Construction state self-learning formation judging and speed control system and method

Abstract

The application relates to a construction state self-learning stratum judgment and speed control system and method, which is particularly suitable for a rock milling process in underground continuous wall construction such as a double-wheel slot milling machine, a double-wheel milling and mixing machine and the like, and mainly comprises a self-learning operation network, a milling wheel state detection, a milling speed control and a man-machine interactive interface. The construction state self-learning stratum judgment and speed control system can integrate sample data of multiple construction states, automatically judges the geological condition of the current project by means of a multivariate self-learning operation network, assists a construction personnel in automatically controlling the milling speed, and can effectively protect a speed reducer.

Description

TECHNICAL FIELD

[0001] The application relates to a construction state self-learning stratum judgment and speed control system and method, and belongs to the technical field of engineering machinery control. BACKGROUND

[0002] In construction, the feeding speed of underground continuous wall equipment, especially a double-wheel trenching machine and a double-wheel trenching mixer, needs to be adjusted in real time according to different strata. The feeding speed needs to be increased for soft strata to seek maximum efficiency, and the feeding speed needs to be appropriately reduced for hard strata to protect the hydraulic system, especially the rapid temperature rise of the motor and the speed reducer when working under large torque. Because the stratum structure cannot be accurately judged, the current construction process is to observe the state of the milling wheel, including the values of a milling wheel position sensor, a milling wheel feeding speed sensor, a milling wheel pressure sensor, a milling wheel temperature sensor and a milling wheel rotating speed sensor, to manually judge and control the feeding speed according to previous construction experience. SUMMARY

[0003] The application aims to automatically judge the geological conditions of the current project, and to assist the construction personnel in automatically controlling the milling speed, thereby reducing human intervention in the construction process.

[0004] To solve the above problems, the technical scheme adopted by the application is as follows: a construction state self-learning stratum judgment and speed control system, comprising:

[0005] a milling wheel state detection module, used to collect the milling wheel position, the milling wheel feeding speed, the milling wheel pressure, the milling wheel temperature and the milling wheel rotating speed;

[0006] a man-machine interactive interface, used to give the Proctor's coefficient of different positions and different strata and to display the milling wheel feeding speed;

[0007] a self-learning operation network, used to save sample data of multiple construction states under multiple strata, each sample including the values of the milling wheel position, the milling wheel pressure, the milling wheel rotating speed, the milling wheel temperature, the feeding speed and the Proctor's coefficient given by the man-machine interactive interface for different positions and different strata, and used to calculate the target feeding speed of the milling wheel under different Proctor's coefficients according to the sample data;

[0008] a feeding speed control module, used to control the current milling wheel feeding speed at the target feeding speed of the milling wheel under the current Proctor's coefficient.

[0009] Further, the milling wheel state detection module comprises a milling wheel position sensor, a milling wheel feeding speed sensor, a milling wheel pressure sensor, a milling wheel temperature sensor and a milling wheel rotating speed sensor.

[0010] Further, the self-learning operation network comprises a data storage module, which is used to save sample data of multiple construction states under multiple strata.

[0011] Further, the self-learning operation network further comprises a multivariate data fusion module, which is configured to establish a coordinate relationship between each of the multivariate, and fuse the sample data of the multiple formation construction states saved in the data storage module into the coordinate relationship to generate a function relationship between different variables.

[0012] Further, the self-learning operation network further comprises a data operation module, which is configured to bring the current construction data in the form of variables into the function of the multivariate data fusion module to calculate the target feed speed of the milling wheel under different Protodyakonov coefficients.

[0013] Further, the multivariate data fusion module arranges and combines two of the six variables of the sample to form a coordinate relationship, and the six variables generate a coordinate relationship. With the increase of the number of samples, the number of sampling points on the coordinate system increases on each coordinate relationship. A certain multiple function is used to fit the distribution trajectory of the sampling points to describe the relationship between the two variables.

[0014] Further, the feed speed control module comprises a controller, a winch flow valve, a winch back pressure valve and a winch motor. The controller sends the target feed speed of the milling wheel under different Protodyakonov coefficients calculated by the data operation module to the human-computer interaction interface and displays it. According to the target feed speed of the milling wheel under different Protodyakonov coefficients calculated by the data operation module, the controller outputs a control signal to adjust the hydraulic system winch flow valve, winch back pressure valve and winch motor to control the current milling wheel feed speed to keep at the target feed speed of the milling wheel under the current Protodyakonov coefficient.

[0015] Correspondingly, a construction state self-learning formation judgment and speed control method comprises:

[0016] Given the Protodyakonov coefficients of different positions and different formations;

[0017] Collect the milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature and feed speed of multiple construction states under multiple formations;

[0018] Save the milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature, feed speed of multiple construction states under multiple formations and the given Protodyakonov coefficients of different positions and different formations as sample data;

[0019] Establish a coordinate relationship between each of the milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature, feed speed and the given Protodyakonov coefficients of different positions and different formations to generate a function relationship between different variables. Bring the current construction data in the form of variables into the function relationship to calculate the target feed speed of the milling wheel under different Protodyakonov coefficients.

[0020] According to the target feed speed of the milling wheel under different Proskauer coefficients, the winch flow valve, winch back pressure valve and winch motor are controlled to control the current milling wheel feed speed at the target feed speed of the milling wheel under the current Proskauer coefficient.

[0021] Furthermore, the process of generating the functional relationship between different variables is as follows: take two of the six variables in the sample, perform permutations and combinations, and form a coordinate relationship. The six variables are generated. Coordinate relationships, in each coordinate relationship, as the number of samples increases, the number of sampling points on the coordinate system increases; a certain multi-time function is used to fit the distribution trajectory of the sampling points to describe the relationship between the two variables.

[0022] Accordingly, a computing device includes:

[0023] One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the above method.

[0024] The beneficial effects achieved by the present invention are:

[0025] The present invention uses a multivariable self-learning operation network to automatically judge the geological conditions of the current project, assist construction personnel in automatically controlling the milling speed, and effectively protect the reducer. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A principle block diagram provided according to an embodiment of the present invention.

[0027] Figure 1 In the figure, the respective reference numerals represent: 1. milling wheel status detection module; 2. human-computer interaction interface module; 3. self-learning operation network; 4. feed speed control module. DETAILED DESCRIPTION

[0028] like Figure 1 The present invention provides a construction status self-learning stratum judgment and speed control system, which includes a self-learning operation network, milling wheel status detection, feed speed control and a human-computer interaction interface.

[0029] During construction, it is necessary to first collect data from multiple construction status samples in various strata, including values ​​from the milling wheel position sensor, milling wheel feed speed sensor, milling wheel pressure sensor, milling wheel temperature sensor, and milling wheel speed sensor. At the same time, a human-computer interface is used to generate Proctor coefficients for different locations and strata.

[0030] The self-learning computing network stores, integrates and computes sample data. Specifically:

[0031] The data storage module is used to save sample data of multiple construction states under multiple strata, each sample including the values of the milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature, feed speed and the given Proctor coefficient of different positions and different strata by the human-computer interaction interface.

[0032] The multivariate data fusion module respectively establishes coordinate relationships among multiple variables, and fuses the sample data of the construction states under multiple strata saved in the data storage module into the coordinate relationships to generate function relationships among different variables.

[0033] The data operation module can bring the current construction data in the form of variables into the functions of the multivariate data fusion module to calculate the target feed speed of the milling wheel under different Proctor coefficients.

[0034] The fusion process of the multivariate data fusion module is to arrange and combine two of the six variables of the sample to form a coordinate relationship, and six variables generate In each coordinate relationship, the number of sampling points on the coordinate system increases with the increase of the number of samples. When the number of sampling points is large enough, the distribution of the sampling points in the coordinate system can be observed, and then a certain multiple function is used to fit the distribution trajectory of the sampling points to describe the relationship between the two variables.

[0035] For example, under a certain milling wheel position, milling wheel speed, milling wheel temperature and Proctor coefficient variable, the coordinate relationship between the milling wheel pressure and the feed speed can be established. With the increase of the number of samples, the inverse proportional function can be used to describe the function relationship between the milling wheel pressure and the feed speed, that is, p=kf(v), k is the slope, and the value is negative. The slower the feed speed, the greater the milling wheel pressure.

[0036] Because the system is a non-time discrete system and the logic is relatively simple, a basic function, a quadratic function or a cubic function can basically complete the fitting. The fitting process is to draw a curve within a certain deviation range, and the deviation range of the curve should cover as many sampling points as possible. The multiple function is deduced from the drawn curve, and it can be determined that this function can completely describe the relationship between the two variables.

[0037] A large number of sampling data can generate functions among multiple variables after passing through the multivariate data fusion module. In the current construction data, if the milling wheel position, milling wheel speed, milling wheel temperature and milling wheel pressure are taken as input variables and brought into these functions, the target feed speed of the milling wheel under different Proctor coefficients can be calculated.

[0038] The feed speed control includes a controller, a hoist flow valve, a hoist back pressure valve and a hoist motor.

[0039] The controller sends the target feeding speed calculated by the data operation module and the Plouffe coefficient to a human-computer interaction interface and displays.

[0040] The controller outputs a control signal according to the target feeding speed calculated by the data operation module, adjusts the hydraulic system winch flow valve, the winch back pressure valve and the winch motor, and controls the current milling wheel feeding speed at the target feeding speed of the milling wheel under the current Plouffe coefficient.

[0041] The above only describes the preferred embodiments of the present application, and it should be noted that those skilled in the art can make some improvements and modifications without departing from the technical principles of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.

[0042] A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions which, when executed by a computing device, cause the computing device to perform a construction state self-learning formation determination and speed control method.

[0043] A computing device comprising one or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, and the one or more programs comprise instructions for performing a construction state self-learning formation determination and speed control method.

[0044] Those skilled in the art will appreciate that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer usable program code.

[0045] The present application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the computer or other programmable data processing apparatus produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 An apparatus for performing the function specified in one or more flows and / or blocks. Figure 1 An apparatus for performing the function specified in one or more flows and / or blocks.

[0046] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 one or more flow or block Figure 1 one or more blocks or blocks specified in the flow.

[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that are executed on the computer or other programmable apparatus provide steps for implementing the flow Figure 1 one or more flow or block Figure 1 one or more blocks or blocks specified in the flow.

[0048] The above merely provides an embodiment of the present application, but is not intended to limit the present application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims

1. A construction status self-learning stratum judgment and velocity control system, characterized in that: include: Milling wheel status detection module, used to collect milling wheel position, milling wheel feed speed, milling wheel pressure, milling wheel temperature and milling wheel speed; Human-computer interaction interface, used to set the Proctor coefficient at different locations and formations and display the milling wheel feed speed; The self-learning computing network is used to store sample data of multiple construction conditions in various strata. Each sample includes the values ​​of milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature, feed speed, and the Proctor coefficient given by the human-computer interface for different positions and different strata; And according to the sample data, the target feed speed of the milling wheel under different Proctor coefficients is obtained; A feed speed control module is used to control the current milling wheel feed speed to the target feed speed of the milling wheel under the current Proctor coefficient; The self-learning operation network includes a data storage module, which is used to store sample data of multiple construction states under multiple strata; The self-learning operation network further includes a multivariate data fusion module, which is used to establish coordinate relationships between multiple variables, integrate sample data under various subsurface construction conditions stored in the data storage module into the coordinate relationships, and generate functional relationships between different variables; The self-learning operation network further includes a data operation module, which is used to bring the current construction data into the function of the multivariable data fusion module in the form of variables, and calculate the target feed speed of the milling wheel under different Proctor coefficients; The multivariate data fusion module takes two of the six variables of the sample and arranges and combines them to form a coordinate relationship. The six variables are generated Coordinate relationships, in each coordinate relationship, as the number of samples increases, the number of sampling points on the coordinate system increases; use a multi-time function to fit the distribution trajectory of the sampling points to describe the relationship between the two variables.

2. A construction status self-learning stratum judgment and velocity control system according to claim 1, characterized in that: The milling wheel state detection module includes a milling wheel position sensor, a milling wheel feed speed sensor, a milling wheel pressure sensor, a milling wheel temperature sensor and a milling wheel rotation speed sensor.

3. A construction status self-learning stratum judgment and velocity control system according to claim 1, characterized in that: The feed speed control module includes a controller, a winch flow valve, a winch back pressure valve and a winch motor; the controller sends the target feed speed of the milling wheel under different Proskauer coefficients calculated by the data calculation module to the human-computer interaction interface and displays it; and the controller outputs a control signal according to the target feed speed of the milling wheel under different Proskauer coefficients calculated by the data calculation module, adjusts the hydraulic system winch flow valve, winch back pressure valve and winch motor, and controls the current milling wheel feed speed to maintain the target feed speed of the milling wheel under the current Proskauer coefficient.

4. A method for self-learning formation judgment and speed control of construction status, characterized in that: include: Given different locations and different formations, the Proctor coefficient; Collect milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature and feed speed in multiple construction states under various strata; The milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature, feed speed and Proctor coefficient of different positions and different formations under multiple construction conditions in various formations are saved as sample data; Establish coordinate relationships among milling wheel position, milling wheel pressure, milling wheel speed, milling wheel temperature, feed speed, and given Proctor coefficients at different locations and formations, and generate functional relationships among different variables. Substitute the current construction data into the function relationship in the form of variables, and calculate the target feed speed of the milling wheel under different Proctor coefficients; According to the target feed speed of the milling wheel under different Proctor coefficients, the hoist flow valve, hoist back pressure valve and hoist motor are controlled to control the current milling wheel feed speed to the target feed speed of the milling wheel under the current Proctor coefficient; The process of generating the functional relationship between different variables is as follows: take two of the six variables in the sample, arrange and combine them, and form a coordinate relationship. The six variables are generated. Coordinate relationships, in each coordinate relationship, as the number of samples increases, the number of sampling points on the coordinate system increases; use a multi-time function to fit the distribution trajectory of the sampling points to describe the relationship between the two variables.

5. A computing device, characterized in that include: One or more processors, one or more memories, and one or more programs, wherein the one or more programs are stored in the one or more memories and configured to be executed by the one or more processors, the one or more programs comprising instructions for executing the method according to claim 4.

Images