An electric pole intelligent production execution management system based on an internet of things

Abstract

This invention relates to the field of pole production and manufacturing execution management, and discloses an intelligent pole production execution management system based on the Internet of Things (IoT). The system includes a data acquisition unit, an edge processing unit, a cloud management platform, an intelligent analysis unit, and a human-machine interaction unit. The system collects data on raw material ratios, mold status, curing temperature, humidity, and other detection data through sensors. The edge processing unit identifies anomalies in real time and performs rapid adjustments. The cloud management platform generates a digital twin of the pole and combines it with an algorithm model to adaptively adjust curing temperature, minimize energy consumption, predict lifespan, predict production capacity, and assess mold lifespan. The human-machine interaction unit presents process information to operators through an augmented reality terminal and supports two-way feedback. This system enables real-time monitoring and closed-loop optimization of the entire pole production process, reducing energy consumption, improving consistency, extending service life, and significantly enhancing the intelligence and reliability of the production process.

Description

Technical Field

[0001] This invention relates to the field of pole production and manufacturing execution management, and specifically to an Internet of Things-based intelligent production execution management system for poles. Background Technology

[0002] As a key foundational component in power transmission and distribution networks, utility poles are widely used in urban and rural power grid construction, transmission line construction, and communication facility support. The manufacturing process of utility poles typically includes steel reinforcement frame fabrication, concrete pouring, mold vibration molding, steam curing, and quality inspection. With the continuous expansion of power construction, the production scale and quality requirements for utility poles are increasingly demanding. Achieving high-efficiency, low-energy-consumption, and high-quality coordinated production has become a core requirement for the industry's development.

[0003] Currently, pole production management largely relies on traditional Manufacturing Execution Systems (MES) and manual scheduling. Data collection is mainly concentrated in the post-production inspection phase, lacking real-time online monitoring capabilities, leading to information lag. Key process parameters during production, such as curing temperature, humidity, and mold vibration frequency, are often set manually based on experience, making adaptive adjustment difficult and prone to excessive energy consumption or insufficient strength. Furthermore, existing systems generally lack a full-process quality traceability mechanism, failing to pinpoint the cause of defects in a timely manner, resulting in batch rework and resource waste, and insufficient production flexibility and intelligence.

[0004] Therefore, an IoT-based intelligent production execution management system for utility poles is proposed. By deploying sensors to collect key data in the production process and combining digital twins and algorithm optimization models, the system enables visualized management and dynamic control of the entire lifecycle of utility poles, from raw material input to finished product delivery. This system can improve production efficiency and energy utilization, as well as achieve quality traceability and lifespan prediction, thus providing a higher level of intelligent solutions for the utility pole manufacturing industry. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an Internet of Things-based intelligent production execution management system for utility poles, thereby resolving the technical problems existing in the prior art.

[0006] The above-mentioned technical objective of the present invention is achieved through the following technical solution: An IoT-based intelligent production execution management system for utility poles includes: The data acquisition unit is used to acquire data on raw material ratio, mold status, curing temperature, humidity, vibration frequency, and testing during the pole production process. An edge processing unit, connected to the data acquisition unit, is used to preprocess real-time data and perform rapid adjustments within the process. A cloud-based management platform is used to store digital twins of utility poles and to manage the twins throughout their entire lifecycle. The intelligent analysis unit is connected to the cloud management platform and is used to optimize production, predict quality, and trace defects based on the collected data. The human-computer interaction unit, connected to the intelligent analysis unit, is used to present pole twin information through an augmented reality terminal or mobile terminal and support operator feedback.

[0007] Preferably, the intelligent analysis unit is used to optimize the curing process based on a reinforcement learning algorithm, and the formula for adjusting the curing temperature is: ; In the formula, The optimized curing temperature is expressed in °C. The initial set temperature is expressed in °C; α is the temperature adjustment factor, ranging from 0 to 1. The target intensity growth rate is expressed in MPa / h. The intensity growth rate is measured in real time, and the unit is MPa / h.

[0008] Preferably, the intelligent analysis unit determines the vibration duration of the mold through a vibration energy consumption optimization model, and the optimization formula is: ; In the formula, The objective is to minimize total energy consumption, expressed in kWh. The vibration power in the i-th stage is expressed in kW. The duration of vibration in stage i is in seconds; n is the number of vibration stages.

[0009] Preferably, the cloud management platform is used to predict the lifespan of the pole twin, and the prediction formula is: ; In the formula, L is the predicted life of the pole; f(T) is the temperature curve function, reflecting the influence of curing temperature on strength; g(H) is the humidity function, reflecting the influence of curing humidity on porosity. Stress level; These are the empirical regression coefficients.

[0010] Preferably, the edge processing unit uses a defect prediction formula to determine the real-time data: ; In the formula, D is the defect deviation coefficient; To collect data in real time; This is the historical average. Standard deviation; When D> It was determined that there was an abnormality in the process. This is a preset threshold.

[0011] Preferably, the intelligent analysis unit uses a multi-objective optimization function to comprehensively evaluate production efficiency and energy consumption, specifically: ; In the formula, F is the comprehensive optimization function; Q is the actual output; E represents the maximum theoretical output; E represents the actual energy consumption. Based on maximum energy consumption; For the weighting coefficients, satisfying .

[0012] Preferably, the cloud management platform uses the following formula to adaptively adjust the production cycle time: ; In the formula, The adjusted production cycle time; γ is the initial production cycle time; γ is the energy consumption adjustment coefficient. Real-time energy consumption; For reference energy consumption; The intelligent analysis unit calculates the predicted yield rate of the production process based on the following formula: ; In the formula, P is the predicted pass rate; The number of qualified poles is predicted based on real-time parameters; This represents the total number of poles produced.

[0013] Preferably, the cloud management platform uses a time series forecasting model to predict future production capacity, using the following formula: ; In the formula, To predict output; This represents the current output. These are the autoregressive coefficients; The moving average coefficient; For random disturbance terms; The edge processing unit uses the following formula to evaluate the mold's service life: ; In the formula, For the remaining service life, This represents the maximum number of times the mold can be used. R represents the current number of uses; R represents the wear rate.

[0014] Preferably, the intelligent analysis unit uses a real-time feedback iterative formula to perform closed-loop updates of the process parameters: ; In the formula, These are the process parameters at the t-th iteration; The target performance index; For performance metrics collected in real time; The learning rate has a value between 0 and 1. The cloud management platform determines the service performance of utility poles based on a reliability evaluation model, which is as follows: ; In the formula, R(t) represents the reliability of the pole at time t; This is an inefficiency rate.

[0015] Preferably, the intelligent analysis unit employs a multi-objective trade-off function to comprehensively optimize output, lifespan, and energy consumption: ; In the formula, G is the comprehensive optimization value; Q is the actual output; L represents the theoretical maximum output; L is the predicted lifetime value. E represents the reference lifespan; E represents the actual energy consumption. For reference energy consumption; For the weighting coefficients, satisfying .

[0016] In summary, the present invention has the following main beneficial effects: This invention achieves comprehensive real-time data acquisition from raw material proportions and mold status to the curing environment by deploying temperature sensors, humidity sensors, stress sensors, and RFID tags during the pole production process. An edge processing unit analyzes the collected data in real time, and can quickly trigger adjustments when there is insufficient vibration, temperature deviation, or abnormal humidity, preventing the problem from escalating. Unlike traditional methods that rely on manual experience for settings, this invention achieves intelligent sensing and dynamic control of the production process, giving pole production self-adaptive capabilities. This not only improves process stability and consistency but also reduces energy waste and quality fluctuations caused by human error, thereby enhancing overall production efficiency.

[0017] This invention introduces digital twins and algorithm models into a cloud management platform, applying reinforcement learning, energy consumption optimization, and lifespan prediction formulas to actual production. By dynamically adjusting maintenance temperature and production cycle, a balance is achieved between the intensity growth rate and energy utilization rate. Through a multi-objective optimization function, the system achieves global scheduling between maximizing output and minimizing energy consumption. Simultaneously, the lifespan prediction model, based on temperature curves, humidity curves, and stress levels, can predict the service life of poles during the production stage and correct processes in advance. Thus, this invention not only effectively reduces production energy consumption but also transforms quality control from post-production inspection to pre-production prediction, improving product reliability and traceability.

[0018] This invention constructs a closed-loop optimization mechanism from detection to tracing, feedback, and final correction. When the pole inspection result is unqualified, the system automatically traces the source to the specific process and adjusts the process parameters in the next batch to avoid the recurrence of the same defect. At the same time, the human-machine interaction unit provides operators with pole twin information and a process visualization interface through augmented reality terminals or mobile devices. Workers can provide real-time feedback on anomalies and directly affect the system optimization process, realizing human-machine collaboration. The combination of the closed-loop feedback mechanism and human-machine interaction design in this invention enables the system to have continuous learning and self-evolution capabilities, which not only improves the level of production flexibility but also ensures high quality and low risk in large-scale production environments. Attached Figure Description

[0019] Figure 1 This is a system module diagram of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Example 1

[0021] refer to Figure 1 A smart production execution management system for utility poles based on the Internet of Things, comprising: The data acquisition unit is used to acquire data on raw material ratio, mold status, curing temperature, humidity, vibration frequency, and testing during the pole production process. An edge processing unit, connected to the data acquisition unit, is used to preprocess real-time data and perform rapid adjustments within the process. A cloud-based management platform is used to store digital twins of utility poles and to manage the twins throughout their entire lifecycle. The intelligent analysis unit is connected to the cloud management platform and is used to optimize production, predict quality, and trace defects based on the collected data. The human-computer interaction unit, connected to the intelligent analysis unit, is used to present pole twin information through an augmented reality terminal or mobile terminal and support operator feedback. Example 2

[0022] On the production site, data acquisition units are deployed at mixers, molds, curing kilns and testing stations to collect key data such as raw material ratio, curing temperature, humidity, mold vibration frequency, and stress level. The error in raw material preparation is controlled within ±0.5%; The curing temperature is 20-120℃; Humidity: 50-95% RH; The mold vibration frequency is 10-100Hz; Stress levels range from 0 to 60 MPa; If the temperature is below 20℃, the edge processing unit automatically starts the heating device; if the temperature is above 120℃, the cooling valve is triggered to prevent the concrete from losing water. The edge processing unit performs real-time anomaly detection on the acquired data using a deviation coefficient formula: ; In the formula, D is the defect deviation coefficient; To collect data in real time; This is the historical average. The standard deviation is ; when 1 ≤ D ≤ 3, the data is marked as suspicious and redundant testing is required; When D < 1, it is considered normal. Its working principle is to use statistical methods to detect deviations and combine anomaly removal with redundancy detection to ensure the accuracy and reliability of the system's analysis of input data. The cloud management platform generates a digital twin for each utility pole and records data throughout its entire lifecycle. The human-machine interaction unit presents the twin's parameters to the operator through an augmented reality terminal. The worker uploads abnormal information, and the system updates the twin in real time and provides feedback on corrective measures, thus achieving human-machine collaboration. Example 3

[0023] During the maintenance phase, the system collects data on the pole strength growth rate in real time. and with the target value Compare, The range is 0.6-1.2 MPa / h, when < At that time, the system executes the temperature correction formula: ; In the formula, The optimized curing temperature is expressed in °C. The initial temperature is set to 60℃; α is the temperature adjustment factor, with a value range of 0-1. If α < 0.1, the temperature correction is too slow and the strength may be insufficient. If α > 0.5, the correction is too fast and may cause cracks. The preferred range is 0.2-0.3. The target intensity growth rate is expressed in MPa / h. The intensity growth rate is measured in real time. Its working principle is to achieve adaptive curing by utilizing the linear response relationship between strength growth rate and temperature, so that the concrete hydration reaction rate is sufficient to increase strength while avoiding cracks caused by high temperature dehydration. The system also calls the lifetime prediction formula: ; In the formula, L is the predicted lifespan of the pole, with a reasonable range of 30-50 years; f(T) is the temperature curve function, reflecting the influence of curing temperature on strength; g(H) is the humidity function, reflecting the influence of curing humidity on porosity. Stress level; These are the empirical regression coefficients; If L < 30 years, the system will automatically extend the maintenance period or increase the vibration frequency; if L > 50 years, it indicates process redundancy and can reduce energy consumption. By combining life prediction with temperature control, the production process can be optimized in advance for service performance. Example 4

[0024] In the mold vibration process, the intelligent analysis unit achieves energy saving through an energy consumption optimization model: ; In the formula, The objective is to minimize total energy consumption, expressed in kWh. The vibration power in the i-th stage is expressed in kW. The duration of the i-th vibration stage is 10-60 seconds; n is the number of vibration stages. If the total energy consumption is greater than 10 kWh, the high-power duration should be shortened; if the total energy consumption is less than 5 kWh, the low-power duration should be extended to ensure compactness. Production cycle time is adjusted using a formula: ; In the formula, The adjusted production cycle time is 10 minutes per piece; The initial production cycle time is γ; γ is the energy consumption adjustment coefficient, ranging from 0.05 to 0.2. Real-time energy consumption; For reference energy consumption; like > Extending the cycle time reduces energy consumption; if <0.8 Shorten the cycle time to increase production; Meanwhile, the system adopts a comprehensive efficiency-energy consumption evaluation function: ; In the formula, F is the comprehensive optimization function; Q is the actual output; E represents the maximum theoretical output; E represents the actual energy consumption. Based on maximum energy consumption; Let be the weighting coefficient, satisfying ; Its working principle is to normalize the evaluation of efficiency and energy consumption, and dynamically select the optimization direction when there is a contradiction between efficiency and energy consumption through weight balancing. If F < 0.4, the system is considered to have low efficiency and high energy consumption, and the system will prioritize reducing energy consumption. If F > 0.8, it indicates high efficiency and reasonable energy consumption, and the current process should be maintained. The working principle is to normalize the evaluation of output and energy consumption, so that data of different dimensions can be compared, and then use weights to balance efficiency and energy consumption targets, and dynamically select strategies to increase production or save energy. Example 5

[0025] The system uses an iterative learning formula: ; In the formula, These are the process parameters at the t-th iteration; The target performance index; For performance metrics collected in real time; The learning rate has a value between 0 and 1. like If <0.01, the convergence speed is slow; if If the value is greater than 0.2, the oscillation is severe; like < If so, the maintenance time will be increased. > If so, then lower the temperature; The system also calculates the pass rate prediction: ; In the formula, P is the predicted pass rate; The number of qualified poles is predicted based on real-time parameters; This represents the total number of poles produced. If P < 90%, immediately issue an alarm and correct the process; if P > 98%, it indicates process redundancy, and energy consumption can be reduced. In addition, the cloud management platform uses time series models to predict future production capacity: ; In the formula, To predict output; This represents the current output. These are the autoregressive coefficients; The moving average coefficient; For random disturbance terms; If the predicted output is more than 10% lower than the planned output, replenish raw materials in advance; if the predicted output is more than 20% higher than the demand, reduce the production speed to avoid inventory backlog. The system continuously approaches the target through iterative formulas, the pass rate prediction ensures quality and early warning, and the capacity prediction avoids shutdowns or overproduction. Example 6

[0026] The edge processing unit evaluates the mold life: ; In the formula, For the remaining service life, This represents the maximum number of times the mold can be used. R represents the current number of uses; R is the wear and tear rate, typically 1-5%. like <100, issue an immediate warning and replace; if If the value is greater than 500, it is still within the safe zone; The intelligent analysis unit further employs a comprehensive optimization function: ; In the formula, G is the comprehensive optimization value; Q is the actual output; L represents the theoretical maximum output; L is the predicted lifetime value. E represents the reference lifespan; E represents the actual energy consumption. For reference energy consumption; Let be the weighting coefficient, satisfying ; If G < 0.5, then prioritize extending maintenance to ensure lifespan; if G > 0.8, then prioritize increasing production. Finally, the cloud platform uses a reliability function: ; In the formula, R(t) represents the reliability of the pole at time t; The failure rate is typically 0.001-0.005 per year. If R(30) < 0.7, it is determined that the reliability is insufficient and the maintenance period should be extended; if R(30) > 0.9, it indicates that the quality is redundant and energy consumption can be reduced.

[0027] In summary, this invention, based on sensor data, utilizes edge processing for anomaly detection and rapid adjustment. It constructs a digital twin on a cloud platform and optimizes it using various algorithmic formulas. During maintenance, the system employs a temperature correction formula to ensure strength growth rate; in lifespan prediction, it combines temperature, humidity, and stress for pre-performance control; and in vibration, it achieves efficiency and energy consumption balance through energy consumption optimization and cycle time adjustment, further evaluating performance using a comprehensive efficiency and energy consumption function. Furthermore, the system continuously corrects the process using a feedback iterative formula, combining yield rate prediction and capacity prediction to provide early warnings of quality and production scheduling risks. Simultaneously, it ensures long-term service safety of equipment and products through mold life assessment and reliability functions. Through the linkage and feedback mechanism of these multi-level algorithms, this invention achieves real-time monitoring, adaptive control, and closed-loop optimization throughout the entire pole production process, significantly improving production efficiency, reducing energy consumption, and enhancing product consistency and reliability.

[0028] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart production execution management system for utility poles based on the Internet of Things, characterized in that, include: The data acquisition unit is used to acquire data on raw material ratio, mold status, curing temperature, humidity, vibration frequency, and testing during the pole production process. An edge processing unit, connected to the data acquisition unit, is used to preprocess real-time data and perform rapid adjustments within the process. A cloud-based management platform is used to store digital twins of utility poles and to manage the twins throughout their entire lifecycle. The intelligent analysis unit is connected to the cloud management platform and is used to optimize production, predict quality, and trace defects based on the collected data. The human-computer interaction unit, connected to the intelligent analysis unit, is used to present pole twin information through an augmented reality terminal or mobile terminal and support operator feedback.

2. The IoT-based intelligent production execution management system for utility poles according to claim 1, characterized in that, The intelligent analysis unit is used to optimize the curing process based on reinforcement learning algorithms. The formula for adjusting the curing temperature is: ; In the formula, The optimized curing temperature is expressed in °C. The initial set temperature is expressed in °C; α is the temperature adjustment factor, ranging from 0 to 1. The target intensity growth rate is expressed in MPa / h. The intensity growth rate is measured in real time, and the unit is MPa / h.

3. The IoT-based intelligent production execution management system for utility poles according to claim 2, characterized in that, The intelligent analysis unit determines the vibration duration of the mold using a vibration energy consumption optimization model. The optimization formula is as follows: ; In the formula, The objective is to minimize total energy consumption, expressed in kWh. The vibration power in the i-th stage is expressed in kW. The duration of vibration in stage i is in seconds; n is the number of vibration stages.

4. The IoT-based intelligent production execution management system for utility poles according to claim 3, characterized in that, The cloud management platform is used to predict the lifespan of pole twins, and the prediction formula is as follows: ; In the formula, L is the predicted life of the pole; f(T) is the temperature curve function, reflecting the influence of curing temperature on strength; g(H) is the humidity function, reflecting the influence of curing humidity on porosity. Stress level; These are the empirical regression coefficients.

5. The IoT-based intelligent production execution management system for utility poles according to claim 4, characterized in that, The edge processing unit uses a defect prediction formula to determine the real-time data: ; In the formula, D is the defect deviation coefficient; To collect data in real time; This is the historical average. Standard deviation; When D> It was determined that there was an abnormality in the process. This is a preset threshold.

6. The IoT-based intelligent production execution management system for utility poles according to claim 5, characterized in that, The intelligent analysis unit uses a multi-objective optimization function to comprehensively evaluate production efficiency and energy consumption, specifically: ; In the formula, F is the comprehensive optimization function; Q is the actual output; E represents the maximum theoretical output; E represents the actual energy consumption. Based on maximum energy consumption; Let be the weighting coefficient, satisfying .

7. The IoT-based intelligent production execution management system for utility poles according to claim 6, characterized in that, The cloud management platform uses the following formula to adaptively adjust the production cycle time: ; In the formula, The adjusted production cycle time; γ is the initial production cycle time; γ is the energy consumption adjustment coefficient. Real-time energy consumption; For reference energy consumption; The intelligent analysis unit calculates the predicted yield rate of the production process based on the following formula: ; In the formula, P is the predicted pass rate; The number of qualified poles is predicted based on real-time parameters; This represents the total number of poles produced.

8. The IoT-based intelligent production execution management system for utility poles according to claim 7, characterized in that, The cloud management platform uses a time series forecasting model to predict future production capacity. The formula is as follows: ; In the formula, To predict output; This represents the current output. These are the autoregressive coefficients; The moving average coefficient; For random disturbance terms; The edge processing unit uses the following formula to evaluate the mold's service life: ; In the formula, For the remaining service life, This represents the maximum number of times the mold can be used. R represents the current number of uses; R represents the wear rate.

9. The IoT-based intelligent production execution management system for utility poles according to claim 8, characterized in that, The intelligent analysis unit uses a real-time feedback iterative formula to update the process parameters in a closed loop. ; In the formula, These are the process parameters at the t-th iteration; The target performance index; For performance metrics collected in real time; The learning rate has a value between 0 and 1. The cloud management platform determines the service performance of utility poles based on a reliability evaluation model, which is as follows: ; In the formula, R(t) represents the reliability of the pole at time t; This is an inefficiency rate.

10. The IoT-based intelligent production execution management system for utility poles according to claim 9, characterized in that, The intelligent analysis unit employs a multi-objective trade-off function to comprehensively optimize output, lifespan, and energy consumption. ; In the formula, G is the comprehensive optimization value; Q is the actual output; L represents the theoretical maximum output; L is the predicted lifetime value. E represents the reference lifespan; E represents the actual energy consumption. For reference energy consumption; Let be the weighting coefficient, satisfying .

Images