Mining method based on quantum heuristic ore rock self-adaptive crushing and space-time coordination

Abstract

This invention discloses a quantum-inspired adaptive crushing and spatiotemporal coordination mining method, belonging to the field of ore mining technology. It includes: real-time acquisition of ore and rock parameters during drilling to construct a three-dimensional dynamic barrier field characterizing the crushing difficulty; dynamic adjustment of the crushing equipment's operating frequency and energy waveform based on the barrier field value, achieving efficient crushing through coherent enhancement with the inherent frequency of the ore and rock; mapping crushing points to transportation units to construct spatiotemporal coordination unit pairs, defining the coupling relationship between discharge rate and arrival time using a preset state correlation function; maintaining a probabilistic superposition state of candidate paths for the mobile equipment, triggering probabilistic collapse decisions based on the local environment; and dynamically adjusting the coupling strength of the coordination unit pairs based on mining efficiency to evolve the optimal coordination mode. Inspired by quantum mechanics, this invention achieves on-demand energy supply, precise crushing-transportation coordination, and intelligent path decision-making through classical physics field simulation, significantly improving energy utilization, system robustness, and overall production efficiency.

Description

Technical Field

[0001] This invention relates to the field of ore mining technology, and in particular to a mining method based on quantum-inspired adaptive crushing of ore and rock and spatiotemporal coordination. Background Technology

[0002] Ore mining is a complex systems engineering project, with crushing and transportation being two core components whose efficiency directly determines the overall production capacity and economic benefits of the mine. However, existing technologies suffer from the following prominent problems: First, the energy utilization rate of crushing is low. The spatial distribution of ore and rock properties is extremely uneven. Traditional crushing equipment typically operates with constant power or simple feedback regulation, failing to accurately match energy input according to real-time lithological changes, leading to over-crushing or under-crushing and significant energy waste. Industry statistics show that energy consumption in the crushing stage accounts for approximately 30% to 50% of the total energy consumption in the mining process, with energy utilization efficiency generally below 40%. This extensive energy supply model not only causes huge economic losses but also generates excessive fine particles due to over-crushing, increasing the burden and cost of subsequent mineral processing.

[0003] Secondly, coordination between crushing and transportation is difficult. The discharge rate at the crushing point and the arrival time of transport vehicles are not accurately synchronized, often resulting in "vehicles waiting for materials" or "materials waiting for vehicles," leading to equipment idleness and efficiency losses. Existing centralized dispatching systems heavily rely on stable communication, which is unreliable in harsh mining environments (such as underground and deep open-pit mines). Once communication is interrupted, coordination fails. This high dependence on the central control system makes the overall robustness of the mining production system poor, making it difficult to adapt to complex and changing mining environments.

[0004] Furthermore, equipment path planning is rigid. Path planning for mobile equipment (such as mining trucks and loaders) often employs deterministic algorithms (such as Dijkstra's algorithm, A*). Traditional path planning algorithms are ill-suited to adapt to dynamically changing working environments (such as sudden obstacles or traffic congestion) and are prone to getting stuck in local optima, making it difficult to maximize global efficiency. They also lack the ability to handle uncertainty and are unable to effectively explore and learn in dynamic environments.

[0005] In recent years, although there have been attempts to introduce artificial intelligence and big data technologies into intelligent mining, most have remained at the level of a passive response model of "perception-decision-execution," failing to achieve fundamental breakthroughs in energy utilization mechanisms and collaborative models. Therefore, a completely new technological approach is urgently needed, innovating simultaneously from two dimensions: crushing mechanisms and collaborative models, to systematically solve the aforementioned problems. Summary of the Invention

[0006] The purpose of this invention is to provide a mining method based on quantum-inspired adaptive crushing and spatiotemporal coordination of ore and rock. This invention draws on the tunneling effect, quantum entanglement, and wave function collapse concepts in quantum mechanics. Through classical physical field simulation, it constructs a self-optimizing mechanism for the entire chain from ore and rock crushing to transportation scheduling, realizing efficient energy utilization and precise coordination between crushing and transportation. This solves problems such as low energy utilization rate of crushing, difficulty in coordinating crushing and transportation, and rigid equipment path decision-making in the mining process.

[0007] To achieve the above objectives, this invention provides a mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination, comprising the following steps: S1. During the mining process, the physical and mechanical parameters of the ore and rock are collected in real time while drilling to construct a three-dimensional dynamic potential barrier field that characterizes the distribution of the difficulty of ore and rock crushing. The value of each point in the potential barrier field represents the energy threshold required for the ore and rock at that location to be crushed to the specified particle size. S2. The crushing equipment dynamically adjusts its own operating frequency and impact energy waveform according to the potential barrier field value at its location, so that the spectrum characteristics of the crushing energy produce a coherent enhancement effect with the natural frequency of the current ore and rock, thereby achieving effective crushing with an input below the energy threshold. S3. Map multiple crushing points in the mining area to multiple transportation units one by one, construct several spatiotemporal collaborative unit pairs, and preset a state correlation function for each collaborative unit pair. The state correlation function defines the coupling relationship between the change of the material output rate of the crushing point and the arrival time window of the corresponding transportation unit. S4. Maintain a set of candidate paths and their corresponding probability amplitudes for each mobile device to form a path superposition state. When the device reaches the path decision point, trigger probability collapse through real-time perceived local environmental information, select an actual execution path from the superposition state, and feed back the selection result to update the probability amplitude of subsequent paths. S5. Based on the real-time monitoring of mining efficiency indicators, dynamically adjust the coupling strength between collaborative units to enable the entire mining process to adaptively evolve into the optimal crushing-transportation collaborative mode.

[0008] Preferably, the construction of the three-dimensional dynamic potential barrier field in step S1 specifically includes: S11. Real-time data collection of drilling speed, torque, and vibration spectrum is achieved using a drilling-while-drilling measurement sensor installed on the drilling rig. S12. The uniaxial compressive strength, hardness coefficient and crushing energy index of the ore and rock are derived by using the preset lithology identification model. S13. A continuous potential barrier field covering the entire working face is generated using the Kriging interpolation method and dynamically updated as mining progresses.

[0009] Preferably, the specific method for dynamically adjusting the operating frequency and impact energy waveform in step S2 is as follows: The controller of the crushing equipment is based on the barrier field value Calculate the modulation coefficient and generate the impulse energy waveform according to the following formula: ; in, As the reference energy, The main frequency is adaptively adjusted according to the barrier field. The waveform amplitude modulation factor. For the initial phase, This is the attenuation coefficient.

[0010] According to claim 3, the mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination is characterized in that step S2 further includes a frequency tracking and locking process: Real-time analysis of vibration signals fed back by ore and rock during the crushing process to extract the natural frequencies of ore and rock. and the main frequency of the broken energy To natural frequency Dynamic convergence is used to maximize the coherent enhancement effect.

[0011] Preferably, the specific form of the preset state association function in step S3 is as follows: ; in, For the first The estimated arrival time window for each transport unit, Based on the arrival time, In order to be with the first The first transportation unit mapping The actual discharge rate of each crushing point For the target discharge rate, This represents the initial coupling strength coefficient.

[0012] Preferably, the path superposition state maintenance and probability collapse in step S4 specifically includes the following sub-steps: S41. Initialize a set of candidate paths for each mobile device. and assign an initial probability magnitude. Satisfying the normalization condition ; S42. During equipment movement, continuously perceive local environmental information, including obstacle distribution, the location of other equipment, and road conditions, and calculate the estimated reward for each candidate path. ; S43. Upon reaching the path decision point, update the probability amplitude according to the current probability amplitude and the estimated reward using the following formula: ; in, The decision sensitivity coefficient is then expressed as a probability. Select path As the actual execution path; S44. Record the actual execution effect of path selection and update the probability amplitude of unselected paths to enable subsequent decisions to have path exploration and memory capabilities.

[0013] Preferably, the specific method for dynamically adjusting the coupling strength in step S5 is as follows: Real-time statistics of ore output, equipment utilization rate, and overall energy consumption per unit time are used to calculate the overall efficiency value. ;like If the value is below the preset threshold, adjust the coupling strength coefficient according to the following formula. : ; in, To adjust the step size, The target performance value is used; the adjusted coupling strength coefficient is applied to subsequent correlation calculations of cooperative units.

[0014] Preferably, the method further includes a communication adaptive adjustment step: The system monitors the communication network status of the mining area in real time. When the communication quality is lower than a preset threshold, it automatically reduces the coupling strength between collaborative units, allowing each transportation unit to rely more on locally cached correlation function parameters for autonomous decision-making. When communication is restored, the coupling strength is automatically restored.

[0015] Preferably, the method further includes a self-learning optimization step: Data on the potential barrier field, fracturing parameters, path selection records, and corresponding mining efficiency indicators from historical mining processes are collected. A reinforcement learning algorithm is used to train an optimization model, which is then used to dynamically adjust the waveform modulation parameters in step S2 and the decision sensitivity coefficient in step S4. and the adjustment step size in step S5 .

[0016] Preferably, the method further includes an initialization step before step S1: Based on historical geological exploration data and mining records, an initial barrier field is constructed as prior information, and an initial target discharge rate is preset for each break point, and an initial benchmark arrival time is preset for each transportation unit.

[0017] Therefore, the mining method based on quantum-inspired adaptive rock crushing and spatiotemporal coordination, which adopts the above structure, has the following beneficial effects: (1) This invention achieves precise matching between crushing energy and ore characteristics through the construction of a potential barrier field and modulation of energy waveform, realizing "on-demand energy supply and coherent enhancement". Experiments show that compared with the traditional constant power crushing method, this invention can save 15% to 30% of energy, while reducing the subsequent beneficiation burden caused by over-crushing. This precise energy control not only reduces production costs, but also effectively reduces unnecessary energy consumption and equipment wear.

[0018] (2) This invention introduces "spatiotemporal collaborative unit pairs" and state association functions to achieve decentralized and precise collaboration. Each transportation unit only needs to obtain the target time window once before departure to execute autonomously without relying on continuous real-time communication, effectively avoiding the phenomenon of "vehicles waiting for materials" or "materials waiting for vehicles", and improving equipment utilization by more than 20%. This decentralized collaboration mechanism greatly reduces the complexity of the system and improves the reliability and flexibility of the system.

[0019] (3) The path decision-making mechanism based on probability collapse in this invention combines exploratory and deterministic approaches and can adapt to dynamic environments. When the equipment encounters sudden obstacles or congestion, it can quickly adjust its path selection and avoid repeating mistakes through a probability amplitude memory mechanism, thereby improving overall transportation efficiency by 15% to 25%. This intelligent path planning method enables the mine transportation system to better cope with complex and ever-changing operating environments.

[0020] (4) This invention supports adaptive adjustment of communication, automatically reducing coupling strength when communication is interrupted or deteriorated, enabling each unit to make autonomous decisions based on local information, ensuring that the system can maintain basic operation even in harsh environments, and greatly improving the reliability of mine production. This adaptive capability to the communication environment makes this invention particularly suitable for scenarios with poor communication conditions, such as underground mines and deep open-pit mines.

[0021] (5) This invention continuously optimizes key parameters through reinforcement learning, enabling the method to adapt to long-term evolution such as lithological changes and equipment aging throughout the mine's life cycle, thus achieving sustainable performance improvement. This self-learning capability allows the system to continuously accumulate experience and gradually improve performance during operation.

[0022] (6) This invention systematically introduces quantum heuristics into mining engineering, forming a completely new solution that differs from traditional automation and informatization approaches, and possesses extremely high technical barriers and licensing stability. This interdisciplinary technological innovation opens up new directions for intelligent mining and has significant theoretical and practical value.

[0023] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0024] Figure 1This is an overall flowchart of the mining method based on quantum-inspired adaptive crushing and spatiotemporal coordination of ore and rock according to the present invention; Figure 2 This is a schematic diagram of drilling test data acquisition in an embodiment of the present invention; Figure 3 This is a schematic diagram of the three-dimensional barrier field surface in an embodiment of the present invention; Figure 4 This is a waveform modulation control block diagram in an embodiment of the present invention; Figure 5 This is a schematic diagram comparing the energy waveform modulation effects in embodiments of the present invention; Figure 6 This is a schematic diagram of the spatiotemporal coordination unit relationship in an embodiment of the present invention; Figure 7 This is a schematic diagram of the path probability collapse decision-making process in an embodiment of the present invention. Detailed Implementation

[0025] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0026] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0027] like Figure 1 As shown, the mining method based on quantum-inspired adaptive rock crushing and spatiotemporal coordination provided by this invention includes the following steps S1 to S5, forming a complete closed-loop optimization process: S1. Barrier Field Construction: During the mining process, the physical and mechanical parameters of the ore and rock are collected in real time while drilling to construct a three-dimensional dynamic barrier field that characterizes the distribution of the difficulty of ore and rock fracturing. S2. Adaptive crushing: The crushing equipment dynamically adjusts its own operating frequency and impact energy waveform according to the potential barrier field value at its location to achieve coherent enhanced crushing. S3, Cooperative Unit Pair: Map the breakpoints to the transportation units one by one, construct spatiotemporal cooperative unit pairs and preset state association functions; S4. Path Collapse: Maintains a probabilistic superposition state of candidate paths for mobile devices and triggers probabilistic collapse decisions based on local environmental information. S5. Cooperative Evolution: Based on real-time monitoring of mining efficiency indicators, the coupling strength between cooperative units is dynamically adjusted to enable the entire mining process to evolve adaptively.

[0028] The above steps will be explained in detail below through specific embodiments.

[0029] Example 1 This embodiment applies the present invention to a large open-pit iron mine, and the specific implementation process is as follows.

[0030] Step S1: Construct a three-dimensional dynamic potential barrier field This step involves constructing a three-dimensional dynamic barrier field using measurement-while-drilling (MSD) technology. Figure 2 The diagram illustrates the data acquisition process for drilling tests. The drilling rig was modified for drilling measurements by installing a drill rate sensor, a torque sensor, and a triaxial vibration sensor. During borehole drilling operations, the above data was collected in real time at a sampling frequency of 100 Hz. The data was transmitted wirelessly to an edge computing server in the mining area.

[0031] The server has a built-in lithology identification model that uses a backpropagation neural network. The input layer receives drilling speed, torque, and vibration spectrum features (frequency domain features extracted by FFT transformation), and the output layer is the uniaxial compressive strength and fracturing energy index of the ore and rock. The model is pre-trained using historical borehole data and core test data from the mining area, and the verification accuracy reaches over 90%.

[0032] Figure 3 A schematic diagram of the three-dimensional potential barrier field surface is shown. Using the fracturing energy index obtained from the inversion of each borehole point, a three-dimensional potential barrier field grid covering the entire mining face is generated using the Kriging interpolation method, with a grid resolution of 1 m × 1 m × 0.5 m. The potential barrier field is updated every 8 hours as the drilling progresses to ensure it reflects the latest lithological changes. The surface undulations in the diagram represent the height of the potential barrier field value; raised areas represent high fracturing difficulty (high energy threshold), while recessed areas represent low fracturing difficulty (low energy threshold), providing an accurate "energy map" for subsequent fracturing equipment.

[0033] Step S2: Adaptive Breaking Five hydraulic breakers are installed on the mining face. Each breaker integrates an adaptive breaking controller, and its energy waveform modulation principle is as follows: Figure 3 As shown.

[0034] Figure 4 This is a waveform modulation control block diagram. The controller reads the GPS coordinates of the breaker's location in real time and obtains the barrier field value at that location from the barrier field server. Assuming the current situation... Reference energy According to the relationship calibrated in the pre-experiment, the main frequency and The relationship is Amplitude modulation factor If the value is 0.3 and the attenuation coefficient β is 0.02, then the generated energy waveform is: ; Figure 5 This diagram illustrates the comparison of energy waveform modulation effects. It compares the differences between the traditional constant-amplitude waveform (top) and the modulated waveform of this invention (bottom). The frequency and amplitude of the modulated waveform dynamically change with the potential barrier field; energy is more concentrated in the high-barrier region, while energy is appropriately reduced in the low-barrier region.

[0035] Simultaneously, the accelerometer on the hydraulic breaker monitors the echo vibration signal after impact in real time, and extracts the natural frequency of the ore through spectrum analysis. In this example, the measured natural frequency of the ore is approximately 7.8 Hz, and the controller sets the waveform's main frequency... The frequency was dynamically adjusted from 8.5 Hz to 7.8 Hz, and after several iterations, it was locked at 7.9 Hz, achieving coherent enhancement through frequency matching. Operators observed through the monitoring interface that, after adopting this method, the operating current of the hydraulic breaker decreased by an average of 22% under the same crushing effect, demonstrating a significant improvement in energy utilization.

[0036] Step S3: Establish spatiotemporal collaborative unit pairs like Figure 6 As shown, this step establishes a one-to-one mapping relationship between the breakage points and the transportation units. The left side of the figure shows the breakage points P1, P2, and P3, and the right side shows the corresponding transportation units T1, T2, T3, and T4, forming cooperative unit pairs through the mapping relationship.

[0037] In practice, the five breakage points on the working face are numbered as follows: The 10 mining trucks responsible for transportation were numbered as follows: The collaborative field construction module, based on the principles of "nearest service and load balancing," will... to and to Mapping is performed: each break point is mapped to 2 trucks, forming 5 pairs of cooperative units, namely: .

[0038] Associating a preset state function with each unit. Taking a unit pair as an example, according to the mining plan, Target discharge rate tons / hour, base arrival time minutes (i.e., from the parking lot to...) (Normal driving time). Initial coupling strength coefficient. Set it to 0.05. The correlation function is shown in the formula labeled in the figure: ; in for The current actual discharge rate is obtained in real time through the production sensor on the breaker. tons / hour minutes means You need to arrive 1 minute early. To address situations where the discharge rate is too low; when tons / hour A minute means that the vehicle can arrive one minute late to avoid arriving too early and causing a wait.

[0039] Before each truck departs, it obtains the target time window for that shift from the collaborative field construction module. After that, it can execute autonomously without real-time communication. When the truck returns after completing a transport mission, it retrieves the updated information again. This achieves closed-loop feedback.

[0040] Step S4: Path probability collapse decision like Figure 7 As shown, this step provides a path probability collapse decision-making mechanism for mobile devices. The figure illustrates the process of a vehicle selecting a path through probability amplitude updates and collapse when faced with three candidate paths at an intersection.

[0041] Each mining truck is equipped with an onboard decision terminal, which includes a high-precision mining area map and route decision-making algorithm. Return from unloading point to break point For example: S41: Initialize candidate paths and probability values. Based on the current location and the target point, plan 3 candidate paths. The initial probability amplitude is ,satisfy .

[0042] S42: The truck continuously senses its local environment while driving. It detects its path using onboard millimeter-wave radar and cameras. A malfunctioning piece of equipment is blocking the road 200 meters ahead, causing an estimated 3-minute delay. Calculate the estimated reward. ;path Traffic is smooth and expected to proceed normally. ;path There is slight congestion, and a delay of 1 minute is expected. The estimated reward value is generated by a preset evaluation function, taking into account factors such as travel time, energy consumption, and safety.

[0043] S43: Upon reaching the fork in the road (decision point), update the probability amplitude based on the current probability amplitude and the estimated reward. Calculate the decision sensitivity coefficient. Calculate according to the formula shown in the figure: ; The specific numerical calculations are as follows: ; ; ; Calculate the normalization factor: ; The normalized probability magnitude is: ; ; ; The corresponding selection probability is: ; like Figure 7 As shown, the probability of selection is marked next to each path. A random number generator generates random numbers between 0 and 1, with the probability falling within the specified range. select select select The random number this time was 0.512, falling into... Range, select path implement.

[0044] S44: Record the selection result and the actual passage effect. If If the actual travel time matches the expectation, the probability amplitude remains unchanged; if it is better than expected, it is increased according to certain rules. The probability amplitude is reduced. and If the results are worse than expected, then the price should be appropriately reduced. The probability amplitude. This mechanism ensures that, in similar scenarios, the truck has an increasingly higher probability of choosing a good path, while gradually eliminating poor paths, but always retains a certain exploration probability to avoid getting trapped in local optima.

[0045] Step S5: Dynamic Evolution of the Cooperative Field This step dynamically adjusts the coupling strength between collaborative unit pairs based on real-time monitored mining efficiency indicators.

[0046] Emergent behavior monitoring platform (deployed in dispatch center) calculates the overall efficiency value of the entire mining area in real time. . Defined as: ; The platform calculates the average weekly. Value. If the weekly average If the value falls below a preset threshold of 0.8, coupling strength adjustment is triggered. , Calculate according to the formula: ; A new coupling strength coefficient of 0.0506 was issued to the collaborative field construction module, and subsequent correlation calculations adopted the new value. After several weeks of iteration, the system gradually found the optimal coupling strength, and the overall performance stabilized above 0.86.

[0047] This completes the task. Figure 1 This illustrates a complete closed-loop optimization cycle. As mining progresses, steps S1 to S5 continuously cycle, and the system constantly evolves adaptively.

[0048] Example 2 This embodiment applies the invention to underground metal mines with poor communication conditions, focusing on demonstrating the implementation process of the communication adaptive adjustment step described in claim 8.

[0049] The underground environment suffers from severe wireless signal attenuation, with communication blind spots existing in some areas. In this embodiment, the initial coupling strength between the cooperative unit pairs is set to... (Higher than Example 1, to compensate for insufficient information when communication is poor). Each mining truck and loader has a built-in communication quality monitoring module in its on-board terminal to evaluate the connection status with the ground dispatch center in real time. The communication quality index C is defined as a comprehensive function of signal strength and bit error rate, ranging from 0 to 1.

[0050] The communication adaptive adjustment process is as follows: When the truck is driving normally, (Good), using standard coupling strength Perform time window calculations. When the truck enters the blind spot, When the coupling strength drops below 0.2, low coupling mode is triggered: the vehicle terminal automatically adjusts the effective coupling strength to... This significantly reduces sensitivity to changes in real-time discharge rate, relying more on the baseline arrival time obtained at the start. The decision is made based on the parameters of the associated function in conjunction with the local cache.

[0051] When the truck drove out of the blind spot Recovered to above 0.8 Gradually recover to Meanwhile, the terminal caches the driving data (actual path, arrival time, etc.) during the blind spot period and uploads it to the dispatch center after communication is restored for subsequent model optimization.

[0052] This embodiment verifies the strong robustness of the present invention in harsh communication environments: even in blind spots where communication is completely interrupted, the vehicle can still operate autonomously based on local information and a low-coupling mode, with the overall system efficiency decreasing by only 8%, while the traditional centralized dispatch system would almost be paralyzed under the same conditions.

[0053] Example 3 This embodiment adds a self-learning optimization step to the first embodiment, demonstrating how reinforcement learning can continuously optimize system parameters.

[0054] A reinforcement learning training platform was deployed in the dispatch center, employing the Deep Q-Network (DQN) algorithm. The state space includes: the statistical characteristics of the current barrier field (mean, variance), the actual output rate at each break point, the waiting time of each transport unit, and the overall efficiency. The historical sequence of values; the action space includes: waveform modulation parameters. (0.2 to 0.5), decision sensitivity coefficient (0.5 to 1.5), adjust step size (0.05 to 0.2); the reward function is defined as the overall effectiveness. Change in value .

[0055] The system uploads its daily operational data (including all records from steps S1 to S5) to the training platform to build training samples. A model update is performed every weekend, generating new parameter combinations, which are then automatically distributed to all devices the following Monday.

[0056] After three months of self-learning and optimization, the system parameters adaptively evolved to the optimal configuration tailored to the lithological characteristics of the mining area: It has stabilized around 0.28. It stabilized at 0.95. The value stabilized at 0.12. Compared to the period with fixed parameters, the overall performance improved by 7%, demonstrating the effectiveness of the self-learning mechanism.

[0057] It should be noted that the above embodiments are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art can make several modifications and improvements based on the technical solutions disclosed in this invention. For example: The potential barrier field construction in step S1 can be achieved using other interpolation methods (such as inverse distance weighting, spline function) or machine learning methods (such as random forest, Gaussian process regression). The energy waveform modulation in step S2 can adopt other function forms (such as square wave, triangle wave, or custom waveform), as long as it can achieve spectrum modulation. The state association function in step S3 can take the form of a nonlinear function, such as an exponential function or a logarithmic function, to accommodate more complex coupling relationships. The probability magnitude update in step S4 can be achieved using other probability models (such as Boltzmann distribution, Bayesian update). The weights of the comprehensive performance indicators in step S5 can be adjusted or other indicators (such as safety factors and environmental protection indicators) can be introduced according to the specific circumstances of the mine.

[0058] These modifications and improvements all fall within the spirit and principles of this invention and should be included within the scope of protection of this invention.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A quantum heuristic-based ore rock self-adaptive crushing and space-time coordinated mining method, characterized in that, Includes the following steps: S1. During the mining process, the physical and mechanical parameters of the ore and rock are collected in real time while drilling to construct a three-dimensional dynamic potential barrier field that characterizes the distribution of the difficulty of ore and rock crushing. The value of each point in the potential barrier field represents the energy threshold required for the ore and rock at that location to be crushed to the specified particle size. S2. The crushing equipment dynamically adjusts its own operating frequency and impact energy waveform according to the potential barrier field value at its location, so that the spectrum characteristics of the crushing energy produce a coherent enhancement effect with the natural frequency of the current ore and rock, thereby achieving effective crushing with an input below the energy threshold. S3. Map multiple crushing points in the mining area to multiple transportation units one by one, construct several spatiotemporal collaborative unit pairs, and preset a state correlation function for each collaborative unit pair. The state correlation function defines the coupling relationship between the change of the material output rate of the crushing point and the arrival time window of the corresponding transportation unit. S4. Maintain a set of candidate paths and their corresponding probability magnitudes for each mobile device to form a path superposition state; When the device reaches the path decision point, it triggers probability collapse through real-time perceived local environmental information, selects an actual execution path from the superposition state, and feeds back the selection result to update the probability amplitude of subsequent paths. S5. Based on the real-time monitoring of mining efficiency indicators, dynamically adjust the coupling strength between collaborative units to enable the entire mining process to adaptively evolve into the optimal crushing-transportation collaborative mode.

2. The mining method based on quantum heuristic ore rock self-adaptive crushing and space-time coordination according to claim 1, characterized in that, The construction of the three-dimensional dynamic potential barrier field in step S1 specifically includes: S11. Real-time data collection of drilling speed, torque, and vibration spectrum is achieved using a drilling-while-drilling measurement sensor installed on the drilling rig. S12. The uniaxial compressive strength, hardness coefficient and crushing energy index of the ore and rock are derived by using the preset lithology identification model. S13. A continuous potential barrier field covering the entire working face is generated using the Kriging interpolation method and dynamically updated as mining progresses.

3. The mining method based on quantum heuristic ore rock self-adaptive crushing and space-time coordination according to claim 1, characterized in that, The specific method for dynamically adjusting the operating frequency and impact energy waveform in step S2 is as follows: The controller of the crushing device is configured to determine a barrier field value The modulation factor is calculated and the impact energy waveform is generated according to the following equation: ； wherein, is the reference energy, is the main frequency adapted according to the barrier field, is the waveform amplitude modulation factor, is the initial phase, is the decay coefficient.

4. The mining method based on quantum heuristic ore rock self-adaptive crushing and space-time coordination according to claim 3, characterized in that, Step S2 also includes a frequency tracking locking process: Real-time analysis of the vibration signals of the ore and rock feedback during the crushing process, extraction of the inherent frequency of the ore and rock , and the main frequency of the crushing energy towards the inherent frequency Dynamic approach to maximize the coherence enhancement effect.

5. The mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination according to claim 1, characterized in that, The specific form of the preset state association function in step S3 is as follows: ； in, For the first The estimated arrival time window for each transport unit, Based on the arrival time, In order to be with the first The first transportation unit mapping The actual discharge rate of each crushing point For the target discharge rate, This represents the initial coupling strength coefficient.

6. The mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination according to claim 1, characterized in that, Step S4, path superposition state maintenance and probability collapse, specifically includes the following sub-steps: S41. Initialize a set of candidate paths for each mobile device. and assign an initial probability magnitude. Satisfying the normalization condition ; S42. During equipment movement, continuously perceive local environmental information, including obstacle distribution, the location of other equipment, and road conditions, and calculate the estimated reward for each candidate path. ; S43. Upon reaching the path decision point, update the probability amplitude according to the current probability amplitude and the estimated reward using the following formula: ； in, The decision sensitivity coefficient is then expressed as a probability. Select path As the actual execution path; S44. Record the actual execution effect of path selection and update the probability amplitude of unselected paths to enable subsequent decisions to have path exploration and memory capabilities.

7. The mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination according to claim 1, characterized in that, The specific method for dynamically adjusting the coupling strength in step S5 is as follows: Real-time statistics of ore output, equipment utilization rate, and overall energy consumption per unit time are used to calculate the overall efficiency value. ;like If the value is below the preset threshold, adjust the coupling strength coefficient according to the following formula. : ； in, To adjust the step size, The target performance value is used; the adjusted coupling strength coefficient is applied to subsequent correlation calculations of cooperative units.

8. The mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination according to claim 1, characterized in that, The method also includes a communication adaptive adjustment step: The system monitors the communication network status of the mining area in real time. When the communication quality is lower than a preset threshold, it automatically reduces the coupling strength between collaborative units, allowing each transportation unit to rely more on locally cached correlation function parameters for autonomous decision-making. When communication is restored, the coupling strength is automatically restored.

9. The mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination according to claim 1, characterized in that, The method also includes a self-learning optimization step: Data on the potential barrier field, fracturing parameters, path selection records, and corresponding mining efficiency indicators from historical mining processes are collected. A reinforcement learning algorithm is used to train an optimization model, which is then used to dynamically adjust the waveform modulation parameters in step S2 and the decision sensitivity coefficient in step S4. and the adjustment step size in step S5 .

10. The mining method based on quantum-inspired adaptive rock and ore crushing and spatiotemporal coordination according to claim 1, characterized in that, The method also includes an initialization step before step S1: Based on historical geological exploration data and mining records, an initial barrier field is constructed as prior information, and an initial target discharge rate is preset for each break point, and an initial benchmark arrival time is preset for each transportation unit.

Images