Intelligent monitoring method for spinning process based on bracelet terminal

Abstract

The invention discloses an intelligent monitoring method for a spinning process based on a bracelet terminal, relates to the technical field of spinning process monitoring, and is used for solving the problem of inaccurate path identification in a spinning monitoring process. According to the method, the initial inspection path is generated by combining the spatial distance of the textile equipment and the task priority, the path is adjusted according to the real-time position and the task completion progress, data acquisition and fusion processing are performed through the bracelet terminal, positioning results are unified to the same coordinate system, correction is performed by combining the confidence coefficient, and the current position and the preset path are compared in real time. The deviation distance and direction are calculated, a multi-level early warning mechanism is triggered, a deviation correction path is dynamically generated to guide workers to return to an inspection path, task omission caused by path deviation is reduced, an equipment coverage matrix and a thermodynamic diagram are generated in combination with inspection path data, equipment coverage records and deviation information, and the coverage condition and blind area distribution are reflected; and tasks are allocated to high-priority equipment and blind areas, so that routing inspection resources are reasonably allocated, and the coverage rate of the blind areas is improved.

Description

Technical Field

[0001] The present invention relates to the field of textile monitoring technology, and more specifically, to a textile process intelligent monitoring method based on a wristband terminal. Background Art

[0002] With the rapid development of Industry 4.0 and intelligent manufacturing, the textile industry is facing many challenges such as improving production efficiency, optimizing equipment management and ensuring personnel safety. Traditional textile process management and equipment inspection often rely on manual experience and manual records, resulting in low efficiency, inaccurate data and difficulty in real-time monitoring of potential risks on the production line. Especially in a large-scale production environment, how to achieve comprehensive monitoring of processes, equipment and personnel through intelligent means? As a portable wearable device, the wristband terminal integrates functions such as positioning, sensing, communication and real-time data processing, and has gradually become an effective tool to solve these problems. Through the wristband terminal, it can track the worker's inspection path in real time, monitor the worker's physiological state and collect equipment operation data, providing data support for intelligent production management.

[0003] Deficiencies in existing technologies: In the production environment of a textile factory, the execution of inspection tasks is crucial. The workers' inspection routes directly affect the equipment maintenance efficiency and the operating status of the production equipment. However, workers often deviate from the original inspection routes due to factors such as operating fatigue, complex environment, and busy processes. This deviation will not only lead to omissions in equipment inspections and increase the risk of potential failures, but will also affect the smoothness of the production process and lead to a decrease in production efficiency. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, there is a solution as follows to solve the problem of inaccurate path identification in the textile monitoring process in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The intelligent monitoring method of textile process based on wristband terminal includes the following steps: During the inspection and monitoring of the textile process, the initial inspection path is generated according to the spatial distance of the equipment and the task priority, and the path is adjusted according to the real-time location data and task completion progress during the inspection process; Obtain and process the data collected by the built-in sensor of the wristband terminal, unify it into the same coordinate system, calculate the global position of the processed data in combination with the confidence and environmental error correction, and generate the positioning result; Compare the real-time position with the planned path, calculate the deviation distance and direction, and trigger multi-level warnings based on the deviation distance and direction, dynamically correct the path, and conduct inspections based on the corrected inspection path; Acquire the path data, equipment coverage records and deviation information generated during the inspection process, generate equipment coverage matrix and heat map, calculate thermal value and blind spot priority, and prioritize inspection tasks to high-priority equipment and blind spots.

[0006] In a preferred embodiment, during the inspection and monitoring of the textile process, an initial inspection path is generated according to the spatial distance of the equipment and the task priority, and the path is adjusted according to the real-time position data and the task completion progress during the inspection process. The specific steps are as follows: Define the target task set, which includes inspection importance factor, inspection time, and spatial location of equipment; Establish the spatial distance matrix and task priority matrix of the equipment and generate the initial inspection path; The inspection time, the spatial distance of the equipment and the task priority are combined into the objective function of the path; The path is optimized through genetic algorithm, the device index is converted into a path sequence, the fitness of the path is evaluated according to the objective function, and a new path sequence is generated through selection, crossover and mutation operations. When the path converges or reaches the maximum number of iterations, the optimal path is output.

[0007] In a preferred embodiment, the data collected by the built-in sensor of the wristband terminal is obtained and processed, unified into the same coordinate system, and the global position is calculated based on the processed data in combination with the confidence and environmental error correction to generate the positioning result. The specific steps include: Obtain the data collected by the sensors set in the wristband terminal, and use Gaussian filtering to denoise the original positioning data collected by each sensor; Map the sensor's positioning data to a unified coordinate system; Calculate the confidence of each sensor estimate based on historical data and real-time signal strength; Perform sensor data fusion to combine the positioning results of each sensor into a global position estimate; The fusion result is corrected for errors caused by the environmental impact to obtain the corrected positioning result.

[0008] In a preferred embodiment, the real-time position is compared with the predetermined path, the deviation distance and deviation direction are calculated, and a multi-level warning is triggered according to the deviation distance and deviation direction. The specific steps are as follows: Perform deviation detection and obtain the current positioning result position at time t based on the multi-sensor fusion result , represents the horizontal axis, Represents the ordinate, the closest point to the planned path at time t , represents the horizontal axis, Represents the ordinate, and the two are compared to calculate the deviation distance between the current positioning result position at time t and the predetermined path And the deviation direction, the deviation distance calculation formula is: ,in, Indicates the minimum distance between the current position and the predetermined path; The deviation direction calculation formula is: ,in, Indicates the angular deviation of the current position relative to the predetermined path; when or When , it is determined that the worker has deviated from the path, where is the deviation distance threshold, is the deviation direction threshold; When a deviation from the path is detected, the early warning mechanism is triggered immediately, and the wristband terminal sends vibration, sound or screen prompts to the worker to notify him to return to the correct path; According to the degree of deviation and , set up different levels of early warning mechanisms: When the deviation is slight, the worker is prompted to make slight adjustments; If the deviation is significant, the bracelet will vibrate continuously and display the correction path simultaneously. If it is a serious deviation, it will immediately trigger the background management notification to remind the management personnel to intervene.

[0009] In a preferred embodiment, dynamic deviation correction of the path is performed, and inspection is performed according to the inspection path after the deviation correction, including the following steps: After a worker deviates from the path, dynamic correction is performed and the optimal inspection point is selected using a distance-weighted objective function; Based on the optimal inspection point and the current position, the Dijkstra algorithm is combined for path planning to generate the shortest path from the current position to the optimal inspection point.

[0010] In a preferred embodiment, the path data, equipment coverage records and deviation information generated during the inspection process are obtained, the equipment coverage matrix and thermal map are generated, the thermal value and blind spot priority are calculated, and the inspection tasks are preferentially assigned to high-priority equipment and blind spots, including the following steps: The wristband terminal collects the path data, equipment coverage records, and deviation information generated during the inspection process, and performs task mapping for each path point and inspection equipment; Device task mapping: determine whether a device has been inspected based on the mapping relationship between path points and devices, and generate a device coverage matrix; Based on the equipment coverage matrix and the location of the path points, a heat map of the equipment inspection in the factory is generated to show the inspection density distribution and blind spot locations: Calculate the thermal value based on the equipment inspection frequency and equipment importance factor; The blind spot identification process is to record the equipment set with a patrol frequency of 0 as the patrol blind spot; Redefine path optimization goals and adjust inspection task allocation based on heat maps and inspection blind spots.

[0011] The technical effects and advantages of the textile process intelligent monitoring method based on the wristband terminal of the present invention are as follows: The present invention generates an initial inspection path by combining the spatial distance of textile equipment with the task priority, and dynamically adjusts the path using real-time location data and task completion progress during the inspection process, effectively improving the flexibility and adaptability of the inspection task. Based on the data collection and fusion processing of the built-in multi-sensor of the wristband terminal, the positioning results are unified to the same coordinate system, and combined with the confidence weighting and environmental error correction algorithm, the positioning accuracy is significantly improved, providing reliable data support for the dynamic adjustment of the inspection path of textile equipment; In addition, by comparing the current position with the predetermined path in real time, accurately calculating the deviation distance and deviation direction, and triggering a multi-level early warning mechanism, a correction path is dynamically generated to guide workers back to the correct inspection trajectory, reducing the risk of task omissions caused by path deviation. Combined with the path data, equipment coverage records and deviation information generated during the inspection of textile equipment, the present invention generates an equipment coverage matrix and a heat map to intuitively reflect the inspection coverage and blind spot distribution, and prioritizes inspection tasks to high-priority equipment and blind spots, thereby achieving reasonable allocation of inspection resources and improving blind spot coverage. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a flow chart of the intelligent monitoring method of textile process based on the wristband terminal of the present invention. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] In order to achieve the above objectives, Figure 1 A structural schematic diagram of a textile process intelligent monitoring method based on a wristband terminal of the present invention is given, which specifically includes the following steps: During the inspection and monitoring of the textile process, the initial inspection path is generated according to the spatial distance of the equipment and the task priority, and the path is adjusted according to the real-time location data and task completion progress during the inspection process; Obtain and process the data collected by the built-in sensor of the wristband terminal, unify it into the same coordinate system, calculate the global position of the processed data in combination with the confidence and environmental error correction, and generate the positioning result; Compare the real-time position with the planned path, calculate the deviation distance and direction, and trigger multi-level warnings based on the deviation distance and direction, dynamically correct the path, and conduct inspections based on the corrected inspection path; Acquire the path data, equipment coverage records and deviation information generated during the inspection process, generate equipment coverage matrix and heat map, calculate thermal value and blind spot priority, and prioritize inspection tasks to high-priority equipment and blind spots.

[0015] Step 1: Perform intelligent path planning and real-time adjustment for textile inspection. In the intelligent monitoring scenario of textile processes based on wristband terminals, the intelligent path planning and real-time adjustment mechanism aims to dynamically optimize the worker inspection path to ensure that all equipment is inspected efficiently, while reducing path deviations caused by environmental complexity, worker fatigue or unreasonable task allocation. This step includes four sub-steps: equipment and task modeling, path initialization and optimization, real-time path adjustment and dynamic path feedback. The specific steps are as follows: In the textile process, we first need to build a mathematical model of equipment and tasks to describe the spatial distribution of inspection equipment, the correlation between processes and the execution requirements of tasks. Suppose there are n equipment in the textile workshop, and their positions are expressed in two-dimensional coordinates as ,P is the spatial location set of the device, which provides the basis for path planning. is the horizontal coordinate of device n, is the vertical coordinate of device n, for example, Indicates the position of the i-th device; Each device i has an inspection importance factor and estimated inspection time , based on these parameters, the target task set is defined as: ,in, Describe the importance of equipment inspections, such as key equipment will be given a higher value; in addition, each device i has an inspection importance factor, which can be calculated by the following formula: ,in, It is the criticality coefficient of the equipment, indicating its importance to the operation of the production line; is the failure rate of the equipment; It is the cumulative value of the device running time. By comprehensively considering these factors, the importance of the device can be reasonably quantified, providing a basis for subsequent path priority calculation; On this basis, the spatial distance matrix between devices is introduced and the task priority matrix , which is calculated as follows: ; in, Measure the spatial distance between devices and provide location reference for path planning; The importance and distance of devices are integrated to form a weighted matrix representing the task priority. Devices with higher priorities have greater weights in path planning. It is the influence range adjustment parameter used to control the decay rate of the correlation between devices; The spatial distance matrix describes the physical distance between devices, and its value can be adjusted based on environmental barriers (such as whether there is a wall between devices); Based on the task set TJ, the initial inspection path is generated according to the spatial distance of the path and the task priority. ,For example It means inspecting devices 1, 3, 5, and 2 in sequence. The objective function of the defined path is: ,in, Indicates the kth device in the path, m is the number of devices included in the path, and are distance weight and priority weight respectively, Inspection is time-consuming. is the spatial distance between devices, is the priority between devices; J is the comprehensive performance index of the path, including inspection time, distance between devices, and task priority, to ensure the efficiency of the path; The path is optimized through genetic algorithms. By simulating the biological evolution process, genetic algorithms can efficiently search for the approximate optimal path sequence. The main steps include: Convert the device index i into a path sequence, evaluate the fitness of the path according to the objective function J, generate a new path sequence through selection, crossover and mutation operations, and output the optimal path when the path converges or reaches the maximum number of iterations; During the inspection process, the path is dynamically adjusted according to the worker's real-time location and task completion progress. The worker's current location is , real-time path adjustment needs to consider the following two parts: (1) Reorder unfinished tasks and group the remaining devices together Re-sort, the sorting index is: ,in, is the distance between worker position c and equipment i, The importance of equipment inspection, It is a time decay parameter, indicating that the closer the device is to the inspection deadline, the higher its priority; (2) Path correction: regenerate the path based on the sorting results , the optimization function is: ,in, is the number of path devices after adjustment; Path correction allows workers to inspect high-priority equipment first, reducing unnecessary deviations; Perform dynamic path feedback, such as real-time navigation and path correction through the wristband terminal. Suppose the current path deviation is: ,in, is the nearest device position on the path, when (deviation threshold), the wristband terminal will issue navigation prompts and generate a corrected path , its objective function is: ,in, The deviation correction weight is used to emphasize the inspection of high-priority equipment, balance the equipment priority and path distance, and guide workers to return to the inspection track according to the deviation correction path. At the same time, the deviation data is recorded for path optimization. It should be noted that the location and working status of the workers can be determined to a certain extent through the wristband terminal they wear. For example, the determination of the worker's location depends on multiple positioning technologies integrated in the wristband terminal, including GPS positioning, indoor positioning technology (UWB, Wi-Fi, Bluetooth, etc.). The worker's working status (such as whether he is in patrol, whether he has worked overtime, whether he is tired, etc.) can be detected and judged by the following sensors: physiological monitoring sensors (heart rate, skin temperature, acceleration). For example, the heart rate sensor monitors the worker's heart rate and judges the worker's physical load and fatigue status by analyzing the changes in heart rate. If the heart rate exceeds a certain threshold, it may indicate that the worker is performing high-intensity work or is in a fatigued state. The wristband worn by the worker can also be connected to the task management system to dynamically update the working status according to the worker's current task assignment (such as patrol equipment, maintenance tasks, etc.). For example, when the system detects that the worker has stayed in the planned patrol area for too long, it may prompt the worker that the task has been completed overtime.

[0016] Step 2: Perform multi-sensor fusion positioning to solve the problems of signal interference and error accumulation in complex indoor environments, integrate sensor data set in multiple wristband terminals (such as GPS, Wi-Fi, UWB, Bluetooth and inertial sensors), build a high-precision positioning system, and provide reliable location information support for real-time adjustment of inspection routes. The following are the specific processing steps: Perform data collection and preprocessing, collect positioning data from multiple sensors, and perform preliminary denoising and formatting to provide consistent data input for subsequent fusion. Assume that the sensor set is , N is a positive integer, where each sensor Provides an independent position estimate , and is accompanied by a confidence , indicates the reliability of the sensor positioning result. The higher the value, the smaller the positioning error. Data denoising: The raw data of each sensor (Original positioning data) is denoised and Gaussian filtering is used to filter out random interference; Unified coordinate system: the positioning data of all sensors are mapped to a unified coordinate system G to improve the comparability of data; Confidence calculation, based on historical data and real-time signal strength, calculates the confidence of each sensor estimate ,in, represents the real-time measurement variance of the sensor (obtained by calculating the variance of historical data), is the sensor signal strength; Perform sensor data fusion to combine the positioning results of each sensor into a global position estimate , to improve positioning accuracy; Based on the confidence level of the sensor , perform weighted summation of the positioning data of each sensor: ; The fusion result is corrected for errors, considering the impact of the environment. The error correction formula is: , where M is the number of environmental impact factors, is the offset vector of the i-th influencing factor, is the distance between the worker’s current position and the influencing factor, is the influence range control parameter, The weights of the impact factors are dynamically adjusted based on historical data; Corrected positioning results: ,in, The correction value for environmental impact is set to take into account the metal interference or signal shielding in the actual factory environment; During the worker inspection process, the sensor fusion strategy is dynamically adjusted to reallocate sensor weights according to environmental changes and signal quality to ensure the real-time and stability of the positioning system. The specific steps are as follows: Real-time signal strength monitoring, through signal strength changes Dynamically adjust sensor confidence: ,in, is the signal strength attenuation coefficient, It is the change in sensor signal strength, which is used to adjust the confidence level in real time; In certain scenarios (such as signal interference or sensor failure), switch the fusion strategy and select the sensor with the highest confidence as the main data source, that is, single dominance. When the confidence difference is small, average the results of multiple sensors. According to the stability of the fusion positioning results, adjust the fusion weight parameters : ,in, It is a dynamic weight that comprehensively considers confidence and real-time signal stability; For example, the signal strength and quality parameters (such as signal-to-noise ratio and data packet loss rate) of each sensor are continuously monitored. According to the real-time monitoring results, the confidence of the sensor is adjusted. Then, the abnormal state of the sensor is identified according to the anomaly detection algorithm (such as a control chart based on statistical characteristics). When a sensor is detected to be faulty, it is automatically removed from the fusion calculation and the weights of other sensors are adjusted to ensure the continuity of the positioning system. The corrected positioning results are fed back to the wristband terminal for workers to view the position and inspection path in real time. According to the latest positioning information, combined with intelligent path planning and real-time adjustment mechanism, the inspection path is dynamically optimized; Verify the final positioning results, identify potential anomalies, ensure the accuracy and stability of the positioning results, and use the trajectory similarity calculation method based on the historical path to verify whether the current positioning results are consistent with the normal trajectory. The calculation formula of the trajectory similarity XS is: , where T is the number of trajectory points, To control the deviation tolerance range, is the current trajectory point, is the reference trajectory point; Multi-sensor fusion positioning technology achieves high-precision worker positioning through four steps: data collection and preprocessing, fusion positioning, dynamic adjustment and verification feedback, combining the characteristics of different sensor data. It provides basic data support for inspection path adjustment, and ensures the reliability of positioning results through dynamic optimization weights and environmental correction mechanisms, providing stable location information input for intelligent monitoring of textile processes.

[0017] Step 3: Automatically warn and correct path deviations. By monitoring the workers’ positions in real time and comparing them with the planned paths, timely reminders are given when deviations are found, and new inspection guidance paths are generated to ensure comprehensive coverage and efficient execution of inspection tasks. The following are the specific processing steps: Perform deviation detection and obtain the current positioning result position based on the multi-sensor fusion result , represents the horizontal axis, Indicates the ordinate, the closest point to the intended path , represents the horizontal axis, Represents the ordinate, and the two are compared to calculate the deviation distance between the positioning result and the predetermined path And the deviation direction, the deviation distance calculation formula is: ,in, Indicates the minimum distance between the current position and the predetermined path; The deviation direction calculation formula is: ,in, Indicates the angular deviation of the current position relative to the predetermined path; when (Deviation Distance Threshold) or (Deviation direction threshold) is set, the worker is judged to have deviated from the path. The deviation distance threshold and direction deviation threshold can be dynamically set according to the workshop layout and the accuracy requirements of the inspection task; When a deviation from the path is detected, the early warning mechanism is triggered immediately, and the wristband terminal sends vibration, sound or screen prompts to the worker to notify him to return to the correct path; According to the degree of deviation and , set up different levels of early warning mechanisms: Slight deviation : Prompt the worker to make slight adjustments; Significant deviation : Send out continuous vibration prompts and display the correction path simultaneously; Serious deviation : Immediately trigger the background management notification to remind the management personnel to intervene; Warning intensity Variation with the degree of deviation: ,in, and is the weight parameter of deviation distance and direction, which is used to control the sensitivity of the warning signal; Dynamically adjust the prompt mode according to the deviation level and ambient noise level. For example, in high-noise areas, the system prioritizes prompting workers through vibration and screen rather than sound prompts. Record the frequency of workers' deviations over a period of time and cumulative deviation , generating a deviation score: ; The dynamic adjustment of the early warning mechanism ensures rapid response to different deviation levels, preventing small errors from evolving into serious deviations, and The strength of the deviation can indicate the severity of the worker’s deviation and guide him to adjust his behavior.

[0018] When a worker deviates from the path, they need to be quickly guided back to the correct position, that is, a new inspection path is generated through a dynamic deviation correction algorithm. , guide workers to the nearest effective inspection point; The generation of the deviation correction path needs to comprehensively consider the dynamic changes of the textile factory environment. For example, some paths may be temporarily closed due to equipment movement or busy workers. At this time, the deviation correction path should dynamically avoid these areas. In addition, the speed of workers during the inspection process will also affect the path adjustment. The deviation correction path needs to be optimized in combination with the current status of the workers; First, the distance is used to screen the target inspection points to ensure that the inspection points with closer distances are selected first to reduce the walking time of workers on the deviation correction path. The distance weighted objective function expression is: ,in, is the distance between the worker and inspection point i, is the importance factor of the inspection point, is the importance weight; The optimal inspection point selection formula is: , where U is the set of unfinished inspection points, For the new target inspection point, represents the i-th inspection point; Based on the optimal inspection point and current location , combined with path planning algorithms (such as Dijkstra algorithm), generate the shortest path from the current location to the optimal inspection point; Deviation recording and feedback optimization is the learning and improvement link of the system, recording all path deviation events and analyzing them to optimize future path planning and early warning mechanisms; Recorded data items include the current position of the deviation and predetermined waypoints , deviation distance and direction , the time when the deviation occurs and time-consuming to correct ; Use clustering algorithms (such as K-means) to identify high-frequency locations of deviation events : ,in, is the set of deviation points belonging to cluster i; Analyze possible causes (such as unreasonable route design, environmental interference, etc.) based on deviation data and put forward improvement suggestions; Deviation detection is based on the dynamic comparison of real-time location data with the planned path. The early warning mechanism responds in grades according to the degree of deviation. The correction path generation quickly guides workers to return to inspection tasks through dynamic optimization algorithms.

[0019] Step 4: Path optimization and heat map analysis. After the real-time adjustment of path deviation is completed, the path optimization and heat map analysis is to generate a heat map of equipment inspection coverage through comprehensive analysis of inspection data, identify equipment inspection blind spots and high-frequency inspection areas, and combine inspection path records and deviation data to optimize future path planning and task allocation, so as to achieve dynamic optimization and closed-loop improvement of intelligent monitoring of textile processes. The specific steps are as follows: The wristband terminal collects the path data generated during the inspection process (the worker's walking trajectory during the inspection, including spatial position, time information and dynamic status), equipment coverage records (whether the worker covers the equipment in the inspection path, and the inspection frequency of each equipment) and deviation information (the worker's deviation from the predetermined path during the inspection, including position deviation, direction deviation and correction record), and performs task mapping for each path point and inspection equipment to analyze the inspection frequency and coverage of the equipment; Path data set construction, collecting the location data of all path points during the inspection process , n is a positive integer, and the set P includes ,in represents the position and time of path point i ( For location, is time), P is the set of path points that workers actually walk during the inspection process; Device task mapping, which associates path points with device collections , the E set includes , m is a positive integer, and mapping is performed. If the path point Distance satisfy (Device coverage radius), then the device is considered Has been inspected: ,E is the set of equipment in the factory, and the mapping relationship between the waypoints and the equipment determines whether the equipment has been inspected; according to , generate the device coverage matrix C, where, , indicating the device The inspection frequency of the equipment, the equipment coverage matrix provides the inspection coverage of the equipment, which is the basis for generating the heat map; Generate a heat map of equipment inspections in the factory based on the equipment coverage matrix and the location of the path points, showing the inspection density distribution and blind spot locations; According to the frequency of equipment inspection and equipment importance factor , calculate the thermal value: ,in, Yes Equipment The distance to the center of the path, is the thermal diffusion control parameter; The thermal value reflects the attention paid to the equipment in the inspection route, and the higher the value, the more attention the equipment receives; The blind spot identification process is for Device collection , recorded as inspection blind area, the blind area priority calculation formula is: ,in, Indicates the time decay factor of the device not being inspected. is the time weight; Based on the heat map and inspection blind area data, redefine the path optimization target and adjust the inspection task allocation. While covering the blind area, optimize the inspection path length and task completion efficiency. The specific steps are as follows: Considering the path length, inspection importance and blind spot coverage, the path optimization objective function is: ,in, is the length of path segment k, is the thermal value covered by the path segment, is the blind area priority of the path segment coverage, and Control the weight of thermal and blind zone priorities; For blind spot devices , and similarly increase its importance factor: ,in, is the importance enhancement coefficient, Control the increase; Dynamically adjust the equipment importance factor and allocate inspection resources to high-priority areas; Combining the optimization objective function with the dynamically adjusted equipment importance factor, the inspection paths and tasks are reallocated, and the paths are optimized using a genetic algorithm: Convert the equipment set into an inspection path sequence, evaluate the path fitness according to the equipment importance factor, generate new paths through selection, crossover and mutation, and terminate when the path converges or the maximum number of iterations is reached; According to the optimized path, inspection tasks are assigned to workers, blind spot equipment is preferentially assigned to workers with idle tasks, and task allocation is dynamically adjusted according to the worker status (such as walking speed, current workload).

[0020] It should be noted that the threshold information in this embodiment is pre-set by professionals and will not be explained in detail here. Some parameter English letters in the embodiments have the same situation, but different meanings are explained when used, which will not be explained one by one here.

[0021] The present invention generates an initial inspection path by combining the spatial distance of textile equipment with the task priority, and dynamically adjusts the path using real-time location data and task completion progress during the inspection process, effectively improving the flexibility and adaptability of the inspection task. Based on the data collection and fusion processing of the built-in multi-sensor of the wristband terminal, the positioning results are unified to the same coordinate system, and combined with the confidence weighting and environmental error correction algorithm, the positioning accuracy is significantly improved, providing reliable data support for the dynamic adjustment of the inspection path of textile equipment; In addition, by comparing the current position with the predetermined path in real time, accurately calculating the deviation distance and deviation direction, and triggering a multi-level early warning mechanism, a correction path is dynamically generated to guide workers back to the correct inspection trajectory, reducing the risk of task omissions caused by path deviation. Combined with the path data, equipment coverage records and deviation information generated during the inspection of textile equipment, the present invention generates an equipment coverage matrix and a heat map to intuitively reflect the inspection coverage and blind spot distribution, and prioritizes inspection tasks to high-priority equipment and blind spots, thereby achieving reasonable allocation of inspection resources and improving blind spot coverage.

[0022] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0023] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0024] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0025] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0026] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0027] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. The intelligent monitoring method of textile process based on wristband terminal is characterized by: The steps include: During the inspection and monitoring of the textile process, the initial inspection path is generated according to the spatial distance of the equipment and the task priority, and the path is adjusted according to the real-time location data and task completion progress during the inspection process; Obtain and process the data collected by the built-in sensor of the wristband terminal, unify it into the same coordinate system, calculate the global position of the processed data in combination with the confidence and environmental error correction, and generate the positioning result; Compare the real-time position with the planned path, calculate the deviation distance and direction, and trigger multi-level warnings based on the deviation distance and direction, dynamically correct the path, and conduct inspections based on the corrected inspection path; Acquire the path data, equipment coverage records and deviation information generated during the inspection process, generate equipment coverage matrix and heat map, calculate thermal value and blind spot priority, and prioritize inspection tasks to high-priority equipment and blind spots.

2. According to claim 1, the intelligent monitoring method for textile process based on the bracelet terminal is characterized in that: During the inspection and monitoring of the textile process, the initial inspection path is generated according to the spatial distance of the equipment and the task priority, and the path is adjusted according to the real-time location data and task completion progress during the inspection. The specific steps are as follows: Define the target task set, which includes inspection importance factor, inspection time, and spatial location of equipment; Establish the spatial distance matrix and task priority matrix of the equipment and generate the initial inspection path; The inspection time, the spatial distance of the equipment and the task priority are combined into the objective function of the path; The path is optimized through genetic algorithm, the device index is converted into a path sequence, the fitness of the path is evaluated according to the objective function, and a new path sequence is generated through selection, crossover and mutation operations. When the path converges or reaches the maximum number of iterations, the optimal path is output.

3. The intelligent monitoring method for textile process based on the bracelet terminal according to claim 2 is characterized in that: The data collected by the built-in sensor of the wristband terminal is obtained and processed, unified into the same coordinate system, and the global position is calculated based on the processed data combined with confidence and environmental error correction to generate the positioning result. The specific steps include: Obtain the data collected by the sensors set in the wristband terminal, and use Gaussian filtering to denoise the original positioning data collected by each sensor; Map the sensor's positioning data to a unified coordinate system; Calculate the confidence of each sensor estimate based on historical data and real-time signal strength; Perform sensor data fusion to combine the positioning results of each sensor into a global position estimate; The fusion result is corrected for errors caused by the environmental impact to obtain the corrected positioning result.

4. The intelligent monitoring method for textile process based on the bracelet terminal according to claim 3 is characterized in that: Compare the real-time position with the planned path, calculate the deviation distance and deviation direction, and trigger multi-level warnings based on the deviation distance and deviation direction. The specific steps are as follows: Perform deviation detection and obtain the current positioning result position at time t based on the multi-sensor fusion result , represents the horizontal axis, Represents the ordinate, the closest point to the predetermined path at time t , represents the horizontal axis, Represents the ordinate, and the two are compared to calculate the deviation distance between the current positioning result position at time t and the predetermined path And the deviation direction, the deviation distance calculation formula is: ,in, Indicates the minimum distance between the current position and the predetermined path; The deviation direction calculation formula is: ,in, Indicates the angular deviation of the current position relative to the predetermined path; when or When , it is determined that the worker has deviated from the path, where is the deviation distance threshold, is the deviation direction threshold; When a deviation from the path is detected, the early warning mechanism is triggered immediately, and the wristband terminal sends vibration, sound or screen prompts to the worker to notify him to return to the correct path; According to the degree of deviation and , set up different levels of early warning mechanisms: When the deviation is slight, the worker is prompted to make slight adjustments; If the deviation is significant, the bracelet will vibrate continuously and display the correction path simultaneously. If it is a serious deviation, it will immediately trigger the background management notification to remind the management personnel to intervene.

5. The intelligent monitoring method for textile process based on the wristband terminal according to claim 4 is characterized in that: Performing dynamic deviation correction on the path and performing inspection according to the inspection path after deviation correction includes the following steps: After a worker deviates from the path, dynamic correction is performed and the optimal inspection point is selected using a distance-weighted objective function; Based on the optimal inspection point and the current position, the Dijkstra algorithm is combined for path planning to generate the shortest path from the current position to the optimal inspection point.

6. The intelligent monitoring method for textile process based on the wristband terminal according to claim 5 is characterized in that: Obtain the path data, equipment coverage records and deviation information generated during the inspection process, generate equipment coverage matrix and heat map, calculate thermal value and blind spot priority, and prioritize inspection tasks to high-priority equipment and blind spots, including the following steps: The wristband terminal collects the path data, equipment coverage records, and deviation information generated during the inspection process, and performs task mapping for each path point and inspection equipment; Device task mapping: determine whether a device has been inspected based on the mapping relationship between path points and devices, and generate a device coverage matrix; Generate a heat map of equipment inspections in the factory based on the equipment coverage matrix and the location of the path points, showing the inspection density distribution and blind spot locations; Calculate the thermal value based on the equipment inspection frequency and equipment importance factor; The blind spot identification process is to record the equipment set with a patrol frequency of 0 as the patrol blind spot; Redefine path optimization goals and adjust inspection task allocation based on heat maps and inspection blind spots.

Images