A protective sleeve with a bracket mechanism

By designing the bracket mechanism and machine learning model on the protective sleeve, the stability and monitoring problems of the sleeve in high-temperature and high-pressure environments are solved, and more scientific maintenance planning and production arrangements are achieved.

CN118653025BActive Publication Date: 2024-11-05RIZHAO DONGTAI COPPER ALLOY IND CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411132302.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-05
Estimated Expiration
2044-08-19

AI Technical Summary

Technical Problem

The existing protective sleeves are prone to displacement or loosening in high temperature and high pressure environments, and have a single function, so they cannot monitor the status in real time, resulting in the inability to understand the equipment situation in a timely manner, affecting production and use.

Method used

A protective sleeve with a bracket mechanism is designed, including a sleeve body, a bracket mechanism, abutment mechanism and a positioning mechanism. The sleeve body is fixed through the bracket mechanism, and the abutment mechanism limits the sleeve body, and the positioning mechanism is located from the blast furnace air outlet. The sleeve is supported and fixed internally and externally, and combined with machine learning models to predict the service life of the sleeve and support parameters, generating early warning level instructions.

Benefits of technology

It effectively increases the stability of the casing, avoids shaking, evaluates its safety, discovers potential hidden dangers in advance, promptly repairs and maintenance, reduces maintenance costs, and arranges production plans reasonably.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118653025B_ABST
    Figure CN118653025B_ABST
Patent Text Reader

Abstract

The present invention belongs to the technical field of protective sleeve supports, and discloses a protective sleeve with a bracket mechanism, comprising: a sleeve body; a bracket mechanism, which is arranged outside the sleeve body and detachably connected to the sleeve body, and is used to fix and support the sleeve body; an abutment mechanism, which is arranged inside the sleeve body, detachably connected to the sleeve body, and is used to limit the sleeve body; a positioning mechanism, which is arranged at the top of the sleeve body, and is used to connect the bracket assembly and the abutment assembly; the present invention provides a bracket mechanism and an abutment mechanism, and when the sleeve body is installed inside a blast furnace tuyere sleeve, the abutment mechanism can be used to abut and limit the sleeve body from the inside of the blast furnace tuyere sleeve, and at the same time, the bracket mechanism is fixedly installed outside the blast furnace tuyere sleeve to support and fix the sleeve body, which can effectively increase the stability of the installation of the sleeve body and avoid instability.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of protective sleeve supports, and in particular relates to a protective sleeve with a bracket mechanism. Background Art

[0002] In extreme environments such as the offshore oil and gas industry and blast furnace tuyere, equipment is often faced with challenges of high temperature, high pressure and severe wear. In order to protect key components and extend the life of equipment, copper-based composite materials are widely used in the production of protective sleeves due to their superior heat resistance and wear resistance. Existing protective sleeves are prone to displacement or loosening in high temperature and high pressure environments, and corresponding support devices are needed to increase their stability and thus ensure their protective effect.

[0003] For example, a Chinese patent application with publication number CN113639139A discloses a PE electric fusion sleeve protection device and an installation method. The PE electric fusion sleeve protection device includes at least two sets of detachable protection device components. The protection device components are in an annular cylindrical structure and are fixedly mounted on the PE pipes at both ends of the PE electric fusion sleeve by metal screws and fixing bolts. The PE electric fusion sleeve protection device provided by the invention can disperse the external force it is subjected to to the PE pipes at both ends of the PE electric fusion sleeve in the event of settlement or excavation external force, especially in a soft base environment such as pit filling or water filling, effectively protecting the PE electric fusion sleeve from being subjected to or less subjected to external stress, ensuring the bonding strength of the welding point between the PE electric fusion sleeve and the PE pipe, solving the problems of distortion, deformation and other air leakage of the PE electric fusion sleeve caused by settlement and external force, and realizing the protection of the PE pipe.

[0004] The existing protective sleeve has the following problems:

[0005] The protective sleeve is placed inside the blast furnace tuyere sleeve. When protecting the blast furnace tuyere sleeve, it is not effectively fixed, and the long-term damage caused by high temperature, friction, etc. makes it impossible to effectively guarantee the stability of the sleeve, making it easy to shake during work. In addition, the overall function of the existing protective sleeve is relatively single, and the status of the sleeve cannot be monitored in real time, resulting in the inability to timely understand the specific situation of the sleeve during work, so that the staff cannot timely carry out inspection and maintenance, affecting normal production and use, and needs to be improved. Summary of the invention

[0006] The object of the present invention is to provide a protective sleeve with a bracket mechanism, so as to solve the technical problems raised in the prior art.

[0007] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a protective sleeve with a bracket mechanism, comprising: a sleeve body; a bracket mechanism, which is arranged outside the sleeve body and detachably connected to the sleeve body, and is used to fix and support the sleeve body; an abutment mechanism, which is arranged inside the sleeve body and detachably connected to the sleeve body, and is used to limit the sleeve body; a positioning mechanism, which is arranged at the top of the sleeve body and is used to connect the bracket mechanism and the abutment mechanism; wherein the abutment mechanism is used to limit the sleeve body from the inside of the blast furnace tuyere sleeve, and the positioning mechanism is used to fix and support the sleeve body from the outside of the blast furnace tuyere sleeve.

[0008] Preferably, the bracket mechanism consists of a first bracket assembly and a second bracket assembly, the first bracket assembly and the second bracket assembly have the same structure and are symmetrically arranged, and the first bracket assembly includes: a connecting plate, which is arranged at the top of the sleeve body; a L-shaped positioning rod, which is symmetrically arranged at the top of the connecting plate, and one end extends to the side away from the connecting plate; a slide, which is slidably arranged on the L-shaped positioning rod; a positioning bolt, which is threadedly connected to the slide, and one end extends to the inside of the slide and abuts against the L-shaped positioning rod; a connecting rod, which is hinged at the lower end of the slide and is vertically arranged to the slide; an arc-shaped clamping plate, which is hinged on one side of the connecting rod and connected to the slide through the connecting rod.

[0009] Preferably, the abutment mechanism comprises: a clamping ring sleeve, which is arranged at the port of the sleeve body; a limiting hole, which is arranged through the side wall of the sleeve body; and an abutment member, which passes through the limiting hole and has one end abutting against the side wall of the clamping ring sleeve.

[0010] Preferably, the positioning mechanism comprises: a screw rod fixedly arranged at the end of the sleeve body; and a nut threadedly connected to the screw rod for fixing the connecting plate and the clamping ring.

[0011] Preferably, it also includes a control system, the control system includes:

[0012] The data acquisition module collects historical training parameters of the casing body, which include comprehensive influencing parameters and the service life of the casing body. The comprehensive influencing parameters include the material, working temperature, medium type, medium flow, stress and service time of the casing body.

[0013] Model training module, based on historical training parameters, trains a machine learning model to predict the service life of the casing body, collects real-time comprehensive influencing parameters, and predicts the service life of the casing body based on the trained machine learning model;

[0014] The data acquisition module is used to obtain the historical support data of the support device. The historical support data includes comprehensive influencing parameters and support parameter sets. The support parameter sets are converted into support parameter numbers. The support parameter numbers are , Indicates the total number of support parameter numbers;

[0015] The parameter prediction module trains a machine learning model to predict the support parameter number at future moments based on the comprehensive influencing parameters, and then obtains the support parameter set corresponding to the support parameter number;

[0016] The analysis module is used to generate a stability coefficient based on the predicted support parameter set at the future moment, and compare and analyze the stability coefficient with the preset stability coefficient threshold to determine and generate an early warning level instruction.

[0017] Preferably, the training method of the machine learning model for predicting the service life of the casing body includes:

[0018] The collected comprehensive influencing parameters are converted into a corresponding set of feature vectors.

[0019] Each group of feature vectors is used as the input of the machine learning model, and the machine learning model takes the service life of the casing body corresponding to each group of comprehensive influencing parameters as the output, and the actual service life of the casing body corresponding to each group of comprehensive influencing parameters is used as the prediction target, and minimizing the loss function value of the machine learning model is used as the training target; when the loss function value of the machine learning model is less than or equal to the preset target loss value, the training is stopped.

[0020] Preferably, the support parameter set is , , The vibration frequency, displacement and contact pressure of the casing body can be respectively corresponded. Indicates that the support parameter number is When , the corresponding values ​​of the vibration frequency, displacement and contact pressure of the casing body.

[0021] Preferably, the training method of the machine learning model for predicting the future moment support parameter number includes:

[0022] Preset forecast time step , sliding step length And the sliding window length ; Use the sliding window method to convert the historical support data into multiple training samples. One training sample corresponds to one label and constitutes a set of training data. Multiple sets of training data constitute a training set. The training set is used as the input of the machine learning model to predict the time step. The future moment support parameter number is taken as the output, the subsequent support parameter number of each training set is taken as the prediction target, and the prediction accuracy is taken as the training target to train the machine learning model; a machine learning model is generated that predicts the future moment support parameter number based on the comprehensive influencing parameters.

[0023] Preferably, the stability coefficient is generated as follows:

[0024] ;

[0025] In the formula, represents the stability coefficient, Indicates that the support parameter number is The vibration frequency of the casing body is Indicates that the support parameter number is The displacement of the casing body is Indicates that the support parameter number is The contact pressure of the casing body is represents the weight coefficient, Both are greater than 0.

[0026] Preferably, the stability coefficient is compared and analyzed with a preset stability coefficient threshold, and the method for determining the generation of the warning level instruction is as follows:

[0027] The warning level instructions include level one warning and level two warning, and the severity of the level one warning and level two warning decreases in sequence;

[0028] The preset stability coefficient threshold is , ,in, ;

[0029] when , it means that the stability coefficient does not exceed the threshold, and no warning level instruction is generated at this time;

[0030] when When , it means that the stability coefficient exceeds the minimum threshold, and a second-level warning is generated;

[0031] when When , it means that the stability coefficient exceeds the maximum threshold, and a first-level warning is generated.

[0032] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0033] 1. The present invention provides a support mechanism and an abutment mechanism on the sleeve body. When the sleeve body is installed inside the blast furnace tuyere sleeve, the abutment mechanism can be used to abut and limit the sleeve body from the inside of the blast furnace tuyere sleeve. At the same time, the support mechanism is fixedly installed on the outside of the blast furnace tuyere sleeve to support and fix the sleeve body, which can effectively increase the installation stability of the sleeve body, avoid shaking or instability, and effectively use the sleeve body to protect the blast furnace tuyere sleeve.

[0034] 2. The present invention predicts the service life of the casing body by comprehensively considering multiple parameters. For casings subjected to high pressure, high temperature or corrosive media, it is helpful to evaluate their safety and avoid accidents. According to the prediction results, a more scientific and reasonable maintenance plan can be formulated to avoid excessive or insufficient maintenance and reduce maintenance costs. At the same time, the production plan of the blast furnace can be reasonably arranged to avoid the impact of production due to failure of the protective casing.

[0035] 3. The present invention can obtain the supported state of the casing body in advance and discover possible safety hazards of the supported casing body in advance by predicting the support parameter set at future moments. By generating a stability coefficient according to the predicted support parameter set at future moments and dividing different warning level instructions according to a preset stability coefficient threshold, it can be convenient for staff to carry out timely inspection and maintenance, thereby ensuring the stability of the casing body installed in the blast furnace tuyere sleeve. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] 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 described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A three-dimensional diagram of a protective sleeve with a bracket mechanism according to the present invention is shown;

[0038] Figure 2 A cross-sectional view of a protective sleeve with a bracket mechanism according to the present invention is shown;

[0039] Figure 3 A schematic structural diagram of a first bracket assembly of the present invention is shown;

[0040] Figure 4 The present invention is shown Figure 2 A schematic diagram of the structure enlargement of part A;

[0041] Figure 5 A schematic diagram of the structure of the clamping ring sleeve of the present invention is shown;

[0042] Figure 6 A control system module diagram of Embodiment 2 of the present invention is shown;

[0043] Figure 7 A control system module diagram of embodiment 3 of the present invention is shown.

[0044] : Reference numerals: 100, sleeve body; 200, bracket mechanism; 201, first bracket assembly; 201a, connecting plate; 201b, L-shaped positioning rod; 201c, sliding seat; 201d, positioning bolt; 201e, connecting rod; 201f, arc-shaped clamping plate; 201g, first through hole; 202, second bracket assembly; 300, abutment mechanism; 301, clamping ring; 302, limiting hole; 303, abutment member; 304, second through hole; 400, positioning mechanism; 401, screw; 402, nut. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] Example 1

[0047] Reference Figure 1 As shown, a protective sleeve with a bracket mechanism includes: a sleeve body 100, a bracket mechanism 200, an abutment mechanism 300 and a positioning mechanism 400, wherein the sleeve body 100 is arranged as a cylindrical barrel, the bracket mechanism 200 is arranged outside the sleeve body 100 and is detachably connected to the sleeve body 100, and is used to fix and support the sleeve body 100; the abutment mechanism 300 is arranged inside the sleeve body 100, and is detachably connected to the sleeve body 100, and is used to limit the sleeve body 100; the positioning mechanism 400 is arranged at the top of the sleeve body 100, and is used to connect the bracket mechanism 200 and the abutment mechanism 300.

[0048] In this embodiment, when the sleeve body 100 is placed inside the blast furnace tuyere sleeve, the abutment mechanism 300 and the bracket mechanism 200 can be installed on the sleeve body 100 in sequence through the positioning mechanism 400, and then the abutment mechanism 300 is used to abut the inner wall of the blast furnace tuyere sleeve to limit the sleeve body 100, and then the bracket mechanism 200 is used to clamp and fix it on the outer wall of the blast furnace tuyere sleeve, thereby fixing the sleeve body 100 inside the blast furnace tuyere sleeve to prevent it from shaking, thereby effectively protecting the blast furnace tuyere sleeve.

[0049] Specifically, refer to Figure 1As shown, the positioning mechanism 400 includes: a screw rod 401 fixedly disposed at the end of the sleeve body 100 ; a nut 402 threadedly connected to the screw rod 401 for fixing the support mechanism 200 and the abutment mechanism 300 .

[0050] Specifically, refer to Figure 1 and Figure 3 As shown, the bracket mechanism 200 is composed of a first bracket assembly 201 and a second bracket assembly 202. The first bracket assembly 201 and the second bracket assembly 202 have the same structure and are symmetrically arranged. The first bracket assembly 201 includes: a connecting plate 201a, an L-shaped positioning rod 201b, a slide seat 201c, a positioning bolt 201d, a connecting rod 201e, an arc-shaped clamping plate 201f and a first through hole 201g, wherein the connecting plate 201a is arranged in an arc-shaped plate shape as a whole and fits with the end of the sleeve body 100; the L-shaped positioning rod 201b is symmetrically arranged at the top of the connecting plate 201a, and a The end extends to the side away from the connecting plate 201a; the slide 201c is slidably set on the L-shaped positioning rod 201b; the positioning bolt 201d is threadedly connected to the slide 201c, and one end extends to the inside of the slide 201c and abuts against the L-shaped positioning rod 201b; the connecting rod 201e is hinged at the lower end of the slide 201c and is vertically set to the slide 201c; the arc-shaped clamping plate 201f is hinged on one side of the connecting rod 201e and is connected to the slide 201c through the connecting rod 201e; the first through hole 201g is set through the connecting plate 201a and matches the screw 401.

[0051] In this embodiment, the first bracket assembly 201 and the second bracket assembly 202 can be respectively sleeved on the screw rod 401 through the first through hole 201g, and then fixed by the nut 402, and then the slide seat 201c is moved on the L-shaped positioning rod 201b to adjust the position of the arc clamping plate 201f. Connecting ears are provided on both sides of the arc clamping plate 201f, and connecting holes are provided on the connecting ears. The arc clamping plates 201f on the first bracket assembly 201 and the second bracket assembly 202 are brought close to each other, and the arc clamping plates 201f are connected by fastening bolts passing through the connecting holes to achieve clamping and fixing of the outer wall of the blast furnace tuyere sleeve, so that the sleeve body 100 can be fixed to prevent it from displacement or loosening in the blast furnace tuyere sleeve, and the distance between the first bracket assembly 201 and the second bracket assembly 202 can be adjusted by the slide seat 201c, so that the blast furnace tuyere sleeves with different outer diameters can be clamped, and the sleeve body 100 can be fixed, with good flexibility.

[0052] Specifically, refer to Figure 2 , Figure 4 and Figure 5As shown, the abutment mechanism 300 includes: a clamping ring sleeve 301, a limiting hole 302, an abutment member 303 and a second through hole 304, wherein the clamping ring sleeve 301 is arranged at the port of the sleeve body 100, and the clamping ring sleeve 301 is arranged in an inverted cone shape as a whole, and its upper surface matches the end of the sleeve body 100, and its lower end extends and is located inside the sleeve body 100, and abuts with the convex eaves protruding on the inner wall of the sleeve body 100, and the second through hole 304 is arranged through the upper surface of the clamping ring sleeve 301, and the clamping ring sleeve 301 is sleeved on the screw 401 through the second through hole 304; the limiting hole 302 is arranged through the side wall of the sleeve body 100; the abutment member 303 passes through the limiting hole 302, and one end abuts with the side wall of the clamping ring sleeve 301.

[0053] In the present embodiment, when the sleeve body 100 is placed inside the blast furnace tuyere sleeve, the clamping ring sleeve 301 can be sleeved on the screw rod 401 through the second through hole 304 and locked and fixed by the nut 402. While the nut 402 is locked and fixed, on the one hand, the clamping ring sleeve 301 can be used to protect the port of the sleeve body 100, thereby reducing damage to the port caused by high temperature, friction, etc., and extending the service life of the sleeve body 100. On the other hand, the side wall of the clamping ring sleeve 301 can be used to abut against one end of the abutment 303, thereby pushing one end of the abutment 303 outward, and a plurality of abutment members 303 can be used to abut and limit the inner wall of the blast furnace tuyere sleeve, thereby further limiting the sleeve body 100 and increasing its stability.

[0054] Working principle: During operation, the sleeve body 100 can be placed inside the blast furnace tuyere sleeve, and then the clamping ring sleeve 301 is sleeved on the screw rod 401 through the second through hole 304, so that one end of the clamping ring sleeve 301 extends to the inside of the sleeve body 100, and then the first bracket assembly 201 and the second bracket assembly 202 are respectively sleeved on the screw rod 401 through the first through hole 201g, and then fixed by the nut 402, and the clamping ring sleeve 301 is also fixed at the same time, and the side wall of the clamping ring sleeve 301 can be used to abut against one end of the abutment 303, so that one end of the abutment 303 is pushed outward, and a plurality of abutments 303 are used to abut and limit the inner wall of the blast furnace tuyere sleeve, so as to fix the sleeve. The main body 100 is further limited to increase the stability of the sleeve main body 100 in the blast furnace tuyere sleeve and prevent it from shaking. At the same time, the slide 201c can be used to move on the L-shaped positioning rod 201b to adjust the position of the arc clamp 201f. Connecting ears are provided on both sides of the arc clamp 201f, and connecting holes are provided on the connecting ears. The arc clamp 201f on the first bracket assembly 201 and the second bracket assembly 202 are brought close to each other, and the fastening bolts are passed through the connecting holes to connect the arc clamp 201f, so as to clamp and fix the outer wall of the blast furnace tuyere sleeve, thereby fixing the sleeve main body 100 to prevent it from displacement or loosening in the blast furnace tuyere sleeve.

[0055] Example 2

[0056] Reference Figure 6 As shown, the present invention further includes a control system based on embodiment 1, and the control system includes:

[0057] The data acquisition module collects historical training parameters of the casing body 100, which include comprehensive influencing parameters and the service life of the casing body 100. The comprehensive influencing parameters include the material, working temperature, medium type, medium flow, stress and use time of the casing body 100.

[0058] The material of the sleeve body 100 includes ceramic material, silicon carbide material, magnesium and aluminum refractory materials, etc. The hardness, thermal stability and wear resistance of the sleeve body 100 are different due to different materials, which will affect the overall service life of the sleeve body 100.

[0059] The working temperature refers to the temperature inside the sleeve body 100 during operation. High temperature will accelerate the thermal fatigue and creep process of the sleeve body 100, thereby affecting the service life. The maximum temperature, average temperature and temperature fluctuation of the working environment of the sleeve body 100 can be recorded as a reference, which can be obtained through a temperature sensor.

[0060] The medium type refers to the type of medium flowing inside the casing body 100 during operation. The medium types include oxygen, ammonia, natural gas, coal powder, etc. Different medium types cause different degrees of wear and corrosion to the inside of the casing body 100, which in turn affects the service life of the casing body.

[0061] The medium flow rate refers to the flow rate of the medium flowing through the casing body 100 per unit time. Different flow rates will cause different degrees of wear and corrosion inside the casing body 100, which will in turn affect the service life of the casing body 100. The medium flow rate can be obtained through a flow sensor.

[0062] Stress refers to the mechanical stress that the casing body 100 may be subjected to during installation and use, such as compression stress, bending stress, etc. High stress levels will accelerate the fatigue and creep process of the casing body. Therefore, the stress level is an important characteristic parameter, and stress can be obtained through a stress sensor.

[0063] The usage time refers to the cumulative usage time of the sleeve body 100 in operation. Under the condition of a certain service life, the longer the cumulative usage time is, the shorter the service life of the sleeve body is. The usage time can be obtained through the real-time monitoring system.

[0064] The material and medium type of the sleeve body 100 can be input through a screen page that interacts with the support device.

[0065] Model training module, based on historical training parameters, trains a machine learning model to predict the service life of the casing body, collects real-time comprehensive influencing parameters, and predicts the service life of the casing body based on the trained machine learning model;

[0066] The training method of the machine learning model for predicting the service life of the casing body includes:

[0067] The collected comprehensive influencing parameters are converted into a corresponding set of feature vectors.

[0068] Each group of feature vectors is used as the input of the machine learning model, and the machine learning model takes the service life of the casing body corresponding to each group of comprehensive influencing parameters as the output, and the actual service life of the casing body corresponding to each group of comprehensive influencing parameters is used as the prediction target, and minimizing the loss function value of the machine learning model is used as the training target; when the loss function value of the machine learning model is less than or equal to the preset target loss value, the training is stopped.

[0069] The machine learning model may be one of support vector machine regression, random forest regression or neural network regression models.

[0070] The loss function value of the machine learning model is the mean square error.

[0071] Mean square error is one of the commonly used loss functions. The model is trained with minimization as the goal, so that the machine learning model can better fit the data, thereby improving the performance and accuracy of the model.

[0072] In the loss function is the loss function value of the machine learning model, is the feature vector group number; is the number of eigenvector groups; For the The service life of the casing body corresponding to the group feature vector, For the The service life of the casing body corresponding to the group feature vector in real time.

[0073] Other model parameters of the machine learning model, target loss value, optimization algorithm, training set test set validation set ratio, and loss function optimization are all achieved through actual engineering implementation and continuous experimental tuning.

[0074] In this embodiment, the service life of the casing body is predicted by comprehensively considering multiple parameters, which is helpful for evaluating the safety of casing subjected to high pressure, high temperature or corrosive media and avoiding accidents. A more scientific and reasonable maintenance plan can be formulated based on the prediction results to avoid excessive or insufficient maintenance and reduce maintenance costs. In addition, the replacement and maintenance of the protective casing can be reasonably arranged to reduce unplanned downtime, and the production plan of the blast furnace can be reasonably arranged to avoid production being affected by protective casing failure.

[0075] Example 3

[0076] Reference Figure 7 As shown, the present invention further includes, based on Example 2:

[0077] The data acquisition module is used to obtain the historical support data of the support device. The historical support data includes comprehensive influencing parameters and support parameter sets. The support parameter sets are converted into support parameter numbers. The support parameter numbers are , Indicates the total number of support parameter numbers.

[0078] Specifically, the support parameter set is .

[0079] Exemplarily, when numbering the support parameter sets, , The vibration frequency, displacement and contact pressure of the casing body 100 can be respectively corresponded, wherein the contact pressure refers to the contact pressure between the casing body and the inner wall of the blast furnace tuyere sleeve. Indicates that the support parameter number is , the corresponding values ​​of the vibration frequency, displacement and contact pressure of the sleeve body 100.

[0080] Specifically, the vibration frequency, displacement and contact pressure of the sleeve body 100 can be obtained by an acceleration sensor, a displacement sensor and a pressure sensor, respectively.

[0081] The parameter prediction module trains a machine learning model to predict the support parameter number at future moments based on the comprehensive influencing parameters, and then obtains the support parameter set corresponding to the support parameter number.

[0082] Methods for training machine learning models that predict future time support parameter numbers include:

[0083] The comprehensive influencing parameters are used as the input of the multi-feature time series prediction machine learning model, and the future moment support parameter number is used as the output of the multi-feature time series prediction machine learning model. The future moment support parameter number is used as the prediction target, and minimizing the sum of prediction accuracies of all training data is used as the training target. The multi-feature time series prediction machine learning model is trained until the sum of prediction accuracies converges and the training is stopped.

[0084] The loss function value of the machine learning model is the mean square error.

[0085] Mean square error is one of the commonly used loss functions.

[0086] The model is trained with minimization as the goal, so that the machine learning model can better fit the data, thereby improving the performance and accuracy of the model.

[0087] In the loss function is the loss function value of the machine learning model, is the feature vector group number; is the number of eigenvector groups; For the The future time support parameter number corresponding to the group feature vector, For the The future time support parameter number to which the group feature vector actually corresponds.

[0088] Other model parameters of the machine learning model, target loss value, optimization algorithm, training set test set validation set ratio, and loss function optimization are all achieved through actual engineering implementation and continuous experimental tuning.

[0089] Methods for predicting future time support parameter numbers include:

[0090] Preset forecast time step , sliding step length And the sliding window length ; Use the sliding window method to convert the historical support data into multiple training samples. One training sample corresponds to one label and constitutes a set of training data. Multiple sets of training data constitute a training set. The training set is used as the input of the machine learning model to predict the time step. The future moment support parameter number is taken as the output, the subsequent support parameter number of each training set is taken as the prediction target, and the prediction accuracy is taken as the training target to train the machine learning model; a machine learning model is generated that predicts the future moment support parameter number based on the comprehensive influencing parameters.

[0091] Specifically, a simple example of the sliding window method is as follows: assuming that you want to use historical support data packets 1, 2, 3, 4, 5, 6, 7 to train a time prediction model to predict the value of one time step in the future, you can use a sliding window of length 4 and a sliding step of length 1 to generate a predicted future training set and prediction target. For example, the training sets are 1, 2, 3, 4, 2, 3, 4, 5 and 3, 4, 5, 6, and the prediction targets are 5, 6 and 7.

[0092] The sliding window method can be used to accurately and in advance predict the support parameter number at a future moment based on the existing historical support data packets in the selected scheduling area, and then obtain the support parameter set corresponding to the support parameter number, so that the process of the supporting device supporting the casing body 100 can be monitored, and the potential safety hazards of the supported casing body 100 can be discovered in advance, and accurate data support can be provided for subsequent inspection and maintenance, and there will be no lag in the status monitoring of the supported casing body 100.

[0093] The analysis module is used to generate a stability coefficient based on the predicted support parameter set at the future moment, and compare and analyze the stability coefficient with the preset stability coefficient threshold to determine and generate an early warning level instruction.

[0094] Specifically, the stability coefficient is generated as follows:

[0095] ;

[0096] In the formula, represents the stability coefficient, Indicates that the support parameter number is The vibration frequency of the casing body 100 is Indicates that the support parameter number is When the displacement of the sleeve body 100, Indicates that the support parameter number is The contact pressure of the sleeve body 100 is represents the weight coefficient, Both are greater than 0.

[0097] It should be noted that, the greater the vibration frequency and displacement of the sleeve body 100, and the smaller the relative contact pressure of the sleeve body 100, the greater the corresponding stability coefficient, and the stability of the sleeve body 100 is relatively low. Conversely, the smaller the vibration frequency and displacement of the sleeve body 100, and the greater the relative contact pressure of the sleeve body 100, the smaller the corresponding stability coefficient, and the stability of the sleeve body 100 is relatively high.

[0098] It should be noted that the formulas involved in the above-mentioned are all calculated by removing dimensions and taking numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight coefficients in the formulas and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight coefficient depends on the amount of sample data and the corresponding processing coefficients initially set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameters and the quantized values.

[0099] The stability coefficient is compared with the preset stability coefficient threshold value to determine the method of generating the warning level instruction as follows:

[0100] The warning level instructions include level one warning and level two warning, and the severity of the level one warning and level two warning decreases in sequence.

[0101] The preset stability coefficient threshold is , ,in, .

[0102] when , it means that the stability coefficient does not exceed the threshold, and no warning level instruction is generated at this time.

[0103] when When , it means that the stability coefficient exceeds the minimum threshold, and a second-level warning is generated.

[0104] when When , it means that the stability coefficient exceeds the maximum threshold, and a first-level warning is generated.

[0105] It should be noted that the first-level warning and the second-level warning can correspond to the maintenance response time respectively. When the first-level warning is generated, the staff needs to immediately inspect and maintain the casing body 100; when the second-level warning is generated, the staff can respond within the appropriate time and inspect and maintain the casing body 100.

[0106] In this embodiment, by predicting the support parameter set at a future moment, the supported state of the casing body 100 can be obtained in advance, and the potential safety hazards of the supported casing body 100 can be discovered in advance. By generating a stability coefficient based on the predicted support parameter set at a future moment, and dividing different warning level instructions according to a preset stability coefficient threshold, it is convenient for the staff to carry out timely inspection and maintenance, thereby ensuring the stability of the casing body 100 installed in the blast furnace tuyere sleeve, and further enabling the blast furnace tuyere sleeve to work stably.

[0107] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0108] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A protective sleeve with a bracket mechanism, It is characterized in that include: A casing body (100); A support mechanism (200), arranged outside the sleeve body (100) and detachably connected to the sleeve body (100), and used for fixedly supporting the sleeve body (100); an abutment mechanism (300), arranged inside the sleeve body (100), detachably connected to the sleeve body (100), and used to limit the position of the sleeve body (100); A positioning mechanism (400), arranged at the top end of the sleeve body (100), and used to connect the support mechanism (200) and the abutment mechanism (300); The abutment mechanism (300) is used to limit the position of the sleeve body (100) from the inside of the blast furnace tuyere sleeve, and the positioning mechanism (400) is used to fix and support the sleeve body (100) from the outside of the blast furnace tuyere sleeve; The support mechanism (200) is composed of a first support assembly (201) and a second support assembly (202); the first support assembly (201) and the second support assembly (202) have the same structure and are symmetrically arranged; the first support assembly (201) comprises: A connecting plate (201a) is arranged on the top end of the sleeve body (100); An L-shaped positioning rod (201b) is symmetrically arranged on the top of the connecting plate (201a), and one end of the L-shaped positioning rod extends to a side away from the connecting plate (201a); A sliding seat (201c) slidably disposed on the L-shaped positioning rod (201b); A positioning bolt (201d) is threadedly connected to the slide seat (201c), and one end of the positioning bolt extends into the interior of the slide seat (201c) and abuts against the L-shaped positioning rod (201b); A connecting rod (201e) is hinged to the lower end of the sliding seat (201c) and is arranged vertically with the sliding seat (201c); An arc-shaped clamping plate (201f) is hinged on one side of the connecting rod (201e) and is connected to the sliding seat (201c) via the connecting rod (201e); The abutment mechanism (300) comprises: A compression ring (301) is arranged at a port of the sleeve body (100); A limiting hole (302) is provided through the side wall of the sleeve body (100); The abutment member (303) passes through the limiting hole (302), and one end of the abutment member abuts against the side wall of the clamping ring sleeve (301).

2. A protective sleeve with a bracket mechanism as claimed in claim 1, It is characterized in that The positioning mechanism (400) comprises: A screw rod (401) is fixedly arranged at the end of the sleeve body (100); A nut (402) is threadedly connected to the screw rod (401) and is used to fix the connecting plate (201a) and the pressing ring sleeve (301).

3. A protective sleeve with a bracket mechanism as claimed in claim 2, It is characterized in that Also included is a control system, the control system comprising: A data acquisition module for collecting historical training parameters of the casing body (100), the historical training parameters including comprehensive influencing parameters and the service life of the casing body, the comprehensive influencing parameters including the material, working temperature, medium type, medium flow, stress and service time of the casing body (100); Model training module, based on historical training parameters, trains a machine learning model to predict the service life of the casing body, collects real-time comprehensive influencing parameters, and predicts the service life of the casing body based on the trained machine learning model; The data acquisition module is used to obtain the historical support data of the support device. The historical support data includes comprehensive influencing parameters and support parameter sets. The support parameter sets are converted into support parameter numbers. The support parameter numbers are , Indicates the total number of support parameter numbers; The parameter prediction module trains a machine learning model to predict the support parameter number at future moments based on the comprehensive influencing parameters, and then obtains the support parameter set corresponding to the support parameter number; The analysis module is used to generate a stability coefficient based on the predicted support parameter set at the future moment, and compare and analyze the stability coefficient with the preset stability coefficient threshold to determine and generate an early warning level instruction.

4. A protective sleeve with a bracket mechanism as claimed in claim 3, It is characterized in that The training method of the machine learning model for predicting the service life of the casing body includes: Convert the collected comprehensive influencing parameters into a corresponding set of feature vectors; Each group of feature vectors is used as the input of the machine learning model, and the machine learning model takes the service life of the casing body corresponding to each group of comprehensive influencing parameters as the output, and the actual service life of the casing body corresponding to each group of comprehensive influencing parameters is used as the prediction target, and minimizing the loss function value of the machine learning model is used as the training target; when the loss function value of the machine learning model is less than or equal to the preset target loss value, the training is stopped.

5. A protective sleeve with a bracket mechanism as claimed in claim 4, It is characterized in that The support parameter set is , , correspond to the vibration frequency, displacement and contact pressure of the casing body (100), respectively. Indicates that the support parameter number is , the corresponding values ​​of the vibration frequency, displacement and contact pressure of the sleeve body (100).

6. A protective sleeve with a bracket mechanism as claimed in claim 5, It is characterized in that Methods for training machine learning models that predict future time support parameter numbers include: Preset forecast time step , sliding step length And the sliding window length ; Use the sliding window method to convert the historical support data into multiple training samples. One training sample corresponds to one label and constitutes a set of training data. Multiple sets of training data constitute a training set. The training set is used as the input of the machine learning model to predict the time step. The future moment support parameter number is taken as the output, the subsequent support parameter number of each training set is taken as the prediction target, and the prediction accuracy is taken as the training target to train the machine learning; a machine learning model is generated that predicts the future moment support parameter number based on the comprehensive influencing parameters.

7. A protective sleeve with a bracket mechanism as claimed in claim 6, It is characterized in that The stability factor is generated as follows: ; In the formula, represents the stability coefficient, Indicates that the support parameter number is The vibration frequency of the casing body (100) is Indicates that the support parameter number is The displacement of the casing body (100) when Indicates that the support parameter number is The contact pressure of the casing body (100) is represents the weight coefficient, Both are greater than 0.

8. A protective sleeve with a bracket mechanism as claimed in claim 7, It is characterized in that The stability coefficient is compared with the preset stability coefficient threshold value to determine the method of generating the warning level instruction as follows: The warning level instructions include level one warning and level two warning, and the severity of the level one warning and level two warning decreases in sequence; The preset stability coefficient threshold is , ,in, ; when , it means that the stability coefficient does not exceed the threshold, and no warning level instruction is generated at this time; when When , it means that the stability coefficient exceeds the minimum threshold, and a second-level warning is generated; when When , it means that the stability coefficient exceeds the maximum threshold, and a first-level warning is generated.