Intelligent loading control method for shaft excavation bucket

Abstract

The present invention relates to the field of intelligent control technology, and in particular to an intelligent loading control method for a shaft excavation bucket. The method comprises the following steps: performing an impact assessment process of a hoist pit failure on the shaft area to generate hoist pit failure impact data; performing a bucket simulated transportation swing behavior analysis process based on bucket drive transportation control parameters and bucket loading monitoring data to generate bucket simulated transportation swing behavior data; performing a bucket simulated transportation swing trend distribution analysis process based on bucket simulated transportation swing behavior data to generate bucket simulated transportation swing trend distribution data; performing a dynamic bucket drive transportation control parameter analysis based on bucket simulated transportation swing trend distribution data to generate dynamic bucket drive transportation control parameters. The present invention realizes intelligent and efficient drive control and feedback in the shaft excavation process by analyzing the loading status of the bucket and the environmental information of the shaft area.

Description

Technical Field

[0001] The invention relates to the field of intelligent control technology, and in particular to an intelligent loading control method for a shaft excavation bucket. Background Art

[0002] As a common method in underground engineering construction, shaft excavation is widely used in mining, infrastructure construction and other fields. In shaft excavation operations, buckets are usually used as the main means of transportation to transport the soil and rocks produced by excavation to the ground. Due to the complex environment of the shaft and the harsh construction conditions, the bucket is easily affected by various uncertain factors during use, resulting in reduced efficiency and even safety accidents. The high humidity, high temperature and high noise environment in the shaft pose a huge challenge to manual monitoring and the safety of operators, and problems such as bucket swing, uneven loading or overloading lead to bucket collision, overturning and other accidents. By combining data analysis and machine learning, the control information of the bucket during shaft excavation is automatically analyzed to improve the work efficiency of shaft excavation. However, the existing intelligent loading control method of the shaft excavation bucket only focuses on a single parameter (such as bucket mass or position), and cannot realize the comprehensive monitoring and dynamic control of the bucket loading state, mechanical behavior during transportation and environmental factors; for the safety protection of personnel in the bucket, foundation pit water accumulation alarm and other potential risks, no effective solution has been proposed in the prior art. Summary of the invention

[0003] Based on this, the present invention provides an intelligent loading control method for a shaft excavation bucket to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent loading control method for a shaft excavation bucket comprises the following steps:

[0005] Step S1: using the monitoring sensors built into the shaft to monitor the shaft environment and perform spatiotemporal mapping of the monitoring data to generate shaft environment spatiotemporal mapping data; performing an impact assessment of the hoist pit fault based on the shaft environment spatiotemporal mapping data to generate hoist pit fault impact data;

[0006] Step S2: when the hoist foundation pit fault impact data is greater than the preset hoist foundation pit alarm threshold, the foundation pit alarm feedback operation is performed through the hoist foundation pit fault impact data; otherwise, the hoist foundation pit fault impact data is continuously monitored;

[0007] Step S3: using the built-in monitoring sensor of the bucket to perform bucket loading monitoring processing to generate bucket loading monitoring data, wherein the bucket loading monitoring data includes bucket loading visual data, bucket loading centroid data and bucket loading mass data; performing bucket loading semantic state analysis based on the bucket loading visual data to generate bucket loading semantic state data; performing bucket loading state feedback operation through the bucket loading semantic state data;

[0008] Step S4: obtaining the bucket driving transport control parameters of the hoisting equipment; performing bucket loading mechanical characteristic analysis based on bucket loading center of mass data and bucket loading mass data to generate bucket loading mechanical characteristic data; performing bucket simulated transport swing behavior analysis and processing based on bucket driving transport control parameters, bucket loading mechanical characteristic data and shaft environment spatiotemporal mapping data to generate bucket simulated transport swing behavior data;

[0009] Step S5: performing swing trend distribution analysis and processing of the bucket simulation transportation based on the bucket simulation transportation swing behavior data to generate bucket simulation transportation swing trend distribution data;

[0010] Step S6: Based on the bucket simulation transport swing trend distribution data, the bucket driven transport control parameters are dynamically adjusted to generate dynamic bucket driven transport control parameters, and bucket driven transport collaborative feedback operations and bucket transport dynamic drive control operations are executed through the dynamic bucket driven transport control parameters.

[0011] Furthermore, the vertical shaft environment spatiotemporal mapping data in step S1 includes vertical shaft temperature and humidity mapping data and vertical shaft air pressure mapping data.

[0012] Further, step S1 includes the following steps:

[0013] Step S11: using the monitoring sensor built into the shaft to perform shaft environment monitoring processing on the shaft area to generate shaft environment monitoring data;

[0014] Step S12: using the time-space difference technology to perform environmental time-space mapping processing on the shaft environment monitoring data to generate shaft environment time-space mapping data;

[0015] Step S13: Performing time series characteristic analysis on the shaft temperature and humidity mapping data to generate shaft temperature and humidity time series characteristic data;

[0016] Step S14: performing an environmental impact trend analysis of the elevator base station based on the shaft temperature and humidity time series characteristic data to generate environmental impact trend data of the elevator base station;

[0017] Step S15: Perform an impact assessment process on the hoist foundation pit fault according to the hoist base station environmental impact trend data to generate hoist foundation pit fault impact data.

[0018] Further, step S14 includes the following steps:

[0019] Step S141: Acquire historical shaft temperature and humidity data and historical elevator base station impact data;

[0020] Step S142: performing shaft temperature and humidity perception specificity analysis based on historical shaft temperature and humidity data to generate shaft temperature and humidity perception specificity data;

[0021] Step S143: performing a temperature and humidity perception-specific base station impact factor analysis on the historical elevator base station impact data based on the shaft temperature and humidity perception-specific data to generate a temperature and humidity perception-specific base station impact factor;

[0022] Step S144: using the temperature and humidity sensing specific base station influencing factors to perform an elevator base station environmental impact trend analysis on the shaft temperature and humidity time series characteristic data, and generate elevator base station environmental impact trend data.

[0023] Further, step S3 includes the following steps:

[0024] Step S31: using the monitoring sensor built into the bucket to perform bucket loading monitoring processing to generate bucket loading monitoring data;

[0025] Step S32: performing bucket loading entity object recognition processing on the bucket loading visual data based on a preset convolutional neural network model to generate bucket loading entity object data;

[0026] Step S33: performing a bucket loading entity object distribution spatial analysis based on the bucket loading visual data to generate bucket loading entity object distribution spatial data;

[0027] Step S34: Perform bucket loading semantic state analysis based on bucket loading entity object data and bucket loading entity object distribution space data to generate bucket loading semantic state data; perform bucket loading state feedback operation through bucket loading semantic state data.

[0028] Further, step S4 includes the following steps:

[0029] Step S41: obtaining the bucket driving and transport control parameters of the hoisting equipment;

[0030] Step S42: performing bucket loading mechanical characteristic analysis based on bucket loading centroid data and bucket loading mass data to generate bucket loading mechanical characteristic data;

[0031] Step S43: performing mechanical distribution analysis of the vertical shaft influence according to the vertical shaft air pressure mapping data to generate the vertical shaft influence mechanical distribution data;

[0032] Step S44: using multiple regression analysis to analyze the bucket driving transport control parameters, bucket loading mechanical characteristic data and shaft influence mechanical distribution data for bucket simulated transport mechanical effect, and generating bucket simulated transport mechanical effect data;

[0033] Step S45: performing bucket transport traction swing limit analysis according to bucket drive transport control parameters to generate bucket transport traction swing limit data;

[0034] Step S46: Perform bucket simulation transport swing behavior analysis and processing based on bucket transportation traction swing restriction data and bucket simulation transport mechanical effect data to generate bucket simulation transport swing behavior data.

[0035] Further, step S42 includes the following steps:

[0036] Perform bucket loading gravity center offset characteristic analysis on bucket loading gravity center data to generate bucket loading gravity center offset characteristic data;

[0037] The bucket loading mechanical characteristic analysis is performed based on the bucket loading center of gravity offset characteristic data and the bucket loading mass data to generate the bucket loading mechanical characteristic data.

[0038] Further, step S5 includes the following steps:

[0039] Step S51: performing bucket simulation transportation swing mode analysis according to bucket simulation transportation swing behavior data to generate bucket simulation transportation swing mode data;

[0040] Step S52: performing bucket transport swing frequency analysis on the bucket simulated transport swing behavior data to generate bucket simulated transport swing frequency data;

[0041] Step S53: performing bucket simulation transport swing descriptor analysis according to bucket simulation transport swing mode data and bucket simulation transport swing frequency data to generate bucket simulation transport swing descriptor data;

[0042] Step S54: Designing a distribution mapping relationship between the force influence and the swing trend of the bucket simulation transportation based on the bucket simulation transportation swing descriptor data, and generating a bucket simulation transportation swing trend distribution prediction model;

[0043] Step S55: Transmitting the bucket simulation transport mechanical effect data to the bucket simulation transport swing trend distribution prediction model to perform the bucket simulation transport swing trend distribution prediction processing to generate the bucket simulation transport swing trend distribution data.

[0044] Further, step S54 includes the following steps:

[0045] Step S541: performing a swing superposition state analysis of the transport force influence according to the bucket simulation transport swing descriptor data, and generating transport force image swing superposition state data;

[0046] Step S542: Design a decision leaf node of the force influence and swing trend of bucket simulation transportation by using a preset decision tree algorithm on the transport force image swing superposition state data, and generate bucket simulation transportation swing trend decision leaf node data;

[0047] Step S543: using the bucket transport traction swing restriction data to perform decision condition limiting processing on the bucket transport simulation swing trend decision leaf node data, and generating limited bucket transport simulation swing trend decision leaf node data;

[0048] Step S544: Design a bucket simulation transport swing trend distribution prediction model by limiting the bucket simulation transport swing trend decision leaf node data, and generate a bucket simulation transport swing trend distribution prediction model.

[0049] Further, step S6 includes the following steps:

[0050] Step S61: designing bucket simulation transportation swing trend fuzzy logic factors based on bucket simulation transportation swing trend distribution data;

[0051] Step S62: performing fuzzy logic characteristic analysis and processing of the steady-state control demand of the bucket simulation transportation according to the fuzzy logic factor of the swing trend of the bucket simulation transportation, and generating fuzzy logic characteristic data of the steady-state control demand of the bucket simulation transportation;

[0052] Step S63: Use the fuzzy logic characteristic data of the steady-state control requirements of the bucket simulation transportation to dynamically adjust the bucket driven transportation control parameters, generate dynamic bucket driven transportation control parameters, and execute bucket driven transportation collaborative feedback operations and bucket transportation dynamic drive control operations through the dynamic bucket driven transportation control parameters.

[0053] The beneficial effect of the present application is that, by installing multiple monitoring sensors in the shaft, the shaft environment is monitored in real time, including key parameters such as temperature, humidity, and air pressure, and the shaft environment monitoring data is processed in environmental space-time mapping using space-time difference technology. The space-time difference technology can effectively convert the shaft environment monitoring data into space-time mapping data, revealing the changing trend of the shaft environment at different times and spaces, realizing the prediction of dynamic environmental changes, and providing accurate data support for the scheduling and control of the bucket transportation system. The temporal characteristics of the shaft temperature and humidity mapping data are analyzed for the environmental impact trend of the elevator base station, the time law and change trend of the temperature and humidity data in the shaft are extracted, the long-term impact trend of the shaft environment on the elevator base station is revealed, the potential relationship between environmental changes and equipment failures is identified, equipment damage and downtime caused by environmental factors are reduced, and work efficiency and safety are improved. Through the built-in monitoring sensor of the bucket, the loading status data of the bucket is collected in real time, including the weight inside the bucket, material status and other information. By applying convolutional neural network (CNN) to process bucket loading visual data, it is possible to accurately identify different loading objects and their types in the bucket, identify the position and shape of the objects, realize automatic material recognition, and perform spatial analysis of bucket loading entity object distribution based on bucket loading visual data to fully understand the distribution of each object in the bucket, identify problems such as unstable center of gravity and uneven material stacking, and analyze the loading status of the bucket, such as full load, empty load, etc. Bucket loading semantic state analysis is performed based on bucket loading entity object data and bucket loading entity object distribution spatial data to perform bucket loading state feedback operations, determine whether the bucket is in a safe and appropriate loading state, ensure safety and efficiency during bucket transportation, and avoid accidents caused by loading problems. By obtaining the bucket drive transportation control parameters of the hoist equipment, the operating status and control settings of the hoist are understood, including key data such as the hoist's traction, speed, and carrying capacity. Bucket loading mechanical characteristics analysis is performed based on bucket loading center of mass data and bucket loading mass data to accurately evaluate the loading force state of the bucket during transportation. According to the shaft air pressure mapping data, the mechanical distribution analysis of the shaft influence is carried out. The air pressure changes in the shaft will affect the bucket's transportation path, speed and stability. The impact of air pressure fluctuations on bucket transportation is evaluated, and then the mechanical distribution in the shaft is obtained. Multivariate regression analysis is used in combination with bucket drive transportation control parameters, bucket loading mechanical characteristic data, and shaft influence mechanical distribution data to fully simulate the mechanical effects of the bucket during transportation, identify unstable factors in bucket transportation, and optimize the bucket control strategy to ensure that the bucket can maintain stable operation under various external conditions. Bucket transportation traction swing limit analysis is carried out according to the bucket drive transportation control parameters, and the maximum bucket transportation traction swing limit capacity of the hoist during bucket transportation is reasonably evaluated, so as to more accurately analyze the bucket's swing behavior and the maximum limit of the swing behavior.By analyzing the simulated transport swing behavior and swing frequency of the bucket, the swing mode under different transport conditions is extracted to reflect the regular motion characteristics of the bucket transportation, identify the high-frequency or low-frequency swing problems of the bucket during transportation, optimize the operating parameters of the elevator and the bucket transportation control strategy, and reduce the impact of the swing frequency on transportation efficiency and safety. In addition, the bucket simulation transport swing descriptor analysis is carried out to quantify the core parameters of the bucket swing behavior, and fully understand the amplitude, direction and period of the bucket swing, so as to establish a swing trend prediction model for bucket transportation, predict the swing trend of the bucket during transportation, and provide a scientific basis for adjusting the operating parameters and optimizing the elevator control to avoid potential safety hazards caused by excessive swing. The mechanical effect data of the bucket simulation transport is transmitted to the bucket simulation transport swing trend distribution prediction model for the bucket simulation transport swing trend distribution prediction processing, understand the dynamic changes of the swing trend during the bucket transportation process, ensure the stability of the bucket transportation, and improve the overall operation efficiency and safety, so as to prevent collision, tilt or bucket damage caused by excessive swing, and ensure the safety and stability of the bucket transportation process. The swing trend distribution data of bucket simulation transportation is used to design the swing trend fuzzy logic factor of bucket simulation transportation, which comprehensively reflects the strength and directionality of the swing trend. The fuzzy logic characteristic analysis and processing of the steady-state control demand of bucket simulation transportation is carried out according to the swing trend fuzzy logic factor of bucket simulation transportation. The corresponding steady-state control demand data is dynamically generated for different swing trends, so that the control system has greater flexibility and adaptability in dealing with swing suppression, and the adaptability to complex transportation scenes is improved. It also realizes precise control of bucket swing, effectively ensuring that the bucket remains steady during transportation. The fuzzy logic characteristic data of the steady-state control demand of bucket simulation transportation is used to dynamically adjust the bucket drive transportation control parameters. The dynamic adjustment of the bucket drive transportation control parameters can respond quickly according to the real-time swing trend changes, realize the dynamic optimization of the transportation parameters, and the bucket drive transportation collaborative feedback operation is used to remind the internal personnel in the shaft excavation. Through the dynamic drive control operation, the stability and control accuracy of the system under complex working conditions are improved, thereby ensuring that the bucket is always in a controlled state during transportation, and further improving the safety and efficiency of shaft excavation operations.

[0054] Therefore, the intelligent loading control method of the shaft excavation bucket of the present invention comprehensively utilizes the environmental monitoring data in the shaft, the bucket loading status data and the bucket transportation mechanical characteristic data, and realizes the comprehensive monitoring and dynamic control of the bucket loading status, mechanical behavior during transportation and shaft environmental factors. Through the spatiotemporal mapping and dynamic analysis based on multidimensional data, the impact of the elevator foundation pit failure, the bucket swing trend and the transportation stability can be evaluated in real time. At the same time, by dynamically adjusting the bucket drive transportation control parameters, the safety and efficiency of the bucket transportation process are effectively improved. In addition, the bucket loading status and personnel safety status are detected by the built-in monitoring device of the bucket to perform the bucket loading status feedback operation, and the linkage feedback is realized with the foundation pit water accumulation alarm device and the bucket anti-collision system, which can comprehensively prevent potential risks, thereby solving the problems of single bucket monitoring, insufficient response capability and lack of comprehensive linkage control in the prior art, and significantly improving the intelligence level and safety assurance capability of the shaft excavation operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic flow chart of the steps of an intelligent loading control method for a shaft excavation bucket according to the present invention;

[0056] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0057] Figure 3 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0058] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0059] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0060] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities are implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0061] It should be understood that although the terms "first", "second", etc. are used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, a first element is referred to as a second element, and similarly, a second element is referred to as a first element without departing from the scope of the exemplary embodiments. The term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0062] To achieve this, please refer to Figures 1 to 3 The present invention provides an intelligent loading control method for a shaft excavation bucket. In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of a step flow chart of an intelligent loading control method for a shaft excavation bucket according to the present invention. The intelligent loading control method for a shaft excavation bucket comprises the following steps:

[0063] Step S1: using the monitoring sensors built into the shaft to monitor the shaft environment and perform spatiotemporal mapping of the monitoring data to generate shaft environment spatiotemporal mapping data; performing an impact assessment of the hoist pit fault based on the shaft environment spatiotemporal mapping data to generate hoist pit fault impact data;

[0064] In the embodiment of the present invention, the monitoring sensor built in the shaft is used to monitor the shaft environment in the shaft area. In the key areas of the shaft (such as the shaft wall, the hanging plate, the hoist base station, etc.), a series of environmental monitoring sensors (including temperature and humidity sensors, air pressure sensors, vibration sensors, acceleration sensors, etc.) are deployed to monitor the shaft environment in real time. Each sensor is connected to the central control system through a wireless communication module, and transmits the real-time collected environmental data such as temperature, humidity, air pressure, vibration, etc. to the data center. The system sets the data collection frequency of the sensor to once per second to ensure that environmental changes can be monitored in time. The collected data is processed by the embedded control system, and the data is digitally converted and filtered to output the shaft environment monitoring data in a unified format. In the shaft, the data collected by each monitoring sensor has spatiotemporal characteristics, that is, each sensor not only collects time series data, but also its position will affect the difference of the monitoring data. In order to accurately reflect the environmental changes at different locations and times, the data collected by all sensors are processed by spatiotemporal difference technology. First, by calibrating the geographical location and timestamp of the sensor, the environmental monitoring data in the shaft is converted into a spatiotemporal data set with geographical coordinates and time tags. Then, the spatiotemporal interpolation algorithm (such as inverse distance weighted method or Kriging interpolation method) is used to map the data in time and space, and the data at different locations and time points are interpolated so that the environmental data at each moment and each location can be seamlessly connected, thereby generating the spatiotemporal mapping data of the shaft environment. The time series characteristics of the shaft temperature and humidity mapping data are analyzed. In the shaft, the changes in temperature and humidity are closely related to factors such as hoist operation and bucket operation. The time series characteristics of temperature and humidity are crucial for subsequent environmental impact analysis and control decisions. By analyzing the time series characteristics of the temperature and humidity data in the spatiotemporal mapping data of the shaft environment, the time series data of temperature and humidity are first extracted. Then, the fast Fourier transform (FFT) is used to analyze the periodic changes of temperature and humidity, and the high-frequency and low-frequency characteristics of temperature and humidity changes are identified. In order to further understand the changing laws of temperature and humidity, the autoregressive integrated moving average (ARIMA) model is used to analyze the trend changes of temperature and humidity data to detect whether there are long-term seasonal changes or temporary abnormal fluctuations. Through these analyses, the temperature and humidity time series characteristic data related to the elevator base station and bucket operation are obtained, which provides data support for the analysis of the environmental impact trend of the elevator base station. The environmental impact trend of the elevator base station is analyzed based on the time series characteristic data of the temperature and humidity of the shaft. The temperature and humidity time series data are correlated with the operating data of the elevator base station (such as elevator load, lifting speed, bucket lifting frequency, etc.) to identify the relationship between temperature and humidity changes and the operating status of the elevator. Then, a mathematical model of the environmental impact trend of the elevator base station is established using methods such as regression analysis and support vector machine (SVM). Through this process, the impact trend of temperature and humidity changes on elevator efficiency, bucket stability and operation cycle is clearly observed.According to the environmental impact trend data of the elevator base station, the impact assessment of the elevator pit failure is carried out to identify the key environmental factors that affect the elevator pit failure (such as temperature and humidity fluctuations, air pressure changes, etc.). Secondly, based on the fault tree analysis (FTA) and failure mode effect analysis (FMEA) methods, the risk level of elevator pit failure under different environmental changes is evaluated. For each environmental change, the corresponding failure probability is calculated, and the impact of these failures on the entire shaft hoisting operation is evaluated. Finally, the impact data of the elevator pit failure is generated through simulation analysis.

[0065] Step S2: when the hoist foundation pit fault impact data is greater than the preset hoist foundation pit alarm threshold, the foundation pit alarm feedback operation is performed through the hoist foundation pit fault impact data; otherwise, the hoist foundation pit fault impact data is continuously monitored;

[0066] In the embodiment of the present invention, the data affecting the hoist pit fault is monitored in real time. When the data exceeds the preset alarm threshold, the system will immediately trigger the pit alarm feedback operation. During the implementation process, the data affecting the hoist pit fault will be continuously collected through the real-time monitoring system. These data include but are not limited to the water level, vibration, pressure and other sensor data in the pit. If the monitored data exceeds the set safety threshold, the system will send an alarm signal through the control center, and the control system will be linked to execute corresponding safety processing measures, such as automatically stopping the operation of the hoist, shutting down the pit drainage system or starting the emergency response program. The alarm signal can not only remind the on-site operators in time, but also be transmitted to the management personnel through the remote monitoring platform to ensure that measures are taken in the first time to prevent accidents. If the data affecting the hoist pit fault is lower than the preset threshold, the system will enter the monitoring mode and continuously collect the data affecting the pit fault. These data will be regularly transmitted to the monitoring platform for analysis and archiving. At the same time, when the data is not abnormal, the hoist continues to operate according to the normal working process. During the monitoring period, the system will continuously compare and analyze the data to ensure that the safety status of the pit is within the normal range and automatically update the safety status of the pit. If the monitoring data shows any potential risks, the system will automatically trigger an early warning and return to the alarm feedback process.

[0067] Step S3: using the built-in monitoring sensor of the bucket to perform bucket loading monitoring processing to generate bucket loading monitoring data, wherein the bucket loading monitoring data includes bucket loading visual data, bucket loading centroid data and bucket loading mass data; performing bucket loading semantic state analysis based on the bucket loading visual data to generate bucket loading semantic state data; performing bucket loading state feedback operation through the bucket loading semantic state data;

[0068] In an embodiment of the present invention, the loading condition of the bucket is monitored in real time by a plurality of monitoring sensors (such as weighing sensors, visual sensors, and acceleration sensors) built into the bucket, and bucket loading monitoring data is generated, wherein the bucket loading monitoring data includes bucket loading visual data, bucket loading centroid data, and bucket loading mass data. Based on a preset convolutional neural network (CNN) model, these image data are processed for object recognition. After training, the CNN model can identify different types of materials (such as ore, sand, etc.) in the bucket and their specific shapes and sizes or people. Through image classification and object detection technology, the model can accurately distinguish and calibrate the position, size, and relative distribution of material entities. After processing, bucket loading entity object data is generated, which includes the type, quantity, and distribution information of each material object in the bucket, providing a basis for further loading status analysis. According to the bucket loading visual data and the generated bucket loading entity object data, a distribution space analysis of the bucket loading entity object is performed. By analyzing the spatial position of the material in the bucket, the distribution uniformity and aggregation of the material are evaluated. This process is based on image analysis technology and geometric space analysis methods. By performing three-dimensional modeling and calculation on the spatial position, angle, shape, etc. of each object in the bucket, it is determined whether the material is tilted or piled up. The spatial analysis data is processed by algorithms to digitize the spatial distribution of various objects in the bucket loading space to generate bucket loading entity object distribution spatial data. The bucket loading semantic state analysis is performed by comprehensive analysis of the bucket loading entity object data and bucket loading entity object distribution spatial data. This analysis evaluates the rationality and safety of the current loading state of the bucket based on data such as the type, quantity, distribution and spatial position of the materials in the bucket. Using a rule-based reasoning system or a fuzzy logic reasoning model, according to different loading standards and safety restrictions, the stacking method and loading balance of the materials in the bucket are judged, or whether the bucket is loaded with people and whether the bucket is full or empty, and the bucket loading semantic state data is generated. The bucket loading semantic state data contains key information such as the empty or full state of the bucket loading, the object information of the loaded objects, and whether there are dangerous factors. Based on the generated bucket loading semantic state data, the control system performs the bucket loading state feedback operation. If the loading status does not meet the safety standards, the system will send out a warning signal and start the automatic adjustment operation to adjust the loading distribution of the material or adjust the lifting rate of the bucket to ensure the safety of the bucket operation.

[0069] Step S4: obtaining the bucket driving transport control parameters of the hoisting equipment; performing bucket loading mechanical characteristic analysis based on bucket loading center of mass data and bucket loading mass data to generate bucket loading mechanical characteristic data; performing bucket simulated transport swing behavior analysis and processing based on bucket driving transport control parameters, bucket loading mechanical characteristic data and shaft environment spatiotemporal mapping data to generate bucket simulated transport swing behavior data;

[0070] In an embodiment of the present invention, the working state of the hoist equipment is monitored in real time by the hoist control system to obtain the bucket drive transportation control parameters. These control parameters include key data such as the lifting rate, traction, driving power, braking force and acceleration of the bucket. The mechanical characteristics of the bucket loading are analyzed based on the bucket loading center of mass data and the bucket loading mass data, and the center of mass offset analysis method is used to analyze the offset of the center of mass during the loading process. The specific method includes calculating the change of the center of gravity of the material of the bucket under different load conditions, and comparing it with the ideal center of gravity position. The obtained bucket loading center of gravity offset characteristic data includes the direction, amplitude and its change trend over time. The mechanical characteristics of the bucket loading are analyzed based on the bucket loading center of gravity offset characteristic data and the bucket loading mass data, and the mechanical characteristics of the bucket are simulated and calculated using a mechanical model. Specifically, a mechanical analysis tool (such as finite element analysis or rigid body dynamics model) is used to calculate the mechanical parameters such as force distribution, torque change, and moment of inertia of the bucket under different working conditions according to the bucket loading mass data and center of gravity offset data. At the same time, by establishing an interaction model between the bucket and the hoist, the traction, vibration and stability changes caused by the center of gravity offset of the bucket during the lifting process are analyzed. This process generates bucket loading mechanical characteristic data, including key information such as the acceleration, force state, offset torque and vibration characteristics of the bucket during the lifting process. These data can provide support for the subsequent optimization of the control strategy to ensure that the bucket maintains stable operation during the entire transportation process. The mechanical distribution analysis of the shaft influence is carried out according to the shaft air pressure mapping data. The shaft air pressure data is a real-time monitoring of the air pressure changes in the shaft through the built-in air pressure sensor, reflecting the air pressure distribution in the shaft, and providing the influence of the shaft environment changes on the mechanical effects generated during the bucket transportation process. Numerical analysis methods such as finite element analysis (FEA) or fluid mechanics simulation are used to analyze the influence of shaft air pressure on the buoyancy, air resistance and vibration of the bucket. This process can reveal the interference and influence of shaft air pressure changes on the dynamic performance of the bucket and generate shaft influence mechanical distribution data. The bucket drive transportation control parameters, bucket loading mechanical characteristic data and shaft influence mechanical distribution data are integrated for multivariate regression analysis. The control parameters of bucket-driven transportation include the traction force, speed, lifting angle, etc. of the bucket, while the mechanical characteristic data of bucket loading involves physical characteristics such as the mass of the bucket load, the center of gravity position, and its influence on the movement of the bucket. The mechanical distribution data of shaft influence includes the influence of factors such as temperature, humidity, and air pressure changes in the shaft environment on the mechanical effects of the bucket transportation process. Through the multivariate regression analysis method, these three sets of data are input as independent variables, and the mathematical model of the mechanical effect of bucket simulation transportation is established using the multivariate regression model. At this time, regression analysis is used to quantitatively describe the relative importance of various factors (such as control parameters, loading characteristics, and environmental influences) and their influence on the mechanical effects during bucket transportation.Specifically, the bucket driving transport control parameters and the mass characteristics of the bucket loading will affect the mechanical response of the bucket. For example, excessive traction causes the bucket to swing violently, while a bucket loading with a larger mass causes a greater inertial force. Shaft environmental factors (such as air pressure changes) cause the bucket's motion trajectory in the shaft to change, thereby affecting the mechanical effect. Generate bucket simulation transportation mechanical effect data, which contains the mechanical response results of the bucket under different control parameters, load characteristics and shaft environmental conditions. These mechanical effect data provide data support for subsequent transportation control strategies, optimize the bucket's transportation trajectory, control parameter settings and mechanical response, and ensure that the bucket maintains a stable and safe operating state under different working conditions. According to the bucket's driving transportation control parameters, including bucket traction, speed, lifting angle, etc., the bucket transportation traction swing limit analysis is carried out. The core purpose of the analysis is to control the maximum swing limit of the bucket during transportation, and collect the bucket's operating data under different transportation parameters, including the size of the traction force, the bucket's speed, the angle change during the lifting process, etc., which all affect the bucket's motion state. Then, by establishing the motion equation and mechanical model, the swing amplitude generated under different parameter combinations is evaluated. The dynamic simulation model is used to simulate the swing of the bucket during transportation. By setting the limits of traction, speed and angle, the swing amplitude and speed under different conditions are analyzed, the maximum swing range of the bucket during transportation is determined, and effective limiting measures for traction swing are proposed. These limiting measures will be optimized and adjusted according to the physical model and simulation results. Based on the traction swing limit data of the bucket transportation and the mechanical effect data of the bucket simulation transportation, the swing behavior of the bucket simulation transportation is analyzed. Using the mechanical effect data of the bucket simulation transportation, the dynamic response of the bucket during transportation is analyzed, including the influence of load changes, control parameter changes and shaft environmental factors on the bucket swing. Combined with the traction swing limit data of the bucket transportation, further simulation and simulation analysis are carried out. At this time, the swing limit data will be used as an input constraint to limit the excessive swing of the bucket during the simulation process and ensure that the bucket maintains stable operation during transportation. Through simulation analysis, the swing frequency, amplitude and trajectory data of the bucket under different transportation conditions are obtained, and the swing behavior data of the bucket simulation transportation is generated.

[0071] Step S5: performing swing trend distribution analysis and processing of the bucket simulation transportation based on the bucket simulation transportation swing behavior data to generate bucket simulation transportation swing trend distribution data;

[0072] In an embodiment of the present invention, the swing characteristics of the bucket generated during the lifting process are extracted from the bucket simulation transportation swing behavior data. By analyzing these data, the swing behavior of the bucket is classified and pattern recognized using a pattern recognition algorithm, and bucket simulation transportation swing mode data is generated, including different swing mode types and their corresponding occurrence conditions. These data provide a basis for subsequent dynamic stability analysis and help understand the swing characteristics of the bucket under different conditions. The frequency domain analysis of the bucket simulation transportation swing behavior data is performed using Fourier transform or wavelet transform. First, the acceleration and displacement data of the bucket are collected in real time using a high-speed data acquisition module, and Fourier transform is performed in combination with the bucket swing data, and converted to the frequency domain to obtain the vibration amplitude of the bucket at different frequencies, forming the bucket simulation transportation swing frequency data. Based on the bucket simulation transportation swing mode data and the bucket simulation transportation swing frequency data, the bucket simulation transportation swing descriptor analysis is performed. The descriptor analysis uses a method combining statistical analysis and physical model to quantitatively describe the swing behavior of the bucket. By mapping different swing modes with their frequency characteristics, a multidimensional descriptor model is constructed, which includes the amplitude, frequency, energy distribution and phase of the swing. Multivariate regression analysis and principal component analysis are used to further optimize the analysis process, extract the key features that can describe the motion state of the bucket, and generate the bucket simulation transportation swing descriptor data. The bucket simulation transportation swing descriptor data is used to design the distribution mapping relationship between force influence and swing trend. First, based on the mechanical model and the bucket loading data, the mechanical effects under different working conditions during bucket transportation are analyzed. Finite element analysis or multibody dynamics model is used to simulate the mechanical effects on the bucket during the lifting process, including the swing of the bucket and the influence of the external environment (such as shaft temperature, humidity, wind speed, etc.) on its stability. Then, combined with the swing descriptor data, the mapping relationship between the force influence and the swing trend of the bucket is constructed. Through machine learning algorithms, such as decision tree algorithms, a mapping model is trained to convert the swing descriptor data into the swing trend prediction results of the bucket. The generated bucket simulation transportation swing trend distribution prediction model can predict the swing trend of the bucket under different conditions and provide real-time feedback to the control system to adjust the lifting process of the bucket. The mechanical effect data of bucket simulated transportation is transmitted to the bucket simulated transportation swing trend distribution prediction model. The model predicts the swing trend of the bucket in the future and the corresponding transportation position by analyzing the mechanical effect data, and outputs the bucket simulated transportation swing trend distribution data. The real-time data input model of the bucket is used, combined with historical data and force influence analysis, to predict the swing range, frequency change and force state of the bucket. The generated bucket simulated transportation swing trend distribution data provides a prediction of the dynamic behavior of the bucket in the future transportation process, providing a basis for subsequent control decisions.

[0073] Step S6: Based on the bucket simulation transport swing trend distribution data, the bucket driven transport control parameters are dynamically adjusted to generate dynamic bucket driven transport control parameters, and bucket driven transport collaborative feedback operations and bucket transport dynamic drive control operations are executed through the dynamic bucket driven transport control parameters.

[0074] In an embodiment of the present invention, the bucket simulated transport swing trend distribution data is analyzed to extract relevant fuzzy logic factors. The goal of this process is to extract key fuzzy factors that affect the bucket swing behavior from the transport swing trend distribution data, which factors generally include the bucket's movement speed, swing amplitude, load characteristics, and air pressure changes in the shaft environment. By using fuzzy mathematics methods, different fuzzy sets are set to describe these factors, such as low swing, medium swing, and high swing. In this process, the bucket simulated transport swing trend distribution data is first quantified and converted into numerical fuzzy factors. These factors are mapped by fuzzy logic rules. According to the bucket simulated transport swing trend fuzzy logic factors, the fuzzy logic characteristics of the bucket's simulated transport steady-state control requirements are analyzed. First, according to the bucket's working environment and actual stress conditions, the fuzzy control algorithm is used to analyze the stability requirements under different working conditions during the simulated transportation process. At this time, the analysis mainly focuses on controlling the bucket's swing and improving its stability. Factors considered in the analysis include the swing of the bucket under different load conditions, the impact of temperature and humidity changes in the shaft environment on the transportation trajectory, and the dynamic response characteristics of the bucket at different speeds. Through the fuzzy inference system, combined with the pre-designed fuzzy rules (for example, if the swing amplitude is large, a higher stability control is required), reasoning and calculation are performed, and finally the fuzzy logic characteristic data of the bucket simulation transportation steady-state control requirements are generated. These characteristic data will reflect the stability requirements of the bucket in various states, and the generated fuzzy logic characteristic data provide a practical basis for the control strategy. The bucket drive transportation control parameters are dynamically adjusted according to the fuzzy logic characteristic data of the bucket simulation transportation steady-state control requirements. Since the bucket drive transportation control parameters are variable parameters, the bucket drive transportation control parameters can be used to dynamically control the force of the bucket to minimize the swing of the bucket. First, the bucket drive control parameters (such as traction, speed, lifting angle, etc.) are adjusted dynamically in real time through the output of the fuzzy control system. Through the fuzzy logic inference algorithm, the previously generated fuzzy logic characteristic data are input into the control system and adjusted in real time according to the pre-set fuzzy control rules. Specifically, if the system determines that the swing amplitude of the bucket exceeds the predetermined safety range, the swing amplitude is reduced by dynamically adjusting the control parameters such as traction and lifting speed to maintain the stable state of transportation. At the same time, the dynamically adjusted control parameters will be fed back through the bucket's drive control system to start the coordinated control operation of the bucket transportation. For example, if the traction force is set too high, the system will automatically adjust to a reasonable range, and when the bucket is executed, an audible and visual alarm signal will be issued through the bucket drive transportation coordinated feedback operation. The alarm equipment worn by the personnel will simultaneously issue a warning signal to remind the workers at the bottom of the well to avoid the falling bucket. In addition, the dynamic adjustment process will be combined with the real-time operation data feedback of the bucket for continuous adjustment to ensure that every link in the transportation process is in the best stable state.

[0075] Furthermore, the vertical shaft environment spatiotemporal mapping data in step S1 includes vertical shaft temperature and humidity mapping data and vertical shaft air pressure mapping data.

[0076] Further, step S1 includes the following steps:

[0077] Step S11: using the monitoring sensor built into the shaft to perform shaft environment monitoring processing on the shaft area to generate shaft environment monitoring data;

[0078] In an embodiment of the present invention, a series of environmental monitoring sensors (including temperature and humidity sensors, air pressure sensors, vibration sensors, acceleration sensors, etc.) are deployed in key areas of the shaft (such as shaft walls, hanging plates, hoist base stations, etc.) to monitor the shaft environment in real time. Each sensor is connected to the central control system through a wireless communication module, and transmits real-time collected environmental data such as temperature, humidity, air pressure, vibration, etc. to the data center. The system sets the data collection frequency of the sensor to once per second to ensure that environmental changes can be monitored in a timely manner. The collected data is processed by an embedded control system, and the data is digitally converted and filtered to output shaft environment monitoring data in a unified format. These data are used for subsequent environmental spatiotemporal mapping and trend analysis to provide accurate basic environmental information for subsequent steps.

[0079] Step S12: using the time-space difference technology to perform environmental time-space mapping processing on the shaft environment monitoring data to generate shaft environment time-space mapping data;

[0080] In an embodiment of the present invention, in the shaft, the data collected by each monitoring sensor has a spatiotemporal characteristic, that is, each sensor not only collects time series data, but also its position will affect the difference of the monitoring data. In order to accurately reflect the environmental changes at different locations and times, the data collected by all sensors are processed by spatiotemporal difference technology. First, by calibrating the geographic location and timestamp of the sensor, the environmental monitoring data in the shaft is converted into a spatiotemporal data set with geographic coordinates and time tags. Then, the data is spatiotemporally mapped using a spatiotemporal interpolation algorithm (such as the inverse distance weighted method or the Kriging interpolation method), and the data at different locations and time points are interpolated and calculated, so that the environmental data at each moment and each location can be seamlessly connected, thereby generating the shaft environment spatiotemporal mapping data. This process can effectively eliminate the problem of missing data collected at different locations and achieve full coverage of the shaft environment data.

[0081] Step S13: Performing time series characteristic analysis on the shaft temperature and humidity mapping data to generate shaft temperature and humidity time series characteristic data;

[0082] In the embodiment of the present invention, in the shaft, the temperature and humidity changes are closely related to factors such as the operation of the hoist and the operation of the bucket, and the time series characteristics of the temperature and humidity are crucial for the subsequent environmental impact analysis and control decisions. By performing a time series feature analysis on the temperature and humidity data in the time-space mapping data of the shaft environment, the time series data of the temperature and humidity are first extracted. Then, the fast Fourier transform (FFT) is used to analyze the periodic changes of temperature and humidity, and the high-frequency and low-frequency characteristics of the temperature and humidity changes are identified. In order to further understand the changing laws of temperature and humidity, the autoregressive integrated moving average (ARIMA) model is used to analyze the trend changes of temperature and humidity data to detect whether there are long-term seasonal changes or temporary abnormal fluctuations. Through these analyses, the time series characteristic data of temperature and humidity related to the hoist base station and the bucket operation are obtained, thereby providing data support for the environmental impact trend analysis of the hoist base station.

[0083] Step S14: performing an environmental impact trend analysis of the elevator base station based on the shaft temperature and humidity time series characteristic data to generate environmental impact trend data of the elevator base station;

[0084] In an embodiment of the present invention, based on the time series characteristic data of the temperature and humidity of the shaft, a time series analysis model is used to analyze the environmental impact trend of the elevator base station. First, the temperature and humidity time series data are correlated with the operating data of the elevator base station (such as elevator load, lifting speed, bucket lifting frequency, etc.) to identify the relationship between temperature and humidity changes and the operating status of the elevator. Then, a mathematical model of the environmental impact trend of the elevator base station is established using methods such as regression analysis and support vector machine (SVM). Through this process, the impact trend of temperature and humidity changes on the efficiency of the elevator, the stability of the bucket and the operation cycle can be clearly observed. If it is found in the analysis that the temperature and humidity changes have a trend of having a significant impact on the operation of the elevator, the system will automatically generate corresponding trend reports and warnings to help decision makers adjust the operation plan in time to avoid the potential impact of abnormal temperature and humidity on the elevator base station.

[0085] Step S15: Perform an impact assessment process on the hoist foundation pit fault according to the hoist base station environmental impact trend data to generate hoist foundation pit fault impact data.

[0086] In an embodiment of the present invention, sufficient environmental data is obtained through temperature and humidity time series feature analysis and hoist base station environmental impact trend analysis. On this basis, these data are used to evaluate the potential failure impact of the hoist pit. First, the key environmental factors that affect the hoist pit failure (such as temperature and humidity fluctuations, air pressure changes, etc.) are identified based on the hoist base station environmental impact trend data and historical failure data. Secondly, based on the fault tree analysis (FTA) and failure mode effects analysis (FMEA) methods, the risk level of the hoist pit failure under different environmental changes is evaluated. For each environmental change, the corresponding failure probability is calculated, and the impact of these failures on the entire shaft hoisting operation is evaluated. Finally, the hoist pit failure impact data is generated through simulation analysis. This data can be used to formulate safer operating strategies and reduce the risk of failures.

[0087] Further, step S14 includes the following steps:

[0088] Step S141: Acquire historical shaft temperature and humidity data and historical elevator base station impact data;

[0089] In an embodiment of the present invention, the temperature and humidity data of the shaft are collected and stored in real time through the temperature and humidity sensors and other environmental monitoring equipment built into the shaft. Historical shaft temperature and humidity data refers to the continuous record of the temperature and humidity of the shaft over a period of time in the past (such as the past 3 months, half a year, etc.), including temperature, humidity and other data. The data will be transmitted to the central data management system via wireless transmission, and each piece of data will be accompanied by a timestamp and sensor identification to ensure the accuracy and traceability of the data. In addition, the elevator base station impact data is derived from historical operation records, including the load, lifting speed, bucket lifting frequency, etc. of the elevator. The data is provided by the on-site elevator control system, updated regularly and saved to the database. The historical elevator base station impact data records the operating performance of the elevator under different environmental conditions, such as whether the elevator load increases and whether the operating stability decreases when the temperature and humidity change greatly. These data will provide a basis for subsequent environmental impact analysis.

[0090] Step S142: performing shaft temperature and humidity perception specificity analysis based on historical shaft temperature and humidity data to generate shaft temperature and humidity perception specificity data;

[0091] In an embodiment of the present invention, a temperature and humidity perception-specific analysis is performed based on historical shaft temperature and humidity data, with the aim of identifying the temperature and humidity variation patterns that are closely related to the operation of the elevator base station by deeply mining the patterns in the data. First, the shaft temperature and humidity data are analyzed for seasonality, periodicity, and trend using a time series analysis method. The periodic fluctuations in the data are identified, and the sliding average method is applied to smooth the data to remove short-term fluctuations. Then, the data is divided into different climate intervals through a clustering algorithm (such as K-means clustering), the temperature and humidity fluctuation range is calibrated, and the temperature and humidity variation characteristics under each climate interval are analyzed to identify the environmental change characteristics related to the elevator base station. These characteristics include the amplitude, frequency, and duration of temperature and humidity fluctuations. These analysis results will form shaft temperature and humidity perception-specific data for subsequent analysis of the environmental impact of the elevator base station.

[0092] Step S143: performing a temperature and humidity perception-specific base station impact factor analysis on the historical elevator base station impact data based on the shaft temperature and humidity perception-specific data to generate a temperature and humidity perception-specific base station impact factor;

[0093] In the embodiment of the present invention, the influence factor analysis of the base station is carried out by combining the specific data of the vertical shaft temperature and humidity perception with the historical elevator base station influence data. First, the operation data of the historical elevator base station is subjected to regression analysis for the key features in the specific data of the vertical shaft temperature and humidity perception (such as the temperature fluctuation amplitude, the humidity change frequency, etc.), and the temperature and humidity factors are closely related to the operation performance of the elevator are identified. At this time, a multivariate linear regression model is adopted, and the various change parameters of temperature and humidity are used as independent variables, and the operation data of the elevator (such as load, speed, stability, etc.) are used as dependent variables to calculate the influence weights of different environmental factors on the elevator base station. In this process, the historical data needs to be standardized to eliminate the influence of different dimensions on the regression model. At the same time, the principal component analysis (PCA) method is used to reduce the data dimension and extract the main influencing factors of temperature and humidity on the operation of the elevator. These influencing factors reflect the direct impact of temperature and humidity changes on the operation of the elevator base station, and provide specific base station influencing factor data for subsequent analysis.

[0094] Step S144: using the temperature and humidity sensing specific base station influencing factors to perform an elevator base station environmental impact trend analysis on the shaft temperature and humidity time series characteristic data, and generate elevator base station environmental impact trend data.

[0095] In an embodiment of the present invention, based on the temperature and humidity perception-specific base station influencing factor, combined with the shaft temperature and humidity time series characteristic data, the environmental impact trend analysis of the elevator base station is performed. First, the temperature and humidity perception-specific base station influencing factor and the temperature and humidity time series characteristic data are used to establish the relationship between the elevator base station and the environmental factors through a regression model. Specifically, a time series prediction model, such as a long short-term memory (LSTM) network, is constructed to analyze the trend of the impact of temperature and humidity changes on the elevator base station. The LSTM model can capture the long-term dependence and seasonal changes in the temperature and humidity data, and predict the environmental impact trend of the elevator base station in the future. In addition, a dynamic system analysis method (such as a Kalman filter) is used to optimize the prediction results of the model to make the trend prediction more accurate. During the training process of the model, historical data is used for verification and tuning to improve the accuracy of the prediction. Through this process, the system can generate the environmental impact trend data of the elevator base station, and provide the potential impact trend of temperature and humidity changes on the elevator base station in the future, thereby helping relevant operators to make timely adjustments in actual operations.

[0096] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S3 in the embodiment, step S3 includes the following steps:

[0097] Step S31: using the monitoring sensor built into the bucket to perform bucket loading monitoring processing to generate bucket loading monitoring data;

[0098] In an embodiment of the present invention, the loading condition of the bucket is monitored in real time through a variety of monitoring sensors (such as weighing sensors, visual sensors, and acceleration sensors) built into the bucket. The weighing sensor is used to measure the weight of the material inside the bucket, and the ultrasonic sensor is used to detect the height of the material in the bucket to ensure accurate grasp of the type and quantity of materials loaded in the bucket. At the same time, the acceleration sensor is used to monitor the stability and dynamic changes of the bucket during the lifting process. The data of all sensors are collected through the sensor interface module and transmitted to the central control system for preliminary processing and analysis. These monitoring data will be summarized and converted into digital information, and finally generate bucket loading monitoring data (such as weight, material height, loading balance, etc.), providing key data support for subsequent operations.

[0099] Step S32: performing bucket loading entity object recognition processing on the bucket loading visual data based on a preset convolutional neural network model to generate bucket loading entity object data;

[0100] In an embodiment of the present invention, the bucket is loaded with visual data to perform entity object recognition processing of the material in the bucket. A high-resolution visual sensor (such as a camera) is installed inside the bucket to capture visual image data of the material in the bucket. Based on a preset convolutional neural network (CNN) model, these image data are processed for object recognition. After training, the CNN model can recognize different types of materials (such as ore, sand, etc.) in the bucket and their specific shapes and sizes or people. Through image classification and object detection technology, the model can accurately distinguish and calibrate the position, size and relative distribution of material entities. After processing, the bucket loading entity object data is generated, which contains the type, quantity and distribution information of each material object in the bucket, providing a basis for further loading status analysis.

[0101] Step S33: performing a bucket loading entity object distribution spatial analysis based on the bucket loading visual data to generate bucket loading entity object distribution spatial data;

[0102] In an embodiment of the present invention, a distribution space analysis of bucket loading entity objects is performed based on bucket loading visual data and generated bucket loading entity object data. By analyzing the spatial position of the material in the bucket, the distribution uniformity and aggregation of the material are evaluated. This process is based on image analysis technology and geometric space analysis methods. By performing three-dimensional modeling and calculation on the position, angle, shape, etc. of each object in the bucket in space, it is determined whether the material has tilt or accumulation. The spatial analysis data is processed by an algorithm to digitize the spatial distribution of various objects in the bucket loading space to generate bucket loading entity object distribution space data. These data can provide comprehensive reference information for subsequent loading semantic state analysis and control strategies to ensure that the material distribution of the bucket meets safety standards.

[0103] Step S34: Perform bucket loading semantic state analysis based on bucket loading entity object data and bucket loading entity object distribution space data to generate bucket loading semantic state data; perform bucket loading state feedback operation through bucket loading semantic state data.

[0104] In the embodiment of the present invention, bucket loading semantic state analysis is performed by comprehensive analysis of bucket loading entity object data and bucket loading entity object distribution spatial data. The analysis is based on data such as the type, quantity, distribution and spatial position of the material in the bucket to evaluate the rationality and safety of the current loading state of the bucket. A rule-based reasoning system or a fuzzy logic reasoning model is used to judge the stacking mode and loading balance of the materials in the bucket according to different loading standards and safety restrictions, or whether the bucket is loaded with people and the full or empty state of the bucket loading, and generate bucket loading semantic state data. The bucket loading semantic state data contains key information such as the empty or full state of the bucket loading, the object information of the loaded object, and whether there are dangerous factors. Based on the generated bucket loading semantic state data, the control system performs the bucket loading state feedback operation. If the loading state does not meet the safety standard, the system will issue a warning signal and start the automatic adjustment operation to adjust the loading distribution of the material or adjust the lifting rate of the bucket to ensure the safety of the bucket operation.

[0105] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S4 in FIG. 1 , in this embodiment, step S4 includes the following steps:

[0106] Step S41: obtaining the bucket driving and transport control parameters of the hoisting equipment;

[0107] In an embodiment of the present invention, the working state of the hoist equipment is monitored in real time by the hoist control system to obtain the bucket drive transportation control parameters. These control parameters include key data such as the bucket's lifting rate, traction, driving power, braking force, and acceleration. These data come from the sensors and control units of the hoist, such as the motor drive module, accelerometer, force sensor, and load sensor. These sensors continuously collect data during the operation of the equipment and feed it back to the central control system through the data transmission system. During the data acquisition process, all relevant control parameters are recorded and stored in real time to provide detailed system performance data for subsequent analysis. Finally, the generated bucket drive transportation control parameters include numerical data such as the bucket's speed and traction, which serve as the basis for control decisions.

[0108] Step S42: performing bucket loading mechanical characteristic analysis based on bucket loading centroid data and bucket loading mass data to generate bucket loading mechanical characteristic data;

[0109] In an embodiment of the present invention, a center of mass shift analysis method is used to analyze the center of mass shift during loading. The specific method includes calculating the change in the center of gravity of the material in the bucket under different load conditions, and comparing it with the ideal center of gravity position. The obtained bucket loading center of gravity shift characteristic data includes the direction, amplitude and its change trend over time. The bucket loading mechanical characteristics analysis is performed based on the bucket loading center of gravity shift characteristic data and the bucket loading mass data, and the mechanical characteristics of the bucket are simulated and calculated using a mechanical model. Specifically, a mechanical analysis tool (such as finite element analysis or rigid body dynamics model) is used to calculate the mechanical parameters such as force distribution, torque change, and moment of inertia of the bucket under different working conditions according to the bucket loading mass data and center of gravity shift data. At the same time, by establishing an interaction model between the bucket and the hoist, the traction, vibration and stability changes caused by the center of gravity shift of the bucket during the lifting process are analyzed. The process generates bucket loading mechanical characteristic data, including key information such as acceleration, force state, offset torque and vibration characteristics of the bucket during the lifting process. These data can provide support for subsequent control strategy optimization to ensure that the bucket maintains stable operation throughout the transportation process.

[0110] Step S43: performing mechanical distribution analysis of the vertical shaft influence according to the vertical shaft air pressure mapping data to generate the vertical shaft influence mechanical distribution data;

[0111] In the embodiment of the present invention, the shaft air pressure data is obtained by monitoring the air pressure changes in the shaft in real time through the built-in air pressure sensor, reflecting the air pressure distribution in the shaft, providing the influence of the shaft environment changes on the mechanical effects generated during the bucket transportation process, and using numerical analysis methods, such as finite element analysis (FEA) or fluid mechanics simulation, to analyze the influence of the shaft air pressure on the buoyancy, air resistance and vibration of the bucket. This process can reveal the interference and influence of the shaft air pressure changes on the dynamic performance of the bucket, and generate shaft influence mechanical distribution data. These data include the mechanical interference effect of the shaft on the bucket transportation process under different air pressure conditions, which further helps to optimize the operation control during the bucket transportation process.

[0112] Step S44: using multiple regression analysis to analyze the bucket driving transport control parameters, bucket loading mechanical characteristic data and shaft influence mechanical distribution data for bucket simulated transport mechanical effect, and generating bucket simulated transport mechanical effect data;

[0113] In the embodiment of the present invention, the bucket driving transportation control parameters, bucket loading mechanical characteristic data and shaft influence mechanical distribution data are integrated for multiple regression analysis. The bucket driving transportation control parameters include the traction force, speed, lifting angle, etc. of the bucket, while the bucket loading mechanical characteristic data involve the physical characteristics such as the mass of the bucket load, the center of gravity position and its influence on the movement of the bucket. The shaft influence mechanical distribution data includes the influence of factors such as temperature, humidity and air pressure changes in the shaft environment on the mechanical effects of the bucket transportation process. Through the multiple regression analysis method, these three sets of data are input as independent variables, and a mathematical model of the bucket simulation transportation mechanical effect is established using the multiple regression model. At this time, the relative importance of each factor (such as control parameters, loading characteristics and environmental influences) and their influence on the mechanical effect during the bucket transportation process are quantitatively described by regression analysis. Specifically, the bucket driving transportation control parameters and the mass characteristics of the bucket loading will affect the mechanical response of the bucket, such as excessive traction causing the bucket to swing violently, while the bucket loading with a larger mass will cause a greater inertial force. Environmental factors in the shaft (such as changes in air pressure) cause the bucket's motion trajectory to change in the shaft, thus affecting the mechanical effect. Generate bucket simulation transportation mechanical effect data, which contains the mechanical response results of the bucket under different control parameters, load characteristics and shaft environmental conditions. These mechanical effect data provide data support for subsequent transportation control strategies, optimize the bucket's transportation trajectory, control parameter settings and mechanical response, and ensure that the bucket maintains a stable and safe operation state under different working conditions.

[0114] Step S45: performing bucket transport traction swing limit analysis according to bucket drive transport control parameters to generate bucket transport traction swing limit data;

[0115] In the embodiment of the present invention, according to the driving and transport control parameters of the bucket, including the bucket traction force, speed, lifting angle, etc., the bucket transportation traction swing limit analysis is performed. The core purpose of the analysis is to control the maximum swing limit of the bucket during transportation, and collect the operation data of the bucket under different transportation parameters, including the size of the traction force, the speed of the bucket, the angle change during the lifting process, etc., which all affect the motion state of the bucket. Then, by establishing the motion equation and the mechanical model, the swing amplitude generated under different parameter combinations is evaluated. On this basis, the swing of the bucket during transportation is simulated using a dynamic simulation model. By setting the limits of traction force, speed and angle, the swing amplitude and speed under different conditions are analyzed, the maximum swing range of the bucket during transportation is determined, and effective limiting measures for traction swing are proposed. These limiting measures will be optimized and adjusted according to the physical model and simulation results. The bucket transportation traction swing limit data finally generated provides key data support for subsequent transportation control, ensuring that the bucket can effectively control the swing during transportation, maintain the stability of the bucket, and avoid excessive mechanical shock.

[0116] Step S46: Perform bucket simulation transport swing behavior analysis and processing based on bucket transportation traction swing restriction data and bucket simulation transport mechanical effect data to generate bucket simulation transport swing behavior data.

[0117] In an embodiment of the present invention, based on the bucket transportation traction swing restriction data and the bucket simulation transportation mechanical effect data, the bucket simulation transportation swing behavior analysis is performed. Using the bucket simulation transportation mechanical effect data, the dynamic response of the bucket during transportation is analyzed, including the influence of load changes, control parameter changes and shaft environmental factors on the bucket swing. By carefully analyzing these data, the swing behavior pattern of the bucket under different control parameters and environmental conditions is obtained. Next, combined with the bucket transportation traction swing restriction data, further simulation and simulation analysis is performed. At this time, the swing restriction data will be used as an input constraint to limit the excessive swing of the bucket during the simulation process, ensuring that the bucket maintains stable operation during transportation. Through simulation analysis, the swing frequency, amplitude and trajectory data of the bucket under different transportation conditions are obtained. Finally, the generated bucket simulation transportation swing behavior data provides detailed analysis results, which helps to further adjust the transportation parameters of the bucket, optimize the swing control during transportation, and ensure that the bucket can be transported smoothly and safely in the shaft environment.

[0118] Further, step S42 includes the following steps:

[0119] Perform bucket loading gravity center offset characteristic analysis on bucket loading gravity center data to generate bucket loading gravity center offset characteristic data;

[0120] The bucket loading mechanical characteristic analysis is performed based on the bucket loading center of gravity offset characteristic data and the bucket loading mass data to generate the bucket loading mechanical characteristic data.

[0121] In an embodiment of the present invention, the bucket loading center of mass data is obtained through sensors built into the bucket (such as weight sensors and accelerometers). The center of mass data reflects the center position of the material distribution in the bucket. In order to ensure accurate calculation of the dynamic stability of the bucket, a center of mass offset analysis method is used to analyze the offset of the center of mass during loading. It includes calculating the change in the center of gravity of the material in the bucket under different load conditions and comparing it with the ideal center of gravity position. The distribution of the material in the bucket is modeled using a spatial coordinate system model, and the dynamic offset characteristics of the bucket loading material are obtained through the mass matrix and the center of mass calculation formula. The bucket loading center of mass offset characteristic data obtained by the analysis result includes the direction, amplitude and its change trend over time. These data are helpful to identify the risks of uneven loading or material dislocation, and to provide early warning of stability problems caused. Based on the obtained bucket loading center of mass offset characteristic data and bucket loading mass data, the bucket loading mechanical characteristics analysis is performed. The analysis process combines the mass distribution of the material in the bucket, the center of gravity offset and the dynamic behavior of the bucket during transportation, and uses a classical mechanical model to simulate and calculate the mechanical characteristics of the bucket. Specifically, mechanical analysis tools (such as finite element analysis or rigid body dynamics model) are used to calculate the mechanical parameters of the bucket under different working conditions, such as force distribution, torque change, and moment of inertia, based on the bucket's loading mass data and center of gravity offset data. At the same time, by establishing an interaction model between the bucket and the hoist, the traction, vibration, and stability changes caused by the center of gravity offset of the bucket during the lifting process are analyzed. This process generates bucket loading mechanical characteristic data, including key information such as the acceleration, force state, offset torque, and vibration characteristics of the bucket during the lifting process. These data can provide support for subsequent control strategy optimization to ensure that the bucket maintains stable operation throughout the transportation process.

[0122] Further, step S5 includes the following steps:

[0123] Step S51: performing bucket simulation transportation swing mode analysis according to bucket simulation transportation swing behavior data to generate bucket simulation transportation swing mode data;

[0124] In an embodiment of the present invention, the swing characteristics of the bucket generated during the lifting process are extracted from the bucket simulation transportation swing behavior data. By analyzing these data, the swing behavior of the bucket is classified and pattern recognized using a pattern recognition algorithm. Specifically, the swing data of the bucket is segmented using a time series analysis method (such as an autoregressive model or a sliding window analysis) to extract key features such as the swing frequency, amplitude, and phase. Clustering algorithms (such as K-means or DBSCAN) are used to classify different types of swing modes and identify common swing modes of the bucket under different working conditions. Through pattern recognition, bucket simulation transportation swing mode data are generated, including different types of swing modes and their corresponding occurrence conditions. These data provide a basis for subsequent dynamic stability analysis and help understand the swing characteristics of the bucket under different conditions.

[0125] Step S52: performing bucket transport swing frequency analysis on the bucket simulated transport swing behavior data to generate bucket simulated transport swing frequency data;

[0126] In an embodiment of the present invention, Fourier transform or wavelet transform is used to perform frequency domain analysis on the bucket simulation transportation swing behavior data. First, the acceleration and displacement data of the bucket are collected in real time using a high-speed data acquisition module, and Fourier transform is performed in combination with the bucket's swing data, and converted to the frequency domain to obtain the vibration amplitude of the bucket at different frequencies. Through frequency analysis, the main frequency vibration frequency of the bucket under different working conditions is extracted. The frequency distribution of the bucket's swing is further analyzed by wavelet transform in order to capture more complex and nonlinear frequency changes. These frequency data are integrated to form bucket simulation transportation swing frequency data. The data contains the main vibration frequencies of the bucket in different time periods and their changing trends, providing a basis for subsequent dynamic control and stability optimization.

[0127] Step S53: performing bucket simulation transport swing descriptor analysis according to bucket simulation transport swing mode data and bucket simulation transport swing frequency data to generate bucket simulation transport swing descriptor data;

[0128] In an embodiment of the present invention, a bucket simulation transportation swing descriptor analysis is performed based on the bucket simulation transportation swing mode data and the bucket simulation transportation swing frequency data. The descriptor analysis uses a method that combines statistical analysis and physical models to quantitatively describe the swing behavior of the bucket. By mapping different swing modes with their frequency characteristics, a multidimensional descriptor model is constructed, which includes characteristics such as the amplitude, frequency, energy distribution and phase of the swing. Multiple regression analysis and principal component analysis are used to further optimize the analysis process and extract key features that can describe the motion state of the bucket. Bucket simulation transportation swing descriptor data are generated, which include the characteristic values ​​of various swing modes and their performance during transportation. These descriptor data provide detailed dynamic information for the formulation of control strategies and help predict the future swing behavior of the bucket.

[0129] Step S54: Designing a distribution mapping relationship between the force influence and the swing trend of the bucket simulation transportation based on the bucket simulation transportation swing descriptor data, and generating a bucket simulation transportation swing trend distribution prediction model;

[0130] In an embodiment of the present invention, the distribution mapping relationship between the force influence and the swing trend is designed using the bucket simulation transportation swing descriptor data. First, based on the mechanical model and the bucket loading data, the mechanical effects under different working conditions during the bucket transportation process are analyzed. Finite element analysis or multi-body dynamics model is used to simulate the mechanical effects on the bucket during the lifting process, including the swing of the bucket and the influence of the external environment (such as shaft temperature and humidity, wind speed, etc.) on its stability. Then, combined with the swing descriptor data, a mapping relationship between the force influence and the swing trend of the bucket is constructed. Through a machine learning algorithm, such as a decision tree algorithm, a mapping model is trained to convert the swing descriptor data into a swing trend prediction result of the bucket. The generated bucket simulation transportation swing trend distribution prediction model can predict the swing trend of the bucket under different conditions, and provide real-time feedback to the control system to adjust the lifting process of the bucket.

[0131] Step S55: Transmitting the bucket simulation transport mechanical effect data to the bucket simulation transport swing trend distribution prediction model to perform the bucket simulation transport swing trend distribution prediction processing to generate the bucket simulation transport swing trend distribution data.

[0132] In an embodiment of the present invention, the mechanical effect data of bucket simulation transportation (such as the acceleration, vibration frequency, center of gravity offset and other data of the bucket) is transmitted to the bucket simulation transportation swing trend distribution prediction model. The model predicts the swing trend of the bucket and the corresponding transportation position in the future by analyzing the mechanical effect data, and outputs the bucket simulation transportation swing trend distribution data. The real-time data input model of the bucket is used, combined with historical data and force influence analysis, to predict the swing range, frequency change and force state of the bucket. Through the predicted data, the control system can adjust its motion strategy in real time during the operation of the bucket to reduce the impact of the swing on the stability and transportation efficiency of the bucket. The generated bucket simulation transportation swing trend distribution data provides a prediction of the dynamic behavior of the bucket in the future transportation process, providing a basis for subsequent control decisions.

[0133] Further, step S54 includes the following steps:

[0134] Step S541: performing a swing superposition state analysis of the transport force influence according to the bucket simulation transport swing descriptor data, and generating transport force image swing superposition state data;

[0135] In an embodiment of the present invention, based on the bucket simulation transportation swing descriptor data, a comprehensive analysis of the different mechanical influences on the bucket during transportation is performed through a force model. Specifically, a mechanical modeling method is used to superimpose multiple swing modes of the bucket with their corresponding force influences to analyze the force conditions of the bucket under complex working conditions. The superposition method is combined with force analysis to identify the interactions and superposition effects between different swing modes. The tools used in this analysis process are finite element analysis software or multi-body dynamics simulation tools. With the support of these tools, various force influences (such as changes in the center of gravity of the bucket, shaft temperature and humidity, and other factors) are modeled to further obtain the comprehensive force state under each working condition during transportation. Finally, the generated transport force image swing superposition state data provides a multi-dimensional performance of the bucket under different force states, providing a detailed data basis for subsequent decision tree analysis and trend prediction.

[0136] Step S542: Design a decision leaf node of the force influence and swing trend of bucket simulation transportation by using a preset decision tree algorithm on the transport force image swing superposition state data, and generate bucket simulation transportation swing trend decision leaf node data;

[0137] In an embodiment of the present invention, a preset decision tree algorithm further analyzes the transport force image swing superposition state data to identify the main decision factors affecting the bucket simulation transport swing trend. First, a set of key features, such as the bucket's swing frequency, force amplitude, bucket mass and its distribution, center of gravity offset, transport speed, etc., are selected as input features. A decision tree model is constructed based on these input features through a decision tree algorithm (such as CART or ID3 algorithm). The decision tree divides different transport states through a series of conditional branches, and generates decision leaf nodes based on different force influences and swing behaviors. Each leaf node represents a specific transport state or trend, and these nodes contain specific combinations of bucket swing modes and force conditions. In this way, the generated bucket simulation transport swing trend decision leaf node data can accurately describe the behavior trend of the bucket under different force conditions.

[0138] Step S543: using the bucket transport traction swing restriction data to perform decision condition limiting processing on the bucket transport simulation swing trend decision leaf node data, and generating limited bucket transport simulation swing trend decision leaf node data;

[0139] In an embodiment of the present invention, the bucket transport traction swing limit data is used to further limit the leaf node data of the decision tree. First, according to the design and operation parameters of the bucket, such as traction, the maximum acceleration that the bucket withstands during the lifting process, the maximum swing amplitude, and the maximum load of the bucket, the transport swing of the bucket is limited. These restrictions are integrated into each leaf node of the decision tree to ensure that the bucket does not exceed the designed safe swing range under different working conditions. Specifically, the traction limit and swing amplitude data will be used as additional conditions to further refine the branch conditions of the decision tree model and conditionally limit each decision node. Through this analysis, the generated limited bucket simulation transport swing trend decision leaf node data can reflect the stability range of the bucket under actual working conditions, exclude transportation states that do not meet the restrictions, and ensure the safe and efficient operation of the bucket.

[0140] Step S544: Design a bucket simulation transport swing trend distribution prediction model by limiting the bucket simulation transport swing trend decision leaf node data, and generate a bucket simulation transport swing trend distribution prediction model.

[0141] In an embodiment of the present invention, the design of a bucket simulation transportation swing trend distribution prediction model is performed by using limited bucket simulation transportation swing trend decision leaf node data. First, the decision leaf node data processed by limited conditions is input into a machine learning model, such as a random forest model for integrated processing, to establish a prediction model for bucket simulation transportation swing trend. These models can predict the future swing trend of the bucket based on known force influences and swing states. By training the decision tree model, it is verified and adjusted in combination with actual operation data to ensure the accuracy and robustness of the model. In the process of model design, influencing factors under different working conditions will also be considered, such as shaft environmental temperature and humidity, air pressure changes, and bucket load fluctuations. Ultimately, the generated bucket simulation transportation swing trend distribution prediction model will be able to accurately predict the swing behavior of the bucket under different working conditions, provide dynamic prediction of the swing trend during transportation, and provide support for subsequent intelligent control and scheduling systems.

[0142] Further, step S6 includes the following steps:

[0143] Step S61: designing bucket simulation transportation swing trend fuzzy logic factors based on bucket simulation transportation swing trend distribution data;

[0144] In an embodiment of the present invention, relevant fuzzy logic factors are extracted by analyzing the bucket simulation transportation swing trend distribution data. The goal of this process is to extract the key fuzzy factors that affect the bucket swing behavior from the transportation swing trend distribution data. These factors usually include the bucket's movement speed, swing amplitude, load characteristics, air pressure changes in the shaft environment, etc. By using fuzzy mathematics methods, different fuzzy sets are set to describe these factors, such as low swing, medium swing and high swing fuzzy sets. In this process, the bucket simulation transportation swing trend distribution data is first quantified and converted into numerical fuzzy factors. These factors are mapped through fuzzy logic rules to form operational fuzzy logic factor data, thereby providing basic data for subsequent fuzzy logic analysis. This process mainly uses fuzzy control system tools, and calculates and classifies relevant factors based on the input conditions provided by the system.

[0145] Step S62: performing fuzzy logic characteristic analysis and processing of the steady-state control demand of the bucket simulation transportation according to the fuzzy logic factor of the swing trend of the bucket simulation transportation, and generating fuzzy logic characteristic data of the steady-state control demand of the bucket simulation transportation;

[0146] In an embodiment of the present invention, a fuzzy logic characteristic analysis is performed on the steady-state control demand of the simulated transportation of the bucket according to the fuzzy logic factor of the swing trend of the bucket simulation transportation. First, according to the working environment and actual stress conditions of the bucket, the stability requirements under different working conditions during the simulated transportation process are analyzed using a fuzzy control algorithm. At this time, the analysis mainly focuses on controlling the swing of the bucket and improving its stability. Factors to be considered during the analysis include the swing of the bucket under different load conditions, the impact of temperature and humidity changes in the shaft environment on the transportation trajectory, and the dynamic response characteristics of the bucket at different speeds. Through the fuzzy inference system, combined with the pre-designed fuzzy rules (for example, if the swing amplitude is large, a higher stability control is required), reasoning and calculation are performed, and finally the fuzzy logic characteristic data of the steady-state control demand of the simulated transportation of the bucket are generated. These characteristic data will reflect the stability requirements of the bucket in various states, and the generated fuzzy logic characteristic data provide a practical basis for the control strategy.

[0147] Step S63: Use the fuzzy logic characteristic data of the steady-state control requirements of the bucket simulation transportation to dynamically adjust the bucket driven transportation control parameters, generate dynamic bucket driven transportation control parameters, and execute bucket driven transportation collaborative feedback operations and bucket transportation dynamic drive control operations through the dynamic bucket driven transportation control parameters.

[0148] In the embodiment of the present invention, the bucket driving transport control parameters are dynamically adjusted according to the fuzzy logic characteristic data of the generated bucket simulation transport steady-state control requirements. Since the bucket driving transport control parameters are variable parameters, the force of the bucket can be dynamically controlled by the bucket driving transport control parameters to minimize the swing of the bucket. First, the driving control parameters of the bucket (such as traction, speed, lifting angle, etc.) are dynamically adjusted in real time through the output of the fuzzy control system. Through the fuzzy logic reasoning algorithm, the previously generated fuzzy logic characteristic data is input into the control system and adjusted in real time according to the pre-set fuzzy control rules. Specifically, if the system determines that the swing amplitude of the bucket exceeds the predetermined safety range, the swing amplitude is reduced by dynamically adjusting the control parameters such as traction and lifting speed to maintain the stable state of transportation. At the same time, the dynamically adjusted control parameters will be fed back through the driving control system of the bucket to start the coordinated control operation of the bucket transportation. For example, if the traction force is set too high, the system will automatically adjust it to a reasonable range, and when the bucket is running, it will send out an audible and visual alarm signal through the bucket-driven transportation collaborative feedback operation, and the alarm equipment worn by the personnel will simultaneously send out a warning signal to remind the workers at the bottom of the well to avoid the falling bucket. In addition, the dynamic adjustment process will also be combined with the real-time operation data feedback of the bucket for continuous adjustment to ensure that every link in the transportation process is in the best stable state.

[0149] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0150] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent loading control method for a shaft excavation bucket, characterized in that: The following steps are involved: Step S1: using the monitoring sensors built into the shaft to monitor the shaft environment and perform spatiotemporal mapping of the monitoring data to generate shaft environment spatiotemporal mapping data; performing an impact assessment of the hoist pit fault based on the shaft environment spatiotemporal mapping data to generate hoist pit fault impact data; Step S2: when the hoist foundation pit fault impact data is greater than the preset hoist foundation pit alarm threshold, the foundation pit alarm feedback operation is performed through the hoist foundation pit fault impact data; otherwise, the hoist foundation pit fault impact data is continuously monitored; Step S3: using the built-in monitoring sensor of the bucket to perform bucket loading monitoring processing to generate bucket loading monitoring data, wherein the bucket loading monitoring data includes bucket loading visual data, bucket loading centroid data and bucket loading mass data; performing bucket loading semantic state analysis based on the bucket loading visual data to generate bucket loading semantic state data; performing bucket loading state feedback operation through the bucket loading semantic state data; Step S4: obtaining the bucket driving transport control parameters of the hoisting equipment; performing bucket loading mechanical characteristic analysis based on bucket loading center of mass data and bucket loading mass data to generate bucket loading mechanical characteristic data; performing bucket simulated transport swing behavior analysis and processing based on bucket driving transport control parameters, bucket loading mechanical characteristic data and shaft environment spatiotemporal mapping data to generate bucket simulated transport swing behavior data; Step S5: performing swing trend distribution analysis and processing of the bucket simulation transportation based on the bucket simulation transportation swing behavior data to generate bucket simulation transportation swing trend distribution data; Step S6: Based on the bucket simulation transport swing trend distribution data, the bucket driven transport control parameters are dynamically adjusted to generate dynamic bucket driven transport control parameters, and bucket driven transport collaborative feedback operations and bucket transport dynamic drive control operations are executed through the dynamic bucket driven transport control parameters.

2. The intelligent loading control method for a shaft excavation bucket according to claim 1, characterized in that: The vertical shaft environment spatiotemporal mapping data in step S1 includes vertical shaft temperature and humidity mapping data and vertical shaft air pressure mapping data.

3. The intelligent loading control method for a shaft excavation bucket according to claim 2, characterized in that: Step S1 includes the following steps: Step S11: using the monitoring sensor built into the shaft to perform shaft environment monitoring processing on the shaft area to generate shaft environment monitoring data; Step S12: using the time-space difference technology to perform environmental time-space mapping processing on the shaft environment monitoring data to generate shaft environment time-space mapping data; Step S13: Performing time series characteristic analysis on the shaft temperature and humidity mapping data to generate shaft temperature and humidity time series characteristic data; Step S14: performing an environmental impact trend analysis of the elevator base station based on the shaft temperature and humidity time series characteristic data to generate environmental impact trend data of the elevator base station; Step S15: Perform an impact assessment process on the hoist foundation pit fault according to the hoist base station environmental impact trend data to generate hoist foundation pit fault impact data.

4. The intelligent loading control method for a shaft excavation bucket according to claim 3, characterized in that: Step S14 includes the following steps: Step S141: Acquire historical shaft temperature and humidity data and historical elevator base station impact data; Step S142: performing shaft temperature and humidity perception specificity analysis based on historical shaft temperature and humidity data to generate shaft temperature and humidity perception specificity data; Step S143: performing a temperature and humidity perception-specific base station impact factor analysis on the historical elevator base station impact data based on the shaft temperature and humidity perception-specific data to generate a temperature and humidity perception-specific base station impact factor; Step S144: using the temperature and humidity sensing specific base station influencing factors to perform an elevator base station environmental impact trend analysis on the shaft temperature and humidity time series characteristic data, and generate elevator base station environmental impact trend data.

5. The intelligent loading control method for a shaft excavation bucket according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: using the monitoring sensor built into the bucket to perform bucket loading monitoring processing to generate bucket loading monitoring data; Step S32: performing bucket loading entity object recognition processing on the bucket loading visual data based on a preset convolutional neural network model to generate bucket loading entity object data; Step S33: performing a bucket loading entity object distribution spatial analysis based on the bucket loading visual data to generate bucket loading entity object distribution spatial data; Step S34: Perform bucket loading semantic state analysis based on bucket loading entity object data and bucket loading entity object distribution space data to generate bucket loading semantic state data; perform bucket loading state feedback operation through bucket loading semantic state data.

6. The intelligent loading control method for a shaft excavation bucket according to claim 2, characterized in that: Step S4 includes the following steps: Step S41: obtaining the bucket driving and transport control parameters of the hoisting equipment; Step S42: performing bucket loading mechanical characteristic analysis based on bucket loading centroid data and bucket loading mass data to generate bucket loading mechanical characteristic data; Step S43: performing mechanical distribution analysis of the vertical shaft influence according to the vertical shaft air pressure mapping data to generate the vertical shaft influence mechanical distribution data; Step S44: using multiple regression analysis to analyze the bucket driving transport control parameters, bucket loading mechanical characteristic data and shaft influence mechanical distribution data for bucket simulated transport mechanical effect, and generating bucket simulated transport mechanical effect data; Step S45: performing bucket transport traction swing limit analysis according to bucket drive transport control parameters to generate bucket transport traction swing limit data; Step S46: Perform bucket simulation transport swing behavior analysis and processing based on bucket transportation traction swing restriction data and bucket simulation transport mechanical effect data to generate bucket simulation transport swing behavior data.

7. The intelligent loading control method for a shaft excavation bucket according to claim 6, characterized in that: Step S42 includes the following steps: Perform bucket loading gravity center offset characteristic analysis on bucket loading gravity center data to generate bucket loading gravity center offset characteristic data; The bucket loading mechanical characteristic analysis is performed based on the bucket loading center of gravity offset characteristic data and the bucket loading mass data to generate the bucket loading mechanical characteristic data.

8. The intelligent loading control method for a shaft excavation bucket according to claim 6, characterized in that: Step S5 includes the following steps: Step S51: performing bucket simulation transportation swing mode analysis according to bucket simulation transportation swing behavior data to generate bucket simulation transportation swing mode data; Step S52: performing bucket transport swing frequency analysis on the bucket simulated transport swing behavior data to generate bucket simulated transport swing frequency data; Step S53: performing bucket simulation transport swing descriptor analysis according to bucket simulation transport swing mode data and bucket simulation transport swing frequency data to generate bucket simulation transport swing descriptor data; Step S54: Designing a distribution mapping relationship between the force influence and the swing trend of the bucket simulation transportation based on the bucket simulation transportation swing descriptor data, and generating a bucket simulation transportation swing trend distribution prediction model; Step S55: Transmitting the bucket simulation transport mechanical effect data to the bucket simulation transport swing trend distribution prediction model to perform the bucket simulation transport swing trend distribution prediction processing to generate the bucket simulation transport swing trend distribution data.

9. The intelligent loading control method for a shaft excavation bucket according to claim 8, characterized in that: Step S54 includes the following steps: Step S541: performing a swing superposition state analysis of the transport force influence according to the bucket simulation transport swing descriptor data, and generating transport force image swing superposition state data; Step S542: Design a decision leaf node of the force influence and swing trend of bucket simulation transportation by using a preset decision tree algorithm on the transport force image swing superposition state data, and generate bucket simulation transportation swing trend decision leaf node data; Step S543: using the bucket transport traction swing restriction data to perform decision condition limiting processing on the bucket transport simulation swing trend decision leaf node data, and generating limited bucket transport simulation swing trend decision leaf node data; Step S544: Design a bucket simulation transport swing trend distribution prediction model by limiting the bucket simulation transport swing trend decision leaf node data, and generate a bucket simulation transport swing trend distribution prediction model.

10. The intelligent loading control method for a shaft excavation bucket according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: designing bucket simulation transportation swing trend fuzzy logic factors based on bucket simulation transportation swing trend distribution data; Step S62: performing fuzzy logic characteristic analysis and processing of the steady-state control demand of the bucket simulation transportation according to the fuzzy logic factor of the swing trend of the bucket simulation transportation, and generating fuzzy logic characteristic data of the steady-state control demand of the bucket simulation transportation; Step S63: Use the fuzzy logic characteristic data of the steady-state control requirements of the bucket simulation transportation to dynamically adjust the bucket driven transportation control parameters, generate dynamic bucket driven transportation control parameters, and execute bucket driven transportation collaborative feedback operations and bucket transportation dynamic drive control operations through the dynamic bucket driven transportation control parameters.

Images