Intelligent electro-hydraulic exploitation equipment control method and system

Abstract

The invention belongs to the technical field of equipment control, and discloses an intelligent electro-hydraulic mining equipment control method and system, and the method comprises the steps: obtaining and screening historical ore body mining data, and constructing a learning data set; training an equipment parameter optimization model by using the data set, wherein the model can predict an optimal control parameter sequence according to ore body characteristics and equipment state data; in the actual mining process, ore body characteristics and equipment state data are collected in real time and input into the optimization model to obtain a control parameter sequence; and the rotating speed of the hydraulic pump, the main loop pressure set value and the opening degree of the unloading valve serve as a target control sequence, and the electro-hydraulic mining equipment is controlled to work. According to the method, through a data-driven intelligent control strategy, dynamic optimization of control parameters is achieved, equipment can adjust key parameters in time according to ore body characteristic changes and state fluctuations, the mining efficiency and the equipment adaptability are remarkably improved, the service life of the equipment is prolonged, and the maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment control, and more specifically, to a method and system for controlling intelligent electro-hydraulic mining equipment. Background Art

[0002] Electro-hydraulic mining equipment combines electrical control systems with hydraulic actuators for mineral resource extraction. It is widely used in mines, tunnels, quarries, and other fields. Through the coordinated operation of the electro-hydraulic system, efficient operations such as excavation, crushing, and transportation are achieved. As a modern mining method, electro-hydraulic mining has become a key technical means of mineral resource development.

[0003] Despite the numerous advantages of electro-hydraulic mining equipment, existing operational control systems still face challenges and limitations. Traditional electro-hydraulic mining equipment control systems are relatively crude in their parameter adjustment, often relying on operator experience for settings. This makes it difficult to accurately adapt to the varying characteristics of different ore bodies and mining environments. This human-driven control approach can easily lead to inefficient energy utilization, increased equipment wear, and even safety hazards. Furthermore, during actual mining, ore bodies often vary significantly, and existing control systems, which often rely on fixed parameter settings, fail to respond to and adjust to these variations in real time. This results in unstable mining efficiency, increased equipment failure rates, and increased maintenance costs. Summary of the Invention

[0004] In order to overcome the problems of unstable mining efficiency, increased equipment failure rate and rising maintenance costs caused by existing technologies, the present invention proposes an intelligent electro-hydraulic mining equipment control method and system to solve the above problems.

[0005] The present invention provides the following technical solutions: A method for controlling intelligent electro-hydraulic mining equipment, comprising: The present invention also provides an intelligent electro-hydraulic mining equipment control system for implementing an intelligent electro-hydraulic mining equipment control method, comprising: Acquire historical ore mining data and filter it to obtain an ore mining learning dataset. The ore mining data includes ore body characteristics, equipment status data, and a control parameter sequence. The control parameter sequence is composed of control parameters collected at a preset frequency during the mining process. The control parameters include hydraulic pump speed, main circuit pressure setting value, and unloading valve opening. Using an ore body mining learning dataset to train an equipment parameter optimization model, the equipment parameter optimization model is used to obtain a control parameter sequence based on ore body characteristics and equipment status data; Acquire real-time equipment status data and ore body characteristics, and input the real-time equipment status data and ore body characteristics into the equipment parameter optimization model to obtain the control parameter sequence; The hydraulic pump speed in the obtained control parameter sequence is used as the target speed, the main circuit pressure setting value is used as the target pressure, and the unloading valve opening is used as the target opening to obtain a target control sequence; the electro-hydraulic mining equipment is controlled to perform mining operations according to the target control sequence.

[0006] Preferably, the acquiring of historical ore body mining data and screening to obtain an ore body mining learning data set comprises: For any historical ore body mining data, obtain the equipment status data in the ore body mining data; Determine whether ore body mining data can be used as reference data based on equipment status data; The ore body mining data with the judgment result of yes are screened out to form the ore body mining learning data set.

[0007] Preferably, the ore body characteristics include target ore hardness and content, main impurity hardness and content, and hardest impurity hardness and content; and the equipment status data include hydraulic oil temperature change rate, maximum hydraulic oil temperature, system pressure fluctuation rate, and equipment vibration intensity; The hydraulic oil temperature change rate is calculated by using a linear regression method based on all the hydraulic oil temperature data collected at a preset frequency during the mining process; the maximum hydraulic oil temperature is the maximum value of all the collected hydraulic oil temperature data; the system pressure fluctuation rate is calculated by using the ratio of the standard deviation to the average value of the system pressure data collected at a preset frequency during the mining process; the equipment vibration intensity is obtained by calculating the root mean square value of the vibration frequency data collected at a preset frequency during the mining process.

[0008] Preferably, judging whether the ore body mining data can be used as reference data based on the equipment status data includes: Determining whether the hydraulic oil temperature change rate is less than a preset hydraulic oil temperature change rate threshold; Determine whether the maximum hydraulic oil temperature is less than a preset maximum hydraulic oil temperature threshold; Determine whether the system pressure fluctuation rate is less than a preset system pressure fluctuation rate threshold; Determine whether the device vibration intensity is less than a preset device vibration intensity threshold; If the hydraulic oil temperature change rate, the maximum hydraulic oil temperature, the system pressure fluctuation rate and the equipment vibration intensity are all less than their respective thresholds, it is determined that the ore body mining data can be used as reference data; otherwise, it is determined that the ore body mining data cannot be used as reference data.

[0009] Preferably, the method of using the ore body mining learning data set to train the equipment parameter optimization model includes: Obtaining an ore body mining learning data set and preprocessing the data, wherein the preprocessing includes outlier detection and processing, feature normalization, and standardization; Randomly divide the data in the dataset into training set and test set; Calculate the comprehensive hardness index based on the ore body characteristics and calculate the stability index based on the equipment status data; The hardness comprehensive index and stability index are used as the main features, combined with the ore body characteristics and equipment status data features to construct a feature matrix; Build a gradient boosting decision tree model and set hyperparameters such as learning rate, maximum tree depth, and minimum number of split samples; The feature matrix is used as the input variable and the control parameter sequence is used as the output variable. The model is trained using the training set data, the root mean square error is used as the loss function, and the cross-validation method is used to optimize the hyperparameters. Use the test set to evaluate model performance. When the model accuracy reaches the preset threshold, save the model as a device parameter optimization model. If the accuracy does not reach the threshold, adjust the hyperparameters and retrain until the model accuracy reaches the preset threshold.

[0010] Preferably, the obtaining of real-time equipment status data and ore body characteristics includes: Before mining operations, samples of the ore body to be mined are collected, and the hardness and content of the target ore are obtained through mineral analysis technology; the main impurities in the sample are identified through mineral composition analysis technology, and their hardness and content are measured; the impurity with the highest hardness in the sample is identified through mineral hardness testing technology, and its hardness and content are measured; and the ore body characteristics are obtained by combining them; Start the equipment for a low-load trial run, and collect hydraulic oil temperature data, system pressure data, and equipment vibration data at a preset frequency; calculate the current equipment status data based on the collected data.

[0011] Preferably, inputting the real-time equipment status data and ore body characteristics into the equipment parameter optimization model comprises: Pre-processing of real-time ore body characteristics and equipment status data; Calculate the comprehensive hardness index based on the ore body characteristic data, and calculate the stability index based on the equipment status data; The hardness comprehensive index and stability index are used as the main features, combined with the ore body characteristics and equipment status data features to construct a feature matrix; The characteristic matrix is input into the equipment parameter optimization model.

[0012] Preferably, controlling the electro-hydraulic mining equipment to perform mining operations according to the target control sequence includes: Divide the target control sequence into multiple control periods in chronological order, and each control period corresponds to a set of control parameter values; Set the safety thresholds for hydraulic pump speed, main circuit pressure, and unloading valve opening; For each control period, the corresponding target speed is compared with the hydraulic pump speed safety threshold. If the target speed exceeds the safety threshold, the safety threshold is used as the actual control value and transmitted to the hydraulic pump motor through the frequency converter to adjust the actual speed of the hydraulic pump. Compare the corresponding target pressure with the main circuit pressure safety threshold. If the target pressure exceeds the safety threshold, the safety threshold is used as the actual control value, and the main circuit pressure value is set through the electro-hydraulic proportional valve controller; The corresponding target opening is compared with the safety threshold of the unloading valve opening. If the target opening exceeds the safety threshold, the safety threshold is used as the actual control value and the opening of the unloading valve is adjusted through the electro-hydraulic proportional control module.

[0013] A historical data screening module is used to obtain historical ore mining data and screen it to obtain an ore mining learning data set. The ore mining data includes ore body characteristics, equipment status data, and a control parameter sequence. The control parameter sequence is composed of control parameters collected at a preset frequency during the mining process. The control parameters include hydraulic pump speed, main circuit pressure setting value, and unloading valve opening; a model training module for training an equipment parameter optimization model using an ore body mining learning data set, wherein the equipment parameter optimization model is used to obtain a control parameter sequence based on ore body characteristics and equipment status data; A control parameter acquisition module is used to obtain real-time equipment status data and ore body characteristics, and input the real-time equipment status data and ore body characteristics into the equipment parameter optimization model to obtain a control parameter sequence; The control execution module is used to obtain a target control sequence by using the hydraulic pump speed in the obtained control parameter sequence as the target speed, the main circuit pressure setting value as the target pressure, and the unloading valve opening as the target opening; and control the electro-hydraulic mining equipment to perform mining operations according to the target control sequence.

[0014] The present invention provides a method and system for controlling intelligent electro-hydraulic mining equipment, which has the following beneficial effects: By systematically screening historical ore mining data based on key indicators such as hydraulic oil temperature change rate, maximum hydraulic oil temperature, system pressure fluctuation rate, and equipment vibration intensity, it is possible to effectively eliminate unstable, abnormal, or potentially risky mining data. This screening mechanism ensures the high quality of the learning dataset, providing a reliable foundation for subsequent model training, thereby significantly improving the model's accuracy and practicality. Compared to traditional control methods that rely on human experience, this learning method based on high-quality data can more objectively and comprehensively capture the relationship between ore body characteristics and control parameters.

[0015] By collecting real-time data on ore characteristics and equipment status, combined with trained models for parameter prediction, dynamic optimization of control parameters is achieved. This real-time adaptive adjustment mechanism enables electro-hydraulic mining equipment to promptly adjust key parameters such as hydraulic pump speed, main circuit pressure setpoint, and unloading valve opening based on changes in ore characteristics and fluctuations in equipment status, thereby maintaining optimal mining efficiency. Compared to traditional control systems with fixed parameter settings, this intelligent control approach significantly improves the equipment's adaptability to different ore bodies, thereby increasing mining efficiency and resource utilization, extending equipment life, and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a control method for intelligent electro-hydraulic mining equipment according to the present invention; Figure 2 This is a module schematic diagram of an intelligent electro-hydraulic mining equipment control system of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0018] Example 1 See also Figure 1 In this embodiment, a method for controlling intelligent electro-hydraulic mining equipment includes: S1. Obtain historical ore mining data and filter it to obtain an ore mining learning dataset. The ore mining data includes ore body characteristics, equipment status data, and a control parameter sequence. The control parameter sequence consists of control parameters collected at a preset frequency during the mining process. The control parameters include hydraulic pump speed, main circuit pressure setting value, and unloading valve opening. The historical ore mining data is obtained and filtered to obtain the ore mining learning data set including: For any historical ore body mining data, obtain the equipment status data in the ore body mining data; Determine whether ore body mining data can be used as reference data based on equipment status data; The ore body mining data with the judgment result of yes are screened out to form the ore body mining learning data set.

[0019] Ore body characteristics include target ore hardness and content, main impurity hardness and content, and hardest impurity hardness and content. Equipment status data includes hydraulic oil temperature change rate, maximum hydraulic oil temperature, system pressure fluctuation rate, and equipment vibration intensity. The hydraulic oil temperature change rate is calculated using the linear regression method based on all the hydraulic oil temperature data collected at a preset frequency during the mining process; the maximum hydraulic oil temperature is the maximum value of all the collected hydraulic oil temperature data; the system pressure fluctuation rate is calculated by the ratio of the standard deviation to the average value of the system pressure data collected at a preset frequency during the mining process; the equipment vibration intensity is obtained by calculating the root mean square value of the vibration frequency data collected at a preset frequency during the mining process.

[0020] Judging whether ore mining data can be used as reference data based on equipment status data includes: Determining whether the hydraulic oil temperature change rate is less than a preset hydraulic oil temperature change rate threshold; Determine whether the maximum hydraulic oil temperature is less than a preset maximum hydraulic oil temperature threshold; Determine whether the system pressure fluctuation rate is less than a preset system pressure fluctuation rate threshold; Determine whether the device vibration intensity is less than a preset device vibration intensity threshold; If the hydraulic oil temperature change rate, the maximum hydraulic oil temperature, the system pressure fluctuation rate and the equipment vibration intensity are all less than their respective thresholds, it is determined that the ore body mining data can be used as reference data; otherwise, it is determined that the ore body mining data cannot be used as reference data.

[0021] In this embodiment, the process of acquiring and filtering historical ore mining data to generate an ore mining learning dataset can be as follows: First, historical ore mining data records are exported from the enterprise mining data management system. Each data set contains three categories of information: ore characteristics, equipment status data, and control parameter sequences. Ore characteristics data include target ore hardness and content, major impurity hardness and content, and the hardest impurity hardness and content. This data can be obtained using a mineral hardness tester and composition analysis equipment. The control parameter sequence consists of control parameters collected at a preset frequency (e.g., every 5 seconds) during the mining process, including hydraulic pump speed, main circuit pressure setpoint, and unloading valve opening.

[0022] For each set of historical ore mining data, four key equipment status indicators are calculated. These indicators are derived from serial data consisting of various parameters collected at a preset frequency (e.g., every 5 seconds). The hydraulic oil temperature change rate is calculated using linear regression from the hydraulic oil temperature time series data. The maximum hydraulic oil temperature is determined by finding the maximum value in the hydraulic oil temperature series data. The system pressure fluctuation rate is calculated by taking the ratio of the standard deviation to the mean of the system pressure time series data. This indicator reflects the stability of the system pressure. A lower fluctuation rate indicates stable equipment operation, which helps extend equipment life and improve mining efficiency. Equipment vibration intensity is calculated by calculating the root mean square value of the vibration frequency series data. This indicator comprehensively reflects the energy of vibrations at various frequencies and is a key parameter for assessing equipment operating status. Excessive vibration intensity often indicates potential equipment failure or poor operating condition.

[0023] During the reference data screening process, reasonable screening thresholds can be preset based on equipment manufacturer recommendations or industry safety standards, including thresholds for hydraulic oil temperature change rate, maximum hydraulic oil temperature, system pressure fluctuation rate, and equipment vibration intensity. For each set of historical ore mining data, each indicator is sequentially determined to be below the corresponding preset threshold. If all four indicators are below their respective thresholds, the data set is marked as qualified and can be used as reference data; otherwise, it is marked as unqualified.

[0024] This screening method effectively eliminates unstable, abnormal, or potentially risky mining data, ensuring the quality of the learning dataset. By excluding operating condition data that could cause equipment damage or inefficiency, the accuracy and practicality of subsequent models can be significantly improved. After screening, all qualified data is combined into an ore body mining learning dataset. This data demonstrates good equipment operating status characteristics and provides high-quality samples for subsequent model training. This scientific data screening and learning dataset construction method ensures that the intelligent electro-hydraulic mining equipment control system learns based on high-quality historical experience data, thereby improving the equipment's adaptive control capabilities and mining efficiency, while reducing equipment failure rates and maintenance costs.

[0025] S2. Using the ore body mining learning data set to train an equipment parameter optimization model, the equipment parameter optimization model is used to obtain a control parameter sequence based on the ore body characteristics and equipment status data; Using the ore mining learning dataset to train the equipment parameter optimization model includes: Obtain ore mining learning data sets and preprocess the data, including outlier detection and processing, feature normalization, and standardization; Randomly divide the data in the dataset into training set and test set; Calculate the comprehensive hardness index based on the ore body characteristics and calculate the stability index based on the equipment status data; The hardness comprehensive index and stability index are used as the main features, combined with the ore body characteristics and equipment status data features to construct a feature matrix; Build a gradient boosting decision tree model and set hyperparameters such as learning rate, maximum tree depth, and minimum number of split samples; The feature matrix is used as the input variable and the control parameter sequence is used as the output variable. The model is trained using the training set data, the root mean square error is used as the loss function, and the cross-validation method is used to optimize the hyperparameters. Use the test set to evaluate model performance. When the model accuracy reaches the preset threshold, save the model as a device parameter optimization model. If the accuracy does not reach the threshold, adjust the hyperparameters and retrain until the model accuracy reaches the preset threshold.

[0026] In this embodiment, the process of training the equipment parameter optimization model using the ore body mining learning data set can be as follows: first, a screened ore body mining learning data set is obtained, and the data is preprocessed to improve the effect and efficiency of subsequent model training. The preprocessing steps include outlier detection and processing, feature normalization and standardization. Outlier detection can use statistical methods such as box plots or Z-score to identify data points that deviate from the normal distribution range. For detected outliers, the detected outliers can be deleted or processed using median replacement. Feature normalization and standardization convert features of different dimensions to the same scale. Min-Max normalization or Z-score standardization methods can be used, which helps to improve the convergence speed and stability of the model.

[0027] After preprocessing, the data in the dataset is randomly divided into a training set and a test set in a ratio of 8:2. The training set is used for the model learning process, while the test set is used to evaluate the model's generalization ability. In order to fully utilize the information of the ore body characteristics and equipment status data, it is necessary to construct more representative features. To calculate and extract the comprehensive hardness index based on the ore body characteristics, a weighted average method can be used to weight the target ore hardness, the main impurity hardness, and the hardest impurity hardness according to their respective content ratios to obtain an index that can comprehensively reflect the overall hardness characteristics of the ore body. Similarly, to calculate the stability index based on the equipment status data, indicators such as the hydraulic oil temperature change rate, the maximum hydraulic oil temperature, the system pressure fluctuation rate, and the equipment vibration intensity can be normalized and weighted to form an index that can reflect the overall stability of the equipment.

[0028] Next, the hardness index and stability index were used as key features, combined with the original orebody characteristics and equipment status data to construct a feature matrix. This feature engineering approach retains the original data information while introducing higher-level comprehensive features, helping the model better capture the complex relationships between orebody characteristics, equipment status, and control parameters.

[0029] In terms of model selection, this example uses a gradient boosting decision tree model, such as XGBoost or LightGBM. These models excel at handling complex nonlinear relationships and mixed-type features. During model building, key hyperparameters must be set, including the learning rate (typically set between 0.01 and 0.1), the maximum tree depth (which can be set between 3 and 10), and the minimum number of splits (which can be set between 5 and 20). These parameters directly impact the model's complexity and generalization ability, and their optimal values must be determined through subsequent optimization.

[0030] The model is trained using the feature matrix as input and the control parameter sequence as output, using the training set data. During training, the root mean square error (RMSE) is used as the loss function. This metric effectively measures the degree of deviation between the predicted and actual values. To determine the optimal hyperparameter combination, a K-fold cross-validation method (for example, K=5) can be used. The training set is divided into K subsets, with K-1 subsets used for training each time, and the remaining subset used for validation. After K cycles, the average performance is taken as the evaluation result for this set of hyperparameters. Methods such as grid search or Bayesian optimization can be used to systematically explore the hyperparameter space and find the optimal hyperparameter combination.

[0031] After training is complete, the model performance is evaluated using the test set. When the model's accuracy on the test set (measured by the coefficient of determination) reaches the preset standard, the model is saved as the final equipment parameter optimization model. If the model performance does not meet expectations, it is necessary to adjust hyperparameters and retrain, or consider adding features, increasing training samples, or trying different model structures until the model accuracy reaches the preset threshold. This iterative optimization approach ensures that the final equipment parameter optimization model has good predictive capabilities and can accurately predict the optimal control parameter sequence based on the input ore body characteristics and equipment status data, providing reliable decision support for intelligent electro-hydraulic mining equipment.

[0032] S3. Acquire real-time equipment status data and ore body characteristics, and input the real-time equipment status data and ore body characteristics into an equipment parameter optimization model to obtain a control parameter sequence; Obtain real-time equipment status data and ore body characteristics including: Before mining operations, samples of the ore body to be mined are collected, and the hardness and content of the target ore are obtained through mineral analysis technology; the main impurities in the sample are identified through mineral composition analysis technology, and their hardness and content are measured; the impurity with the highest hardness in the sample is identified through mineral hardness testing technology, and its hardness and content are measured; and the ore body characteristics are obtained by combining them; Start the equipment for a low-load trial run, and collect hydraulic oil temperature data, system pressure data, and equipment vibration data at a preset frequency; calculate the current equipment status data based on the collected data.

[0033] Inputting real-time equipment status data and ore body characteristics into the equipment parameter optimization model includes: Pre-processing of real-time ore body characteristics and equipment status data; Calculate the comprehensive hardness index based on the ore body characteristic data, and calculate the stability index based on the equipment status data; The hardness comprehensive index and stability index are used as the main features, combined with the ore body characteristics and equipment status data features to construct a feature matrix; The characteristic matrix is input into the equipment parameter optimization model.

[0034] In this embodiment, the process for obtaining real-time equipment status data and ore body characteristics can be as follows: Before actual mining operations, samples of the ore body to be mined must first be collected for analysis. Drilling equipment can be used to collect multiple ore body samples in a grid-based pattern across the mining area to ensure representativeness. The collected samples are then sent to an on-site mobile laboratory or a mine analysis center for rapid analysis. Using the aforementioned mineral analysis techniques, the hardness and content data of the target ore are obtained, and the hardness and content of the main impurities and the hardest impurities are identified, which are then combined to form a complete description of the ore body characteristics.

[0035] After obtaining the ore body characteristics, equipment status data needs to be collected. The electro-hydraulic mining equipment is started for a low-load trial run. The purpose of this step is to evaluate the equipment's initial operating status without placing excessive strain on the equipment. The low-load trial run is typically set at 30% to 50% of the rated load and lasts for 15 to 30 minutes to ensure that all equipment systems are fully preheated and reach a stable operating state. During the trial run, a sensor network installed on the equipment collects hydraulic oil temperature data, system pressure data, and equipment vibration data in real time at a preset frequency (e.g., once per second). Hydraulic oil temperature is collected using temperature sensors installed at key points in the hydraulic system; system pressure data is collected using pressure sensors installed in the main circuit and key branches; and equipment vibration data is collected using acceleration sensors fixed to key structural parts of the equipment.

[0036] Based on the data collected during the trial run, the current equipment status data is calculated using the aforementioned method, including the hydraulic oil temperature change rate, maximum hydraulic oil temperature, system pressure fluctuation rate, and equipment vibration intensity. These real-time equipment status indicators reflect the current operating status of the equipment and provide basic data for subsequent parameter optimization.

[0037] Next, the real-time data on ore characteristics and equipment status is fed into the trained equipment parameter optimization model. This real-time data undergoes preprocessing consistent with the training phase, including outlier detection, feature normalization, and standardization. After preprocessing, a comprehensive hardness index is calculated based on the ore characteristic data, and a stability index is calculated based on the equipment status data, using the same calculation methods used in the training phase to ensure data consistency.

[0038] The calculated hardness composite index and stability index are used as key features, combined with preprocessed orebody characteristics and equipment status data, to construct a feature matrix based on the feature order determined during model training. Finally, this constructed feature matrix is input into the equipment parameter optimization model, which predicts the optimal control parameter sequence based on the input feature data. This model prediction method, based on real-time data, enables electro-hydraulic mining equipment to adaptively adjust control parameters based on current orebody characteristics and equipment status, achieving intelligent mining operations and improving mining efficiency.

[0039] S4. Using the hydraulic pump speed in the obtained control parameter sequence as the target speed, the main circuit pressure setting value as the target pressure, and the unloading valve opening as the target opening to obtain a target control sequence; controlling the electro-hydraulic mining equipment to perform mining operations according to the target control sequence.

[0040] Controlling electro-hydraulic mining equipment to perform mining operations according to target control sequences includes: Divide the target control sequence into multiple control periods in chronological order, and each control period corresponds to a set of control parameter values; Set the safety thresholds for hydraulic pump speed, main circuit pressure, and unloading valve opening; For each control period, the corresponding target speed is compared with the hydraulic pump speed safety threshold. If the target speed exceeds the safety threshold, the safety threshold is used as the actual control value and transmitted to the hydraulic pump motor through the frequency converter to adjust the actual speed of the hydraulic pump. Compare the corresponding target pressure with the main circuit pressure safety threshold. If the target pressure exceeds the safety threshold, the safety threshold is used as the actual control value, and the main circuit pressure value is set through the electro-hydraulic proportional valve controller; The corresponding target opening is compared with the safety threshold of the unloading valve opening. If the target opening exceeds the safety threshold, the safety threshold is used as the actual control value and the opening of the unloading valve is adjusted through the electro-hydraulic proportional control module.

[0041] Example 2 See also Figure 2 The present invention provides an intelligent electro-hydraulic mining equipment control system for implementing an intelligent electro-hydraulic mining equipment control method, including: A historical data screening module is used to obtain historical ore mining data and screen it to obtain an ore mining learning dataset. The ore mining data includes ore body characteristics, equipment status data, and control parameter sequences. The control parameter sequences are composed of control parameters collected at a preset frequency during the mining process. The control parameters include hydraulic pump speed, main circuit pressure setting value, and unloading valve opening. A model training module is used to train an equipment parameter optimization model using an ore body mining learning dataset. The equipment parameter optimization model is used to obtain a control parameter sequence based on ore body characteristics and equipment status data. A control parameter acquisition module is used to obtain real-time ore body characteristics and equipment status data of the ore body to be mined, and input the real-time ore body characteristics and equipment status data into the equipment parameter optimization model to obtain a control parameter sequence; The control execution module is used to obtain a target control sequence by using the hydraulic pump speed in the obtained control parameter sequence as the target speed, the main circuit pressure setting value as the target pressure, and the unloading valve opening as the target opening; and control the electro-hydraulic mining equipment to perform mining operations according to the target control sequence.

[0042] In this embodiment, the target control sequence is obtained by using the hydraulic pump speed as the target speed, the main circuit pressure setting value as the target pressure, and the unloading valve opening as the target opening. The process of controlling the electro-hydraulic mining equipment to perform mining operations based on the target control sequence can be as follows: First, three key control parameters are extracted from the control parameter sequence output by the equipment parameter optimization model: the hydraulic pump speed, the main circuit pressure setting value, and the unloading valve opening. These are set as the target speed, target pressure, and target opening, respectively, to form the target control sequence. This target control sequence is a time series data that reflects the control parameter combinations that should be used at different times during the mining process.

[0043] To achieve precise timing control, the target control sequence needs to be divided into multiple control periods in chronological order, with each period corresponding to a set of control parameter values. The control periods can be divided based on a preset control frequency, such as every 30 seconds, or the period length can be dynamically adjusted based on changes in ore body characteristics. This segmented control approach enables the equipment to adapt to changes in ore body characteristics during mining, achieving more refined adaptive control.

[0044] Before actual control begins, safety thresholds for each control parameter must be set to ensure the equipment operates within a safe range. The hydraulic pump speed safety threshold is typically set at 85% to 95% of the rated speed, the main circuit pressure safety threshold is set at approximately 90% of the system design pressure, and the unloading valve opening safety threshold is determined based on system design and safety requirements. Setting these safety thresholds requires consideration of various factors, including the manufacturer's technical specifications, the equipment's age, and ambient temperature.

[0045] For each control period, the system executes the following control process: First, the target speed for the current period is compared with the hydraulic pump speed safety threshold. If the target speed is lower than or equal to the safety threshold, the target speed is used as the actual control value. If the target speed exceeds the safety threshold, the safety threshold is used as the actual control value to ensure safe equipment operation. After determining the actual control value, the control command is transmitted to the frequency converter via the industrial control network. The frequency converter adjusts the output frequency accordingly, thereby controlling the actual speed of the hydraulic pump motor. Adjusting the hydraulic pump speed directly affects the system flow rate and is fundamental to controlling the operating capacity of the mining equipment.

[0046] Similarly, the target pressure for the current time period is compared with the main circuit pressure safety threshold. If the target pressure is lower than or equal to the safety threshold, the target pressure is used directly as the actual control value; if the target pressure exceeds the safety threshold, the safety threshold is used as the actual control value. After determining the actual control value, the main circuit pressure value is set by the electro-hydraulic proportional valve controller. Main circuit pressure control typically uses a closed-loop control method. The controller dynamically adjusts the opening of the proportional valve based on the actual pressure value fed back by the pressure sensor to stabilize the system pressure near the set value. Precise control of the main circuit pressure is crucial for improving mining efficiency and protecting equipment.

[0047] For the unloading valve opening, the target opening for the current time period is compared with the unloading valve opening safety threshold. If the target opening is less than or equal to the safety threshold, the target opening is used directly as the actual control value; if the target opening exceeds the safety threshold, the safety threshold is used as the actual control value. After determining the actual control value, the unloading valve opening is adjusted via the electro-hydraulic proportional control module. As a key component in system pressure regulation, the opening of the unloading valve directly affects the system's pressure distribution and energy utilization efficiency. By precisely controlling the unloading valve opening, energy loss can be minimized while maintaining system operating pressure.

[0048] Through this segmented adaptive control method based on model prediction, electro-hydraulic mining equipment can adjust control parameters in real time based on ore body characteristics and its own status, achieving intelligent mining operations. This not only improves mining efficiency and resource utilization, but also extends equipment life, reduces maintenance costs, and creates significant economic benefits for mining companies. In actual application, as mining experience accumulates and data becomes more abundant, the system's intelligence and adaptability can be further enhanced by regularly updating and optimizing the equipment parameter optimization model.

[0049] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only one type. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0050] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0051] 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 scope of protection of the present invention.

Claims

1. A method for controlling intelligent electro-hydraulic mining equipment, characterized in that: include: Acquire historical ore mining data and filter it to obtain an ore mining learning dataset. The ore mining data includes ore body characteristics, equipment status data, and a control parameter sequence. The control parameter sequence is composed of control parameters collected at a preset frequency during the mining process. The control parameters include hydraulic pump speed, main circuit pressure setting value, and unloading valve opening. Using an ore body mining learning dataset to train an equipment parameter optimization model, the equipment parameter optimization model is used to obtain a control parameter sequence based on ore body characteristics and equipment status data; Acquire real-time equipment status data and ore body characteristics, and input the real-time equipment status data and ore body characteristics into the equipment parameter optimization model to obtain the control parameter sequence; The hydraulic pump speed in the obtained control parameter sequence is used as the target speed, the main circuit pressure setting value is used as the target pressure, and the unloading valve opening is used as the target opening to obtain a target control sequence; the electro-hydraulic mining equipment is controlled to perform mining operations according to the target control sequence.

2. The intelligent electro-hydraulic mining equipment control method according to claim 1, characterized in that: The acquisition of historical ore body mining data and screening to obtain an ore body mining learning data set includes: For any historical ore body mining data, obtain the equipment status data in the ore body mining data; Determine whether ore body mining data can be used as reference data based on equipment status data; The ore body mining data with the judgment result of yes are screened out to form the ore body mining learning data set.

3. The intelligent electro-hydraulic mining equipment control method according to claim 2, characterized in that: The ore body characteristics include the target ore hardness and content, the main impurity hardness and content, the hardest impurity hardness and content, and the equipment status data include the hydraulic oil temperature change rate, the maximum hydraulic oil temperature, the system pressure fluctuation rate, and the equipment vibration intensity; The hydraulic oil temperature change rate is calculated by using a linear regression method based on all hydraulic oil temperature data collected at a preset frequency during the mining process; the maximum hydraulic oil temperature is the maximum value of all the collected hydraulic oil temperature data; The system pressure fluctuation rate is calculated by the ratio of the standard deviation to the average value of the system pressure data collected at a preset frequency during the mining process; The vibration intensity of the equipment is obtained by calculating the root mean square value of vibration frequency data collected at a preset frequency during the mining process.

4. The intelligent electro-hydraulic mining equipment control method according to claim 3, characterized in that: The determination of whether the ore body mining data can be used as reference data based on the equipment status data includes: Determining whether the hydraulic oil temperature change rate is less than a preset hydraulic oil temperature change rate threshold; Determine whether the maximum hydraulic oil temperature is less than a preset maximum hydraulic oil temperature threshold; Determine whether the system pressure fluctuation rate is less than a preset system pressure fluctuation rate threshold; Determine whether the device vibration intensity is less than a preset device vibration intensity threshold; If the hydraulic oil temperature change rate, the maximum hydraulic oil temperature, the system pressure fluctuation rate and the equipment vibration intensity are all less than their respective thresholds, it is determined that the ore body mining data can be used as reference data; otherwise, it is determined that the ore body mining data cannot be used as reference data.

5. The intelligent electro-hydraulic mining equipment control method according to claim 4, characterized in that: The use of the ore body mining learning data set to train the equipment parameter optimization model includes: Obtaining an ore body mining learning data set and preprocessing the data, wherein the preprocessing includes outlier detection and processing, feature normalization, and standardization; Randomly divide the data in the dataset into training set and test set; Calculate the comprehensive hardness index based on the ore body characteristics and calculate the stability index based on the equipment status data; The hardness comprehensive index and stability index are used as the main features, combined with the ore body characteristics and equipment status data features to construct a feature matrix; Build a gradient boosting decision tree model and set hyperparameters such as learning rate, maximum tree depth, and minimum number of split samples; The feature matrix is used as the input variable and the control parameter sequence is used as the output variable. The model is trained using the training set data, the root mean square error is used as the loss function, and the cross-validation method is used to optimize the hyperparameters. Use the test set to evaluate model performance. When the model accuracy reaches the preset threshold, save the model as a device parameter optimization model. If the accuracy does not reach the threshold, adjust the hyperparameters and retrain until the model accuracy reaches the preset threshold.

6. The intelligent electro-hydraulic mining equipment control method according to claim 5, characterized in that: The acquisition of real-time equipment status data and ore body characteristics includes: Before mining operations, samples of the ore body to be mined are collected, and the hardness and content of the target ore are obtained through mineral analysis technology; the main impurities in the sample are identified through mineral composition analysis technology, and their hardness and content are measured; the impurity with the highest hardness in the sample is identified through mineral hardness testing technology, and its hardness and content are measured; and the ore body characteristics are obtained by combining them; Start the equipment for a low-load trial run, and collect hydraulic oil temperature data, system pressure data, and equipment vibration data at a preset frequency; calculate the current equipment status data based on the collected data.

7. The intelligent electro-hydraulic mining equipment control method according to claim 6, characterized in that: The inputting of real-time equipment status data and ore body characteristics into the equipment parameter optimization model includes: Pre-processing of real-time ore body characteristics and equipment status data; Calculate the comprehensive hardness index based on the ore body characteristic data, and calculate the stability index based on the equipment status data; The hardness comprehensive index and stability index are used as the main features, combined with the ore body characteristics and equipment status data features to construct a feature matrix; The characteristic matrix is input into the equipment parameter optimization model.

8. The intelligent electro-hydraulic mining equipment control method according to claim 7, characterized in that: Controlling the electro-hydraulic mining equipment to perform mining operations according to the target control sequence includes: Divide the target control sequence into multiple control periods in chronological order, and each control period corresponds to a set of control parameter values; Set the safety thresholds for hydraulic pump speed, main circuit pressure, and unloading valve opening; For each control period, the corresponding target speed is compared with the hydraulic pump speed safety threshold. If the target speed exceeds the safety threshold, the safety threshold is used as the actual control value and transmitted to the hydraulic pump motor through the frequency converter to adjust the actual speed of the hydraulic pump. Compare the corresponding target pressure with the main circuit pressure safety threshold. If the target pressure exceeds the safety threshold, the safety threshold is used as the actual control value, and the main circuit pressure value is set through the electro-hydraulic proportional valve controller; The corresponding target opening is compared with the safety threshold of the unloading valve opening. If the target opening exceeds the safety threshold, the safety threshold is used as the actual control value and the opening of the unloading valve is adjusted through the electro-hydraulic proportional control module.

9. An intelligent electro-hydraulic mining equipment control system, used to implement an intelligent electro-hydraulic mining equipment control method according to any one of claims 1 to 8, characterized in that: include: A historical data screening module is used to obtain historical ore mining data and screen it to obtain an ore mining learning data set. The ore mining data includes ore body characteristics, equipment status data, and a control parameter sequence. The control parameter sequence is composed of control parameters collected at a preset frequency during the mining process. The control parameters include hydraulic pump speed, main circuit pressure setting value, and unloading valve opening; a model training module for training an equipment parameter optimization model using an ore body mining learning data set, wherein the equipment parameter optimization model is used to obtain a control parameter sequence based on ore body characteristics and equipment status data; A control parameter acquisition module is used to obtain real-time equipment status data and ore body characteristics, and input the real-time equipment status data and ore body characteristics into the equipment parameter optimization model to obtain a control parameter sequence; The control execution module is used to obtain a target control sequence by using the hydraulic pump speed in the obtained control parameter sequence as the target speed, the main circuit pressure setting value as the target pressure, and the unloading valve opening as the target opening; and control the electro-hydraulic mining equipment to perform mining operations according to the target control sequence.

Images