Control system and control method for adjusting bundle weight of deformed steel bars

Abstract

The invention discloses a control system for adjusting the bundle weight of deformed steel bars. The control system comprises an electric strong magnetic alignment device, a weighing scale, a PLC control unit and a hydraulic shear control unit. The electric strong magnetic alignment device is installed at the position where the steel billet impacts the baffle and used for accurately adjusting the magnetic strength and direction according to a PLC instruction. The weighing scale is installed at the billet collecting and bundling position and used for measuring the weight of a billet bundle in real time and transmitting weight data to the PLC control unit. The PLC control unit is used for receiving weight data weighed by the weighing scale in real time and inputting the weight data into the trained prediction model to obtain the adjusted initial position, moving speed, shearing time, target bundle weight value before next shearing, shearing length and shearing times of the determined scissors. A corresponding instruction is generated and transmitted to the hydraulic shear control unit; and the hydraulic shear control unit is used for receiving and executing an instruction sent by the PLC control unit. By means of automatic control and intelligent decision making, manual intervention and waiting time are reduced, and production efficiency and yield are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of steel processing, and in particular relates to a control system and a control method for adjusting the weight of a bundle of threaded steel bars. Background Art

[0002] Rebar, also known as hot-rolled ribbed steel bars, are widely used in the construction of civil engineering projects such as houses, bridges and roads. They are an important component of construction steel. The nominal diameters of rebars are 6, 8, 10, 12, 16, 20, 25, 32, 40 and 50 mm, and are usually cut in two lengths of 9m and 12m. The production and inspection of rebars must comply with national standards, such as GB1499.2-2007. The actual weight of rebars produced at the factory needs to be controlled within a numerical range based on theoretical weight. The actual weight range is specified in the national standard "Steel for Reinforced Concrete Part 2: Hot-rolled Ribbed Steel Bars" (GB / T1499.2). The weight deviation of national standard rebars should not exceed 3.0% of the total weight, and the deviation of a single bar should not exceed ±8% of the theoretical weight.

[0003] In the traditional steel billet processing, after being heated in a heating furnace, the billet needs to go through rough, medium and fine rolling processes, and then hit the baffle for alignment. However, this method often has low alignment accuracy and serious rebound phenomenon, which affects the quality of subsequent finished products and production costs. At the same time, the traditional hydraulic scissors are not precise enough in the process of cutting and collecting steel and bundling, which also increases the cost. In addition, the general fine-tuning of the positive and negative tolerances of the diameter is basically judged by the operator's experience, which is difficult to adjust and the accuracy is not high enough. Summary of the invention

[0004] The purpose of the present invention is to address the problems existing in the prior art and provide a control system and a control method for adjusting the weight of a bundle of threaded steel bars, integrating multiple links such as electric strong magnetic alignment, weighing, PLC control and hydraulic shearing into one system to achieve automated control of billet alignment and shearing.

[0005] On the one hand, the present invention provides a control system for adjusting the weight of a rebar bundle, comprising: a strong magnetic alignment unit, a weighing unit, a bundling unit and a hydraulic scissor control unit sequentially arranged on a billet bundling production line, and also comprising a PLC control unit arranged outside the billet bundling production line; The strong magnetic alignment unit is used to adjust the magnetic field strength and action time of the strong magnetic alignment unit according to the instructions of the PLC control unit, and control the alignment unit to align the steel billet bundle; The weighing unit is used to measure the weight of the steel billet bundle in real time and transmit the weight data to the PLC control unit; The PLC control unit is used to receive the weight data measured by the weighing unit in real time, and input the weight data into the trained prediction model to obtain the predicted cutting parameters, which include the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length and the number of cutting times; The hydraulic scissor control unit is used to shear the billet bundle according to the predicted shearing parameters; The bundling unit is used for bundling the sheared steel billets.

[0006] Through the above technical solution, automated control and intelligent decision-making are used to reduce manual intervention and waiting time, improve production efficiency and output; accurately control the initial position of the scissors, movement speed, cutting time, target bundle weight value before the next cut, cutting length and number of cuts to ensure that the weight and quality of the steel billet after shearing meet the standards and improve the product qualification rate; in addition, reduce the cost increase caused by errors and waste in the production process, while reducing the degree of dependence on manual labor, further reducing production costs.

[0007] By precisely controlling the initial position of the scissors, the moving speed, the cutting time, and the target bundle weight value before the next cutting, the stability and accuracy of the cutting process can be ensured, and the cutting error and waste can be reduced. At the same time, cutting according to the target bundle weight value helps to achieve standardized production of products and improve product quality and consistency. In addition, by reasonably controlling the cutting length and the number of cuttings, it can be ensured that the weight of the billet bundle meets the preset standard, reducing quality problems caused by insufficient or excessive weight. At the same time, optimizing the number of cuttings can also help improve production efficiency and reduce costs.

[0008] Furthermore, the strong magnetic alignment unit includes a baffle disposed at the end of the billet bundling production line, a transmission mechanism disposed on the baffle facing the billet bundling production line, an electromagnet disposed on the other side of the baffle, and a strong magnetic controller connected to the electromagnet. The electromagnet generates a magnetic field, combined with the drive of the transmission mechanism, to achieve precise alignment of the billets. The strong magnetic controller can adjust the magnetic field strength and action time according to the PLC instructions, further optimize the alignment effect, and improve the automation and response speed of the system.

[0009] Furthermore, the strong magnetic controller is used to adjust the magnetic field strength and action time of the electromagnet according to the instructions of the PLC control unit; thereby ensuring the stable alignment of the steel billet, preventing rebound, and improving the accuracy and efficiency of the alignment.

[0010] Further, the training of the prediction model includes: Construct a sample training set, including the standard weight value of each bundle of steel, the time value of each cutting, the alignment accuracy value, the length of a single steel bar, the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length, and the number of cutting times; Construct a recurrent neural network model. The deep neural network model includes an input layer, an output layer, and several hidden layers. Each layer contains multiple neurons. The weights, biases, and activation functions stored in these neurons jointly construct and define the mapping relationship from the feature variables of the input layer to the output results; its mathematical description is: , in the above formula, y j (k) represents the output of the jth neuron in layer k, m k-1 is the number of neurons in the previous layer, is the weight of the previous layer connected to the i-th neuron in this layer, b k-1 is the bias of the previous layer; The neural network model is trained using the constructed sample training set, and the trained prediction model is output.

[0011] By collecting actual production data to build a sample training set and using a recurrent neural network model for training, we can learn the inherent laws and trends in the production process. This data-driven approach improves the accuracy and reliability of the prediction model and provides strong support for subsequent shearing strategies and bale weight control.

[0012] Further, the PLC control unit comprises: Data acquisition module, used to receive weight data in real time; The logic judgment module is used to determine the initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors according to the trained prediction model and the real-time received weight data. It is also used to predict the subsequent production trend. When it is predicted that the production status deviates from the preset target, the initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors are automatically adjusted. The command output module is used to send control commands to the hydraulic scissors control unit and the strong magnetic controller.

[0013] The data acquisition module receives weight data in real time to ensure the timeliness and accuracy of the data; the logic judgment module determines the optimal initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors based on the prediction model and real-time data, which improves the intelligent level of decision-making; the command output module sends the control command to the relevant execution unit to realize the closed-loop control of the system. This compact and fully functional PLC control unit improves the overall performance and reliability of the system.

[0014] Furthermore, the logic judgment module is also used to continuously optimize the control strategy based on historical production data and real-time feedback, and provide real-time production status and data diagnosis reports to production management personnel.

[0015] By continuously learning and optimizing control strategies, the adaptive learning module can further improve the intelligence and adaptability of the system. At the same time, it provides real-time production status and data diagnosis reports to production managers, which helps to timely discover and solve problems in the production process and improve the efficiency and level of production management.

[0016] Furthermore, it also includes a remote monitoring and fault diagnosis unit, which is used to monitor the video and production data of the production site in real time, and detect anomalies in the production data. If an anomaly is detected, the fault type is identified, the cause of the fault is analyzed, and suggestions for troubleshooting are given. Through the remote monitoring and fault diagnosis functions, safety hazards and fault problems at the production site are discovered and handled in a timely manner to ensure production safety. Once abnormal data or signs of a fault are detected, the remote monitoring and fault diagnosis unit can immediately start the fault diagnosis process, identify the fault type, analyze the cause of the fault, and give suggestions for handling. This rapid fault response and diagnosis mechanism helps reduce maintenance costs and time, and improve the reliability and availability of equipment.

[0017] Furthermore, the remote monitoring and fault diagnosis unit is also used to transmit the real-time video and production data of the production site to the remote monitoring center via network transmission. The real-time video and production data of the production site are transmitted to the remote monitoring center via network transmission, thereby realizing remote monitoring and management. This remote monitoring method helps production managers to grasp the production status in real time, make decisions and adjustments in time, and improve the efficiency and level of production management.

[0018] In another aspect, the present invention provides a control method for a control system for adjusting the weight of a bundle of threaded steel bars, comprising the following steps: The current weight data of the steel billet bundle is collected in real time through the weighing scale, and the current weight data is directly transmitted to the data acquisition module of the PLC control unit; The logic judgment module calculates the optimal initial position of the scissors, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times based on the trained prediction model and weight data; According to the output results of the logic judgment module, specific control instructions are generated, including precise movement instructions and cutting operation instructions of the scissors, and the generated control instructions are sent to the hydraulic scissors control unit in real time; During the production process, the production status is continuously monitored, including but not limited to the conveying speed, alignment accuracy, and cutting efficiency of the steel billets. When the production status is detected to deviate from the preset target, the logic judgment module automatically triggers the internal parameter adjustment mechanism. According to the output results of the prediction model and real-time data feedback, the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length, and the number of cutting times are fine-tuned; The receiving remote monitoring and fault diagnosis unit collects real-time video and production data from the production site and transmits them to the remote monitoring center. The remote monitoring center uses video monitoring and data analysis software to display and analyze production data in real time. Once abnormal data or signs of fault are found, the fault diagnosis process is immediately started; The fault diagnosis process includes fault type identification, fault cause analysis and fault handling suggestion generation.

[0019] Compared with the prior art, the beneficial effects of the present invention are: 1. Improve production efficiency: through automated control and intelligent decision-making, reduce manual intervention and waiting time, improve production efficiency and output; 2. Improve product quality: accurately control the initial position of the scissors, moving speed, shearing time, target bundle weight value before the next shearing, shearing length and shearing times, ensure that the weight and quality of the steel billet after shearing meet the standards, and improve the product qualification rate; 3. Reduce production costs: reduce the cost increase caused by errors and waste in the production process, and at the same time reduce the degree of dependence on manual labor, further reducing production costs; 4. Enhance production safety: through remote monitoring and fault diagnosis functions, timely discover and deal with safety hazards and fault problems on the production site to ensure production safety; 5. Improve management efficiency: realize real-time collection and analysis of production data, provide production management personnel with real-time production status and data diagnosis reports, and improve management efficiency and decision-making accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of the structure of a control system for adjusting the weight of a bundle of threaded steel bars according to an embodiment of the present invention; Figure 2 The present invention is a flow chart of a control method for adjusting the bundle weight of threaded steel bars according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings 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.

[0022] In the description of the present invention, it should be noted that the directions or positional relationships indicated by terms such as "middle", "upper", "lower", "left", "right", "inside" and "outside" are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0023] like Figure 1 As shown, the specific scheme of the embodiment is as follows: A control system for adjusting the weight of a rebar bundle, comprising: a strong magnetic alignment unit, a weighing unit, a bundling unit and a hydraulic scissor control unit which are sequentially arranged on a billet bundling production line, and also comprising a PLC control unit arranged outside the billet bundling production line; The strong magnetic alignment unit is used to adjust the magnetic field strength and action time of the strong magnetic alignment unit according to the instructions of the PLC control unit, and control the alignment unit to align the steel billet bundle; The weighing unit is used to measure the weight of the steel billet bundle in real time and transmit the weight data to the PLC control unit; The PLC control unit is used to receive the weight data measured by the weighing unit in real time, and input the weight data into the trained prediction model to obtain the predicted cutting parameters, which include the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length and the number of cutting times; The hydraulic scissor control unit is used to shear the billet bundle according to the predicted shearing parameters; The bundling unit is used for bundling the sheared steel billets.

[0024] By utilizing automated control and intelligent decision-making, human intervention and waiting time can be reduced, and production efficiency and output can be improved. The initial position of the scissors, moving speed, cutting time, target bundle weight before the next cut, cutting length, and number of cuts can be accurately controlled to ensure that the weight and quality of the steel billet after shearing meet the standards, thereby improving the product qualification rate. In addition, the cost increase caused by errors and waste in the production process can be reduced, while the dependence on manual labor can be reduced, further reducing production costs.

[0025] The strong magnetic alignment unit includes a baffle installed at the end of the billet bundling production line, a transmission mechanism installed on the baffle facing the billet bundling production line, an electromagnet installed on the other side of the baffle, and a strong magnetic controller connected to the electromagnet. The electromagnet generates a magnetic field, combined with the drive of the transmission mechanism, to achieve precise alignment of the billets. The strong magnetic controller can adjust the magnetic field strength and action time according to the PLC instructions, further optimize the alignment effect, and improve the automation and response speed of the system.

[0026] The strong magnetic controller is used to adjust the magnetic field strength and action time of the electromagnet according to the instructions of the PLC control unit; thereby ensuring the stable alignment of the billet, preventing springback, and improving the accuracy and efficiency of the alignment.

[0027] Among them, the four parameters of the initial position of the scissors, the moving speed, the cutting time and the target bale weight value before the next cutting are determined as the cutting strategy; and the two parameters of the cutting length and the number of cutting times are used as the bale weight control parameters.

[0028] By precisely controlling the parameters in the shearing strategy, the stability and accuracy of the shearing process can be ensured, and shearing errors and waste can be reduced. At the same time, shearing according to the target bundle weight value helps to achieve standardized production of products and improve product quality and consistency. In addition, by reasonably controlling the shearing length and number of times, it can be ensured that the weight of the billet bundle meets the preset standard, reducing quality problems caused by insufficient or excessive weight. At the same time, optimizing the number of shears also helps to improve production efficiency and reduce costs.

[0029] The training of the prediction model includes: Construct a sample training set, including the standard weight value of each bundle of steel, the time value of each cutting, the alignment accuracy value, the length of a single steel bar, the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length, and the number of cutting times; Design a recurrent neural network model and build a recurrent neural network model. The deep neural network model includes an input layer, an output layer, and several hidden layers. Each layer contains multiple neurons. The weights, biases, and activation functions stored in these neurons jointly construct and define the mapping relationship from the feature variables of the input layer to the output results; its mathematical description is: , in the above formula, y j (k) represents the output of the jth neuron in layer k, m k-1 is the number of neurons in the previous layer, is the weight of the previous layer connected to the i-th neuron in this layer, b k-1 is the bias of the previous layer; Its input is the above numerical data, and its output is the initial position of the scissors, the moving speed of the scissors, the cutting time, the target bundle weight value before the next cutting, the cutting length and the number of cutting times; The neural network model is trained using the constructed sample training set, and the trained prediction model is output.

[0030] By collecting actual production data to build a sample training set and using a recurrent neural network model for training, we can learn the inherent laws and trends in the production process. This data-driven approach improves the accuracy and reliability of the prediction model and provides strong support for subsequent shearing strategies and bale weight control.

[0031] It should be noted here that in actual applications, when using the recurrent neural network model described above, the only input parameter is the weight data measured in real time by the weighing scale, and this weight data represents the standard weight value of each bundle of steel used in model training.

[0032] In addition, since the model is trained using a dataset containing multiple features (such as the standard weight of each bundle of steel, cutting time, alignment accuracy, and length of a single steel bar), while in actual applications only the actual weight of the steel may be provided, this single input needs to be properly processed or transformed (such as estimating missing feature values ​​by default filling in standard data) so that the model can understand and make predictions based on it.

[0033] In addition, if it is predicted that the current bundle weight is too large, the system will reduce the cutting length of each steel bar or increase the number of cutting times to reduce the bundle weight.

[0034] The PLC control unit includes: Data acquisition module, used to receive weight data in real time; The logic judgment module is used to determine the initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors based on the trained prediction model and the weight data received in real time. It is also used to predict the subsequent production trend. When it is predicted that the production status deviates from the preset target, the initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors are automatically adjusted. For example, if it is predicted that the weight of the next bundle of steel may be too large, the system may adjust the scissors position in advance and extend the cutting time to ensure that the bundle weight is controlled within the preset range; The command output module is used to send control commands to the hydraulic scissors control unit and the strong magnetic controller.

[0035] The data acquisition module receives weight data in real time to ensure the timeliness and accuracy of the data; the logic judgment module determines the optimal initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors based on the prediction model and real-time data, which improves the intelligent level of decision-making; the command output module sends the control command to the relevant execution unit to realize the closed-loop control of the system. This compact and fully functional PLC control unit improves the overall performance and reliability of the system.

[0036] The logic judgment module is also used to continuously optimize the control strategy based on historical production data and real-time feedback, and provide real-time production status and data diagnosis reports to production managers.

[0037] By continuously learning and optimizing control strategies, the adaptive learning module can further improve the intelligence and adaptability of the system. At the same time, it provides real-time production status and data diagnosis reports to production managers, which helps to timely discover and solve problems in the production process and improve the efficiency and level of production management.

[0038] In addition, the system also includes a remote monitoring and fault diagnosis unit, which is used to monitor the video and production data of the production site in real time and detect anomalies in the production data. If an anomaly is detected, the fault type is identified, the cause of the fault is analyzed, and suggestions for troubleshooting are given. Through remote monitoring and fault diagnosis functions, safety hazards and fault problems at the production site can be discovered and handled in a timely manner to ensure production safety. Once abnormal data or signs of a fault are detected, the remote monitoring and fault diagnosis unit can immediately start the fault diagnosis process, identify the fault type, analyze the cause of the fault, and give suggestions for handling. This rapid fault response and diagnosis mechanism helps reduce maintenance costs and time and improve equipment reliability and availability.

[0039] It should be noted here that remote monitoring is not limited to video monitoring, which is mainly used to observe the situation on the production site, but also includes real-time monitoring of production data, such as the real-time coordinates of the scissors, the temperature of the steel, the magnetic force of the strong magnetic baffle, etc. The data are transmitted to the remote monitoring center through the network for real-time display and analysis.

[0040] The remote monitoring and fault diagnosis unit is also used to transmit the real-time video and production data of the production site to the remote monitoring center through network transmission. The real-time video and production data of the production site are transmitted to the remote monitoring center through network transmission, realizing remote monitoring and management. This remote monitoring method helps production managers to grasp the production status in real time, make decisions and adjustments in time, and improve the efficiency and level of production management.

[0041] In this embodiment, data anomaly detection: First, the system performs anomaly detection on the collected production data to identify data points that are inconsistent with the normal state.

[0042] Fault type identification: Based on the characteristics of abnormal data and historical experience, the system will try to identify the specific fault type (such as equipment failure, operational error, etc.).

[0043] Fault cause analysis: By further analyzing abnormal data and equipment status information, the system will infer the cause of the fault.

[0044] Troubleshooting suggestions: Based on the analysis results of the fault cause, the system will give corresponding fault handling suggestions or automatically execute preset fault recovery operations.

[0045] In addition, the logic of fault diagnosis is mainly based on data analysis and historical databases. The system identifies and diagnoses abnormal conditions in the production process by comparing real-time data with historical data under normal conditions. At the same time, the system will continue to learn and optimize the diagnostic logic to improve the accuracy and efficiency of fault diagnosis.

[0046] On the other hand, according to the same technical concept as the above embodiment, the present invention provides a control method for adjusting the weight of a bundle of threaded steel bars, comprising the following steps: The current weight data of the steel billet bundle is collected in real time through the weighing scale, and the current weight data is directly transmitted to the data acquisition module of the PLC control unit; The logic judgment module calculates the optimal initial position of the scissors, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times based on the trained prediction model and weight data; According to the output results of the logic judgment module, specific control instructions are generated, including precise movement instructions and cutting operation instructions of the scissors, and the generated control instructions are sent to the hydraulic scissors control unit in real time; During the production process, the production status is continuously monitored, including but not limited to the conveying speed, alignment accuracy, and cutting efficiency of the steel billets. When the production status is detected to deviate from the preset target, the logic judgment module automatically triggers the internal parameter adjustment mechanism. According to the output results of the prediction model and real-time data feedback, the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length, and the number of cutting times are fine-tuned; The receiving remote monitoring and fault diagnosis unit collects real-time video and production data from the production site and transmits them to the remote monitoring center. The remote monitoring center uses video monitoring and data analysis software to display and analyze production data in real time. Once abnormal data or signs of fault are found, the fault diagnosis process is immediately started; The fault diagnosis process includes fault type identification, fault cause analysis and fault handling suggestion generation.

[0047] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A control system for adjusting the bundle weight of threaded steel, characterized in that: include: A strong magnetic alignment unit, a weighing unit, a bundling unit and a hydraulic scissor control unit are sequentially arranged on the billet bundling production line, and also includes a PLC control unit arranged outside the billet bundling production line; The strong magnetic alignment unit is used to adjust the magnetic field strength and action time of the strong magnetic alignment unit according to the instructions of the PLC control unit, and control the alignment unit to align the steel billet bundle; The weighing unit is used to measure the weight of the billet bundle in real time and transmit the weight data to the PLC control unit; The PLC control unit is used to receive the weight data measured by the weighing unit in real time, and input the weight data into the trained prediction model to obtain the predicted cutting parameters, which include the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length and the number of cutting times; The hydraulic scissor control unit is used to shear the billet bundle according to the predicted shearing parameters; The bundling unit is used for bundling the sheared steel billets.

2. A control system for adjusting the bundle weight of threaded steel bars according to claim 1, characterized in that: The strong magnetic alignment unit includes a baffle arranged at the end of the billet bundling production line, a conveying mechanism arranged on the baffle facing the billet bundling production line, an electromagnet arranged on the other side of the baffle, and a strong magnetic controller connected to the electromagnet.

3. A control system for adjusting the bundle weight of threaded steel bars according to claim 2, characterized in that: The strong magnetic controller is used to adjust the magnetic field strength and action time of the electromagnet according to the instructions of the PLC control unit.

4. A control system for adjusting the bundle weight of threaded steel bars according to claim 1, characterized in that: The training of the prediction model includes: Construct a sample training set, including the standard weight value of each bundle of steel, the time value of each cutting, the alignment accuracy value, the length of a single steel bar, the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length, and the number of cutting times; Construct a recurrent neural network model. The deep neural network model includes an input layer, an output layer, and several hidden layers. Each layer contains multiple neurons. The weights, biases, and activation functions stored in these neurons jointly construct and define the mapping relationship from the feature variables of the input layer to the output results; its mathematical description is: , in the above formula, y j (k) represents the output of the jth neuron in layer k, m k-1 is the number of neurons in the previous layer, is the weight of the previous layer connected to the i-th neuron in this layer, b k-1 is the bias of the previous layer; The neural network model is trained using the constructed sample training set, and the trained prediction model is output.

5. A control system for adjusting the bundle weight of threaded steel bars according to claim 3, characterized in that: The PLC control unit comprises: Data acquisition module, used to receive weight data in real time; The logic judgment module is used to determine the initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors according to the trained prediction model and the real-time received weight data. It is also used to predict the subsequent production trend. When it is predicted that the production status deviates from the preset target, the initial position, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and cutting times of the scissors are automatically adjusted. The command output module is used to send control commands to the hydraulic scissors control unit and the strong magnetic controller.

6. A control system for adjusting bundle weight of threaded steel bars according to claim 1, characterized in that: The logic judgment module is also used to continuously optimize the control strategy based on historical production data and real-time feedback, and provide real-time production status and data diagnosis reports.

7. A control system for adjusting bundle weight of threaded steel bars according to claim 1, characterized in that: It also includes a remote monitoring and fault diagnosis unit, which is used to monitor the video and production data of the production site in real time and detect anomalies in the production data. If an anomaly is detected, the fault type is identified, the cause of the fault is analyzed, and fault handling suggestions are given.

8. A control system for adjusting the bundle weight of threaded steel bars according to claim 7, characterized in that: The remote monitoring and fault diagnosis unit is also used to transmit the real-time video and production data of the production site to the remote monitoring center via network transmission.

9. A control method for adjusting the weight of a rebar bundle control system, characterized in that: The following steps are involved: The current weight data of the steel billet bundle is collected in real time through the weighing scale, and the current weight data is directly transmitted to the data acquisition module of the PLC control unit; Based on the trained prediction model and weight data, the logic judgment module calculates the optimal initial position of the scissors, moving speed, cutting time, target bundle weight value before the next cutting, cutting length and number of cutting times; According to the output results of the logic judgment module, specific control instructions are generated, including precise movement instructions and cutting operation instructions of the scissors, and the generated control instructions are sent to the hydraulic scissors control unit in real time; During the production process, the production status is continuously monitored, including but not limited to the conveying speed, alignment accuracy, and cutting efficiency of the steel billets. When the production status is detected to deviate from the preset target, the logic judgment module automatically triggers the internal parameter adjustment mechanism. According to the output results of the prediction model and real-time data feedback, the initial position of the scissors, the moving speed, the cutting time, the target bundle weight value before the next cutting, the cutting length, and the number of cutting times are fine-tuned; The receiving remote monitoring and fault diagnosis unit collects real-time video and production data from the production site and transmits them to the remote monitoring center. The remote monitoring center uses video monitoring and data analysis software to display and analyze production data in real time. Once abnormal data or signs of fault are found, the fault diagnosis process is immediately started; The fault diagnosis process includes fault type identification, fault cause analysis and fault handling suggestion generation.

Images