Cooperative dynamic load distribution method and device for driving and anchoring all-in-one machine and medium

Abstract

The invention provides a driving and anchoring all-in-one machine cooperative dynamic load distribution method and device and a medium, and relates to the technical field of driving and anchoring all-in-one machines, and the method comprises the steps: executing state recognition of a plurality of operation units in a driving and anchoring all-in-one machine, and obtaining real-time load data; performing power demand prediction on the plurality of operation units to obtain a plurality of operation power demands; based on the available power upper limit and the power redundancy threshold value of the main drive system, whether a power residual space exists or not is judged; if the power residual space exists, load distribution is executed according to the multiple operation power requirements, and a load distribution decision is generated; and performing dynamic load distribution on the plurality of operation units according to the load distribution decision. The technical problem that in the prior art, a power distribution strategy cannot be reasonably adjusted according to actual load requirements and working condition changes can be solved, and the technical effect of improving the overall operation efficiency is achieved.

Description

Technical Field

[0001] This application relates to the field of tunneling and anchoring machine technology, and in particular to a dynamic load distribution method, equipment and medium for tunneling and anchoring machine collaboration. Background Technology

[0002] As a key piece of equipment in coal mine and tunnel engineering, the integrated tunneling and anchoring machine (TOC) directly affects the overall construction progress and project cost due to its operational efficiency and resource utilization. With the increasing complexity of underground engineering operations, TOCs are developing towards intelligent and collaborative systems.

[0003] Currently, existing tunneling and anchoring machines employ a fixed power allocation strategy during operation, scheduling power resources according to preset fixed priorities or empirical parameters for each work unit. However, this static allocation method has significant limitations when facing complex and dynamically changing geological conditions and working environments. On the one hand, the load status and power demand of different work units change constantly during operation. For example, the power demand of the cutting system increases significantly when encountering hard rock, while the propulsion and anchoring systems may be in a low-load or waiting state at certain times. On the other hand, current systems typically lack deep perception and data fusion capabilities for real-time operating status, making it impossible to accurately identify abnormal working conditions such as hydraulic fluctuations and motor overload, thus failing to adjust the power allocation strategy in a timely manner to ensure the overall stable operation of the system.

[0004] In summary, existing technologies suffer from technical problems such as fixed power distribution strategies and a lack of real-time perception and dynamic response capabilities for the operating status of work units. This results in an inability to make reasonable adjustments based on actual load requirements and changes in working conditions, further affecting the key performance of the tunneling and anchoring machine in complex environments, including operating efficiency, system stability, and energy consumption control. Summary of the Invention

[0005] The purpose of this application is to provide a dynamic load distribution method, equipment, and medium for integrated tunneling and anchoring machines, in order to solve the technical problems in the prior art where the fixed power distribution strategy and lack of real-time perception and dynamic response capability of the operating status of the working unit make it impossible to make reasonable adjustments according to actual load requirements and changes in working conditions, which further affects the key performance of integrated tunneling and anchoring machines in complex environments, such as operating efficiency, system stability, and energy consumption control.

[0006] In view of the above problems, this application provides a dynamic load distribution method, equipment and medium for integrated tunneling and anchoring machines.

[0007] In a first aspect, this application provides a dynamic load allocation method for the collaborative operation of a tunneling and anchoring machine, comprising: performing status identification of multiple working units in the tunneling and anchoring machine to obtain real-time load data; performing power demand prediction on the multiple working units to obtain multiple working power demands; determining whether there is remaining power space based on the upper limit of available power of the main drive system and the power redundancy threshold; if there is remaining power space, performing load allocation according to the multiple working power demands to generate a load allocation decision; and performing dynamic load allocation on the multiple working units according to the load allocation decision.

[0008] Preferably, the dynamic load distribution method for the integrated tunneling and anchoring machine further includes: acquiring the state parameters of the multiple working units, wherein the state parameters include the cutting motor current, the cutting motor hydraulic pressure, the propulsion cylinder displacement speed, the anchor bolting machine torque, and the anchor cable tension; establishing a state mapping model based on the state parameters, and mapping the state parameters to the real-time load data.

[0009] Preferably, the dynamic load allocation method for the integrated tunneling and anchoring machine further includes: extracting a first working unit based on the plurality of working units; training a first working power demand prediction channel using the load data sample set of the first working unit as input features and the power demand sample set of the first working unit as output features to obtain a first power prediction learning coefficient; if the first power prediction learning coefficient exceeds a first predetermined power prediction learning constraint, obtaining the first working power demand prediction channel; traversing the plurality of working units based on the first working power demand prediction channel to obtain a working power demand prediction channel; and predicting the power demand of the plurality of working units based on the real-time load data using the working power demand prediction channel to obtain the plurality of working power demands.

[0010] Preferably, the dynamic load allocation method for the integrated tunneling and anchoring machine further includes: calculating the remaining power based on the maximum output power and the real-time main drive output power; calculating the difference between the multiple operating power requirements and the remaining power; if the difference is greater than or equal to the power redundancy threshold, it is determined that there is remaining power space.

[0011] Preferably, the dynamic load allocation method for the integrated tunneling and anchoring machine further includes: assigning preset priority weights to the multiple work units; calculating a load allocation coefficient by ratio of the product of each work power requirement and each priority weight to the sum of the products of the power requirements and priority weights of the multiple work units; and allocating the load to be allocated according to the load allocation coefficient to obtain the load allocation decision.

[0012] Preferably, the dynamic load allocation method for the integrated tunneling and anchoring machine further includes: acquiring multi-parameter monitoring data of the multiple work units; determining whether there is an abnormal event based on the multi-parameter monitoring data; if an abnormal event is detected, triggering the priority adjustment mechanism of the power scheduling command, updating the load allocation decision in real time, and determining the dynamic load allocation decision.

[0013] Preferably, the dynamic load distribution method for the integrated tunneling and anchoring machine further includes: constructing an abnormal event identification model, which is modeled based on multi-parameter monitoring data samples during the operation of the multiple work units, wherein the multi-parameter monitoring data samples include power change rate, hydraulic oil pressure fluctuation rate, motor current slope, and anchoring load mutation amplitude; performing feature fusion and critical value comparison on the multi-parameter monitoring data to identify abnormal events; after identifying abnormal events, automatically generating a power response scheme based on the event type and impact level, and adjusting the load distribution decision of at least one work unit.

[0014] Preferably, the dynamic load allocation method for the integrated tunneling and anchoring machine further includes: training an evolution model based on the operating data of the multiple working units under different geological and load conditions, wherein the evolution model is used to learn the power coupling relationship and priority evolution law among the multiple working units; and adaptively adjusting the preset priority weights of the multiple working units and the dynamic load allocation decision in the evolution model according to the real-time operating status of the multiple working units.

[0015] Secondly, this application also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the dynamic load distribution method for the integrated tunneling and anchoring machine as described in any one of the first aspects above.

[0016] Thirdly, a computer-readable storage medium storing a computer program that, when executed, implements the steps of the dynamic load distribution method for the integrated tunneling and anchoring machine as described in any one of the first aspects.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by realizing the technical goal of dynamic power scheduling and intelligent load distribution among multiple working units of the tunneling and anchoring machine, the technical effects of improving overall operating efficiency, ensuring safe and stable operation of equipment, and effectively reducing energy consumption are achieved.

[0018] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the dynamic load distribution method for the integrated tunneling and anchoring machine in this application.

[0021] Figure 2 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0022] Explanation of reference numerals in the attached drawings: Bus 300, Receiver 301, Processor 302, Transmitter 303, Memory 304, Bus Interface 305. Detailed Implementation

[0023] This application provides a dynamic load distribution method, equipment, and medium for integrated tunneling and anchoring machines, solving the technical problems in existing technologies where fixed power distribution strategies and a lack of real-time perception and dynamic response capabilities to the operating status of work units prevent reasonable adjustments based on actual load demands and changes in working conditions. This further impacts the key performance aspects of integrated tunneling and anchoring machines in complex environments, such as operating efficiency, system stability, and energy consumption control. The application achieves the technical goal of dynamic power scheduling and intelligent load distribution among multiple work units of the integrated tunneling and anchoring machine, thereby improving overall operating efficiency, ensuring safe and stable equipment operation, and effectively reducing energy consumption.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a dynamic load distribution method for the coordinated operation of a tunneling and anchoring machine, which is applied to a dynamic load distribution system for the coordinated operation of a tunneling and anchoring machine. The method specifically includes the following steps: S1: Perform status identification of multiple working units in the integrated tunneling and anchoring machine and obtain real-time load data.

[0026] Furthermore, this application also includes: acquiring the status parameters of the plurality of working units, wherein the status parameters include the cutting motor current, the cutting motor hydraulic oil pressure, the propulsion cylinder displacement speed, the anchor bolt machine torque, and the anchor cable tension; establishing a status mapping model based on the status parameters, and mapping the status parameters to the real-time load data.

[0027] Specifically, during the operation of the integrated tunneling and anchoring machine, status parameters of multiple work units are acquired to describe the operating status of each subsystem when performing different tasks. Work units refer to functional modules such as the cutting device, propulsion device, anchor drilling rig, and anchor cable tensioning system. Status parameters are key indicators reflecting the working status of these functional modules. These include the cutting motor current, representing the energy consumption intensity of the cutting system when cutting coal and rock; and the cutting motor hydraulic oil pressure, reflecting the pressure environment of the hydraulic drive system and thus indicating the mechanical load. Next, the propulsion cylinder displacement speed represents the movement speed of the hydraulic cylinder in the propulsion system, indirectly reflecting the speed and resistance of the equipment's forward movement; the anchor drilling rig torque represents the torque magnitude during anchor installation, affecting anchoring quality and safety; and the anchor cable tension describes the tension applied when the anchor cable is tightened, which is an important measure of the roof support effect.

[0028] A state mapping model is established based on state parameters to transform the perceived multidimensional operational data into real-time load data that can be used for calculation. The state mapping model can be a mathematical model, a machine learning model, or an expert system, depending on the coupling complexity between parameters. It identifies the functional relationships between state parameters; for example, when the cutting current and oil pressure continuously increase, it indicates that the cutting resistance is increasing, suggesting that the real-time load is also increasing. The state parameters at each moment are combined to convert the load currently borne by the system, i.e., the real-time load data, for subsequent power scheduling and load allocation. Table 1 shows the mapping table between the state parameters and real-time load of the work unit.

[0029] Table 1: Mapping Table of Job Unit Status Parameters and Real-time Load S2: Based on the real-time load data, predict the power demand of the multiple work units to obtain multiple work power demands.

[0030] Furthermore, this application also includes: extracting a first work unit based on the plurality of work units; training a first work power demand prediction channel using the load data sample set of the first work unit as input features and the power demand sample set of the first work unit as output features to obtain a first power prediction learning coefficient; if the first power prediction learning coefficient exceeds a first predetermined power prediction learning constraint, obtaining the first work power demand prediction channel; traversing the plurality of work units based on the first work power demand prediction channel to obtain a work power demand prediction channel; and predicting the power demand of the plurality of work units based on the real-time load data using the work power demand prediction channel to obtain the plurality of work power demands.

[0031] Specifically, the first work unit is randomly selected from multiple work units for initial analysis. Work units typically include mechanical functional modules such as cutting, propulsion, and anchoring. Next, the load data sample set of the first work unit is used as input features. This means organizing the load parameters (such as current, oil pressure, and speed) of this unit under different working conditions from historical records into a data set, which is then used as input variables for model training. Simultaneously, its power demand sample set is used as output features, i.e., the power consumption or demand recorded within the same time period, serving as the target value for model training. Through input-output pairing, a first work unit power demand prediction channel is trained to map the load to power demand prediction model. The result is the first power prediction learning coefficient, used to measure the model's fit or predictive ability during the learning process.

[0032] Then, it is determined whether the first power prediction learning coefficient exceeds the first predetermined power prediction learning constraint. The first power prediction learning coefficient is an indicator used to evaluate whether the model has converged or whether the training is effective, and the first predetermined power prediction learning constraint is a set threshold standard. For example, if the first predetermined power prediction learning coefficient exceeds the first predetermined power prediction learning constraint, it means that the prediction channel is effective, and thus the power demand prediction channel of the job unit is saved.

[0033] Furthermore, based on the acquired first job power demand prediction channel, other job units are traversed, and corresponding job power demand prediction channels are established one by one. Each job unit will have an independent prediction model, which infers its future or real-time power demand from its load data, realizing parallel power prediction for multiple modules. Finally, using all job power demand prediction channels and combining the real-time acquired load data, the power demand of multiple job units is predicted, thereby obtaining the power request at the current moment.

[0034] S3: Based on the upper limit of available power of the main drive system and the power redundancy threshold, determine whether there is any remaining power space.

[0035] Furthermore, this application also includes: calculating the remaining power based on the maximum output power and the real-time main drive output power; calculating the difference between the multiple operating power requirements and the remaining power, and if the difference is greater than or equal to the power redundancy threshold, it is determined that there is remaining power space.

[0036] Specifically, the remaining power is calculated based on the maximum output power and the real-time main drive output power. The maximum output power refers to the highest power value that the main drive system of the tunneling and anchoring machine can provide under ideal operating conditions, determined by the equipment design parameters, such as 120 kilowatts. The real-time main drive output power refers to the power actually being output by the main drive system during the current operation, for example, 95 kilowatts at a certain moment. Subtracting the current value from the maximum value yields the remaining power, which serves as the schedulable power space.

[0037] Subsequently, it is necessary to calculate the difference between the power demand and the remaining power for multiple operations. The sum of the current or predicted power demand of each operation unit is compared with the current remaining power of the system to determine whether the power is sufficient. For example, if the current predicted demand for the three operation units of cutting, advancing, and anchoring is 10 kW, 8 kW, and 9 kW respectively, then the total demand is 27 kW. If the remaining power is 25 kW, then the difference is 2 kW.

[0038] Finally, if the difference is greater than or equal to the power redundancy threshold, it is determined that there is remaining power capacity. The power redundancy threshold is a manually set criterion used to identify whether there are sufficient surplus power resources for scheduling. The power redundancy threshold is set to 3 kW or 5 kW to ensure the stability and security of power allocation. If the current difference is lower than the power redundancy threshold, power protection or delayed scheduling mechanisms may be triggered; conversely, if the difference is equal to or higher than the threshold, it will be confirmed that there are sufficient power resources, and load allocation can continue.

[0039] S4: If there is a remaining power space, perform load allocation according to the multiple work power requirements and generate a load allocation decision.

[0040] Furthermore, this application also includes: assigning preset priority weights to the plurality of work units; calculating a load allocation coefficient by ratio of the product of each work power requirement and each priority weight to the sum of the products of the power requirements and priority weights of the plurality of work units; and allocating the load to be allocated according to the load allocation coefficient to obtain the load allocation decision.

[0041] Specifically, assigning preset priority weights to multiple work units means that each work unit is assigned a value representing its priority based on its importance, urgency, or resource dependence during the anchoring operation. The preset priority weight is a proportional coefficient greater than zero, used to guide subsequent resource allocation strategies. For example, the cutting unit may be most critical in the initial advance stage, and its preset priority weight could be set to 0.5; the propulsion unit, as a supporting action, could be set to 0.3; and if the anchor bolting operation is temporarily suspended, the preset priority weight might be 0.2. The preset priority weights provide a basic resource scheduling reference for the entire load distribution system.

[0042] Next, the load allocation coefficient is calculated by ratioing the product of each operation's power demand and its priority weight to the sum of the products of the power demands and priority weights of multiple operation units. Each operation unit's current power demand is multiplied by its corresponding priority weight to obtain a weighted power demand. For example, if the cutting unit's power demand is 20 kW and its priority weight is 0.5, its weighted demand is 10; the propulsion unit's power demand is 15 kW and its priority weight is 0.3, resulting in a weighted value of 4.5; and the anchor bolt unit's demand is 10 kW and its priority weight is 0.2, resulting in a weighted value of 2. The weighted values ​​are summed to obtain a total of 16.5. Dividing the weighted value of each operation unit by this total yields their respective load allocation coefficients: 0.606, 0.273, and 0.121.

[0043] Then, based on the load allocation coefficient, the load to be allocated is determined, resulting in a load allocation decision. This means that the currently available power resources are allocated according to the previously calculated proportional coefficient. Assuming the current system has a remaining power of 33 kilowatts, 20 kilowatts will be allocated to the cutting unit, 9 kilowatts to the propulsion unit, and 4 kilowatts to the anchor bolt unit. This not only ensures the power supply for high-priority work units but also takes into account the coordination of the overall work rhythm, preventing any work unit from interrupting operation due to insufficient power.

[0044] S5: Based on the load allocation decision, dynamically allocate the load to the multiple work units.

[0045] Furthermore, this application also includes: acquiring multi-parameter monitoring data of the plurality of work units; determining whether there is an abnormal event based on the multi-parameter monitoring data; if an abnormal event is detected, triggering the priority adjustment mechanism of the power scheduling command, updating the load allocation decision in real time, and determining the dynamic load allocation decision.

[0046] Furthermore, this application also includes: constructing an abnormal event identification model, which is modeled based on multi-parameter monitoring data samples during the operation of the multiple work units, wherein the multi-parameter monitoring data samples include power change rate, hydraulic oil pressure fluctuation rate, motor current slope, and anchor load mutation amplitude; performing feature fusion and critical value comparison on the multi-parameter monitoring data to identify abnormal events; after identifying abnormal events, automatically generating a power response scheme based on the event type and impact level, and adjusting the load distribution decision of at least one work unit.

[0047] Furthermore, this application also includes: training an evolutionary model based on the operating data of the multiple work units under different geological and load conditions, wherein the evolutionary model is used to learn the power coupling relationship and priority evolution law among the multiple work units; and adaptively adjusting the preset priority weights of the multiple work units and the dynamic load allocation decision in the evolutionary model according to the real-time operating status of the multiple work units.

[0048] Specifically, acquiring multi-parameter monitoring data from multiple work units refers to the system's real-time collection of key operating parameters from each work unit of the integrated tunneling and anchoring machine during operation. Monitoring data includes electrical parameters such as current and voltage, hydraulic parameters such as oil pressure and temperature, and mechanical parameters such as torque, displacement, and speed. For example, the cutting unit might collect the cutting motor current and hydraulic oil pressure, the propulsion system would monitor cylinder displacement and speed, and the anchor bolt system would acquire tension and torque. Multi-parameter monitoring data comprehensively reflects the current operating status of the equipment and forms the basis for subsequent judgments on whether it is operating normally.

[0049] Analyze multi-parameter monitoring data to determine if any abnormal events exist. Abnormal events refer to sudden or unusual changes that deviate from normal operating conditions, such as a sudden increase in power, drastic fluctuations in hydraulic oil pressure, or a sharp increase in motor current. Judgment methods can be based on rule settings, statistical analysis, or model learning. For example, if the cutting motor power suddenly increases from 20 kW to 35 kW within a short period, accompanied by current fluctuations exceeding a set threshold, it may be identified as an abnormal event.

[0050] Once an abnormal event is detected, the priority adjustment mechanism of the power scheduling command will be triggered, meaning that the originally set load allocation strategy will be intervened in real time. For example, if a propulsion unit malfunctions or overloads, its priority will be automatically reduced, and more power resources will be transferred to normally operating units, such as bolting machines or cutting machines. This mechanism can effectively prevent faulty units from excessively consuming resources and improve overall operating efficiency. Subsequently, the system will update the load allocation decision in real time based on the adjustment results, forming a new dynamic load allocation scheme to adapt to changes in sudden operating conditions.

[0051] To achieve intelligent identification of abnormal events, an abnormal event identification model is constructed. This model is obtained by modeling historical data from multiple work units during operation. The multi-parameter monitoring data samples contain information from multiple dimensions. For example, the power change rate indicates the rate of power increase or decrease, the hydraulic oil pressure fluctuation rate reflects the stability of the system pressure, the motor current slope indicates the load change trend, and the amplitude of anchor load abrupt change is used to determine the impact changes during the tensioning process of anchor bolts or cables. A comprehensive analysis is performed using feature fusion and critical value comparison methods. If the detection result exceeds a certain preset threshold, it is identified as an abnormal event.

[0052] After identifying abnormal events, a power response plan is automatically generated based on the event type and impact level. For example, if the event type is motor overload and the impact level is moderate, the load distribution of the working unit may be reduced by 20%; if the hydraulic system collapses and the impact level is severe, the power supply may be cut off immediately and the remaining power may be redistributed to the other units according to priority.

[0053] Furthermore, to enable the entire system to adapt and evolve, an evolutionary model is trained based on operational data from multiple work units under different geological and load conditions. This model learns the power coupling relationships and priority evolution patterns among the work units. Power coupling refers to whether a power change in one work unit affects other units; for example, an increase in cutting power may cause power fluctuations in the hydraulic system. Priority evolution patterns refer to which work unit should receive higher resource allocation under different geological conditions. The evolutionary model can summarize patterns from massive amounts of data and adaptively adjust its preset priority weights and final dynamic load allocation decisions based on the real-time status of the work units during runtime.

[0054] In summary, the dynamic load distribution method for the integrated tunneling and anchoring machine provided in this application has the following technical effects: by realizing the technical goal of dynamic power scheduling and intelligent load distribution among multiple working units of the integrated tunneling and anchoring machine, it achieves the technical effects of improving overall operating efficiency, ensuring safe and stable operation of equipment, and effectively reducing energy consumption.

[0055] Example 2: Based on the inventive concept of the dynamic load distribution method for the integrated tunneling and anchoring machine in collaboration with the aforementioned examples, this application also provides an electronic device, including: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the dynamic load distribution method for the integrated tunneling and anchoring machine in collaboration as described in any one of Examples 1 above.

[0056] Appendix Figure 2 This is a schematic diagram of the structure of an exemplary electronic device of this application. Figure 2 In this document, the bus architecture is represented by bus 300. Bus 300 may include any number of interconnected buses and bridges, and bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 may also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 during operation.

[0057] In Embodiment 3, based on the dynamic load distribution method of the tunneling and anchoring machine in collaboration with the aforementioned embodiments, and using the same inventive concept, this application also provides a computer-readable storage medium storing a computer program, which, when executed, implements the steps of the dynamic load distribution method of the tunneling and anchoring machine in collaboration as described in any one of Embodiment 1 above.

[0058] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily 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 this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0059] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A dynamic load distribution method for integrated tunneling and anchoring machines, characterized in that, include: Perform status identification of multiple working units in the integrated tunneling and anchoring machine and obtain real-time load data; Based on the real-time load data, power demand prediction is performed on the multiple work units to obtain multiple work power demands; Based on the upper limit of available power of the main drive system and the power redundancy threshold, determine whether there is any remaining power space; If there is a remaining power capacity, load allocation is performed based on the multiple work power requirements to generate a load allocation decision. Based on the load allocation decision, dynamic load allocation is performed on the multiple work units.

2. The dynamic load distribution method for integrated tunneling and anchoring machines as described in claim 1, characterized in that, include: The status parameters of the multiple working units are obtained, including the cutting motor current, the cutting motor hydraulic oil pressure, the propulsion cylinder displacement speed, the anchor bolt machine torque, and the anchor cable tension. A state mapping model is established based on the state parameters, and the state parameters are mapped to the real-time load data.

3. The dynamic load distribution method for integrated tunneling and anchoring machines as described in claim 1, characterized in that, include: Extract the first work unit based on the plurality of work units; Using the load data sample set of the first work unit as input features and the power demand sample set of the first work unit as output features, the first work power demand prediction channel is trained to obtain the first power prediction learning coefficient. If the first power prediction learning coefficient exceeds the first predetermined power prediction learning constraint, obtain the first job power demand prediction channel. Based on the first operation power demand prediction channel, the operation power demand prediction channel is obtained by traversing the multiple operation units. Based on the power demand prediction channel, the power demand of the multiple work units is predicted based on the real-time load data to obtain the power demand of the multiple work units.

4. The dynamic load distribution method for integrated tunneling and anchoring machines as described in claim 1, characterized in that, include: Calculate the remaining power based on the maximum output power and the real-time main drive output power; The difference between the power requirements of the multiple operations and the remaining power is calculated. If the difference is greater than or equal to the power redundancy threshold, it is determined that there is remaining power space.

5. The dynamic load distribution method for integrated tunneling and anchoring machines as described in claim 1, characterized in that, include: Assign preset priority weights to the multiple work units; The load allocation coefficient is calculated by ratioing the product of each job's power requirement and each priority weight to the sum of the products of the power requirements and priority weights of multiple job units. The load allocation decision is obtained by allocating the load to be allocated based on the load allocation coefficient.

6. The dynamic load distribution method for integrated tunneling and anchoring machines as described in claim 1, characterized in that, include: Acquire multi-parameter monitoring data of the multiple work units; Based on the multi-parameter monitoring data, determine whether any abnormal events exist; If an abnormal event is detected, the priority adjustment mechanism of the power scheduling command is triggered to update the load allocation decision in real time and determine the dynamic load allocation decision.

7. The dynamic load distribution method for integrated tunneling and anchoring machines as described in claim 6, characterized in that, include: An abnormal event identification model is constructed. The abnormal event identification model is modeled based on multi-parameter monitoring data samples during the operation of the multiple work units. The multi-parameter monitoring data samples include power change rate, hydraulic oil pressure fluctuation rate, motor current slope, and anchor load sudden change amplitude. The multi-parameter monitoring data is subjected to feature fusion and critical value comparison to identify abnormal events; After identifying an abnormal event, a power response plan is automatically generated based on the event type and impact level, and the load allocation decision of at least one work unit is adjusted.

8. The dynamic load distribution method for integrated tunneling and anchoring machines as described in claim 6, characterized in that, include: Based on the operational data of the multiple work units under different geological and load conditions, an evolutionary model is trained. The evolutionary model is used to learn the power coupling relationship and priority evolution law among the multiple work units. Based on the real-time operating status of the multiple work units, the preset priority weights of the multiple work units and the dynamic load allocation decision are adaptively adjusted in the evolution model.

9. An electronic device, characterized in that, include: At least one processor; A memory that is communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the steps of the dynamic load distribution method for the integrated tunneling and anchoring machine as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the steps of the dynamic load distribution method for the integrated tunneling and anchoring machine as described in any one of claims 1 to 8.

Images