Deep sea rock debris granularity information prediction management method and related equipment

Abstract

The embodiment of the invention provides a deep-sea rock debris granularity information prediction management method and related equipment, and the method comprises the steps: obtaining the collection data of development equipment in a current collection environment in real time, the collection data comprising collection environment data and collection mineral data; performing prediction analysis on the acquired data through a preset rock debris particle size prediction model, and determining predicted distribution data of rock debris particle sizes corresponding to the acquired minerals under the current acquired environment data; and based on the predicted distribution data, adjusting acquisition parameters of the development equipment and executing a corresponding development strategy. Through the steps of the method, the mining operation is optimized and adjusted by combining the environment data and the mineral data which are collected in real time and utilizing the accurate granularity prediction model, the rock debris recovery rate can be remarkably increased in the deep-sea mining operation, generation and loss of fine particles are reduced, and the lowest disturbance of the mining process to the environment is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mineral resource development, and in particular to a deep-sea rock debris particle size information prediction management method and device, an electronic device and a storage medium thereof. BACKGROUND

[0002] With the development of deep-sea mineral resources, how to efficiently carry out mining operations and ensure minimal environmental impact has become a major technical challenge. In the process of deep-sea mining, the development equipment will generate a large amount of rock debris particles, especially fine particles, which can have a serious impact on the ecological environment of the surrounding sea area. In addition, traditional rock debris particle size prediction methods mostly rely on laboratory data or static models, which cannot respond to changes in the deep-sea environment in real time, resulting in low ore recovery rate, poor mining operation efficiency, and increased environmental pollution.

[0003] In the prior art, although there are some rock debris particle size prediction methods, most of them ignore the dynamic changes of the deep-sea environment and the optimization adjustment of the mining equipment. For example, changes in environmental factors such as ore body depth, hydrostatic pressure, and ore characteristics will affect the crushing behavior of the rock and the particle size distribution of the rock debris. These factors are particularly important in the process of deep-sea mining, so traditional methods often fail to effectively cope with the complexity of the deep-sea environment.

[0004] Therefore, the existing deep-sea rock debris particle size information prediction management method has the problem of being unable to predict the particle size distribution of the rock debris in real time and adjust the operating parameters of the mining equipment according to the predicted distribution data. SUMMARY

[0005] The present application provides a deep-sea rock debris particle size information prediction management method to solve the problem that the existing deep-sea rock debris particle size information prediction management method cannot predict the particle size distribution of the rock debris in real time and adjust the operating parameters of the mining equipment according to the predicted distribution data.

[0006] In a first aspect, the present application provides a deep-sea rock debris particle size information prediction management method, which comprises the following steps: real-time acquisition of collection data of the development equipment under the current collection environment, the collection data including collection environment data and collection mineral data; predictive analysis of the collection data by a pre-set rock debris particle size prediction model to determine the predicted distribution data of the collection mineral corresponding rock debris particle size under the current collection environment data; adjustment of the collection parameters of the development equipment based on the predicted distribution data and execution of the corresponding development strategy.

[0007] Optionally, the real-time acquisition of the collection data of the development equipment under the current collection environment comprises: acquire depth data and pressure data of a current acquisition environment in which the development device is located through a preset environment sensor; In the database, acquisition mineral data that the development device is developing is determined, and the acquisition mineral data includes mineral types and mineral parameter data.

[0008] Optionally, before the acquisition data is predicted and analyzed through the preset rock debris granularity prediction model to determine the predicted distribution data of the rock debris granularity corresponding to the acquisition mineral under the current acquisition environment data, the method further includes: acquiring tool characteristic parameters of the development device, the tool characteristic parameters including a rotational speed and a diameter of the development device; based on the tool characteristic parameters of the development device and the acquisition mineral data, a first strain model layer of a rock breaking tool and an ore body is constructed, and the first strain model layer is used to describe a strain relationship between the development device and the ore body; based on the acquisition environment data in which the development device is located, a second strain model layer of internal collapse of the ore body is constructed, and the second strain model layer is used to describe an internal self-collapse relationship of the acquisition mineral in the current acquisition environment data; based on the first strain model layer and the second strain model layer, the preset rock debris granularity prediction model is determined.

[0009] Optionally, the predicted distribution data of the rock debris granularity corresponding to the acquisition mineral under the current acquisition environment data is determined by predicting and analyzing the acquisition data through the preset rock debris granularity prediction model, including: the acquisition mineral data is processed through the first strain model layer to determine crushing capacity data of the current acquisition mineral by the current development device; based on the crushing capacity data, a first prediction distribution coefficient of the current acquisition mineral is determined.

[0010] Optionally, the predicted distribution data of the rock debris granularity corresponding to the acquisition mineral under the current acquisition environment data is determined by predicting and analyzing the acquisition data through the preset rock debris granularity prediction model, including: the acquisition environment data and the acquisition mineral data are processed through the second strain model layer to determine total damage data of the current acquisition mineral under the current acquisition environment data; based on the total damage data, a second prediction distribution coefficient of the current acquisition mineral is determined.

[0011] Optionally, the total damage data of the current acquisition mineral under the current acquisition environment data is determined by processing the acquisition environment data and the acquisition mineral data through the second strain model layer, including: According to the depth data and pressure data under the current collected environment data, crack density increment data of the current collected mineral is determined; According to the development length, damage accumulation calculation of the crack density increment data is performed, and the crushing time of the current collected mineral is determined. Based on the volume of the current collected mineral and the crushing time, total damage data of the current collected mineral is determined.

[0012] Optionally, the adjusting the collection parameters of the development equipment and performing the corresponding development strategy based on the predicted distribution data comprises: Based on the predicted distribution data, the development impact force, rotation speed, cutting thickness, traction speed and operation mode of the development equipment are adjusted. According to the predicted distribution data, the depth data of the development equipment is adjusted, and the rock breaking tool with corresponding development capacity is replaced.

[0013] In a second aspect, the present application further provides a deep-sea rock debris particle size information prediction management device, comprising: A first collection module is configured to acquire collection data of a development equipment under a current collection environment in real time, wherein the collection data comprises collection environment data and collected mineral data. A first determination module is configured to perform prediction analysis on the collection data by using a preset rock debris particle size prediction model, and determine predicted distribution data of rock debris particle size corresponding to the collected mineral under the current collection environment data. A first adjustment module is configured to adjust collection parameters of the development equipment and perform a corresponding development strategy based on the predicted distribution data.

[0014] In a third aspect, the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the deep-sea rock debris particle size information prediction management method provided by the present application.

[0015] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the deep-sea rock debris particle size information prediction management method provided by the present application.

[0016] In the present application, the acquisition data of the development device in the current acquisition environment is acquired in real time, and the acquisition data includes acquisition environment data and acquisition mineral data; the acquisition data is predicted and analyzed by a preset rock debris particle size prediction model to determine the predicted distribution data of the acquisition mineral corresponding to the rock debris particle size under the current acquisition environment data; and the acquisition parameters of the development device are adjusted based on the predicted distribution data and the corresponding development strategy is executed. Through the above method steps, the mining operation is optimized and adjusted by combining the real-time acquisition of the environment data and the mineral data, using the accurate particle size prediction model, which can significantly improve the rock debris recovery rate in deep sea mining operation, reduce the loss of fine particles, and ensure the minimum disturbance to the environment in the mining process. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0018] Figure 1 is a flow chart of a deep sea rock debris particle size information prediction management method provided by an embodiment of the present application; Figure 2 is a structural schematic diagram of another deep sea rock debris particle size information prediction management device provided by an embodiment of the present application; Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0020] As shown in Figure 1 , a deep sea rock debris particle size information prediction management method provided by an embodiment of the present application includes the following steps: Figure 1 is a flow chart of a deep sea rock debris particle size information prediction management method provided by an embodiment of the present application, which includes the following steps: 101, acquiring acquisition data of a development device in a current acquisition environment in real time.

[0021] In the embodiment of the present application, the deep-sea rock debris size information prediction management method described above can be applied to a deep-sea rock debris size information prediction management platform. The deep-sea rock debris size information prediction management platform has functions such as mineral collection data processing, mineral collection data transmission and reception, and mineral collection data memory storage, and can be constructed based on a server or a server cluster. The server or server cluster can be an electronic device with mineral collection data capability.

[0022] The development equipment described above can be machinery and tools used for mineral development, crushing, collection, and other operations in the mining process. Specifically, because different development equipment corresponds to different functional types, different development equipment needs to be adapted for collecting different types of minerals. Therefore, in deep-sea resource development operations, different functional types and resistant development equipment can be selected according to different deep-sea environments and different mineral types.

[0023] Generally, deep-sea drilling machines can be used for ore drilling and development operations at a depth of 2000 meters under the sea. Because deep-sea drilling machines are equipped with depth sensors, pressure sensors, and ore hardness testers, and have certain resistance to deep-sea environments, they can ensure the efficiency and accuracy of mining operations.

[0024] The current collection environment described above can refer to the physical and geographical environmental conditions in which the development equipment is located at a certain time. It can generally include but is not limited to water depth, hydrostatic pressure, temperature, etc. in the mining area.

[0025] The collection data described above can include but is not limited to collection environment data and collection mineral data, as well as various data obtained in real time during the development process through sensors or other monitoring equipment.

[0026] The collection environment data described above can include but is not limited to various physical, chemical, and geographical data about the environment in which the mining area is located, which is collected in real time during the development process through sensors and monitoring systems. These data describe the environmental characteristics of the mining area where the development equipment is located, mainly including water depth, temperature, pressure, flow rate, etc. For example, in deep-sea mining operations, development equipment such as drilling machines and mining equipment will operate in deep-sea environments. The collected environmental data can include: Water depth data: the depth of the current development equipment in the mining area is monitored in real time by a depth sensor, for example, 2000 meters; Hydrostatic pressure: the hydrostatic pressure is monitored by a pressure sensor according to the change in water depth, assuming that the hydrostatic pressure is 20 Mpa at a depth of 2000 meters; Water temperature data: the water temperature sensor measures the water temperature to be 4°C; Flow rate data: the flow rate of ocean currents in the deep sea also affects the diffusion of rock debris, so the mining equipment can be equipped with a flow rate sensor to monitor the flow rate in real time.

[0027] The mineral data collected above can refer to the real-time acquisition of characteristic data about the ore or mineral itself through sensors, detection instruments and other equipment, including but not limited to the type, hardness, composition, brittle toughness of the ore, and other characteristic information for evaluating the development difficulty of the ore body and the particle size distribution of the rock debris. For example, in deep-sea mining operations, the equipment for collecting mineral data can include: Mineral hardness sensor: used to measure the hardness of the ore in real time, for example, the sensor detects that the hardness of the ore is 8.5 (Mohs hardness), indicating that the ore is hard and may require a larger impact force to break; Mineral composition analyzer: this device detects the main components in the ore through chemical composition analysis technology, such as the content of elements such as copper, cobalt, iron, etc. For example, the content of copper in the ore is 10%, and the content of cobalt is 0.6%; Mineral brittle toughness tester: measures the conversion or transition degree of deep-sea rock brittle toughness, which is represented by a numerical value. The higher the conversion / transition degree, the easier it is to produce fine particles.

[0028] 102. Predictive analysis of the collected data through the preset rock debris particle size prediction model to determine the predicted distribution data of the rock debris particle size corresponding to the collected mineral under the current collection environment data.

[0029] In the embodiments of the present application, the above-mentioned preset rock debris particle size prediction model can refer to a deep learning model that can predict the distribution of rock debris particle size according to the physical characteristics of the target ore and the corresponding collection environment data. Generally, the above-mentioned preset rock debris particle size prediction model can analyze the mineral data and environmental data collected in a specific environment to predict the distribution of rock debris particle size. Specifically, the above-mentioned preset rock debris particle size prediction model can integrate rock mechanics principles, ore breaking characteristics and environmental factors to provide particle size prediction for mining operations under different depths and ore body conditions. For example, in deep-sea mining operations, the above-mentioned preset rock debris particle size prediction model can analyze how the high-pressure environment of the deep sea affects the breaking degree of the ore, crack propagation and the size of the rock debris particles. In shallower waters, more large particles can be formed after rock breaking, while in deeper waters, the expansion of a large number of cracks in the rock can lead to the production of fine rock debris particles due to the increase in hydrostatic pressure.

[0030] In one possible embodiment, the above-mentioned deep-sea rock debris particle size information prediction management platform can calculate and analyze the current real-time collected environmental data and mineral data based on the above-mentioned preset rock debris particle size prediction model, thereby predicting the particle size distribution of the rock debris. The analysis process includes inputting the collected data into the model, calculating the distribution ratio of the rock debris in different particle size ranges, and providing data support for subsequent operation adjustment and optimization.

[0031] The prediction distribution data can refer to the prediction analysis of the size and distribution of the ore debris, which is usually expressed in size intervals and corresponding distribution ratios. This data reflects the size and distribution of the ore debris under different environmental conditions, and is the basis for adjusting the operating parameters of the mining equipment.

[0032] Specifically, the prediction distribution data can specifically show the size and distribution ratio of the ore debris, and can also be prediction information of the distribution direction, for example, the size of the ore debris in the current area is between 2-5 mm, and the percentage is 60%, and the distribution is diffused to the lower part of the seabed.

[0033] The size of the ore debris can refer to the size and distribution of the ore debris produced by crushing the ore in the mining operation. Specifically, fine ore debris may be dispersed by water flow and have a greater impact on the surrounding environment, while large ore debris size may result in a decrease in ore recovery rate, for example, after crushing, the ore debris may be mostly concentrated in 2-5 mm, and a small part of the size is less than 0.5 mm. According to the hardness, brittleness and mining environmental conditions of the ore, larger size of the ore debris requires stronger impact force to break, and the recovery of fine particles of the ore debris may face more environmental challenges, such as water flow dispersion and pollution. By predicting the size of the ore debris, the parameters of the mining equipment can be effectively adjusted to avoid resource waste and reduce the negative impact on the environment.

[0034] 103、Based on the prediction distribution data, adjust the collection parameters of the development equipment and execute the corresponding development strategy.

[0035] In the embodiment of the present application, the deep-sea ore debris size information prediction management platform analyzes the prediction distribution data to obtain the parameters that need to be adjusted for the corresponding development equipment under the current development environment, including but not limited to impact force, mining depth and mining rate, etc., so as to ensure that the distribution of the size of the ore debris under the development intensity meets the expected standard, thereby improving the ore recovery rate, optimizing the mining operation process, and reducing the impact on the environment.

[0036] In the embodiment of the present application, the real-time collection data of the development equipment in the current collection environment is obtained, including collection environment data and collection mineral data; the collection data is predicted and analyzed by a preset ore debris size prediction model to determine the prediction distribution data of the corresponding ore debris size of the collection mineral under the current collection environment data; based on the prediction distribution data, the collection parameters of the development equipment are adjusted and the corresponding development strategy is executed. Through the above method steps, combined with the real-time collection of environmental data and mineral data, the precise size prediction model is used to optimize and adjust the mining operation, which can significantly improve the recovery rate of the ore debris in the deep-sea mining operation, reduce the loss of fine particles, and ensure the minimum disturbance to the environment in the mining process.

[0037] Optionally, in the step of obtaining the collection data of the development equipment in the current collection environment in real time, the depth data and pressure data of the current collection environment in which the development equipment is located can also be collected through preset environmental sensors; in the database, the collection mineral data that the development equipment is currently developing is determined.

[0038] In embodiments of the present invention, the aforementioned pre-set environmental sensors may be sensor modules integrated into mining equipment, capable of real-time monitoring and collecting environmental data about the equipment. These sensors are pre-calibrated to ensure accurate measurement of environmental conditions, such as water depth and pressure, during actual mining operations. Common environmental sensors used in deep-sea mining include depth sensors and pressure sensors, which measure the depth of the water in which the equipment is located and the hydrostatic pressure of the surrounding environment, respectively.

[0039] The above depth data can be used to indicate the water depth of the water area where the development equipment is currently located. Generally speaking, the hydrostatic pressure of seawater on the development equipment will be affected by the depth at which it is located. The greater the water depth, that is, the greater the depth data, the greater the pressure, and the greater the pressure acting between the development equipment and the corresponding minerals.

[0040] The above pressure data will affect the mineral crack propagation, damage accumulation and rock fragment particle size. Therefore, when performing predictive distribution data analysis, it is necessary to consider the impact of pressure data on mineral distribution to ensure the accuracy of particle size prediction.

[0041] The above-mentioned collected mineral data includes but is not limited to mineral type and mineral parameter data.

[0042] The mineral type mentioned above can refer to the type of mineral being developed or the classification of a mineral resource. Different mineral types have different physical and chemical properties, which affect their performance during the crushing process. For example, the hardness, brittleness, and mineralogical composition of polymetallic sulfide ores and cobalt-rich crusts can vary, which in turn determines the particle size of the rock fragments produced during crushing.

[0043] The aforementioned mineral parameter data can refer to a set of numerical values ​​describing the physical and chemical properties of a mineral, including density, hardness, compressive strength, fracture toughness coefficient, and crack density. These can be measured or retrieved from a database based on the type and properties of the ore and used to characterize the mineral's behavior during the crushing process. For example, the ore's compressive strength affects the external forces it can withstand during crushing, the mineral's fracture toughness affects crack propagation, and the ore's crack density is closely related to the formation of rock fragment particle size.

[0044] In a possible embodiment, the deep-sea cutting particle size information prediction management platform collects deep-sea environment data in real time through a preset environment sensor arranged on the development device, and matches and determines the collected mineral type and mineral parameter data through a background database.

[0045] Optionally, before predicting and analyzing the collected data through the preset cutting particle size prediction model to determine the predicted distribution data of the cutting particle size of the collected mineral under the current collection environment data, the step further includes obtaining tool characteristic parameters of the development device; constructing a first strain model layer of the rock breaking tool and the ore body based on the tool characteristic parameters of the development device and the collected mineral data; constructing a second strain model layer of the internal collapse of the ore body based on the collection environment data of the development device; and determining the preset cutting particle size prediction model based on the first strain model layer and the second strain model layer.

[0046] In the embodiment of the present application, the tool characteristic parameters can include but are not limited to the rotational speed, diameter and other operation parameters of the development device for describing the development intensity. Specifically, the rotational speed directly affects the contact force and breaking efficiency of the device and the ore body, a higher rotational speed can provide greater impact force to help the device break the ore more effectively, while the diameter affects the contact area of the device, and thus affects the range and intensity of ore breaking. Through these parameters, the platform can adjust the operation state of the tool, thereby optimizing the cutting particle size prediction.

[0047] In a possible embodiment, before development, the deep-sea cutting particle size information prediction management platform can build two key strain model layers based on the tool characteristic parameters of the development device and the collected mineral data. These model layers are used to describe the interaction between the development device and the ore body, helping the platform to predict the particle size distribution of the cutting.

[0048] The first strain model layer is used to describe the strain relationship between the development device and the ore body, wherein the strain relationship can refer to the change of shape and size of an object under external force, which is usually manifested as deformation of the object. For deep-sea mining operations, the contact between the development device and the ore body will cause the ore body to deform and produce cracks, and the crack propagation eventually leads to the formation of cutting. The first strain model layer calculates the strain distribution of the ore body under the action of the development device by considering factors such as the rotational speed, diameter of the development device and mineral type (such as ore hardness, toughness, etc.). For example, under a higher rotational speed, the strain is larger and the ore is more likely to break; while a smaller device diameter can cause the strain to concentrate in a local area, resulting in poor breaking effect.

[0049] The second strain model layer is used to describe the internal self-disintegration relationship of the collected mineral in the current collection environment data. The hydrostatic pressure and water depth in the deep sea environment have a significant impact on the microstructure (such as crack density, lattice defects, etc.) of the ore inside. Under higher pressure, the cracks inside the ore can accelerate the expansion and cause the ore to self-disintegrate. The second strain model layer combines the physical properties (such as hardness, brittleness) of the collected mineral and the environmental data (such as depth, pressure) to simulate the fragmentation process of the ore body under environmental pressure. Through this layer model, the platform can accurately calculate the self-disintegration rate of the ore and the formation and distribution characteristics of the rock debris under a specific collection environment.

[0050] Optionally, in the step of predicting and analyzing the collection data by the preset rock debris particle size prediction model to determine the predicted distribution data of the rock debris particle size of the collected mineral under the current collection environment data, the method further includes processing the collected mineral data by the first strain model layer to determine the fragmentation capability data of the current development device on the current collected mineral; and determining the first predicted distribution coefficient of the current collected mineral based on the fragmentation capability data.

[0051] In the embodiments of the present application, the strain distribution of the development device after contacting the ore body can be obtained by analyzing and calculating the collected mineral data by the first strain model layer. Specifically, the tool characteristic parameters (such as rotation speed, diameter, etc.) of the development device and the physical property data (such as ore hardness, brittleness, etc.) of the collected mineral can be input into the strain model to simulate the interaction between the device and the ore body, which specifically means that after the ore body is subjected to the action of the device, the ore body deforms and cracks are generated. The model calculates the fragmentation characteristics of the mineral under this operation condition based on the strain distribution.

[0052] The fragmentation capability data can refer to the fragmentation effect of the current development device on the current collected mineral under specific mining operation conditions. This data reflects the fragmentation capability of the device when processing specific minerals, for example, the number or degree of fragmentation of the ore that can be effectively fragmented by the device under different rotation speeds and diameters. Specifically, when the rotation speed and diameter of the device are high, the strain force acting on the ore body is large, the fragmentation capability is strong, the crack propagation of the ore is more significant, and more small particle rock debris is generated. Lower rotation speed or smaller device diameter may result in insufficient fragmentation of the ore, and the proportion of large blocks of ore in the ore body is high. The fragmentation capability data is a quantitative analysis of the interaction between the device and the ore, which reflects the fragmentation efficiency of the ore under specific device conditions.

[0053] The first prediction distribution coefficient can refer to determining the parameterized coefficient of the size distribution of the crushed rock after the mineral is crushed based on the crushing capacity data. Specifically, the size and proportion of the crushed rock after crushing are predicted through the crushing capacity data. This coefficient reflects the influence of the operating parameters of the equipment (such as speed, diameter, etc.) and the characteristics of the mineral (such as hardness, brittleness) on the size of the crushed rock. For example, larger crushing capacity data can correspond to finer crushed rock size, while smaller crushing capacity can result in more large-particle crushed rock.

[0054] Optionally, in the step of predicting and analyzing the collected data through the preset crushed rock size prediction model to determine the predicted distribution data of the crushed rock size corresponding to the collected mineral under the current collected environmental data, the step further comprises processing the collected environmental data and the collected mineral data through a second strain model layer to determine the total damage data of the current collected mineral under the current collected environmental data; and determining the second prediction distribution coefficient of the current collected mineral based on the total damage data.

[0055] In the embodiments of the present application, the total loss data can refer to the overall damage state of the mineral under the current collected environment, which can be analyzed in combination with the damage effect of the mineral characteristics (such as hardness, brittleness, etc.) and environmental factors (such as water depth, pressure, etc.) on the mineral. Specifically, it can be calculated by the second strain model layer, according to the influence of hydrostatic pressure and temperature and other factors on the mineral in the deep sea environment, to determine the expansion of the internal cracks of the ore. For example, when the deep sea pressure is high, the micro-cracks in the ore can accelerate the expansion, leading to easier crushing of the mineral.

[0056] More specifically, the total loss data can be calculated according to different development stages, such as crack expansion, crushing, and disintegration. In the deep sea environment, the damage of the ore is not only affected by mechanical crushing, but also by environmental pressure. The hydrostatic pressure and temperature and other factors in the deep sea water, especially the high pressure in the deep water environment, usually cause the micro-cracks in the ore to further expand and accelerate the crushing of the ore. Therefore, the total damage data not only reflects the crushing of the ore under the action of the development equipment, but also considers the effect of the deep sea environmental factors on the crack expansion of the ore.

[0057] The hydrostatic pressure and pore pressure in the deep sea environment help to expand the internal micro-cracks of the ore, thus exacerbating the damage degree of the ore. Specifically, as the depth increases, the hydrostatic pressure borne by the ore increases, and the internal crack increment also becomes more significant. By simulating the crack expansion process through the hydrostatic pressure and the characteristics of the ore such as hardness, the crack increment is associated with the damage degree over time, eventually leading to the crushing of the ore.

[0058] With the extension of the development time, the ore body is subjected to mechanical impact while the environmental pressure continues to act, the ore cracks will gradually increase and expand, thus exacerbating the damage of the ore body. Therefore, the total damage data is not only related to the physical properties of the ore (such as hardness, brittleness, etc.), but also closely related to the operation time of the development equipment.

[0059] The above-mentioned second prediction distribution coefficient can be used to describe the cuttings particle size distribution of the mineral under the current collection environment. By calculating the total damage data of the mineral, the deep-sea cuttings particle size information prediction management platform can predict the cuttings particle size distribution characteristics generated in the crushing process of the mineral. The second prediction distribution coefficient reflects how the crack expansion and mineral damage caused by the environmental pressure in the deep-sea environment affect the final cuttings particle size. For example, higher total damage data may correspond to finer cuttings particle size, while lower damage may result in more large-particle cuttings. Through this coefficient, the deep-sea cuttings particle size information prediction management platform can accurately predict the particle size distribution of the mineral after crushing under the current environment, and adjust the operation parameters of the mining equipment to optimize the mining effect.

[0060] Optionally, in the step of processing the collection environment data and the collection mineral data through the second strain model layer to determine the total damage data of the current collection mineral under the current collection environment data, the crack density increment data of the current collection mineral can also be determined according to the depth data and the pressure data under the current collection environment data; the crack density increment data is damage accumulated calculation according to the development time to determine the crushing time of the current collection mineral; and the total damage data of the current collection mineral is determined based on the volume of the current collection mineral and the crushing time.

[0061] In the embodiment of the present application, the crack density increment data can refer to the increase of the number and density of cracks inside the ore under the current collection environment due to the environmental pressure and the operation of the development equipment. It can be understood that in the deep-sea environment, high hydrostatic pressure is the main factor affecting the crack increment. As the ore is processed by the mining equipment, cracks will be generated and expanded inside the ore, and the density of these cracks will increase with the increase of the deep-sea hydrostatic pressure. The crack density increment data can be obtained by calculating the crack expansion speed and the change of crack number through the second strain model layer based on the current environment data (such as depth data and pressure data) and the mineral properties.

[0062] Specifically, the high pressure in the deep-sea environment promotes the rapid expansion of the micro-cracks of the ore, so the crack density increases rapidly in this process, and finally leads to the crushing of the ore. For example, assuming that the current operation depth is 2000 meters and the hydrostatic pressure is 20 Mpa, the crack density of the ore increases by a certain percentage per hour under this depth condition, and the crack density increment data is the quantitative value of the change of the crack number with time.

[0063] In a possible embodiment, the deep-sea rock debris particle size information prediction management platform can calculate the damage accumulation of the ore during the development process according to the crack density increment data. Specifically, the ore is continuously subjected to mechanical impact and environmental pressure under the action of the development device, the number of cracks of the ore gradually increases, and the damage gradually intensifies. The cumulative process of damage considers the relationship between the crack increment and the time, and the total damage is usually calculated by time integration. For example, during the operation process, the crack density increment data gradually increases with time, and the platform can calculate the damage accumulation according to the development time and the increment data of the crack density. That is, the damage is added up at each time (for example, every hour), and the cumulative effect of the ore material is considered to obtain the damage accumulation value at the end of the operation.

[0064] The crushing time can refer to the time required for the ore to be completely crushed from the beginning of the external force to the beginning of the development process, which is based on the result of damage accumulation calculation. The platform calculates the time required for the ore to break based on the damage progress of the ore. Specifically, the damage state of the ore is obtained by damage accumulation calculation, and the crushing time required from the beginning of the operation to the complete crushing of the ore is calculated by combining the physical properties (such as brittleness, hardness, etc.) of the ore. For example, if the damage accumulation value of the ore reaches a certain threshold, it will be calculated that the ore may break in the next few seconds or minutes. It should be noted that the crushing individual is mainly for the main body that has not been developed but has been affected by cracks.

[0065] Optionally, in the step of adjusting the collection parameters of the development device and executing the corresponding development strategy based on the prediction distribution data, the development impact force, the rotation speed, the cutting thickness, the traction speed, and the operation mode of the development device can be adjusted based on the prediction distribution data; the depth data of the development device is adjusted, and the rock breaking tool with corresponding development capacity is replaced.

[0066] In the embodiment of the present application, the deep-sea rock debris particle size information prediction management platform dynamically adjusts multiple operation parameters of the development device based on the real-time collected prediction distribution data, thereby optimizing the crushing process of the ore. First, the deep-sea rock debris particle size information prediction management platform adjusts the development impact force and the rotation speed of the development device in real time according to the predicted rock debris particle size distribution data. When the prediction data shows that the ore is relatively hard and requires a larger impact force, the deep-sea rock debris particle size information prediction management platform increases the impact force and the rotation speed of the device to improve the crushing efficiency; when the prediction shows that the ore is relatively fragile and easy to produce small particles, the deep-sea rock debris particle size information prediction management platform reduces the impact force and the rotation speed to avoid excessive crushing and ensure more uniform particle size distribution.

[0067] In addition, the deep-sea cutting particle size information prediction management platform also adjusts the working depth of the development equipment according to the predicted distribution data. In the deep-sea environment, the hardness and crushing characteristics of the ore change with the change of water depth, so the deep-sea cutting particle size information prediction management platform optimizes the working depth of the equipment according to the cutting particle size prediction results at different depths. When the prediction shows that the ore at a certain horizon in the deep sea is hard and needs higher impact force, the deep-sea cutting particle size information prediction management platform will adjust the working depth and select the most suitable working position for development to ensure that the ore can be efficiently crushed.

[0068] The deep-sea cutting particle size information prediction management platform can also replace suitable rock breaking tools according to the change of the cutting particle size prediction distribution. When the prediction shows that more large-particle cutting is generated after ore crushing, the deep-sea cutting particle size information prediction management platform will select a more powerful rock breaking tool; on the contrary, when the particle size is fine and small-particle loss needs to be reduced, the deep-sea cutting particle size information prediction management platform will use a suitable and mild rock breaking tool to maximize the recovery rate and reduce the environmental impact.

[0069] Through these dynamic adjustments, the deep-sea cutting particle size information prediction management platform can flexibly adjust the working state of the development equipment according to real-time prediction data, thereby significantly improving the mining efficiency, optimizing the cutting particle size distribution, and reducing the negative impact on the environment.

[0070] As shown in Figure 2 The embodiment of the present application also provides a deep-sea cutting particle size information prediction management device 200, which comprises: A first collection module 201 is configured to acquire collection data of a development equipment in a current collection environment in real time, wherein the collection data comprises collection environment data and collection mineral data; A first determination module 202 is configured to perform prediction analysis on the collection data by using a preset cutting particle size prediction model, and determine prediction distribution data of cutting particle size corresponding to the collection mineral under the current collection environment data; A first adjustment module 203 is configured to adjust collection parameters of the development equipment and execute corresponding development strategies based on the prediction distribution data.

[0071] Optionally, the first collection module 201 comprises: A first collection sub-module is configured to collect depth data and pressure data of a current collection environment in which the development equipment is located by using a preset environment sensor; A first determination sub-module is configured to determine collection mineral data of a collection mineral being developed by the development equipment in a database, wherein the collection mineral data comprises mineral type and mineral parameter data.

[0072] Optionally, the device further comprises: The first acquisition module is configured to acquire a tool characteristic parameter of the development device, wherein the tool characteristic parameter comprises a rotational speed and a diameter of the development device. The first construction module is configured to construct a first strain model layer of the rock breaking tool and the ore body based on the tool characteristic parameter of the development device and the collected mineral data, wherein the first strain model layer is used to describe a strain relationship between the development device and the ore body. The second construction module is configured to construct a second strain model layer of internal collapse of the ore body based on the collected environment data in which the development device is located, wherein the second strain model layer is used to describe an internal self-collapse relationship of the collected mineral in the current collected environment data. The second determination module is configured to determine the preset rock debris granularity prediction model based on the first strain model layer and the second strain model layer.

[0073] Optionally, the first determination module 202 comprises: The second determination submodule is configured to process the collected mineral data through the first strain model layer to determine the crushing capacity data of the current development device on the current collected mineral. The third determination submodule is configured to determine the first prediction distribution coefficient of the current collected mineral based on the crushing capacity data.

[0074] Optionally, the first determination module 202 comprises: The first processing submodule is configured to process the collected environment data and the collected mineral data through the second strain model layer to determine total damage data of the current collected mineral under the current collected environment data. The fourth determination submodule is configured to determine the second prediction distribution coefficient of the current collected mineral based on the total damage data.

[0075] Optionally, the first processing submodule further comprises: The first determination unit is configured to determine crack density increment data of the current collected mineral according to depth data and pressure data under the current collected environment data. The second determination unit is configured to perform damage accumulation calculation on the crack density increment data according to a development duration to determine a crushing time of the current collected mineral. The third determination unit is configured to determine total damage data of the current collected mineral based on a volume of the current collected mineral and the crushing time.

[0076] Optionally, the first adjustment module 203 comprises: The first adjustment submodule is configured to adjust a development impact force, a rotational speed, a cutting thickness, a traction speed, and an operation mode of the development device based on the prediction distribution data. a second adjusting sub-module, configured to adjust the depth data of the development device according to the prediction distribution data, and replace the rock breaking tool configured with the corresponding development capacity.

[0077] As Figure 3 shown in the figure, the embodiment of the present application further provides an electronic device 300, comprising a processor, and the processor can execute any one of the deep-sea rock debris particle size information prediction management methods.

[0078] Specifically, the electronic device 300 comprises a processor 301 and a memory 302, and a computer program for executing the deep-sea rock debris particle size information prediction management method stored in the memory 302 and capable of running on the processor 301, wherein: The processor 301 runs the computer program of the deep-sea rock debris particle size information prediction management method stored in the memory 302, and executes the following steps: real-time acquisition of collection data of the development device in a current collection environment, wherein the collection data comprises collection environment data and collection mineral data; prediction analysis of the collection data by a preset rock debris particle size prediction model to determine prediction distribution data of rock debris particle size corresponding to the collection mineral under the current collection environment data; adjustment of collection parameters of the development device based on the prediction distribution data and execution of a corresponding development strategy.

[0079] Optionally, the processor 301 executes the real-time acquisition of the collection data of the development device in the current collection environment, comprising: acquisition of depth data and pressure data of the current collection environment of the development device by a preset environment sensor; determination of collection mineral data of the development device being developed in a database, wherein the collection mineral data comprises mineral type and mineral parameter data.

[0080] Optionally, before the processor 301 executes the prediction analysis of the collection data by the preset rock debris particle size prediction model to determine the prediction distribution data of the rock debris particle size corresponding to the collection mineral under the current collection environment data, the method further comprises: acquisition of tool characteristic parameters of the development device, wherein the tool characteristic parameters comprise rotational speed and diameter of the development device; construction of a first strain model layer of rock breaking tool and ore body based on the tool characteristic parameters of the development device and the collection mineral data, wherein the first strain model layer is used to describe the strain relationship between the development device and the ore body; construction of a second strain model layer of internal collapse of the ore body based on the collection environment data of the development device, wherein the second strain model layer is used to describe the internal self-collapse relationship of the collection mineral in the current collection environment data. determine the preset cutting particle size prediction model based on the first strain model layer and the second strain model layer.

[0081] Optionally, the processor 301 performs the prediction analysis on the collection data through the preset cutting particle size prediction model to determine the predicted distribution data of the cutting particle size of the collection mineral under the current collection environment data, including: processing the collection mineral data through the first strain model layer to determine the crushing capacity data of the current development device on the current collection mineral; determining the first prediction distribution coefficient of the current collection mineral based on the crushing capacity data.

[0082] Optionally, the processor 301 also performs the prediction analysis on the collection data through the preset cutting particle size prediction model to determine the predicted distribution data of the cutting particle size of the collection mineral under the current collection environment data, including: processing the collection environment data and the collection mineral data through the second strain model layer to determine the total damage data of the current collection mineral under the current collection environment data; determining the second prediction distribution coefficient of the current collection mineral based on the total damage data.

[0083] Optionally, the processor 301 also performs the processing of the collection environment data and the collection mineral data through the second strain model layer to determine the total damage data of the current collection mineral under the current collection environment data, including: determining the crack density increment data of the current collection mineral according to the depth data and the pressure data under the current collection environment data; damage accumulation calculation on the crack density increment data according to the development duration to determine the crushing time of the current collection mineral; determining the total damage data of the current collection mineral based on the volume of the current collection mineral and the crushing time.

[0084] Optionally, the processor 301 performs the adjustment of the collection parameters of the development device and the execution of the corresponding development strategy based on the predicted distribution data, including: adjusting the development impact force, the rotation speed, the cutting thickness, the traction speed, and the operation mode of the development device based on the predicted distribution data; adjusting the depth data of the development device according to the predicted distribution data, and replacing the rock breaking tool configured with the corresponding development capacity.

[0085] The embodiment of the present application further provides a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement each process of the deep-sea cuttings particle size information prediction management method provided by the embodiment of the present application or the application-side deep-sea cuttings particle size information prediction management method, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0086] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and can be stored in a computer readable storage medium. When the program is executed, the processes of the above-mentioned embodiment methods can be included. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM) or a random access memory (RAM).

[0087] The above only describes the preferred embodiments of the present application, and of course cannot limit the scope of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope of the present application.

Claims

1. A method for predicting and managing deep-sea debris particle size information, characterized in that: include: Acquire the data collected by the development equipment in the current collection environment in real time, including collection environment data and collection mineral data; Performing a prediction analysis on the collected data using a preset rock chip particle size prediction model to determine the predicted distribution data of the rock chip particle size corresponding to the collected minerals under the current collection environment data; Based on the predicted distribution data, the acquisition parameters of the development device are adjusted and the corresponding development strategy is executed.

2. The deep-sea debris particle size information prediction and management method according to claim 1, characterized in that: The real-time acquisition of the collected data of the development device in the current collection environment includes: Collect depth data and pressure data of the current collection environment where the development device is located through a preset environmental sensor; In the database, the collected mineral data being developed by the development equipment is determined, where the collected mineral data includes mineral type and mineral parameter data.

3. The deep-sea debris particle size information prediction and management method according to claim 1, characterized in that: Before performing predictive analysis on the collected data using a preset rock chip particle size prediction model to determine predicted distribution data of rock chip particle sizes corresponding to collected minerals under current collection environment data, the method further includes: Acquiring tool characteristic parameters of the development device, wherein the tool characteristic parameters include a rotation speed and a diameter of the development device; constructing a first strain model layer of the rock breaking tool and the ore body based on the tool characteristic parameters of the development equipment and the collected mineral data, wherein the first strain model layer is used to describe the strain relationship between the development equipment and the ore body; Based on the acquisition environment data of the development equipment, a second strain model layer of internal collapse of the ore body is constructed, wherein the second strain model layer is used to describe the internal self-disintegration relationship of the acquired mineral in the current acquisition environment data; The preset rock cuttings particle size prediction model is determined based on the first strain model layer and the second strain model layer.

4. The method for predicting and managing deep-sea debris particle size information according to claim 3, wherein: The method of performing a predictive analysis on the collected data by using a preset rock chip particle size prediction model to determine the predicted distribution data of the rock chip particle size corresponding to the collected minerals under the current collection environment data includes: Processing the collected mineral data through the first strain model layer to determine the crushing capacity data of the currently developed equipment for the currently collected mineral; Based on the crushing capacity data, a first predicted distribution coefficient of the currently mined mineral is determined.

5. The method for predicting and managing deep-sea debris particle size information according to claim 3, wherein: The method of performing a predictive analysis on the collected data by using a preset rock chip particle size prediction model to determine the predicted distribution data of the rock chip particle size corresponding to the collected minerals under the current collection environment data includes: Processing the collected environment data and the collected mineral data through the second strain model layer to determine total damage data of the current collected mineral under the current collected environment data; Based on the total damage data, a second predicted distribution coefficient of the currently mined mineral is determined.

6. The method for predicting and managing deep-sea debris particle size information according to claim 5, wherein: The processing of the collected environment data and the collected mineral data by the second strain model layer to determine the total damage data of the currently collected minerals under the current collected environment data includes: Determining the crack density increment data of the currently collected mineral based on the depth data and pressure data under the currently collected environmental data; Performing damage accumulation calculation on the crack density increment data according to the development time to determine the crushing time of the currently collected minerals; Based on the volume of the currently collected mineral and the crushing time, total damage data of the currently collected mineral is determined.

7. The method for predicting and managing deep-sea debris particle size information according to claim 1, wherein: The adjusting the acquisition parameters of the development device and executing the corresponding development strategy based on the predicted distribution data includes: Based on the predicted distribution data, adjusting the development impact force, rotation speed, cutting thickness, pulling speed, and operation mode of the development equipment; According to the predicted distribution data, the depth data of the development equipment is adjusted, and the rock breaking tools corresponding to the development capabilities are replaced.

8. A deep-sea debris particle size information prediction and management device, characterized in that: include: The first acquisition module is used to acquire the acquisition data of the development equipment in the current acquisition environment in real time, and the acquisition data includes acquisition environment data and acquisition mineral data; A first determination module is configured to perform a prediction analysis on the collected data using a preset rock chip particle size prediction model to determine predicted distribution data of rock chip particle sizes corresponding to the collected minerals under the current collection environment data; The first adjustment module is used to adjust the acquisition parameters of the development device and execute the corresponding development strategy based on the predicted distribution data.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for predicting and managing deep-sea rock debris particle size information as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the deep-sea rock debris particle size information prediction and management method according to any one of claims 1 to 7.

Images