A distributed manufacturing resource intelligent scheduling method and system

Abstract

The present application relates to the technical field of distributed manufacturing resource intelligent scheduling, and particularly relates to a distributed manufacturing resource intelligent scheduling method and system, the method comprising the following steps: obtaining equipment operation state data and workpiece quality data; based on the equipment operation state data and the workpiece quality data, evaluating the equipment performance degradation degree; according to the equipment performance degradation degree, correcting the equipment capability parameters in the scheduling system; before task allocation, based on the equipment performance degradation degree and the task requirements, generating task risk assessment information; according to the task risk assessment information, assisting the dispatcher to make task allocation decisions. The above can improve the intelligent level of the scheduling system and the accuracy of the decisions.

Description

Technical Field

[0001] This invention relates to the technical field of intelligent scheduling of distributed manufacturing resources, and specifically to a method and system for intelligent scheduling of distributed manufacturing resources. Background Technology

[0002] In modern industrial production systems, managing geographically dispersed production facilities with diverse equipment to improve efficiency, control costs, and ensure on-time delivery is a significant challenge. Distributed manufacturing resource intelligent scheduling methods are widely used to address these issues, with their core being the efficient and rational allocation of tasks and arrangement of production processes. However, in many practically deployed distributed manufacturing systems, the operational status information of core processing equipment, a key input to intelligent scheduling methods, often suffers from inherent limitations in its update mechanism. These status updates primarily rely on built-in hard fault alarms or periodic manual inspections and data entry by on-site operators. This reliance can lead to a lag in the scheduling system's understanding of equipment status, making it difficult to reflect subtle changes in equipment operation in real time, especially when equipment performance undergoes gradual degradation. Summary of the Invention

[0003] The purpose of this invention is to address the aforementioned shortcomings by proposing a distributed intelligent scheduling method and system for manufacturing resources.

[0004] The present invention adopts the following technical solution:

[0005] A distributed intelligent scheduling method for manufacturing resources, comprising the following steps:

[0006] Acquire equipment operating status data and workpiece quality data;

[0007] Based on equipment operating status data and workpiece quality data, assess the degree of equipment performance degradation;

[0008] Adjust the equipment capability parameters within the scheduling system according to the degree of equipment performance degradation;

[0009] Before task assignment, task risk assessment information is generated based on the degree of equipment performance degradation and task requirements;

[0010] Based on task risk assessment information, assist the scheduler in making task allocation decisions;

[0011] The steps for assessing the degree of equipment performance degradation based on equipment operating status data and workpiece quality data include: acquiring multi-source processing signals of equipment operation; processing the multi-source processing signals of equipment operation to obtain real-time processing response characteristics; acquiring the material response characteristic pattern of the new alloy material; the material response characteristic pattern of the new alloy material characterizes the subsurface micro-defects caused by the interaction between equipment latent degradation and material properties; comparing the real-time processing response characteristics with the material response characteristic pattern of the new alloy material to predict the risk of internal defects; and comprehensively assessing the degree of equipment performance degradation by combining the risk of internal defects with the degree of equipment vibration deviation and the degree of workpiece surface quality deviation.

[0012] Through this technical solution, this application can perceive the implicit degradation of equipment performance in real time and incorporate it into scheduling decisions, thereby avoiding scheduling errors caused by the lag in equipment status perception. It effectively solves the problems of untimely equipment status updates and lack of correlation analysis between quality data and equipment status data in the prior art, and significantly improves the intelligence level and decision accuracy of the scheduling system.

[0013] Furthermore, the steps for adjusting the equipment capacity parameters within the scheduling system based on the degree of equipment performance degradation include:

[0014] To obtain microstructural characteristics and mechanical properties data of the current batch of novel materials;

[0015] The microstructure characteristics and mechanical properties of the current batch of new materials are compared with the preset material property benchmarks to identify the degree of deviation of the properties of the current batch of materials.

[0016] Based on the degree of deviation of the characteristics of the current batch of materials, dynamically adjust the weighting coefficients or adjustment factors used to correct the equipment capacity parameters;

[0017] By using the adjusted weighting coefficients or adjustment factors, and in conjunction with the degree of equipment performance degradation, the equipment capability parameters within the scheduling system are corrected.

[0018] Furthermore, before task allocation, the steps for generating task risk assessment information based on the degree of equipment performance degradation and task requirements include:

[0019] Identify the location of the tasks to be assigned in the product manufacturing process and their dependencies on subsequent processes;

[0020] Predict the potential delays or quality non-conformities that may occur when assigned tasks are executed on the equipment;

[0021] Based on the position of the task to be assigned in the product production process and its dependence on subsequent processes, calculate the impact of delay time or quality non-conformity rate on the start time and completion time of subsequent processes and product delivery cycle.

[0022] The impact will be quantified as a risk score for the transmission effect along the production chain and incorporated into the task risk assessment information.

[0023] Furthermore, the steps for acquiring equipment operating status data and workpiece quality data include:

[0024] High-sensitivity piezoelectric accelerometers and high-precision acoustic emission sensors are deployed in key parts of the core processing equipment to collect minute vibration signals and acoustic emission signals generated during equipment operation;

[0025] Real-time digital filtering processing of minute vibration signals and acoustic emission signals;

[0026] Time-domain and frequency-domain features are extracted from filtered minute vibration signals.

[0027] Time-domain and frequency-domain features are extracted from the filtered acoustic emission signal.

[0028] The extracted vibration features and acoustic emission features are fused to form equipment operating status data;

[0029] An online optical inspection system and a coordinate measuring machine are deployed at the end of the production line to perform real-time inspection on each finished workpiece and obtain the workpiece's dimensional deviation and surface roughness data. The obtained dimensional deviation and surface roughness data are the workpiece quality data.

[0030] By using a unique workpiece identifier, the real-time detected workpiece quality data can be accurately correlated with the operating status data of the equipment that processes the workpiece.

[0031] Furthermore, the steps of fusing the extracted vibration features and acoustic emission features to form equipment operating status data include:

[0032] Obtain the current operating mode information of the device;

[0033] Based on the current working mode information of the equipment, obtain the vibration feature fusion weight and acoustic emission feature fusion weight corresponding to the current working mode from the preset working mode and fusion weight mapping rules;

[0034] By using vibration feature fusion weights and acoustic emission feature fusion weights, the extracted vibration features and acoustic emission features are weighted and fused to form equipment operating status data.

[0035] Furthermore, the steps of fusing the extracted vibration features and acoustic emission features to form equipment operating status data include:

[0036] When switching the device's operating mode, obtain the operating mode information before the switch and the operating mode information after the switch;

[0037] Based on the working mode information before and after the switch, determine the transition phase of the working mode switch.

[0038] During the transition phase of switching working modes, a time decay-based weighted fusion strategy is adopted to interpolate the fusion weights corresponding to the working modes before and after the switch to obtain the transition fusion weights.

[0039] By using transition fusion weights, the extracted vibration features and acoustic emission features are weighted and fused to form equipment operating status data.

[0040] Furthermore, before task allocation, the steps for generating task risk assessment information based on the degree of equipment performance degradation and task requirements include:

[0041] Obtain the specific threshold values ​​for the product's microstructure or surface morphology as required by the task;

[0042] Based on the degree of equipment performance degradation and specific index thresholds, predict the types of subsurface defects and the risk level of internal stress concentration generated during processing;

[0043] Obtain the correlation rules between long-term product reliability or specific functions and subsurface defect types and internal stress concentration risk levels;

[0044] Based on association rules, the impact of subsurface defect types and internal stress concentration risk levels on the long-term reliability or specific functions of the product is quantified.

[0045] The quantified impact is used as a latent defect risk score and integrated into the task risk assessment information.

[0046] Furthermore, the steps to incorporate the quantified impact as a latent defect risk score into the task risk assessment information include:

[0047] Obtain information on the types of latent defects contained in the quantified impact;

[0048] Based on the information on the type of latent defect, obtain the risk presentation granularity or dimension corresponding to the latent defect type from the preset defect type and risk presentation rules;

[0049] Based on the granularity or dimension of risk presentation, the quantitative impact is transformed to generate a latent defect risk score with a specific granularity or dimension;

[0050] Incorporate latent defect risk scores with specific granularity or dimensions into the task risk assessment information.

[0051] This application also discloses a distributed manufacturing resource intelligent scheduling system, applied to a distributed manufacturing resource intelligent scheduling method, the system comprising:

[0052] The acquisition module is used to acquire equipment operating status data and workpiece quality data;

[0053] The performance evaluation module assesses the degree of equipment performance degradation based on equipment operating status data and workpiece quality data.

[0054] The correction module adjusts the equipment capability parameters within the scheduling system based on the degree of equipment performance degradation.

[0055] The risk assessment module generates task risk assessment information based on the degree of equipment performance degradation and task requirements before task allocation;

[0056] The auxiliary module assists the scheduler in making task allocation decisions based on task risk assessment information.

[0057] The steps for assessing the degree of equipment performance degradation based on equipment operating status data and workpiece quality data include: acquiring multi-source processing signals of equipment operation; processing the multi-source processing signals of equipment operation to obtain real-time processing response characteristics; acquiring the material response characteristic pattern of the new alloy material; the material response characteristic pattern of the new alloy material characterizes the subsurface micro-defects caused by the interaction between equipment latent degradation and material properties; comparing the real-time processing response characteristics with the material response characteristic pattern of the new alloy material to predict the risk of internal defects; and comprehensively assessing the degree of equipment performance degradation by combining the risk of internal defects with the degree of equipment vibration deviation and the degree of workpiece surface quality deviation.

[0058] Through this technical solution, this application provides a system capable of implementing the above-mentioned intelligent scheduling method for distributed manufacturing resources. Through modular design, the system can effectively integrate various functions, providing hardware and software support for practical applications. This enables more accurate perception, evaluation, and scheduling decision assistance for equipment performance degradation, significantly improving the overall operating efficiency and reliability of the distributed manufacturing system.

[0059] This application achieves more refined and intelligent scheduling management of distributed manufacturing resources by introducing equipment performance degradation assessment and task risk assessment mechanisms. This method overcomes the shortcomings of existing technologies, such as delayed updates of equipment status information, lack of effective correlation between quality data and equipment status data, and fragile scheduling decisions. It significantly improves the decision-making accuracy and robustness of the scheduling system, effectively reduces production costs and resource consumption, and enhances customer satisfaction and corporate reputation.

[0060] To further understand the features and technical content of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are for reference and illustration only and are not intended to limit the present invention. Attached Figure Description

[0061] Figure 1 This is a flowchart of a distributed intelligent scheduling method for manufacturing resources according to the present invention;

[0062] Figure 2 This is a schematic diagram of the structure of a distributed intelligent scheduling system for manufacturing resources according to the present invention. Detailed Implementation

[0063] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. Furthermore, the accompanying drawings of the present invention are for simple illustrative purposes only and are not depictions of actual dimensions; this is stated in advance. The following embodiments will further describe the relevant technical content of the present invention in detail, but the disclosed content is not intended to limit the scope of protection of the present invention.

[0064] This embodiment provides a distributed intelligent scheduling method and system for manufacturing resources, combined with... Figure 1 and Figure 2 As shown.

[0065] refer to Figure 1 A distributed intelligent scheduling method for manufacturing resources, comprising the following steps:

[0066] Acquire equipment operating status data and workpiece quality data;

[0067] Based on equipment operating status data and workpiece quality data, assess the degree of equipment performance degradation;

[0068] Adjust the equipment capability parameters within the scheduling system according to the degree of equipment performance degradation;

[0069] Before task assignment, task risk assessment information is generated based on the degree of equipment performance degradation and task requirements;

[0070] Based on task risk assessment information, assist the scheduler in making task allocation decisions;

[0071] The steps for assessing the degree of equipment performance degradation based on equipment operating status data and workpiece quality data include: acquiring multi-source processing signals of equipment operation; processing the multi-source processing signals of equipment operation to obtain real-time processing response characteristics; acquiring the material response characteristic pattern of the new alloy material; the material response characteristic pattern of the new alloy material characterizes the subsurface micro-defects caused by the interaction between equipment latent degradation and material properties; comparing the real-time processing response characteristics with the material response characteristic pattern of the new alloy material to predict the risk of internal defects; and comprehensively assessing the degree of equipment performance degradation by combining the risk of internal defects with the degree of equipment vibration deviation and the degree of workpiece surface quality deviation.

[0072] Among them, "equipment operating status data" refers to various real-time or near-real-time data reflecting the current working status of the equipment, such as vibration signals, acoustic emission signals, temperature, current, and voltage. These data can characterize the health status and operational stability of the equipment from different dimensions. "Workpiece quality data" refers to the inspection data of the finished workpiece in terms of dimensional accuracy, surface roughness, and microstructure. This data directly reflects the equipment's processing capacity and product quality. "Equipment performance degradation degree" is a quantitative assessment of the degree to which the equipment's current processing capacity has decreased relative to its design or initial performance. It may manifest as decreased processing accuracy, reduced efficiency, and increased failure risk. "Equipment capability parameters within the scheduling system" are the equipment performance indicators that the scheduling system uses for task allocation and production scheduling, such as maximum processing speed, minimum processing time, and the highest achievable accuracy level. The accuracy of these parameters directly affects the effectiveness of scheduling decisions. "Task risk assessment information" is a comprehensive quantitative description of the various risks (such as delays, quality defects, and increased costs) that a specific task may face when executed on a specific piece of equipment.

[0073] In one implementation, the distributed manufacturing resource intelligent scheduling method first requires acquiring equipment operating status data and workpiece quality data. Equipment operating status data can be acquired by installing various sensors on key parts of the equipment. For example, accelerometers can be deployed to collect vibration signals from the equipment, or acoustic emission sensors can be deployed to capture sound wave signals generated by internal friction, crack propagation, etc. These sensors can continuously and in real time collect data. Workpiece quality data can be acquired by setting up online inspection equipment at the end of the production line. For example, optical inspection systems can be used to inspect the surface quality of workpieces, or coordinate measuring machines can be used to measure the dimensional accuracy of workpieces. After these data are collected, they typically undergo preliminary data cleaning and preprocessing to remove noise and outliers, ensuring the accuracy and reliability of the data. For example, digital filters can be used to filter the acquired raw signals to eliminate high-frequency noise interference.

[0074] Subsequently, based on the acquired equipment operating status data and workpiece quality data, the degree of equipment performance degradation is assessed. This can be achieved by establishing an equipment performance model. For example, machine learning algorithms can be used to train a predictive model that outputs the equipment performance degradation index, taking equipment operating status data (such as vibration spectrum characteristics and acoustic emission energy) and workpiece quality data (such as dimensional deviations and surface roughness) as input. This model can learn the complex nonlinear relationship between equipment operating characteristics and actual processing quality. For example, when there is an increase in energy at a specific frequency in the equipment's vibration signal, accompanied by a deterioration in the workpiece surface roughness index, the model can identify potential performance degradation such as bearing wear or tool wear.

[0075] Next, based on the assessed degree of equipment performance degradation, the equipment capacity parameters within the scheduling system are adjusted. For example, if the assessment shows a slight decrease in the processing accuracy of a certain piece of equipment, the "maximum achievable accuracy" parameter recorded in the scheduling system should be lowered accordingly. If the equipment's operating efficiency decreases, its "productivity per unit time" parameter should also be adjusted. This adjustment can be linear or non-linear, depending on the mapping relationship between the degree of performance degradation and the capacity parameters. For example, a preset correction factor table can be used to adjust the equipment capacity parameters by a percentage according to different degradation levels.

[0076] Before task assignment, task risk assessment information is generated based on the degree of equipment performance degradation and task requirements. Task requirements may include specific indicators such as machining accuracy, surface quality, and delivery time. For example, if a task requires extremely high machining accuracy, and the equipment to be assigned is assessed as having moderate performance degradation, then the quality risk of performing the task on that equipment will be assessed as high. Task risk assessment information can be a comprehensive risk score or a risk report containing multiple dimensions (such as quality risk, delay risk, and cost risk). For example, a risk assessment model can be built, taking into input parameters such as the degree of equipment performance degradation, the accuracy requirements of the task, and the urgency of the task, and outputting a quantified task risk index.

[0077] Finally, the generated task risk assessment information assists schedulers in making task allocation decisions. When allocating tasks, schedulers no longer rely solely on the surface-level "normal / faulty" status of equipment, but gain deeper insights into the actual processing capabilities and potential risks of the equipment. For example, when the scheduling system recommends assigning a high-precision task to a particular piece of equipment, if the task risk assessment information indicates a high quality risk, the scheduler can choose to assign the task to a more stable piece of equipment or implement additional quality control measures. This decision-making assistance mechanism enables schedulers to make more informed and robust decisions, thereby avoiding production delays and quality problems caused by hidden equipment degradation.

[0078] The distributed intelligent scheduling method for manufacturing resources proposed in this application significantly improves the depth and breadth of the scheduling system's perception of the status of manufacturing resources by introducing real-time and refined assessment of the degree of equipment performance degradation and combining it with task requirements to generate task risk assessment information.

[0079] Specifically, traditional scheduling methods, when faced with latent problems such as slight increases in spindle bearing clearance, may misjudge the equipment as being in a "normal" state because the fault alarm threshold has not been reached, and assign tasks based on this misjudgment. This could lead to high-precision tasks being assigned to equipment with impaired actual processing capabilities, ultimately resulting in substandard product quality and production delays. This application, by acquiring equipment operating status data (such as minute vibration signals) and workpiece quality data (such as minor dimensional deviations), and assessing the degree of equipment performance degradation based on this data, can promptly identify latent problems in the equipment. For example, when the system detects an abnormal increase in energy in a specific frequency band of the equipment vibration signal, and this increase is correlated with the dimensional deviation of the workpiece, it can be determined that the equipment performance is degrading.

[0080] Furthermore, this application dynamically adjusts the equipment capability parameters within the scheduling system based on the assessed degree of equipment performance degradation. This means that when the machining accuracy or efficiency of a piece of equipment decreases due to performance degradation, the corresponding parameters within the scheduling system will be adjusted in a timely manner, thereby ensuring that subsequent task allocation is based on the actual capabilities of the equipment, rather than idealized ones. For example, if the accuracy assessment result of a CNC machine tool shows that it can no longer meet the machining requirements of the highest accuracy level, its "maximum achievable accuracy" parameter in the scheduling system will be lowered to avoid assigning it tasks with extremely high accuracy requirements.

[0081] Furthermore, this application generates task risk assessment information based on the degree of equipment performance degradation and task requirements before task allocation. This allows schedulers to obtain a more comprehensive risk view when making decisions. For example, for an urgent order with strict delivery time requirements and involving multiple high-precision processes, this application not only considers the current load and availability of the equipment but also combines the degree of equipment performance degradation to predict the potential delay time or quality non-conformity rate when the task is executed on that equipment, quantifying it as a risk score for the transmission effect across the production chain. This risk assessment information can assist schedulers in making more informed decisions. For example, even if a piece of equipment is currently idle, if its task risk assessment information indicates a high quality risk, the scheduler may choose to allocate it to another piece of equipment with more stable performance or take additional quality control measures, thereby effectively avoiding production accidents and decreased customer satisfaction caused by hidden equipment problems.

[0082] Specifically, acquiring multi-source processing signals during equipment operation refers to the real-time acquisition of various physical signals generated by the equipment during processing through various sensors deployed on the equipment, such as, but not limited to, acoustic emission sensors, vibration sensors, force sensors, and temperature sensors. These signals can reflect the operating status of the equipment and the dynamic changes in the processing process from different dimensions. Processing these multi-source processing signals to obtain real-time processing response characteristics can be understood as preprocessing, feature extraction, and feature fusion of the acquired raw multi-source signals. Preprocessing includes operations such as noise reduction and filtering; feature extraction can employ time-domain, frequency-domain, or time-frequency-domain analysis methods to obtain statistical or spectral characteristics of the signal, such as energy, amplitude, frequency, kurtosis, and margin; feature fusion aims to integrate effective information from different types of signals to form real-time processing response characteristics that comprehensively characterize the current processing state. In practical applications, acquiring the material response characteristic patterns of novel alloy materials is crucial. These patterns characterize the subsurface micro-defects caused by the interaction between equipment latent degradation and material properties. This involves establishing a correlation model between the internal microstructure (e.g., grains, phase transformations, dislocations) and subsurface defects (e.g., microcracks, pores, residual stress) of the novel alloy material under different processing conditions and equipment degradation states, based on prior experiments, simulations, or expert knowledge, and the signal response during processing. This model serves as a benchmark to identify potential latent degradation that may occur when processing novel alloy materials. Furthermore, comparing real-time processing response characteristics with the material response characteristic patterns of novel alloy materials to predict internal defect risks involves matching or analyzing the differences between the current real-time processing response characteristics and preset material response characteristic patterns using pattern recognition, machine learning algorithms, or statistical analysis methods. When real-time characteristics deviate significantly from the normal pattern, it indicates that the equipment may be inducing or exacerbating subsurface micro-defects in the novel alloy material, thus predicting potential internal defect risks. Therefore, comprehensively assessing the degree of equipment performance degradation by integrating internal defect risk with the degree of equipment vibration deviation and workpiece surface quality deviation involves using the predicted internal defect risk as an important assessment indicator, and weighting and fusing it with traditional indicators such as the degree of equipment vibration deviation (e.g., abnormal vibration levels obtained through vibration sensor data analysis) and the degree of workpiece surface quality deviation (e.g., surface roughness, dimensional deviations, etc., obtained through online optical inspection systems and coordinate measuring machines). This comprehensive assessment can more fully and accurately reflect the overall performance degradation of the equipment, including both explicit and implicit degradation.

[0083] This application's solution, by introducing the acquisition and processing of multi-source machining process signals during equipment operation, can capture the microscopic dynamic changes of the equipment more meticulously during processing. In particular, by acquiring the material response characteristic patterns of novel alloy materials and comparing them with real-time machining response characteristics, the system can identify latent equipment degradation that is difficult to detect using traditional methods—namely, subsurface microscopic defects caused by the interaction between the equipment and the novel alloy materials. This prediction of latent defect risk compensates for the shortcomings of assessments relying solely on equipment vibration and workpiece surface quality, as many critical defects may first form within the material or at the subsurface level, without being apparent externally. Finally, by integrating internal defect risk with the explicit deviations in equipment vibration and workpiece surface quality, the assessment of equipment performance degradation is both comprehensive and in-depth, thus providing a more reliable basis for subsequent scheduling decisions.

[0084] In some preferred embodiments, it is assumed that a distributed manufacturing system is processing a novel titanium alloy material used in the aerospace field. First, high-frequency vibration sensors, acoustic emission sensors, and cutting force sensors deployed on the spindle, cutting tool, and workpiece fixture of the processing equipment are used to collect multi-source processing signals in real time. These signals are transmitted to a data processing unit, where they undergo digital filtering, wavelet transform, and other processing to extract real-time processing response characteristics in the time domain, frequency domain, and time-frequency domain, such as vibration energy spectrum, acoustic emission event rate, and cutting force fluctuation amplitude. Simultaneously, the system has pre-established a correlation model between the internal grain structure changes and microcrack initiation of the novel titanium alloy material under different cutting parameters and tool wear conditions and the aforementioned processing response characteristics—that is, the material response characteristic mode of the novel alloy material—through extensive experiments and finite element simulations. When the real-time processing response characteristics deviate significantly from this mode, for example, abnormal peaks at specific frequencies appear in the acoustic emission signals, or the cutting force fluctuation mode does not conform to the normal processing mode, the system predicts the existence of internal defect risks, such as subsurface intergranular cracks or uneven phase transformation. Subsequently, the internal defect risk is quantified into a risk score and comprehensively weighted with the degree of equipment vibration deviation detected by traditional methods (e.g., excessive vibration amplitude of the spindle bearing) and the degree of workpiece surface quality deviation (e.g., excessive surface roughness detected by an online optical inspection system). For example, the weight of internal defect risk can be set to 0.5, vibration deviation to 0.3, and surface quality deviation to 0.2, ultimately calculating a comprehensive equipment performance degradation index. This index will serve as an important basis for the scheduling system to correct equipment capability parameters and generate task risk assessment information, ensuring the processing quality and reliability of new titanium alloy workpieces.

[0085] This application further proposes steps for adjusting the equipment capability parameters within the scheduling system based on the degree of equipment performance degradation, including:

[0086] To obtain microstructural characteristics and mechanical properties data of the current batch of novel materials;

[0087] The microstructure characteristics and mechanical properties of the current batch of new materials are compared with the preset material property benchmarks to identify the degree of deviation of the properties of the current batch of materials.

[0088] Based on the degree of deviation of the characteristics of the current batch of materials, dynamically adjust the weighting coefficients or adjustment factors used to correct the equipment capacity parameters;

[0089] By using the adjusted weighting coefficients or adjustment factors, and in conjunction with the degree of equipment performance degradation, the equipment capability parameters within the scheduling system are corrected.

[0090] Specifically, obtaining the microstructural characteristics and mechanical properties of the current batch of novel materials refers to acquiring microstructural information such as grain size, phase composition, and crystal structure using specialized material testing equipment, such as scanning electron microscopes, transmission electron microscopes, and X-ray diffractometers; and simultaneously, acquiring mechanical properties such as tensile strength, yield strength, elongation, hardness, and toughness using equipment such as tensile testing machines, hardness testers, and impact testing machines. These data comprehensively characterize the intrinsic properties of the current batch of novel materials and form the basis for evaluating their processing performance.

[0091] This process involves comparing the microstructure and mechanical properties of the current batch of novel materials with preset material property benchmarks to identify the degree of deviation from the current batch's characteristics. The preset material property benchmarks can be understood as the range of microstructure and mechanical property parameters of the novel material under ideal conditions or in a standard batch. Through comparison, the differences between the current batch and the standard benchmarks can be quantified, such as increases or decreases in grain size or hardness. These deviations directly affect the material's processing behavior and the quality of the final product.

[0092] In practical applications, the weighting coefficients or adjustment factors used to correct equipment capability parameters are dynamically adjusted based on the degree of deviation of the current batch of materials' characteristics. These weighting coefficients or adjustment factors are multipliers or additives used to quantify the impact of equipment performance degradation on equipment capability parameters. For example, if the hardness of the current batch of materials is higher than the benchmark, even with the same degree of equipment performance degradation, its impact on the processing may be greater. In this case, the weighting coefficient can be increased to make the correction effect of equipment performance degradation on equipment capability parameters more significant. Conversely, if the material characteristics deviate to make it easier to process, the weighting coefficient can be decreased. This dynamic adjustment ensures the flexibility and adaptability of the correction process.

[0093] Therefore, by using the adjusted weighting coefficients or adjustment factors, combined with the degree of equipment performance degradation, the equipment capability parameters within the scheduling system are corrected. This means that the final equipment capability parameter correction no longer depends solely on the equipment's own degradation state, but comprehensively considers the coupling effect between equipment degradation and the deviation of the current batch of material characteristics, thus obtaining a more accurate and realistic equipment capability assessment.

[0094] In some preferred embodiments, suppose a distributed manufacturing system needs to process a batch of new high-strength alloy materials. First, metallographic analysis and tensile tests are performed on this batch of alloy materials to obtain microstructural characteristics and mechanical property data, such as grain size, hardness, and tensile strength. For example, the test results show that the average grain size of this batch of materials is 10% smaller than the standard benchmark, and the hardness is 5% higher. Based on these deviations, the system determines that this batch of materials is relatively difficult to process. At this point, the scheduling system dynamically adjusts the weighting coefficients used to correct equipment capability parameters. For example, if the equipment performance degradation is assessed as moderate, the equipment capability parameters might be reduced by 5% without considering material characteristics. However, because the current batch of materials has high hardness, the system will adjust the weighting coefficient from 1.0 to 1.2, making the reduction in equipment capability parameters 5% * 1.2 = 6%. Finally, the scheduling system will use this equipment capability parameter, corrected for material characteristics, to allocate tasks, ensuring that even with a certain degree of equipment degradation, the most suitable equipment can be selected for this challenging material, or processing parameters can be adjusted to meet quality requirements.

[0095] Before task assignment, the steps for generating task risk assessment information based on the degree of equipment performance degradation and task requirements include:

[0096] Identify the location of the tasks to be assigned in the product manufacturing process and their dependencies on subsequent processes;

[0097] Predict the potential delays or quality non-conformities that may occur when assigned tasks are executed on the equipment;

[0098] Based on the position of the task to be assigned in the product production process and its dependence on subsequent processes, calculate the impact of delay time or quality non-conformity rate on the start time and completion time of subsequent processes and product delivery cycle.

[0099] The impact will be quantified as a risk score for the transmission effect along the production chain and incorporated into the task risk assessment information.

[0100] Specifically, identifying the location of an assigned task within the product manufacturing process and its dependencies on subsequent processes involves analyzing the product's process roadmap or production flow chart to determine which stage of the production process the current assigned task is in (e.g., upstream, midstream, or downstream process), and how the completion of this task will affect the initiation conditions and execution schedule of one or more subsequent processes. For example, if a task is a upstream process on the critical path, its delay will directly lead to delays in all subsequent dependent processes.

[0101] Predicting the potential delays or quality defects when an assigned task is executed on a device can be understood as using a predictive model (e.g., a machine learning model or a statistical model) to estimate the probability and extent to which the completion time of the task may exceed expectations or the product quality may fail to meet standards when executed on a specific device, based on factors such as the degree of device performance degradation, historical production data, task complexity, and the current load of the device. For example, when the degree of device performance degradation is high, the predicted delays or quality defects will increase accordingly.

[0102] In practical applications, based on the position of the task to be assigned in the product production process and its dependence on subsequent processes, the impact of delay time or quality defect rate on the start time and completion time of subsequent processes and the product delivery cycle is calculated. Specifically, the predicted delay time or quality defect rate is used as input, combined with the production plan and the logical relationship between processes, and through simulation or chain calculation, the cumulative impact of these potential problems on the key time nodes of the entire production plan (such as the planned start time and completion time of subsequent processes) and the final product delivery commitment (such as the total delivery cycle) is evaluated.

[0103] Furthermore, quantifying the impact as a production chain transmission effect risk score and integrating it into task risk assessment information means converting the calculated impact on the start-up time, completion time, and product delivery cycle of subsequent processes into a unified and comparable numerical indicator—the production chain transmission effect risk score—through a pre-defined scoring rule or risk model. This score reflects the potential destructive power or scope of impact of task risk on the entire production chain and serves as an important component of task risk assessment information, providing schedulers with a basis for decision-making.

[0104] In some preferred embodiments, suppose a distributed manufacturing system is producing a new type of aero-engine blade. The production process of this blade includes multiple steps such as casting, rough machining, finish machining, heat treatment, and surface coating. Now there is a finish machining task to be assigned, which needs to be performed on a CNC machine tool whose performance has been somewhat degraded.

[0105] First, the system identifies the position of the finishing task within the blade production process: it is located after rough machining and before heat treatment, and the initiation of the heat treatment process is strictly dependent on the completion of the finishing task. Simultaneously, the system recognizes that substandard quality in the finishing task will directly impact the effectiveness of subsequent heat treatment and surface coating processes.

[0106] Secondly, based on the performance degradation of the CNC machine tool (e.g., excessive spindle vibration, high predicted tool wear) and the stringent requirements of the finishing task for accuracy and surface quality, the system predicts that when the finishing task is executed on the CNC machine tool, it may cause a delay of 2 hours and there is a 5% probability that the surface roughness of the blade will be unqualified.

[0107] Next, based on the dependency of the finishing task on the subsequent heat treatment process, the system calculates that if the finishing task is delayed by 2 hours, the start time of the heat treatment process will be delayed by 2 hours accordingly; if the quality of the finishing task is unqualified, the entire batch of blades may need to be reworked or scrapped, which will extend the product delivery cycle by at least one week.

[0108] Finally, the system quantifies the impact of the aforementioned 2-hour delay and one-week extension of the delivery cycle into a production chain transmission risk score. For example, a 2-hour delay might be quantified as 50 points, while a one-week extension of the delivery cycle might be quantified as 200 points. These scores are incorporated into the overall risk assessment information for the finishing task. When reviewing task allocation plans, schedulers will see not only the execution risk of the task itself but also its potential high-risk score for the entire production chain. This allows them to prioritize assigning the task to more stable, lower-risk equipment or take proactive measures (such as preparing backup equipment or adjusting subsequent process plans) to mitigate or reduce risks, ensuring the smooth operation of the entire blade production process.

[0109] The steps for obtaining equipment operating status data and workpiece quality data include:

[0110] High-sensitivity piezoelectric accelerometers and high-precision acoustic emission sensors are deployed in key parts of the core processing equipment to collect minute vibration signals and acoustic emission signals generated during equipment operation;

[0111] Real-time digital filtering processing of minute vibration signals and acoustic emission signals;

[0112] Time-domain and frequency-domain features are extracted from filtered minute vibration signals.

[0113] Time-domain and frequency-domain features are extracted from the filtered acoustic emission signal.

[0114] The extracted vibration features and acoustic emission features are fused to form equipment operating status data;

[0115] An online optical inspection system and a coordinate measuring machine are deployed at the end of the production line to perform real-time inspection on each finished workpiece and obtain the workpiece's dimensional deviation and surface roughness data. The obtained dimensional deviation and surface roughness data are the workpiece quality data.

[0116] By using a unique workpiece identifier, the real-time detected workpiece quality data can be accurately correlated with the operating status data of the equipment that processes the workpiece.

[0117] Specifically, high-sensitivity piezoelectric accelerometers and high-precision acoustic emission sensors are deployed in key components of core machining equipment, such as spindles, feed axes, and tool clamping mechanisms, to ensure the capture of minute vibration and acoustic emission signals generated during equipment operation. These signals directly reflect the internal state of the equipment and the dynamic changes in the machining process. Among them, minute vibration signals can characterize the mechanical wear, loosening, or imbalance of the equipment, while acoustic emission signals can reflect microscopic events such as material deformation and crack propagation.

[0118] The acquired minute vibration and acoustic emission signals are then subjected to real-time digital filtering. This processing aims to remove noise interference from the signal, such as environmental noise and electromagnetic interference, to improve the signal-to-noise ratio and ensure the accuracy of subsequent feature extraction. Various algorithms can be used for digital filtering, such as Butterworth filters and Chebyshev filters, selected based on the specific application scenario and signal characteristics.

[0119] The filtered minute vibration signal and acoustic emission signal undergo time-domain feature extraction and frequency-domain feature extraction, respectively. Time-domain feature extraction can include root mean square value, peak value, kurtosis, waveform factor, etc., to describe the statistical characteristics of the signal on the time axis. Frequency-domain feature extraction uses methods such as Fourier transform to obtain the signal's spectral information, such as the dominant frequency, sideband energy, harmonic components, etc., to reveal the energy distribution and periodicity of the signal on the frequency axis. These features can comprehensively reflect the operating status of the equipment and potential fault modes.

[0120] The extracted vibration and acoustic emission features are then fused to form more comprehensive and robust equipment operating status data. Fusion can employ various methods, such as feature-level fusion and decision-level fusion. Feature-level fusion involves concatenating or weighting the feature vectors from different sensors to form a high-dimensional feature vector. Decision-level fusion involves classifying or judging the features from different sensors separately, and then synthesizing these judgments. Through fusion, the complementarity of information from different sensors can be fully utilized, improving the accuracy and reliability of equipment operating status perception.

[0121] At the end of the production line, an online optical inspection system and a coordinate measuring machine (CMM) are deployed to perform real-time inspection of each completed workpiece. The online optical inspection system can quickly acquire information such as the surface morphology and dimensional contours of the workpiece, for example, by identifying surface defects and measuring critical dimensions using machine vision technology. The CMM provides high-precision dimensional measurement to obtain dimensional deviations and surface roughness data of the workpiece. These data are defined as workpiece quality data and are important bases for evaluating the quality of the processing and the processing capabilities of the equipment.

[0122] To achieve correlation analysis between equipment operating status and workpiece quality, a unique workpiece identifier is used to precisely link real-time detected workpiece quality data with the equipment operating status data that processed the workpiece. The unique workpiece identifier can be a QR code, RFID tag, or production batch number, ensuring that the quality data of each workpiece can be accurately traced back to its corresponding processing equipment and process. This precise correlation provides a data foundation for subsequent equipment performance degradation assessment.

[0123] This application's solution deploys high-sensitivity piezoelectric accelerometers and high-precision acoustic emission sensors at key locations on core processing equipment, enabling comprehensive and real-time acquisition of minute vibration and acoustic emission signals during equipment operation. These signals, after real-time digital filtering, time-domain feature extraction, and frequency-domain feature extraction, are effectively transformed into vibration and acoustic emission characteristics that characterize the equipment's health and processing dynamics. By fusing these multi-source features, more comprehensive and accurate equipment operating status data can be generated, overcoming the limitations of insufficient information from a single sensor. Simultaneously, deploying an online optical inspection system and a coordinate measuring machine at the end of the production line enables real-time, high-precision quality inspection of each completed workpiece, acquiring crucial dimensional deviation and surface roughness data. Finally, by using a unique workpiece identifier, the equipment operating status data is precisely correlated with the workpiece quality data, establishing a direct mapping relationship between equipment status and product quality, providing a solid data foundation for subsequent equipment performance degradation assessment and intelligent scheduling.

[0124] This application further proposes a step for fusing the extracted vibration features and acoustic emission features to form equipment operating status data, including:

[0125] Obtain the current operating mode information of the device;

[0126] Based on the current working mode information of the equipment, obtain the vibration feature fusion weight and acoustic emission feature fusion weight corresponding to the current working mode from the preset working mode and fusion weight mapping rules;

[0127] By using vibration feature fusion weights and acoustic emission feature fusion weights, the extracted vibration features and acoustic emission features are weighted and fused to form equipment operating status data.

[0128] Specifically, obtaining the current operating mode information of the equipment refers to acquiring the current operating status or processing stage of the equipment in real time through methods such as the equipment's own controller, sensor data analysis, or operator input. For example, operating mode information may include roughing, finishing, no-load, loading, and standby. The preset operating mode and fusion weight mapping rule can be understood as a database or lookup table stored in the scheduling system or equipment control system. This rule predefines the relative importance or contribution of vibration characteristics and acoustic emission characteristics in forming equipment operating status data under different operating modes. For example, in some operating modes, vibration characteristics may be more sensitive to equipment performance degradation, thus their fusion weight will be higher; while in other operating modes, acoustic emission characteristics may provide more critical information, and their fusion weight will be correspondingly increased. These weight coefficients or adjustment factors can be determined through historical data analysis, expert experience, or machine learning model training. In practical applications, the vibration characteristic fusion weight and acoustic emission characteristic fusion weight are numerical parameters used to weight the extracted vibration characteristics and acoustic emission characteristics. The setting of these weight coefficients aims to ensure that the fused equipment operating status data can more accurately and comprehensively reflect the true health status of the equipment under different operating modes. Furthermore, the extracted vibration and acoustic emission features are weighted and fused to form equipment operating status data. This involves multiplying the vibration and acoustic emission features, after time-domain and frequency-domain feature extraction, by their respective vibration feature fusion weights and acoustic emission feature fusion weights. The weighted features are then combined or superimposed to generate a comprehensive set of equipment operating status data. This weighted fusion method can dynamically adjust the contribution of different types of features according to the current operating mode of the equipment, making the final equipment operating status data more representative and accurate.

[0129] In some preferred embodiments, it is assumed that a CNC machine tool operates in three typical modes during machining tasks: "roughing," "finishing," and "no-load." When the machine is in "roughing" mode, due to the large cutting volume and strong cutting force, it is more prone to significant mechanical vibration. In this mode, the vibration characteristics are more sensitive to performance degradation such as wear and loosening. Therefore, in the preset working mode and fusion weight mapping rules, the vibration characteristic fusion weight is set to 0.7 for "roughing" mode, while the acoustic emission characteristic fusion weight is set to 0.3. When the machine switches to "finishing" mode, the cutting volume decreases, and the requirements for machining accuracy and surface quality are higher. In this mode, the acoustic emission signal may better reflect the microscopic wear of the tool and the generation of internal material defects. Therefore, for "finishing" mode, the vibration characteristic fusion weight is set to 0.4, while the acoustic emission characteristic fusion weight is set to 0.6. When the machine is in "no-load" mode, the main focus is on the machine's no-load stability and bearing wear. In this mode, the characteristics of vibration and acoustic emission signals may differ significantly from those under load. For the "no-load" mode, the vibration feature fusion weight and acoustic emission feature fusion weight can be set to 0.5 and 0.5 respectively, or adjusted more finely according to the actual situation. In this way, the system can dynamically obtain the corresponding fusion weights from preset rules based on the current operating mode information of the equipment, and use these weights to perform weighted fusion of the real-time extracted vibration and acoustic emission features. Therefore, the equipment operating status data generated under different operating modes can more accurately reflect the key health indicators of the equipment in that mode, avoiding misjudgments or information omissions that may be caused by a single weight strategy, thus providing a more reliable basis for subsequent intelligent scheduling decisions.

[0130] The steps for fusing the extracted vibration features and acoustic emission features to form equipment operating status data include:

[0131] When switching the device's operating mode, obtain the operating mode information before the switch and the operating mode information after the switch;

[0132] Based on the working mode information before and after the switch, determine the transition phase of the working mode switch.

[0133] During the transition phase of switching working modes, a time decay-based weighted fusion strategy is adopted to interpolate the fusion weights corresponding to the working modes before and after the switch to obtain the transition fusion weights.

[0134] By using transition fusion weights, the extracted vibration features and acoustic emission features are weighted and fused to form equipment operating status data.

[0135] Specifically, when switching equipment operating modes, the system is configured to monitor the equipment's operating status in real time. Once a change in operating mode is detected, it acquires both the operating mode information before and after the switch. For example, when the equipment switches from "roughing mode" to "finishing mode," the system records the operating mode information before the switch for "roughing mode" and the operating mode information after the switch for "finishing mode." This operating mode information may include mode identifiers, preset processing parameter ranges, expected load characteristics, etc.

[0136] Furthermore, based on the acquired information about the operating mode before and after the switch, the system is used to determine the transition phase of the operating mode switch. This transition phase refers to the time interval during which the equipment gradually evolves from one stable operating state to another. For example, the start and end points of this transition phase can be defined by analyzing the command sequence of the equipment control system and the changing trends of data from internal sensors (such as spindle speed, feed rate, and tool load). The length of this transition phase can be preset or dynamically adjusted based on the specific type of equipment, the differences in the switching modes, and empirical data.

[0137] During the transition phase of operating mode switching, to more accurately reflect the equipment's operating status, this application employs a time-decay-based weighted fusion strategy. This strategy aims to interpolate the fusion weights corresponding to the operating mode before and after the switch to obtain the transition fusion weights. Specifically, as time progresses from the start to the end of the transition phase, the influence of the fusion weights of the operating mode before the switch gradually weakens, while the influence of the fusion weights of the operating mode after the switch gradually strengthens. For example, linear interpolation, exponential decay, or S-curve functions can be used to calculate the transition fusion weights at different time points. These fusion weights include vibration feature fusion weights and acoustic emission feature fusion weights, which are used to weight the extracted vibration features and acoustic emission features, respectively.

[0138] Finally, the extracted vibration and acoustic emission features are weighted and fused using the obtained transition fusion weights to form more accurate equipment operating status data during the working mode switching transition phase. This weighted fusion process is similar to the fusion method in the above implementation, but its key lies in the dynamic adjustment of the fusion weights to adapt to the dynamic characteristics of the equipment during the mode switching process.

[0139] In some preferred embodiments, it is assumed that a CNC milling machine needs to switch from "rough milling mode" to "finish milling mode" when performing a machining task of a complex part.

[0140] First, when the system detects a switch command from "rough milling mode" to "fine milling mode", it will immediately obtain the working mode information before the switch (rough milling mode) and the working mode information after the switch (fine milling mode).

[0141] Next, the system determines the transition phase of this mode switch to be 10 seconds based on preset rules or by real-time analysis of equipment parameters (such as the change curves of spindle speed, feed rate, tool load, etc.).

[0142] Over the next 10 seconds, the system continuously monitors the minute vibration and acoustic emission signals generated during equipment operation and extracts the corresponding vibration and acoustic emission features. Simultaneously, the system dynamically calculates the transition fusion weights based on a time-decrease-based weighted fusion strategy. For example, at the beginning of the transition phase (t=0s), the fusion weights may be more biased towards the rough milling mode; at the end of the transition phase (t=10s), the fusion weights will completely transition to the finish milling mode weights. At intermediate moments (e.g., t=5s), the fusion weights will be an interpolation of the rough milling mode weights and the finish milling mode weights. For example, linear interpolation can be used, i.e., transition fusion weight = (1-t / 10) * rough milling mode weight + (t / 10) * finish milling mode weight.

[0143] Finally, the system utilizes these dynamically calculated transition fusion weights to perform weighted fusion of the real-time extracted vibration and acoustic emission features, thereby generating more accurate equipment operating status data during the mode switching transition phase. This data is then used to assess the degree of equipment performance degradation, ensuring accurate assessment of equipment health even in dynamic switching scenarios, thus assisting schedulers in making better task allocation decisions.

[0144] This application further proposes a step for generating task risk assessment information based on the degree of equipment performance degradation and task requirements before task allocation, including:

[0145] Obtain the specific threshold values ​​for the product's microstructure or surface morphology as required by the task;

[0146] Based on the degree of equipment performance degradation and specific index thresholds, predict the types of subsurface defects and the risk level of internal stress concentration generated during processing;

[0147] Obtain the correlation rules between long-term product reliability or specific functions and subsurface defect types and internal stress concentration risk levels;

[0148] Based on association rules, the impact of subsurface defect types and internal stress concentration risk levels on the long-term reliability or specific functions of the product is quantified.

[0149] The quantified impact is used as a latent defect risk score and integrated into the task risk assessment information.

[0150] Specifically, the acquisition of specific threshold values ​​for the product's microstructure or surface morphology in the task requirements refers to the system's analysis of the task's specific quality requirements for the final product at the microscopic level (e.g., grain size, phase composition, inclusion distribution) or the macroscopic surface level (e.g., surface roughness, waviness, residual stress) upon receiving the assigned task. These requirements are typically given in the form of quantified threshold values, such as requiring a grain size of less than 10 micrometers or a surface roughness Ra value of less than 0.2 micrometers. The purpose is to provide a clear quality benchmark for subsequent latent defect prediction and risk assessment.

[0151] The system predicts the types of subsurface defects and the risk level of internal stress concentration during processing based on the degree of equipment performance degradation and specific threshold indicators. This can be understood as the system comprehensively analyzing the assessed degree of equipment performance degradation (e.g., abnormal spindle vibration, accelerated tool wear) against the specific threshold indicators required by the task. For example, when the equipment degrades to a certain extent, combined with the task's stringent requirements for surface morphology, the system can predict potential subsurface defects such as microcracks, porosity, and non-metallic inclusions that may occur during processing, and assess the risk level of internal stress concentration caused by these defects. The aim is to identify potential quality hazards that are difficult to detect with the naked eye or conventional inspections in advance.

[0152] In practical applications, obtaining the correlation rules between long-term product reliability or specific functions and the types of subsurface defects and the risk level of internal stress concentration specifically refers to establishing a knowledge base or model. This knowledge base or model includes historical data, expert experience, simulation results, etc., to describe how different types of subsurface defects and the risk level of internal stress concentration affect the long-term service performance (e.g., fatigue life, creep performance, corrosion resistance) or specific functions (e.g., conductivity, optical performance) of a product. For example, a certain type of microcrack may reduce the fatigue life of a product by 20%, while a certain degree of internal stress concentration may increase the probability of product failure under a specific load. The purpose is to provide a scientific basis for quantifying the impact of latent defects on products.

[0153] Furthermore, quantifying the impact of subsurface defect types and internal stress concentration risk levels on the long-term reliability or specific functions of a product, based on association rules, means that the system, according to the aforementioned association rules, transforms the predicted subsurface defect types and internal stress concentration risk levels into specific numerical values ​​affecting the long-term reliability or specific functions of the product. For example, if a certain subsurface defect is predicted, and this defect, according to association rules, will lead to a reduction in the product's fatigue life, then this reduction is quantified into a specific impact value. The purpose is to transform abstract defect risks into measurable, concrete impacts on product performance.

[0154] Therefore, incorporating the quantified impact as a latent defect risk score into the task risk assessment information means integrating the aforementioned quantified impact value as an independent or weighted score into the overall task risk assessment information. This latent defect risk score reflects the risk that, when a task is performed on specific equipment, the interaction between equipment degradation and material properties may lead to latent defects in the product, affecting its long-term performance. The aim is to make task risk assessment more comprehensive and in-depth, considering not only explicit risks but also latent risks.

[0155] In some preferred embodiments, suppose a distributed manufacturing system needs to process a batch of novel high-temperature alloy materials for aero-engine blades. This task requires the blades to have extremely high fatigue life and creep resistance, and imposes strict threshold requirements on the material's microstructure and surface residual stress.

[0156] First, the system will obtain the specific threshold values ​​for the micrograin size (e.g., average grain size less than 50 micrometers) and surface residual compressive stress (e.g., surface residual compressive stress greater than -300 MPa) of the high-temperature alloy blade as required by the task.

[0157] Secondly, considering the performance degradation of a particular machining equipment (e.g., a five-axis milling machine) (e.g., abnormal micro-vibration due to spindle bearing wear, high tool wear), the system predicts the types of subsurface microcracks (e.g., microcracks distributed along grain boundaries) and the risk level of internal tensile stress concentration that may occur during machining on that equipment. For example, it predicts that a moderate level of subsurface microcracks and a high risk of internal tensile stress concentration may occur in the root region of a blade.

[0158] Next, the system retrieves association rules between long-term product reliability (e.g., fatigue life) and the type of subsurface microcracks and the risk level of internal stress concentration from a pre-set knowledge base. For example, the rules might indicate that a specific type of subsurface microcrack and a high risk of internal tensile stress concentration could reduce the fatigue life of the high-temperature alloy blade by 15% to 20%.

[0159] Then, based on these association rules, the system quantifies the predicted risks of subsurface microcracks and internal tensile stress concentration into specific values ​​that affect the fatigue life of the blade, for example, by 18% reduction in fatigue life.

[0160] Finally, this quantified impact (i.e., an 18% reduction in fatigue life) is incorporated into the overall risk assessment information for the task as a latent defect risk score. When reviewing the task risk assessment information, the scheduler will see not only the usual production cycle delay risk or surface quality non-conformity rate risk, but also a clear latent defect risk score, indicating that processing on this equipment may significantly reduce the product's fatigue life. Based on this, the scheduler can make more informed decisions, such as assigning the task to equipment with superior performance, adjusting processing parameters to reduce risk, or even considering adding additional non-destructive testing procedures to ensure the long-term reliability and safety of the aero-engine blades.

[0161] This application further proposes steps for incorporating quantified impact as a latent defect risk score into task risk assessment information, including:

[0162] Obtain information on the types of latent defects contained in the quantified impact;

[0163] Based on the information on the type of latent defect, obtain the risk presentation granularity or dimension corresponding to the latent defect type from the preset defect type and risk presentation rules;

[0164] Based on the granularity or dimension of risk presentation, the quantitative impact is transformed to generate a latent defect risk score with a specific granularity or dimension;

[0165] Incorporate latent defect risk scores with specific granularity or dimensions into the task risk assessment information.

[0166] Specifically, obtaining information on the types of latent defects included in the quantified impact refers to identifying and extracting the specific types of latent defects that cause the impact from the calculation results of the aforementioned quantified impact. These types of latent defects may include, but are not limited to, microcracks, porosity, inclusions, grain boundary segregation, residual stress, etc., with the aim of clarifying the source and nature of the risk.

[0167] In this context, obtaining the risk presentation granularity or dimension corresponding to the latent defect type from preset defect type and risk presentation rules, based on latent defect type information, refers to the system maintaining a knowledge base or database containing multiple defect types and their corresponding risk presentation methods. For example, for microcracks, the risk may need to be presented in the form of a spatial distribution map to indicate the specific location where the crack may occur; for internal stress concentration, the risk evolution trend may need to be presented in the form of a time series graph to predict the critical point of stress accumulation. The risk presentation granularity or dimension may include, but is not limited to, spatial dimensions (such as defect location and distribution density), temporal dimensions (such as defect evolution rate and duration), severity dimensions (such as defect size and quantity), and impact scope dimensions (such as the impact on subsequent processes). Its purpose is to provide guidance for subsequent risk score conversion, ensuring that risk information can be understood and utilized in the most effective way.

[0168] In practical applications, transforming quantified impacts based on the granularity or dimension of risk presentation to generate latent defect risk scores with specific granularity or dimensions refers to reconstructing, refining, or aggregating the original quantified impact data according to the acquired granularity or dimension of risk presentation. For example, if the risk presentation dimension is spatial distribution, the quantified impact can be decomposed into risk values ​​for different regions; if the risk presentation granularity is severity levels, the quantified impact can be mapped to predefined risk levels (such as low, medium, and high). This transformation can be achieved using various data processing and visualization techniques, with the aim of converting abstract quantified impacts into concrete, intuitive risk scores that are easy for decision-makers to understand and use.

[0169] Furthermore, integrating latent defect risk scores with specific granularity or dimensions into task risk assessment information means presenting the transformed and structured latent defect risk scores as a component of the task risk assessment information, along with other risk assessment indicators (such as delay time, quality non-compliance rate, etc.), to the dispatcher. This can be displayed on the dispatching interface in various forms such as charts, heatmaps, and risk level indicators. The purpose is to provide the dispatcher with a comprehensive, multi-dimensional risk view, assisting them in making more informed task allocation decisions.

[0170] In some preferred embodiments, it is assumed that when processing a batch of new alloy materials, two main latent defect risks are predicted by the above method: one is the risk of subsurface microcracks, and the other is the risk of internal residual stress concentration.

[0171] First, the system acquires information on the types of latent defects contained in the quantified impact, namely "subsurface microcracks" and "internal residual stress concentrations".

[0172] Next, based on the preset defect types and risk presentation rules, the system identifies that for "subsurface microcracks", the corresponding risk presentation granularity or dimension is "spatial distribution and size", because the location and size of microcracks have a significant impact on subsequent fatigue life; while for "internal residual stress concentration", the corresponding risk presentation granularity or dimension is "stress gradient and regional range", because the gradient and range of influence of stress concentration determine its threat to structural integrity.

[0173] Based on the granularity or dimension of these risks, the system transforms the original quantitative impact. For example, for microcrack risk, a three-dimensional risk map containing the coordinates of potential crack locations, expected crack length and depth is generated as the latent defect risk score; for residual stress concentration risk, a two-dimensional heat map showing the stress concentration area, maximum stress value and stress gradient changes is generated as the latent defect risk score.

[0174] Ultimately, these latent defect risk scores, with specific granularity or dimensions, are integrated into the task risk assessment information and presented to the scheduler in a visual manner. The scheduler can clearly see which areas may contain microcracks and which parts have a high risk of residual stress concentration. Based on this refined information, the scheduler can decide to assign the task to equipment with more precise processing capabilities or equipped with online stress monitoring functions, adjust the processing path to avoid high-risk areas, or even arrange additional non-destructive testing procedures, thereby effectively avoiding product failures caused by latent defects and ensuring the processing quality and product reliability of new alloy materials.

[0175] refer to Figure 2 This application also proposes a distributed manufacturing resource intelligent scheduling system for implementing a distributed manufacturing resource intelligent scheduling method. The system includes:

[0176] The acquisition module is used to acquire equipment operating status data and workpiece quality data;

[0177] The performance evaluation module assesses the degree of equipment performance degradation based on equipment operating status data and workpiece quality data.

[0178] The correction module adjusts the equipment capability parameters within the scheduling system based on the degree of equipment performance degradation.

[0179] The risk assessment module generates task risk assessment information based on the degree of equipment performance degradation and task requirements before task allocation;

[0180] The auxiliary module assists the scheduler in making task allocation decisions based on task risk assessment information.

[0181] The steps for assessing the degree of equipment performance degradation based on equipment operating status data and workpiece quality data include: acquiring multi-source processing signals of equipment operation; processing the multi-source processing signals of equipment operation to obtain real-time processing response characteristics; acquiring the material response characteristic pattern of the new alloy material; the material response characteristic pattern of the new alloy material characterizes the subsurface micro-defects caused by the interaction between equipment latent degradation and material properties; comparing the real-time processing response characteristics with the material response characteristic pattern of the new alloy material to predict the risk of internal defects; and comprehensively assessing the degree of equipment performance degradation by combining the risk of internal defects with the degree of equipment vibration deviation and the degree of workpiece surface quality deviation.

[0182] The acquisition module is configured to collect necessary raw data from the distributed manufacturing environment. Specifically, this module can integrate various sensor interfaces, data acquisition units, and data exchange interfaces with existing manufacturing execution systems or enterprise resource planning systems to acquire real-time equipment operating status data and finished workpiece quality data. Equipment operating status data may include, but is not limited to, parameters such as equipment vibration, temperature, current, and power, while workpiece quality data may include information such as dimensional deviations, surface roughness, and internal defects.

[0183] The performance evaluation module is configured to receive equipment operating status data and workpiece quality data provided by the acquisition module, and to quantitatively assess the degree of equipment performance degradation based on this data. This module can employ advanced data analysis algorithms, such as machine learning models, statistical process control methods, or physical model-based degradation prediction algorithms, to identify performance degradation trends of the equipment under long-term operation or specific operating conditions. Evaluation results are typically expressed in numerical or graded form to reflect the equipment's health status and potential failure risks.

[0184] The correction module is configured to dynamically adjust the equipment capacity parameters maintained within the scheduling system based on the degree of equipment performance degradation output by the performance evaluation module. In actual manufacturing scheduling, the theoretical capacity parameters of equipment may not accurately reflect its true performance in actual operation, especially when equipment performance degradation exists. By introducing the degree of degradation as a correction factor, this correction module can more accurately adjust parameters such as available capacity, processing accuracy, and reliability of the equipment, ensuring the accuracy and effectiveness of scheduling decisions.

[0185] The risk assessment module is configured to generate task risk assessment information before task assignment, taking into account both the degree of equipment performance degradation and the specific requirements of the task to be assigned. This module can analyze the task's requirements for equipment accuracy, stability, and reliability, and, combined with the equipment's current degradation state, predict the risks that the task may face when executed on a specific piece of equipment, such as substandard processing quality, production delays, or equipment failure. Risk assessment information can include risk level, estimated potential losses, and the probability of the risk occurring.

[0186] The auxiliary module is configured to receive task risk assessment information generated by the risk assessment module and, based on this, assist the scheduler in making task allocation decisions. This module provides an intuitive risk visualization interface, showing the scheduler the risk levels under different task allocation schemes, and can recommend the optimal task allocation scheme based on preset scheduling strategies or optimization objectives. Through this module, the scheduler can gain a more comprehensive understanding of the potential risks of task allocation, thereby making more informed and robust decisions.

[0187] The solution proposed in this application visualizes each logical step in the distributed intelligent scheduling method for manufacturing resources as a collaborative system module, thereby achieving real-time perception of the status of manufacturing resources, accurate performance evaluation, dynamic correction of scheduling parameters, and intelligent early warning of task risks.

[0188] The content disclosed above is only a preferred and feasible embodiment of the present invention, and is not intended to limit the scope of protection of the present invention. Therefore, all equivalent technical changes made based on the content of the present invention specification and drawings are included within the scope of protection of the present invention. Furthermore, the elements therein can be updated as technology develops.

Claims

1. A distributed intelligent scheduling method for manufacturing resources, characterized in that, The method includes the following steps: Acquire equipment operating status data and workpiece quality data; Based on equipment operating status data and workpiece quality data, assess the degree of equipment performance degradation; Adjust the equipment capability parameters within the scheduling system according to the degree of equipment performance degradation; Before task assignment, task risk assessment information is generated based on the degree of equipment performance degradation and task requirements; Based on task risk assessment information, assist the scheduler in making task allocation decisions; The steps for assessing the degree of equipment performance degradation based on equipment operating status data and workpiece quality data include: acquiring multi-source processing signals of equipment operation, processing the multi-source processing signals of equipment operation to obtain real-time processing response characteristics, acquiring the material response characteristic pattern of alloy materials, the material response characteristic pattern of alloy materials characterizing the subsurface micro-defects caused by the interaction between equipment latent degradation and material properties, comparing the real-time processing response characteristics with the material response characteristic pattern of alloy materials to predict internal defect risks, and comprehensively assessing the degree of equipment performance degradation by combining the internal defect risks with the degree of equipment vibration deviation and the degree of workpiece surface quality deviation. Before task assignment, the steps for generating task risk assessment information based on the degree of equipment performance degradation and task requirements include: Obtain the specific threshold values ​​for the product's microstructure or surface morphology as required by the task; Based on the degree of equipment performance degradation and specific index thresholds, predict the types of subsurface defects and the risk level of internal stress concentration generated during processing; Obtain the correlation rules between long-term product reliability or specific functions and subsurface defect types and internal stress concentration risk levels; Based on association rules, the impact of subsurface defect types and internal stress concentration risk levels on the long-term reliability or specific functions of the product is quantified. The quantified impact is used as a latent defect risk score and integrated into the task risk assessment information.

2. The distributed manufacturing resource intelligent scheduling method as described in claim 1, characterized in that, The steps for adjusting the equipment capability parameters within the scheduling system based on the degree of equipment performance degradation include: Obtain microstructure characteristics and mechanical property data of the current batch of alloy materials; The microstructure characteristics and mechanical properties of the current batch of alloy materials are compared with the preset material property benchmarks to identify the degree of deviation of the properties of the current batch of alloy materials. Based on the degree of deviation of the characteristics of the current batch of alloy materials, dynamically adjust the weighting coefficients or adjustment factors used to correct the equipment capacity parameters; By using the adjusted weighting coefficients or adjustment factors, and in conjunction with the degree of equipment performance degradation, the equipment capability parameters within the scheduling system are corrected.

3. The distributed manufacturing resource intelligent scheduling method as described in claim 1, characterized in that, Before task assignment, the steps for generating task risk assessment information based on the degree of equipment performance degradation and task requirements include: Identify the location of the tasks to be assigned in the product manufacturing process and their dependencies on subsequent processes; Predict the potential delays or quality non-conformities that may occur when assigned tasks are executed on the equipment; Based on the position of the task to be assigned in the product production process and its dependence on subsequent processes, calculate the impact of delay time or quality non-conformity rate on the start time and completion time of subsequent processes and product delivery cycle. The impact will be quantified as a risk score for the transmission effect along the production chain and incorporated into the task risk assessment information.

4. The distributed manufacturing resource intelligent scheduling method as described in claim 1, characterized in that, The steps for obtaining equipment operating status data and workpiece quality data include: High-sensitivity piezoelectric accelerometers and high-precision acoustic emission sensors are deployed in key parts of the core processing equipment to collect minute vibration signals and acoustic emission signals generated during equipment operation; Real-time digital filtering processing of minute vibration signals and acoustic emission signals; Time-domain and frequency-domain features are extracted from filtered minute vibration signals. Time-domain and frequency-domain features are extracted from the filtered acoustic emission signal. The extracted vibration features and acoustic emission features are fused to form equipment operating status data; An online optical inspection system and a coordinate measuring machine are deployed at the end of the production line to perform real-time inspection on each finished workpiece and obtain the workpiece's dimensional deviation and surface roughness data. The obtained dimensional deviation and surface roughness data constitute the workpiece quality data. By using a unique workpiece identifier, the real-time detected workpiece quality data can be accurately correlated with the operating status data of the equipment that processes the workpiece.

5. The distributed manufacturing resource intelligent scheduling method as described in claim 4, characterized in that, The steps for fusing the extracted vibration features and acoustic emission features to form equipment operating status data include: Obtain the current operating mode information of the device; Based on the current working mode information of the equipment, obtain the vibration feature fusion weight and acoustic emission feature fusion weight corresponding to the current working mode from the preset working mode and fusion weight mapping rules; By using vibration feature fusion weights and acoustic emission feature fusion weights, the extracted vibration features and acoustic emission features are weighted and fused to form equipment operating status data.

6. The distributed manufacturing resource intelligent scheduling method as described in claim 5, characterized in that, The steps for fusing the extracted vibration features and acoustic emission features to form equipment operating status data include: When switching the device's operating mode, obtain the operating mode information before the switch and the operating mode information after the switch; Based on the working mode information before and after the switch, determine the transition phase of the working mode switch. During the transition phase of switching working modes, a time decay-based weighted fusion strategy is adopted to interpolate the fusion weights corresponding to the working modes before and after the switch to obtain the transition fusion weights. By using transition fusion weights, the extracted vibration features and acoustic emission features are weighted and fused to form equipment operating status data.

7. The distributed manufacturing resource intelligent scheduling method as described in claim 1, characterized in that, The steps to incorporate quantified impact as a latent defect risk score into task risk assessment information include: Obtain information on the types of latent defects contained in the quantified impact; Based on the information on the type of latent defect, obtain the risk presentation granularity or dimension corresponding to the latent defect type from the preset defect type and risk presentation rules; Based on the granularity or dimension of risk presentation, the quantitative impact is transformed to generate a latent defect risk score with a specific granularity or dimension; Incorporate latent defect risk scores with specific granularity or dimensions into the task risk assessment information.

8. A distributed manufacturing resource intelligent scheduling system, applied to the distributed manufacturing resource intelligent scheduling method as described in claim 1, characterized in that, The system includes: The acquisition module is used to acquire equipment operating status data and workpiece quality data; The performance evaluation module assesses the degree of equipment performance degradation based on equipment operating status data and workpiece quality data. The correction module adjusts the equipment capability parameters within the scheduling system based on the degree of equipment performance degradation. The risk assessment module generates task risk assessment information based on the degree of equipment performance degradation and task requirements before task allocation; The auxiliary module assists the scheduler in making task allocation decisions based on task risk assessment information. The steps for assessing the degree of equipment performance degradation based on equipment operating status data and workpiece quality data include: acquiring multi-source processing signals of equipment operation, processing the multi-source processing signals of equipment operation to obtain real-time processing response characteristics, acquiring the material response characteristic pattern of alloy materials, the material response characteristic pattern of alloy materials characterizing the subsurface micro-defects caused by the interaction between equipment latent degradation and material properties, comparing the real-time processing response characteristics with the material response characteristic pattern of alloy materials to predict internal defect risks, and comprehensively assessing the degree of equipment performance degradation by combining the internal defect risks with the degree of equipment vibration deviation and the degree of workpiece surface quality deviation. Before task assignment, the steps for generating task risk assessment information based on the degree of equipment performance degradation and task requirements include: Obtain the specific threshold values ​​for the product's microstructure or surface morphology as required by the task; Based on the degree of equipment performance degradation and specific index thresholds, predict the types of subsurface defects and the risk level of internal stress concentration generated during processing; Obtain the correlation rules between long-term product reliability or specific functions and subsurface defect types and internal stress concentration risk levels; Based on association rules, the impact of subsurface defect types and internal stress concentration risk levels on the long-term reliability or specific functions of the product is quantified. The quantified impact is used as a latent defect risk score and integrated into the task risk assessment information.

Images