Intelligent industry chain big data management system based on cloud computing

Abstract

The invention discloses an intelligent industrial chain big data management system based on cloud computing, and relates to the technical field of industrial chain management. According to the intelligent industry chain big data management system based on cloud computing, a centralized processing mechanism for real-time operation state data of each production device in an industry chain is constructed based on a cloud computing platform, an operation health index of the device is calculated through a health analysis unit, and a preset abnormal interval is compared by a judgment management unit; according to the system, a multi-source operation parameter acquisition and cloud fusion processing mechanism is introduced, and a health index model is constructed based on an operation state parameter set and a sensitivity coefficient, so that the dynamic evaluation of the state of the equipment and the grading judgment of the abnormality are realized; compared with a traditional single parameter monitoring mode, the method has higher accuracy and real-time performance, the performance degradation risk can be warned in advance, and the equipment management intelligence level and the industrial chain operation toughness are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial chain management technology, and specifically to a smart industrial chain big data management system based on cloud computing. Background Art

[0002] With the continuous development of information technology, sensing technology and industrial automation, traditional industrial chain management has gradually evolved towards intelligence and digitalization. Especially in the context of growing demand for multi-factory collaborative manufacturing, flexible production, supply chain collaboration and customer customization, industrial chain management has put forward higher requirements for the comprehensiveness of data acquisition, the real-time analysis and the intelligence of scheduling decisions.

[0003] Existing industrial chain management systems usually operate in the form of independent modules, such as equipment status monitoring systems, order management systems, inventory management systems, etc. The data standards between systems are not unified and the information island phenomenon is serious, which makes it difficult for enterprises to form a unified and dynamic global perception and regulation of the entire industrial chain. In addition, traditional systems mostly rely on local server deployment and manual intervention, with limited computing power and lack of elastic expansion capabilities. It is difficult to efficiently support the real-time processing of multi-source heterogeneous data and the intelligent analysis of complex models, which seriously restricts the response speed and management accuracy of the industrial chain.

[0004] In addition, the limitations of existing technologies include at least the following problems. First, in the process of managing the operating status of production equipment in the industrial chain, data collection and abnormality judgment are usually only relied on the local monitoring system of the equipment itself, and there is a lack of a centralized processing mechanism based on the cloud computing platform, which makes it difficult to achieve unified analysis and efficient comparison of the operating status of multiple devices. There are problems such as data dispersion, processing delays, and difficulty in forming a global health portrait; secondly, traditional methods often only focus on a single parameter of the equipment, such as temperature or pressure, and lack of fusion analysis of multi-dimensional operating parameters such as temperature, pressure, vibration, etc., which makes it difficult to accurately identify the abnormal status of the equipment, and is prone to false alarms or omissions, reducing the accuracy of management decisions; thirdly, most existing systems do not have a dynamic health index calculation and management mechanism, making it difficult to quantify the operating health level of the equipment in real time, and it is difficult to take hierarchical control measures based on the health index, which may eventually lead to sudden equipment failures that are difficult to warn in advance, thereby causing chain shutdowns, production interruptions and other problems, seriously restricting the stability and intelligence level of the overall operation of the industrial chain. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a smart industrial chain big data management system based on cloud computing, which solves the problems existing in the existing technology such as decentralized equipment operation monitoring, single parameter evaluation, inaccurate abnormality identification, and lack of a unified health management mechanism.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a smart industrial chain big data management system based on cloud computing, including: a production equipment operation data acquisition unit, which is used to acquire the real-time operation status data of each production equipment in the industrial chain in real time, and perform centralized preprocessing based on the cloud computing platform; a production equipment operation health analysis unit, which is used to analyze the real-time operation health index of each production equipment in the industrial chain based on the preprocessed real-time operation status data; a production equipment operation health judgment management unit, which is used to judge the real-time operation health index of each production equipment in the industrial chain with the preset operation health abnormality interval. If the real-time operation health index of the production equipment is within the preset operation health abnormality interval, it is judged that the production equipment is abnormal, and the preset production equipment management measures are taken.

[0007] Furthermore, the real-time operating status data includes a real-time operating temperature value, a real-time operating pressure value, and a real-time operating vibration frequency value.

[0008] Furthermore, the specific steps for analyzing the real-time operation health index of each production equipment in the industrial chain are as follows: obtain the operation status parameter set of each production equipment in the industrial chain, and the operation status parameter set includes the operation temperature parameter value, the maximum operation temperature threshold, the minimum operation temperature threshold, the operation pressure parameter value, the maximum operation pressure threshold, the minimum operation pressure threshold, the operation vibration frequency parameter value, the maximum operation vibration frequency threshold, and the minimum operation vibration frequency threshold; read the real-time operation temperature value, real-time operation pressure value, and real-time operation vibration frequency value of each production equipment in the industrial chain, and perform a comprehensive analysis in combination with the operation status parameter set of the corresponding production equipment to obtain the real-time operation health index of each production equipment in the industrial chain.

[0009] Furthermore, the specific formula for calculating the real-time operation health index of a production equipment in the industrial chain is as follows: Among them, YxJ is the real-time operation health index of a certain production equipment in the industrial chain, YwD is the real-time operation temperature value of a certain production equipment in the industrial chain, YwC is the operation temperature parameter value of a certain production equipment in the industrial chain, WdZ is the maximum operation temperature threshold of a certain production equipment in the industrial chain, WdX is the minimum operation temperature threshold of a certain production equipment in the industrial chain, λ1 is the operation temperature sensitivity coefficient stored in the database, YyL is the real-time operation pressure value of a certain production equipment in the industrial chain, YyC is the operation pressure parameter value of a certain production equipment in the industrial chain, YyZ is the maximum operation pressure threshold of a certain production equipment in the industrial chain, YyX is the minimum operation pressure threshold of a certain production equipment in the industrial chain, λ2 is the operation pressure sensitivity coefficient stored in the database, ZdP is the real-time operation vibration frequency value of a certain production equipment in the industrial chain, ZdC is the operation vibration frequency parameter value of a certain production equipment in the industrial chain, ZdZ is the maximum operation vibration frequency threshold of a certain production equipment in the industrial chain, ZdX is the minimum operation vibration frequency threshold of a certain production equipment in the industrial chain, and λ3 is the operation vibration frequency sensitivity coefficient stored in the database.

[0010] Furthermore, it also includes: a market demand analysis unit, which is used to obtain the periodic order quantity, periodic market demand fluctuation amplitude, and periodic market demand change rate of each sales product in the current production cycle within the industrial chain, and analyze the market demand fluctuation index of each sales product in the current production cycle within the industrial chain; a market demand judgment management unit, which is used to judge and analyze the market demand fluctuation index of each sales product in the current production cycle within the industrial chain with a preset market demand fluctuation abnormal range. If the market demand fluctuation index of the current production cycle is within the preset market demand fluctuation abnormal range, it is judged as product demand abnormality, and preset product demand management measures are taken.

[0011] Furthermore, the specific steps for analyzing the market demand fluctuation index of each sales product in the current production cycle within the industrial chain are as follows: obtain the historical cycle maximum order volume, historical cycle market demand maximum fluctuation range, and historical cycle market demand maximum change rate of each sales product in the production cycle within the industrial chain; comprehensively analyze the cycle order volume, cycle market demand fluctuation range, and cycle market demand change rate of each sales product in the current production cycle within the industrial chain, combined with the historical cycle maximum order volume, historical cycle maximum fluctuation range, and historical cycle market demand maximum change rate of the production cycle within the industrial chain, to obtain the market demand fluctuation index of each sales product in the current production cycle within the industrial chain.

[0012] Furthermore, the specific formula for calculating the market demand fluctuation index of a certain sales product in the current production cycle within the industrial chain is as follows: Among them, ScX is the market demand fluctuation index of a certain sales product in the current production cycle within the industrial chain, e is a natural constant, ZdD is the periodic order quantity of a certain sales product in the current production cycle within the industrial chain, ZdZ is the historical periodic maximum order quantity of a certain sales product in the production cycle within the industrial chain, μ1 is the order fluctuation coefficient stored in the database, XqB is the periodic market demand fluctuation amplitude of a certain sales product in the current production cycle within the industrial chain, XqZ is the historical periodic market demand maximum fluctuation amplitude of a certain sales product in the production cycle within the industrial chain, μ2 is the demand fluctuation amplitude coefficient stored in the database, XbH is the periodic market demand change rate of a certain sales product in the current production cycle within the industrial chain, XbZ is the historical periodic market demand maximum change rate of a certain sales product in the production cycle within the industrial chain, and μ3 is the demand change coefficient stored in the database.

[0013] Furthermore, it also includes: an inventory analysis unit, which is used to obtain the current inventory, stranded inventory, and inventory response time difference of each sales product in the industrial chain, and analyze the inventory adaptation index of each sales product in the industrial chain; an inventory judgment management unit, which is used to judge and analyze the inventory adaptation index of each sales product in the industrial chain and the preset inventory adaptation abnormality interval. If the inventory adaptation index of the sales product is within the preset inventory adaptation abnormality interval, it is determined to be a product inventory abnormality, and preset product inventory management measures are taken.

[0014] Furthermore, the specific steps for analyzing the inventory adaptation index of each sales product in the industrial chain are as follows: obtain the optimal inventory quantity, maximum inventory quantity, and maximum allowable inventory retention time of each sales product in the industrial chain; comprehensively analyze the current inventory quantity, retained inventory quantity, and inventory response time difference of each sales product in the industrial chain, combined with the optimal inventory quantity, maximum inventory quantity, and maximum allowable inventory retention time of each sales product in the industrial chain, to obtain the inventory adaptation index of each sales product in the industrial chain.

[0015] Furthermore, the specific formula for calculating and analyzing the inventory adaptation index of a certain sales product within the industry chain is as follows: Among them, KsP is the inventory adaptation index of a certain sales product in the industrial chain, DkC is the current inventory of a certain sales product in the industrial chain, ZyK is the optimal inventory of a certain sales product in the industrial chain, δ1 is the inventory deviation impact coefficient stored in the database, LkC is the stranded inventory of a certain sales product in the industrial chain, ZkC is the maximum inventory of a certain sales product in the industrial chain, δ2 is the stranded inventory weight coefficient stored in the database, KxY is the inventory response time difference of a certain sales product in the industrial chain, YxK is the maximum allowable inventory stranded time of a certain sales product in the industrial chain, δ3 is the inventory response sensitivity coefficient stored in the database, and e is a natural constant.

[0016] The present invention has the following beneficial effects:

[0017] (1) The cloud computing-based smart industry chain big data management system, by introducing a production equipment operation data acquisition unit and an operation health analysis unit, realizes the fusion collection and cloud-based centralized processing of multi-source real-time operation status parameters of various production equipment in the industry chain, including temperature, pressure, vibration frequency, etc. Different from the traditional local monitoring method that relies on a single parameter for fault warning, this system is based on the full reference comparison mechanism of the operation status parameter set. In the health assessment process, the system introduces the operation parameter value, upper and lower thresholds and the sensitivity coefficients stored in the database, such as temperature sensitivity coefficient, pressure sensitivity coefficient, and vibration frequency sensitivity coefficient, to build a multi-factor weighted model, and then calculates the real-time operation health index of each device. By dynamically comparing with the preset operation health abnormality interval, it realizes the accurate identification and hierarchical judgment of abnormal devices, avoids false alarms and missed alarms, and greatly improves the real-time and accuracy of fault identification. In addition, the system can also dynamically track the continuous fluctuation trend of the health index, so as to issue a warning at the early stage of equipment performance degradation, avoid the sudden equipment downtime causing systemic risks to the operation of the industry chain, and significantly enhance the operation resilience and intelligent response capability of the industry chain.

[0018] (2) The cloud computing-based smart industry chain big data management system, by constructing a market fluctuation multi-parameter model with order quantity, demand fluctuation amplitude and demand change rate as the core, not only obtains the sales order and market demand dynamics in the current production cycle, but also integrates the maximum order quantity, maximum fluctuation amplitude and maximum change rate of the historical cycle as a standardized reference baseline, and introduces the order fluctuation coefficient, demand amplitude coefficient and change coefficient preset in the database, and forms an innovative fluctuation evaluation formula through the exponential function and normalization comparison method. This mechanism effectively solves the one-sided problem of the existing market management system that only relies on current sales to judge trends. It can characterize the uncertainty and fluctuation characteristics of the market from a more macro historical dimension, and accurately capture and judge the demand change trend of each sales product. When the market demand fluctuation index falls into the preset abnormal range, the system can automatically mark it as a demand abnormality category, thereby driving the pre-adjustment of production and sales plans, inventory strategies, and resource scheduling, ensuring the agility and scientific nature of resource allocation, and significantly improving the company's adaptability and response efficiency to the rapidly changing market environment.

[0019] (3) The cloud computing-based smart industry chain big data management system obtains structural parameters such as the optimal inventory, maximum inventory, and maximum retention time of each product, and integrates them with dynamic state parameters such as current inventory, retention inventory, and response time difference to form a multi-factor weight evaluation model. The system introduces three types of strategic weights in the index calculation process: inventory deviation impact coefficient, retention inventory weight coefficient, and inventory response sensitivity coefficient. This allows the evaluation model to reflect the degree of deviation between inventory and ideal configuration, and to reveal the risk of inventory backlog and response lag. It achieves a comprehensive evaluation of inventory status from three dimensions: structural rationality, temporal dynamics, and configuration responsiveness. When the inventory adaptation index falls into the abnormal range, the system can intelligently issue an early warning to drive management strategies such as promotion clearance, replenishment scheduling, or cessation of warehousing, truly realizing active optimization and dynamic balance of inventory structure, greatly reducing inventory backlog, supply interruption risk, and resource waste, and significantly improving inventory turnover efficiency and product supply and demand matching.

[0020] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a block diagram of the cloud computing-based smart industry chain big data management system of the present invention.

[0022] Figure 2 This is a flowchart of the specific steps for analyzing the real-time operation health index of each production equipment in the industrial chain in the cloud computing-based smart industrial chain big data management system of the present invention. DETAILED DESCRIPTION

[0023] See also Figure 1 The embodiment of the present invention provides a technical solution: a cloud computing-based smart industrial chain big data management system, comprising: a production equipment operation data acquisition unit, configured to acquire real-time operation status data of each production equipment in the industrial chain in real time and perform centralized preprocessing based on a cloud computing platform; a production equipment operation health analysis unit, configured to analyze the real-time operation health index of each production equipment in the industrial chain based on the preprocessed real-time operation status data; and a production equipment operation health judgment management unit, configured to judge the real-time operation health index of each production equipment in the industrial chain against a preset operation health abnormality interval. If the real-time operation health index of the production equipment is within the preset operation health abnormality interval, it is determined that the production equipment is abnormal, and preset production equipment management measures are taken, including:

[0024] Based on the degree of deviation of the health index, the equipment status is divided into mild abnormality, moderate abnormality or severe abnormality, forming an abnormality level identification;

[0025] Push information such as equipment number, abnormality level, specific deviation parameters, etc. to the equipment operation and maintenance platform and management personnel terminal in real time;

[0026] For seriously abnormal equipment, the system can automatically generate shutdown recommendations and provide impact analysis reports, indicating whether it is necessary to isolate it from the production chain;

[0027] Linking with maintenance management systems (such as CMMS) to automatically generate maintenance work orders and match maintenance personnel and tool resources;

[0028] Dynamically adjust equipment operation schedules and maintenance plans based on equipment abnormalities to ensure production continuity;

[0029] If the abnormal equipment is related to a key process link, it will also trigger a linkage warning for upstream and downstream equipment and inventory status.

[0030] The real-time operating status data includes real-time operating temperature value, real-time operating pressure value, and real-time operating vibration frequency value.

[0031] The real-time operating temperature value can be measured and obtained by a temperature sensor (such as a thermocouple, RTD, etc.).

[0032] The real-time operating pressure value can be measured and obtained by a pressure sensor (such as a strain gauge, piezoelectric or capacitive sensor).

[0033] The real-time running vibration frequency value can be measured and obtained through an acceleration sensor or a vibration sensor.

[0034] Specifically, if Figure 2 As shown in the figure, the specific steps for analyzing the real-time operation health index of each production equipment in the industrial chain are as follows: obtain the operation status parameter set of each production equipment in the industrial chain, the operation status parameter set includes the operation temperature parameter value, the maximum operation temperature threshold, the minimum operation temperature threshold, the operation pressure parameter value, the maximum operation pressure threshold, the minimum operation pressure threshold, the operation vibration frequency parameter value, the maximum operation vibration frequency threshold, and the minimum operation vibration frequency threshold; read the real-time operation temperature value, real-time operation pressure value, and real-time operation vibration frequency value of each production equipment in the industrial chain, and perform a comprehensive analysis in combination with the operation status parameter set of the corresponding production equipment to obtain the real-time operation health index of each production equipment in the industrial chain.

[0035] Among them, the operating temperature parameter value refers to the preset temperature value of the production equipment during normal operation, which is usually the ideal operating temperature when the equipment is running. It is a standard value set according to the technical requirements and usage conditions of the equipment. It can be obtained from the equipment manual or through long-term operation data analysis. It is usually specified by the manufacturer or engineer, and can also be set through historical data or experiments.

[0036] The maximum operating temperature threshold refers to the maximum temperature limit allowed for production equipment. Exceeding this temperature may cause damage to the equipment or reduce its service life. This value is usually provided by the equipment manufacturer or obtained through heat resistance performance testing and standard regulations of the equipment.

[0037] The minimum operating temperature threshold refers to the minimum temperature limit allowed for production equipment. Temperatures below this limit may affect the normal operation of the equipment. It is usually provided by the manufacturer or set based on the minimum operating environment temperature of the equipment.

[0038] The operating pressure parameter value refers to the ideal pressure value that the production equipment should maintain during normal operation. It is usually set according to the working conditions designed for the equipment, and is also obtained from the equipment manual or through long-term operating data analysis. This value may vary depending on the equipment model and purpose.

[0039] The maximum operating pressure threshold refers to the maximum pressure that production equipment can withstand during operation. Exceeding this pressure may cause equipment damage or failure. It is obtained through the equipment design specifications or technical parameters provided by the manufacturer.

[0040] The minimum operating pressure threshold refers to the minimum pressure value allowed for production equipment during operation. A pressure lower than this may cause the equipment to have difficulty in normal operation or even be damaged. It is usually provided by the equipment manufacturer or set based on the working principle of the equipment and the minimum operating pressure.

[0041] The operating vibration frequency parameter refers to the vibration frequency of the production equipment during normal operation. This is usually a standard value set based on the mechanical structure, working conditions, etc. of the equipment. It can be obtained through equipment testing or historical data analysis, or it can be set through the equipment manual or relevant standards.

[0042] The maximum operating vibration frequency threshold refers to the maximum vibration frequency that production equipment can withstand. Exceeding this value may cause excessive vibration of the equipment, affecting its operating stability. It is generally obtained through the equipment design standards or performance data provided by the manufacturer.

[0043] The minimum operating vibration frequency threshold refers to the minimum vibration frequency that production equipment should have during operation. A frequency lower than this may mean that the equipment is not operating properly and it is difficult to reach normal working conditions. This is also determined by the equipment designer or through equipment testing.

[0044] The specific formula for calculating the real-time operational health index of a piece of production equipment in the industrial chain is as follows: Among them, YxJ is the real-time operation health index of a certain production equipment in the industrial chain, YwD is the real-time operation temperature value of a certain production equipment in the industrial chain, YwC is the operation temperature parameter value of a certain production equipment in the industrial chain, WdZ is the maximum operation temperature threshold of a certain production equipment in the industrial chain, WdX is the minimum operation temperature threshold of a certain production equipment in the industrial chain, λ1 is the operation temperature sensitivity coefficient stored in the database, YyL is the real-time operation pressure value of a certain production equipment in the industrial chain, YyC is the operation pressure parameter value of a certain production equipment in the industrial chain, YyZ is the maximum operation pressure threshold of a certain production equipment in the industrial chain, YyX is the minimum operation pressure threshold of a certain production equipment in the industrial chain, λ2 is the operation pressure sensitivity coefficient stored in the database, ZdP is the real-time operation vibration frequency value of a certain production equipment in the industrial chain, ZdC is the operation vibration frequency parameter value of a certain production equipment in the industrial chain, ZdZ is the maximum operation vibration frequency threshold of a certain production equipment in the industrial chain, ZdX is the minimum operation vibration frequency threshold of a certain production equipment in the industrial chain, and λ3 is the operation vibration frequency sensitivity coefficient stored in the database.

[0045] It should be explained that the specific steps for obtaining the operating temperature sensitivity coefficient λ1, operating pressure sensitivity coefficient λ2, and operating vibration frequency sensitivity coefficient λ3 stored in the database are: first, extract the operating data of the equipment under different temperatures, pressures, and vibration frequencies, and then calculate the degree of influence of each factor on the equipment's operating efficiency or failure rate through regression analysis or sensitivity analysis. Specifically, the relationship between changes in temperature, pressure, and vibration frequency and equipment performance is quantified through statistical methods to derive their respective sensitivity coefficients, which reflect the response characteristics of the equipment under different operating conditions.

[0046] In this implementation plan, a dynamic and accurate health index calculation method is formed by constructing a multi-parameter health assessment mechanism based on the operating status parameter set and combining core operating data such as real-time temperature, pressure and vibration frequency. Compared with the traditional method of relying on a single threshold to judge the equipment status, this method introduces maximum / minimum thresholds and sensitivity coefficients to make the assessment more detailed and scientific, effectively improving the accuracy and foresight of equipment abnormality identification. At the same time, through historical data modeling and analysis of sensitivity coefficients, an adaptive response to different equipment characteristics and failure patterns is achieved, which helps to identify equipment operation hazards at an early stage and intervene in maintenance in advance, thereby ensuring the continuity of the industrial chain and the stability of the equipment.

[0047] Specifically, it also includes: a market demand analysis unit, which is used to obtain the periodic order volume, periodic market demand fluctuation range, and periodic market demand change rate of each sales product in the current production cycle of the industrial chain, and analyze the market demand fluctuation index of each sales product in the current production cycle of the industrial chain; a market demand judgment management unit, which is used to judge and analyze the market demand fluctuation index of each sales product in the current production cycle of the industrial chain with a preset market demand fluctuation abnormal range. If the market demand fluctuation index of the current production cycle is within the preset market demand fluctuation abnormal range, it is determined that the product demand is abnormal, and preset product demand management measures are taken, including:

[0048] Conduct trend line analysis on the demand index to identify typical patterns such as sudden increase in demand, sudden decrease in demand, or cyclical shift;

[0049] Automatically trigger the update of the short-term sales forecast model and re-evaluate the market demand for the next cycle;

[0050] Automatically generate suggestions for increasing or reducing production or adjusting production lines based on inventory status and equipment health;

[0051] Linking the order system to reorder the priority and delivery sequence of currently unfinished orders;

[0052] If the order demand of major B-side customers fluctuates, the system will automatically notify the account manager for communication or confirmation;

[0053] If a significant drop in demand is detected, the preset promotion strategy library can be triggered to generate price reduction, promotion, and channel placement recommendations.

[0054] The specific steps for analyzing the market demand fluctuation index of each sales product in the current production cycle within the industrial chain are as follows: obtain the historical cycle maximum order volume, historical cycle market demand maximum fluctuation range, and historical cycle market demand maximum change rate of each sales product in the production cycle within the industrial chain; comprehensively analyze the cycle order volume, cycle market demand fluctuation range, and cycle market demand change rate of each sales product in the current production cycle within the industrial chain, combined with the historical cycle maximum order volume, historical cycle maximum fluctuation range, and historical cycle market demand maximum change rate of the production cycle within the industrial chain, to obtain the market demand fluctuation index of each sales product in the current production cycle within the industrial chain.

[0055] Among them, the maximum order volume in the historical cycle refers to the maximum number of orders for sales products received by the market in the past production cycle. It reflects the maximum degree of market demand and usually occurs during the peak sales season or special promotions. Historical order data can be extracted through the company's order management system (such as the ERP system). It is necessary to analyze the order data of sales products in the past several production cycles (for example, the past year or the past few quarters) to find the maximum order volume of sales products in a single production cycle. For example: obtain the total number of orders for each month, quarter or year, and find the period with the largest order volume as the maximum order volume of the historical cycle.

[0056] The maximum fluctuation range of market demand in the historical period indicates the range of change of market demand for sales products within a certain production cycle. It measures the severity of demand fluctuations and reflects the instability of market demand. The fluctuation range of market demand can be measured by calculating the standard deviation or variance of the historical sales data of sales products. The acquisition steps are as follows: extract the monthly, weekly or daily sales data of sales products in each production cycle from the sales records, calculate the standard deviation of the sales data of sales products, and find the maximum fluctuation value. This maximum value is the maximum fluctuation range of market demand for sales products. For example, take the sales volume of each month in a certain period of time, calculate the fluctuation range of each month, and select the maximum fluctuation value as the maximum demand fluctuation range of the historical period.

[0057] The maximum rate of change of market demand in the historical period indicates the rate of change of market demand for sales products within a certain production cycle, reflecting the speed of demand change. It can be used to measure the speed of growth or decline of market demand, and can be obtained by calculating the change in the market demand growth rate of sales products. The specific steps are as follows: extract past sales data from the sales records of sales products, and calculate the growth rate of demand for sales products by comparing sales data between different periods, for example: demand growth rate = ((current period sales volume - previous period sales volume) / previous period sales volume) × 100%, calculate the demand change rate of each period (such as monthly change rate, quarterly change rate), and then find the maximum value of the demand change rate in the historical period, that is, the maximum demand change rate in the historical period.

[0058] The cycle order volume refers to the actual number of orders for sales products within the current production cycle, reflecting the actual market demand for sales products. Order data can be extracted from the company's order management system (such as the ERP system) to count the total number of orders for sales products within the current production cycle. This parameter directly reflects the actual market demand for the product.

[0059] The fluctuation range of cyclical market demand indicates the range of change in market demand for sales products within the current production cycle. It measures the degree of fluctuation in market demand and reflects the instability of market demand. It can be calculated by analyzing the historical sales data or market data of sales products. Specifically, the standard deviation or variance of the demand data for sales products within the current production cycle (such as monthly or weekly sales) can be calculated to obtain the fluctuation range.

[0060] The periodic market demand change rate indicates the rate of increase or decrease in market demand for products sold during the current production cycle. A higher demand change rate indicates that market demand is growing or decreasing rapidly, reflecting market volatility. The demand growth rate can be calculated by comparing the sales data of the products sold in the current cycle with that in the previous cycle. For example, the change rate can be calculated by (current cycle sales volume - previous cycle sales volume) / previous cycle sales volume.

[0061] The specific formula for calculating the market demand fluctuation index of a certain sales product in the current production cycle within the industry chain is as follows: Among them, ScX is the market demand fluctuation index of a certain sales product in the current production cycle within the industrial chain, e is a natural constant, which is taken as 2.71 in this embodiment, ZdD is the periodic order quantity of a certain sales product in the current production cycle within the industrial chain, ZdZ is the historical periodic maximum order quantity of a certain sales product in the production cycle within the industrial chain, μ1 is the order fluctuation coefficient stored in the database, XqB is the periodic market demand fluctuation amplitude of a certain sales product in the current production cycle within the industrial chain, XqZ is the historical periodic market demand maximum fluctuation amplitude of a certain sales product in the production cycle within the industrial chain, μ2 is the demand fluctuation amplitude coefficient stored in the database, XbH is the periodic market demand change rate of a certain sales product in the current production cycle within the industrial chain, XbZ is the historical periodic market demand maximum change rate of a certain sales product in the production cycle within the industrial chain, and μ3 is the demand change coefficient stored in the database.

[0062] It should be explained that the specific steps for obtaining the order fluctuation coefficient μ1, demand fluctuation coefficient μ2, and demand variation coefficient μ3 stored in the database are as follows: for the order fluctuation coefficient, it is calculated by analyzing the ratio of the standard deviation of the order quantity to the mean (coefficient of variation) in the historical sales cycle of the product, reflecting the degree of dispersion of the order data; for the demand fluctuation coefficient, it is calculated based on the maximum and minimum demand difference in each cycle of the historical sales data of the product, and normalized with its relative mean; for the demand variation coefficient, the market demand change rate between adjacent cycles in the historical sales cycle of the product is statistically analyzed, and its maximum change value or average change range is extracted to measure the sensitivity of market demand changes. These parameters are written into the database after aggregating historical data and performing standardized analysis, providing a reference benchmark for the calculation of the market volatility index of the current cycle.

[0063] In this implementation plan, a standardized and dynamic market demand assessment system is established by constructing a market demand fluctuation index model that integrates multi-dimensional data such as periodic order volume, demand fluctuation amplitude and change rate, and combining historical extreme value data with the fluctuation sensitivity coefficient stored in the database. This mechanism can not only quantify the market demand stability and changing trends of various products in the current production cycle, but also assist the system in identifying abnormal demand types (such as sudden increases and decreases), and automatically link production capacity adjustments, order scheduling and promotion strategies, greatly improving the company's response speed to market fluctuations and strategy matching, ensuring accurate and efficient resource allocation, and realizing intelligent supply and demand collaboration under market guidance.

[0064] Specifically, it also includes: an inventory analysis unit for obtaining the current inventory, stranded inventory, and inventory response time difference of each sales product in the industry chain, and analyzing the inventory adaptation index of each sales product in the industry chain; an inventory judgment management unit for judging and analyzing the inventory adaptation index of each sales product in the industry chain and a preset inventory adaptation abnormality interval. If the inventory adaptation index of the sales product is within the preset inventory adaptation abnormality interval, it is determined that the product inventory is abnormal, and preset product inventory management measures are taken, including:

[0065] The system determines that the problem is excessive inventory, insufficient inventory, or delayed inventory turnover, and classifies and handles it accordingly;

[0066] For products with low inventory, the system generates a replenishment request; for products with high inventory, the subsequent warehousing plan is automatically suspended;

[0067] If inventory backlogs are severe, the system will invoke preset inventory reduction strategies, including internal transfers, external promotions, and price reductions for warehouses.

[0068] Based on abnormal inventory results, production rhythm and sales targets are adjusted in a coordinated manner to optimize production and sales collaboration;

[0069] For products with delayed inventory response, the system prioritizes the allocation of fast logistics resources to shorten the delivery cycle;

[0070] Set manual review thresholds for strategy automation execution nodes and implement management approval mechanisms for important categories or large batches of materials.

[0071] The specific steps for analyzing the inventory adaptation index of each sales product in the industrial chain are as follows: obtain the optimal inventory level, maximum inventory level, and maximum allowable inventory retention time of each sales product in the industrial chain; comprehensively analyze the current inventory level, retained inventory level, and inventory response time difference of each sales product in the industrial chain, combined with the optimal inventory level, maximum inventory level, and maximum allowable inventory retention time of each sales product in the industrial chain, to obtain the inventory adaptation index of each sales product in the industrial chain.

[0072] Among them, the current inventory level refers to the real-time inventory quantity recorded in the warehousing system at a certain moment in the current production cycle for each sales product. The acquisition steps include: connecting to the company's warehouse management system (such as WMS or ERP module), regularly synchronizing or calling the inventory data interface in real time, and extracting the current actual inventory quantity of each SKU as the parameter value.

[0073] Stranded inventory refers to the number of inventory products that have exceeded the maximum allowable detention time but have not yet been shipped out during the current cycle, reflecting the inventory backlog situation. The steps for obtaining it include: based on the inventory entry and exit records, counting the remaining inventory corresponding to batches of each product whose entry time exceeds the maximum allowable detention time, and summarizing them by product dimension to obtain the total stranded inventory.

[0074] The inventory response time difference refers to the average time delay between a product's entry into the warehouse and its successful exit from the warehouse, reflecting the flexibility and response efficiency of the product's inventory turnover. The acquisition steps include: extracting the entry time and corresponding exit time of multiple historical entry batches of the product, calculating its average response interval, and normalizing it with the weights of different batches to obtain the average inventory response time difference of the product.

[0075] The optimal inventory level refers to the ideal inventory quantity calculated to ensure supply and demand balance within the current production cycle after comprehensively considering the product's historical sales volume, market demand fluctuations, supply cycle and safety stock level. The steps for obtaining it include: based on the product's sales records in multiple historical cycles, combined with the current market volatility index and replenishment cycle, using a weighted moving average or demand forecasting model (such as EMA, ARIMA, etc.) to calculate the dynamic optimal inventory reference value for each sales product in the current cycle.

[0076] The maximum inventory level refers to the maximum inventory limit that an enterprise sets for each sales product under the constraints of warehouse resources, warehouse capacity restrictions and inventory strategies. The steps for obtaining it include: extracting the maximum capacity setting value reserved for each type of product in the warehouse from the warehouse management system (WMS), combining it with warehouse planning rules, product stacking methods and storage cycle restrictions, or entering it into the system after the enterprise sets it according to category characteristics and strategies.

[0077] The maximum allowable inventory retention time refers to the maximum time that each sales product is allowed to stay in inventory without affecting circulation efficiency, quality preservation, capital occupation, etc. The steps for obtaining it include: setting a reasonable retention upper limit based on product attributes (such as whether it is a fast-moving consumer product or perishable product), past inventory turnover cycle, sales frequency and other factors, and after the company formulates an inventory classification strategy, entering it into the inventory management system as a product-level response control parameter.

[0078] The specific formula for calculating and analyzing the inventory adaptation index of a certain sales product within the industry chain is as follows: Among them, KsP is the inventory adaptation index of a certain sales product in the industrial chain, DkC is the current inventory of a certain sales product in the industrial chain, ZyK is the optimal inventory of a certain sales product in the industrial chain, δ1 is the inventory deviation impact coefficient stored in the database (measures the impact of the deviation between the inventory and the optimal inventory on the inventory adaptation index), LkC is the stranded inventory of a certain sales product in the industrial chain, ZkC is the maximum inventory of a certain sales product in the industrial chain, δ2 is the stranded inventory weight coefficient stored in the database (indicating the weight of the stranded inventory ratio in the overall inventory adaptability evaluation), KxY is the inventory response time difference of a certain sales product in the industrial chain, YxK is the maximum allowable inventory stranded time of a certain sales product in the industrial chain, δ3 is the inventory response sensitivity coefficient stored in the database (indicating the impact of inventory outbound response delay on adaptability), and e is a natural constant, which is 2.71 in this embodiment.

[0079] It should be explained that the specific steps for obtaining the inventory deviation impact coefficient δ1, stranded inventory weight coefficient δ2, and inventory response sensitivity coefficient δ3 stored in the database are: first, based on indicators such as the inventory deviation rate, stranded inventory ratio, and inventory response time difference of each sales product in recent production cycles, calculate the strength of its correlation with risk events such as inventory backlog, supply interruption, and abnormal inventory turnover as the basis for preliminary weights; second, invite business departments such as warehousing, supply chain, and sales to participate in the weight survey, and set the initial weight value based on the company's actual emphasis on the rationality of inventory structure, sales capacity, and response speed; finally, through historical backtesting and sensitivity analysis, fine-tune and optimize δ1, δ2, and δ3, and finally solidify them into parameter configurations that adapt to the current management strategy.

[0080] In this implementation plan, by constructing an inventory adaptation index model with current inventory, stranded inventory and inventory response time difference as core indicators, dynamic evaluation and classification judgment of the inventory status of each sales product is achieved. The system integrates structural parameters such as optimal inventory, maximum inventory capacity and maximum allowable stranded time, and combines the weight coefficients of inventory deviation, backlog and response lag to form a multi-dimensional and refined inventory health evaluation mechanism. Compared with the traditional static inventory management model, this method can accurately identify typical problems such as excessive inventory, insufficient inventory or delayed circulation, and automatically link replenishment control, destocking strategy and production scheduling, effectively improving the rationality of inventory structure and circulation efficiency, and significantly enhancing the intelligence and responsiveness of enterprise inventory regulation.

[0081] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0082] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. The cloud computing-based smart industry chain big data management system is characterized by: include: The production equipment operation data acquisition unit is used to obtain the real-time operation status data of each production equipment in the industrial chain and perform centralized pre-processing based on the cloud computing platform; The production equipment operation health analysis unit is used to analyze the real-time operation health index of each production equipment in the industrial chain based on pre-processed real-time operation status data; The production equipment operation health judgment management unit is used to judge the real-time operation health index of each production equipment in the industrial chain against the preset operation health abnormality range. If the real-time operation health index of the production equipment is within the preset operation health abnormality range, it is judged that the production equipment is abnormal, and the preset production equipment management measures are taken.

2. The cloud computing-based smart industry chain big data management system according to claim 1 is characterized in that: The real-time operating status data includes a real-time operating temperature value, a real-time operating pressure value, and a real-time operating vibration frequency value.

3. The cloud computing-based smart industry chain big data management system according to claim 2 is characterized in that: The specific steps for analyzing the real-time operational health index of each production equipment in the industrial chain are as follows: Obtaining an operating status parameter set for each production equipment in the industrial chain, the operating status parameter set including an operating temperature parameter value, a maximum operating temperature threshold, a minimum operating temperature threshold, an operating pressure parameter value, a maximum operating pressure threshold, a minimum operating pressure threshold, an operating vibration frequency parameter value, a maximum operating vibration frequency threshold, and a minimum operating vibration frequency threshold; The real-time operating temperature value, real-time operating pressure value, and real-time operating vibration frequency value of each production equipment in the industrial chain are read, and a comprehensive analysis is performed in combination with the operating status parameter set of the corresponding production equipment to obtain the real-time operating health index of each production equipment in the industrial chain.

4. The cloud computing-based smart industry chain big data management system according to claim 3 is characterized in that: The specific formula for calculating the real-time operational health index of a piece of production equipment in the industrial chain is as follows: Among them, YxJ, YwD, YwC, WdZ, WdX, YyL, YyC, YyZ, YyX, ZdP, ZdC, ZdZ, and ZdX are respectively the real-time operation health index, real-time operation temperature value, operation temperature parameter value, maximum operation temperature threshold, minimum operation temperature threshold, real-time operation pressure value, operation pressure parameter value, maximum operation pressure threshold, minimum operation pressure threshold, real-time operation vibration frequency value, operation vibration frequency parameter value, maximum operation vibration frequency threshold, and minimum operation vibration frequency threshold of a certain production equipment in the industrial chain; λ1, λ2, and λ3 are respectively the operation temperature sensitivity coefficient, operation pressure sensitivity coefficient, and operation vibration frequency sensitivity coefficient stored in the database.

5. The cloud computing-based smart industry chain big data management system according to claim 1 is characterized in that: Also includes: The market demand analysis unit is used to obtain the periodic order volume, periodic market demand fluctuation range, and periodic market demand change rate of each sales product in the current production cycle of the industry chain, and analyze the market demand fluctuation index of each sales product in the current production cycle of the industry chain; The market demand judgment management unit is used to judge and analyze the market demand fluctuation index of each sales product in the current production cycle within the industrial chain and the preset market demand fluctuation abnormal range. If the market demand fluctuation index of the current production cycle is within the preset market demand fluctuation abnormal range, it is judged as product demand abnormality, and preset product demand management measures are taken.

6. The cloud computing-based smart industry chain big data management system according to claim 5 is characterized in that: The specific steps for analyzing the market demand volatility index of each product sold in the current production cycle within the industry chain are as follows: Obtain the historical maximum order volume, the maximum fluctuation range of market demand, and the maximum change rate of market demand for each sales product in the production cycle of the industry chain; The periodic order volume, periodic market demand fluctuation range, and periodic market demand change rate of each sales product in the current production cycle of the industrial chain are comprehensively analyzed in combination with the historical periodic maximum order volume, historical periodic market demand maximum fluctuation range, and historical periodic market demand maximum change rate of the production cycle within the industrial chain to obtain the market demand fluctuation index of each sales product in the current production cycle of the industrial chain.

7. The cloud computing-based smart industry chain big data management system according to claim 6 is characterized in that: The specific formula for calculating the market demand volatility index of a certain sales product in the current production cycle within the industry chain is as follows: Among them, ScX, ZdD, XqB, and XbH are the market demand fluctuation index, cycle order quantity, cycle market demand fluctuation amplitude, and cycle market demand change rate of a certain sales product in the current production cycle within the industrial chain, respectively; ZdZ, XqZ, and XbZ are the historical cycle maximum order quantity, historical cycle maximum market demand fluctuation amplitude, and historical cycle maximum market demand change rate of a certain sales product in the production cycle within the industrial chain, respectively; e is a natural constant; μ1, μ2, and μ3 are the order fluctuation coefficient, demand fluctuation amplitude coefficient, and demand change coefficient stored in the database, respectively.

8. The cloud computing-based smart industry chain big data management system according to claim 1 is characterized in that: Also includes: The inventory analysis unit is used to obtain the current inventory, stranded inventory, and inventory response time difference of each sales product in the industry chain, and analyze the inventory adaptation index of each sales product in the industry chain; The inventory judgment management unit is used to judge and analyze the inventory adaptation index of each sales product in the industrial chain and the preset inventory adaptation abnormality range. If the inventory adaptation index of the sales product is within the preset inventory adaptation abnormality range, it is judged as product inventory abnormality and the preset product inventory management measures are taken.

9. The cloud computing-based smart industry chain big data management system according to claim 8, characterized in that: The specific steps for analyzing the inventory fit index of each product sold within the industry chain are as follows: Obtain the optimal inventory level, maximum inventory level, and maximum allowable inventory retention time for each product sold within the industry chain; The current inventory, backlog inventory, and inventory response time difference of each sales product in the industrial chain are comprehensively analyzed in combination with the optimal inventory, maximum inventory, and maximum allowable inventory backlog time of each sales product in the industrial chain to obtain the inventory adaptation index of each sales product in the industrial chain.

10. The cloud computing-based smart industry chain big data management system according to claim 9, characterized in that: The specific formula for calculating and analyzing the inventory adaptation index of a certain sales product within the industry chain is as follows: Among them, KsP, DkC, ZyK, LkC, ZkC, KxY, and YxK are the inventory adaptation index, current inventory, optimal inventory, stranded inventory, maximum inventory, inventory response time difference, and maximum allowable inventory stranded time of a certain sales product in the industrial chain, respectively. δ1, δ2, and δ3 are the inventory deviation impact coefficient, stranded inventory weight coefficient, and inventory response sensitivity coefficient stored in the database, respectively. e is a natural constant.

Images