Discrete manufacturing equipment efficiency maximization strategy determination system and method

Abstract

The invention discloses a discrete manufacturing equipment efficiency maximization strategy determination system and method, effectively achieving the purpose of improving the equipment utilization rate, and the system comprises a multi-source data collection unit which comprises a multi-source data collection module and an edge calculation module; the intelligent decision-making unit comprises a prediction module, a multi-objective optimization module and a weight fusion module; the execution control unit comprises a strategy issuing module, a self-adaptive adjustment module and a dynamic scheduling module; the feedback optimization unit comprises a digital twin simulation module and an incremental learning module; the device is novel in structure, ingenious in conception and easy and convenient to operate, the joint manufacturing efficiency of manufacturing equipment is effectively improved, the energy consumption cost is reduced, the delivery punctuality rate is increased, and carbon emission is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of equipment management methods, and relates to a system and method for determining a strategy for maximizing the efficiency of discrete manufacturing equipment. Background Art

[0002] Discrete manufacturing (such as industries like automotive parts and electronics assembly) has characteristics such as complex production processes, diverse product types, and large order fluctuations. Equipment efficiency directly determines the production capacity and cost competitiveness of an enterprise. Traditional efficiency optimization mainly relies on manual experience to adjust equipment parameters or single-dimensional indicators (such as maximizing equipment utilization rate), and it is difficult to balance economic, technical, and environmental goals in a dynamic production environment. With the development of intelligent manufacturing, how to achieve global optimization of equipment efficiency through multi-source data fusion and intelligent decision-making has become the core challenge in the industry.

[0003] In addition, most existing efficiency optimizations ignore multi-dimensional constraints such as order urgency and customer priority, which easily lead to delivery delays or losses of liquidated damages; and they do not consider dynamic factors such as equipment health status and time-of-use electricity prices. Long-term operation may cause equipment failures or a sharp increase in energy consumption costs. Therefore, a system and method for determining a strategy for maximizing the efficiency of discrete manufacturing equipment that can consider dynamic factors such as order urgency, customer priority, equipment health status, and time-of-use electricity prices are needed to solve the above problems. Summary of the Invention

[0004] In view of the above problems, the present invention proposes a system and method for determining a strategy for maximizing the efficiency of discrete manufacturing equipment, which well solves the problems in the prior art.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] A system for determining a strategy for maximizing the efficiency of discrete manufacturing equipment, comprising:

[0007] A multi-source data acquisition unit, including a multi-source data acquisition module for collecting equipment data, order data, and environmental data inside the factory building and an edge computing module for cleaning the data;

[0008] An intelligent decision-making unit, including a prediction module, a multi-objective optimization module, and a weight fusion module;

[0009] The prediction module is used to predict order demand, equipment health, and equipment energy consumption cost;

[0010] The multi-objective optimization module is used to evaluate the economy, technology, and environment of the factory building;

[0011] A weight fusion module, which is used to perform weighted fusion by combining the subjective weights and objective weights of the prediction module, economy, technology, and environment, and finally generate an optimization strategy for multi-objective optimization;

[0012] An execution control unit, including a policy distribution module, an adaptive adjustment module, and a dynamic scheduling module;

[0013] The policy distribution module is used to transcode the generated optimization strategy and send it to the adaptive adjustment module;

[0014] The adaptive adjustment module is used to adjust the device operation parameters to balance efficiency and energy consumption;

[0015] The dynamic scheduling module is used to adjust the order queue;

[0016] A feedback optimization unit, including a digital twin simulation module and an incremental learning module; the digital twin simulation module is used to simulate the optimization strategy to verify the production capacity deviation; the incremental learning module is used to feedback the daily actual production data collected to the prediction module and update the prediction module regularly.

[0017] Preferably, the multi-source data acquisition module includes a vibration sensor, a device on / off state sensor, a current sensor, an enterprise resource planning system, an API interface, and a temperature and humidity sensor.

[0018] The present invention also discloses a method for determining the efficiency maximization strategy of a discrete manufacturing device. Based on a discrete manufacturing device efficiency maximization strategy determination system, it includes the following steps:

[0019] Preparation stage, system deployment, configure and calibrate the data acquisition unit, software, and interface of the system;

[0020] Step S1, multi-source data acquisition and edge preprocessing, collect device data, order data, and environmental data through the multi-source data acquisition module, and clean the collected data through the edge computing module;

[0021] Step S2, multi-dimensional prediction, predict the order demand, device health, and device energy consumption cost through the prediction module;

[0022] Step S3, generation of multi-objective optimization strategy, construct an economic, technical, and environmental evaluation index system through the multi-objective optimization module; fuse the subjective weight and objective weight through the weight fusion module to generate a comprehensive weight; finally generate multiple Pareto optimization strategies through the multi-objective optimization module and send them to the policy distribution module;

[0023] Step S4, Policy Execution and Dynamic Adjustment: After receiving the optimization policy, the policy distribution module converts the optimization policy into device control instructions through an industrial automation standard protocol and sends them to the adaptive adjustment module. The adaptive adjustment module monitors the device load in real time and dynamically adjusts the device processing parameters; reorders the production queue according to the customer level and penalty cost through the dynamic scheduling module;

[0024] Step S5, Digital Twin Verification and Model Iteration: Simulate the execution of the optimization policy on the digital twin platform through the digital twin simulation module, calculate the deviation between the theoretical production capacity and the actual production capacity. When the deviation value between the actual production capacity and the theoretical production capacity > 10%, trigger policy backtracking; through the incremental learning module, feedback the daily actual production data collected to the prediction module and perform daily incremental updates on the prediction module.

[0025] Preferably, in step S1, the multi-source data collection includes the following steps:

[0026] Step S11: Real-time collect device vibration, current, temperature and humidity data through the multi-source data collection module, and synchronize the production plan scheduling, order urgency, profit margin and delivery cycle of the enterprise resource planning system;

[0027] Step S12: Use the edge computing module to clean the original data using edge computing nodes and extract key features.

[0028] Preferably, in step S12, the key features include one or more of the overall equipment efficiency, order completion rate, and actual energy consumption cost.

[0029] Preferably, in step S2, the multi-dimensional prediction includes:

[0030] Order demand prediction: Analyze the historical order seasonal fluctuations and market trends using a time series model and output the future weekly order volume prediction results;

[0031] Equipment health prediction: Build a fault warning model based on a long short-term memory network, input the peak value of the vibration spectrum and the variance of the current fluctuation, and output the fault probability threshold warning;

[0032] Energy consumption cost prediction: Combine the production plan scheduling collected by the multi-source data collection module and the time-of-use electricity price curve to predict the total energy consumption cost in each period and generate peak-valley energy consumption optimization suggestions.

[0033] Preferably, in step S3, it includes the following steps:

[0034] Step S31: Judge the subjective weights of the prediction module, economy, technology, and environmental friendliness through the multi-objective optimization module;

[0035] Step S32: Calculate the objective weights through the entropy weight method based on the volatility of each index in the historical data, correct the subjective weight deviation, and obtain the final weights.

[0036] Step S33: Use the non-dominated sorting genetic algorithm to generate three Pareto optimization strategies with the goal of maximizing the comprehensive evaluation value based on the final weights obtained in Step S32.

[0037] Preferably, in Step S31, the influencing factors for evaluating economy include unit production cost and order profit margin, the influencing factors for evaluating technology include equipment utilization rate and order on-time delivery rate, and the influencing factors for evaluating environmental friendliness include unit product carbon emissions and the proportion of peak-valley electricity price energy consumption.

[0038] Preferably, in Step S4, when the adaptive adjustment module dynamically adjusts the equipment processing parameters, it adjusts the spindle speed and feed rate based on the real-time load and processing quality threshold.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1. The present invention has a multi-objective optimization module, which is used to evaluate the economy, technology, and environmental friendliness of the factory building respectively through the multi-objective optimization module, and then facilitate the generation of optimization strategies for multi-objective optimization.

[0041] 2. The present invention has a dynamic scheduling module, which facilitates the adjustment of the order scheduling queue through the dynamic scheduling module. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a schematic structural diagram of the system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] Next, in combination with the attached Figure 1 A further detailed description will be made of the specific implementation manners of the present invention.

[0045] As Figure 1 shown, in order to achieve the purpose of full-dimensional collection of equipment operation status, production tasks, and environmental data, a discrete manufacturing equipment efficiency maximization strategy determination system includes:

[0046] A multi-source data acquisition unit, including a multi-source data acquisition module for collecting equipment data, order data, and environmental data inside the factory, and an edge computing module for data cleaning;

[0047] It should be noted that the multi-source data acquisition module includes vibration sensors (used to monitor the mechanical status of equipment), equipment power on / off status sensors (recording equipment start / stop time), current sensors (collecting motor load), enterprise resource planning system (ERP) interface (obtaining production plan and order data), API interface (interfacing with MES system) and temperature and humidity sensors (monitoring environmental parameters); the edge computing module, based on edge computing nodes, uses sliding window mean filtering to eliminate noise data, and removes outliers through DBSCAN clustering algorithm, which can obtain key features such as equipment comprehensive efficiency (0EE) after cleaning, order completion rate, and actual energy consumption cost;

[0048] The intelligent decision-making unit includes a prediction module, a multi-objective optimization module and a weight fusion module; the prediction module is used to predict order demand, equipment health and equipment energy consumption cost, among which, order demand prediction: based on the ARIMA time series model, analyze the seasonal fluctuations and market trends of historical orders, and output the order volume forecast for the next 7 days; equipment health prediction: using LSTM neural network, input vibration spectrum peak (0-5kHz), current fluctuation variance (threshold ±10%), output the failure probability in the next 24 hours (trigger alarm when threshold>85%); energy consumption cost prediction: combining the time-of-use electricity price curve (peak / flat / valley time period) and production plan scheduling, predict the total energy consumption cost of each time period, and generate peak-valley transfer suggestions (in this embodiment, high energy consumption processes can be adjusted to valley electricity price periods);

[0049] The multi-objective optimization module is used to evaluate the economic, technical and environmental performance of the factory respectively; among them, economic performance: unit production cost (yuan / piece), order profit rate (%); technical performance: equipment utilization rate (%), order on-time delivery rate (%); environmental performance: unit product carbon emissions (kg / piece), peak and valley electricity price energy consumption ratio (%); the non-dominated sorting genetic algorithm (NSGA-II) with elite strategy is used to generate the Pareto frontier solution set;

[0050] The weight fusion module is used to combine the subjective weights of the prediction module, economy, technology and environment with the objective weights for weighted fusion, and finally generate an optimization strategy for multi-objective optimization; in this embodiment, the weight fusion module calculates the subjective weights (based on the expert scoring matrix) by the AHP hierarchical analysis method, combines the objective weights calculated by the entropy weight method, and generates a comprehensive weight by weighted fusion in a ratio of 6:4;

[0051] Execution control unit, including policy issuing module, adaptive adjustment module and dynamic scheduling module;

[0052] The policy distribution module converts the optimization policy into device control instructions (such as G-code, Modbus instructions) through the OPC UA protocol, and is used to send the generated optimization policy to the adaptive adjustment module after transcoding;

[0053] The adaptive adjustment module is used to adjust the device operation parameters to balance efficiency and energy consumption. In this embodiment, the adaptive adjustment module dynamically adjusts the spindle speed (range 500 - 3000 rpm) and feed rate (range 10 - 50 mm / s) based on the real-time load (triggered when the CPU utilization rate > 80%) and the machining quality threshold (tolerance ±0.05 mm);

[0054] The dynamic scheduling module is used to adjust the order queue. In this embodiment, the dynamic scheduling module adopts a weighted priority algorithm, with the customer level weight accounting for 70% (VIP customers first) and the liquidated damages cost weight accounting for 30%, to generate the production queue sorting;

[0055] The feedback optimization unit includes a digital twin simulation module and an incremental learning module;

[0056] The digital twin simulation module is used to simulate the optimization policy and verify the production capacity deviation; In this embodiment, the digital twin simulation module simulates the policy execution in Siemens NX, calculates the deviation between the theoretical production capacity and the actual production capacity, and triggers policy backtracking when the deviation value > 10%;

[0057] The incremental learning module adopts the Stochastic Gradient Descent (SGD) algorithm, and feeds the actual production data to the prediction module every day to update the model parameters, and is used to feed the collected daily actual production data to the prediction module and update the prediction module;

[0058] The present invention also discloses a method for determining the efficiency maximization strategy of a discrete manufacturing device, based on a system for determining the efficiency maximization strategy of a discrete manufacturing device, consisting of Figure 1 As shown, in order to be able to perform efficiency maximization adjustment on different manufacturing devices, it includes the following steps:

[0059] Preparation stage, system deployment, configure and calibrate the data acquisition unit, software, and interfaces of the system for determining the efficiency maximization strategy of the discrete manufacturing device, including sensor installation, enterprise resource planning system (ERP) interface configuration, and calibrate the clock synchronization accuracy of the edge computing node (error < 1 ms);

[0060] Step S1, multi-source data acquisition and edge preprocessing, collect device data, order data, and environmental data through the multi-source data acquisition module, and clean the collected data through the edge computing module;

[0061] In step S1, multi-source data collection includes the following steps:

[0062] Step S11: Real-time collect equipment vibration (sampling rate 10 kHz), current (accuracy ±0.5%), and temperature and humidity data (resolution 0.1 °C) through the multi-source data collection module, and synchronize the production plan scheduling, order urgency (high / medium / low), profit margin (orders with 15% profit margin are high-quality orders), and delivery cycle (orders with ≤7 days are urgent orders) of the enterprise resource planning (ERP) system;

[0063] Step S12: Use the edge computing nodes through the edge computing module to clean the original data and extract key features;

[0064] It should be noted that the edge computing module refers to a device deployed at the network edge with capabilities such as computing, storage, and communication. In this embodiment, it is a micro data center that can provide data storage and computing services, and cleans the original data by removing noise, filling in missing values, and correcting outliers;

[0065] The key features include one or more of the overall equipment effectiveness (OEE = availability rate × performance rate × first-pass yield), order completion rate (actual completed quantity / planned quantity), and actual energy consumption cost (kWh × electricity price);

[0066] Step S2: Multi-dimensional prediction, predict order demand, equipment health, and equipment energy consumption cost;

[0067] In step S2, multi-dimensional prediction includes the following steps:

[0068] Step S21: Order demand prediction: Analyze the historical order seasonal fluctuations and market trends using a time series model, and output the predicted results of the future weekly order volume. In this embodiment, the ARIMA model is used, and R2>0.85;

[0069] Step S22: Equipment health prediction: Build a fault warning model based on a long short-term memory network, input the peak value of the vibration spectrum and the variance of the current fluctuation, and output the alarm of the fault probability threshold. In this embodiment, the LSTM model is used, and AUC>0.9;

[0070] Step S23: Energy consumption cost prediction: Combine the production plan scheduling collected by the multi-source data collection module and the time-of-use electricity price curve to predict the total energy consumption cost of each period and generate peak-valley energy consumption optimization suggestions;

[0071] Step S3: Generate multi-objective optimization strategies, build an economic, technical, and environmental evaluation index system; fuse subjective weights and objective weights to generate a comprehensive weight; finally generate multiple Pareto optimization strategies through the multi-objective optimization module;

[0072] In step S3, the following steps are included:

[0073] Step S31: The multi-objective optimization module determines the subjective weights of the manual judgment prediction module, economy, technology, and environmental friendliness.

[0074] In step S31, the influencing factors for evaluating the economy are the unit production cost and the order profit margin; the influencing factors for evaluating the technology are the equipment utilization rate and the order on-time delivery rate; the influencing factors for evaluating the environmental friendliness are the carbon emissions per unit product and the proportion of peak-valley electricity price energy consumption. In this embodiment, after calculation by the AHP (Analytic Hierarchy Process), the proportion of subjective weights is: economy (weight 40%), technology (35%), environmental friendliness (25%).

[0075] Step S32: Based on the volatility of each index in the historical data, the objective weights are calculated by the entropy weight method to correct the deviation of the subjective weights. In this embodiment, after correction by the entropy weight method, a comprehensive weight is generated (economy 38%, technology 36%, environmental friendliness 26%).

[0076] Step S33: The non-dominated sorting genetic algorithm is used to generate 3 Pareto optimization strategies with the goal of maximizing the comprehensive evaluation value. In this embodiment, 3 Pareto optimization strategies are generated through the NSGA-II algorithm (Strategy A focuses on the economy, Strategy B balances the three, and Strategy C focuses on environmental friendliness).

[0077] Step S4: Strategy execution and dynamic adjustment. After receiving the optimization strategy, the strategy distribution module converts the optimization strategy into equipment control instructions through the industrial automation standard protocol and sends them to the adaptive adjustment module. The adaptive adjustment module monitors the equipment load in real time and dynamically adjusts the equipment processing parameters; the production queue is reordered according to the customer level and the penalty cost through the dynamic scheduling module.

[0078] In step S4, when the adaptive adjustment module dynamically adjusts the equipment processing parameters, based on the real-time load and the processing quality threshold, the spindle speed and the feed rate are adjusted (for example, the spindle speed is reduced by 15% to balance the energy consumption).

[0079] Step S5: Digital twin verification and model iteration. Through the digital twin simulation module, the execution of the optimization strategy is simulated on the digital twin platform, and the deviation between the theoretical production capacity and the actual production capacity is calculated. When the deviation value between the actual production capacity and the theoretical production capacity > 10%, the strategy backtracking is triggered; through the incremental learning module, the daily actual production data collected is fed back to the prediction module, and the prediction module is updated daily (learning rate η = 0.01).

[0080] The structure of the present invention is novel, the concept is ingenious, and the operation is simple and convenient. Through this design, the purpose of improving the equipment utilization rate is effectively achieved, thereby increasing the co-manufacturing efficiency of manufacturing equipment, reducing the energy consumption cost, improving the on-time delivery rate, and reducing the carbon emissions.

[0081] Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A discrete manufacturing equipment efficiency maximization strategy determination system, characterized by: include: A multi-source data acquisition unit, including a multi-source data acquisition module for collecting equipment data, order data, and environmental data inside the factory, and an edge computing module for data cleaning; Intelligent decision-making unit, including prediction module, multi-objective optimization module and weight fusion module; The forecasting module is used to forecast order demand, equipment health, and equipment energy consumption costs; Multi-objective optimization module, used to evaluate the economic, technical and environmental performance of the plant; The weight fusion module is used to combine the subjective weights of the prediction module, economy, technology and environment with the objective weights to finally generate an optimization strategy for multi-objective optimization; Execution control unit, including policy issuing module, adaptive adjustment module and dynamic scheduling module; A strategy delivery module is used to transcode the generated optimization strategy and send it to the adaptive adjustment module; Adaptive adjustment module, used to adjust equipment operating parameters to balance efficiency and energy consumption; Dynamic scheduling module, used to adjust the order queue; Feedback optimization unit, including digital twin simulation module and incremental learning module; The digital twin simulation module is used to simulate the optimization strategy and verify the capacity deviation; The incremental learning module is used to feed back the collected daily actual production data to the prediction module and to update the prediction module regularly.

2. A discrete manufacturing equipment efficiency maximization strategy determination system according to claim 1, characterized in that: The multi-source data acquisition module includes a vibration sensor, an equipment power on / off status sensor, a current sensor, an enterprise resource planning system, an API interface, and a temperature and humidity sensor.

3. A method for determining a strategy for maximizing the efficiency of discrete manufacturing equipment, comprising a system for determining a strategy for maximizing the efficiency of discrete manufacturing equipment according to any one of claims 1 to 2, characterized in that: The following steps are involved: Preparation phase, system deployment, configuration and calibration of the system’s data acquisition units, software, and interfaces; Step S1: Multi-source data collection and edge preprocessing: The device data, order data and environment data are collected through the multi-source data collection module, and the collected data is cleaned through the edge computing module; Step S2: multi-dimensional prediction, using the prediction module to predict order demand, equipment health, and equipment energy consumption cost; Step S3, generating a multi-objective optimization strategy, constructing an economic, technical and environmental evaluation index system through a multi-objective optimization module; integrating subjective weights and objective weights through a weight fusion module to generate a comprehensive weight; The multi-objective optimization module finally generates multiple Pareto optimization strategies and sends them to the strategy delivery module; Step S4, strategy execution and dynamic adjustment. After the strategy issuing module receives the optimization strategy, it converts the optimization strategy into equipment control instructions through the industrial automation standard protocol and sends it to the adaptive adjustment module. The adaptive adjustment module monitors the equipment load in real time and dynamically adjusts the equipment processing parameters. The dynamic scheduling module re-sorts the production queue according to the customer level and the penalty cost. Step S5, digital twin verification and model iteration, simulate the execution of the optimization strategy on the digital twin platform through the digital twin simulation module, calculate the deviation between the theoretical capacity and the actual capacity, and trigger the strategy backtracking when the deviation value between the actual capacity and the theoretical capacity is greater than 10%; through the incremental learning module, feed back the collected daily actual production data to the prediction module, and perform daily incremental updates on the prediction module.

4. The method for determining a discrete manufacturing equipment efficiency maximization strategy according to claim 3, characterized in that: In step S1, multi-source data collection includes the following steps: Step S11, real-time collection of equipment vibration, current, temperature and humidity data through a multi-source data collection module, and synchronization of production schedule, order urgency, profit margin and delivery cycle of the enterprise resource planning system; Step S12: Use the edge computing module to clean the original data using the edge computing nodes and extract key features.

5. The method for determining a discrete manufacturing equipment efficiency maximization strategy according to claim 4, characterized in that: In step S12, the key features include one or more of equipment overall efficiency, order completion rate, and actual energy consumption cost.

6. The method for determining a discrete manufacturing equipment efficiency maximization strategy according to claim 3, characterized in that: In step S2, the multi-dimensional prediction includes: Order demand forecasting: Use time series models to analyze historical order seasonal fluctuations and market trends, and output future weekly order volume forecasts; Equipment health prediction: Build a fault warning model based on long short-term memory network, input vibration spectrum peak value and current fluctuation variance, and output fault probability threshold alarm; Energy consumption cost prediction: Combined with the production schedule and time-of-use electricity price curve collected by the multi-source data acquisition module, the total energy consumption cost of each period is predicted and peak and valley energy consumption optimization suggestions are generated.

7. The method for determining a discrete manufacturing equipment efficiency maximization strategy according to claim 3, characterized in that: The step S3 includes the following steps: Step S31, judging the subjective weights of the prediction module, economy, technology and environment through a multi-objective optimization module; Step S32: Based on the volatility of each indicator in the historical data, the objective weight is calculated by the entropy weight method, and the subjective weight deviation is corrected to obtain the final weight; Step S33: Using a non-dominated sorting genetic algorithm based on the final weights obtained in step S32, with the goal of maximizing the comprehensive evaluation value, three Pareto optimization strategies are generated.

8. The method for determining a discrete manufacturing equipment efficiency maximization strategy according to claim 7, characterized in that: In step S31, the factors affecting the economic evaluation include unit production cost and order profit margin, the factors affecting the technical evaluation include equipment utilization and order on-time delivery rate, and the factors affecting the environmental evaluation include unit product carbon emissions and peak-valley electricity price energy consumption ratio.

9. The method for determining a discrete manufacturing equipment efficiency maximization strategy according to claim 3, characterized in that: In step S4, when the adaptive adjustment module dynamically adjusts the equipment processing parameters, it adjusts the spindle speed and feed rate based on the real-time load and processing quality threshold.

Images