Multi-channel combined machine tool motion control method and system based on group intelligence

Abstract

The invention belongs to the technical field of ant colony algorithms, and particularly relates to a multi-channel combined machine tool motion control method and system based on swarm intelligence, and the method comprises the steps: building a real-time comprehensive state efficiency index fusing the congestion degree and the health degree through collecting the real-time queuing length, temperature and vibration data of each processing channel, and carrying out the real-time comprehensive state efficiency index; the index serves as dynamic correction heuristic information to be fused into an ant colony algorithm, and the channel selection probability is calculated to distribute processing tasks; and meanwhile, pheromones are fed back and updated by utilizing the actual total consumed time of the workpiece. According to the invention, dynamic perception and adaptive scheduling of the operation state of the machine tool are realized, congestion and sub-health channels are effectively avoided, and the production efficiency and the system load balancing capability are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of ant colony optimization technology. More specifically, this invention relates to a motion control method and system for multi-channel combined machine tools based on swarm intelligence. Background Technology

[0002] Multi-channel machining centers are key equipment in modern precision manufacturing. By coordinating the operation of multiple parallel machining channels, they greatly improve production efficiency and product throughput. Motion control is a key technology to ensure their efficient operation. Traditionally, the focus has been on trajectory planning, feed rate, and interpolation control of a single machine tool. With the improvement of industrial automation, how to dynamically, collaboratively, and globally optimize the workpiece flow of the entire machine tool group has become a bottleneck problem in improving production line efficiency.

[0003] To address complex resource allocation and path selection problems, researchers have introduced swarm intelligence algorithms, among which the Ant Colony Optimization (ACO) algorithm has attracted widespread attention due to its self-organization and robustness. The ACO algorithm treats workpieces as "ants" and processing channels as "paths," utilizing pheromones along the paths... and heuristic information Together, we guide the selection of paths, thereby achieving global optimization.

[0004] However, when applying the traditional ant colony algorithm to the scheduling scenario of multi-channel combined machine tools with high precision and high real-time performance, there are significant drawbacks. The main problem is that the heuristic information used is often based on static or single indicators, such as the reciprocal of the ideal processing time of the processing channel. Such static heuristic functions cannot effectively perceive the dynamic congestion status (such as the current queue length) and health status (such as machine tool temperature and vibration) of multi-channel combined machine tools under real-time operating conditions.

[0005] This scheduling strategy, which relies on static indicators, limits the adaptability and optimization capabilities of the ACO algorithm, leading to a mismatch between task allocation decisions and complex real-time operating conditions. Therefore, there is an urgent need for a dynamic scheduling strategy that can integrate into the real-time operating status of the processing channel to overcome the limitations of the traditional ant colony algorithm. Summary of the Invention

[0006] To address the technical problem that traditional ant colony algorithms, which rely solely on static indicators, cannot respond to real-time machine tool operating conditions, this invention provides solutions in the following aspects.

[0007] In a first aspect, the present invention provides a motion control method for a multi-channel combined machine tool based on swarm intelligence, comprising: acquiring system state data and initializing an ant colony algorithm, wherein the state data includes real-time queuing state data and machine tool health data for each processing channel; evaluating the congestion index and health index of each processing channel based on the real-time queuing state data and machine tool health data, and constructing a real-time comprehensive state efficiency index for each processing channel; using the comprehensive state efficiency index as a dynamic correction heuristic and incorporating it into the channel selection probability calculation formula of the ant colony algorithm to calculate the probability that a workpiece selects the processing channel from a waiting node; allocating tasks according to the probability and outputting motion control commands, and updating the pheromone of the ant colony algorithm based on the actual total time consumed by the processing channel.

[0008] Unlike traditional scheduling methods that rely solely on static ideal time, this invention introduces real-time queue length, temperature, and vibration data of machine tools to construct congestion and health indicators. This leads to the development of a dynamic, real-time comprehensive state efficiency indicator. By incorporating this indicator as heuristic information into the ant colony algorithm and combining it with a closed-loop pheromone update mechanism based on actual time consumption, dynamic adaptive scheduling of workpiece flow is achieved. This avoids congested and sub-healthy channels, significantly improving the load balancing capability, production efficiency, and operational stability of multi-channel machine tools.

[0009] Preferably, the machine tool health data includes the real-time temperature and real-time vibration amplitude of the machining channel.

[0010] Preferably, the congestion index of the processing channel is calculated using the following formula: In the formula, For processing channel Congestion index; For processing channel The current workpiece queue length; For the workpiece in the machining channel Ideal processing time; This represents the maximum ideal processing time for all processing channels; It is a natural exponential function; This is the preset congestion threshold queue length.

[0011] This invention introduces an exponential penalty term based on queue length when calculating the congestion index. Once the queue length exceeds a critical value, the congestion index grows exponentially. It can highly sensitively identify and report the oversaturation state of the channel, and force the algorithm to quickly cut off the input of new tasks when the channel is about to become severely congested. This is more effective than traditional linear load balancing strategies in preventing production line bottlenecks and deadlocks.

[0012] Preferably, the formula for calculating the health index of the processing channel is: In the formula, For processing channel Health indicators; This indicates taking the maximum value; , These are the preset upper and lower limits of the processing channel temperature, respectively; For processing channel Real-time temperature; It is a natural exponential function; For processing channel The real-time vibration amplitude; This is the reference vibration amplitude for normal operation.

[0013] This invention constructs a health index calculation model that couples temperature and vibration. It not only defines the safe temperature range but also introduces a nonlinear sensitivity correction for temperature to vibration. Compared with independent monitoring of various indicators, this scheme reflects the physical characteristic that machine tools are more sensitive to vibration under high temperature conditions. It can accurately assess the processing risk of machine tools under complex working conditions of high temperature accompanied by small vibrations. As a result, the system can prioritize the allocation of precision tasks to channels with more stable conditions, which significantly improves the consistency of processing quality.

[0014] Preferably, the formula for calculating the real-time comprehensive status efficiency index of the processing channel is: In the formula, For processing channel Real-time comprehensive status efficiency index; For processing channel Health indicators; It is a natural exponential function; For processing channel Congestion index; This is the preset theoretical maximum congestion level.

[0015] This invention uses health as the efficiency benchmark and congestion as the decay factor to synthesize a real-time comprehensive state efficiency index, ensuring the comprehensiveness of scheduling decisions: when congestion increases, the index decays rapidly; when congestion is light, the index returns to health as the dominant factor; through a dynamic trade-off mechanism, it ensures that the system will neither send workpieces into congested channels nor into idle channels that are in a sub-healthy risk state, thus achieving the best balance between efficiency and safety.

[0016] Preferably, the method further includes: mapping the workpiece waiting area of ​​the machine tool to waiting nodes of the ant colony algorithm, and mapping each processing channel to selectable target nodes.

[0017] Preferably, the task allocation and motion control command output based on the probability includes: selecting a target processing channel for the workpiece using a roulette wheel selection mechanism based on the probability, and outputting corresponding motion control commands to the machine tool control system to drive the workpiece to the target processing channel.

[0018] Preferably, updating the pheromone of the ant colony algorithm based on the actual total time spent in the processing channel includes: calculating the pheromone release amount inversely proportional to the actual total time spent by the workpiece in the processing channel; multiplying the pheromone concentration on the corresponding path before the update by a preset pheromone evaporation factor to obtain the evaporated pheromone; adding the pheromone release amount to the evaporated pheromone to obtain the updated pheromone concentration on the corresponding path; the corresponding path is the path between the waiting node and the node corresponding to the target processing channel.

[0019] This invention uses a closed-loop feedback mechanism based on the actual total time consumed by the workpiece to update the pheromone, which can truly reflect the final effect of the scheduling decision. If a channel slows down for unknown reasons, its actual time increases, the amount of pheromone released decreases, and the probability of subsequent workpieces being assigned to this channel decreases accordingly. This self-correction mechanism gives the system strong robustness and can automatically adapt to environmental disturbances that the model did not predict.

[0020] Preferably, the pheromone release amount is equal to the ratio of a preset pheromone enhancement constant to the actual total time consumed by the workpiece in the target processing channel.

[0021] In a second aspect, the present invention provides a multi-channel combined machine tool motion control system based on swarm intelligence, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned multi-channel combined machine tool motion control method based on swarm intelligence is implemented.

[0022] By adopting the above technical solution, the above-mentioned multi-channel combined machine tool motion control method based on swarm intelligence is generated into a computer program and stored in a memory so that it can be loaded and executed by a processor. In this way, a terminal device can be made based on the memory and the processor for convenient use.

[0023] The beneficial effects of this invention are as follows: This invention acquires real-time queuing status and machine tool health data from each processing channel, constructs a real-time comprehensive status efficiency index as a dynamic correction heuristic, and endows the scheduling algorithm with real-time perception of the physical environment. It can dynamically adjust the workpiece allocation probability according to the current congestion level and health status of the channel, and update the pheromone based on the actual total time consumption, thereby realizing the transformation from static planning to dynamic adaptive scheduling, effectively avoiding the problem of mismatch between task allocation and real-time working conditions, and improving the overall production efficiency. Attached Figure Description

[0024] Figure 1 This is a flowchart illustrating the multi-channel combined machine tool motion control method based on swarm intelligence in this invention; Figure 2 This is a schematic diagram illustrating the load distribution in the channel health-congestion space; Figure 3 The diagram illustrates the cumulative total waiting time for two scheduling strategies. Figure 4 The figure is a schematic diagram illustrating, for example, the performance indicators of a multi-channel control system. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0027] This invention discloses a multi-channel combined machine tool motion control method based on swarm intelligence, referring to... Figure 1 This includes steps S1-S4: S1: Obtain system status data and initialize the ant colony algorithm.

[0028] It should be noted that, in order to overcome the limitation of traditional scheduling algorithms that rely solely on static indicators and cannot respond to the real-time operating conditions of machine tools, it is first necessary to build a digital perception capability for the operating environment of multi-processing channel combined machine tools, mapping the real-time operating conditions of the physical world into state variables that the algorithm can process, thereby providing a data foundation for subsequent dynamic decision-making.

[0029] Specifically, the workpiece waiting area of ​​the machine tool is mapped to the waiting nodes of the ant colony algorithm. Each processing channel is mapped to a selectable target node; the system parameters for the ant colony algorithm are preset, including the total number of processing channels. pheromone factors Heuristic function factor pheromone volatile factors Initial pheromones for all paths and pheromone enhancement constant In this embodiment, and Set to 1.0 and 3.0 to enhance responsiveness to real-time status; Set to 0.1; Set to 10; Set it to 100.

[0030] Furthermore, through industrial IoT platforms and sensor networks, all data in the system can be collected in real time. Status data for each processing channel, the status data including: (1) Queue status data: The processing channel is obtained through position sensors or counters. Current workpiece queue length This refers to the number of workpieces in the waiting queue.

[0031] (2) Machine tool health data: acquired through embedded sensors for machining channels Real-time temperature and real-time vibration amplitude The units are °C and mm / s, respectively. 2 .

[0032] (3) Theoretical time data: The workpiece in the processing channel is obtained according to the process specification. Ideal processing time The unit is seconds (s).

[0033] S2: Based on real-time queuing status data and machine tool health data, evaluate the congestion and health indicators of each processing channel, and construct a real-time comprehensive status efficiency indicator for each processing channel.

[0034] It should be noted that a single physical parameter cannot directly guide scheduling decisions, and congestion cost and health risk differ in terms of scale and physical meaning. Therefore, it is necessary to establish a mathematical model to quantify the congestion level and health status of processing channels separately, and integrate them into a unified efficiency evaluation standard to distinguish the actual carrying capacity of different processing channels at the current moment.

[0035] Specifically, for the processing channel Combined with the current workpiece queue length and ideal processing time The congestion index of the processing channels is calculated to characterize the current queuing pressure of the processing channels. In the calculation, the maximum value of the ideal processing time for all processing channels needs to be determined in advance. And set the critical queue length for congestion. .

[0036] Then processing channel The specific formula for calculating the congestion index is as follows:

[0037] In the formula, For processing channel Congestion index; For processing channel The current workpiece queue length; For the workpiece in the machining channel Ideal processing time; This represents the maximum ideal processing time for all processing channels; It is a natural exponential function; This is the preset congestion threshold queue length.

[0038] Among them, linear terms As a linear benchmark for congestion, it makes the queue length... The longer, and the longer the processing time required The longer the channel, the higher the congestion baseline; the +1 in the denominator is used to ensure numerical stability and normalization; exponent term As a congestion penalty factor, when Exceeding the critical value At that time, the exponential function will make The queuing volume increases exponentially, which demonstrates that in real-time production, oversaturated queuing has a significant negative impact on system efficiency, and the channel must be forcibly cleared through extremely high congestion levels.

[0039] Among them, the preset congestion critical queuing length This is used to define the threshold for a processing channel to enter a congested state. Setting it too low will cause the system to become overly sensitive to normal queuing fluctuations, frequently switching processing channels and causing scheduling oscillations; if... If the setting is too large, congestion risks cannot be identified in a timely manner, leading to queue accumulation; therefore, the preset congestion critical queue length should be set appropriately. The value range is 20% to 40% of the maximum buffer capacity of the processing channel. In this embodiment, Set it to 5.

[0040] Furthermore, regarding the processing channel Combined with real-time temperature and real-time vibration amplitude The health index of the machining channel is calculated to characterize the movement stability of the machining channel in its current healthy state, thereby proactively avoiding risks to machining accuracy and efficiency caused by sub-health conditions; the specific calculation formula is as follows:

[0041] In the formula, For processing channel The health index ranges from 0 to 1. A larger value indicates a healthier channel status and a higher priority. This indicates taking the maximum value; , These are the preset upper and lower limits of the processing channel temperature, respectively; For processing channel Real-time temperature, Used to demonstrate the nonlinear sensitivity of temperature to vibration; It is a natural exponential function; For processing channel The real-time vibration amplitude; This is the reference vibration amplitude for normal operation.

[0042] Among them, the linear terms in the calculation formula This constitutes a temperature-based health baseline, when the real-time temperature... Rise and approach When this value decreases, it indicates a decline in health, thus eliminating the overheating channel; the exponential term in the calculation formula As a vibration penalty factor, when vibration When the value increases, the exponential term decreases, lowering the health index, and the percentage in the denominator decreases. Ensure that the temperature When the temperature rises, even if the vibration amplitude remains unchanged, the denominator of the penalty term increases, making the exponential term smaller overall. This results in a more severe penalty for vibration at high temperatures, preventing the machine tool from continuing to operate under high load in a sub-healthy state. This demonstrates that the machine tool is more sensitive to vibration at high temperatures.

[0043] Among them, the preset upper limit of the processing channel temperature and lower limit This is used to define the safe operating temperature range of the machine tool. If the range is set too narrowly, it will drastically reduce the number of available machining channels, decreasing system throughput; if the range is set too wide, it will fail to protect the machine tool and increase the risk of failure. Therefore, in other embodiments, the implementer can set it according to the machine tool model and the characteristics of the processed material. In this embodiment, Set to 60 degrees Celsius, Set to 20 degrees Celsius.

[0044] Among them, the reference vibration amplitude during normal operation Used to measure the degree of vibration abnormality, if If the setting is too low, the system will misinterpret normal processing vibrations as faults, leading to false alarms; if If the setting is too large, minute mechanical wear cannot be detected; therefore, the reference vibration amplitude... The value range is from 0.5 to 1.5 mm / s 2 In this embodiment, Set to 0.8 mm / s 2 .

[0045] Finally, using the health index as the efficiency benchmark and the congestion index as the decay factor, a real-time comprehensive status efficiency index for the processing channel is constructed. The specific calculation formula is as follows:

[0046] In the formula, For processing channel Real-time comprehensive status efficiency index; For processing channel Health indicators; It is a natural exponential function; For processing channel Congestion index; This is the preset theoretical maximum congestion level.

[0047] Among these, health is a prerequisite for scheduling optimization; therefore, the health index is used... As a benchmark for efficiency; the exponential term As a decay factor for the congestion index: when the channel congestion index As the exponential term increases, it rapidly approaches zero, causing the real-time integrated state efficiency index to... A sharp decline occurs when the congestion index of the congestion channel decreases. When the value is small, the exponent term is close to 1. near Scheduling is primarily based on the health status of the machine tools.

[0048] Among them, the preset theoretical maximum congestion level The weights used to control the impact of congestion on overall efficiency, if If the setting is too small, congestion factors will dominate, and the system will tend to load balance but may ignore health risks; if... Setting the congestion level too high can dilute the impact of congestion and potentially lead to queue buildup; therefore, the theoretical maximum congestion level should be set accordingly. The value range is from 30 to 80. In this embodiment, the value will be... Set it to 50.

[0049] For example, Figure 2This diagram illustrates the load distribution in the channel health-congestion space. The scatter plot shows the initial health and congestion distributions of each channel, and uses bubble sizes to compare the final load allocation of the two strategies. For the sub-healthy channel (channel 2), with a low health value, the load allocated by this invention is significantly less than that allocated by the prior art, reflecting the present invention's strategy of actively avoiding sub-healthy channels. Conversely, for the highly efficient healthy channel (channel 3), with a high health value and the shortest ideal time, the load allocated by this invention is significantly greater than that allocated by the prior art, reflecting the present invention's strategy of prioritizing the use of efficient machine tools. In summary, this demonstrates that the modified heuristic information of this invention can transfer the workpiece's load allocation from sub-healthy resources to highly efficient healthy resources, achieving refined resource management and load balancing based on the real-time channel status.

[0050] S3: The comprehensive state efficiency index is used as a dynamic correction heuristic and integrated into the channel selection probability calculation formula of the ant colony algorithm to calculate the probability of the workpiece selecting the processing channel from the waiting node.

[0051] It should be noted that traditional ant colony algorithms typically use static heuristic information, which cannot respond to real-time environmental changes, resulting in delayed scheduling decisions. This step introduces the real-time comprehensive state efficiency index calculated in step S2 to construct dynamically corrected heuristic information, giving the algorithm the ability to perceive and adapt to environmental changes in real time.

[0052] Specifically, the real-time comprehensive state efficiency index As a dynamic correction heuristic for ant colony algorithms ,Right now .

[0053] Furthermore, regarding the workpiece Calculate its value from the waiting node Select processing channel The probability is calculated using the following formula:

[0054] In the formula, For workpiece From waiting node Select processing channel The probability of; For path Current time The accumulated pheromone concentration; The preset pheromone factor; For processing channel Real-time comprehensive status efficiency index; This is a preset heuristic function factor; For workpiece The current set of available processing channels; For set Any processing channel in the process; For path Current time The accumulated pheromone concentration; For processing channel Real-time comprehensive status efficiency index.

[0055] The calculation formula combines historical experience with the current state: This represents the historically preferred path. This represents the current real-time operating condition, ensuring that scheduling decisions are influenced by both the channel's historical performance and its real-time efficiency; probability. Size and and All are positively correlated, thus guiding the workpiece to prioritize processing channels that have historically performed well and are currently in good condition.

[0056] S4: Assign tasks based on probability and output motion control commands, and update the pheromone of the ant colony algorithm based on the actual total processing time of the processing channel.

[0057] It should be noted that the closed-loop control of the algorithm relies on the continuous updating of pheromones and strengthens high-quality paths through a positive feedback mechanism, thereby approaching the global optimum over a long period of time. This step uses actual processing data to adjust the pheromones, realizing a complete control closed loop from decision-making to feedback.

[0058] Specifically, based on the probability calculated in step S3, a roulette wheel betting mechanism is used to determine the workpiece. Select target processing channel It also outputs corresponding motion control commands to the machine tool control system to drive the workpiece to the target processing channel.

[0059] Furthermore, when the workpiece In the target processing channel After the processing is completed, obtain the actual total time spent. That is, the sum of waiting time and actual processing time; and the path The pheromones on the surface are updated, including: First, calculate the pheromone release amount for this task. The specific calculation formula is as follows:

[0060] In the formula, For workpiece In the path The amount of pheromones released; The preset pheromone enhancement constant; For workpiece In the processing channel The actual total time spent.

[0061] The formula shows that the amount of pheromone released is inversely proportional to the actual total time consumed. The smaller the hour, the more pheromones are released. The more efficient the path, the stronger the positive feedback reward.

[0062] Then, a global pheromone update is performed, the specific calculation formula is as follows:

[0063] In the formula, For the updated path The concentration of pheromones on the surface; The preset pheromone evaporation factor; The path before the update The concentration of pheromones on the surface; For workpiece In the path The amount of pheromones released.

[0064] The calculation formula uses the volatile factor. By attenuating old pheromones and simultaneously adding new pheromones, the algorithm prevents pheromone accumulation indefinitely and ensures that it has the ability to continuously explore new paths. This feedback mechanism based on the actual total time consumption further enhances the adaptability of the scheduling strategy.

[0065] For example, Figure 3 This diagram illustrates the cumulative total waiting time for two scheduling strategies. The line graph shows the growth trend of the cumulative total waiting time during continuous workpiece allocation. The slope of the cumulative waiting time curve (red line) corresponding to this invention is significantly lower than that of the gray line in the prior art. This trend demonstrates that this invention can continuously optimize scheduling decisions, effectively preventing the accumulation of waiting time and the occurrence of workpiece flow bottlenecks. Furthermore, the difference between the red line and the gray line represents the total waiting time saved by this invention throughout the entire production cycle, reflecting a long-term stable performance improvement.

[0066] For example, Figure 4This diagram illustrates the performance indicators of multi-channel control. Using a radar chart, it compares the overall performance of the present invention with that of existing technologies in three core indicators: total workpiece completion time, total workpiece waiting time, and channel load balancing. All axial indicators are normalized to the principle of "the smaller the better," with larger areas indicating better performance. The polygonal area of ​​the red region corresponding to the present invention is significantly larger than the gray dashed area corresponding to the existing technology, demonstrating that the dynamic scheduling strategy of the present invention comprehensively surpasses existing technologies in terms of efficiency and load balancing, achieving a comprehensive improvement in multi-channel control performance.

[0067] This invention also discloses a multi-channel combined machine tool motion control system based on swarm intelligence, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the multi-channel combined machine tool motion control method based on swarm intelligence according to this invention is implemented.

[0068] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

Claims

1. A multi-channel combined machine tool motion control method based on swarm intelligence, characterized in that, include: Acquire system status data and initialize the ant colony algorithm. The status data includes real-time queuing status data and machine tool health data for each processing channel. Based on the real-time queuing status data and machine tool health data, the congestion index and health index of each processing channel are evaluated, and a real-time comprehensive status efficiency index of each processing channel is constructed. The comprehensive state efficiency index is used as a dynamic correction heuristic and is incorporated into the channel selection probability calculation formula of the ant colony algorithm to calculate the probability that the workpiece selects the processing channel from the waiting node. Tasks are assigned and motion control commands are output based on the probability, and the pheromone of the ant colony algorithm is updated based on the actual total time consumed by the processing channel.

2. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 1, characterized in that, The machine tool health data includes the real-time temperature and real-time vibration amplitude of the machining channel.

3. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 2, characterized in that, The formula for calculating the congestion index of the processing channel is: ； In the formula, For processing channel Congestion index; For processing channel The current workpiece queue length; For the workpiece in the machining channel Ideal processing time; This represents the maximum ideal processing time for all processing channels; It is a natural exponential function; This is the preset congestion threshold queue length.

4. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 2, characterized in that, The formula for calculating the health index of the processing channel is: ； In the formula, For processing channel Health indicators; This indicates taking the maximum value; , These are the preset upper and lower limits of the processing channel temperature, respectively; For processing channel Real-time temperature; It is a natural exponential function; For processing channel The real-time vibration amplitude; This is the reference vibration amplitude for normal operation.

5. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 1, characterized in that, The formula for calculating the real-time comprehensive status efficiency index of the processing channel is: ； In the formula, For processing channel Real-time comprehensive status efficiency index; For processing channel Health indicators; It is a natural exponential function; For processing channel Congestion index; This is the preset theoretical maximum congestion level.

6. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 1, characterized in that, The method further includes: mapping the workpiece waiting area of ​​the machine tool to waiting nodes of the ant colony algorithm, and mapping each processing channel to selectable target nodes.

7. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 6, characterized in that, Based on the stated probability, tasks are allocated and motion control commands are output, including: Based on the probability, a roulette wheel selection mechanism is used to select the target processing channel for the workpiece, and corresponding motion control commands are output to the machine tool control system to drive the workpiece to be transported to the target processing channel.

8. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 7, characterized in that, The step of updating the pheromone in the ant colony algorithm based on the actual total processing time of the processing channel includes: Calculate the pheromone release amount, which is inversely proportional to the actual total time spent by the workpiece in the processing channel; multiply the pheromone concentration on the corresponding path before the update by a preset pheromone evaporation factor to obtain the pheromone after evaporation; add the pheromone release amount to the evaporated pheromone to obtain the pheromone concentration on the corresponding path after the update; the corresponding path is the path between the waiting node and the node corresponding to the target processing channel.

9. The multi-channel combined machine tool motion control method based on swarm intelligence according to claim 8, characterized in that, The pheromone release amount is equal to the ratio of the preset pheromone enhancement constant to the actual total time spent by the workpiece in the target processing channel.

10. A multi-channel combined machine tool motion control system based on swarm intelligence, characterized in that, include: A processor and a memory, wherein the memory stores computer program instructions that, when executed by the processor, implement the multi-channel combined machine tool motion control method based on swarm intelligence according to any one of claims 1-9.

Images