A crane operation method in a closed defocusing environment

Abstract

A crane operation method in a closed defocusing environment, which relates to the field of crane control technology, comprises the following steps: S1, model construction, establishing a regression model; S2, goodness of fit evaluation, using R² The value is used to evaluate the degree of fit of the regression model to the data; S3, using explosion-proof laser scanners and explosion-proof positioning sensors to monitor the gas concentration and combustible gas density in the coke pool in real time, and record the corresponding crane operation speed Y As the response variable; S4, estimate the regression coefficient, generate the regression equation and corresponding statistical indicators R 2 ; S5, model application and speed control, integrate the regression model into the PLC control system; based on real-time monitoring X 1 and X 2 Calculate the safe operating speed Y and adjust the motor speed to Y The present invention combines the linear regression model, real-time monitoring technology and PLC control system to provide a guarantee for the safe operation of the crane in a closed decoking environment.

Description

Technical Field

[0001] The present invention relates to the technical field of crane control, and in particular to a crane operation method in a closed defocusing environment. Background Art

[0002] As an indispensable part of the petrochemical industry chain, the coking industry has always played an important role in the energy structure. As an important petrochemical raw material, petroleum coke is widely used in metallurgy, chemical industry, building materials and other fields. With the rapid development of my country's economy and the continuous optimization of the industrial structure, the demand for petroleum coke has increased year by year, and the market potential is huge.

[0003] Traditional petroleum coke production methods have many drawbacks, especially in the high-temperature and high-pressure coking environment, where friction and collision between mechanical equipment can easily generate sparks, causing accidental explosions. As one of the mechanical equipment, cranes are at risk of causing explosions when operated in such an environment. Especially in the flammable and explosive coking environment, such risks are more significant. Therefore, it is necessary to upgrade the control technology of the crane to ensure that the crane's lifting mechanism, trolley mechanism and carriage mechanism always operate within a safe operating speed range and ensure high operating efficiency.

[0004] A Chinese patent (publication number: CN109110682A) discloses an explosion-proof stacker and an explosion-proof stacking method thereof; the patent strictly controls the speed of the entire equipment, and the operating speed in each direction does not exceed 60m / min, which meets the national safety standards for explosion-proof equipment, so that even if there is collision and friction between metals, no sparks will appear in the equipment. However, the patent cannot adjust the operating speed of each mechanism according to the explosive environment, so it cannot be applied to a closed coking environment. Summary of the invention

[0005] In order to overcome the deficiencies in the background technology, the present invention discloses a crane operation method in a closed de-coking environment.

[0006] In order to achieve the above-mentioned invention object, the present invention adopts the following technical scheme:

[0007] A crane operation method in a closed de-focusing environment comprises the following steps:

[0008] S1. Model construction: Establish a regression model, the expression is:

[0009] Y=β0+β1X1+β2X2+ε

[0010] Where Y is the running speed (m / s), X1 and X2 are the coke pool gas concentrations (g / m 3 ) and combustible gas density (kg / m 3), β0 is the intercept term, β1 and β2 are the corresponding regression coefficients, and ε represents the error term;

[0011] S2, goodness of fit assessment, using R 2 The value is used to evaluate the fitting degree of the regression model to the data; the calculation formula is:

[0012]

[0013] Among them, R 2 is the goodness of fit, SS res is the residual sum of squares of the regression model, SS tot is the total sum of squares of the regression model;

[0014] S3, data collection, using explosion-proof laser scanners and explosion-proof positioning sensors to monitor the coke pool gas concentration X1 and combustible gas density X2 in real time, and record the corresponding crane operating speed Y as the response variable;

[0015] S4. Regression analysis and parameter estimation: Use the statistical analysis tool Scikit-learn to perform linear regression analysis on the data, estimate the regression coefficients β0, β1, β2, and generate the regression equation and the corresponding statistical index R. 2 ;

[0016] S5. Model application and speed control. R calculated by regression model 2 Value, evaluate the performance of the regression model, R 2 If the value is not less than 0.85, the regression model obtained in step S4 is integrated into the PLC control system; the PLC control system calculates the safe operating speed Y based on the real-time monitored X1 and X2 values, and adjusts the motor speed to the Y value by setting the frequency converter.

[0017] Preferably, in step S2, SS res The calculation method is SS tot The calculation method is

[0018]

[0019] Preferably, in step S3, data preprocessing is performed after data collection to remove outliers and missing values, or to replace missing values ​​with the average value of adjacent time points.

[0020] Preferably, it also includes dynamic adjustment and continuous optimization, continuously monitoring X1 and X2, regularly updating the estimated regression coefficients β0, β1, β2 using steps S4 and S5; and dynamically adjusting the operating speed of the crane according to changes in the coke pool gas concentration and the combustible gas density.

[0021] Preferably, it also includes a crane operation explosion-proof system, which includes a sensor module, a data acquisition and transmission module, a data preprocessing module, a data analysis and modeling module, a model evaluation module, a control system module, a user interface and monitoring module, and a feedback and optimization module;

[0022] The sensor module is used to monitor the gas concentration and combustible gas density in the coke pool in real time; the data acquisition and transmission module is used to collect data from the sensors and transmit it to the central processing unit; the data preprocessing module is used to clean and process the raw data, remove outliers and fill in missing values; the data analysis and modeling module is used to train the regression model using historical data and calculate the regression model parameters; the model evaluation module is used to evaluate the model performance; the control system module is used to control the speed of the crane according to the model prediction results; the user interface and monitoring module is used to provide an operator interface to monitor the system status and perform manual intervention.

[0023] Preferably, the ε value in step S1 is related to the operating mechanism and working level of the crane; at working level A3, the ε value corresponding to the lifting mechanism of the crane is 0.00267~0.0267m / s, the ε value corresponding to the trolley mechanism is 0.0267~0.267m / s, and the ε value corresponding to the carriage mechanism is 0.0267~0.267m / s; at working level A4, the ε value corresponding to the lifting mechanism is 0.003~0.0333m / s, the ε value corresponding to the trolley mechanism is 0.0833~0.25m / s, and the ε value corresponding to the carriage mechanism is 0.0833~0.25m / s; at working level A5, the ε value corresponding to the lifting mechanism is 0.00667~0.0667m / s, the ε value corresponding to the trolley mechanism is 0.0267~0.267m / s, and the ε value corresponding to the carriage mechanism is 0.0267~0.267m / s.

[0024] Due to the adoption of the above-mentioned technical solution, the present invention has the following beneficial effects:

[0025] The invention discloses a crane operation method in a closed coking environment, which combines a linear regression model, a real-time monitoring technology and a PLC control system to provide a comprehensive technical solution for the safe operation of the crane at different working levels. The safe operating speed calculated by the linear regression model can be dynamically adjusted according to real-time environmental conditions, such as coke pool gas concentration and combustible gas density, to ensure that the crane always operates within a safe range. The ε value is introduced as an error term to make the model more flexible, adapt to different working environments and requirements, and improve prediction accuracy.

[0026] The present invention further cleans the collected data, removes outliers, and fills in missing values ​​to ensure the accuracy of subsequent analysis.

[0027] The present invention further establishes an automated update mechanism to regularly evaluate system performance and update regression model parameters based on the latest data to ensure the long-term performance and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 Block diagram of an explosion protection system for a crane operation. DETAILED DESCRIPTION

[0029] The present invention can be explained in detail through the following embodiments. The purpose of disclosing the present invention is to protect all technical improvements within the scope of the present invention. In the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "front", "back", "left", "right", etc. indicating directions or positional relationships, they only correspond to the drawings of the present application for the convenience of describing the present invention, and do not indicate or imply that the device or element referred to must have a specific direction.

[0030] Embodiment 1, a crane operation method in a closed decoking environment, comprising the following steps:

[0031] S1. Model construction: Establish a regression model, the expression is:

[0032] Y=β0+β1X1+β2X2+ε

[0033] Where Y is the running speed (m / s), X1 and X2 are the coke pool gas concentrations (g / m 3 ) and combustible gas density (kg / m 3 ), β0 is the intercept term, β1 and β2 are the corresponding regression coefficients, and ε represents the error term; ε is related to the crane's operating mechanism and working level; at working level A3, the ε value corresponding to the crane's lifting mechanism is 0.00267~0.0267m / s, the ε value corresponding to the trolley mechanism is 0.0267~0.267m / s, and the ε value corresponding to the trolley mechanism is 0.0267~0.267m / s; at working level A4, the ε value corresponding to the lifting mechanism is The value is 0.003~0.0333m / s, the ε value corresponding to the trolley mechanism is 0.0833~0.25m / s, and the ε value corresponding to the carriage mechanism is 0.0833~0.25m / s; at working level A5, the ε value corresponding to the lifting mechanism is 0.00667~0.0667m / s, the ε value corresponding to the trolley mechanism is 0.0267~0.267m / s, and the ε value corresponding to the carriage mechanism is 0.0267~0.267m / s.

[0034] S2, goodness of fit assessment, using R 2 The value is used to evaluate the fitting degree of the regression model to the data; the calculation formula is:

[0035]

[0036] Among them, R 2 is the goodness of fit, which indicates the proportion of the variation explained by the model to the total variation. SS res is the residual sum of squares of the regression model, which represents the difference between the predicted value and the actual value, SS res The calculation method is SS tot is the total sum of squares of the regression model, indicating the difference between the actual value and its mean value, SS tot The calculation method is

[0037] S3, data collection, deploy explosion-proof laser scanners and explosion-proof positioning sensors on site, use explosion-proof laser scanners and explosion-proof positioning sensors to monitor the coke pool gas concentration X1 and combustible gas density X2 in real time, and record the corresponding crane running speed Y as the response variable; ensure that the sensors used have high precision and low latency, and meet explosion-proof standards to adapt to hazardous environments; set a reasonable data collection frequency to ensure the timeliness and accuracy of the data. In order to improve the reliability of the regression model, data preprocessing is performed after data collection to remove outliers and missing values, or replace missing values ​​with the average value of adjacent time points.

[0038] S4. Regression analysis and parameter estimation: Use the statistical analysis tool Scikit-learn to perform linear regression analysis on the data, estimate the regression coefficients β0, β1, β2, and generate the regression equation and the corresponding statistical index R. 2 ;

[0039] S5. Model application and speed control. R calculated by regression model 2 Value, evaluate the performance of the regression model, R 2 If the value is not less than 0.85, the regression model obtained in step S4 is integrated into the PLC control system; the PLC control system calculates the safe operating speed Y based on the real-time monitored X1 and X2 values, and adjusts the motor speed to the Y value by setting the frequency converter to ensure that the crane operating speed remains within a safe range to avoid the risk of detonation.

[0040] In order to further improve the adaptability, it is necessary to dynamically adjust and continuously optimize the regression model, continuously monitor X1 and X2, and regularly use steps S4 and S5 to update the estimated regression coefficients β0, β1, β2; for example, update the estimated regression coefficients β0, β1, β2 every 5 to 10 minutes; dynamically adjust the operating speed of the crane according to the changes in the coke pool gas concentration and the combustible gas density.

[0041] This embodiment is carried out in the explosion-proof system of crane operation, as shown in the attached Figure 1As shown, the crane operation explosion-proof system includes a sensor module, a data acquisition and transmission module, a data preprocessing module, a data analysis and modeling module, a model evaluation module, a control system module, a user interface and monitoring module, and a feedback and optimization module;

[0042] The sensor module is used to monitor the gas concentration and combustible gas density in the coke pool in real time. The sensor module includes an explosion-proof laser scanner and an explosion-proof positioning sensor. The data acquisition and transmission module is used to collect data from the sensor and transmit it to the central processing unit. The data acquisition and transmission module includes a data acquisition card and a wireless or wired communication network. The data preprocessing module is used to clean and process the raw data, remove outliers and fill in missing values. The data analysis and modeling module is used to train the regression model using historical data and calculate the regression model parameters. The model evaluation module is used to evaluate the model performance. The control system module is used to control the speed of the crane according to the model prediction results. The user interface and monitoring module is used to provide an operator interface to monitor the system status and perform manual intervention.

[0043] Example 2, a crane operation method in a closed coke removal environment, setting the crane working level to A3, coke pool gas concentration X1: range from 0 to 5 g / m 3 Combustible gas density X2: ranges from 0.5 to 2 kg / m 3 Between; a linear regression model was trained using historical data and the following regression coefficients were obtained:

[0044] β0 is 1.5, β1 is -0.2, and β2 is -0.8;

[0045] The resulting regression model is:

[0046] Y=1.5-0.2X1-0.8X2+ε

[0047] Among them, the ε value corresponding to the lifting mechanism of the crane is 0.0167m / s, the ε value corresponding to the trolley mechanism is 0.0833m / s, and the ε value corresponding to the trolley mechanism is 0.1333m / s;

[0048] At a certain moment, the data was collected:

[0049] X1=3.0g / m 3 ; X2=1.2kg / m 3 ;

[0050] According to the regression model, it can be calculated that at this time the operating speed of the crane's lifting mechanism should be controlled within 0.5567m / s, the operating speed of the trolley mechanism should be controlled within 0.6233m / s, and the operating speed of the carriage mechanism should be controlled within 0.6733m / s.

[0051] The parts of the present invention that are not described in detail are prior art. It is obvious to those skilled in the art that the present invention is not limited to the details of the above-mentioned exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention; therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive, and it is intended that all changes that fall within the meaning and scope of equivalent elements are included in the present invention.

Claims

1. A crane operation method in a closed de-focusing environment, characterized in that: The following steps are involved: S1. Model construction: Establish a regression model, the expression is: Y=β0+β1X1+β2X2+ε Where Y is the running speed (m / s), X1 and X2 are the coke pool gas concentrations (g / m 3 ) and combustible gas density (kg / m 3 ), β0 is the intercept term, β1 and β2 are the corresponding regression coefficients, and ε represents the error term; S2, goodness of fit assessment, using R 2 The value is used to evaluate the fitting degree of the regression model to the data; the calculation formula is: Among them, R 2 is the goodness of fit; SS res is the residual sum of squares of the regression model; SS tot is the total sum of squares of the regression model; S3, data collection, using explosion-proof laser scanners and explosion-proof positioning sensors to monitor the coke pool gas concentration X1 and combustible gas density X2 in real time, and recording the corresponding crane operating speed Y as the response variable; S4. Regression analysis and parameter estimation: Use the statistical analysis tool Scikit-learn to perform linear regression analysis on the data, estimate the regression coefficients β0, β1, β2, and generate the regression equation and the corresponding statistical index R. 2 ; S5. Model application and speed control. R calculated by regression model 2 Value, evaluate the performance of the regression model, R 2 If the value is not less than 0.85, the regression model obtained in step S4 is integrated into the PLC control system; the PLC control system calculates the safe operating speed Y based on the real-time monitored X1 and X2 values, and adjusts the motor speed to the Y value by setting the frequency converter.

2. The crane operation method in a closed decoking environment according to claim 1, characterized in that: In step S2, SS res The calculation method is SS tot The calculation method is 3. The crane operation method in a closed decoking environment according to claim 1, characterized in that: In step S3, data preprocessing is performed after data collection to remove outliers and missing values, or to replace missing values ​​with the average value of adjacent time points.

4. The crane operation method in a closed decoking environment according to claim 1, characterized in that: It also includes dynamic adjustment and continuous optimization, continuously monitoring X1 and X2, and regularly updating the estimated regression coefficients β0, β1, β2 using steps S4 and S5; dynamically adjusting the operating speed of the crane according to changes in the coke pool gas concentration and the combustible gas density.

5. The crane operation method in a closed decoking environment according to claim 1, characterized in that: It also includes a crane operation explosion-proof system, which includes a sensor module, a data acquisition and transmission module, a data preprocessing module, a data analysis and modeling module, a model evaluation module, a control system module, a user interface and monitoring module, and a feedback and optimization module; The sensor module is used to monitor the coke pool gas concentration and combustible gas density in real time; The data acquisition and transmission module is used to collect data from sensors and transmit it to the central processing unit; the data preprocessing module is used to clean and process raw data, remove outliers and fill missing values; the data analysis and modeling module is used to train regression models using historical data and calculate regression model parameters; The model evaluation module is used to evaluate the model performance; the control system module is used to control the speed of the crane according to the model prediction results; The user interface and monitoring module is used to provide an operator interface to monitor system status and perform manual intervention.

6. The crane operation method in a closed decoking environment according to claim 1, characterized in that: The ε value in step S1 is related to the operating mechanism and working level of the crane; at working level A3, the ε value corresponding to the lifting mechanism of the crane is 0.00267~0.0267m / s, the ε value corresponding to the trolley mechanism is 0.0267~0.267m / s, and the ε value corresponding to the carriage mechanism is 0.0267~0.267m / s; at working level A4, the ε value corresponding to the lifting mechanism is 0.003~0.0333m / s, the ε value corresponding to the trolley mechanism is 0.0833~0.25m / s, and the ε value corresponding to the carriage mechanism is 0.0833~0.25m / s; at working level A5, the ε value corresponding to the lifting mechanism is 0.00667~0.0667m / s, the ε value corresponding to the trolley mechanism is 0.0267~0.267m / s, and the ε value corresponding to the carriage mechanism is 0.0267~0.267m / s.

Images