Mining AGV intelligent carrying control method and system

Abstract

The invention discloses a mining AGV intelligent carrying control method and system, and particularly relates to the technical field of mining AGVs, and the method comprises the steps: dividing a target management region into i mining sub-regions, and enabling each mining sub-region to correspond to a mining AGV; obtaining task allocation training data of i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data comprises load feature data and an initial load value corresponding to the load feature data; training a load prediction model for predicting an initial load value based on the task allocation training data; the coal mine transportation condition is analyzed in real time according to the real-time transportation monitoring data, the load adjustment value is accurately determined, the situation that the coal mine transportation efficiency is low due to the fact that the load value of the mining AGV is too large or too small is avoided, the load adjustment value is accurately determined, and then it is helpful for ensuring task allocation balance of the mining AGV and improving the transportation efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of mining AGVs, and more specifically, to a mining AGV intelligent handling control method and system. Background Art

[0002] With the continuous development of automation technology, automatic guided vehicles (AGVs) have been widely used in industries, warehousing, and mining transportation. In the mining field, through intelligent systems for monitoring, coordination, and management, mining automatic guided vehicles (AGVs) can manage different types of mining AGVs, so that these mining AGVs can autonomously complete the transportation of coal mines, thereby maximizing production efficiency and reducing labor burden. However, with the development of society, various types of automatic guided vehicles are being used more and more widely; traditional automatic guided vehicle task allocation methods are more concerned with the use of static task allocation strategies, and are unable to flexibly adjust task allocation according to the real-time environment and the operating status of mining AGVs, resulting in low efficiency; therefore, it is necessary to provide a novel intelligent task allocation method for mining AGVs to achieve intelligent and dynamic management of various types of mining AGVs.

[0003] At present, the existing methods can realize the dynamic scheduling and coordination of multiple AGVs to achieve optimal task allocation. For example, the application document with publication number CN115373349A discloses a method and system for scheduling a mobile handling robot. Although the above method can realize the task allocation of mining AGVs, the efficiency of mining AGVs in transporting coal mines is improved, but there are also some defects and problems in actual use, such as: 1. Before the mining AGV transports coal, the load value of the mining AGV is not predicted, so that during the transportation process, the load value is controlled only by human judgment, resulting in the load value being too large or too small, affecting the efficiency of coal transportation; 2. When transporting coal, the mining AGV did not adjust the load value accurately according to the progress of transporting coal, which reduced the efficiency of coal transportation.

[0004] To this end, the present invention provides a mining AGV intelligent handling control method and system. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a mining AGV intelligent handling control method and system to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a mining AGV intelligent handling control method, comprising: Divide the target management area into i mining sub-areas, each of which corresponds to a mining AGV; obtain task allocation training data of i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; A load prediction model is trained to predict the initial load value based on the task allocation training data; The initial load value predicted by the trained load prediction model is used as the current load value of the mining AGV, and the coal mine in the mining sub-area is transported, and the transportation monitoring data of the i-th mining AGV is collected in real time; the transportation monitoring data of the mining AGV is extracted, and the transportation monitoring threshold of the i-th mining AGV is obtained to analyze the transportation monitoring data to obtain the transportation evaluation coefficient; Setting a transport assessment coefficient threshold, comparing the transport assessment coefficient with the transport assessment coefficient threshold, and obtaining load adjustment information according to the comparison result; According to the load adjustment information, the current load value of the mining AGV corresponding to each mining sub-area is extracted, and the load adjustment value of the corresponding mining AGV is generated based on the current load value corresponding to the mining AGV.

[0007] Furthermore, the method for obtaining task allocation training data of i mining AGVs is as follows: The load characteristic data includes coal volume, coal weight and center of gravity inclination angle; The volume of the coal mine is obtained by scanning the identification code of the coal mine with the camera of the mining AGV; the weight of the coal mine is obtained by the gravity sensor installed in the mining AGV; the inclination angle of the center of gravity is obtained in real time by the inclination sensor installed in the mining AGV, which measures the inclination angle of the center of gravity when the mining AGV transports the coal mine; The initial load value is obtained by measuring a load sensor installed on the mining AGV, that is, when the load characteristic data is obtained, the initial load value of the corresponding mining AGV is obtained by measuring the load sensor at the same time.

[0008] Furthermore, a load prediction model for predicting the initial load value is trained based on the task allocation training data, and the training method is: Each set of load characteristic data is used as the input of the load prediction model. The load prediction model takes the initial load value corresponding to each set of load characteristic data as output, takes the initial load value corresponding to the load characteristic data in the task allocation training data as the prediction target, and takes minimizing the prediction error of all initial load values ​​as the training target; the load prediction model is trained until the prediction error reaches convergence, and the training is stopped to train a load prediction model that predicts the initial load value according to the load characteristic data output; the load prediction model is a polynomial regression model or a SVM model.

[0009] Furthermore, the transport monitoring data includes the real-time power, operation time and failure rate of the mining AGV, and the transport monitoring threshold includes the power threshold, the operation time threshold and the failure rate threshold; The real-time power consumption is obtained by the power monitoring equipment installed on the mining AGV; the operating time is obtained by obtaining the startup and shutdown time of the mining AGV through the data log of the mining AGV, and calculating the time interval between the startup and shutdown time; the failure rate is the number of failure events of the mining AGV per unit time; the unit time includes days, weeks or years.

[0010] Furthermore, the method of obtaining the transportation monitoring threshold of the i-th mining AGV to analyze the transportation monitoring data includes: Calculate the absolute value of the power difference between the real-time power of each mining AGV and the power threshold, and use the absolute value of the power difference as the power evaluation coefficient; Calculate the absolute value of the difference between the running time of each mining AGV and the running time threshold, and use the absolute value of the running time difference as the running time evaluation coefficient; Calculate the absolute value of the failure rate difference between the failure rate of each mining AGV and the failure rate threshold, and use the absolute value of the failure rate difference as the failure rate evaluation coefficient; Based on the ambient temperature and humidity of the mining sub-area corresponding to the i-th mining AGV, the power evaluation coefficient, the operating time evaluation coefficient, and the failure rate evaluation coefficient are dimensionlessly quantified and calculated in a formula to obtain the transportation evaluation coefficient. , and its calculation formula is: ; In the formula, is the transportation evaluation coefficient of the i-th mining AGV, is the power evaluation coefficient of the i-th mining AGV, is the operating time evaluation coefficient of the i-th mining AGV, is the failure rate evaluation coefficient of the i-th mining AGV, is the ambient temperature of the mining sub-area corresponding to the i-th mining AGV, is the ambient humidity of the mining sub-area corresponding to the i-th mining AGV, represents the power weight of the i-th mining AGV, represents the running time weight of the i-th mining AGV, represents the failure rate weight of the i-th mining AGV, represents the ambient temperature weight of the i-th mining AGV, represents the environmental humidity weight of the i-th mining AGV, , , , and All are greater than zero, and C is a preset constant; A temperature sensor and a humidity sensor are installed in the mining sub-area corresponding to the i-th mining AGV, and the ambient temperature and ambient humidity are respectively measured by the temperature sensor and the humidity sensor and the average values ​​thereof are calculated to obtain the obtained values.

[0011] Further, the method of comparing the transport assessment coefficient with the transport assessment coefficient threshold and obtaining the load adjustment information according to the comparison result includes: If the transport assessment factor If it is greater than or equal to the transport assessment coefficient threshold, load non-adjustment information is generated; If the transport assessment factor If the value is less than the transport assessment factor threshold, load adjustment information is generated.

[0012] Furthermore, the method for generating a load adjustment value of the corresponding mining AGV based on the current load value of the corresponding mining AGV includes: Calculating a first load difference between a current load value of the mining AGV and a preset standard load value of a target mining AGV; Calculate a second load difference between the current load value of the mining AGV and the current load value of the mining AGV with an adjacent serial number; Generate a load adjustment value of the corresponding mining AGV according to the first load difference and the second load difference; According to the load adjustment value of the corresponding mining AGV, the load value of the corresponding mining AGV is allocated; Among them, the method for generating a load adjustment value corresponding to the mining AGV according to the first load difference and the second load difference includes: Determine whether the first load difference is equal to a preset first load threshold, and determine whether the second load difference is equal to a preset second load threshold; If the first load difference is equal to the preset first load threshold, and the second load difference is equal to the preset second load threshold, the first load difference or the second load difference is used as the load adjustment value of the corresponding mining AGV to obtain the load adjustment value corresponding to the mining AGV.

[0013] Furthermore, the generation process of the preset standard load value of the target mining AGV is as follows: Obtain the current load value of the preset target mining AGV; Calculate the difference between the preset design load value of the target mining AGV and the preset standard preload value of the target mining AGV, and mark it as the target load difference; The current load value of the preset target mining AGV is adjusted according to the target load difference to obtain the preset standard load value of the target mining AGV; The standard preload value is a preset standard load value of the target mining AGV.

[0014] Furthermore, the target management area refers to the total area covered by i mining AGVs when transporting coal, and the mining sub-area is obtained by manually dividing the target management area according to the size of the total area.

[0015] In a second aspect, the present invention provides a mining AGV intelligent handling control system, which is used to implement the above-mentioned mining AGV intelligent handling control method, including: A data acquisition module is used to divide the target management area into i mining sub-areas, each of which corresponds to a mining AGV; obtain task allocation training data of i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; A load prediction model training module is used to train a load prediction model for predicting initial load values ​​based on task allocation training data; The transportation monitoring module is used to use the initial load value predicted by the trained load prediction model as the current load value of the mining AGV, transport the coal mine in the mining sub-area, and collect the transportation monitoring data of the i-th mining AGV in real time; extract the transportation monitoring data of the mining AGV, and obtain the transportation monitoring threshold of the i-th mining AGV to analyze the transportation monitoring data to obtain the transportation evaluation coefficient; A comparison module, used for setting a transport assessment coefficient threshold, comparing the transport assessment coefficient with the transport assessment coefficient threshold, and obtaining load adjustment information according to the comparison result; A load adjustment module, used to extract the current load value of the mining AGV corresponding to each mining sub-area according to the load adjustment information, and generate a load adjustment value of the corresponding mining AGV based on the current load value of the corresponding mining AGV; The method for generating a load adjustment value corresponding to a mining AGV comprises: Calculating a first load difference between a current load value of the mining AGV and a preset standard load value of a target mining AGV; Calculate a second load difference between the current load value of the mining AGV and the current load value of the mining AGV with an adjacent serial number; Generate a load adjustment value of the corresponding mining AGV according to the first load difference and the second load difference; According to the load adjustment value of the corresponding mining AGV, the load value of the corresponding mining AGV is allocated.

[0016] In a third aspect, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the above-mentioned mining AGV intelligent transportation control method by calling the computer program stored in the memory.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the above-mentioned intelligent transport control method for a mining AGV.

[0018] Technical effects and advantages of the present invention: The present invention divides the target management area into i mining sub-areas, each of which corresponds to a mining AGV; obtains task allocation training data of i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; a load prediction model for predicting the initial load value is trained based on the task allocation training data; the initial load value predicted by the trained load prediction model is used as the current load value of the mining AGV, the coal mine in the mining sub-area is transported, and the transportation monitoring data of the i-th mining AGV is collected in real time; the transportation monitoring data of the mining AGV is extracted, and the transportation monitoring threshold of the i-th mining AGV is obtained to analyze the transportation monitoring data to obtain a transportation evaluation coefficient; a transportation evaluation coefficient threshold is set, and the transportation evaluation coefficient threshold is used to calculate the transportation evaluation coefficient threshold. The estimation coefficient is compared with the transport estimation coefficient threshold, and the load adjustment information is obtained according to the comparison result; according to the load adjustment information, the current load value of the mine AGV corresponding to each mining sub-area is extracted, and the load adjustment value of the corresponding mine AGV is generated based on the current load value corresponding to the mine AGV; in the actual process of transporting coal by mine AGV, the present invention uses the initial load value trained by the load prediction model as the current load value, which is conducive to transporting the coal in the mining sub-area according to the predicted load value, and then analyzing the transportation coal situation in real time according to the real-time transportation monitoring data, and accurately determining the load adjustment value, so as to avoid the situation where the load value of the mine AGV is too large or too small, resulting in low coal transportation efficiency, and realize accurate determination of the load adjustment value, which helps to ensure balanced task distribution of the mine AGV and improve transportation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a mining AGV intelligent handling control method according to Example 1; Figure 2 This is a schematic diagram of mining AGV transportation in Example 1; Figure 3 This is a structural diagram of a mining AGV intelligent handling control system in Example 2; Figure 4 This is a schematic diagram of an electronic device according to Embodiment 3; Figure 5A schematic diagram of a computer-readable storage medium of Example 4. DETAILED DESCRIPTION

[0020] 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.

[0021] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0022] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0023] Example 1 See also Figure 1 As shown, this embodiment discloses a mining AGV intelligent handling control method, which is applied to a mining AGV, including: Step 1: Divide the target management area into i mining sub-areas, each of which corresponds to a mining AGV; obtain task allocation training data for i mining AGVs; i is an integer greater than or equal to 1; See also Figure 2As shown, it should be noted that the target management area refers to the total area covered by multiple mining AGVs when transporting coal mines, and the mining sub-area is obtained by artificially dividing the target management area according to the size of the total area; it should be further noted that after obtaining i mining AGVs, each mining sub-area is also marked with a serial number, and a corresponding transportation route is set according to the mining AGV corresponding to each marked mining sub-area, so that the mining AGV performs the transportation task according to the predetermined transportation route to improve the task allocation efficiency of the mining AGV; the transportation task includes but is not limited to the load value of the mining AGV; it should be noted that the mining AGV has an explosion-proof design to meet the safety standards of mining operations.

[0024] Further, when the coal demand area sends the task volume of transporting coal, task allocation training data is collected; It should be noted that the coal mine demand area is the destination of the coal mine transported by the mining AGV. When the coal mine demand area sends the coal mine transportation task volume, the mining AGV transports the corresponding coal mine according to the coal mine transportation task volume. The coal mine transportation task volume is pre-stored in the system database. It should also be explained that the method of sending the coal mine transportation task volume is not the main solution of the present invention, and there are also a series of existing methods of sending the coal mine transportation task volume to achieve this function. Therefore, the present invention will not elaborate on this. The main reason for the quantitative transportation of coal by the mining AGV (automatic guided vehicle) is that reasonable load transportation reduces excessive wear of equipment, extends the service life of AGV, reduces maintenance and replacement costs, ensures the continuity and stability of coal mine transportation, reduces stagnation in the production process, and improves overall production efficiency.

[0025] The method for obtaining the task allocation training data of i mining AGVs is as follows: Specifically, the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; In a preferred implementation, the load characteristic data includes the volume of the coal mine, the weight of the coal mine and the inclination angle of the center of gravity; The volume of the coal mine is obtained by scanning the identification code of the coal mine by the camera of the mining AGV; it should be noted that the volume of the coal mine is pre-stored in the system database; the larger the volume of the coal mine, the larger the initial load value of the mining AGV; The weight of the coal is obtained through the gravity sensor installed on the mining AGV. It should be noted that when the mining AGV transports the coal, it automatically obtains the weight of the coal based on the gravity sensor. The heavier the coal, the greater the initial load value.

[0026] The gravity center tilt angle is obtained in real time by the inclination sensor installed on the mining AGV, which measures the gravity center tilt angle when the mining AGV transports coal. The larger the gravity center tilt angle, the smaller the initial load value. The initial load value is obtained by measuring a load sensor installed on the mining AGV, that is, when the load characteristic data is obtained, the initial load value of the corresponding mining AGV is obtained by measuring the load sensor at the same time.

[0027] Step 2: Train a load prediction model for predicting the initial load value based on the task allocation training data; A load prediction model for predicting initial load values ​​is trained based on the task allocation training data. The training method is:

[0028] Each set of load characteristic data is used as the input of the load prediction model. The load prediction model outputs the initial load value corresponding to each set of load characteristic data, takes the initial load value corresponding to the load characteristic data in the task allocation training data as the prediction target, and takes minimizing the prediction error of all initial load values ​​as the training target; the load prediction model is trained until the prediction error reaches convergence, and the training is stopped to train a load prediction model that outputs the predicted initial load value according to the load characteristic data; the load prediction model is one of a polynomial regression model or a SVM model; the prediction error is calculated as follows: , the load forecasting model is trained with the minimization as the goal, where is the group number of the load characteristic data, is the prediction error, For the The predicted initial load value corresponding to the group load characteristic data, For the The actual initial load value corresponding to the group load characteristic data.

[0029] It should be noted that other model parameters of the load forecasting model, such as the depth of the network model, the number of neurons in each layer, convergence conditions, the ratio of the training set, the test set, and the validation set, and the loss function, are all obtained through actual engineering implementation and continuous experimental tuning; Step 3: Use the initial load value predicted by the trained load prediction model as the current load value of the mining AGV, transport the coal mine in the mining sub-area, and collect the transportation monitoring data of the i-th mining AGV in real time; extract the transportation monitoring data of the mining AGV, and obtain the transportation monitoring threshold of the i-th mining AGV to analyze the transportation monitoring data to obtain the transportation evaluation coefficient; In a preferred implementation, the transport monitoring data includes the real-time power, operation time and failure rate of the mining AGV, and the transport monitoring threshold includes a power threshold, an operation time threshold and a failure rate threshold; It should be noted that the real-time power consumption is obtained through the power monitoring equipment installed on the mining AGV; the operating time is obtained by obtaining the start and shutdown time of the mining AGV through the data log of the mining AGV, and calculating the time interval between the start and shutdown time; the failure rate is the number of failure events of the mining AGV per unit time; by obtaining the real-time power consumption, operating time and failure rate, the mining AGV in the process of transporting coal can be monitored in real time; the unit time includes but is not limited to days, weeks, years or other time intervals.

[0030] Specifically, the method for obtaining the transportation monitoring threshold of the i-th mining AGV to analyze the transportation monitoring data includes: Calculate the absolute value of the power difference between the real-time power of each mining AGV and the power threshold, and use the absolute value of the power difference as the power evaluation coefficient; Calculate the absolute value of the difference between the running time of each mining AGV and the running time threshold, and use the absolute value of the running time difference as the running time evaluation coefficient; Calculate the absolute value of the failure rate difference between the failure rate of each mining AGV and the failure rate threshold, and use the absolute value of the failure rate difference as the failure rate evaluation coefficient; Furthermore, based on the ambient temperature and humidity of the mining sub-area corresponding to the i-th mining AGV, the power evaluation coefficient, the operating time evaluation coefficient, and the failure rate evaluation coefficient are dimensionlessly quantified and calculated in a formula to obtain the transportation evaluation coefficient , and its calculation formula is: ; In the formula, is the transportation evaluation coefficient of the i-th mining AGV, is the power evaluation coefficient of the i-th mining AGV, is the operating time evaluation coefficient of the i-th mining AGV, is the failure rate evaluation coefficient of the i-th mining AGV, is the ambient temperature of the mining sub-area corresponding to the i-th mining AGV, is the ambient humidity of the mining sub-area corresponding to the i-th mining AGV, represents the power weight of the i-th mining AGV, represents the running time weight of the i-th mining AGV, represents the failure rate weight of the i-th mining AGV, represents the ambient temperature weight of the i-th mining AGV, represents the environmental humidity weight of the i-th mining AGV, , , , and All are greater than zero, and C is a preset constant; It should be noted that a temperature sensor and a humidity sensor are installed in the mining sub-area corresponding to the i-th mining AGV, and the ambient temperature and ambient humidity are respectively measured by the temperature sensor and the humidity sensor and the average value thereof is calculated; Step 4: Set a transport assessment coefficient threshold, compare the transport assessment coefficient with the transport assessment coefficient threshold, and obtain load adjustment information based on the comparison result; Specifically, the method of comparing the transport assessment coefficient with the transport assessment coefficient threshold and obtaining the load adjustment information according to the comparison result includes: If the transport assessment factor If it is greater than or equal to the transport evaluation coefficient threshold, the load non-adjustment information is generated, indicating that the i-th mining AGV transports coal stably, and the current load value of the corresponding mining AGV is moderate, and there is no need to adjust the current load value; If the transport assessment factor If it is less than the transport evaluation coefficient threshold, load adjustment information is generated, indicating that the i-th mining AGV transporting coal mines is unstable, and the current load value of the corresponding mining AGV is inappropriate, and the current load value needs to be adjusted; It should be noted that the load value adjustment method can change the load value of the mining AGV by increasing or decreasing the weight or volume of the object. It should be further noted that the load value adjustment method is not the main solution of the present invention, and there are also a series of existing load value adjustment methods to achieve this function. Therefore, the present invention will not go into details about this.

[0031] Step 5: extracting the current load value of the mining AGV corresponding to each mining sub-area according to the load adjustment information, and generating the load adjustment value of the corresponding mining AGV based on the current load value of the mining AGV; Specifically, the method for generating a load adjustment value corresponding to a mining AGV includes: Calculate a first load difference between the current load value of the mining AGV and a preset standard load value of the target mining AGV; wherein the preset target mining AGV is randomly selected as the load adjustment value object, which is not limited here; Specifically, the process of generating the preset standard load value of the target mining AGV is as follows: Obtain the current load value of the preset target mining AGV; Calculate the difference between the preset design load value of the target mining AGV and the preset standard preload value of the target mining AGV, and mark it as the target load difference; The current load value of the preset target mining AGV is adjusted according to the target load difference to obtain the preset standard load value of the target mining AGV; Example: Calculate the standard load value as follows: The current load value of the preset target mining AGV is obtained as 35.

[0032] Calculate the difference between the preset design load value of the target mining AGV and the preset standard preload value of the target mining AGV: the design load value is 50, the standard preload value is 45, and the difference is 50-45=5.

[0033] The current load value of the preset target mining AGV is adjusted according to the target load difference: 35+5=40.

[0034] Therefore, based on the data and process provided, the standard load value is 40; It should be noted that the standard preload value is a preset standard load value of the target mining AGV.

[0035] It is further explained that due to fluctuations in the external environment such as the ambient temperature and humidity in the mining sub-area, the battery of the corresponding mining AGV ages; or the corresponding mining AGV transportation failure causes the standard load value to change. For this reason, there may be a difference between the standard pre-load value and the design load value. For this reason, the difference between the standard pre-load value and the design load value is calculated as the target load difference to ensure the accuracy of the preset standard load value of the target mining AGV.

[0036] Further, a second load difference between a current load value of the corresponding mining AGV and a current load value of an adjacent numbered mining AGV is calculated, and the adjacent numbered mining AGV is the corresponding mining AGV for which the second load difference is currently calculated; Generate a load adjustment value of the corresponding mining AGV according to the first load difference and the second load difference; According to the load adjustment value of the corresponding mining AGV, the load value of the corresponding mining AGV is allocated; Specifically, according to the first load difference and the second load difference, the method for generating a load adjustment value of the corresponding mining AGV includes: Determine whether the first load difference is equal to a preset first load threshold, and determine whether the second load difference is equal to a preset second load threshold; If the first load difference is equal to the preset first load threshold, and the second load difference is equal to the preset second load threshold, the first load difference or the second load difference is used as the load adjustment value of the corresponding mining AGV to obtain the load adjustment value corresponding to the mining AGV; It should be noted that the load adjustment value of each corresponding mining AGV refers to whether to set a load adjustment value for the mining AGV corresponding to each mining sub-area according to the size of the transportation assessment coefficient. For example, if there is a mining sub-area in which the transportation assessment coefficient is greater than or equal to the transportation assessment coefficient threshold, it means that the current load value of the corresponding mining AGV transporting the coal mine is moderate, and then load non-adjustment information is generated, that is, the load adjustment value of the mining AGV corresponding to the mining sub-area is zero; it should be further noted that the current load value of the corresponding mining AGV is first obtained, and then the first load difference between the current load value of the corresponding mining AGV and the preset standard load value of the target mining AGV is calculated, and the first load difference between the current load value of the corresponding mining AGV and the current load value of the adjacent mining AGV is calculated. two load differences; then, determine whether the first load difference is equal to the preset first load threshold, and determine whether the second load difference is equal to the preset second load threshold; if the first load difference is equal to the preset first load threshold, and the second load difference is equal to the preset second load threshold, then use the first load difference or the second load difference as the load adjustment value of the corresponding mining AGV; on the contrary, for the mining AGV whose transportation assessment coefficient meets the transportation assessment coefficient threshold, the load values ​​of the different corresponding mining AGVs can be accurately adjusted through the operation of the same principle as above. When the mining AGV has poor transportation performance, the load value can be accurately judged in time to avoid the mining AGV being unable to withstand the set load value due to poor performance, thereby preventing the coal mine from being damaged and improving the transportation efficiency at the same time; Example: Get the current load value of the corresponding mining AGV: Assume that the current load value of the mining AGV is 25.

[0037] Calculate the first load difference: Assume that the preset standard load value of the target mining AGV is 40.

[0038] The first load difference = target load - current load = 40 - 25 = 15.

[0039] Calculate the second load difference: Assume that the current load value of the adjacent mining AGV is 30.

[0040] The second load difference = adjacent load - current load = 30 - 25 = 5.

[0041] Determine whether the load difference is equal to the preset load threshold: If the first load difference is equal to a preset first load threshold (for example, set to 15), and the second load difference is equal to a preset second load threshold (for example, set to 5), the adjustment operation is performed.

[0042] Determine the adjustment value: Depending on the situation, the first load difference or the second load difference is selected as the load adjustment value.

[0043] In one embodiment, if the first load difference is not equal to the preset first load threshold, it is determined that there is an abnormal load value adjustment of the target mining AGV, and the mining AGV maintenance personnel are notified to repair the target mining AGV; In another embodiment, if the second load difference is not equal to the preset second load threshold, a third load difference corresponding to the current load value of the mining AGV and the current load value of another adjacent numbered mining AGV is calculated; Determine whether the third load difference is equal to the preset second load threshold value, and if the third load difference is equal to the preset second load threshold value, use the first load difference or the third load difference as the load adjustment value of the corresponding mining AGV to obtain the load adjustment value of the corresponding mining AGV; It should also be noted that if there are multiple current load values ​​corresponding to the mining AGV and the difference between the current load value of another adjacent numbered mining AGV is not equal to the preset load threshold, then it is judged that the mining AGV has a serious load abnormality problem, and the equipment maintenance personnel are notified to inspect the mining AGV.

[0044] According to the load adjustment value of each corresponding mining AGV, each corresponding mining AGV is controlled to deliver the coal to the coal demand area until the transportation is completed according to the coal transportation task volume and then stops.

[0045] The present invention divides the target management area into i mining sub-areas, each of which corresponds to a mining AGV; obtains task allocation training data of i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; a load prediction model for predicting the initial load value is trained based on the task allocation training data; the initial load value predicted by the trained load prediction model is used as the current load value of the mining AGV, the coal mine in the mining sub-area is transported, and the transportation monitoring data of the i-th mining AGV is collected in real time; the transportation monitoring data of the mining AGV is extracted, and the transportation monitoring threshold of the i-th mining AGV is obtained to analyze the transportation monitoring data to obtain a transportation evaluation coefficient; a transportation evaluation coefficient threshold is set, and the transportation evaluation coefficient threshold is used to calculate the transportation evaluation coefficient threshold. The estimation coefficient is compared with the transport estimation coefficient threshold, and the load adjustment information is obtained according to the comparison result; according to the load adjustment information, the current load value of the mine AGV corresponding to each mining sub-area is extracted, and the load adjustment value of the corresponding mine AGV is generated based on the current load value corresponding to the mine AGV; in the actual process of transporting coal by mine AGV, the present invention uses the initial load value trained by the load prediction model as the current load value, which is conducive to transporting the coal in the mining sub-area according to the predicted load value, and then analyzing the transportation coal situation in real time according to the real-time transportation monitoring data, and accurately determining the load adjustment value, so as to avoid the situation where the load value of the mine AGV is too large or too small, resulting in low coal transportation efficiency, and realize accurate determination of the load adjustment value, which helps to ensure balanced task distribution of the mine AGV and improve transportation efficiency.

[0046] Example 2 See also Figure 3 As shown, this embodiment provides a mining AGV intelligent handling control system, including: A data acquisition module is used to divide the target management area into i mining sub-areas, each of which corresponds to a mining AGV; obtain task allocation training data of i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; A load prediction model training module is used to train a load prediction model for predicting initial load values ​​based on task allocation training data; The transportation monitoring module is used to use the initial load value predicted by the trained load prediction model as the current load value of the mining AGV, transport the coal mine in the mining sub-area, and collect the transportation monitoring data of the i-th mining AGV in real time; extract the transportation monitoring data of the mining AGV, and obtain the transportation monitoring threshold of the i-th mining AGV to analyze the transportation monitoring data to obtain the transportation evaluation coefficient; A comparison module, used for setting a transport assessment coefficient threshold, comparing the transport assessment coefficient with the transport assessment coefficient threshold, and obtaining load adjustment information according to the comparison result; A load adjustment module, used to extract the current load value of the mining AGV corresponding to each mining sub-area according to the load adjustment information, and generate a load adjustment value of the corresponding mining AGV based on the current load value of the corresponding mining AGV; The method for generating a load adjustment value corresponding to a mining AGV comprises: Calculating a first load difference between a current load value of the mining AGV and a preset standard load value of a target mining AGV; Calculate a second load difference between the current load value of the mining AGV and the current load value of the mining AGV with an adjacent serial number; Generate a load adjustment value of the corresponding mining AGV according to the first load difference and the second load difference; According to the load adjustment value of the corresponding mining AGV, the load value of the corresponding mining AGV is allocated.

[0047] Example 3 See also Figure 4 As shown, an electronic device 500. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are run by one or more processors, the above-mentioned intelligent handling control method of a mining AGV can be executed.

[0048] The system according to the embodiment of the present application can also be used Figure 4 The electronic device architecture shown in FIG. Figure 4 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store a mining AGV intelligent handling control method provided by the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 4 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 4 One or more components of an electronic device are shown.

[0049] Example 4 See also Figure 5 As shown, a computer-readable storage medium stores instructions. When the instructions are executed on a computer, the computer executes the above-mentioned intelligent transportation control method of a mining AGV.

[0050] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weights in the formula and the preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. The size of the weight depends on the amount of sample data and the corresponding processing coefficient initially set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0051] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0052] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A mining AGV intelligent handling control method, characterized in that: include: Divide the target management area into i mining sub-areas, each of which corresponds to a mining AGV; Obtain task allocation training data for i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; A load prediction model is trained to predict the initial load value based on the task allocation training data; The initial load value predicted by the trained load prediction model is used as the current load value of the mining AGV, and the coal mine in the mining sub-area is transported, and the transportation monitoring data of the i-th mining AGV is collected in real time; the transportation monitoring data of the mining AGV is extracted, and the transportation monitoring threshold of the i-th mining AGV is obtained to analyze the transportation monitoring data to obtain the transportation evaluation coefficient; Setting a transport assessment coefficient threshold, comparing the transport assessment coefficient with the transport assessment coefficient threshold, and obtaining load adjustment information according to the comparison result; According to the load adjustment information, the current load value of the mining AGV corresponding to each mining sub-area is extracted, and the load adjustment value of the corresponding mining AGV is generated based on the current load value corresponding to the mining AGV.

2. The method for controlling the intelligent handling of mining AGVs according to claim 1, characterized in that: The method for obtaining the task allocation training data of i mining AGVs is as follows: The load characteristic data includes coal volume, coal weight and center of gravity inclination angle; The volume of the coal mine is obtained by scanning the identification code of the coal mine with the camera of the mining AGV; the weight of the coal mine is obtained by the gravity sensor installed in the mining AGV; the inclination angle of the center of gravity is obtained in real time by the inclination sensor installed in the mining AGV, which measures the inclination angle of the center of gravity when the mining AGV transports the coal mine; The initial load value is obtained by measuring a load sensor installed on the mining AGV, that is, when the load characteristic data is obtained, the initial load value of the corresponding mining AGV is obtained by measuring the load sensor at the same time.

3. The method for controlling the intelligent handling of mining AGVs according to claim 1, characterized in that: A load prediction model for predicting initial load values ​​is trained based on the task allocation training data. The training method is: Each set of load characteristic data is used as the input of the load prediction model. The load prediction model takes the initial load value corresponding to each set of load characteristic data as output, takes the initial load value corresponding to the load characteristic data in the task allocation training data as the prediction target, and takes minimizing the prediction error of all initial load values ​​as the training target; the load prediction model is trained until the prediction error reaches convergence, and the training is stopped to train a load prediction model that predicts the initial load value according to the load characteristic data output; the load prediction model is a polynomial regression model or a SVM model.

4. A mining AGV intelligent handling control method according to claim 3, characterized in that: The transport monitoring data includes the real-time power, operation time and failure rate of the mining AGV, and the transport monitoring threshold includes the power threshold, operation time threshold and failure rate threshold; The real-time power consumption is obtained by the power monitoring equipment installed on the mining AGV; the operating time is obtained by obtaining the startup and shutdown time of the mining AGV through the data log of the mining AGV, and calculating the time interval between the startup and shutdown time; the failure rate is the number of failure events of the mining AGV per unit time; the unit time includes days, weeks or years.

5. The method for controlling the intelligent handling of mining AGVs according to claim 4 is characterized in that: The method for obtaining the transportation monitoring threshold of the i-th mining AGV to analyze the transportation monitoring data includes: Calculate the absolute value of the power difference between the real-time power of each mining AGV and the power threshold, and use the absolute value of the power difference as the power evaluation coefficient; Calculate the absolute value of the difference between the running time of each mining AGV and the running time threshold, and use the absolute value of the running time difference as the running time evaluation coefficient; Calculate the absolute value of the failure rate difference between the failure rate of each mining AGV and the failure rate threshold, and use the absolute value of the failure rate difference as the failure rate evaluation coefficient; Based on the ambient temperature and humidity of the mining sub-area corresponding to the i-th mining AGV, the power evaluation coefficient, the operating time evaluation coefficient, and the failure rate evaluation coefficient are dimensionlessly quantified and calculated in a formula to obtain the transportation evaluation coefficient. , and its calculation formula is: ； In the formula, is the transportation evaluation coefficient of the i-th mining AGV, is the power evaluation coefficient of the i-th mining AGV, is the operating time evaluation coefficient of the i-th mining AGV, is the failure rate evaluation coefficient of the i-th mining AGV, is the ambient temperature of the mining sub-area corresponding to the i-th mining AGV, is the ambient humidity of the mining sub-area corresponding to the i-th mining AGV, represents the power weight of the i-th mining AGV, represents the running time weight of the i-th mining AGV, represents the failure rate weight of the i-th mining AGV, represents the ambient temperature weight of the i-th mining AGV, represents the environmental humidity weight of the i-th mining AGV, , , , and All are greater than zero, and C is a preset constant; A temperature sensor and a humidity sensor are installed in the mining sub-area corresponding to the i-th mining AGV, and the ambient temperature and ambient humidity are respectively measured by the temperature sensor and the humidity sensor and the average values ​​thereof are calculated to obtain the obtained values.

6. A mining AGV intelligent handling control method according to claim 5, characterized in that: The method of comparing the transport assessment coefficient with the transport assessment coefficient threshold and obtaining load adjustment information according to the comparison result includes: If the transport assessment factor If it is greater than or equal to the transport assessment coefficient threshold, load non-adjustment information is generated; If the transport assessment factor If the value is less than the transport assessment factor threshold, load adjustment information is generated.

7. The method for controlling the intelligent handling of mining AGVs according to claim 6, characterized in that: The method for generating a load adjustment value of a corresponding mining AGV based on a current load value of the corresponding mining AGV includes: Calculating a first load difference between a current load value of the mining AGV and a preset standard load value of a target mining AGV; Calculate a second load difference between the current load value of the mining AGV and the current load value of the mining AGV with an adjacent serial number; Generate a load adjustment value of the corresponding mining AGV according to the first load difference and the second load difference; According to the load adjustment value of the corresponding mining AGV, the load value of the corresponding mining AGV is allocated; Among them, the method for generating a load adjustment value corresponding to the mining AGV according to the first load difference and the second load difference includes: Determine whether the first load difference is equal to a preset first load threshold, and determine whether the second load difference is equal to a preset second load threshold; If the first load difference is equal to the preset first load threshold, and the second load difference is equal to the preset second load threshold, the first load difference or the second load difference is used as the load adjustment value of the corresponding mining AGV to obtain the load adjustment value corresponding to the mining AGV.

8. The method for controlling the intelligent handling of mining AGVs according to claim 7, characterized in that: The generation process of the preset standard load value of the target mining AGV is as follows: Obtain the current load value of the preset target mining AGV; Calculate the difference between the preset design load value of the target mining AGV and the preset standard preload value of the target mining AGV, and mark it as the target load difference; The current load value of the preset target mining AGV is adjusted according to the target load difference to obtain the preset standard load value of the target mining AGV; The standard preload value is a preset standard load value of the target mining AGV.

9. The method for controlling the intelligent handling of mining AGVs according to claim 8, characterized in that: The target management area refers to the total area covered by i mining AGVs when transporting coal, and the mining sub-area is obtained by pre-dividing the target management area according to the size of the total area.

10. A mining AGV intelligent handling control system, used to implement a mining AGV intelligent handling control method according to any one of claims 1 to 9, characterized in that: include: A data acquisition module is used to divide the target management area into i mining sub-areas, each of which corresponds to a mining AGV; Obtain task allocation training data for i mining AGVs; i is an integer greater than or equal to 1; the task allocation training data includes load characteristic data and an initial load value corresponding to the load characteristic data; A load prediction model training module is used to train a load prediction model for predicting initial load values ​​based on task allocation training data; The transportation monitoring module is used to use the initial load value predicted by the trained load prediction model as the current load value of the mining AGV, transport the coal mine in the mining sub-area, and collect the transportation monitoring data of the i-th mining AGV in real time; extract the transportation monitoring data of the mining AGV, and obtain the transportation monitoring threshold of the i-th mining AGV to analyze the transportation monitoring data to obtain the transportation evaluation coefficient; A comparison module, used for setting a transport assessment coefficient threshold, comparing the transport assessment coefficient with the transport assessment coefficient threshold, and obtaining load adjustment information according to the comparison result; A load adjustment module, used to extract the current load value of the mining AGV corresponding to each mining sub-area according to the load adjustment information, and generate a load adjustment value of the corresponding mining AGV based on the current load value of the corresponding mining AGV; The method for generating a load adjustment value corresponding to a mining AGV comprises: Calculating a first load difference between a current load value of the mining AGV and a preset standard load value of a target mining AGV; Calculate a second load difference between the current load value of the mining AGV and the current load value of the mining AGV with an adjacent serial number; Generate a load adjustment value of the corresponding mining AGV according to the first load difference and the second load difference; According to the load adjustment value of the corresponding mining AGV, the load value of the corresponding mining AGV is allocated.

11. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the mining AGV intelligent transportation control method described in any one of claims 1 to 9 by calling the computer program stored in the memory.

12. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer executes a mining AGV intelligent transportation control method as described in any one of claims 1-9.

Images