Mining equipment mining cost prediction method based on genetic algorithm and machine learning

Abstract

The embodiment of the invention provides mining equipment mining cost prediction based on a genetic algorithm and machine learning. The method comprises the steps that an initial data set related to the equipment mining cost is acquired, and data feature types in the initial data set comprise category features and numerical value features; performing data processing based on the initial data set to obtain a training data set, the data processing including at least one of generative adversarial network generation, noise injection and feature crossing; training a pre-constructed XGBoost model based on the training data set, verifying the XGBoost model by using a five-fold cross validation method in the training process of the XGBoost model, and performing parameter optimization on the XGBoost model by using a genetic algorithm; and predicting the mining cost of the mining equipment according to the trained XGBoost model. According to the technical scheme, the model training data can be effectively obtained, the model training efficiency is improved, and the prediction precision of the model is ensured.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more particularly, to a method for predicting the mining cost of mining equipment based on genetic algorithms and machine learning. Background Art

[0002] With the wide application of digital technology in the mining industry, the analysis and prediction of mining costs have gradually become a key link in improving mining production efficiency and economic benefits. With the rapid development of artificial intelligence technology, machine learning algorithms have begun to be applied to mining cost analysis. However, although the above methods have improved the efficiency and accuracy of cost analysis to a certain extent, due to the difficulty of obtaining training data and the low efficiency of parameter tuning during training, the model training efficiency and prediction accuracy are poor. Therefore, how to effectively obtain model training data, improve model training efficiency, and ensure the prediction accuracy of the model has become an urgent technical problem to be solved. Summary of the Invention

[0003] An embodiment of this application provides a method for predicting the mining cost of mining equipment based on genetic algorithms and machine learning, which can, at least to a certain extent, effectively obtain model training data, improve model training efficiency, and ensure the prediction accuracy of the model.

[0004] Other features and advantages of this application will become apparent through the following detailed description, or be learned in part through the practice of this application.

[0005] According to one aspect of the embodiments of this application, a method for predicting the mining cost of mining equipment based on genetic algorithms and machine learning is provided, including:

[0006] Obtain an initial data set related to the mining cost of equipment, and the data feature types in the initial data set include categorical features and numerical features;

[0007] Perform data processing on the initial data set to obtain a training data set, and the data processing includes at least one of generating based on a generative adversarial network, noise injection, and feature crossover;

[0008] Train a pre-constructed XGBoost model based on the training data set, and during the training process of the XGBoost model, use five-fold cross-validation to verify the XGBoost model, and use a genetic algorithm to optimize the parameters of the XGBoost model;

[0009] Predict the mining cost of mining equipment according to the trained XGBoost model.

[0010] According to one aspect of the embodiments of the present application, there is provided a mining cost prediction device for mining equipment based on genetic algorithms and machine learning, characterized by comprising:

[0011] An acquisition module, configured to acquire an initial data set related to the mining cost of equipment, and the data feature types in the initial data set include categorical features and numerical features;

[0012] A first processing module, configured to perform data processing on the basis of the initial data set to obtain a training data set, and the data processing includes at least one of generating based on a generative adversarial network, noise injection, and feature crossing;

[0013] A training module, configured to train a pre-constructed XGBoost model based on the training data set, and during the training process of the XGBoost model, use a five-fold cross-validation method to verify the XGBoost model, and use a genetic algorithm to optimize the parameters of the XGBoost model;

[0014] A second processing module, configured to predict the mining cost of mining equipment according to the trained XGBoost model.

[0015] According to one aspect of the embodiments of the present application, there is provided a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the mining cost prediction method for mining equipment based on genetic algorithms and machine learning as described in the above embodiments is implemented.

[0016] According to one aspect of the embodiments of the present application, there is provided an electronic device, comprising: one or more processors; a storage device, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the mining cost prediction method for mining equipment based on genetic algorithms and machine learning as described in the above embodiments.

[0017] According to one aspect of the embodiments of the present application, there is provided a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the mining cost prediction method for mining equipment based on genetic algorithms and machine learning provided in the above embodiments.

[0018] In the technical solutions provided by some embodiments of the present application, by obtaining an initial data set related to the mining cost of the equipment, the data feature types in the initial data set include categorical features and numerical features, and based on the initial data set, data processing is performed to obtain a training data set. The data processing includes at least one of generating based on a generative adversarial network, noise injection, and feature crossing. Then, based on the training data set, a pre-constructed XGBoost model is trained, and during the training process of the XGBoost model, a five-fold cross-validation method is used to verify the XGBoost model, and a genetic algorithm is used to optimize the parameters of the XGBoost model. According to the trained XGBoost model, the mining cost of the mining equipment is predicted. In this way, training data can be quickly obtained, and the effectiveness of the obtained training data can be ensured. Moreover, by using a genetic algorithm to tune the parameters of the XGBoost model, the tuning efficiency can be improved, thereby improving the training efficiency of the model and ensuring the prediction accuracy of the model.

[0019] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts. In the drawings:

[0021] Figure 1 shows a schematic flowchart of a method for predicting the mining cost of mining equipment based on a genetic algorithm and machine learning according to an embodiment of the present application;

[0022] Figure 2 shows a training flowchart of an XGBoost model according to an embodiment of the present application;

[0023] Figure 3 shows a schematic flowchart of parameter optimization according to an embodiment of the present application;

[0024] Figure 4 shows a block diagram of a device for predicting the mining cost of mining equipment based on a genetic algorithm and machine learning according to an embodiment of the present application;

[0025] Figure 5 shows a schematic structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art.

[0027] In addition, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of this application. However, those skilled in the art will realize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of this application.

[0028] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these 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 devices and / or microcontroller devices.

[0029] The flowcharts shown in the accompanying drawings are merely illustrative and not necessarily include all the content and operations / steps, nor are they necessarily executed in the order described. For example, some operations / steps can be decomposed, while some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0030] Figure 1 A schematic flow diagram of a method for predicting the mining cost of mining equipment based on a genetic algorithm and machine learning according to an embodiment of this application is shown.

[0031] This method can be applied to a terminal device or a server. Among them, the terminal device can include, but is not limited to, one or more of a smart phone, a tablet computer, a portable computer, and a desktop computer; the server can be a physical server or a cloud server.

[0032] Referring to Figure 2 As shown, the method for predicting the mining cost of mining equipment based on a genetic algorithm and machine learning includes at least steps S110 to S140, which are introduced in detail as follows (hereinafter, this method is described by taking its application to a server as an example):

[0033] In step S110, an initial data set related to the mining cost of the equipment is obtained, and the data feature types in the initial data set include categorical features and numerical features.

[0034] In this embodiment, the server can obtain an initial data set related to the mining cost of the equipment from its own storage space or a third-party storage space (such as a mine data platform, etc.). It should be noted that this initial data set can be pre-recorded and stored by the management personnel during the mine mining process. In one example, the initial data set can include, but is not limited to, at least one of equipment type, working hours, workload, and energy consumption.

[0035] It is worth noting that the types of data features in the initial data set can include categorical features (such as equipment type, etc.) and numerical features (such as working hours, workload, energy consumption, etc.).

[0036] In one example, after obtaining the initial data set, preprocessing operations can be performed on the data set, including deleting outliers, filling missing values with the mean, and classifying and encoding categorical features.

[0037] In step S120, data processing is performed based on the initial data set to obtain a training data set. The data processing includes at least one of generating based on a generative adversarial network, injecting noise, and feature crossing.

[0038] In this embodiment, after obtaining the initial data set, the server can perform data processing on the data features in the initial data set, thereby expanding the data features in the initial data set to obtain a training data set, which can improve the data quality of the training data and the generalization ability of the model after subsequent training is completed.

[0039] In step S130, the pre-constructed XGBoost model is trained based on the training data set. During the training process of the XGBoost model, the five-fold cross-validation method is used to verify the XGBoost model, and the genetic algorithm is used to optimize the parameters of the XGBoost model.

[0040] In this embodiment, the XGBoost model is a machine learning model based on gradient boosting, which can improve the prediction performance by integrating multiple decision trees. Those skilled in the art can pre-construct the XGBoost model, and the server can use the training data set obtained after data processing to train the XGBoost model, so that the trained XGBoost model can predict the mining cost of mine equipment.

[0041] Specifically, the core of the XGBoost model is to use the integration idea - the Boosting idea, which integrates multiple weak learners into a strong learner through a certain method, that is, the result of each tree is to fit the residual between the previous tree and the target value, and all the results are accumulated to obtain the final result, so as to achieve the improvement of the overall model effect.

[0042] In one example, the formula of the XGBoost model can be shown as follows:

[0043]

[0044] Wherein, is the prediction result of sample i, is the prediction result of the first t - 1 trees, and f t (x i ) is the prediction result of the t-th tree.

[0045] And, as Figure 2 shown, during the training process, the server can use five-fold cross-validation to verify the XGBoost model. Specifically, the server can split the training dataset into five parts, use one part as the validation set each time, and the rest as the training set, repeat five times, and take the average value as the final prediction result to evaluate the performance and generalization ability of the model.

[0046] In addition, as Figure 2 shown, the server can also optimize the parameters of the XGBoost model based on the genetic algorithm. Specifically, the server can use the genetic algorithm to adjust and optimize the hyperparameters of the XGBoost model, and the hyperparameters can include but are not limited to the depth of the model tree, the number of estimators, the learning rate, the sampling ratio, and the sample weight.

[0047] In some embodiments of the present application, optimizing the parameters of the XGBoost model using the genetic algorithm includes:

[0048] Randomly generating several groups of initial hyperparameter combinations as individuals;

[0049] Determining the similarity corresponding to each individual according to the sum of the Euclidean distances between each individual and other individuals in the population;

[0050] Using the Gaussian distribution to transform the similarity into a probability and normalizing the probability;

[0051] Calculating the entropy of the population according to the normalized probability and comparing it with the historical average population entropy;

[0052] Controlling the proportion of crossover mutation and genetic offspring generation according to the comparison result.

[0053] In this embodiment, the server can optimize parameters based on the genetic algorithm of population entropy. This algorithm can simultaneously save the excellent individuals in each generation of the population as a population pool for crossover and mutation. It should be noted that during the iterative process of the genetic algorithm, there will be problems of large population diversity in the early stage and small population diversity in the later stage, resulting in falling into local optima. Therefore, in order to ensure the effect of the model, an adaptive control strategy based on population entropy is used to increase the diversity of individuals in the population in the later stage of iteration by adjusting the probabilities of crossover, mutation, and inheritance in the later stage of the population, and solve the local optimum problem.

[0054] Specifically, as Figure 3 shown, the server can first randomly generate several groups of initial hyperparameter combinations as individuals. The similarity between individual P i and each other individual P j in the population is calculated by adding their Euclidean distances, as shown in the following formula:

[0055]

[0056] where P pi is the similarity, len(P) is the population size, and P i , P j are individuals in the population.

[0057] Then, according to the following formula, the similarity is transformed into a probability using the Gaussian distribution:

[0058]

[0059] where P bi is the probability after the similarity transformation, and σ(P pi ) is the variance of the individual similarities in the population.

[0060] After normalizing the probability, the entropy of the population is calculated according to the following formula:

[0061]

[0062] Then, after obtaining the population entropy, it can be compared with the historical average population entropy, and then the ratio α of crossover, mutation, and inheritance to produce offspring is adjusted according to the comparison result. It should be understood that when the population entropy is smaller, α is larger and the probability of crossover and mutation is larger. Specifically, as shown in the following formula:

[0063]

[0064] where is the ratio α value of the previous iteration, γ is the scaling factor, and avg_E is the historical average population entropy.

[0065] Please continue to refer toFigure 1 , in step S140, the mining cost of mining equipment is predicted according to the trained XGBoost model.

[0066] In this embodiment, after the XGBoost model is trained, it can be used to predict the mining cost of mining equipment, thereby improving the prediction efficiency and accuracy.

[0067] Thus, based on Figure 1 the embodiment shown, by obtaining an initial data set related to the mining cost of equipment, the data feature types in the initial data set include categorical features and numerical features, and based on this initial data set, data processing is performed to obtain a training data set. This data processing includes at least one of generating based on a generative adversarial network, noise injection, and feature crossing. Then, based on this training data set, a pre-constructed XGBoost model is trained. During the training process of this XGBoost model, a five-fold cross-validation method is used to validate this XGBoost model, and a genetic algorithm is used to optimize the parameters of this XGBoost model. According to the trained XGBoost model, the mining cost of mining equipment is predicted. In this way, training data can be quickly obtained, and the effectiveness of the obtained training data can be guaranteed. Moreover, by using a genetic algorithm to tune the parameters of the XGBoost model, the tuning efficiency can be improved, thereby improving the training efficiency of the model and ensuring the prediction accuracy of the model.

[0068] In some embodiments of the present application, data augmentation is performed based on the initial data set to obtain a training data set, including:

[0069] Based on the initial data set, a generative adversarial network is used to generate new data features to augment the initial data set and obtain a first data set;

[0070] Noise is injected into the data features in the first data set to obtain a second data set;

[0071] The data features with categorical feature types in the second data set are cross-combined to augment the second data set and obtain a third data set;

[0072] Feature encoding is performed on all data features with categorical feature types in the third data set, and normalization is performed on all data features with numerical feature types in the third data set to obtain a training data set.

[0073] In this embodiment, during the data processing, the server can first generate new data features based on the trained generative adversarial network to expand the initial dataset and obtain the first dataset. It should be noted that the generative adversarial network consists of a generator and a discriminator. Among them, the generator is responsible for generating new data samples, and the discriminator is responsible for distinguishing the generated data from the real data. Through adversarial training, the generator gradually generates samples close to the real data distribution, thereby ensuring the effectiveness of the new data features it generates.

[0074] Next, the server can inject noise into the data features in the first dataset to obtain the second dataset. Specifically, when injecting noise, the server can use Gaussian noise with a mean of 0 and a standard deviation of 0.1. The formula is as follows:

[0075] X * = X + N(0, 0.1)

[0076] where X * is the data after noise injection, X is the original data, and N(0, 0.1) is a normal distribution with a mean of 0 and a variance of 0.1.

[0077] Then, the server can cross - combine the data features with the category - feature type in the second dataset to expand the second dataset and obtain the third dataset. For example, the server can cross - combine the category features of equipment type and mining season. For instance, equipment A is used in spring and equipment B is used in winter. After cross - combination, new data features such as equipment A is used in winter and equipment B is used in spring are obtained.

[0078] Finally, in the data processing, the server can perform feature encoding on the data features with the category - feature type in the third dataset. In one example, the server can perform feature encoding according to the following formula:

[0079]

[0080] where TargetSum is the sum of the target values (training labels) of the specific classification feature up to the current, FeatureCount is the total number of classification features with the same value as the current one observed up to the current, and Prior is a constant value determined by (the sum of the target values in the entire dataset) / (the total number of observations in the dataset).

[0081] Then, perform normalization processing on the data features with the numerical - feature type. The specific formula is as follows:

[0082]

[0083] where Y *is the data after normalization, μ is the mean of all sample data in this feature column, and σ is the standard deviation of all sample data in this feature column.

[0084] In this way, through the above processing, a training data set can be obtained, and then subsequent model training is carried out based on this training data set, so as to ensure the effectiveness of the training data, as well as the generalization ability and prediction accuracy of the trained model.

[0085] The following introduces the device embodiments of the present application, which can be used to execute the mining cost prediction method of mining equipment based on genetic algorithm and machine learning in the above embodiments of the present application. For the details not disclosed in the device embodiments of the present application, please refer to the embodiments of the mining cost prediction method of mining equipment based on genetic algorithm and machine learning above.

[0086] Figure 4 The block diagram of a mining cost prediction device for mining equipment based on genetic algorithm and machine learning according to an embodiment of the present application is shown.

[0087] Refer to Figure 4 As shown, a mining cost prediction device for mining equipment based on genetic algorithm and machine learning according to an embodiment of the present application includes:

[0088] An acquisition module, configured to acquire an initial data set related to the mining cost of equipment, and the data feature types in the initial data set include categorical features and numerical features;

[0089] A first processing module, configured to perform data processing on the initial data set to obtain a training data set, and the data processing includes at least one of generating based on a generative adversarial network, noise injection, and feature crossover;

[0090] A training module, configured to train a pre-constructed XGBoost model based on the training data set, and during the training process of the XGBoost model, use five-fold cross-validation to verify the XGBoost model, and use a genetic algorithm to optimize the parameters of the XGBoost model;

[0091] A second processing module, configured to predict the mining cost of mining equipment according to the trained XGBoost model.

[0092] In some embodiments of the present application, performing data augmentation on the initial data set to obtain a training data set includes:

[0093] Based on the initial data set, use a generative adversarial network to generate new data features to augment the initial data set and obtain a first data set;

[0094] Inject noise into the data features in the first dataset to obtain a second dataset;

[0095] Cross - combine the data features with categorical feature types in the second dataset to expand the second dataset and obtain a third dataset;

[0096] Perform feature encoding on all data features with categorical feature types in the third dataset, and perform normalization on all data features with numerical feature types in the third dataset to obtain a training dataset.

[0097] In some embodiments of the present application, the data features with categorical feature types are feature - encoded according to the following formula:

[0098]

[0099] Among them, TargetSum is the cumulative sum of the target values of this specific categorical feature up to the current; FeatureCount is the total number of categorical features with the same value as the current one observed up to the current; Prior is a constant value.

[0100] In some embodiments of the present application, the XGBoost model is as shown in the following formula:

[0101]

[0102] Among them, is the prediction result of sample i, is the prediction result of the first t - 1 trees, f t (x i ) is the prediction result of the t - th tree.

[0103] In some embodiments of the present application, use a genetic algorithm to optimize the parameters of the XGBoost model, including:

[0104] Randomly generate several groups of initial hyperparameter combinations as individuals;

[0105] Determine the similarity corresponding to each individual according to the sum of the Euclidean distances between each individual and other individuals in the population;

[0106] Use a Gaussian distribution to transform the similarity into a probability and normalize the probability;

[0107] Calculate the entropy of the population according to the normalized probability and compare it with the historical average population entropy;

[0108] Control the proportion of crossover mutation and genetic offspring generation according to the comparison result.

[0109] In some embodiments of the present application, the initial data set includes at least one of device type, working hours, workload, and energy consumption.

[0110] Figure 5 The structural diagram of a computer system of an electronic device suitable for implementing the embodiments of the present application is shown.

[0111] It should be noted that Figure 5 The computer system of the electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0112] As Figure 5 shown, the computer system includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage section 508 into the random access memory (RAM) 503, such as executing the method described in the above embodiments. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0113] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. The drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that the computer program read from it can be installed into the storage section 508 as needed.

[0114] In particular, according to an embodiment of the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, various functions defined in the system of the present application are executed.

[0115] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. In the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The computer program included on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0116] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0117] The units involved in the embodiments described in the present application can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not, in some cases, constitute a limitation on the unit itself.

[0118] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device is caused to implement the methods described in the above embodiments.

[0119] It should be noted that although several modules or units of devices for performing actions are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0120] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the methods according to the embodiments of the present application.

[0121] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include the common general knowledge or conventional technical means in the technical field not disclosed in the present application.

[0122] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A method for predicting mining equipment mining costs based on genetic algorithm and machine learning, characterized in that: include: Acquire an initial data set related to equipment mining costs, wherein the data feature types in the initial data set include category features and numerical features; Performing data processing based on the initial data set to obtain a training data set, wherein the data processing includes at least one of generation based on a generative adversarial network, noise injection, and feature crossover; The pre-built XGBoost model is trained based on the training data set, and during the training process of the XGBoost model, the XGBoost model is validated by a five-fold cross validation method, and the parameters of the XGBoost model are optimized by a genetic algorithm; The mining cost of mining equipment is predicted based on the trained XGBoost model.

2. The method according to claim 1, characterized in that Data expansion is performed based on the initial data set to obtain a training data set, including: Based on the initial data set, a generative adversarial network is used to generate new data features to expand the initial data set to obtain a first data set; Injecting noise into the data features in the first data set to obtain a second data set; Cross-combining data features whose data feature types are category features in the second data set to expand the second data set to obtain a third data set; Feature encoding is performed on all data features in the third data set whose data feature types are categorical features, and all data features in the third data set whose data feature types are numerical features are normalized to obtain a training data set.

3. The method according to claim 2, characterized in that The data features whose data feature types are categorical features are encoded according to the following formula: Among them, TargetSum is the target value of the specific category feature up to the current sum; FeatureCount is the total number of category features with the same value as the current one observed so far; Prior is a constant value.

4. The method according to claim 1, characterized in that: The XGBoost model is shown in the following formula: in, is the prediction result of sample i, is the prediction result of the first t-1 trees, f t (x i ) is the prediction result of the tth tree.

5. The method according to claim 4, characterized in that The XGBoost model is optimized using a genetic algorithm, including: Randomly generate several sets of initial hyperparameter combinations as individuals; Determining the similarity corresponding to each of the individuals according to the sum of the Euclidean distances between each of the individuals and other individuals in the population; Using Gaussian distribution, converting the similarity into probability, and normalizing the probability; Calculate the entropy of the population based on the normalized probability and compare it with the historical average population entropy; Based on the comparison results, the ratio of crossover variation and genetic production of offspring is controlled.

6. The method according to any one of claims 1 to 5, characterized in that The initial data set includes at least one of equipment type, working time, workload, and energy consumption.

7. A mining equipment mining cost prediction device based on genetic algorithm and machine learning, characterized in that: include: An acquisition module, used for acquiring an initial data set related to equipment mining costs, wherein the data feature types in the initial data set include category features and numerical features; A first processing module, configured to perform data processing based on the initial data set to obtain a training data set, wherein the data processing includes at least one of generation based on a generative adversarial network, noise injection, and feature crossover; A training module, for training a pre-built XGBoost model based on the training data set, and during the training process of the XGBoost model, validating the XGBoost model using a five-fold cross validation method, and optimizing parameters of the XGBoost model using a genetic algorithm; The second processing module is used to predict the mining cost of mining equipment according to the trained XGBoost model.

8. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for predicting mining costs of mining equipment based on genetic algorithm and machine learning as described in any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the mining cost prediction method for mining equipment based on genetic algorithm and machine learning as described in any one of claims 1 to 6.

Images