A spinning production management method, system, device and medium

Abstract

This application relates to a spinning production management method, system, equipment, and medium, belonging to the technical field of spinning production. It includes: acquiring sensor data, business data, and equipment operation data of each spinning machine in the workshop, and calculating the comprehensive health index of the spinning machines; performing grid processing on the yarn production workshop and mapping the position of each spinning machine to the grid; calculating the comprehensive risk value of each grid based on the comprehensive health index, and calculating the average risk value of each air supply management area based on the comprehensive risk value; if the average risk value of a certain air supply management area exceeds the warning threshold for N consecutive periods, it is determined to be a high-risk area; within the high-risk area, finding the k spinning machines with the lowest comprehensive health index and marking them as priority inspection machines; generating an inspection path based on the current position of the operator, the position of the priority inspection machines, and the inspection sequence, and sending it to the operator's handheld terminal. This application has the beneficial effect of reducing the waste of manpower and material resources.

Description

Technical Field

[0001] This application relates to the technical field of spinning production, and in particular to a spinning production management method, system, equipment and medium. Background Technology

[0002] In the spinning process, the ring spinning machine is a key piece of equipment, and its operating status directly affects the output and quality of yarn. Traditional spinning production management methods often rely on manual experience for equipment inspection and troubleshooting, making it difficult to grasp the real-time and accurate operating status of each ring spinning machine. With the expansion of production scale and the increase in the degree of equipment automation, the number of ring spinning machines in spinning workshops is large, and the complexity and difficulty of equipment management are constantly increasing. Traditional management methods can no longer meet the needs of modern production.

[0003] Currently, some spinning mills manage their ring spinning machines through regular inspections. Inspectors check each machine in the workshop at fixed intervals, recording operating parameters and malfunctions. When any abnormalities are found, the inspectors promptly notify maintenance personnel. In addition, companies develop corresponding maintenance plans based on the equipment's age and operating time, ensuring regular upkeep and repairs.

[0004] However, the aforementioned technologies represent a passive, responsive management model, which can only address issues after a significant equipment malfunction or anomaly occurs. This approach fails to detect potential problems proactively, potentially leading to production interruptions, equipment damage, and increased production costs. Secondly, manual inspection is inefficient and susceptible to the influence of inspectors' experience and subjective factors, making it difficult to guarantee the accuracy and reliability of inspection results and resulting in a waste of human and material resources. Summary of the Invention

[0005] To reduce the waste of human and material resources, this application provides a spinning production management method, system, equipment, and medium.

[0006] Firstly, this application provides a spinning production management method, which adopts the following technical solution:

[0007] A spinning production management method, comprising:

[0008] Acquire sensor data, business data, and equipment operation data of each spinning machine in the workshop;

[0009] Based on the equipment operation data, the sensor data, and the business data, calculate the comprehensive health index of each spinning machine;

[0010] The yarn production workshop is gridded, and the position of each spinning machine is mapped into the grid.

[0011] The comprehensive risk value of each grid is calculated based on the comprehensive health index, and the average risk value of each air supply management area is calculated based on the comprehensive risk value.

[0012] If the average risk value of a certain air supply management area exceeds the warning threshold for N consecutive periods, it is determined to be a high-risk area.

[0013] Within the high-risk area, locate the k spinning machines with the lowest comprehensive health index and mark them as priority inspection machines;

[0014] Based on the operator's current location, the location of the priority inspection machine, and the inspection sequence, an inspection path is generated and sent to the operator's handheld terminal.

[0015] By adopting the above technical solution, the calculation of the comprehensive health index enables a quantitative assessment of the operating status of each spinning machine. Through grid-based processing, equipment location is correlated with risk values. Combined with the calculation of the average risk value of the air supply management area, high-risk areas exceeding risk standards over multiple consecutive cycles can be identified in a timely manner at a macro level, avoiding systemic production problems that may be caused by localized equipment failures. Based on this, the k spinning machines with the lowest comprehensive health index are prioritized for inspection, ensuring accurate allocation of inspection resources and avoiding the waste of manpower and resources caused by blind inspections. The optimal inspection path is generated by combining the current location of the machine operator and the inspection sequence and distributed to handheld terminals, further optimizing the inspection process and improving inspection efficiency and response speed. Overall, this solution realizes a transformation in equipment management during the spinning production process from passive response to proactive early warning, and from extensive management to refined control. It not only improves the efficiency of equipment failure detection and handling, reducing the risk of production interruptions, but also effectively improves the work efficiency of machine operators by rationally allocating inspection resources and optimizing inspection paths, ultimately promoting the production stability and product quality improvement of the entire spinning workshop.

[0016] Optionally, the steps for calculating the overall health index of each spinning machine include:

[0017] The score for the frequency of decapitation is calculated based on the equipment operation data.

[0018] Calculate equipment status deductions and consumable cycle deductions based on the aforementioned business data;

[0019] Environmental tolerance score is calculated based on the sensor data;

[0020] The comprehensive health index for each spinning machine is calculated based on the deductions for the frequency of yarn breakage, the equipment status, the consumables cycle, and the environmental tolerance.

[0021] By adopting the above technical solution, the complex operating state of the spinning machine is broken down into four core dimensions: breakage frequency, equipment status, consumable cycle, and environmental tolerance. Each dimension is then quantified and scored, enabling a multi-dimensional and refined assessment of the equipment's health status. By comprehensively calculating the scores across these four dimensions, the resulting comprehensive health index not only fully covers the equipment's status characteristics in terms of production efficiency, mechanical performance, consumable management, and environmental adaptability, but also, through the scoring mechanism, sensitively reflects various abnormal indicators, allowing the health index value to accurately quantify the actual health level of the equipment. This multi-dimensional integrated assessment method avoids the one-sidedness of single-indicator assessments, improves the accuracy of equipment health management, helps to identify potential equipment problems early, reduces the failure rate, and ensures the continuity and stability of spinning production.

[0022] Optionally, the step of calculating the comprehensive risk value for each grid based on the comprehensive health index includes:

[0023] The comprehensive health index of each spinning machine is converted into a risk diffusion intensity base, and the superposition value of risk diffusion from all spinning machines to each grid is calculated based on the risk diffusion intensity base.

[0024] Calculate the fly ash risk factor for each grid based on the sensor data;

[0025] Based on the location, wind speed, and wind direction of the air conditioning vents, predict the main airflow path for the next m minutes, and calculate the air supply influence factor for each grid based on the main path.

[0026] Based on the aforementioned fly ash risk factor and the aforementioned air supply impact factor, calculate the comprehensive environmental risk value corresponding to each grid.

[0027] The comprehensive risk value for each grid is calculated based on the comprehensive environmental risk value and the superposition value of the risk diffusion from all spinning machines.

[0028] By adopting the above technical solution, the comprehensive health index of a single spinning machine is converted into a risk diffusion intensity base and a grid superposition value is calculated. This intuitively reflects the potential impact of the equipment's own condition on the surrounding area, extending the individual risk of the equipment to the spatial area. The fly waste risk factor calculated based on sensor data captures the risk of key pollutants affecting production quality in the workshop environment. Furthermore, by combining the air conditioning vent parameters to predict the main airflow path and calculate the air supply influence factor, the dynamic effect of airflow movement on risk diffusion in the workshop is fully considered. The comprehensive environmental risk value formed by the combination of these two factors compensates for the shortcomings of traditional static risk assessments that ignore dynamic environmental changes. Through the coupled calculation of the comprehensive environmental risk value and the equipment risk diffusion superposition value, a three-dimensional risk assessment model covering equipment condition, environmental pollutants, and airflow propagation characteristics is constructed. This ensures that the comprehensive risk value of each grid reflects not only the health hazards of the equipment itself but also the promoting or inhibiting effects of environmental factors on risk diffusion, as well as the mutual influence of risks between different areas. This multi-factor collaborative risk assessment method improves the spatial accuracy and dynamic response capability of risk identification, further reducing the incidence of production failures and enhancing overall production stability.

[0029] Optionally, the steps for generating an inspection path based on the operator's current position, the position of the priority inspection machine, and the inspection sequence include:

[0030] The layout topology of the loading workshop with physical constraints is used as the underlying map for path planning.

[0031] Taking the current position of the machine operator as the starting point of the path, and the positions of all k priority inspection machines as the necessary target points, combined with the constraints of the inspection order, the optimal inspection path connecting the starting point of the path, traversing all k target points and the next task point in sequence is calculated in the underlying map. The optimal inspection path represents the minimum total moving distance or estimated moving time.

[0032] By adopting the above technical solution, a layout topology map with physical constraints is loaded as the underlying map to ensure that path planning can accurately reflect the actual environmental characteristics of the workshop, such as equipment distribution, passage width, and obstacles, thus avoiding the problem of theoretical paths being disconnected from on-site operations. Starting from the current position of the machine operator and prioritizing the inspected machines as the necessary target points, and strictly adhering to the inspection sequence constraints, the optimal path with the minimum total travel distance or estimated time is calculated. This path generation mechanism not only solves the subjectivity and experience-dependent problems of traditional manual path planning but also achieves optimal allocation of inspection resources by quantifying the objective (minimizing distance or time). This allows machine operators to complete the inspection of more critical equipment within the same timeframe, improving work efficiency per unit time. Simultaneously, path planning considering physical constraints ensures the safety and feasibility of the inspection process, avoiding collision risks or passage obstacles caused by unreasonable paths, reducing the labor intensity of machine operators, shortening the inspection cycle, and providing time assurance for the timely detection and handling of equipment failures in the spinning workshop, further improving the stability and continuity of the production process.

[0033] Optionally, the spinning production management method further includes:

[0034] Construct a regional comprehensive cost function based on the average risk value and regional energy consumption cost of the air supply management area;

[0035] The candidate frequencies of the fans are determined based on the allowable adjustment range of the frequency of the fans corresponding to the air supply management area.

[0036] Predict the regional energy consumption cost and regional risk value corresponding to each candidate frequency, and substitute the regional energy consumption cost and regional risk value into the regional comprehensive cost function to obtain the corresponding candidate comprehensive cost;

[0037] Select the candidate frequency corresponding to the lowest overall cost as the optimal setting frequency, and generate the wind turbine frequency adjustment command.

[0038] By adopting the above technical solution, a comprehensive cost function constructed based on the average risk value and regional energy consumption cost of the air supply management area breaks down the barriers of separate decision-making on risk and energy consumption in traditional management. It integrates both into a unified quantitative evaluation framework, ensuring that the decision-making process reflects both the necessity of risk control and the economic efficiency of energy consumption costs. Candidate frequencies are determined by the allowable adjustment range of the fan frequency, and the regional energy consumption cost and regional risk value corresponding to each candidate frequency are predicted, providing input data for the comprehensive cost function under multiple scenarios and ensuring the comprehensiveness of the decision-making basis. The frequency corresponding to the minimum candidate comprehensive cost is selected as the optimal setting frequency, and adjustment instructions are generated, achieving the goal of minimizing energy consumption costs while meeting regional risk control requirements. This dynamic optimization mechanism can adaptively adjust the fan operating parameters according to real-time changes in regional risk value and energy consumption cost, avoiding energy waste or risk control problems caused by fixed-frequency operation. Furthermore, by quantifying risk factors as part of the cost function, energy-saving measures no longer come at the expense of production safety, but rather form a positive interaction with risk management. This not only improved the economic efficiency of fan operation and reduced the overall energy consumption cost of the workshop, but also optimized the air supply environment by dynamically adjusting the fan frequency, indirectly promoting the reduction of regional risk values, and ultimately achieving a dual improvement in the safety and efficiency of the spinning workshop.

[0039] Optionally, steps prior to constructing the regional integrated cost function include:

[0040] Determine whether the average risk value of the current air supply management area exceeds the safety red line threshold;

[0041] If yes, then set the corresponding wind turbine frequency to the highest level; otherwise, construct a regional comprehensive cost function.

[0042] By adopting the above technical solution, a step of judging the average risk value and safety red line threshold of the air supply management area is added before constructing the regional comprehensive cost function. This forms a two-layer decision-making mechanism of safety bottom line control + dynamic cost optimization, effectively improving the safety and flexibility of spinning workshop management. When the regional average risk value exceeds the safety red line threshold, the fan frequency is directly set to the highest level, which can enhance the air supply effect in the most direct and fastest way. By enhancing airflow circulation, the regional risk is quickly reduced, avoiding production accidents caused by the continuous accumulation of risk, and providing a rigid guarantee for workshop safety. When the risk value does not exceed the threshold, the regional comprehensive cost function is then activated to optimize energy consumption and risk in a coordinated manner. On the basis of ensuring safety, reasonable control of energy consumption costs is achieved through fine parameter adjustments, avoiding energy waste caused by blindly maintaining a high frequency. This layered decision-making logic not only adheres to the safety red line and eliminates the possibility of sacrificing production safety in pursuit of cost reduction, but also allows the fan operation strategy to be flexibly adjusted according to the actual risk situation by dynamically switching between "safety priority" and "cost optimization" modes, achieving optimal decision-making in different scenarios.

[0043] Optionally, the spinning production management method further includes:

[0044] A health status evolution model for a spinning frame is constructed based on historical comprehensive health indices, inspection records, and maintenance logs.

[0045] The health status evolution model is used to predict the trend of the comprehensive health index of each spinning machine over the next P cycles, and a degradation curve is generated.

[0046] Based on the prediction results, equipment whose comprehensive health index continues to decline and is expected to fall below the warning threshold within Q cycles is identified and marked as potentially deteriorating equipment.

[0047] Increase the monitoring frequency and sampling density of all grids containing potentially deteriorated equipment, and trigger preventative maintenance work orders to be pushed to the equipment maintenance end.

[0048] By adopting the above technical solution, the comprehensive health index for the next P cycles is predicted using a health status evolution model, and degradation curves are generated. This allows for a direct visualization of the equipment performance decline trend, enabling managers to identify potentially deteriorating machines whose comprehensive health index is continuously decreasing and is expected to fall below the warning threshold within Q cycles. This effectively avoids the production interruption risks associated with traditional post-failure maintenance. Furthermore, by increasing the monitoring frequency and sampling density of the grid containing potentially deteriorating machines, subtle changes in equipment status can be captured more accurately, providing more timely data support for preventative maintenance. Preventative maintenance work orders are triggered and pushed to the equipment maintenance end, ensuring that maintenance resources can intervene early, completing intervention before severe equipment performance degradation, thus reducing the failure rate at the source. This approach not only shifts the focus of equipment management from post-failure repair to pre-failure prevention, reducing production losses and maintenance costs caused by sudden failures, but also avoids resource waste caused by indiscriminate monitoring and maintenance of all equipment by accurately locating potentially deteriorating machines. Simultaneously, the combination of high-frequency monitoring and preventative maintenance further extends the effective service life of equipment and improves the stability and reliability of equipment operation.

[0049] Secondly, this application provides a spinning production management system, which adopts the following technical solution:

[0050] A spinning production management system, comprising:

[0051] The data acquisition module is used to acquire sensor data, business data, and equipment operation data of each spinning machine in the workshop;

[0052] The data processing module is used to calculate the comprehensive health index of each spinning machine based on the equipment operation data, the sensor data, and the business data.

[0053] The meshing module is used to mesh the yarn production workshop and map the position of each spinning machine into the mesh.

[0054] The data processing module is also used to calculate the comprehensive risk value of each grid based on the comprehensive health index, and to calculate the average risk value of each air supply management area based on the comprehensive risk value.

[0055] The judgment module is used to determine a high-risk area when the average risk value of a certain air supply management area exceeds the warning threshold for N consecutive cycles.

[0056] The filtering module is used to find the k spinning machines with the lowest comprehensive health index in the high-risk area and mark them as priority inspection machines;

[0057] The route module is used to generate an inspection path based on the current location of the operator, the location of the priority inspection machine, and the inspection order, and then send it to the operator's handheld terminal.

[0058] Thirdly, this application provides a computer device that adopts the following technical solution:

[0059] A computer device includes a memory, a processor, and a computer program stored in the memory, the processor executing the computer program to implement the spinning production management method as described in the first aspect.

[0060] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0061] A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the spinning production management method as described in the first aspect.

[0062] In summary, this application includes at least one of the following beneficial technical effects:

[0063] 1. Prioritizing the k spinning machines with the lowest overall health index as key inspection targets ensures accurate allocation of inspection resources and avoids the waste of manpower and resources caused by blind inspections. Optimal inspection paths are generated based on the current location of the machine operators and the inspection sequence and distributed to handheld terminals, further optimizing the inspection process and improving efficiency and response speed. Overall, this solution realizes a transformation in equipment management during spinning production from passive response to proactive early warning, and from extensive management to refined control. It not only improves the efficiency of equipment fault detection and handling, reducing the risk of production interruptions, but also effectively improves the work efficiency of machine operators by rationally allocating inspection resources and optimizing inspection paths, ultimately promoting the production stability and product quality improvement of the entire spinning workshop.

[0064] 2. The dynamic optimization mechanism can adaptively adjust the fan operating parameters based on real-time changes in regional risk values ​​and energy costs, avoiding energy waste or risk control issues caused by fixed-frequency operation. Furthermore, by quantifying risk factors as part of the cost function, energy-saving measures no longer come at the expense of production safety, but rather form a positive interaction with risk management. This not only improves the economic efficiency of fan operation and reduces the overall energy cost of the workshop, but also optimizes the air supply environment by dynamically adjusting the fan frequency, indirectly promoting a reduction in regional risk values, ultimately achieving a dual improvement in the safety and efficiency of the spinning workshop. Attached Figure Description

[0065] Figure 1 This is a first flowchart of an embodiment of the method of this application;

[0066] Figure 2 This is a second flowchart of an embodiment of the method of this application;

[0067] Figure 3This is a third flowchart of an embodiment of the method of this application;

[0068] Figure 4 This is the fourth flowchart of an embodiment of the method of this application;

[0069] Figure 5 This is the fifth flowchart of an embodiment of the method of this application. Detailed Implementation

[0070] To make the purpose, technical solution, and advantages of this application clearer, the following description is provided in conjunction with the appendix. Figures 1-5 The present application will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the application.

[0071] The first embodiment of this application discloses a method for managing yarn spinning production. (Refer to...) Figure 1 The spinning production management method includes S110-S170:

[0072] S110 acquires sensor data, business data, and equipment operation data of each spinning machine in the workshop;

[0073] S120 calculates the comprehensive health index of each spinning machine based on equipment operation data, sensor data, and business data;

[0074] S130, the yarn production workshop is gridded and the position of each spinning machine is mapped into the grid;

[0075] S140, calculate the comprehensive risk value of each grid based on the comprehensive health index, and calculate the average risk value of each air supply management area based on the comprehensive risk value;

[0076] S150, if the average risk value of a certain air supply management area exceeds the warning threshold for N consecutive cycles, it is determined to be a high-risk area.

[0077] S160, in high-risk areas, find the k spinning machines with the lowest comprehensive health index and mark them as priority inspection machines;

[0078] S170 generates an inspection path based on the current location of the operator, the location of the priority inspection machine, and the inspection sequence, and sends it to the operator's handheld terminal.

[0079] Specifically, in step S110, comprehensive collection and structured processing of multi-dimensional data from the workshop are required. This step forms the foundation of the entire system's "perception layer," necessitating the establishment of a unified data access platform. This platform employs an Industrial Internet of Things (IIoT) architecture, deploying edge computing gateways to connect to the spinning machine PLC controller, various environmental sensors such as temperature and humidity sensors, dust concentration sensors, RFID tags, and barcode scanning terminals. Each spinning machine uploads operational status data via the OPC UA protocol or Modbus TCP protocol, including key parameters such as spindle speed, breakage signal, winding length, splicing count, and motor current. Environmental sensors report local temperature and humidity and fly waste particle counts at minute-level frequencies. Business systems such as MES periodically push static and dynamic attributes such as equipment maintenance records, traveler replacement logs, and current production product information. All data, after timestamp alignment, enters a real-time stream processing engine for cleaning, deduplication, and format standardization, forming a time-series database (such as InfluxDB or TDengine) organized at the "machine-time" granularity, providing high-fidelity, low-latency data support for subsequent analysis.

[0080] Reference Figure 2 The steps in S120 for calculating the overall health index of each spinning frame include S210-S240:

[0081] S210, Deduct points based on the frequency of head breakage calculated from equipment operation data;

[0082] S220 calculates equipment status deductions and consumable cycle deductions based on business data;

[0083] S230 calculates environmental tolerance deduction based on sensor data;

[0084] S240 calculates the comprehensive health index for each spinning machine based on deductions for breakage frequency, equipment status, consumable cycle, and environmental tolerance.

[0085] Specifically, in step S210, the deduction for the yarn breakage frequency dimension is S1 = MIN(50, (Bminute(m, T) / Bbase(m))*50), where Bminute(m, T) represents the number of yarn breaks on the spinning machine m in the current minute T, and Bbase(m) represents the average number of yarn breaks per minute on the machine m in the same period of the past 30 days under the current production variety. As a historical baseline, the MIN function ensures that the maximum deduction for this dimension does not exceed 50 points.

[0086] The system needs to pre-build a three-dimensional historical statistical model of "variety-shift-time period": For each machine type and the combination of spun varieties, the system automatically extracts the average number of yarn breaks per minute in the same shift (morning / afternoon / night shift) and the same time period (±5 minute window) over the past 30 days as Bbase(m), and caches it in Redis for real-time access. When new data flows in, the system calculates the current number of yarn breaks per minute Bminute(m, T), substitutes it into the formula to obtain the original score, and then uses the MIN function to truncate the upper limit. For example, if the historical average number of yarn breaks per minute for machine m is 2 times / minute, and the current minute suddenly increases to 15 times, then S1=MIN(50,(15 / 2)*50)=50, which triggers the maximum deduction, indicating that the machine has abnormal fluctuations. This mechanism effectively avoids misjudgment caused by occasional yarn breaks, while capturing continuous deterioration trends. In addition, a sliding standard deviation monitoring can be set in the background. If the standard deviation exceeds twice the mean for several consecutive periods, an auxiliary alarm will be triggered in advance.

[0087] In step S220, the device status is deducted:

[0088] S2=30*((Tnow-Tmaintainlast(m)) / Cyclemaintain(m)), where Tnow represents the current system time, Tmaintainlast(m) represents the time of the last critical maintenance of machine m, and Cyclemaintain(m) represents the standard maintenance cycle of machine m.

[0089] Equipment status deductions reflect the negative impact of maintenance delays on equipment reliability. The system needs to maintain an "equipment-maintenance cycle" mapping table. For example, the standard critical maintenance cycle for a spinning machine is Cyclemaintain(m) = 15 days. If the last Tmaintainlast(m) was April 1st, and the current Tnow = April 10th, then 9 days have passed, accounting for 60%. Therefore, S2 = 30 × (9 / 15) = 18 points, indicating a significant deviation. If maintenance is not performed within the cycle, the score continues to rise until it approaches the 30-point cap.

[0090] Consumables cycle deduction points:

[0091] S3=20*((Tnow-Tringlast(m)) / Cyclering(YarnType(m)));

[0092] Tringlast(m) indicates the time when the traveler on machine m was last replaced, and Cyclering(YarnType(m)) indicates the recommended traveler replacement cycle for the currently spun variety YarnType(m), provided by the process database.

[0093] The consumables cycle deduction focuses on controlling the lifespan of the traveler, which relies on a process database. This database needs to pre-enter the recommended replacement cycle (Cyclering(YarnType(m))) for various yarn types. For example, combed JC / T 60 count yarn is recommended to be replaced every 7 days. The system records the time (Tringlast(m)) of each traveler replacement operation via RFID or barcode scanning and synchronizes it to the central database after daily inspection. The aging ratio is then calculated daily on a rolling basis to provide preventative reminders. For example, if a machine's yarn requires traveler replacement every 7 days but has been used for 9 days, the score contribution is 20 × (9 / 7) ≈ 25.7 > 20. In this case, the maximum deduction of 20 points is still applied, which meets the design limit.

[0094] In step S230, the environmental tolerance deduction S4 = 10 * (DeltaRH(m,T) / 10); DeltaRH(m,T) = MAX(0,|RHloc(m,T)-RHoptimallow(m)|,|RHloc(m,T)-RHoptimalhigh(m)|), where RHloc(m,T) is the average humidity of the temperature and humidity sensor at point m on the machine, and RHoptimallow(m) and RHoptimalhigh(m) are the lower and upper limits of the optimal humidity range fitted based on the historical data of the machine.

[0095] Each spinning machine is equipped with dedicated temperature and humidity sensors (spaced approximately 10-15 meters apart). The system collects RHloc(m,T) values ​​every minute. Simultaneously, based on the machine's historical breakage rate and humidity data from the past three months, statistical regression or machine learning methods (such as random forest regression combined with SHAP value analysis) are used to fit the optimal operating range [RHoptimallow(m),RHoptimalhigh(m)]. For example, some high-count yarn varieties prefer higher humidity (e.g., 58%~62%), while low-count rovings may adapt to a wider range (50%~65%). DeltaRH(m, T) is defined as the maximum absolute value of the current humidity deviation from the upper and lower limits; if within the range, it is 0. Finally, S4 = 10 × (DeltaRH / 10), meaning that 1 point is deducted for every 10 percentage points exceeding the limit, with a maximum of 10 points. This design embodies the flexible control concept of "tolerating small deviations and strictly controlling large deviations." Assuming the measured humidity of a certain grid is 70%, and the optimal range for the machine in this area is 55%-60%, then |70-55|=15, |70-60|=10. Taking MAX, we get DeltaRH=15, S4=10×(15 / 10)=15 minutes. This indicates that excessive humidity leads to increased fiber conductivity and reduced static electricity accumulation, but it may also cause problems such as winding rollers.

[0096] In step S240, the comprehensive health index HI(m,T) for each spinning machine is 100-(w1*S1+w2*S2+w3*S3+w4*S4), where w1, w2, w3, and w4 are weighting coefficients and satisfy w1+w2+w3+w4=1.

[0097] The weights w1 to w4 can be flexibly adjusted according to seasonal operating conditions: for example, w4 (environmental item) can be increased to 0.3 during the rainy season, and similarly during the dry winter season; w2 (equipment status) is reduced and w1 (head breakage) is increased during the initial production of new machines to highlight performance verification; under normal production conditions, w1=0.5, w2=0.3, w3=0.15, w4=0.05 can be set. The system provides a visual configuration panel for managers to set, and changes take effect immediately in subsequent calculations. The higher the HI value, the healthier the equipment, which facilitates horizontal comparison and trend tracking. For example, a piece of equipment that frequently breaks heads but has just been maintained may score 100-(50×0.5+0×0.3+5×0.15+8×0.05)=73.85, indicating that although basic maintenance is good, the operating performance is poor.

[0098] In step S130, the system imports the workshop CAD layout and divides it into several regular square grids, such as those with sides of 3-5 meters, matching the sensor coverage radius. Each spinning machine is mapped to its assigned grid j based on its GPS location or manually labeled coordinates. The grid division results are saved in GeoJSON format and a spatial index is created with the device ID for easy retrieval of neighboring devices. This process can be completed using open-source GIS tools (such as QGIS or PostGIS) and integrated into the system's front-end map module. For example, a 2000㎡ spinning workshop can be divided into approximately 100 grids, each with a unique code (such as J01-J99), and associated with HVAC air supply zones.

[0099] Reference Figure 3 The steps in S140 for calculating the comprehensive risk value for each grid based on the comprehensive health index include S310-S350:

[0100] S310 converts the comprehensive health index of each spinning machine into a risk diffusion intensity base, and calculates the superposition value of risk diffusion from all spinning machines to each grid based on the risk diffusion intensity base.

[0101] S320 calculates the fly debris risk factor for each grid based on sensor data;

[0102] S330 predicts the main airflow path for the next m minutes based on the location, wind speed, and wind direction of the air conditioning outlet, and calculates the air supply influence factor for each grid based on the main path.

[0103] S340, calculate the comprehensive environmental risk value for each grid based on the fly flower risk factor and the air supply impact factor;

[0104] S350 calculates the comprehensive risk value for each grid based on the comprehensive environmental risk value and the superposition value of the risk diffusion from all spinning machines.

[0105] Specifically, in step S310, the concept of "risk diffusion" is introduced to simulate the spatial diffusion effect of the potential impact of equipment failure. Its core implementation lies in the superposition model of Rdevice(j, T): for any target grid j, all M spinning machines m are traversed, and the risk base (100-HI(m,T)) / 10 (range 0~10) converted from their comprehensive health index is calculated, then multiplied by... Achieve distance decay. This is the attenuation coefficient, reflecting the risk propagation capability. A larger value indicates faster attenuation, meaning only the adjacent area is affected. It can be calibrated through field experiments: for example, in a sudden surge in failure events, the actual failure frequency of grids at different distances can be measured to infer the impact. This means that for every meter of distance, the risk impact decreases by approximately 55%. This superposition model can be implemented in batches using matrix operations: construct an M×J dimensional distance matrix D and a health impact matrix H, perform broadcast multiplication, and then sum to obtain the risk distribution map for the entire workshop. For example, an old machine with a HI of only 60 can contribute (40 / 10)×exp(-0.3×5)≈4×0.22=0.88 to the risk of adjacent grids, while its risk contribution to distant grids 20 meters away drops to near zero, demonstrating a clear local dominance characteristic.

[0106] In step S320, the fly ash risk factor Rdust(j,T) directly reflects the risk of exceeding cleanliness standards; Rdust(j,T) = Dustavg(j,T) / Dustthreshold, where the fly ash concentration Dustavg(j,T) is reported every minute by a laser scattering dust meter and is used in the calculation after filtering and smoothing; Dustthreshold is usually set to 5 mg / m³ (according to textile industry standards). For example, if the measured value of a certain grid reaches 8 mg / m³, then Rdust = 8 / 5 = 1.6 > 1, which is judged as exceeding the standard.

[0107] In steps S330 and S340, the location, wind speed, and direction of the air conditioning vents can be imported from the BIM model or manually labeled. Combined with CFD (Computational Fluid Dynamics) simulation, airflow path maps under typical operating conditions are pre-generated. The system updates the predicted path in real time based on the current fan frequency and valve opening, determining which grids are downstream of the prevailing wind direction. For example, if the northwest corner vent is in strong cooling mode, the system predicts the airflow will advance southeast, passing through grids J21→J32→J43. Grids along these paths will receive higher weights for the airflow impact factor. The airflow impact factor Rairflow depends not only on path connectivity but also on temperature and humidity deviations: for example, if the supply air temperature is set to 24℃ and the actual measured temperature is 26.5℃, a deviation of +2.5℃ is introduced, resulting in a penalty coefficient. For adjustment coefficients, To account for the deviation, the risk weight propagating along this path is amplified. The final comprehensive environmental risk value for each grid is then calculated. Adjustments can be made according to the season; in summer, focus on temperature control, and in winter, pay attention to humidity balance.

[0108] In step S350, equipment risk and environmental risk are further integrated to form the final comprehensive risk value Rtotal(j,T)=p·Rdevice(j,T)+n·Re(j,T), where p+n=1. This value can be dynamically adjusted according to production priorities. For example, during the production of high value-added products, the weight of equipment risk is increased to ensure stable product quality. Each grid thus obtains a unique comprehensive risk value, forming a workshop-wide risk heatmap.

[0109] Further aggregation is performed by air supply management area, that is, the arithmetic mean of the Rtotal values ​​of all grids belonging to the same air conditioning zone is taken to obtain Rzone(zone,T), which is used for macro-monitoring; zone refers to the air supply management area number.

[0110] In step S160, a dual judgment condition is set: if a certain air supply management area exceeds the warning threshold (e.g., 75 minutes) for "N consecutive cycles" (e.g., N=3, corresponding to 3 minutes), then the air supply management area is judged as a high-risk area.

[0111] S170, based on the current position of the operator, the position of the priority inspection machine, and the inspection sequence, the specific steps for generating the inspection path include:

[0112] The layout topology of the loading workshop with physical constraints is used as the underlying map for path planning.

[0113] Taking the current position of the machine operator as the starting point of the path, and the positions of all k priority inspection machines as the necessary target points, combined with the constraints of the inspection order, the optimal inspection path connecting the starting point of the path, traversing all k target points and the next task point in sequence is calculated in the bottom map. The optimal inspection path represents the minimum total moving distance or estimated moving time.

[0114] Specifically, priority inspection machines are selected within high-risk areas. The k-value can be dynamically adjusted based on the operator's workload, typically k=3~5. The ranking is based not only on the lowest HI (Highest Risk Index) but also on the rate of change in trend: for example, if two machines currently have HIs of 62 and 65 respectively, but the latter has decreased by 8 points in the past 10 minutes (a faster decrease), then it should be given priority. The system can have a built-in "risk urgency" scoring function that combines absolute levels and the slope of change to generate a recommended list. Marked machines are automatically synchronized to the scheduling system.

[0115] A physically constrained workshop topology map is loaded for path planning. This map includes not only geometric coordinates but also labels inaccessible areas (such as electrical cabinets and fire exits), width restrictions on narrow passages, stair ramps, and other limitations. The map is stored in a graph structure, with nodes representing key locations (equipment locations, intersections, task points) and edges representing reachable paths and their costs (distance or travel time). It can be generated through on-site scanning using SLAM mapping technology or converted from manual annotations on AutoCAD drawings. The underlying Dijkstra or A* algorithm engine supports path search.

[0116] Starting from the current position Pstart of the operator, with k target devices Pi (i=1..k) as target points, and the next task point Pnext (such as a shift change point or material collection point) as the destination, the system needs to find the shortest Hamiltonian path: minimize Σdist(Pi→Pi+1), satisfying the requirement of sequentially visiting all necessary points. Considering practical operating habits, priority order can be set, such as from low to high HI, or the algorithm can be freely arranged to minimize the total travel distance. The path result is sent to the handheld terminal APP in the form of navigation arrows, and voice prompts and obstacle avoidance replanning functions are supported. For example, if an operator is located at the south gate post and needs to inspect three low HI devices on the north side before going to the central control room to sign in, the system calculates a detour route that avoids the busy loading and unloading area, with an estimated travel time of 4.2 minutes, which reduces congestion and delays compared to a straight path.

[0117] Reference Figure 4 Furthermore, the spinning production management methods also include S410-S440:

[0118] S410, construct a regional comprehensive cost function based on the average risk value and regional energy consumption cost of the air supply management area;

[0119] S420, determine the candidate frequency of the fan according to the frequency adjustment range of the fan corresponding to the air supply management area;

[0120] S430, predict the regional energy consumption cost and regional risk value corresponding to each candidate frequency, and substitute the regional energy consumption cost and regional risk value into the regional comprehensive cost function to obtain the corresponding candidate comprehensive cost;

[0121] S440 selects the candidate frequency corresponding to the minimum candidate comprehensive cost as the optimal setting frequency and generates a wind turbine frequency adjustment command.

[0122] In addition, the steps prior to constructing the regional integrated cost function include:

[0123] Determine whether the average risk value of the current air supply management area exceeds the safety red line threshold;

[0124] If yes, then set the corresponding wind turbine frequency to the highest level; otherwise, construct a regional comprehensive cost function.

[0125] Specifically, the system first determines whether the Rzone exceeds the safety threshold. If so, it skips optimization and directly forces the corresponding fan frequency to the highest setting (e.g., 50Hz) to suppress the risk as quickly as possible and ensure production safety. If the threshold is not exceeded, it proceeds to the economic optimization process S410-S440.

[0126] In step S410, the regional integrated cost function C(zone,T)=wr*Rzonenorm(zone,T)+we*Pzonenorm(zone,T) is constructed;

[0127] Rzonenorm normalizes the average risk value by using the historical maximum value, such as dividing the average risk value by the historical maximum value. Pzonenorm reflects the pressure of energy consumption expenditure. For example, if the current power Pavg = 35kW, the rated power Prated = 50kW, and the electricity price Price = 1.2 yuan / kWh in a certain area, then Pzonenorm = (35 × 1.2) / 50 = 0.84. If the risk normalization value is 0.65, and wr = 0.6 and we = 0.4, then C = 0.6 × 0.65 + 0.4 × 0.84 = 0.726.

[0128] In step S420, a fan performance model needs to be established: based on the fan law, air volume ∝ frequency, power ∝ frequency³, therefore, P(f) ≈ Prated × (f / frated) can be estimated using the current frequency f. 3 Set the frequency adjustment step size (e.g., ±2Hz) to generate a candidate frequency set {f-4, f-2, f, f+2}, which represents the allowable frequency adjustment range for the limited fan, i.e., the minimum / maximum allowable frequency.

[0129] In step S430, Pavg and Rzone are predicted for each candidate frequency: the former is directly substituted into the Pzonenorm calculation model, while the latter requires reverse simulation of airflow improvement. The higher the frequency, the greater the air exchange volume, the faster the fly waste is diluted, and the lower the Rdust, thereby reducing the overall risk. For example, for every 1 Hz increase in frequency, Rdust decreases by about 5% to 8%; the C value of each candidate is estimated accordingly.

[0130] In step S440, the candidate frequency with the smallest C is selected as the optimal setting, and a Modbus RTU command is generated and sent to the frequency converter to complete closed-loop control. The entire process is executed every 5 minutes to achieve a dynamic balance between risk and energy consumption.

[0131] Reference Figure 5 Furthermore, the spinning production management methods also include S510-S540:

[0132] S510, based on historical comprehensive health index, inspection records and maintenance logs, constructs a health status evolution model for the spinning frame;

[0133] S520 uses a health status evolution model to predict the trend of the comprehensive health index of each spinning machine over the next P cycles and generates a degradation curve.

[0134] S530 identifies equipment whose comprehensive health index continues to decline and is expected to fall below the warning threshold within Q cycles based on the prediction results, and marks it as a potentially deteriorating machine.

[0135] S540 increases the monitoring frequency and sampling density of all grids containing potentially deteriorated equipment and triggers preventative maintenance work orders to be pushed to the equipment maintenance end.

[0136] Specifically, in step S510, an LSTM or Prophet time series model is used, with historical HI sequences as the main input, supplemented by inspection records (whether the steel collar is replaced, the tension plate is calibrated) and maintenance events (overhaul, motor replacement) as external covariates, to train an individualized degradation trajectory prediction model. The model is periodically retrained offline to maintain its timeliness.

[0137] In step S520, trend extrapolation is performed for the next P periods (e.g., P=60 minutes) to generate a degradation curve within the confidence interval, which is then visualized on the device's digital twin interface.

[0138] In step S530, an early warning rule is set: if a spinning machine shows a downward trend for three consecutive prediction points and is expected to fall below the HI=60 threshold within the Q=5th cycle, it is marked as a "potentially deteriorated machine".

[0139] In step S540, a dual response is triggered: first, the sensor sampling frequency of the grid where the potentially deteriorated machine is located is increased (e.g., from 1 minute to 15 seconds) to enhance monitoring density; second, a preventive maintenance work order is automatically generated and pushed to the equipment engineer's APP, which includes suggested measures (e.g., "check belt wear" and "lubricate spindle bearings"), a spare parts list, and a recommended shutdown window.

[0140] Based on the above method embodiments, the second embodiment of this application discloses a spinning production management system. The spinning production management system of this application can implement any of the above-described spinning production management methods, and the specific working processes of each module in the spinning production management system can be referred to the corresponding processes in the above method embodiments.

[0141] For ease of understanding, an example is as follows: A spinning production management system includes:

[0142] The data acquisition module is used to acquire sensor data, business data, and equipment operation data of each spinning machine in the workshop;

[0143] The data processing module is used to calculate the comprehensive health index of each spinning machine based on equipment operation data, sensor data, and business data.

[0144] The meshing module is used to mesh the yarn production workshop and map the position of each spinning machine into the mesh.

[0145] The data processing module is also used to calculate the comprehensive risk value of each grid based on the comprehensive health index, and to calculate the average risk value of each air supply management area based on the comprehensive risk value;

[0146] The judgment module is used to determine a high-risk area when the average risk value of a certain air supply management area exceeds the warning threshold for N consecutive cycles.

[0147] The filtering module is used to find the k spinning machines with the lowest comprehensive health index in high-risk areas and mark them as priority inspection machines;

[0148] The route module is used to generate an inspection path based on the current location of the operator, the location of the priority inspection machine, and the inspection order, and then send it to the operator's handheld terminal.

[0149] The third embodiment of this application provides a computer device, which may include a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement a spinning production management method.

[0150] The memory can communicate with the processor via a communication bus, which can be an address bus, a data bus, a control bus, etc.

[0151] Additionally, the memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device.

[0152] Furthermore, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0153] The fourth embodiment of this application provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as a spinning production management method.

[0154] The computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0155] It should be noted that the computer device and storage medium in the embodiments of this application are respectively electronic devices and storage media applying the above-described spinning production management method. Therefore, all embodiments of the above-described spinning production management method are applicable to the computer device and storage medium, and can achieve the same or similar beneficial effects. For the computer device / storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple; relevant details can be found in the descriptions of the method embodiments.

[0156] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.

[0157] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Any feature disclosed in this specification (including the abstract and drawings) may be replaced by other equivalent or similar features unless specifically stated otherwise. That is, unless specifically stated otherwise, each feature is only one example of a series of equivalent or similar features.

Claims

1. A method for managing spinning production, characterized in that, include: Acquire sensor data, business data, and equipment operation data of each spinning machine in the workshop; Based on the equipment operation data, the sensor data, and the business data, calculate the comprehensive health index of each spinning machine; The yarn production workshop is gridded, and the position of each spinning machine is mapped into the grid. The comprehensive risk value of each grid is calculated based on the comprehensive health index, and the average risk value of each air supply management area is calculated based on the comprehensive risk value. If the average risk value of a certain air supply management area exceeds the warning threshold for N consecutive periods, it is determined to be a high-risk area. Within the high-risk area, locate the k spinning machines with the lowest comprehensive health index and mark them as priority inspection machines; Based on the operator's current location, the location of the priority inspection machine, and the inspection sequence, an inspection path is generated and sent to the operator's handheld terminal.

2. The spinning production management method according to claim 1, characterized in that, The steps for calculating the overall health index of each spinning frame include: The score for the frequency of decapitation is calculated based on the equipment operation data. Calculate equipment status deductions and consumable cycle deductions based on the aforementioned business data; Environmental tolerance score is calculated based on the sensor data; The comprehensive health index for each spinning machine is calculated based on the deductions for the frequency of yarn breakage, the equipment status, the consumables cycle, and the environmental tolerance.

3. The spinning production management method according to claim 2, characterized in that, The steps for calculating the overall risk value for each grid based on the comprehensive health index include: The comprehensive health index of each spinning machine is converted into a risk diffusion intensity base, and the superposition value of risk diffusion from all spinning machines to each grid is calculated based on the risk diffusion intensity base. Calculate the fly ash risk factor for each grid based on the sensor data; Based on the location, wind speed, and wind direction of the air conditioning vents, predict the main airflow path for the next m minutes, and calculate the air supply influence factor for each grid based on the main path. Based on the aforementioned fly ash risk factor and the aforementioned air supply impact factor, calculate the comprehensive environmental risk value corresponding to each grid. The comprehensive risk value for each grid is calculated based on the comprehensive environmental risk value and the superposition value of the risk diffusion from all spinning machines.

4. The spinning production management method according to claim 1, characterized in that, The steps for generating an inspection path based on the operator's current location, the location of the priority inspection machine, and the inspection sequence include: The layout topology of the loading workshop with physical constraints is used as the underlying map for path planning. Taking the current position of the machine operator as the starting point of the path, and the positions of all k priority inspection machines as the necessary target points, combined with the constraints of the inspection order, the optimal inspection path connecting the starting point of the path, traversing all k target points and the next task point in sequence is calculated in the underlying map. The optimal inspection path represents the minimum total moving distance or estimated moving time.

5. The spinning production management method according to claim 4, characterized in that, The spinning production management method also includes: Construct a regional comprehensive cost function based on the average risk value and regional energy consumption cost of the air supply management area; The candidate frequencies of the fans are determined based on the allowable adjustment range of the frequency of the fans corresponding to the air supply management area. Predict the regional energy consumption cost and regional risk value corresponding to each candidate frequency, and substitute the regional energy consumption cost and regional risk value into the regional comprehensive cost function to obtain the corresponding candidate comprehensive cost; Select the candidate frequency corresponding to the lowest overall cost as the optimal setting frequency, and generate the wind turbine frequency adjustment command.

6. The spinning production management method according to claim 5, characterized in that, The steps before constructing the regional comprehensive cost function include: Determine whether the average risk value of the current air supply management area exceeds the safety red line threshold; If yes, then set the corresponding wind turbine frequency to the highest level; otherwise, construct a regional comprehensive cost function.

7. The spinning production management method according to claim 1, characterized in that, The spinning production management method also includes: A health status evolution model for a spinning frame is constructed based on historical comprehensive health indices, inspection records, and maintenance logs. The health status evolution model is used to predict the trend of the comprehensive health index of each spinning machine over the next P cycles, and a degradation curve is generated. Based on the prediction results, equipment whose comprehensive health index continues to decline and is expected to fall below the warning threshold within Q cycles is identified and marked as potentially deteriorating equipment. Increase the monitoring frequency and sampling density of all grids containing potentially deteriorated equipment, and trigger preventative maintenance work orders to be pushed to the equipment maintenance end.

8. A spinning production management system, characterized in that, Implementing the spinning production management method as described in any one of claims 1 to 7 includes: The data acquisition module is used to acquire sensor data, business data, and equipment operation data of each spinning machine in the workshop; The data processing module is used to calculate the comprehensive health index of each spinning machine based on the equipment operation data, the sensor data, and the business data. The meshing module is used to mesh the yarn production workshop and map the position of each spinning machine into the mesh. The data processing module is also used to calculate the comprehensive risk value of each grid based on the comprehensive health index, and to calculate the average risk value of each air supply management area based on the comprehensive risk value. The judgment module is used to determine a high-risk area when the average risk value of a certain air supply management area exceeds the warning threshold for N consecutive cycles. The filtering module is used to find the k spinning machines with the lowest comprehensive health index in the high-risk area and mark them as priority inspection machines; The route module is used to generate an inspection path based on the current location of the operator, the location of the priority inspection machine, and the inspection order, and then send it to the operator's handheld terminal.

9. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the spinning production management method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images