A control method and system for a shaft tunneling machine

Abstract

This invention discloses a control method and system for a shaft tunneling machine, applied in the field of shaft tunneling machines. The method includes: controlling the shaft tunneling machine to adjust its working state using a received control signal. The generation process of the control signal is as follows: acquiring geographical environment change information; determining the geological abrupt change intensity of the working area based on the geographical environment change information; determining an energy consumption disturbance index based at least on the geological abrupt change intensity; processing the energy consumption disturbance index to obtain the predicted energy consumption change rate of the working area; determining energy consumption prediction information based on the predicted energy consumption change rate and the corresponding geological abrupt change intensity; acquiring electrical sampling data; verifying the initial risk probability data determined based on the electrical sampling data to generate fault risk information; and generating a control signal based on the energy consumption prediction information and the fault risk information. The control method and system for a shaft tunneling machine provided by this invention significantly improves the accuracy of parameter adjustment through precise data analysis.

Description

Technical Field

[0001] This invention relates to the field of shaft tunneling machine technology, and in particular to a control method and system for a shaft tunneling machine. Background Technology

[0002] Shaft excavation machines can significantly improve the efficiency of shaft excavation. Compared with traditional blasting methods, they can reduce manual labor and shorten the construction cycle. At the same time, they can precisely control the excavation cross-section size, reduce disturbance to the surrounding rock, and ensure construction safety and project quality.

[0003] Shaft boring machines (TBMs) operate in highly complex and enclosed environments with significant geological uncertainties—key factors such as surrounding rock strength, joint development, and groundwater distribution dynamically evolve during the tunneling process. Current technologies primarily rely on operator experience to judge and adjust TBM operating parameters to achieve dynamic synergy between tunneling efficiency and surrounding rock stability. However, this method is limited by individual cognitive limitations and subjective biases, leading to decreased control precision. This not only results in large fluctuations in advance speed and low tunneling efficiency but also easily causes abnormal cutter wear, drastic fluctuations in equipment load, and frequent start-ups and shutdowns. Prolonged operation under non-optimal conditions further exacerbates problems such as tunnel axis misalignment and segment assembly misalignment, and may even induce localized surrounding rock instability or surface subsidence, posing systemic risks to construction quality, equipment safety, and the surrounding environment. Summary of the Invention

[0004] This invention provides a control method and system for a shaft tunneling machine to solve the technical problem of decreased accuracy in manual experience-based control, thereby improving control precision and tunneling efficiency.

[0005] To solve the above-mentioned technical problems, the present invention provides a control method and system for a vertical shaft tunneling machine, the method comprising:

[0006] The target shaft tunneling machine is controlled by the received control signal to adjust its working state, which includes at least the main drive speed and propulsion pressure of the target shaft tunneling machine. The generation process of the control signal is as follows:

[0007] During the operation of the target shaft tunneling machine, the geographical environment change information of the working area corresponding to the target shaft tunneling machine is acquired, and the geological change intensity of the working area is determined based on the geographical environment change information;

[0008] At least based on the formation abrupt change intensity, an energy consumption disturbance index is determined, wherein the energy consumption disturbance index is used to characterize the overall disturbance degree of the formation abrupt change intensity on the energy consumption of the target shaft boring machine;

[0009] The energy consumption disturbance index is processed to obtain the predicted energy consumption change rate of the working area;

[0010] Based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity, energy consumption prediction information is determined; and,

[0011] Acquire electrical sampling data of the target shaft tunneling machine during its operation;

[0012] Based on the electrical sampling data, initial risk probability data is determined;

[0013] The initial risk probability data is verified to generate fault risk information;

[0014] The control signal is generated based on the energy consumption prediction information and the fault risk information.

[0015] Preferably, determining the intensity of stratigraphic abrupt change in the working area based on the geographical environment change information includes:

[0016] The geographical environment change information is quantified to obtain environmental change characteristics;

[0017] The environmental change characteristics are compared with a preset threshold library to determine the characteristics of sudden environmental changes;

[0018] The characteristics of the abrupt environmental changes are analyzed and processed to determine comprehensive geographical environment assessment information;

[0019] The comprehensive assessment information of the geographical environment is quantified and normalized to determine the intensity of the geological abrupt change.

[0020] Preferably, determining the energy consumption disturbance index based at least on the formation abrupt change intensity includes:

[0021] The formation abrupt change intensity is input into the constructed multi-factor coupled calculation model to obtain the theoretical additional load;

[0022] Based on the energy conversion efficiency curve of the target shaft boring machine, the theoretical additional load is processed to determine the instantaneous power compensation requirement;

[0023] An attenuation analysis is performed on the instantaneous power compensation requirement to determine the disturbance factor;

[0024] The energy consumption disturbance index is obtained by integrating the instantaneous power compensation requirement and the disturbance factor.

[0025] Preferably, determining the energy consumption prediction information based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity includes:

[0026] A correlation analysis is performed between the predicted energy consumption change rate and the corresponding formation abrupt change intensity to determine the cooperative change information;

[0027] The coordinated change information is matched with the preset formation and energy consumption mapping relationship to determine the energy consumption deviation coefficient;

[0028] The energy consumption prediction information is generated based on the energy consumption deviation coefficient and the current operating parameters of the target shaft tunneling machine.

[0029] Preferably, the step of verifying the initial risk probability data and generating fault risk information includes:

[0030] The initial risk probability data is compared with a preset threshold range to generate preliminary verification results;

[0031] The preliminary verification results are analyzed using a sliding time window to obtain the risk confidence level;

[0032] The risk confidence level is mapped to a predefined fault classification system to obtain the fault risk information.

[0033] Another aspect of the present invention provides a control system for a shaft boring machine, comprising:

[0034] The control module is used to control the target shaft tunneling machine to adjust its working state based on received control signals. The working state includes at least the main drive speed and propulsion pressure of the target shaft tunneling machine. The generation process of the control signals is as follows:

[0035] The geological mutation module is used to acquire geographical environment change information of the working area corresponding to the target shaft tunneling machine during the operation of the target shaft tunneling machine, and to determine the geological mutation intensity of the working area based on the geographical environment change information;

[0036] An energy consumption disturbance module is used to determine an energy consumption disturbance index based at least on the formation abrupt change intensity, wherein the energy consumption disturbance index is used to characterize the comprehensive disturbance degree of the formation abrupt change intensity on the energy consumption of the target shaft tunneling machine;

[0037] The energy consumption change rate module is used to process the energy consumption disturbance index to obtain the predicted energy consumption change rate of the working area.

[0038] The prediction module is used to determine energy consumption prediction information based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity; and,

[0039] The acquisition module is used to acquire electrical sampling data of the target shaft tunneling machine during its operation.

[0040] The determination module is used to determine initial risk probability data based on the electrical sampling data;

[0041] The verification module is used to verify the initial risk probability data and generate fault risk information;

[0042] A generation module is used to generate the control signal based on the energy consumption prediction information and the fault risk information.

[0043] Preferably, determining the intensity of stratigraphic abrupt change in the working area based on the geographical environment change information includes:

[0044] A quantization processing unit is used to quantify the geographic environment change information to obtain environmental change characteristics;

[0045] The comparison unit is used to compare the environmental change characteristics with a preset threshold library to determine the characteristics of sudden environmental changes.

[0046] The determination unit is used to analyze and process the characteristics of the abrupt environmental changes to determine comprehensive geographical environment assessment information;

[0047] The processing unit is used to quantify and normalize the comprehensive assessment information of the geographical environment to determine the intensity of the geological abrupt change.

[0048] Preferably, determining the energy consumption disturbance index based at least on the formation abrupt change intensity includes:

[0049] The model unit is used to input the formation mutation intensity into the constructed multi-factor coupled calculation model to obtain the theoretical additional load;

[0050] The processing unit is used to process the theoretical additional load based on the energy conversion efficiency curve of the target shaft boring machine, and determine the instantaneous power compensation requirement.

[0051] The analysis unit is used to perform attenuation analysis on the instantaneous power compensation requirement and determine the disturbance factor;

[0052] An energy consumption disturbance unit is used to integrate the instantaneous power compensation demand and the disturbance factor to obtain the energy consumption disturbance index.

[0053] Preferably, the prediction module includes:

[0054] The correlation analysis unit is used to perform correlation analysis between the predicted energy consumption change rate and the corresponding formation abrupt change intensity to determine the cooperative change information;

[0055] The matching unit is used to match the coordinated change information with the preset formation and energy consumption mapping relationship to determine the energy consumption deviation coefficient;

[0056] The generation unit is used to generate the energy consumption prediction information based on the energy consumption deviation coefficient and the current operating parameters of the target shaft tunneling machine.

[0057] Preferably, the verification module includes:

[0058] A threshold unit is used to compare the initial risk probability data with a preset threshold range to generate a preliminary verification result;

[0059] The analysis unit is used to analyze the preliminary verification results using a sliding time window to obtain the risk confidence level;

[0060] The mapping unit is used to map the risk confidence level to a predefined fault classification system to obtain the fault risk information.

[0061] Compared with the prior art, the beneficial effects of the present invention are at least one of the following:

[0062] This invention effectively solves the problem of insufficient control precision caused by reliance on human experience in existing technologies by constructing an intelligent control closed loop that integrates geological perception and equipment status monitoring. Specifically, during the tunneling process, real-time information on changes in the geographical environment of the working area is acquired, the intensity of geological abrupt changes is quantified, and energy consumption disturbance index and predicted energy consumption change rate are calculated accordingly to generate energy consumption prediction information reflecting future energy consumption trends. Simultaneously, electrical sampling data of the tunneling machine's main drive system is collected, and high-confidence fault risk information is generated through anomaly identification and multi-stage verification mechanisms. Finally, the energy consumption prediction information and fault risk information are synergistically integrated to dynamically generate control signals for adjusting the main drive speed and propulsion pressure, achieving adaptive optimization of tunneling parameters. This method abandons subjective experience-based judgment, enabling the tunneling process to proactively respond to geological changes and avoid equipment operation risks, thereby significantly improving tunneling efficiency, stabilizing propulsion speed, reducing tool wear and energy consumption fluctuations, effectively preventing axis deviation and exacerbation of surrounding rock disturbance, ensuring construction quality, equipment safety, and the stability of the surrounding environment, and realizing efficient, safe, low-consumption, and controllable intelligent shaft tunneling operations. Attached Figure Description

[0063] Figure 1 This is a flowchart illustrating the control method of a vertical shaft tunneling machine in one embodiment of the present invention;

[0064] Figure 2 This is a schematic diagram of the control system of a shaft boring machine in one embodiment of the present invention;

[0065] Figure label:

[0066] The module includes: 11. Control module; 12. Formation mutation module; 13. Energy consumption disturbance module; 14. Energy consumption change rate module; 15. Prediction module; 16. Acquisition module; 17. Determination module; 18. Verification module; and 19. Generation module. Detailed Implementation

[0067] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0068] In the description of this application, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined with "first," "second," "third," etc., may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0069] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "joint" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. The term "and / or" as used herein includes any and all combinations of one or more of the related listed items. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0070] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this specification is for the purpose of describing specific embodiments only and is not intended to limit the invention. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0071] Compared with traditional blasting methods, shaft tunneling machines can significantly improve excavation efficiency, reduce manual labor input, shorten the construction period, and precisely control cross-sectional dimensions, reducing disturbance to the surrounding rock, thereby ensuring construction safety and project quality.

[0072] However, the operating environment is enclosed and the geological conditions are highly uncertain, with dynamic changes in factors such as surrounding rock strength, joints, and groundwater. Existing technologies rely on operators' experience to adjust parameters, which is limited by subjective judgment and easily leads to insufficient control precision. This can cause problems such as propulsion fluctuations, tool wear, equipment overload, axis misalignment, and even surrounding rock instability, posing systemic risks to construction quality and safety.

[0073] One embodiment of the present invention provides a control method for a vertical shaft tunneling machine. For details, please refer to [link / reference]. Figure 1 , Figure 1 The diagram shown is a flowchart illustrating a control method for a shaft boring machine according to one embodiment of the present invention. The method includes:

[0074] S1. The target shaft tunneling machine is controlled to adjust its working state using the received control signals. The working state includes at least the main drive speed and propulsion pressure of the target shaft tunneling machine. The process of generating the control signals is as follows:

[0075] S2. During the operation of the target shaft tunneling machine, acquire information on the changes in the geographical environment of the working area corresponding to the target shaft tunneling machine, and determine the intensity of geological abrupt changes in the working area based on the information on changes in the geographical environment.

[0076] S3. At least based on the formation abrupt change intensity, determine the energy consumption disturbance index, wherein the energy consumption disturbance index is used to characterize the comprehensive disturbance degree of formation abrupt change intensity on the energy consumption of the target shaft tunneling machine;

[0077] S4. Process the energy consumption disturbance index to obtain the predicted energy consumption change rate of the working area.

[0078] S5. Based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity, determine the energy consumption prediction information; and,

[0079] S6. Acquire electrical sampling data of the target shaft tunneling machine during its operation;

[0080] S7. Determine the initial risk probability data based on electrical sampling data;

[0081] S8. Verify the initial risk probability data and generate fault risk information;

[0082] S9. Generate control signals based on energy consumption prediction information and fault risk information.

[0083] Because the geological environment in the working area of ​​a shaft tunneling machine changes in real time and may undergo sudden changes, there is also the risk of equipment failure. Control signals can integrate this dynamic change information and risk warnings to provide a precise basis for equipment adjustment. The main drive speed is the speed parameter that drives the cutterhead to rotate and cut the rock, and the propulsion pressure is the force parameter that propels the tunneling machine downward along the shaft axis. Adjusting these two parameters is because they directly determine the cutterhead cutting efficiency and the equipment's tunneling capacity. When the hardness of the strata increases, increasing the main drive speed can enhance the cutterhead's cutting penetration force, and appropriately increasing the propulsion pressure can prevent equipment jamming. When the strata are soft and prone to collapse, decreasing the main drive speed can reduce disturbance to the surrounding rock, and decreasing the propulsion pressure can prevent excessive compression that could lead to rock instability. At the same time, these two parameters are core factors affecting equipment energy consumption and failure probability; reasonable adjustment can balance operational efficiency and safety risks. Control signals are transmitted to the equipment's main drive system and propulsion system. The main drive system adjusts the motor output power and changes the cutterhead rotation speed according to the signal commands, while the propulsion system adjusts the force of the propulsion cylinder by regulating the hydraulic circuit pressure. To enable tunneling machines to adapt to complex and ever-changing geological environments, avoid accelerated cutterhead wear or equipment overload shutdowns caused by sudden geological changes, reduce the incidence of safety accidents such as cutter blockage and collapse, optimize energy consumption distribution, reduce ineffective energy consumption, improve tunneling efficiency, extend equipment service life, and ensure the high-quality and smooth progress of shaft tunneling projects.

[0084] Preferably, during the operation of the target shaft tunneling machine, information on changes in the geographical environment of the working area corresponding to the target shaft tunneling machine is acquired. Based on this information, the intensity of geological abrupt changes in the working area is determined. The geographical environment change information is quantified to obtain environmental change characteristics; these characteristics are compared with a preset threshold database to determine abrupt environmental change characteristics; the abrupt environmental change characteristics are analyzed to determine comprehensive geographical environment assessment information; and this comprehensive assessment information is then quantified and normalized to determine the intensity of geological abrupt changes. The geological environment in which shaft tunneling machines operate is complex and prone to unknown changes. Existing technologies for traditional tunneling operations often rely on preset geological data or manual inspections to determine geological conditions, resulting in information lag and significant judgment errors. Real-time acquisition of geographical environment change information and determination of geological abrupt changes can provide precise dynamic data on the geological formation for tunneling machine control. Geographical environment change information refers to geological and hydrological data affecting tunneling operations within the tunneling machine's working area, including specific details such as changes in rock hardness, fluctuations in rock integrity, changes in groundwater level and pressure, and signs of fault activity.

[0085] Specifically, in this embodiment of the invention, the intensity of geological abrupt changes is preferably obtained through information on changes in the geographical environment, which can be directly acquired data. Those skilled in the art will understand that the aforementioned information on changes in the geographical environment is merely an example, and the intensity of geological abrupt changes can also be obtained through other geographical information. In the above embodiment, the information on changes in the geographical environment refers to geological and hydrological data affecting tunneling operations within the working area of ​​the tunneling machine.

[0086] The acquisition of the geographical environment change information relies on a multi-source sensor array mounted at the front end of the tunneling machine, including: a front-mounted ground-penetrating radar for transmitting electromagnetic waves with a frequency of 400MHz-900MHz and receiving reflected waveforms, and inverting the change in dielectric constant of the rock mass ahead by analyzing the amplitude attenuation rate and two-way travel time difference of the reflected waves; an ultrasonic detector for collecting the propagation velocity and attenuation coefficient of sound waves in the rock mass; a torque sensor of the cutterhead drive system and a pressure sensor of the propulsion cylinder for collecting instantaneous torque and propulsion thrust in real time; and a pore water pressure gauge installed around the shield for monitoring groundwater pressure.

[0087] Environmental change characteristics are analyzable indicators obtained after quantifying these information, such as the difference in rock hardness per unit depth, the change in rock mass integrity coefficient, and the rate of rise and fall of groundwater level. The preset threshold library is a standard range established based on extensive engineering practice data and geological specifications, encompassing the normal variation range of various environmental parameters under different geological conditions. Using equipment such as ground-penetrating radar, ultrasonic detectors, stress sensors, and hydrological monitoring devices mounted on the tunnel boring machine, real-time geographical environmental data of the working area is collected. After preprocessing this data, including filtering and noise reduction, environmental change characteristics such as the rate of change in rock hardness, the rate of deformation of surrounding rock, and the amplitude of water pressure fluctuations are extracted. These characteristics are then compared one by one with the corresponding standard ranges in the preset threshold library to screen out abrupt environmental change characteristics that exceed the normal range. Subsequently, a weighted summation method is used to analyze and process these abrupt environmental change characteristics. The weights are determined based on the degree of influence of each characteristic on formation stability; for example, the weight of fault activity indicators is higher than that of groundwater level. By analyzing changes in geological position, a comprehensive assessment of the geographical environment reflecting overall environmental anomalies is obtained. Finally, a normalization algorithm is used to convert the comprehensive assessment information into a quantitative value between 0 and 1. The closer the value is to 1, the greater the intensity of the geological abrupt change. Compared with traditional manual judgment or fixed parameter operation mode, it can capture the dynamic changes of the strata in real time and accurately identify risks such as the occurrence of rock strata abrupt changes and faults in advance. It provides a timely basis for adjusting the working status of the tunneling machine, reduces accidents such as overload and collapse of the cutting tool, improves the adaptability and safety of tunneling operations, ensures project progress and construction quality, and makes up for the shortcomings of the existing technology in terms of lagging geological information acquisition and inaccurate judgment.

[0088] Specifically, this involves determining the intensity of geological abrupt changes in the work area based on information about changes in the geographical environment. The specific quantitative processing is as follows: Based on the empirical formula for ultrasonic wave propagation velocity and the dynamic elastic modulus of rock, the difference in dynamic elastic modulus between the current depth and the previous depth (0.5 meters interval) is calculated, and normalized to obtain the characteristics of rock hardness changes. In the field of geotechnical engineering testing, using ultrasonic wave propagation velocity to deduce the dynamic elastic modulus of rock is a mature existing technology. It is usually based on classical elasticity theory. In this embodiment of the invention, instead of directly using the modulus value, it is applied to the dynamic identification of geological abrupt changes: the system collects dynamic elastic modulus data of the current excavation depth and the previous excavation depth (sampling interval set to 0.5 meters) in real time, calculates the difference between the two, and normalizes the difference to obtain a characteristic quantity characterizing the degree of rock hardness abrupt change.

[0089] The energy integral value of the reflected waveform from ground-penetrating radar (GPR) is used to calculate its attenuation ratio relative to a standard intact rock stratum benchmark. Assessing rock mass integrity using GPR reflected wave energy is a standard testing method in the industry. Existing techniques typically qualitatively determine fracture development by measuring the energy integral value of the reflected waveform. A benchmark energy value is pre-calibrated under standard intact rock stratum conditions, and then the attenuation ratio of the currently detected energy integral value relative to the benchmark value is calculated in real time. This allows the determination of the rock mass integrity fluctuation characteristics using a formula.

[0090] The system calculates the rate of change of pore water pressure and sets a threshold. When the rate of change exceeds the threshold, the system is marked as high-risk, thus obtaining groundwater anomaly characteristics. The system calculates the rate of change of pore water pressure over time in real time, and takes the absolute value as the groundwater anomaly characteristic.

[0091] Based on the acquired cutterhead rotation speed, propulsion speed, and tunneling distance, the spatial growth rate of power per unit propulsion distance with respect to tunneling distance is calculated. The system acquires the cutterhead torque, cutterhead rotation speed, propulsion thrust, propulsion speed, and tunneling distance in real time during the current excavation process. First, the product of cutterhead torque and cutterhead rotation speed is calculated to obtain the cutterhead rotation power. Then, the product of propulsion thrust and propulsion speed is calculated to obtain the propulsion system power. Subsequently, the change in the sum of the above two power values ​​corresponding to the current excavation depth and the previous excavation depth (sampling interval set to 0.5 meters) is calculated. Finally, this power change is divided by the distance change between the two corresponding excavation depths to obtain the spatial growth rate of power per unit propulsion distance with respect to tunneling distance. This growth rate can intuitively reflect the power variation law with tunneling distance during the tunneling process, thus obtaining the tunneling parameter response characteristics.

[0092] Environmental change characteristics are obtained based on rock hardness variation characteristics, rock mass integrity fluctuation characteristics, groundwater anomaly characteristics, and tunneling parameter response characteristics. These environmental change characteristics are then compared with a preset threshold library, which stores standard characteristic ranges for different lithologies. If a characteristic value is outside this range, it is determined to be a sudden environmental change characteristic, and its exceedance magnitude is recorded.

[0093] The characteristics of abrupt environmental changes were analyzed and processed to determine comprehensive geographical environment assessment information. A weighted summation algorithm was used, where the weights were determined based on the sensitivity matrix of each feature to stratum stability. Specifically, the weight for fault activity indicators, jointly represented by the characteristic quantities of rock mass integrity fluctuations and tunneling parameter response characteristics, was set at 0.4; the weight for abrupt changes in rock hardness, determined by changes in rock hardness, was set at 0.3; and the weight for abrupt changes in groundwater was set at 0.3. This weight matrix was derived through regression analysis based on a historical engineering accident case database.

[0094] The comprehensive assessment information of the geographical environment is quantified and normalized to determine the intensity of geological abrupt changes. A sigmoid function is used for nonlinear mapping. In one embodiment of this invention, the sensitivity coefficient is set to 1.5, the reference offset is set to 0.5, and the numerical range of the formula for calculating the intensity of geological abrupt changes is strictly limited to between 0 and 1. The closer the value is to 1, the greater the intensity of the geological abrupt change, i.e., the higher the probability of landslides, blockages, or water inrushes.

[0095] Next, based at least on the intensity of formation abrupt changes, an energy consumption disturbance index is determined. This index characterizes the comprehensive disturbance effect of formation abrupt changes on the energy consumption of the target shaft boring machine (TBM). The formation abrupt change intensity is input into the constructed multi-factor coupled calculation model to obtain the theoretical additional load. Based on the energy conversion efficiency curve of the target TBM, the theoretical additional load is processed to determine the instantaneous power compensation requirement. Attenuation analysis is performed on the instantaneous power compensation requirement to determine the disturbance factor. The instantaneous power compensation requirement and the disturbance factor are then integrated to obtain the energy consumption disturbance index. In existing technologies, TBMs mostly adopt fixed energy consumption control strategies, which cannot dynamically adjust energy consumption allocation according to formation changes. When abrupt changes occur in the formation, energy waste or insufficient equipment power is likely to occur. Determining the energy consumption disturbance index can accurately quantify the impact of formation abrupt changes on energy consumption, providing a core basis for subsequent control signal generation. The energy consumption disturbance index is a quantitative indicator that comprehensively reflects the degree of interference of formation abrupt changes on the energy consumption of the TBM; a larger value indicates a more severe impact of formation abrupt changes on energy consumption. The theoretical additional load is the extra operating load that the tunnel boring machine (TBM) bears due to abrupt changes in geological formation, such as the additional cutting force required by the cutterhead when the rock hardness suddenly increases. The energy conversion efficiency curve describes the conversion relationship between the TBM's input electrical energy and output mechanical energy; the conversion efficiency varies under different loads. Instantaneous power compensation requirement is the additional power needed to overcome the theoretical additional load. The disturbance factor is a correction coefficient obtained after considering the load fluctuation attenuation characteristics. By employing mature mechanical analysis methods from existing technologies, and combining data such as changes in rock hardness and fault distribution corresponding to the intensity of ground mutations, a multi-factor coupled calculation model is constructed. The intensity of the ground mutation is substituted into the model to calculate the theoretical additional load that core components of the tunnel boring machine (TBM), such as the cutterhead and propulsion system, must withstand. Then, the energy conversion efficiency curves recorded in the TBM's factory calibration and historical operation are retrieved. Based on the magnitude of the current theoretical additional load, the energy conversion efficiency under the corresponding working condition is found. The instantaneous power compensation requirement to overcome this additional load is derived using the power calculation formula. Subsequently, the decay law of the instantaneous power compensation requirement over time is analyzed. Combined with the duration and decay rate of the ground mutation, a disturbance factor reflecting the stability of load fluctuations is determined. Finally, a weighted summation method is used to integrate the instantaneous power compensation requirement and the disturbance factor, with the instantaneous power compensation requirement having a higher weight, ultimately yielding the energy consumption disturbance index.

[0096] Specifically, the formation mutation intensity is input into the constructed multi-factor coupled calculation model. The prediction model in this embodiment employs a classic multilayer perceptron neural network architecture, using a data-driven approach to accurately capture the complex nonlinear mapping relationship between formation mutation intensity, rock mechanical properties, hydrogeological conditions, and cutterhead additional load. The input layer of the multi-factor coupled calculation model receives multidimensional feature vectors, including formation mutation intensity and real-time groundwater pressure. Two fully connected hidden layers are set, with 32 and 16 neurons respectively, and linear rectified units are used as the activation function to enhance the model's ability to extract nonlinear working condition features, effectively solving the problem that traditional linear regression cannot fit complex formation mutations. The output layer contains a single neuron, directly outputting the theoretical additional load prediction value, which quantifies the increase in cutterhead cutting resistance and propulsion system friction resistance caused by formation mutation.

[0097] The model's training dataset is derived from a fusion of historical tunneling engineering measured data and high-fidelity finite element simulation data. Historical tunneling logs of tunnel boring machines (TBMs) under different geological conditions were collected, and samples containing complete geological abrupt change events were selected. The corresponding abrupt change intensity, rock strength, water pressure, and actual monitored load peak values ​​were extracted, resulting in a total of 5000 valid samples. For extreme abrupt change conditions scarce in the measured data, supplementary samples were generated using discrete element-finite element coupled simulation software, expanding the data coverage and ensuring the model's generalization ability under extreme conditions. All input features were normalized to eliminate dimensional differences, and the dataset was divided into training, validation, and test sets in an 8:1:1 ratio.

[0098] The multi-factor coupled computational model was trained using the backpropagation algorithm. Mean squared error was chosen as the loss function to minimize the deviation between the predicted and actual loads. The Adam optimizer was used to dynamically adjust the learning rate, with an initial learning rate of 0.001, and a Dropout mechanism was introduced with a dropout rate of 0.2 to prevent overfitting. After 200 epochs of iterative training, the model achieved a convergence accuracy of over 95% on the validation set. The final model can adaptively output high-precision predictions of additional loads based on real-time input mutation intensity and geological parameters, without requiring manual coefficient adjustment, significantly improving the robustness of the control strategy to complex geological formations.

[0099] After obtaining the theoretical additional load, the theoretical additional load is processed based on the energy conversion efficiency curve of the target shaft boring machine to determine the instantaneous power compensation requirement. The energy conversion efficiency curve is obtained as follows: before the boring machine leaves the factory and during regular maintenance, different levels of simulated loads (covering the range from zero to 120% of the rated torque) are applied in bench tests, the corresponding input electrical power and output mechanical power are recorded, the efficiency value at each load point is calculated, and a continuous efficiency curve is generated and stored in the controller using a cubic polynomial fitting method.

[0100] The calculation process for instantaneous power compensation requirement is as follows: First, add the current base torque to the theoretical additional load to obtain the total load torque. Then, find the energy conversion efficiency value corresponding to the total load torque on the energy conversion efficiency curve mentioned above. Finally, multiply the theoretical additional load by the current propulsion speed and divide by the found energy conversion efficiency value to calculate the instantaneous power compensation requirement required to overcome the additional load.

[0101] Next, an attenuation analysis is performed on the instantaneous power compensation requirement to determine the disturbance factor. Considering that abrupt changes in formation often have transient impact characteristics, a time decay function is introduced to determine the disturbance factor. Its calculation logic is as follows: the disturbance factor is equal to the negative exponent of the natural constant e, where the base of the exponent is the product of the formation stress release rate coefficient and the time elapsed since the detection of the abrupt change. The formation stress release rate coefficient is a preset constant based on lithological classification; in this embodiment, it is set to 0.1 for hard rock and 0.3 for soft rock. This factor is used to correct for the rapid load decrease trend caused by rock fracturing or stress release, making the calculation results more consistent with the actual physical process.

[0102] Finally, the sum of the disturbance factor plus 1 is multiplied by the instantaneous power compensation requirement, and then multiplied by the safety redundancy coefficient to obtain the energy consumption disturbance index. In this embodiment of the invention, the safety redundancy coefficient ranges from 1.1 to 1.2. The final energy consumption disturbance index is expressed in kilowatts, directly representing the additional peak power required to overcome the current geological abrupt change, providing a precise quantitative basis for subsequent control strategies. Those skilled in the art will understand that the above method for obtaining the energy consumption disturbance index is merely an example, and other methods can also be used to obtain the energy consumption disturbance index.

[0103] Compared to the crude energy consumption control methods in existing technologies, this solution can accurately quantify the dynamic impact of geological changes on energy consumption, avoiding energy waste caused by blindly increasing power or equipment failure caused by insufficient power. It provides accurate energy consumption basis for subsequent adjustment of main drive speed and propulsion pressure, improves the energy utilization efficiency of tunneling machines, enhances the equipment's adaptability to complex strata, reduces work interruptions caused by energy consumption mismatch, and ensures efficient and stable progress of tunneling projects.

[0104] In step S4, the energy consumption disturbance index is processed to obtain the predicted energy consumption change rate of the working area. Current tunneling machine energy consumption control largely relies on real-time energy consumption data feedback for adjustment, which suffers from response lag. When sudden geological changes cause energy consumption fluctuations, it is difficult to predict energy consumption trends in a timely manner. Obtaining the predicted energy consumption change rate allows for early understanding of dynamic energy consumption changes, providing crucial support for subsequent energy consumption prediction information generation and control signal formulation. The predicted energy consumption change rate refers to the expected increase or decrease in tunneling machine energy consumption per unit time, such as a 5% increase or 3% decrease per hour, which directly reflects the future direction and magnitude of energy consumption changes. First, collect the current instantaneous energy consumption data of the tunneling machine, including the electrical energy consumption values ​​of core components such as the main drive system and propulsion system. Combined with the determined energy consumption disturbance index, the commonly used processing method in existing technologies is to use time series analysis to identify the correlation between the energy consumption disturbance index and historical energy consumption changes. Then, the moving average method is used to smooth the energy consumption disturbance index to eliminate errors caused by short-term fluctuations. Subsequently, based on the magnitude and trend of the energy consumption disturbance index, combined with the current operating parameters of the tunneling machine, such as cutterhead speed and propulsion speed, the estimated energy consumption changes for different time periods are calculated through linear interpolation. Finally, these estimated values ​​are converted into the proportion of energy consumption change per unit time, i.e., the predicted energy consumption change rate. Compared with the passive response mode of energy consumption changes in existing technologies, this method can predict energy consumption trends in advance, avoid overload or insufficient power of the equipment power supply system due to sudden changes in energy consumption, provide a forward-looking basis for subsequent adjustments to the main drive speed and propulsion pressure, and help optimize energy consumption allocation, reduce ineffective energy consumption, improve the economy and stability of tunneling machine operation, and ensure that the project progress is not affected by energy consumption issues.

[0105] Specifically, the energy consumption disturbance index is trend-followed to obtain the predicted energy consumption change rate. The system first collects historical data sequences from the past ten sampling periods, filtering out high-frequency noise using a Gaussian filter. Then, it calculates the first-order difference slope of the sequence—the difference between the current value and the value ten periods ago—divided by the time span. The product of this slope and the current total energy consumption is normalized to the rated power, thus obtaining a percentage value representing the relative increase or decrease in energy consumption per unit time in the future. Those skilled in the art will understand that the above method for obtaining the predicted energy consumption change rate is only one example; other methods can also be used to obtain the predicted energy consumption change rate.

[0106] Next, based on the predicted energy consumption change rate and the corresponding formation mutation intensity, energy consumption prediction information is determined. A correlation analysis is performed on the predicted energy consumption change rate and the corresponding formation mutation intensity to determine the coordinated change information; this coordinated change information is matched with a preset formation and energy consumption mapping relationship to determine the energy consumption deviation coefficient; based on the energy consumption deviation coefficient and the obtained current operating parameters of the target shaft tunneling machine, energy consumption prediction information is generated. Existing technologies often rely solely on energy consumption data or formation information, ignoring the dynamic correlation between the two, leading to significant deviations between the prediction results and actual energy consumption. However, combining the predicted energy consumption change rate and formation mutation intensity to determine energy consumption prediction information allows energy consumption forecasts to better align with actual operating scenarios, providing accurate energy consumption data for tunneling machine control. Energy consumption prediction information is predictive data on the magnitude, trend, and peak range of energy consumption during subsequent operating periods of the tunneling machine, including specific details such as estimated energy consumption per unit tunneling depth and total energy consumption over the operating cycle. Synergistic variation information reflects the correlation between the predicted energy consumption change rate and the intensity of formation mutations over time, such as the synchronous increase in the predicted energy consumption change rate when the intensity of formation mutations increases. The formation-energy consumption mapping relationship is based on preset data summarized from a large number of tunneling engineering practices, recording the benchmark range of energy consumption changes corresponding to different formation mutation intensities. The energy consumption deviation coefficient is a quantitative indicator that measures the degree of matching between the synergistic variation information and the preset mapping relationship, used to correct the difference between theoretical mapping and actual working conditions. The specific approach involves first using a correlation analysis algorithm commonly used in existing technologies to calculate the correlation coefficient between the predicted energy consumption change rate and the intensity of formation mutations, identifying the synchronous pattern of their simultaneous increase and decrease, and determining the information on coordinated changes. Then, a pre-defined mapping relationship between formations and energy consumption is retrieved. This relationship is a standard correspondence table established in existing technologies by statistically analyzing multiple sets of measured data on formation mutations and energy consumption changes. The information on coordinated changes is compared and matched one by one with the data in the table, and the difference between the actual correlation and the standard mapping is calculated to obtain the energy consumption deviation coefficient. Subsequently, the current operating parameters of the tunneling machine are acquired, including real-time data such as main drive current, propulsion pressure, and cutterhead speed. The baseline energy consumption corresponding to the coordinated change information is then corrected based on the energy consumption deviation coefficient. For example, if the deviation coefficient is 1.2, the baseline energy consumption is increased by 20%. Finally, energy consumption prediction information containing the trend of energy consumption prediction values ​​and peak nodes for subsequent periods is generated.

[0107] Specifically, based on the coupled analysis of the predicted energy consumption change rate and the formation abrupt change intensity, specific energy consumption prediction information is generated, and the steps are as follows:

[0108] First, calculate the Pearson correlation coefficient between the two: if it is greater than 0.8, it is confirmed as a strong positive correlation caused by geological deterioration; if it is between 0.3 and 0.8, it is considered as a moderate correlation; if it is less than or equal to 0.3, it indicates the presence of non-geological interference factors.

[0109] Secondly, the system calls a preset two-dimensional mapping table with the horizontal axis representing the stratigraphic abrupt change level and the vertical axis representing lithological classification, and retrieves the standard baseline energy consumption growth rate under the current operating conditions. The predicted energy consumption change rate is then divided by this baseline value to obtain the energy consumption deviation coefficient. In one embodiment of this invention, if the baseline value is zero, it is defaulted to 1, thus measuring the degree to which the actual operating conditions deviate from the standard model.

[0110] Finally, the system first estimates the expected crossing time, calculated using the formula shown in Equation 1. The expected crossing time is obtained by dividing the length of the abnormal area detected by the ground-penetrating radar by the current tunneling speed.

[0111]

[0112] To estimate the travel time, The length of the abnormal region. The tunneling speed is denoted by . The expected crossing time will be directly used as the core time parameter for the subsequent linear triangular wave model.

[0113] Subsequently, a linear triangular wave model is used to replace the complex sinusoidal fluctuations: during the time period from 0 to T / 2 (i.e., from 0 to half of the expected crossing time), the correction factor is linearly increased from the baseline value to its maximum value, i.e., 1 + energy consumption deviation coefficient; during the time period from T / 2 to T (i.e., from half of the expected crossing time to the end of the expected crossing time), the correction factor is linearly decreased back to the baseline value. This model simulates the entire process of energy consumption increase when the tunneling machine enters the abnormal zone, the highest energy consumption upon reaching the center, and the energy consumption decrease upon leaving the abnormal zone. Finally, the system multiplies the current total energy consumption by this linearly changing correction factor to generate an energy consumption prediction curve for the next five minutes, and outputs the average prediction value, peak time, peak size, and a ±5% confidence interval. Those skilled in the art will understand that the above method for obtaining the energy consumption prediction curve is only one example, and other methods can also be used to obtain the energy consumption prediction curve.

[0114] Compared to existing single-dimensional energy consumption prediction methods, this approach fully integrates the correlation between geological changes and energy consumption fluctuations, improving the accuracy of energy consumption prediction. It avoids excessive energy consumption or insufficient power due to prediction deviations, providing a reliable energy consumption basis for subsequent control signal generation. At the same time, it helps optimize the adjustment strategy of tunneling machine operating parameters, reduces ineffective energy consumption, improves operational economy, reduces the risk of equipment failure caused by energy consumption mismatch, and ensures efficient project progress.

[0115] Acquire electrical sampling data of the target shaft tunneling machine during its operation. Current technologies often rely on manual inspections or post-fault analysis to assess tunneling machine failure risks, leading to delays in detection and inaccurate assessments. Electrical sampling data, however, reflects the real-time operating status of core components, serving as the foundation for determining initial risk probability data and generating failure risk information, thus providing data support for safe equipment operation. Electrical sampling data consists of various electrical parameters collected by specialized equipment during the tunneling machine's electrical system operation. These parameters include the operating current, voltage, and power factor of the main drive motor; the current fluctuation value of the hydraulic pump motor in the propulsion system; the signal transmission voltage of the control system; and the insulation resistance values ​​of each electrical circuit. Sampling devices such as current sensors, voltage sensors, and power sensors, which are mature technologies in existing technologies, are installed on the wiring of key electrical components such as the main drive system, propulsion system, and control system of the tunneling machine. These sensors are set to a sampling frequency of 10 to 20 times per second, which can capture the dynamic changes of electrical parameters in real time. The sampling devices transmit the collected raw electrical signals to the data acquisition module via wired transmission. The data acquisition module performs preprocessing on the raw signals, such as filtering, amplification, and analog-to-digital conversion, to remove invalid data caused by electromagnetic interference. Finally, standardized electrical sampling data is generated and stored in the database of the equipment control system. Compared with the traditional manual monitoring methods in existing technologies, this method can achieve real-time, continuous, and accurate acquisition of electrical parameters, timely capture early signals of potential faults such as motor overload, abnormal voltage, or line leakage, provide comprehensive and reliable raw data for subsequent fault risk assessment, help to provide early warning of equipment failures, reduce the impact of sudden shutdowns on project progress, reduce the labor intensity of manual inspection and human judgment errors, improve the safety and stability of tunneling machine operation, and extend the service life of electrical components.

[0116] Based on electrical sampling data, initial risk probability data is determined. Assessments of tunneling machine failure risks often rely on qualitative judgments, lacking quantitative evidence, leading to low accuracy in risk warnings. Initial risk probability data transforms equipment anomalies reflected in electrical sampling data into quantifiable risk indicators, laying the foundation for subsequent failure risk information generation and helping to identify potential failures in advance. Initial risk probability data is a quantitative value characterizing the probability of failure of various electrically related components of the tunneling machine, ranging from 0 to 1. The closer the value is to 1, the higher the failure risk. Specifically, it includes the failure probability of the main drive motor, the failure probability of the propulsion system electrical circuit, and the failure probability of the control system signal transmission. First, a fault feature database based on numerous electrical fault cases of tunneling machines is retrieved from existing technologies. This database contains the correlation between different abnormal electrical parameters and corresponding fault types, such as the probability of winding overheating when the main drive motor current continuously exceeds the rated value by 15% or the probability of power supply system fault when the voltage fluctuation exceeds ±10%. Then, key features such as the duration of current exceeding the standard, voltage fluctuation amplitude, or frequency of abnormal power factor are extracted from the electrical sampling data. These features are compared with standard thresholds in the fault feature database. Using commonly used probabilistic statistical methods in existing technologies, the probability of fault occurrence corresponding to each feature is calculated. Subsequently, a weighted sum is performed according to the influence weight of each electrical component on the overall operation of the equipment, finally obtaining initial risk probability data covering the main fault types. Compared with the fuzzy risk judgment methods in existing technologies, this approach enables quantitative assessment of fault risk, making the risk level more intuitive and providing a clear basis for subsequent verification of fault risk information. This helps to identify high-risk components in advance, take timely preventive measures, reduce tunneling interruptions caused by sudden faults, reduce equipment maintenance costs, and improve the objectivity and accuracy of risk assessment, ensuring the continuous and stable progress of the shaft tunneling project.

[0117] Preferably, the initial risk probability data is verified to generate fault risk information. The initial risk probability data is compared with a preset threshold range to generate preliminary verification results; a sliding time window is used to analyze the preliminary verification results to obtain the risk confidence level; the risk confidence level is mapped to a predefined fault classification system to obtain fault risk information. In existing technologies, the initial risk probability data obtained only through a single electrical parameter analysis may be affected by instantaneous interference or sampling errors, posing a risk of misjudgment. Verification can filter invalid data, improve the reliability of risk assessment, and the fault risk information can directly provide accurate fault warnings for control signal generation, avoiding equipment operation with risks. Fault risk information is a comprehensive judgment result that clearly defines the fault type, risk level, and impact range of the tunneling machine, including specific details such as high-risk fault items, risk occurrence confidence level, and possible downtime. The preset threshold range is a risk probability range set based on the tunneling machine's electrical system design standards and historical fault data, divided into three ranges: low risk, medium risk, and high risk. For example, 0 to 0.3 is the low-risk range; 0.3 to 0.7 is the medium-risk range; and 0.7 to 1 is the high-risk range. Sliding time windows are a commonly used time-series data analysis tool in existing technologies. They involve selecting a continuous, fixed duration as the analysis window, such as a 30-second window, to capture risk trends over a period of time. Risk confidence is a quantitative indicator that measures the reliability of preliminary verification results, reflecting the credibility of fault risk assessment; a higher value indicates a stronger certainty of fault occurrence. A predefined fault classification system is a classification standard based on the scope and severity of fault impact, including categories such as electrical system faults, mechanically related faults, and overall downtime risk. The initial risk probability data is compared one by one with a preset threshold range. If the risk probability of a component is between 0.7 and 1, it is initially judged as a high-risk fault; between 0.3 and 0.7, it is judged as a medium-risk fault; and below 0.3, it is judged as a low-risk fault, generating preliminary verification results. Then, using the mature sliding time window algorithm, a 30-second time window is set to continuously analyze the preliminary verification results, statistically analyzing the frequency and duration of the same risk level within the window. For example, if a high-risk state lasts for more than 10 seconds, the risk confidence increases to 0.9; if it lasts for less than 5 seconds, the confidence decreases to 0.4, obtaining the risk confidence of each risk item. Finally, the risk confidence is mapped to a predefined fault classification system. High-risk items with a confidence higher than 0.8 are classified as emergency faults, medium-risk items with a confidence of 0.5 to 0.8 are classified as faults requiring attention, and low-risk items with a confidence lower than 0.5 are classified as normal fluctuations. Finally, the data is integrated to form fault risk information that includes fault type, risk level, and confidence.The advantage of this approach is that, compared to the unverified risk assessments in existing technologies, it can effectively eliminate misjudgments caused by transient interference, improve the accuracy and reliability of fault risk assessment, provide precise basis for subsequent control signal generation, help to adjust the working status of the tunneling machine in a targeted manner, avoid high-risk faults in advance, reduce losses from sudden downtime, and clarify fault classification and risk level, making it easier for operators to take quick countermeasures, thereby improving equipment operating safety and project progress efficiency.

[0118] Finally, control signals are generated based on energy consumption prediction information and fault risk information. Because existing technologies for tunneling machines generate control signals using single reference energy consumption or fault data, parameter adjustments can easily become disconnected from actual working conditions. However, combining energy consumption prediction information and fault risk information to generate control signals enables coordinated control of energy consumption optimization and fault avoidance. Ultimately, the main drive speed and propulsion pressure of the shaft tunneling machine are adjusted through the control signals, allowing the equipment's operating state to adapt to changes in the geological formation and its own operational safety. Control signals are instruction data transmitted to the tunneling machine's control system, including main drive speed adjustment values ​​and propulsion pressure adjustment parameters, which directly drive the equipment's actuators to change their operating state. Energy consumption prediction information is predictive data on the trend, peak, and distribution of energy consumption changes in subsequent operations, such as estimated energy consumption per unit depth and total energy consumption per cycle. Fault risk information is a comprehensive judgment result that clearly defines the fault type, risk level, and scope of impact, including high-risk fault items and risk confidence levels. First, mature multi-source data fusion algorithms from existing technologies are used to correlate the predicted energy consumption change rate and peak energy consumption range in the energy consumption prediction information with the fault type and risk level in the fault risk information. For example, when there is a high-risk electrical fault and the predicted energy consumption is high, a control strategy to reduce the load is prioritized. When there is a low-risk fault and sufficient energy consumption, the focus is on adjusting parameters to maintain efficiency. Then, based on the correlation analysis results, combined with the adjustment logic of the main drive speed and propulsion pressure, for example, when a sudden change in the formation causes a 30% increase in the predicted energy consumption and there is no high-risk fault, the main drive speed is increased by 10% and the propulsion pressure is increased by 8%. If there is a high-risk fault of overheating of the main drive motor, the main drive speed is decreased by 15% and the propulsion pressure is reduced by 12%. Subsequently, the adjustment parameters are optimized through the control algorithm to eliminate the unstable effects caused by parameter fluctuations. Finally, a control signal containing specific speed and pressure values ​​is generated to ensure that the control signal can directly drive the main drive system and propulsion system to perform adjustments. Compared to the single-dimensional control signal generation method in existing technologies, this method can achieve a balance between energy consumption and safety. It allows the adjustment of the main drive speed and propulsion pressure to adapt to the energy consumption requirements brought about by sudden changes in the strata, while avoiding the risk of failure. It prevents equipment from being damaged by overload or becoming inefficient due to improper parameters. At the same time, it improves the adaptability of the tunneling machine to complex working conditions, reduces sudden downtime and maintenance costs, and ensures the efficient, safe and stable advancement of the shaft tunneling project.

[0119] It is important to note that the effective execution of the above control strategy is highly dependent on the stable response and precise energy delivery of the power supply system. If there are hidden dangers in the power supply link, the power compensation requirements calculated above will not be able to be safely implemented. Therefore, this embodiment, based on the explanation of the core control logic, further provides the physical basis supporting the implementation of this control method. Preferably, it provides a construction and commissioning scheme for the power supply system of a shaft boring machine. Regarding the existing technical content such as conventional hardware selection, general electrical connection standards, and basic safety protection measures involved in the power supply system, those skilled in the art can make corresponding decisions according to the actual commissioning requirements, and will not be specifically described in this embodiment of the invention. The following will focus on describing the control method of the shaft boring machine that is strongly related to the above steps S1 to S9, including key construction steps such as dynamic cable positioning and safety threshold calibration to ensure that energy consumption disturbances can be accurately converted into control signals, thereby ensuring the integrity and feasibility of the overall technical solution.

[0120] Another embodiment of the present invention provides a specific operation method for controlling a shaft tunneling machine. The method includes: collecting key electrical parameters from the shaft tunneling machine, including fundamental parameters in current harmonics, partial discharge intensity parameters in insulation resistance, and energy feedback rate parameters, and cleaning and integrating the aforementioned parameters in real time. At the same time, combining the three-dimensional spatial coordinates of the shaft tunneling machine's cable, a multimodal data association model is established. The real-time status of the shaft tunneling machine's power supply system is reflected through the "electrical-spatial" dual dimensions. Based on the aforementioned model, the probabilities of three types of risks—cable overheating, harmonic exceedance, and insulation failure—are integrated to construct a 128-dimensional equipment status matrix.

[0121] Construction of an "Electrical-Spatial" Multimodal Correlation Model: Risk decomposition of power supply safety events for shaft tunneling machines yields three risk categories: cable overheating, harmonic exceedance, and insulation failure, as shown in the table below:

[0122] Table 1. Safety incidents related to power supply for shaft boring machines.

[0123]

[0124] This invention first constructs a multimodal data association model based on the three-dimensional spatial coordinates of the cable. This is achieved by dividing the system into 16 independent monitoring grids and establishing an "electrical-spatial" parameter mapping relationship, integrating three types of risk probabilities. The system receives a 128-dimensional equipment state matrix generated by the power data acquisition module, extracts the spatial coordinate information of each monitoring grid, and simultaneously collects real-time temperature data from the shaft tunneling machine's motor reducer and thruster. After mapping these temperature data to the corresponding spatial grid coordinates, a moving average filtering process is performed to obtain filtered critical equipment temperature data. Based on this, a cable topology model is established using the spatial coordinate information based on the traveling wave ranging principle. The filtered temperature data serves as a trigger condition: when the temperature of the critical equipment exceeds 50°C, a dynamic wave velocity correction mechanism is triggered. The fault distance at a single monitoring point is calculated based on the time difference between the arrival of the traveling wave at the cable's beginning and end, combined with the corrected wave velocity. If an insulation resistance gradient of a grid is detected to be below -5 megohms per meter, it is marked as an "insulation failure risk grid," and a confidence interval contraction mechanism is activated to reduce the positioning error from within 1.5 meters to within 0.8 meters. Subsequently, a similarity matrix is ​​used to cluster outliers to eliminate interfering data, ultimately determining the precise spatial coordinates of the outliers. This positioning result includes coordinates, corrected wave velocity values, and positioning confidence. It is not only synchronized to the power supply safety perception module for dynamic correction of risk probability but also fed back to the shaft tunneling machine control system: when the outlier is less than 10 meters from the tunnel face, it is recommended to reduce the tunneling speed by 20%; when the outlier is located on a critical power supply path, it is recommended to activate the backup power supply circuit, thereby achieving accurate positioning and rapid response of outliers on the power supply path.

[0125] This invention further utilizes the aforementioned positioning information and a 128-dimensional device state matrix for dynamic risk assessment. The system extracts fundamental characteristic values ​​from the state matrix to calculate the zero-sequence current mutation rate and extracts insulation characteristic values ​​focusing on partial discharge intensity and insulation resistance gradient. Simultaneously, it combines anomaly point coordinates and corrected wave velocities to construct a red-black tree data structure with monitoring grids as nodes. Each node contains spatial coordinates, electrical characteristic values, and a spatial weight factor determined by the energy feedback rate characteristic value. The system employs a dual threshold mechanism for risk determination, where the high-risk determination threshold for red nodes is dynamically adjusted based on the spatial weight. By matching the anomaly point coordinates with the red-black tree nodes using Euclidean distance, the threat level of the grid node closest to the anomaly point is increased. The increase coefficient is calculated based on the distance between the grid node and the anomaly point, as well as physical quantities characterizing rock mass strength. Accordingly, the risk probability of black nodes is corrected, and a weighted probability fusion algorithm is used to calculate the overall real-time risk probability of the system, outputting the risk value, high-risk grid coordinates, and main risk types. The assessment results directly drive the graded response strategy: when the risk probability is greater than 0.8, a fault linkage mechanism is triggered; when it is between 0.5 and 0.8, an energy-saving optimization command is generated; and when it is less than or equal to 0.5, normal operation is maintained, thereby achieving real-time and accurate perception of the safety status of the power supply system.

[0126] In the embodiment of the present invention, a multi-objective collaborative optimization mechanism considering geological parameters and process energy consumption is also established. The system extracts the energy feedback rate eigenvalue in the state matrix, and combines geological parameters such as surrounding rock grade and rock mass strength to construct a mapping knowledge graph of the characteristics of the surrounding rock and the electricity consumption per ton of rock. A multivariate nonlinear regression model is used to calculate the electricity consumption per ton of rock, which comprehensively considers the Prandtl hardness coefficient, rock density, tunneling diameter and correction factor. On this basis, a decomposition model of the electricity consumption per ton of rock including cutterhead rock breaking, shoe step change and auxiliary system energy consumption is established, and time series analysis combined with machine learning algorithms is used to predict the energy consumption trend in the next 24 hours based on the energy feedback rate, surrounding rock grade and rock mass strength. The system comprehensively considers the predicted energy consumption and the real-time risk probability, establishes a multi-objective optimization function with the goal of minimizing the weighted energy consumption and risk, and generates optimized main drive speed and propulsion pressure commands; among which, the speed optimization is adjusted based on the original speed, the average value of the energy feedback rate and the risk probability, and the propulsion pressure optimization is adjusted based on the original pressure, rock mass strength and risk probability. These optimized commands are fed back to the control system to revise the tunneling parameters, including recommended cutterhead speed, propulsion pressure and maximum allowable tunneling speed. At the same time, the system establishes a comprehensive efficiency evaluation index composed of transmission efficiency, cable efficiency and energy feedback rate. When this index is lower than 85%, the energy efficiency optimization process is automatically triggered to readjust the equipment operation parameters to achieve the collaborative optimization of the power supply and consumption system and the tunneling process.

[0127] Finally, the embodiment of the present invention provides a construction method for the power supply and consumption system of a modular integrated shaft tunneling machine, which covers three stages: equipment positioning, electrical commissioning and intelligent control. In the equipment positioning stage, a high-precision laser centering instrument is used for coaxiality calibration, and a four-stage step-by-step unloading strategy is implemented, with the unloading amount of each stage controlled within 15% of the rated load; by establishing a dynamic monitoring model of cable stress, a PID controller is used to dynamically adjust the unloading rate to ensure that the axial tensile stress of the cable is always lower than 5 MPa. In the electrical system commissioning stage, a three-stage phase verification process including rough calibration with a multimeter, fine calibration with a phase sequence meter and final verification with a wireless phase detector is implemented, and the phase synchronization quality index is output by fusing the phase verification data through Kalman filtering. It is only judged as qualified when the index is greater than 0.9�; subsequently, a variable frequency series resonance device is used for the withstand voltage test, and a leakage current monitoring model is established to monitor the leakage current in real time. If the current exceeds 5 μA or shows non-linear growth, the protection is immediately triggered. In the intelligent control stage, a dual-output BP neural network with a spatial attention mechanism is constructed, and the 128-dimensional state matrix is mapped in layers according to the spatial grid; a fault linkage closed loop is realized, that is, when the insulation risk probability exceeds 0.85, the power supply of the corresponding grid is cut off within 200 milliseconds and rechecked; an energy-saving execution closed loop is realized, that is, the propulsion pressure is automatically increased in a specific buried depth section; and a state update closed loop is realized, and the state matrix is updated every 5 minutes to trigger the re-optimization of the neural network weights, so as to ensure the construction quality and system reliability.

[0128] Another embodiment of the present invention provides a control system for a shaft boring machine; please refer to [link to relevant documentation]. Figure 2 , Figure 2 The diagram shown is a structural schematic of the control system of a shaft boring machine according to one embodiment of the present invention. The system includes:

[0129] Control module 11 is used to control the target shaft tunneling machine to adjust its working state based on received control signals. The working state includes at least the main drive speed and propulsion pressure of the target shaft tunneling machine. The process of generating the control signals is as follows:

[0130] The stratum mutation module 12 is used to acquire geographical environment change information of the working area corresponding to the target shaft tunneling machine during the working process of the target shaft tunneling machine, and determine the stratum mutation intensity of the working area based on the geographical environment change information;

[0131] Energy consumption disturbance module 13 is used to determine the energy consumption disturbance index based at least on the formation change intensity, wherein the energy consumption disturbance index is used to characterize the comprehensive disturbance degree of formation change intensity on the energy consumption of the target shaft tunneling machine.

[0132] The energy consumption change rate module 14 is used to process the energy consumption disturbance index to obtain the predicted energy consumption change rate of the working area.

[0133] Prediction module 15 is used to determine energy consumption prediction information based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity; and,

[0134] Acquisition module 16 is used to acquire electrical sampling data of the target shaft tunneling machine during its operation.

[0135] Module 17 is used to determine initial risk probability data based on electrical sampling data;

[0136] Verification module 18 is used to verify the initial risk probability data and generate fault risk information;

[0137] The generation module 19 is used to generate control signals based on energy consumption prediction information and fault risk information.

[0138] Preferably, based on information on changes in the geographical environment, the intensity of abrupt changes in the stratigraphy of the work area is determined, including:

[0139] The quantification unit is used to quantify information on changes in the geographical environment to obtain environmental change characteristics.

[0140] The comparison unit is used to compare environmental change characteristics with a preset threshold library to determine the characteristics of mutated environmental changes.

[0141] The unit is used to analyze and process the characteristics of sudden environmental changes and determine comprehensive geographical environment assessment information;

[0142] The processing unit is used to quantify and normalize the comprehensive assessment information of the geographical environment to determine the intensity of stratigraphic abrupt changes.

[0143] Preferably, the energy consumption disturbance index is determined based at least on the intensity of formation abrupt change, including:

[0144] The model unit is used to input the formation mutation intensity into the constructed multi-factor coupled calculation model to obtain the theoretical additional load;

[0145] The processing unit is used to process the theoretical additional load based on the energy conversion efficiency curve of the target shaft tunneling machine and determine the instantaneous power compensation requirements.

[0146] The analysis unit is used to perform attenuation analysis on instantaneous power compensation requirements and determine the disturbance factor;

[0147] The energy consumption disturbance unit is used to integrate instantaneous power compensation demand and disturbance factor to obtain the energy consumption disturbance index.

[0148] Preferably, the prediction module includes:

[0149] The correlation analysis unit is used to perform correlation analysis between the predicted energy consumption change rate and the corresponding formation abrupt change intensity to determine the cooperative change information.

[0150] The matching unit is used to match the coordinated change information with the preset formation and energy consumption mapping relationship to determine the energy consumption deviation coefficient;

[0151] The generation unit is used to generate energy consumption prediction information based on the energy consumption deviation coefficient and the current operating parameters of the target shaft tunneling machine.

[0152] Preferably, the verification module includes:

[0153] The threshold unit is used to compare the initial risk probability data with the preset threshold range to generate preliminary verification results;

[0154] The analysis unit is used to analyze the preliminary verification results using a sliding time window to obtain the risk confidence level;

[0155] The mapping unit is used to map the risk confidence level to a predefined fault classification system to obtain fault risk information.

[0156] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0157] Accordingly, embodiments of the present invention provide a computer-readable storage medium comprising a stored computer program, wherein, when the computer program is executed, it controls the device containing the computer-readable storage medium to perform steps in the control method for a shaft boring machine as described in the above embodiments, for example... Figure 1 Steps S1 to S9 as described above.

[0158] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0159] This solution addresses the problems of existing vertical shaft tunneling methods, such as reliance on manual experience, low control precision, and susceptibility to efficiency decline and safety risks. It proposes an intelligent control method that integrates geological environment perception and equipment electrical status monitoring. This method acquires real-time information on changes in the geographical environment of the working area during tunneling, quantifies the intensity of geological abrupt changes, and constructs an energy consumption disturbance index based on this, further deriving the predicted energy consumption change rate and forming a forward-looking judgment on subsequent energy consumption trends. Simultaneously, by collecting electrical sampling data during tunneling machine operation, potential anomalies are identified and reliable fault risk information is generated through multi-level verification. Finally, the above-mentioned energy consumption prediction information and fault risk information are jointly used for decision-making, automatically generating control signals for dynamically adjusting the main drive speed and propulsion pressure. Thus, the system can autonomously optimize tunneling parameters under complex and variable geological conditions, avoiding problems such as propulsion fluctuations, abnormal cutter wear, or equipment overload caused by human misjudgment. While improving tunneling efficiency and construction stability, it significantly reduces unit energy consumption, decreases equipment failure rate, and effectively controls the risks of surrounding rock disturbance and surface subsidence, comprehensively ensuring the safety, accuracy, and economy of vertical shaft construction.

Claims

1. A control method of a shaft heading machine, characterized by, include: The target shaft tunneling machine is controlled by the received control signal to adjust its working state, which includes at least the main drive speed and propulsion pressure of the target shaft tunneling machine. The generation process of the control signal is as follows: During the operation of the target shaft tunneling machine, the geographical environment change information of the working area corresponding to the target shaft tunneling machine is acquired, and the geological change intensity of the working area is determined based on the geographical environment change information; At least based on the formation abrupt change intensity, an energy consumption disturbance index is determined, wherein the energy consumption disturbance index is used to characterize the overall disturbance degree of the formation abrupt change intensity on the energy consumption of the target shaft boring machine; The energy consumption disturbance index is processed to obtain the predicted energy consumption change rate of the working area; Based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity, energy consumption prediction information is determined; and, Acquire electrical sampling data of the target shaft tunneling machine during its operation; Based on the electrical sampling data, initial risk probability data is determined; The initial risk probability data is verified to generate fault risk information; The control signal is generated based on the energy consumption prediction information and the fault risk information; The determination of the energy consumption disturbance index, based at least on the formation abrupt change intensity, includes: The formation abrupt change intensity is input into the constructed multi-factor coupled calculation model to obtain the theoretical additional load; Based on the energy conversion efficiency curve of the target shaft boring machine, the theoretical additional load is processed to determine the instantaneous power compensation requirement; An attenuation analysis is performed on the instantaneous power compensation requirement to determine the disturbance factor; The energy consumption disturbance index is obtained by integrating the instantaneous power compensation requirement and the disturbance factor.

2. The control method of the raise boring machine according to claim 1, characterized in that, The determination of the stratigraphic abrupt change intensity of the working area based on the geographical environment change information includes: The geographical environment change information is quantified to obtain environmental change characteristics; The environmental change characteristics are compared with a preset threshold library to determine the characteristics of sudden environmental changes; The characteristics of the abrupt environmental changes are analyzed and processed to determine comprehensive geographical environment assessment information; The comprehensive assessment information of the geographical environment is quantified and normalized to determine the intensity of the geological abrupt change.

3. The control method of the raise boring machine according to claim 1, characterized in that, The process of determining energy consumption prediction information based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity includes: A correlation analysis is performed between the predicted energy consumption change rate and the corresponding formation abrupt change intensity to determine the cooperative change information; The coordinated change information is matched with the preset formation and energy consumption mapping relationship to determine the energy consumption deviation coefficient; The energy consumption prediction information is generated based on the energy consumption deviation coefficient and the current operating parameters of the target shaft tunneling machine.

4. The control method of the raise boring machine according to claim 1, characterized in that, The step of verifying the initial risk probability data and generating fault risk information includes: The initial risk probability data is compared with a preset threshold range to generate preliminary verification results; The preliminary verification results are analyzed using a sliding time window to obtain the risk confidence level; The risk confidence level is mapped to a predefined fault classification system to obtain the fault risk information.

5. A control system for a shaft sinking machine, characterized in that include: A control module is used to control the target shaft tunneling machine to adjust its working state based on received control signals. The working state includes at least the main drive speed and propulsion pressure of the target shaft tunneling machine. The generation process of the control signals is as follows: The geological mutation module is used to acquire geographical environment change information of the working area corresponding to the target shaft tunneling machine during the operation of the target shaft tunneling machine, and to determine the geological mutation intensity of the working area based on the geographical environment change information; An energy consumption disturbance module is used to determine an energy consumption disturbance index based at least on the formation abrupt change intensity, wherein the energy consumption disturbance index is used to characterize the comprehensive disturbance degree of the formation abrupt change intensity on the energy consumption of the target shaft boring machine; The energy consumption change rate module is used to process the energy consumption disturbance index to obtain the predicted energy consumption change rate of the working area. The prediction module is used to determine energy consumption prediction information based on the predicted energy consumption change rate and the corresponding formation abrupt change intensity; and, The acquisition module is used to acquire electrical sampling data of the target shaft tunneling machine during its operation. The determination module is used to determine initial risk probability data based on the electrical sampling data; The verification module is used to verify the initial risk probability data and generate fault risk information; The generation module is used to generate the control signal based on the energy consumption prediction information and the fault risk information; The determination of the energy consumption disturbance index, based at least on the formation abrupt change intensity, includes: The model unit is used to input the formation mutation intensity into the constructed multi-factor coupled calculation model to obtain the theoretical additional load; The processing unit is used to process the theoretical additional load based on the energy conversion efficiency curve of the target shaft boring machine, and determine the instantaneous power compensation requirement. The analysis unit is used to perform attenuation analysis on the instantaneous power compensation requirement and determine the disturbance factor; An energy consumption disturbance unit is used to integrate the instantaneous power compensation demand and the disturbance factor to obtain the energy consumption disturbance index.

6. The control system of a raise boring machine according to claim 5, characterized in that, The determination of the stratigraphic abrupt change intensity of the working area based on the geographical environment change information includes: A quantization processing unit is used to quantify the geographic environment change information to obtain environmental change characteristics; The comparison unit is used to compare the environmental change characteristics with a preset threshold library to determine the characteristics of sudden environmental changes. The determination unit is used to analyze and process the characteristics of the abrupt environmental changes to determine comprehensive geographical environment assessment information; The processing unit is used to quantify and normalize the comprehensive assessment information of the geographical environment to determine the intensity of the geological abrupt change.

7. The control system of the shaft boring machine as described in claim 5, characterized in that, The prediction module includes: The correlation analysis unit is used to perform correlation analysis between the predicted energy consumption change rate and the corresponding formation abrupt change intensity to determine the cooperative change information; The matching unit is used to match the coordinated change information with the preset formation and energy consumption mapping relationship to determine the energy consumption deviation coefficient; The generation unit is used to generate the energy consumption prediction information based on the energy consumption deviation coefficient and the current operating parameters of the target shaft tunneling machine.

8. The control system of the shaft boring machine as described in claim 5, characterized in that, The verification module includes: A threshold unit is used to compare the initial risk probability data with a preset threshold range to generate a preliminary verification result; The analysis unit is used to analyze the preliminary verification results using a sliding time window to obtain the risk confidence level; The mapping unit is used to map the risk confidence level to a predefined fault classification system to obtain the fault risk information.

Images