Method for detecting positions of pull rod and grinding roller of medium-speed coal mill
Through ultrasonic sensors and polynomial regression models, the pull rod position of the medium-speed coal mill is solved, and the problem of difficult measurement of the pull rod and grinding roller positions in the equipment is achieved, more accurate equipment status monitoring and fault warning are achieved, and production efficiency and safety are improved. sex.
Patent Information
- Application Number
- CN202411136372.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-19
- Publication Date
- 2024-11-26
AI Technical Summary
In medium-speed coal mills, it is difficult to determine the positions of the pull rods and grinding rollers through direct observation and measurement, resulting in unstable equipment operation and difficulty in predicting potential faults.
Ultrasonic sensors are used to monitor the position of the pull rod in real time, and the vibration frequency, intensity and coal seam thickness are analyzed through polynomial regression model, combined with logical judgment and data preprocessing, the position of the grinding roller is calculated and early warning or protection measures are triggered.
It significantly improves the monitoring accuracy and early warning capabilities of the equipment, ensures safety and reliability, extends the service life of the equipment, and improves the production efficiency and safety level of the coal powdering system.
Smart Images

Figure CN119016177A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of pulverizing and crushing equipment, and in particular to a method for detecting the positions of a pull rod and a grinding roller of a medium-speed coal mill. Background Art
[0002] The medium-speed coal mill is a coal mill with a working speed of 28 to 40 r / min. It is the most important large-scale equipment in the coal-to-oil pulverizing system. It is a professional equipment for the preparation and processing of auxiliary materials for blast furnace ironmaking. It can provide suitable auxiliary materials for the blast furnace ironmaking system - coal powder. This kind of coal mill occupies an important position in the coal pulverizing system. The safety and economy of its operation are crucial to the normal operation of coal pulverizing. The medium-speed coal mill is suitable for grinding medium-hard materials such as bituminous coal and lean coal. Its powder grinding operation is widely used in the pulverizing systems of the power, metallurgy, building materials, chemical industry and other industries, especially in the blast furnace coal injection pulverizing system that requires a large amount of bituminous coal. It has the characteristics of compact structure, low metal consumption, small footprint, low initial investment, low power consumption during operation, and the unit coal grinding power consumption does not increase much at low load, the noise is low, and the coal powder has good uniformity.
[0003] The tie rod of the medium-speed coal mill is a key component connecting the hydraulic loading device and the coal mill loading frame. The main function of the tie rod is to transmit the hydraulic loading force to control the grinding output of the coal mill. The grinding roller of the medium-speed coal mill is an important component of it, which is mainly responsible for squeezing and grinding the raw coal into coal powder. The material selection of the grinding roller is of great significance to improving the quality of coal powder production and extending the service life of the equipment. Common grinding roller materials include alloy cast steel grinding rollers, high chromium alloy cast iron grinding rollers and high-pressure cast iron grinding rollers.
[0004] When the coal mill is working, the position of the tie rod and the grinding roller is extremely important. Real-time monitoring of the position of the tie rod and the grinding roller can ensure that they provide key reference signals for the process links and ensure that they always operate within the predetermined safety range during the production process. Knowing the real-time position of the tie rod and the grinding roller can help operators adjust equipment parameters to ensure that the coal mill operates in the best state. For example, according to the position change of the grinding roller, the coal feed or speed of the coal mill can be adjusted to optimize the particle size distribution and output of the coal powder. However, since the grinding roller is located inside the medium-speed coal mill, it is difficult to determine its position by direct observation and measurement. Therefore, a method for detecting the position of the tie rod and the grinding roller of the medium-speed coal mill is proposed. By real-time monitoring of the tie rod position and calculating the vibration frequency, intensity, coal seam thickness and uniform distribution, the monitoring accuracy of the equipment can be significantly improved. In addition, the tie rod position data is monitored in real time, and then the current position of the grinding roller is calculated. Knowing the real-time position of the grinding roller can help predict its wear condition or potential failure. Summary of the invention
[0005] The purpose of the present invention is to monitor the position of the tie rod and the grinding roller in real time, and calculate the vibration frequency, intensity, coal seam thickness and uniformity according to the tie rod position in real time, which can significantly improve the monitoring accuracy of the equipment, and a method for detecting the tie rod and grinding roller position of a medium-speed coal mill is proposed.
[0006] In order to achieve the above object, the present invention adopts the following technical solutions:
[0007] A method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill, the detection steps are as follows:
[0008] S1: Real-time monitoring of the pull rod position;
[0009] S2: Set multiple pull rod flags and alarm and protection thresholds;
[0010] S3: Analyze the equipment status and operating conditions according to the pull rod position;
[0011] S4: Calculate the position of the grinding roller at this time according to the position of the pull rod;
[0012] S5: Visualize the position of the tie rod and rollers with the equipment status and operating conditions
[0013] The above technical solution further includes:
[0014] In S1, the position of the tie rod is monitored by an ultrasonic sensor to obtain the tie rod position data in real time.
[0015] In S2, a logical judgment is used to determine whether to trigger an alarm or protective measures. The judgment process is as follows;
[0016] Settings:
[0017] The pull rod flag position T_{\text{position}}: the pull rod position is in the lifting and lowering position within this threshold range;
[0018] Warning threshold T_{\text{warn}}: When the vibration frequency or intensity of the pull rod exceeds this threshold, a warning action is triggered;
[0019] Protection threshold T_{\text{protect}}: When the vibration frequency or intensity of the pull rod exceeds this threshold, the machine will be shut down or decelerated;
[0020] Get the data stream x_t of the pull rod position in real time;
[0021] Real-time data processing:
[0022] For each new data point x_t, perform the following steps:
[0023] ifx_t=T_{\text{position}}: report the pull rod flag position;
[0024] if x_t>T_{\text{protect}}: execute protection measures, shut down or slow down;
[0025] elif x_t>T_{\text{warn}}: Issue a warning signal.
[0026] In S3, the tie rod position data is preprocessed so that the data can be used in a polynomial regression model to analyze the equipment status and operating conditions.
[0027] The steps of data preprocessing are:
[0028] Data cleaning:
[0029] Check if there are missing values in the data set, delete and fill them, check if there are duplicate rows in the data set, delete them, identify outliers, delete and replace them, and use filters to reduce noise in the data;
[0030] Feature Engineering:
[0031] Select the tie rod position feature that is most relevant to the output variables of vibration frequency, intensity, and coal seam thickness. Tie rod position data alone is not sufficient to capture the required patterns, so new features can be created.
[0032] Data Standardization:
[0033] Standardization: convert the feature values into a distribution with a mean of 0 and a standard deviation of 1;
[0034] Formula: z=\frac{x-\mu}{\sigma}
[0035] Where mu is the mean and sigma is the standard deviation.
[0036] The steps of the polynomial regression model are:
[0037] x is the transformed feature data, and y is the parameter to be predicted;
[0038] The polynomial regression model can be expressed as:
[0039] y=\beta_0+\beta_1x+\beta_2x^2+\beta_3x^3+\ldots+\beta_nx^n'where (\beta_0,\beta_1,\ldots,\beta_n) are the coefficients of the model and n is the order of the polynomial;
[0040] Model training: Use the collected data to train a polynomial regression model;
[0041] Model evaluation: After training is completed, the performance of the model can be evaluated by calculating the error between the predicted value and the actual value, and drawing a comparison chart between the predicted curve and the actual curve;
[0042] Prediction and application: Once the model is trained and evaluated, the vibration frequency, intensity, coal seam thickness and distribution can be obtained based on the position data of the pull rod.
[0043] In S4, the position of the grinding roller is calculated. The initial angle between the tie rod and the grinding roller is θ0. The tie rod moves up and down, and the grinding roller rotates to form a new angle θ. In order to calculate this angle, the distance Δh moved by the tie rod, the rotation radius r of the grinding roller, and the distance L from the connection point between the tie rod and the grinding roller to the rotation center of the grinding roller can be obtained:
[0044] θ≈tan^-1(△h / r).
[0045] In S5, dynamic images are used to display the data of the pull rod position, vibration frequency, intensity, coal seam thickness and distribution in the coal mill, and grinding roller position in real time.
[0046] The present invention has the following beneficial effects:
[0047] 1. In the present invention, by real-time monitoring of the pull rod position and calculating the vibration frequency, intensity, coal seam thickness and uniform distribution, the monitoring accuracy, early warning capability, safety and reliability of the equipment can be significantly improved, while the operational convenience and intelligence level can be improved, which is of great significance for improving the production efficiency and safety level of industries such as thermal power generation, metallurgy and chemical industry.
[0048] 2. In the present invention, once the vibration frequency or intensity is detected to be beyond the normal range through the pull rod position, the early warning system can be triggered immediately to notify relevant personnel to conduct inspection and maintenance. This real-time early warning helps prevent equipment failure.
[0049] 3. In the present invention, the pull rod position data is monitored in real time, and then the current position of the grinding roller is calculated. Knowing the real-time position of the grinding roller can help predict its wear condition or potential failure. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] Figure 1 The present invention is a schematic diagram of the steps of a method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill. DETAILED DESCRIPTION
[0051] 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.
[0052] Embodiment 1
[0053] like Figure 1 As shown, the present invention proposes a method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill, and the detection steps are as follows:
[0054] S1: Real-time monitoring of the pull rod position;
[0055] S2: Set multiple pull rod flags and alarm and protection thresholds;
[0056] S3: Analyze the equipment status and operating conditions according to the pull rod position;
[0057] S4: Calculate the position of the grinding roller at this time according to the position of the pull rod;
[0058] S5: Visualize the position of the tie rod and grinding roller with the equipment status and operating conditions.
[0059] The working principle of the method for detecting the position of the pull rod and grinding roller of a medium-speed coal mill proposed by the present invention is to first install the sensor at the corresponding position of the hydraulic cylinder installed on the coal mill, and then monitor the position data of the pull rod in real time. After monitoring the position of the pull rod, the pull rod flag position and the alarm and protection thresholds can be set. When the pull rod position is within the flag position range, a position signal is sent. When the vibration frequency or intensity of the pull rod exceeds a specific threshold, a warning operation is triggered. When the vibration frequency or intensity of the pull rod exceeds a specific threshold, a shutdown or speed reduction operation is performed. Once the vibration frequency or intensity is detected to be beyond the normal range through the pull rod position, the early warning system can be immediately triggered to notify relevant personnel to conduct inspection and maintenance, and After that, the position data of the pull rod is preprocessed, including data cleaning, feature engineering and data standardization. Then, the vibration frequency, intensity, coal seam thickness and distribution are obtained through the polynomial regression model, which can significantly improve the monitoring accuracy, early warning capability, safety and reliability of the equipment, while improving the operational convenience and intelligence level. This is of great significance for improving the production efficiency and safety level of industries such as coal mining. Then, the position of the grinding roller is calculated based on the position data of the pull rod. Knowing the real-time position of the grinding roller can help predict its wear condition or potential failure. Then the pull rod position, vibration frequency, intensity, coal seam thickness and distribution in the coal mill, and grinding roller position data are displayed in real time.
[0060] In one embodiment, for the above S1, in S1, the position of the pull rod is monitored by an ultrasonic sensor to obtain the pull rod position data in real time.
[0061] In one embodiment, for the above S2, in S2, a logical judgment is performed to determine whether to trigger an alarm or a protective measure, and the judgment process is as follows;
[0062] Settings:
[0063] The pull rod flag position T_{\text{position}}: the pull rod position is in the lifting and lowering position within this threshold range;
[0064] Warning threshold T_{\text{warn}}: When the lever position exceeds this threshold, a warning action is triggered;
[0065] Protection threshold T_{\text{protect}}: When the pull rod position exceeds this threshold, the machine will stop or slow down;
[0066] Get the data stream x_t of the pull rod position in real time;
[0067] Real-time data processing:
[0068] For each new data point x_t, perform the following steps:
[0069] ifx_t=T_{\text{position}}: report the pull rod flag position;
[0070] if x_t>T_{\text{protect}}: execute protection measures, shut down or slow down;
[0071] elif x_t>T_{\text{warn}}: Issue a warning signal.
[0072] In one embodiment, for the above S3, in S3, data preprocessing is performed on the pull rod position data so that the data is used for a polynomial regression model to analyze the equipment status and operating conditions.
[0073] In one embodiment, for the above S3, the data preprocessing steps are:
[0074] Data cleaning:
[0075] Check if there are missing values in the data set, delete and fill them, check if there are duplicate rows in the data set, delete them, identify outliers, delete and replace them, and use filters to reduce noise in the data;
[0076] Feature Engineering:
[0077] Select the tie rod position features that are most relevant to the output variables of vibration frequency, intensity, and coal seam thickness. Tie rod position data alone is not sufficient to capture the required patterns, so new features can be created.
[0078] Data Standardization:
[0079] Standardization: convert the feature values into a distribution with a mean of 0 and a standard deviation of 1;
[0080] Formula: z=\frac{x-\mu}{\sigma}
[0081] Where mu is the mean and sigma is the standard deviation.
[0082] In one embodiment, for the above S3, the steps of the polynomial regression model are:
[0083] x is the position data of the tie rod (or the converted features), and y is the parameter to be predicted (such as vibration frequency and intensity);
[0084] The polynomial regression model can be expressed as:
[0085] y=\beta_0+\beta_1x+\beta_2x^2+\beta_3x^3+\ldots+\beta_nx^n'where (\beta_0,\beta_1,\ldots,\beta_n) are the coefficients of the model and n is the order of the polynomial;
[0086] Model training: Use the collected data to train a polynomial regression model;
[0087] Model evaluation: After training, the performance of the model can be evaluated by calculating the error between the predicted value and the actual value, and drawing a comparison chart between the predicted curve and the actual curve;
[0088] Prediction and application: Once the model is trained and evaluated, the vibration frequency, intensity, coal seam thickness and distribution can be obtained based on the position data of the pull rod.
[0089] In one embodiment, for the above S4, in S4, the position of the grinding roller is calculated, the initial angle between the pull rod and the grinding roller is θ0, the pull rod moves up and down, and the grinding roller rotates to form a new angle θ. In order to calculate this angle, the distance Δh moved by the pull rod, the rotation radius r of the grinding roller, and the distance L from the connection point between the pull rod and the grinding roller to the rotation center of the grinding roller can be obtained:
[0090] θ≈tan^-1(△h / r).
[0091] In one embodiment, for the above S5, in S5, the data of the pull rod position, vibration frequency, intensity, thickness and uniform distribution of the coal seam in the coal mill, and grinding roller position are displayed in real time through dynamic images.
[0092] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill, characterized in that: The detection steps are: S1: Real-time monitoring of the pull rod position; S2: Set multiple pull rod flags and alarm and protection thresholds; S3: Analyze the equipment status and operating conditions according to the pull rod position; S4: Calculate the position of the grinding roller at this time according to the position of the pull rod; S5: Visualize the position of the tie rod and grinding roller with the equipment status and operating conditions.
2. A method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill according to claim 1, characterized in that: In S1, the position of the tie rod is monitored by an ultrasonic sensor to obtain the tie rod position data in real time.
3. The method for detecting the position of the pull rod and grinding roller of a medium-speed coal mill according to claim 1, characterized in that: In S2, a logical judgment is used to determine whether to trigger an alarm or protective measures. The judgment process is as follows; Settings: The pull rod flag position T_{\text{position}}: the pull rod position is in the lifting and lowering position within this threshold range; Warning threshold T_{\text{warn}}: When the vibration frequency or intensity of the pull rod exceeds this threshold, a warning action is triggered; Protection threshold T_{\text{protect}}: When the vibration frequency or intensity of the pull rod exceeds this threshold, the machine will be shut down or decelerated; Get the data stream x_t of the pull rod position in real time; Real-time data processing: For each new data point x_t, perform the following steps: ifx_t=T_{\text{position}}: report the pull rod flag position; if x_t>T_{\text{protect}}: execute protection measures, shut down or slow down; elif x_t>T_{\text{warn}}: Issue a warning signal.
4. The method for detecting the position of the pull rod and the grinding roller of a medium-speed coal mill according to claim 1, characterized in that: In S3, the tie rod position data is preprocessed so that the data can be used in a polynomial regression model to analyze the equipment status and operating conditions.
5. A method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill according to claim 4, characterized in that: The steps of data preprocessing are: Data cleaning: Check if there are missing values in the data set, delete and fill them, check if there are duplicate rows in the data set, delete them, identify outliers, delete and replace them, and use filters to reduce noise in the data; Feature Engineering: Select the tie rod position features that are most relevant to the output variables of vibration frequency, intensity, and coal seam thickness. Tie rod position data alone is not sufficient to capture the required patterns, so new features can be created. Data Standardization: Standardization: convert the feature values into a distribution with a mean of 0 and a standard deviation of 1; Formula: z=\frac{x-\mu}{\sigma} Where mu is the mean and sigma is the standard deviation.
6. A method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill according to claim 4, characterized in that: The steps of the polynomial regression model are: x is the transformed feature data, and y is the parameter to be predicted; The polynomial regression model can be expressed as: y=\beta_0+\beta_1x+\beta_2x^2+\beta_3x^3+\ldots+\beta_n x^n, where (\beta_0,\beta_1,\ldots,\beta_n) are the coefficients of the model and n is the order of the polynomial; Model training: Use the collected data to train a polynomial regression model; Model evaluation: After training is completed, the performance of the model can be evaluated by calculating the error between the predicted value and the actual value, and drawing a comparison chart between the predicted curve and the actual curve; Prediction and application: Once the model is trained and evaluated, the vibration frequency, intensity, coal seam thickness and distribution can be obtained based on the position data of the pull rod.
7. A method for detecting the position of a pull rod and a grinding roller of a medium-speed coal mill according to claim 1, characterized in that: In S4, the position of the grinding roller is calculated. The initial angle between the tie rod and the grinding roller is θ0. The tie rod moves up and down, and the grinding roller rotates to form a new angle θ. In order to calculate this angle, the distance Δh moved by the tie rod, the rotation radius r of the grinding roller, and the distance L from the connection point between the tie rod and the grinding roller to the rotation center of the grinding roller can be obtained: θ≈tan^-1(△h / r).
8. The method for detecting the position of the pull rod and roller of a medium-speed coal mill according to claim 1, characterized in that: In S5, dynamic images are used to display the data of the pull rod position, vibration frequency, intensity, coal seam thickness and distribution in the coal mill, and grinding roller position in real time.
Citation Information
Cited By
Pull rod displacement feedback method and system of medium-speed coal mill
CN121155757A
