Intelligent processing and manufacturing management system

Abstract

The invention, which relates to the processing and manufacturing field, discloses an intelligent processing and manufacturing management system comprising a data acquisition module, a data transmission and processing module, a production planning and scheduling module, an equipment management module, a quality management module, an inventory management module and a personnel management module. And the equipment management module is used for carrying out full-life-cycle management on the processed and manufactured equipment, monitoring the running state of the equipment in real time, and predicting the fault occurrence probability of the equipment through analysis of the running data of the equipment. According to the management system for intelligent processing and manufacturing, refined and intelligent management of the whole life cycle of equipment from access to scrapping can be realized, the reliability, the available duration and the operation efficiency of the equipment can be effectively improved, common fault models can be identified through the constructed diagnosis model, and the reliability of the equipment can be improved. And faults caused by multiple factors can be accurately positioned and analyzed.

Description

Technical Field

[0001] The present invention relates to the field of processing and manufacturing, and in particular to a management system for intelligent processing and manufacturing. Background Art

[0002] The processing and manufacturing industry is a general term for industrial sectors that mainly process raw materials such as mining products and agricultural products, or reprocess and repair the products of the processing industry, or assemble parts. It generally refers to metallurgy, machinery, thick-walled steel pipes, electronics, chemistry, petrochemicals, wood processing, building materials, papermaking, textiles, food, leather industries, etc.

[0003] The processing and manufacturing industry purchases raw materials on its own and carries out large-scale, standardized, and production-line processing. Large-scale, standardized, and production lines are the most important characteristics of the processing and manufacturing industry.

[0004] In the traditional equipment maintenance and inventory management field of the manufacturing industry, decision-making often relies on experience and simple rules, and cannot make full use of the historical data and real-time data of the equipment for assistance, which makes it more troublesome for the staff to carry out equipment maintenance and inventory management, and seriously affects their efficiency;

[0005] In the past, equipment maintenance was usually post-failure repair and preventive maintenance based on fixed cycles. The status of key equipment components could not be monitored in real time. When a failure occurred outside the fixed cycle, it would cause downtime and interrupt processing and manufacturing.

[0006] Therefore, it is necessary to propose an intelligent processing and manufacturing management system to solve the above problems. Summary of the invention

[0007] The main purpose of the present invention is to provide an intelligent processing and manufacturing management system that can effectively solve the problems in the background technology.

[0008] To achieve the above object, the technical solution adopted by the present invention is:

[0009] An intelligent processing and manufacturing management system, including a data acquisition module, a data transmission and processing module, a production planning and scheduling module, an equipment management module, a quality management module, an inventory management module, and a personnel management module. The equipment management module is used to manage the entire life cycle of the processing and manufacturing equipment, and monitor the operating status of the equipment in real time, including the equipment's startup time, shutdown time, operating speed, power consumption, and fault alarm. By analyzing the equipment's operating data, the probability of equipment failure is predicted;

[0010] The inventory management module is electrically connected to the procurement system and the production system, and is used to implement inventory management of raw materials, semi-finished products and finished products. Based on the constructed inventory demand forecasting model, the inventory is analyzed and evaluated, and an information sharing platform with suppliers is established to manage the inventory in a timely manner.

[0011] Preferably, the data acquisition module collects data based on sensors installed in the processing and manufacturing area, including the collection of working status data, working environment data, processing process data, and product inspection data. The sensors include basic physical parameter sensors, working condition perception sensors, and environmental sensors.

[0012] The basic physical parameter sensors include but are not limited to temperature sensors, pressure sensors, and displacement sensors; the working condition sensing sensors include but are not limited to cutting force sensors, coolant sensors, friction sensors, and wear particle sensors; the environmental sensors include but are not limited to humidity sensors, dust particle sensors, and electromagnetic interference sensors;

[0013] The data transmission and processing module is used to transmit the data collected by the data collection module, and to clean and organize the data in real time;

[0014] The production planning and scheduling module uses genetic algorithms to generate the optimal production plan and scheduling solution based on the acquired order information, combined with inventory conditions, equipment capacity, and process requirements;

[0015] The quality management module monitors and adjusts the manufacturing process in real time based on the processing data and product inspection data collected in real time;

[0016] The personnel management module is used to comprehensively manage the personnel information on the processing and manufacturing production line, including the basic information of the personnel, skill level, training records, and attendance status.

[0017] Preferably, the data acquisition module also includes an adaptive acquisition module for automatically adjusting the data acquisition strategy according to the actual processing conditions of the processing and manufacturing equipment.

[0018] Preferably, the equipment management module is electrically connected to the data acquisition module, and the equipment management module includes an equipment access and identification module, a diagnosis and predictive maintenance module, and an equipment maintenance management and knowledge base module. The equipment access and identification module uses a Modbus intelligent gateway to access processing equipment of different brands and manufactured in different years;

[0019] Assign a unique digital identity to each device, which is built on blockchain technology;

[0020] The equipment maintenance management and knowledge base module includes maintenance plan formulation, maintenance work order generation, maintenance personnel scheduling, and maintenance process recording.

[0021] Preferably, the diagnosis and predictive maintenance module includes a fault diagnosis module and a predictive maintenance module. The fault diagnosis module includes a data integration module, a fusion diagnosis module, a knowledge acquisition and organization module, and a knowledge graph application module. The data integration module is used to collect data collected by the data acquisition module, equipment operation status data, historical maintenance records, and product quality data, perform feature extraction on the data based on convolutional neural networks and recurrent neural networks, and mark the extracted fault features.

[0022] The fusion diagnosis module is used to compare the fault features of the data acquisition module and the marked ones. When the comparison results are the same, the current processing and manufacturing equipment is diagnosed as a fault state. A fusion diagnosis model based on a Bayesian network is constructed based on the extracted features. The extracted features are used as the input nodes of the Bayesian network, and the equipment fault type is used as the output node. Through Bayesian reasoning, the probability of different faults occurring under a given combination of multiple features is calculated. The formula is as follows:

[0023]

[0024] Where A is a different fault type, B is a different feature combination, P(A) is the prior probability of fault A occurring, P(B|A) is the probability of feature combination B occurring when fault A occurs, and P(A|B) is the posterior probability of fault A occurring under feature combination B. The probabilities of all faults A that will occur with a feature combination B are calculated. The fault A with the highest value has the highest probability of occurrence, and the currently faulty component should be replaced.

[0025] Preferably, the knowledge acquisition and organization module is used to collect equipment manuals, maintenance guides, maintenance experience and cases of internal experts provided by equipment manufacturers, and data collected by equipment maintenance management and knowledge base modules to form an initial knowledge source, perform semantic extraction and relationship construction on the knowledge source, and form a knowledge graph. In the knowledge graph, equipment components, fault phenomena, fault causes and maintenance methods are used as nodes, and causal relationships and association relationships between nodes are used as edges;

[0026] The knowledge graph application module is used to perform intelligent reasoning using the knowledge graph during the fault diagnosis process. When at least one fault phenomenon is detected in the equipment, the cause of the fault is quickly located and the corresponding maintenance method is recommended through the knowledge graph.

[0027] Preferably, the predictive maintenance module includes a degradation model building module, a remaining life prediction module, an environmental modeling and strategy network, and a strategy evaluation and update module. The degradation model building module builds a performance degradation model of the component based on the physical characteristics and operation mechanism of the key components of the equipment, and uses the real-time operation data of the equipment to estimate and update the parameters of the degradation model;

[0028] The remaining service life prediction module is used to predict the remaining service life of a component according to its current performance status and performance degradation model, and the specific steps are as follows:

[0029] Clean the component data collected by the data acquisition module, remove outliers and noise, establish a theoretical wear model based on the physical principle of component wear, select an artificial neural network, whose input layer nodes are the characteristic parameters of the equipment and output layer nodes are the wear amount of the equipment, and train the collected data;

[0030] During the actual operation of the equipment, the real-time collected equipment operation data is input into the trained theoretical wear model to obtain the predicted value of the current wear state of the equipment. Based on the predicted value of the equipment wear and the equipment scrapping standard, it is judged whether the equipment is approaching the end of its service life. When the predicted wear is close to the scrapping standard, an early warning message for replacing the equipment is issued in time.

[0031] According to the predicted value of the current wear state of the equipment and the wear rate of the equipment, the remaining life of the equipment is calculated using the formula:

[0032] S = (1-M)*L;

[0033] Where s is the remaining life of the equipment, M is the percentage of the current wear of the equipment to the total allowable wear, and L is the current wear rate of the equipment.

[0034] Preferably, the environment modeling and strategy network models the equipment maintenance process based on the Markov decision process, with the equipment state as the state space, the maintenance operation as the action space, the maintenance cost and the equipment downtime as the reward signal, and constructs a deep Q-network for continuously interacting with the equipment maintenance process model so that the deep Q-network learns the optimal maintenance strategy, records the maintenance strategy, and learns whether to perform maintenance immediately or postpone maintenance according to the currently calculated remaining life of the equipment and the production task schedule;

[0035] The strategy evaluation and update module evaluates the maintenance strategy obtained by the deep Q-network based on the historical maintenance strategy and equipment maintenance process model. By comparing the maintenance cost and equipment availability under different strategies, the deep Q-network is updated. The specific steps are as follows:

[0036] Based on the maintenance strategy and data acquisition module, the equipment status information, the adopted maintenance strategy, the maintenance cost, and the subsequent operation performance of the equipment are collected, and the collected data are sorted and classified;

[0037] Calculate the total cost of each maintenance event, including direct and indirect costs. When evaluating the strategic network, consider the maintenance cost of the equipment throughout its entire life cycle from commissioning to retirement, and compare the average maintenance costs under different strategies.

[0038] Calculate the ratio of the equipment's normal operation time to the total time over a period of time. A high normal operation time ratio indicates high equipment availability. The normal operation time ratio of the equipment within a month is calculated according to the formula:

[0039]

[0040] Where B is the normal operation time ratio of the equipment in a month, Y is the normal operation time of the equipment in a month, and Z is the total working time of the equipment in a month;

[0041] The average operating time between two adjacent equipment failures is calculated. The longer the time, the more effective the maintenance strategy currently used by the equipment is. The maintenance strategy is selected based on the normal operating time ratio and the average maintenance cost under different strategies. The highest normal operating time ratio and the lowest maintenance cost are selected as the optimal maintenance strategy.

[0042] Preferably, the inventory management module includes an inventory perception module, an inventory analysis and prediction module, and an intelligent decision-making module. The inventory perception module includes ultra-high frequency RFID tags affixed to raw materials, semi-finished products and finished products, and a full range of RFID reader-writer arrays deployed in the warehouse, which are used to identify the location, quantity, and entry and exit time of inventory items in real time;

[0043] The inventory analysis and forecasting module analyzes historical order data, market trend data, seasonal factors, macroeconomic data, and social media public opinion data based on deep learning algorithms to build a highly accurate inventory demand forecasting model;

[0044] Based on data mining technology, we conduct in-depth analysis of inventory turnover rate, inventory cost, and obsolete inventory ratio to comprehensively evaluate the health of inventory.

[0045] Preferably, the intelligent decision-making module is used to establish an information sharing platform with suppliers, so that suppliers can view our inventory levels, production plans and order requirements in real time, and we can also obtain suppliers' inventory status, production progress and delivery information in a timely manner. The production department can query the quantity and location of inventory raw materials and semi-finished products in real time to arrange production tasks; the intelligent decision-making module automatically adjusts inventory data and triggers replenishment and material allocation processes based on production progress and material consumption. The specific steps are: setting safety stocks for each raw material inventory;

[0046] During the production process, when the material consumption is reduced due to equipment failure in the production process, the intelligent decision-making module will promptly adjust the inventory reserve of the material and notify the supplier according to the new production plan.

[0047] Compared with the prior art, the present invention provides an intelligent processing and manufacturing management system, which has the following beneficial effects:

[0048] 1. The intelligent processing and manufacturing management system can collect working status data, working environment data, processing data, and product inspection data in processing and manufacturing based on sensors installed in the processing and manufacturing area through the data acquisition module. It can be used as a basis to assist staff in all-round management of the processing and manufacturing process. At the same time, it can also automatically adjust the data acquisition strategy according to the actual processing conditions of the processing and manufacturing equipment. When the equipment performs high-precision processing tasks, the data collection frequency of precision-related parameters is increased. When the equipment is in no-load or low-load operation, the collection frequency of these parameters is reduced. At the same time, the collection of data related to equipment energy consumption is increased. Based on this, the energy utilization efficiency of management equipment can be better optimized.

[0049] 2. This intelligent processing and manufacturing management system can achieve refined and intelligent management of the entire life cycle of equipment from access to scrapping through the set equipment management module, which can effectively improve the reliability, available time and operating efficiency of the equipment. Through the constructed diagnostic model, it can not only identify common fault models, but also accurately locate and analyze faults caused by multiple factors. It can also establish a separate model for processing and manufacturing parts, and use the real-time data of the parts to update the model, which can more accurately reflect the actual degradation of the parts. According to the prediction results, the staff can reasonably arrange the equipment maintenance time to avoid production interruptions caused by sudden equipment failures. It can predict the remaining life of key components of the equipment, which is convenient for maintenance personnel to prepare spare parts and arrange maintenance work in advance.

[0050] 3. The intelligent processing and manufacturing management system can record maintenance strategies through previous maintenance content, and evaluate maintenance strategies based on the records, so as to evaluate the optimal maintenance strategy for equipment maintenance. Therefore, it can improve maintenance efficiency and equipment available time, and reduce total maintenance costs. When managing processing and manufacturing, it can always provide managers with the most preferred maintenance strategy, and can select corresponding managers according to the maintenance strategy, which can further improve the maintenance efficiency of equipment and improve the management ability and efficiency of staff.

[0051] 4. This intelligent processing and manufacturing management system can improve the staff's management ability of processing and manufacturing inventory through the set inventory management module. It can effectively identify the location, quantity and entry and exit time of all products during processing and manufacturing, replenish and handle inventory backlogs according to their remaining inventory and future demand. It can also establish an information sharing platform with suppliers based on inventory levels, reduce the risks caused by communication costs and information asymmetry between suppliers and itself, adjust the reserved quantity of products in inventory in time, and re-evaluate replenishment needs according to the new production plan to avoid unnecessary inventory backlogs. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0053] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0054] Embodiment 1:

[0055] like Figure 1 As shown, an intelligent processing and manufacturing management system includes a data acquisition module, a data transmission and processing module, a production planning and scheduling module, an equipment management module, a quality management module, an inventory management module, and a personnel management module. The equipment management module is used to manage the entire life cycle of the processing and manufacturing equipment, and monitor the operating status of the equipment in real time, including the equipment's startup time, shutdown time, operating speed, power consumption, and fault alarm. By analyzing the equipment's operating data, the probability of equipment failure is predicted;

[0056] The inventory management module is electrically connected to the procurement system and the production system, and is used to implement inventory management of raw materials, semi-finished products and finished products. Based on the constructed inventory demand forecasting model, it analyzes and evaluates the inventory, and establishes an information sharing platform with suppliers to manage the inventory in a timely manner;

[0057] The data acquisition module collects data based on sensors installed in the processing and manufacturing area, including work status data, work environment data, processing data, and product inspection data. The sensors include basic physical parameter sensors, working condition perception sensors, and environmental sensors.

[0058] Basic physical parameter sensors include but are not limited to temperature sensors, pressure sensors, and displacement sensors; working condition sensing sensors include but are not limited to cutting force sensors, coolant sensors, friction sensors, and wear particle sensors; environmental sensors include but are not limited to humidity sensors, dust particle sensors, and electromagnetic interference sensors;

[0059] The data transmission and processing module is used to transmit the data collected by the data acquisition module, and to clean and organize it in real time;

[0060] The production planning and scheduling module uses genetic algorithms to generate the optimal production plan and scheduling solution based on the acquired order information, inventory status, equipment capacity, and process requirements;

[0061] The quality management module monitors and adjusts the manufacturing process in real time based on the real-time collected processing data and product inspection data;

[0062] The personnel management module is used to comprehensively manage the personnel information on the processing and manufacturing production line, including basic information, skill level, training records, and attendance of personnel. According to production tasks and personnel skills, personnel positions and work tasks are reasonably arranged to achieve optimal allocation of human resources. When new products are launched, personnel with relevant skills and experience are selected to form a production team, and targeted training courses are arranged. By setting up smart terminal devices at the production site, employees can view work tasks in real time, submit work progress reports, and give feedback on problems and suggestions;

[0063] The data acquisition module also includes an adaptive acquisition module, which is used to automatically adjust the data acquisition strategy according to the actual processing conditions of the processing and manufacturing equipment. When the equipment is performing high-precision processing tasks, the data collection frequency of the processing accuracy parameters is increased; when the equipment is in a no-load or low-load operating state, the collection frequency of the processing accuracy parameters is reduced, and the collection frequency of the equipment energy consumption data is increased.

[0064] Embodiment 2:

[0065] like Figure 1 As shown, an intelligent processing and manufacturing management system, the equipment management module is electrically connected to the data acquisition module, the equipment management module includes an equipment access and identification module, a diagnosis and predictive maintenance module, an equipment maintenance management and knowledge base module, and the equipment access and identification module adopts a Modbus intelligent gateway to access processing equipment of different brands and different years;

[0066] Assign a unique digital identity to each device, which is built on blockchain technology;

[0067] The equipment maintenance management and knowledge base module includes maintenance plan formulation, maintenance work order generation, maintenance personnel scheduling, and maintenance process records. The maintenance plan is automatically generated based on the equipment fault diagnosis results and production plan, and can be adjusted manually; the maintenance work order records the content of the maintenance task, the required spare parts, the estimated maintenance time and the actual maintenance status, which are used to facilitate traceability and statistical analysis; maintenance personnel scheduling dispatches the corresponding personnel to maintain the equipment based on the characteristics of the fault; the maintenance process record is used to record the overall maintenance process of the equipment; it also includes an equipment management knowledge base, which is used to organize and store the equipment's operating manuals, fault diagnosis cases, and maintenance experience.

[0068] The diagnosis and predictive maintenance module includes a fault diagnosis module and a predictive maintenance module. The fault diagnosis module includes a data integration module, a fusion diagnosis module, a knowledge acquisition and organization module, and a knowledge graph application module. The data integration module is used to collect data collected by the data acquisition module, equipment operation status data, historical maintenance records, and product quality data, and extract features from the data based on convolutional neural networks and recurrent neural networks, and mark the extracted fault features.

[0069] The fusion diagnosis module is used to compare the fault features of the data acquisition module and the marked ones. When the comparison results are the same, the current processing and manufacturing equipment is diagnosed as a fault state. Based on the extracted features, a fusion diagnosis model based on the Bayesian network is constructed. The extracted features are used as the input nodes of the Bayesian network, and the equipment fault type is used as the output node. Through Bayesian reasoning, the probability of different faults occurring under a given combination of multiple features is calculated. The formula is as follows:

[0070]

[0071] Where A is a different fault type, B is a different feature combination, P(A) is the prior probability of fault A occurring, P(B|A) is the probability of feature combination B occurring when fault A occurs, and P(A|B) is the posterior probability of fault A occurring under feature combination B. The probabilities of all faults A occurring under a feature combination B are calculated. The fault A with the highest value has the highest probability of occurrence, and the currently faulty component is replaced.

[0072] When multiple features such as abnormal vibration frequency, increased temperature and decreased machining accuracy appear at the same time, the probabilities of different fault types such as equipment wear and motor failure are calculated to accurately diagnose the cause of the fault.

[0073] The knowledge acquisition and organization module is used to collect equipment manuals, maintenance guides, maintenance experience and cases of internal experts provided by equipment manufacturers, and data collected by equipment maintenance management and knowledge base modules to form an initial knowledge source, perform semantic extraction and relationship construction on the knowledge source, and form a knowledge graph. In the knowledge graph, equipment components, fault phenomena, fault causes and maintenance methods are used as nodes, and the causal relationship and correlation relationship between nodes are used as edges. Take manufacturing tools as an example: tool wear is used as a fault phenomenon node, which is connected to the processing accuracy reduction phenomenon node, and at the same time points to the cause nodes of unreasonable cutting parameters and poor tool materials. These cause nodes are connected to the corresponding maintenance method nodes such as adjusting cutting parameters and replacing tool materials;

[0074] The knowledge graph application module is used to perform intelligent reasoning using the knowledge graph during the fault diagnosis process. When at least one fault phenomenon is detected in the equipment, the cause of the fault is quickly located and the corresponding maintenance method is recommended through the knowledge graph. When the surface roughness of parts processed by machine tools is detected to increase, the knowledge graph can be used to infer that the cause is tool wear or insufficient cutting fluid, and based on this, maintenance recommendations such as replacing tools and adding cutting fluid are provided.

[0075] The predictive maintenance module includes a degradation model building module, a remaining life prediction module, an environmental modeling and strategy network, and a strategy evaluation and update module. The degradation model building module builds a performance degradation model of the key components of the equipment based on their physical characteristics and operating mechanisms, and uses the real-time operating data of the equipment to estimate and update the parameters of the degradation model. Take the ball screw used in the processing and manufacturing of machine tools as an example: for the ball screw of the machine tool, considering its material fatigue and wear factors, a ball screw accuracy degradation model with operating time, load size, and lubrication conditions as variables is established. By real-time monitoring of the load, temperature, and vibration data of the ball screw, the data is substituted into the degradation model, and the parameters in the model are continuously corrected to make the model more accurately reflect the actual degradation of the components.

[0076] The remaining service life prediction module is used to predict the remaining service life of a component based on its current performance status and performance degradation model. The specific steps are as follows:

[0077] Clean the component data collected by the data acquisition module, remove outliers and noise, establish a theoretical wear model based on the physical principle of component wear, select an artificial neural network, whose input layer nodes are the characteristic parameters of the equipment and output layer nodes are the wear amount of the equipment, and train the collected data;

[0078] During the actual operation of the equipment, the real-time collected equipment operation data is input into the trained theoretical wear model to obtain the predicted value of the current wear state of the equipment. Based on the predicted value of the equipment wear and the equipment scrapping standard, it is judged whether the equipment is approaching the end of its service life. When the predicted wear is close to the scrapping standard, an early warning message for replacing the equipment is issued in time.

[0079] According to the predicted value of the current wear state of the equipment and the wear rate of the equipment, the remaining life of the equipment is calculated using the formula:

[0080] S = (1-M)*L;

[0081] Where S is the remaining life of the equipment, M is the percentage of the current wear of the equipment to the total allowable wear, and L is the current wear rate of the equipment.

[0082] The environment modeling and policy network models the equipment maintenance process based on the Markov decision process. The equipment state is used as the state space, the maintenance operation is used as the action space, and the maintenance cost and equipment downtime are used as reward signals. A deep Q-network is constructed to continuously interact with the equipment maintenance process model so that the deep Q-network learns the optimal maintenance strategy, records the maintenance strategy, and learns whether to perform maintenance immediately or postpone maintenance based on the currently calculated remaining life of the equipment and the production task schedule.

[0083] The strategy evaluation and update module evaluates the maintenance strategy obtained by the deep Q-network based on the historical maintenance strategy and equipment maintenance process model. By comparing the maintenance cost and equipment availability under different strategies, the deep Q-network is updated. The specific steps are as follows:

[0084] Based on the maintenance strategy and data acquisition module, the equipment status information, maintenance strategy adopted, maintenance cost, and subsequent operation performance of the equipment are collected, and the collected data is sorted and classified, including recording the equipment model, operation time, fault symptoms, specific maintenance operations taken, and corresponding costs and effects for each maintenance event;

[0085] Calculate the total cost of each maintenance event, including direct costs, such as spare parts purchase costs and maintenance personnel time costs; indirect costs, such as production delays caused by equipment downtime and scrap costs caused by quality degradation. When evaluating the strategy network, consider the maintenance cost of the equipment throughout its entire life cycle from commissioning to scrapping, and compare the average maintenance costs under different strategies;

[0086] Calculate the ratio of the equipment's normal operation time to the total time over a period of time. A high normal operation time ratio indicates high equipment availability. The normal operation time ratio of the equipment within a month is calculated according to the formula:

[0087]

[0088] Where B is the normal operation time ratio of the equipment in a month, Y is the normal operation time of the equipment in a month, and Z is the total working time of the equipment in a month;

[0089] The average operating time between two adjacent equipment failures is calculated. The longer the time, the more effective the maintenance strategy currently used by the equipment is. The maintenance strategy is selected based on the normal operating time ratio and the average maintenance cost under different strategies. The highest normal operating time ratio and the lowest maintenance cost are selected as the optimal maintenance strategy.

[0090] Embodiment three:

[0091] like Figure 1 An intelligent processing and manufacturing management system, the inventory management module includes an inventory perception module, an inventory analysis and prediction module, and an intelligent decision-making module. The inventory perception module includes ultra-high frequency RFID tags attached to raw materials, semi-finished products and finished products, and a full range of RFID reader-writer arrays deployed in the warehouse, which are used to identify the location, quantity, and entry and exit time of inventory items in real time;

[0092] The inventory analysis and forecasting module analyzes historical order data, market trend data, seasonal factors, macroeconomic data, and social media public opinion data based on deep learning algorithms to build a highly accurate inventory demand forecasting model. By analyzing the sales fluctuations of a certain type of processed products in different seasons in the past few years, combined with the current market development trend reports of related industries and the discussion of similar products by consumers on social media, the market demand for the product in the next few months is predicted, thereby providing a forward-looking decision-making basis for inventory management, arranging raw material procurement and production plans in advance, and avoiding inventory backlogs and stockouts;

[0093] Based on data mining technology, we conduct in-depth analysis of inventory turnover rate, inventory cost, and obsolete inventory ratio, and comprehensively evaluate the health of inventory. When the inventory turnover rate of a certain type of raw material continues to decline and the obsolete inventory ratio gradually increases, we automatically generate an inventory optimization recommendation report to prompt managers whether they need to adjust procurement strategies, launch promotional activities to clear obsolete inventory, and re-evaluate the safety inventory level of the raw material.

[0094] The intelligent decision-making module is used to establish an information sharing platform with suppliers. Suppliers can view our inventory levels, production plans and order requirements in real time. We can also obtain suppliers' inventory status, production progress and delivery information in a timely manner. The production department can query the quantity and location of inventory raw materials and semi-finished products in real time to arrange production tasks; the intelligent decision-making module automatically adjusts inventory data and triggers replenishment and material allocation processes based on production progress and material consumption. The specific steps are: set safety stock for each raw material inventory. When one of our raw materials in stock is higher than 10% of the safety stock, send early warning information to the supplier in advance, and the supplier arranges production and delivery in advance based on the early warning information;

[0095] During the production process, when the material consumption is reduced due to equipment failure in the production process, the intelligent decision-making module will promptly adjust the inventory reserve of the material and notify the supplier according to the new production plan.

[0096] It should be noted that the present invention is an intelligent management system for processing and manufacturing. When in use, physical parameter sensors, working condition perception sensors, and environmental sensors are installed at appropriate locations in the processing and manufacturing area. The data acquisition module collects data based on this and sets the data collection frequency. When the equipment performs high-precision processing tasks, the data collection frequency of the processing accuracy parameters is increased; when the equipment is in a no-load or low-load operating state, the collection frequency of the processing accuracy parameters is reduced, and the collection frequency of the equipment energy consumption data is increased. Each processing and manufacturing equipment is divided into a unique digital identity, and maintenance plans are formulated, maintenance work orders are generated, maintenance personnel are scheduled, and maintenance processes are recorded for each different equipment. Fault characteristics are extracted from the working data of the equipment and marked. When data consistent with the fault characteristics is collected, it is determined that the current equipment has a fault, and it is calculated which component in the equipment has the highest probability of failure. Based on the knowledge graph, the cause of the component failure is inferred and checked, and the corresponding maintenance personnel are arranged for the failure, and the component is replaced.

[0097] At the same time, a performance degradation model for the components is established, the model is updated based on the collected data, the remaining life of the current components is predicted based on the model, and information on component replacement is issued in a timely manner according to the predicted time;

[0098] Model the equipment maintenance process to generate the optimal maintenance strategy, and perform maintenance on faulty equipment and faults based on the generated maintenance strategy;

[0099] Analyze the sales fluctuations of a certain type of processed products in different seasons in the past few years, combine the development trend reports of related industries in the current market and the discussion of similar products by consumers on social media, predict the market demand for the product in the next few months, assist staff in providing forward-looking decision-making basis for inventory management, arrange the purchase and production and sales plans of required raw materials in advance according to the decisions, establish an information sharing platform with suppliers, and notify suppliers of products and remaining inventory to meet the quantity requirements of products.

[0100] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An intelligent processing and manufacturing management system, including a data acquisition module, a data transmission and processing module, a production planning and scheduling module, an equipment management module, a quality management module, an inventory management module, and a personnel management module, characterized in that: The equipment management module is used to manage the entire life cycle of the manufacturing equipment, monitor the operating status of the equipment in real time, including the equipment's startup time, shutdown time, operating speed, power consumption, and fault alarm, and predict the probability of equipment failure through analysis of equipment operation data; The inventory management module is electrically connected to the procurement system and the production system, and is used to implement inventory management of raw materials, semi-finished products and finished products. Based on the constructed inventory demand forecasting model, the inventory is analyzed and evaluated, and an information sharing platform with suppliers is established to manage the inventory in a timely manner.

2. The intelligent processing and manufacturing management system according to claim 1, characterized in that: The data acquisition module collects data based on sensors installed in the processing and manufacturing area, including work status data, work environment data, processing process data, and product inspection data. The sensors include basic physical parameter sensors, working condition perception sensors, and environmental sensors. The basic physical parameter sensors include but are not limited to temperature sensors, pressure sensors, and displacement sensors; the working condition sensing sensors include but are not limited to cutting force sensors, coolant sensors, friction sensors, and wear particle sensors; the environmental sensors include but are not limited to humidity sensors, dust particle sensors, and electromagnetic interference sensors; The data transmission and processing module is used to transmit the data collected by the data collection module, and to clean and organize the data in real time; The production planning and scheduling module uses genetic algorithms to generate the optimal production plan and scheduling solution based on the acquired order information, combined with inventory conditions, equipment capacity, and process requirements; The quality management module monitors and adjusts the manufacturing process in real time based on the processing data and product inspection data collected in real time; The personnel management module is used to comprehensively manage the personnel information on the processing and manufacturing production line, including the basic information of the personnel, skill level, training records, and attendance status.

3. The intelligent processing and manufacturing management system according to claim 1, characterized in that: The data acquisition module also includes an adaptive acquisition module for automatically adjusting the data acquisition strategy according to the actual processing conditions of the processing and manufacturing equipment.

4. The intelligent processing and manufacturing management system according to claim 1, characterized in that: The equipment management module is electrically connected to the data acquisition module. The equipment management module includes an equipment access and identification module, a diagnosis and predictive maintenance module, and an equipment maintenance management and knowledge base module. The equipment access and identification module uses a Modbus intelligent gateway to access processing equipment of different brands and manufactured in different years. Assign a unique digital identity to each device, which is built on blockchain technology; The equipment maintenance management and knowledge base module includes maintenance plan formulation, maintenance work order generation, maintenance personnel scheduling, and maintenance process recording.

5. The intelligent processing and manufacturing management system according to claim 4 is characterized in that: The diagnosis and predictive maintenance module includes a fault diagnosis module and a predictive maintenance module. The fault diagnosis module includes a data integration module, a fusion diagnosis module, a knowledge acquisition and organization module, and a knowledge graph application module. The data integration module is used to collect data collected by the data acquisition module, equipment operation status data, historical maintenance records and product quality data, extract features from the data based on convolutional neural networks and recurrent neural networks, and mark the extracted fault features. The fusion diagnosis module is used to compare the fault features of the data acquisition module and the marked ones. When the comparison results are the same, the current processing and manufacturing equipment is diagnosed as a fault state. A fusion diagnosis model based on a Bayesian network is constructed based on the extracted features. The extracted features are used as the input nodes of the Bayesian network, and the equipment fault type is used as the output node. Through Bayesian reasoning, the probability of different faults occurring under a given combination of multiple features is calculated. The formula is as follows: Where A is a different fault type, B is a different feature combination, P(A) is the prior probability of fault A occurring, P(B|A) is the probability of feature combination B occurring when fault A occurs, and P(A|B) is the posterior probability of fault A occurring under feature combination B. The probabilities of all faults A that will occur with a feature combination B are calculated. The fault A with the highest value has the highest probability of occurrence, and the currently faulty component should be replaced.

6. The intelligent processing and manufacturing management system according to claim 5, characterized in that: The knowledge acquisition and organization module is used to collect equipment manuals, maintenance guides, maintenance experience and cases of internal experts provided by equipment manufacturers, and data collected by equipment maintenance management and knowledge base modules to form an initial knowledge source, perform semantic extraction and relationship construction on the knowledge source, and form a knowledge graph. In the knowledge graph, equipment components, fault phenomena, fault causes and maintenance methods are used as nodes, and causal relationships and association relationships between nodes are used as edges; The knowledge graph application module is used to perform intelligent reasoning using the knowledge graph during the fault diagnosis process. When at least one fault phenomenon is detected in the equipment, the cause of the fault is quickly located and the corresponding maintenance method is recommended through the knowledge graph.

7. The intelligent processing and manufacturing management system according to claim 5, characterized in that: The predictive maintenance module includes a degradation model building module, a remaining life prediction module, an environmental modeling and strategy network, and a strategy evaluation and update module. The degradation model building module builds a performance degradation model of the component based on the physical characteristics and operation mechanism of the key components of the equipment, and uses the real-time operation data of the equipment to estimate and update the parameters of the degradation model; The remaining service life prediction module is used to predict the remaining service life of a component according to its current performance status and performance degradation model, and the specific steps are as follows: Clean the component data collected by the data acquisition module, remove outliers and noise, establish a theoretical wear model based on the physical principle of component wear, select an artificial neural network, whose input layer nodes are the characteristic parameters of the equipment and output layer nodes are the wear amount of the equipment, and train the collected data; During the actual operation of the equipment, the real-time collected equipment operation data is input into the trained theoretical wear model to obtain the predicted value of the current wear state of the equipment. Based on the predicted value of the equipment wear and the equipment scrapping standard, it is judged whether the equipment is approaching the end of its service life. When the predicted wear is close to the scrapping standard, an early warning message for replacing the equipment is issued in time. According to the predicted value of the current wear state of the equipment and the wear rate of the equipment, the remaining life of the equipment is calculated using the formula: S = (1-M)*L; Where S is the remaining life of the equipment, M is the percentage of the current wear of the equipment to the total allowable wear, and L is the current wear rate of the equipment.

8. The intelligent processing and manufacturing management system according to claim 5, characterized in that: The environment modeling and strategy network models the equipment maintenance process based on the Markov decision process, with the equipment state as the state space, the maintenance operation as the action space, the maintenance cost and the equipment downtime as the reward signal, and constructs a deep Q-network for continuously interacting with the equipment maintenance process model so that the deep Q-network learns the optimal maintenance strategy, records the maintenance strategy, and learns whether to perform maintenance immediately or postpone maintenance based on the currently calculated remaining life of the equipment and the production task schedule; The strategy evaluation and update module evaluates the maintenance strategy obtained by the deep Q-network based on the historical maintenance strategy and equipment maintenance process model. By comparing the maintenance cost and equipment availability under different strategies, the deep Q-network is updated. The specific steps are as follows: Based on the maintenance strategy and data acquisition module, the equipment status information, the adopted maintenance strategy, the maintenance cost, and the subsequent operation performance of the equipment are collected, and the collected data are sorted and classified; Calculate the total cost of each maintenance event, including direct and indirect costs. When evaluating the strategic network, consider the maintenance cost of the equipment throughout its entire life cycle from commissioning to retirement, and compare the average maintenance costs under different strategies. Calculate the ratio of the equipment's normal operation time to the total time over a period of time. A high normal operation time ratio indicates high equipment availability. The normal operation time ratio of the equipment within a month is calculated according to the formula: Where B is the normal operation time ratio of the equipment in a month, Y is the normal operation time of the equipment in a month, and Z is the total working time of the equipment in a month; The average operating time between two adjacent equipment failures is calculated. The longer the time, the more effective the maintenance strategy currently used by the equipment is. The maintenance strategy is selected based on the normal operating time ratio and the average maintenance cost under different strategies. The highest normal operating time ratio and the lowest maintenance cost are selected as the optimal maintenance strategy.

9. The intelligent processing and manufacturing management system according to claim 1, characterized in that: The inventory management module includes an inventory perception module, an inventory analysis and prediction module, and an intelligent decision-making module. The inventory perception module includes ultra-high frequency RFID tags attached to raw materials, semi-finished products and finished products, and a full range of RFID reader-writer arrays deployed in the warehouse to identify the location, quantity, and entry and exit time of inventory items in real time; The inventory analysis and forecasting module analyzes historical order data, market trend data, seasonal factors, macroeconomic data, and social media public opinion data based on deep learning algorithms to build a highly accurate inventory demand forecasting model; Based on data mining technology, we conduct in-depth analysis of inventory turnover rate, inventory cost, and obsolete inventory ratio to comprehensively evaluate the health of inventory.

10. The intelligent processing and manufacturing management system according to claim 1, characterized in that: The intelligent decision-making module is used to establish an information sharing platform with suppliers. Suppliers can view our inventory levels, production plans and order requirements in real time. We can also obtain suppliers' inventory status, production progress and delivery information in a timely manner. The production department can query the quantity and location of inventory raw materials and semi-finished products in real time to arrange production tasks; the intelligent decision-making module automatically adjusts inventory data and triggers replenishment and material allocation processes based on production progress and material consumption. The specific steps are: setting safety stocks for each raw material inventory; During the production process, when the material consumption is reduced due to equipment failure in the production process, the intelligent decision-making module will promptly adjust the inventory reserve of the material and notify the supplier according to the new production plan.

Images