the roll gap by 0.3mm, and the UF lower roller axially adjusts the roll gap by 0.2mm, which can increase the lower leg tip thickness by 0.3mm and reduce the lower symmetry by 0.2mm.

[0052] When the lower leg tip thickness specification is less than the standard lower limit of 0.4mm, the UR2 lower roller axially adjusts the roll gap by 0.5mm, and the UF lower roller axially adjusts the roll gap by 0.3mm, which can increase the lower leg tip thickness by 0.4mm and reduce the lower symmetry by 0.3mm.

[0053] If the specification exceeds the upper limit of the standard, use the fourth option; When the lower leg tip thickness specification is less than the standard lower limit of 0.3mm, the UR2 lower roller axially negatively adjusts the roll gap by 0.3mm, and the UF lower roller axially negatively adjusts the roll gap by 0.2mm, which can reduce the lower leg tip thickness by 0.3mm and increase the lower symmetry by 0.2mm.

[0054] When the lower leg tip thickness specification is less than the standard lower limit of 0.4mm, the UR2 lower roller axially negatively adjusts the roll gap by 0.5mm, and the UF lower roller axially negatively adjusts the roll gap by 0.3mm, which can reduce the lower leg tip thickness by 0.4mm and increase the lower symmetry by 0.3mm.

[0055] In some embodiments, see Figure 1 , Figure 3 and Fig.12 In response to the deviation of the specification size of the lower leg tip thickness exceeding the third preset value, the step of adjusting the lower horizontal rolls of the universal rolling mill and the semi-universal rolling mill includes: In response to the deviation of the specification size of the lower leg tip thickness being less than the third preset value, adjusting the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill based on the fifth scheme; In response to the deviation of the specification size of the lower leg tip thickness being greater than the third preset value, the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill are adjusted based on the sixth scheme.

[0056] The adjustment range is the third preset value: 0.5mm~0.6mm (exceeding / falling short of the standard); Adjust the roll gap value: UR1 lower roll axial direction, UR2 lower roll axial direction, UF lower roll axial direction; Adjustment logic description: In the case where the lower leg tip thickness specification is seriously substandard, on the basis of the 0.3mm~0.4mm adjustment plan, the axial adjustment of the lower roller of UR1 is required for three passes, and the axial adjustment of the lower roller of UR2 and the lower roller of UF constitute a combined adjustment. The principle is to change the metal feed of the rolled piece through the axial processing of the previous pass of the universal zone, so as to achieve uniform widening and extension, reduce / increase the metal feed at the bottom of the UF universal machine, reduce the axial processing of the UF lower roller, and finally achieve the specification of controlling the lower leg tip thickness, balance the rolling force on the inner side of the lower leg, and make it normal to discharge steel. The impact of the adjustment plan: The axial processing of the lower roller in the three passes of UR1 changes the incoming metal of the lower leg tip as a whole and changes the UF processing volume. The axial processing of the lower roller of the UF finished hole has the most obvious impact on the specifications of the lower leg tip thickness and lower profile.

[0057] Adjustment plan: If the specification is less than the standard lower limit, use the first option; When the lower leg tip thickness specification is less than the standard lower limit of 0.5mm, the axial positive adjustment of the lower roller gap in the 1st and 2nd passes of UR1 is 0.8mm, the axial positive adjustment of the lower roller gap in the 3rd pass of UR1 is 0.5mm, the axial positive adjustment of the lower roller gap in the 1st pass of UR2 is 0.5mm, and the axial positive adjustment of the lower roller gap in the 1st pass of UF is 0.3mm, which can increase the lower leg tip thickness by 0.5mm.

[0058] When the lower leg tip thickness specification is less than the standard lower limit of 0.6mm, the axial positive adjustment of the lower roller gap in the 1st, 2nd and 3rd passes of UR1 is 0.8mm, the axial positive adjustment of the lower roller gap in the 1st pass of UR2 is 0.5mm, and the axial positive adjustment of the lower roller gap in the 1st pass of UF is 0.4mm, which can increase the lower leg tip thickness by 0.6mm.

[0059] If the specification exceeds the upper limit of the standard, use the first option; When the lower leg tip thickness specification is greater than the standard upper limit of 0.5mm, the axial negative roll gap of the lower roller in the 1st and 2nd passes of UR1 is adjusted by 0.8mm, the axial negative roll gap of the lower roller in the 3rd pass of UR1 is adjusted by 0.5mm, the axial negative roll gap of the lower roller in the 1st pass of UR2 is adjusted by 0.5mm, and the axial negative roll gap of the lower roller in the 1st pass of UF is adjusted by 0.3mm, which can reduce the lower leg tip thickness by 0.5mm.

[0060] When the lower leg tip thickness specification is greater than the standard upper limit of 0.6mm, the axial negative roll gap of the lower roller in the 1st, 2nd and 3rd passes of UR1 is adjusted by 0.8mm, the axial negative roll gap of the lower roller in the 1st pass of UR2 is adjusted by 0.5mm, and the axial negative roll gap of the lower roller in the 1st pass of UF is adjusted by 0.4mm, which can reduce the lower leg tip thickness by 0.6mm.

[0061] In some embodiments, the step of constructing the expert experience model comprises: The fused lower leg tip thickness specifications of each team are extracted from the fused data; Analyze the distribution of the fusion lower leg tip thickness specification size values, rank them according to the control effect of the fusion lower leg tip thickness specification, and take the teams whose ranking exceeds the threshold as expert knowledge; Generate an expert experience model based on specification size value distribution and expert knowledge.

[0062] By extracting the fused lower leg tip thickness specifications of each team from the fused data, the actual performance of each team in the production process can be accurately grasped. This helps to identify teams with excellent performance and teams with problems, providing a basis for subsequent analysis and improvement. By analyzing the distribution of the fused lower leg tip thickness specification size values, we can understand the specification stability, discreteness, and potential problem points in the overall production process. This helps to discover regular problems and potential risks in the production process and provide guidance for formulating targeted improvement measures.

[0063] By ranking the control effects of the fused lower leg tip thickness specifications, it is possible to identify which teams have performed well in the production process and have high control accuracy and stability. By using the teams that have ranked above the threshold as expert knowledge, the excellent practices and experiences of these teams in the production process can be extracted. This expert knowledge can provide valuable reference and lessons for other teams, helping them improve their production processes and product quality.

[0064] The expert experience model generated based on the distribution of specification size values ​​and expert knowledge can provide scientific guidance for quality control in the production process. Through model prediction and judgment, abnormal situations in the production process can be discovered in time, providing sufficient time for maintenance and replacement work.

[0065] In some embodiments, historical data of rail production is obtained and multimodal data fusion is performed; Align historical data of different modalities based on timestamps; Extract features from the data of each modality, and fuse the extracted features to form a multimodal feature vector; The principal component analysis method is used to reduce the dimensionality of multimodal feature vectors.

[0066] By aligning historical data of different modalities by timestamp, the synchronization and consistency of data can be ensured, thereby improving the accuracy of data. This helps to reduce errors and misunderstandings caused by data mismatch or asynchrony. Aligned data is easier to perform subsequent feature extraction and fusion operations. This provides a solid foundation for building multimodal feature vectors, which in turn supports deeper data analysis and mining.

[0067] Extracting features from each modality of data can make full use of information from different data sources. This helps to obtain a more comprehensive and accurate description and explanation of the target object. Fusion of the extracted features to form a multimodal feature vector can enhance the performance of the model. The multimodal feature vector contains information from different data sources, which enables the model to more accurately understand and predict the behavior and state of the target object.

[0068] By reducing the dimensionality of multimodal feature vectors through principal component analysis, the dimensionality of the data can be reduced, thereby reducing computational complexity. This helps improve the efficiency and speed of data processing, especially when dealing with large-scale data sets. The reduced dimensionality data retains the main information and features in the original data while removing redundancy and noise. This helps improve the generalization ability of the model, enabling it to better adapt to new data and scenarios.

[0069] In some embodiments, see Figure 1 , the historical data includes sensor data, visual data, text data and numerical data.

[0070] Sensor data provides real-time physical quantity measurements; visual data provides image information of scenes or objects; text data contains descriptive, illustrative or directive content; and numerical data provides quantitative measurements. These different modal data together constitute a comprehensive description of the target object.

[0071] Data from different modalities are often complementary and can fill in the information gaps between each other. For example, sensor data cannot directly reflect the appearance of the device, while visual data provides intuitive visual feedback; text data contains a detailed description of the event, while numerical data provides the frequency or intensity of the event.

[0072] The present invention proposes a system for adjusting the thickness of the lower leg of the rail. Figure 2 ,include: A construction unit 100 is configured to obtain historical data of rail production, perform multimodal data fusion, and construct an expert experience model based on the fused data; The detection unit 200 is configured to detect the thickness of the lower leg tip in real time; A first adjustment unit 300 is configured to adjust a lower horizontal roll of the semi-universal rolling mill in response to a deviation of a specification dimension of the lower leg tip thickness exceeding a first preset value; A second adjustment unit 400, configured to adjust the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill in response to the deviation of the specification size of the lower leg tip thickness exceeding a second preset value; The third adjustment unit 500 is configured to adjust the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill in response to the deviation of the specification size of the lower leg tip thickness exceeding a third preset value.

[0073] The present invention extracts adjustment experience from on-site experts to perform multimodal data fusion, integrates the expert adjustment experience database, uses computer control as a carrier, and constructs an expert experience model to form an independent calculation for adjusting the specification of the lower leg tip thickness of the rail, and adjusts the online lower leg tip thickness specification in real time, so that the lower leg tip thickness specification of the rail is always stable within the internal control standard. It solves the problems of large fluctuations in the thickness of the lower leg tip, errors in manual sampling, and low efficiency of manual adjustment, improves the timeliness of adjustment, and reduces the accidental errors of manual calculation. At the same time, it improves the standardization of steel rolling adjustments and effectively reduces product specification control fluctuations between teams. Through repeated demonstrations and experimental verifications, it is found that this method can solve and adapt to the problem of adjusting the thickness of the lower leg tip of the rail under various production process conditions, and has great development prospects in the metallurgical field at home and abroad.

[0074] In one embodiment, please refer to Table 1 and Table 2. The implementation of the solution is described below using 60 heavy rail as an example: Obtain the rail specifications and dimensions to determine whether the rail lower leg tip thickness specifications need to be adjusted.

[0075] Table 1 Sampling data table before adjustment

[0076] Input sampling data, the rest of the specifications are in standard internal control, the thickness of the lower leg tip needs to be reduced by 0.2mm, click calculate, and generate a solution: adjust the axial negative roll gap of the UF lower roller by 0.2mm. The impact value is: reduce the thickness of the lower leg tip by 0.2mm, increase the lower symmetry by 0.2mm, and increase the bottom width by 0.2mm.

[0077] The model calculation plan is sent down, the actual roll gap value is modified, and then the next roll is sampled. As shown in Table 2.

[0078] Table 2 Adjusted sampling data table

[0079] Analysis of the sampling data after adjustment shows that the issued plan has obvious changes in the specifications of the lower leg tip thickness, and the impact on the specifications of the lower leg tip thickness is also in line with the trend of changes in the plan simulation.

[0080] The purpose of the present invention is to collect, summarize and unify manual adjustment experience, and realize adjustment with manual experience as the adjustment idea and computer model as the adjustment framework.

[0081] Data processing is performed on the difference increments between specifications to achieve automatic adjustment and increase the accuracy of automatic adjustment. The empirical formula modeling method is used to eliminate common interference and improve the control accuracy of the model automatic adjustment on rail specifications.

[0082] Feasibility of the present invention: The basis of the model is to unify the rolling adjustment experience of mature products, take the essence and remove the dross, and finally form a mature product rolling adjustment plan with high efficiency, high requirements and high precision. Such a plan is used as the core to substitute into the computer model to realize automatic adjustment, and an automatic test is carried out in the second line of the rail beam factory. The test results show that the feasibility of the adjustment plan reaches 98.74%, and the success rate of adjustment is 99.87%.

[0083] Prospects of the invention: In steel and vanadium rail beam factories, there is a wealth of experience in manual adjustment of mature products, so more high-efficiency, high-demand, and high-precision rolling adjustment schemes can be formed. This can not only improve rolling efficiency and rolling precision, but also save time costs and reduce production costs.

[0084] Based on the same inventive concept, according to another aspect of the present invention, Fig.13 As shown, an embodiment of the present invention further provides a computer device 30, which includes a processor 310 and a memory 320. The memory 320 stores a computer program 321 that can be run on the processor. When the processor 310 executes the program, the steps of the above method are performed.

[0085] Based on the same inventive concept, according to another aspect of the present invention, Fig.14 As shown, an embodiment of the present invention further provides a computer-readable storage medium 40, which stores a computer program 410 for executing the above method when executed by a processor.

[0086] The embodiment of the present invention may also include a corresponding computer device. The computer device includes a memory, at least one processor, and a computer program stored in the memory and executable on the processor, and the processor executes any one of the above methods when executing the program.

[0087] The memory, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules in the embodiments of the present application. The processor executes various functional applications and data processing of the device by running the non-volatile software programs, instructions and modules stored in the memory, that is, implementing the above method.

[0088] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In an embodiment, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0089] Finally, it should be noted that a person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium of the program can be a disk, an optical disk, a read-only storage memory (ROM) or a random access memory (RAM), etc. The above-mentioned computer program embodiments can achieve the same or similar effects as the corresponding above-mentioned arbitrary method embodiments.

[0090] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.

[0091] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope of the embodiments disclosed in the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.

[0092] It should be understood that, as used herein, the singular forms "a", "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations including one or more of the associated listed items.

[0093] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A method for adjusting the thickness of a rail lower leg tip, characterized in that: include: Obtain historical data on rail production, perform multimodal data fusion, and build an expert experience model based on the fused data; Real-time detection of lower leg tip thickness; In response to the deviation of the specification dimension of the lower leg tip thickness exceeding a first preset value, adjusting the lower horizontal roll of the semi-universal rolling mill; In response to the deviation of the specification size of the lower leg tip thickness exceeding a second preset value, adjusting the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill; In response to the deviation of the specification size of the lower leg tip thickness exceeding the third preset value, the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill are adjusted.

2. A method for adjusting the thickness of a rail lower leg tip according to claim 1, characterized in that: In response to the deviation of the specification size of the lower leg tip thickness exceeding the first preset value, the step of adjusting the lower horizontal roll of the semi-universal rolling mill includes: In response to the deviation of the specification dimension of the lower leg tip thickness being less than a first preset value, adjusting the lower horizontal roll of the semi-universal mill based on a first scheme; In response to the deviation of the specification dimension of the lower leg tip thickness being greater than the first preset value, the lower horizontal roll of the semi-universal rolling mill is adjusted based on the second scheme.

3. The method for adjusting the thickness of the lower leg of a rail according to claim 1, characterized in that: In response to the deviation of the specification size of the lower leg tip thickness exceeding the second preset value, the step of adjusting the lower horizontal rolls of the universal rolling mill and the semi-universal rolling mill includes: In response to the deviation of the specification size of the lower leg tip thickness being less than a second preset value, adjusting the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill based on the third scheme; In response to the deviation of the specification size of the lower leg tip thickness being greater than the second preset value, the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill are adjusted based on the fourth scheme.

4. The method for adjusting the thickness of the lower leg of a rail according to claim 1, characterized in that: In response to the deviation of the specification size of the lower leg tip thickness exceeding the third preset value, the step of adjusting the lower horizontal rolls of the universal rolling mill and the semi-universal rolling mill includes: In response to the deviation of the specification size of the lower leg tip thickness being less than the third preset value, adjusting the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill based on the fifth scheme; In response to the deviation of the specification size of the lower leg tip thickness being greater than the third preset value, the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill are adjusted based on the sixth scheme.

5. The method for adjusting the thickness of the lower leg of a rail according to claim 1, characterized in that: The steps of constructing the expert experience model include: The fused lower leg tip thickness specifications of each team are extracted from the fused data; Analyze the distribution of the fusion lower leg tip thickness specification size values, rank them according to the control effect of the fusion lower leg tip thickness specification, and take the teams whose ranking exceeds the threshold as expert knowledge; Generate an expert experience model based on specification size value distribution and expert knowledge.

6. The method for adjusting the thickness of the lower leg of a rail according to claim 1, characterized in that: Obtain historical data on rail production and perform multimodal data fusion; Align historical data of different modalities based on timestamps; Extract features from the data of each modality, and fuse the extracted features to form a multimodal feature vector; The principal component analysis method is used to reduce the dimensionality of multimodal feature vectors.

7. The method for adjusting the thickness of the lower leg of a rail according to claim 1, characterized in that: The historical data includes sensor data, visual data, text data and numerical data.

8. A system for adjusting the thickness of the lower leg of a rail, characterized in that: include: A construction unit configured to obtain historical data of rail production, perform multimodal data fusion, and construct an expert experience model based on the fused data; A detection unit configured to detect the thickness of the lower leg tip in real time; a first adjustment unit configured to adjust a lower horizontal roll of the semi-universal rolling mill in response to a deviation of a specification dimension of the lower leg tip thickness exceeding a first preset value; a second adjustment unit configured to adjust the lower horizontal rolls of the second universal rolling mill and the semi-universal rolling mill in response to a deviation of the specification size of the lower leg tip thickness exceeding a second preset value; The third adjustment unit is configured to adjust the lower horizontal rolls of the first universal rolling mill, the second universal rolling mill and the semi-universal rolling mill in response to the deviation of the specification size of the lower leg tip thickness exceeding a third preset value.

9. A computer device comprising: at least one processor; and a memory storing a computer program executable on the processor, wherein the processor executes the steps of a method for adjusting the thickness of a rail lower leg tip as claimed in any one of claims 1 to 7 when executing the program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for adjusting the thickness of the lower leg tip of a rail as claimed in any one of claims 1 to 7 are performed.

Images