Remote operation control method and system for port ship loader

Abstract

The present invention relates to the field of control technology, and specifically to a remote operation control method and system for a port ship loader; the method includes: obtaining the distance between the chute outlet and the material at each moment to construct a distance sequence, and using the distance sequence to obtain multiple real distances; obtaining the operation parameters and the real distance at the current moment, and inputting them into a prediction model to obtain a predicted time period and a predicted distance; in response to the predicted distance being less than the minimum value of the real distance, the chute is lifted to a preset height within the predicted time period. That is, the solution of the present invention can keep the distance between the chute and the shipboard material within a certain range, effectively reduce the amount of dust flying into the air, and ensure the safety of the operation.

Description

Technical Field

[0001] The present invention relates to the field of control technology, and more specifically, to a remote operation control method and system for a port ship loader. Background Art

[0002] When the loader loads bulk cargo, it usually uses a chute to unload the bulk cargo into the cabin. During this process, the dust of the bulk cargo will fly into the surrounding air, causing air pollution. At the same time, the dust will also damage the health of workers. In order to reduce dust pollution, two methods are usually used: one method is to spray water, but water spraying increases the cost, and some bulk cargo needs to be kept dry, so water spraying is not suitable. Another method is to lower the chute close to the surface of the material, reduce the falling distance of the material from the chute outlet, and reduce the dust flying into the air. When the chute is close to the surface of the material, it is easy for the chute and the material to rub or collide. When the chute is far away from the surface of the material, it is easy to generate more dust flying into the air.

[0003] A Chinese patent application document with publication number CN110077873A discloses a method and device for preventing the loader chute from colliding with the edge of the cabin. The method sets the current telescopic position and / or walking position of the telescopic arm of the ship loader as a temporary limit when the loader chute reaches any edge of the cabin around the cabin for the first time, and controls the loader chute to move within the set temporary limit to prevent the loader chute from colliding with the edge of the cabin.

[0004] However, the above solution is to prevent the chute of the ship loader from colliding with the edge of the cabin, and cannot keep the distance between the outlet of the chute and the material within a certain range, thereby reducing the amount of dust scattered into the air. Summary of the invention

[0005] The present invention proposes a remote operation control method and system for a port ship loader, which is used to solve the problem in the prior art of how to keep the distance between the outlet of the chute and the material within a certain range to reduce the amount of dust flying into the air. To this end, the present invention provides solutions in the following two aspects.

[0006] In a first aspect, the present invention provides a remote operation control method for a port ship loader, comprising the following steps:

[0007] Obtain the distance between the chute outlet and the material at each moment to construct a distance sequence, and use the distance sequence to obtain multiple real distances; obtain the current operating parameters and real distance, and input them into the prediction model to obtain the predicted time period and predicted distance;

[0008] In response to the predicted distance being less than the minimum value of the actual distance, raising the chute to a preset height within the predicted time period;

[0009] The method of using distance sequence to obtain the true distance is:

[0010] Take the minimum value in the distance sequence as the marking point, take any marking point as the center point, calculate the number of data between the remaining marking points and the center point, traverse all the remaining marking points to obtain the number sequence of the center point, and calculate the mean of all data in the number sequence;

[0011] Calculate the subordination coefficient of each remaining mark point to the center point. The subordination coefficient is positively correlated with the difference between the remaining mark points and the center point, and negatively correlated with the difference between the maximum and minimum values ​​of all the remaining mark points.

[0012] Classify the subordinate coefficients greater than 0 into multiple categories, calculate the variance of each category, and take the number of data in the category with the smallest variance as the number of subordinates of the center point;

[0013] Traverse to get the subordinate numbers of all center points, and construct a subordinate number sequence, and take the center point corresponding to the maximum value in the subordinate number sequence as the true distance.

[0014] The effect is that by controlling the lifting of the chute, the distance between the chute and the shipboard materials is within an optimal range. When loading materials, the content of dust flying into the air can be reduced, effectively protecting the working environment.

[0015] Preferably, the calculation formula of the membership coefficient of the remaining marking points to the center point is:

[0016]

[0017] In the formula, For the The membership coefficient of the marked points to the center point, is the first The number of data between the marked points and the center point, Represents the mean of all data in the number sequence, , Respectively represent The marking points and Marking points, Indicates the maximum value among the marked points. Indicates the minimum value among the points.

[0018] The effect is that by calculating the membership coefficients of the remaining marked points to the center, it is easy to delete data with large errors, thereby improving the accuracy of training the fully connected neural network.

[0019] Preferably, the distance between the chute outlet and the material is expressed as:

[0020]

[0021] in, is the distance between the chute outlet and the material surface, For the first The measuring distance of each sensor, For the ship's board The influence weight of each angle on the measured distance, is the summation function.

[0022] Preferably, the expression of the influence weight is:

[0023]

[0024] in, For the ship's board The influence weight of each angle on the measured distance, , are the horizontal and vertical coordinates of the projection point of the chute outlet axis on the horizontal plane, , For the ship's board The horizontal and vertical coordinates of the projection points of the angles on the horizontal plane, , For the ship's board The horizontal and vertical coordinates of the projection point of an angle on the horizontal plane.

[0025] The effect is that by calculating the influence weights of each corner of the ship plate and using the influence weights to process the measured data, the accuracy of the measured data is improved.

[0026] Preferably, the expression of the preset height is:

[0027]

[0028] in, For the preset height, is the predicted distance, is the distance between the chute outlet and the shipboard at the current moment, is the rising height of the materials on the ship board during the predicted time period.

[0029] The effect is that the preferred preset height can be calculated by the above formula, which makes it easier to control the lifting height of the chute, so that the distance between the chute and the ship's board is within a reasonable range, thereby reducing the amount of dust flying into the air.

[0030] Preferably, the Otsu threshold segmentation method is used to classify the subordination coefficients greater than 0 into two categories.

[0031] The effect is that by classifying the subordinate coefficients, it is easy to screen out more stable categories, thereby improving the accuracy of obtaining the true distance.

[0032] Preferably, the operation parameters include the hull mass and the real distance at the current moment, and the time period between the real distance at the current moment and the adjacent real distance.

[0033] In a second aspect, the present invention further provides a remote operation control system for a port ship loader, comprising: a processor;

[0034] The memory stores computer instructions for remote operation control of a port ship loader. When the computer instructions are executed by the processor, the system executes the above-mentioned remote operation control method of a port ship loader.

[0035] The beneficial effects of the present invention are:

[0036] 1. Input the real distance obtained in real time into the prediction model to obtain the predicted distance at the future moment. Use the predicted distance to control the distance between the chute and the shipboard material. This can keep the distance between the chute and the shipboard material within a certain range without colliding with the material, effectively reducing the amount of dust flying into the air and ensuring the safety of the operation.

[0037] 2. The solution of the present invention improves the accuracy of the prediction results of the prediction model by screening out the real distance with smaller error and training the fully connected neural network with the real distance, thereby improving the accuracy of the prediction results of the prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0039] Figure 1 A flowchart schematically shows a method for controlling remote operation of a port ship loader in this embodiment;

[0040] Figure 2 The structural block diagram of a remote operation control system of a port ship loader in this embodiment is schematically shown. DETAILED DESCRIPTION

[0041] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention. The specific implementation methods of the present invention are described in detail in combination with the drawings.

[0042] Figure 1 A flowchart of the steps of a remote operation control method of a port ship loader in this embodiment is schematically shown.

[0043] Specifically, Figure 1 As shown, a remote operation control method of a port ship loader in this embodiment includes the following steps:

[0044] S1: Obtain the distance between the chute outlet and the material at each moment to construct a distance sequence.

[0045] Four laser rangefinders are evenly installed around the chute. The rangefinder is used to measure the distance between the rangefinder and the material, so as to further calculate the distance between the chute outlet and the material. During the loading process, the hull is affected by the fluctuation of sea water, the influence of wind force or the impact of the material on the hull, causing the hull to shake, specifically left and right swing, up and down fluctuation or the superposition of the two. Therefore, it can be understood that the hull is a dynamic movement process when loading materials.

[0046] In order to improve the accuracy of measuring the distance between the chute outlet and the material surface, the influence weights of the four angles of the ship plate on the measurement results are calculated. It can also be understood as the influence of the four angles of the ship plate on the measurement results during the hull shaking process. The expression of the influence weight is:

[0047]

[0048] in, For the ship's board The influence weight of each angle on the measured distance, , are the horizontal and vertical coordinates of the projection point of the chute outlet axis on the horizontal plane, , For the ship's board The horizontal and vertical coordinates of the projection points of the angles on the horizontal plane, , For the ship's board The horizontal and vertical coordinates of the projection point of an angle on the horizontal plane.

[0049] When the ship loader is loading materials, the hull is in a dynamic shaking process, so during the measurement process, The distance from the center point of the chute outlet to the shipboard The smaller the distance between the two angles, the smaller the value is. The greater the distance that the first corner is lifted upward when shaking, in other words, the The closer the first angle is to the chute outlet than other angles, the smaller the measurement result is than the actual result. Therefore, the weight of its measurement data needs to be increased. On the contrary, the larger its value is, the smaller the corresponding first angle is. The greater the distance that each corner sinks downward when shaking, the The farther the distance between a corner and the chute outlet is compared with other corners, the larger the measurement result is than the actual result. Therefore, the weight of its measurement data needs to be reduced.

[0050] The distance between the chute outlet and the material is calculated based on the obtained influence weight. The expression is: ;in, is the distance between the chute outlet and the material surface, For the first The measuring distance of each sensor, For the ship's board The influence weight of each angle on the measured distance. When calculating the distance between the chute outlet and the material, the influence weight of each angle of the shipboard is referred to, which improves the accuracy of the measurement data.

[0051] The distance value at each moment is calculated in real time according to the above formula, and the distance sequence is constructed using the distance at each moment.

[0052] S2: Use the distance sequence to obtain multiple true distances.

[0053] When measuring the distance between the chute outlet and the material, since the hull is shaking dynamically and the shaking period is not fixed, there will be errors in the measurement process, and the errors are directly reflected in the measurement results. Therefore, it is necessary to select the real distance with smaller error.

[0054] S21: Take the minimum value in the distance sequence as the marking point, take any marking point as the center point, calculate the number of data between the remaining marking points and the center point, traverse all the remaining marking points to obtain the number sequence of the center points, and calculate the mean of all data in the number sequence.

[0055] A rectangular coordinate system is constructed with time as the horizontal axis and distance as the vertical axis. The data in the distance sequence are plotted in the coordinate system. Each data point is smoothly connected with a curve to obtain a corresponding curve. The minimum value in the distance sequence is obtained according to the curve. The minimum value in the distance sequence is used as a marking point. First, the first marking point is taken as the center point, and the number of data between the second, third, ..., nth marking point and the center point is calculated in sequence. The number sequence is constructed using the obtained number of data. Then, the second marking point is taken as the center point, and the number of data between the first, third, ..., nth marking point and the center point is calculated in sequence. The number sequence is constructed using the obtained number of data. The number sequence of the mth center point is recorded as .

[0056] S22: Calculate the subordination coefficient of each remaining marking point to the center point. The subordination coefficient is positively correlated with the difference between the remaining marking points and the center point, and negatively correlated with the difference between the maximum value and the minimum value of all the remaining marking points.

[0057] In one embodiment, the calculation formula of the membership coefficient of the remaining marking points to the center point is:

[0058]

[0059] In the formula, For the The membership coefficient of the marked points to the center point, is the first The number of data between the marked points and the center point, Represents the mean of all data in the number sequence, Indicates Marking points, Indicates A marked point, also the center point, Indicates the maximum value among the marked points. Indicates the minimum value among the marker points. The larger the membership coefficient of the marker point to the center point, the smaller the probability that the marker point has an error relative to the center point.

[0060] S23: Classify the subordination coefficients greater than 0 to obtain multiple categories, calculate the variance of each category, and take the number of data in the category with the smallest variance as the subordination number of the center point.

[0061] Delete the minimum value points with subordinate coefficients less than or equal to 0. Use the Otsu threshold segmentation method to classify the subordinate coefficients greater than 0 into two categories, and calculate the variance of the subordinate coefficients in each category. The number of data in the category with the smallest variance is taken as the number of subordinates of the center point. The smaller the variance, the smaller the difference between the subordinate coefficients and the more stable the data within the category.

[0062] S24: Traverse to obtain the subordinate numbers of all center points, and construct a subordinate number sequence, and take the center point corresponding to the maximum value in the subordinate number sequence as the true distance.

[0063] One center point corresponds to one subordinate number, which can also be understood as one marked point corresponding to one subordinate number. The subordinate numbers of all marked points are constructed into a subordinate number sequence, and a rectangular coordinate system is constructed. The horizontal axis is time and the vertical axis is the number. The data points in the number sequence are plotted in the coordinate system, and the data points are smoothly connected to obtain a curve. The maximum value is obtained according to the curve. The center point corresponding to the maximum value has a smaller error, and the corresponding center point is taken as the true distance.

[0064] S3: Obtain the current operation parameters and actual distance, and input them into the prediction model to obtain the predicted time period and predicted distance.

[0065] The method for obtaining the prediction model is as follows: construct a fully connected neural network and a training set, the training set includes multiple groups of sequences, each group of sequences includes the real distance at the same moment, the hull mass, and the time period between the previous real distance, each group of sequences is set with a label, the label is the next real distance, and the time period between the next real distance, the training set is input into the fully connected neural network for training, the loss function adopts the mean square error loss function, and the prediction model is obtained in response to the loss function value being less than a preset threshold or reaching a preset number of training times.

[0066] The current operation parameters and the real distance are input into the prediction model to obtain the predicted time period and predicted distance. It can be understood that, ideally, when the time reaches the end of the predicted time period, the real distance between the material and the shipboard material is the predicted distance, where the operation parameters include the current hull mass and the real distance, and the time period between the current time and the adjacent real distance.

[0067] S4: In response to the predicted distance being less than the minimum value of the actual distance, the chute is lifted to a preset height when the target time point is reached.

[0068] The expression for the preset height is:

[0069]

[0070] in, For the preset height, is the predicted distance, is the distance between the chute outlet and the shipboard at the current moment, is the rising height of the materials on the ship board during the predicted time period.

[0071] When the predicted distance is less than the minimum value of the actual distance, it indicates that the distance between the chute outlet and the material surface will be too small in the future. The chute outlet is prone to friction and collision with the material surface. The chute needs to be raised to ensure that the chute outlet and the material surface are kept within an optimal distance range without friction and collision with the material surface, thereby reducing the amount of dust flying into the air and effectively protecting the environment.

[0072] Figure 2 The structural block diagram of a remote operation control system of a port ship loader in this embodiment is schematically shown.

[0073] The present invention also provides a remote operation control system for a port ship loader. Figure 2 As shown, the remote operation control system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the remote operation control method of the port ship loader according to the present invention is implemented.

[0074] The remote operation control system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0075] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0076] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A remote operation control method for a port ship loader, characterized in that: The following steps are involved: Obtain the distance between the chute outlet and the material at each moment to construct a distance sequence, and use the distance sequence to obtain multiple real distances; obtain the current operating parameters and real distance, and input them into the prediction model to obtain the predicted time period and predicted distance; In response to the predicted distance being less than the minimum value of the actual distance, raising the chute to a preset height within the predicted time period; The method of using distance sequence to obtain the true distance is: Take the minimum value in the distance sequence as the marking point, take any marking point as the center point, calculate the number of data between the remaining marking points and the center point, traverse all the remaining marking points to obtain the number sequence of the center point, and calculate the mean of all data in the number sequence; Calculate the subordination coefficient of each remaining mark point to the center point. The subordination coefficient is positively correlated with the difference between the remaining mark points and the center point, and negatively correlated with the difference between the maximum and minimum values ​​of all the remaining mark points. Classify the subordinate coefficients greater than 0 into multiple categories, calculate the variance of each category, and take the number of data in the category with the smallest variance as the number of subordinates of the center point; Traverse to get the subordinate numbers of all center points, and construct a subordinate number sequence, and take the center point corresponding to the maximum value in the subordinate number sequence as the true distance.

2. A remote operation control method for a port ship loader according to claim 1, characterized in that: The calculation formula of the membership coefficient of the remaining marking points to the center point is: In the formula, For the The membership coefficient of the marked points to the center point, is the first The number of data between the marked points and the center point, Represents the mean of all data in the number sequence, , Respectively represent The distance value represented by the marker point and the The distance value represented by the marked points, Indicates the maximum value of the distance values ​​represented by the remaining marked points. Indicates the minimum value among the distance values ​​represented by the remaining markers.

3. The remote operation control method of a port ship loader according to claim 1, characterized in that: The expression of the distance between the chute outlet and the material is: in, is the distance between the chute outlet and the material surface, For the first The measuring distance of each sensor, For the ship's board The influence weight of each angle on the measured distance, is the summation function.

4. A remote operation control method for a port ship loader according to claim 3, characterized in that: The expression of influence weight is: in, For the ship's board The influence weight of each angle on the measured distance, , are the horizontal and vertical coordinates of the projection point of the chute outlet axis on the horizontal plane, , For the ship's board The horizontal and vertical coordinates of the projection points of the angles on the horizontal plane, , For the ship's board The horizontal and vertical coordinates of the projection point of an angle on the horizontal plane.

5. The remote operation control method of a port ship loader according to claim 1, characterized in that: The expression for the preset height is: in, For the preset height, To predict the distance, is the height of the material on the ship's deck during the predicted time period.

6. The remote operation control method of a port ship loader according to claim 1, characterized in that: The Otsu threshold segmentation method is used to classify the subordinate coefficients greater than 0 into two categories.

7. The remote operation control method of a port ship loader according to claim 1, characterized in that: The operation parameters include the hull mass and the real distance at the current moment, and the time period between the real distance at the current moment and the adjacent real distance.

8. A remote operation control system for a port ship loader, characterized in that: include: processor; A memory storing computer instructions of a remote operation control method for a port ship loader. When the computer instructions are executed by the processor, the system executes a remote operation control method for a port ship loader according to any one of claims 1 to 7.

Images